profit/lakehouse
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

merge into: profit:scrum/auto-apply-19814
Branches Tags
profit:main
profit:demo/post-pr11-polish-2026-04-28
profit:infra/replace-gpt-oss-2026-04-28
profit:scrum/auto-apply-19814
profit:scrum/iter5-prep-2026-04-24
profit:test/enrich-prd-pipeline
profit:cohesion/python-inventory-and-integration
profit:phase/45-slice-4
profit:phase/45-slice-3
profit:ops/auditor-systemd-units
profit:fix/upsert-outcome-update-merge
profit:auditor/scaffold
profit:fix/upsert-outcome-serde
profit:demo-latest
profit:distillation-v1.0.0
profit:v0.26-memory-complete
...
pull from: profit:main
Branches Tags
profit:demo/post-pr11-polish-2026-04-28
profit:main
profit:infra/replace-gpt-oss-2026-04-28
profit:scrum/auto-apply-19814
profit:scrum/iter5-prep-2026-04-24
profit:test/enrich-prd-pipeline
profit:cohesion/python-inventory-and-integration
profit:phase/45-slice-4
profit:phase/45-slice-3
profit:ops/auditor-systemd-units
profit:fix/upsert-outcome-update-merge
profit:auditor/scaffold
profit:fix/upsert-outcome-serde
profit:demo-latest
profit:distillation-v1.0.0
profit:v0.26-memory-complete

48 Commits
scrum/auto ... main

Author SHA1 Message Date
profit
a5d9070c9c Merge pull request 'Post-PR-#11 polish: demo UI, staffer console, face pool, icons, contractor profile (24 commits)' (#12) from demo/post-pr11-polish-2026-04-28 into main 2026-05-03 05:16:15 +00:00
root
e9d17f7d5a sanitize: drop over-broad path-missing branch + UTF-8-safe redaction 
Re-scrum of yesterday's sanitizer fix surfaced 2 more real bugs in the
fix itself (opus, both WARN, neither caught by kimi/qwen):

W1 (service.rs:1949) — `mentions_path_missing` standalone branch was
too aggressive. A registry-internal error like "/root/.cargo/.../x.rs:
no such file or directory" would 404 because it triggers without
dataset context. That's a real 500. Dropped the standalone branch;
require dataset context AND missing-shape phrase. Lance's actual
"Dataset at path X was not found" still satisfies it.

W2 (service.rs:2018) — `out.push(bytes[i] as char)` corrupted
multi-byte UTF-8 by casting raw bytes to char (only sound for ASCII
< 128). A path containing user-supplied non-ASCII names produced
Latin-1 mojibake. Rewrote redact_paths to track byte indices and
emit unmatched runs as &str slices via push_str(&s[range]) — preserves
multi-byte sequences verbatim. Step advance is now per-char, not
per-byte, via small utf8_char_len helper.

Two new regression tests:
- is_not_found_does_not_match_unrelated_path_missing
- redact_preserves_multibyte_utf8 (uses 工作 + café in input)

12/12 sanitize tests PASS. Smoke 10/10 PASS. Loop closure for opus
re-scrum on the 2026-05-02 fix bundle.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-03 00:15:23 -05:00
root
ac7c996596 sweep up scrum WARNs — model const, stale config, temp_path entropy, smoke gate 
Four findings deferred from the 2026-05-02 scrum, all 1-5 line fixes:

W1 (kimi WARN @ scrum_master_pipeline.ts:1143) — `gemini-3-flash-preview`
hardcoded twice in MAP and REDUCE phases. Extracted TREE_SPLIT_MODEL +
TREE_SPLIT_PROVIDER constants near the existing config block. Diverging
the two would break tree-split coherence (per-shard digests must come
from the same model the reducer collapses).

W2 (qwen WARN @ providers.toml:30) — stale `kimi-k2:1t` reference in
operator-facing comments after PR #13 noted it's upstream-broken. Reframed
as historical context ("was X here pre-2026-05-03 — that model is broken")
so future operators don't paste-route from the comment.

W3 (opus WARN @ vectord-lance/src/lib.rs:622) — temp_path() entropy was
only pid+nanos, which collide under tokio scheduling when multiple tests
in the same cargo process create temp dirs back-to-back. Added per-process
AtomicU64 sequence counter — guarantees uniqueness regardless of clock.

W4 (opus INFO @ scripts/lance_smoke.sh:38) — `|| echo '{}'` swallowed
curl transport failures (gateway down, network broken, timeout), surfacing
as misleading "no method field" jq errors at the next probe. Now captures
$? separately, gates a "curl reachable" probe, and only falls back to
empty body for the dependent jq parse. Smoke went 9 → 10 probes.

Verified: vectord-lance 7/7 tests PASS, gateway cargo check clean,
lance_smoke.sh 10/10 PASS against live gateway.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-03 00:11:59 -05:00
root
7bb66f08c3 lance: scrum-driven sanitizer + smoke-gate fixes (opus 2026-05-02 BLOCK)
Some checks failed
lakehouse/auditor 9 blocking issues: cloud: claim not backed — "Verified live (post-restart): scale_test_10m doc-fetch 4-15ms across"
Cross-lineage scrum on the lance wave (4 bundles, 33 distinct findings)
surfaced 1 real BLOCK and 2 real WARNs from opus that the kimi/qwen
lineages missed. Per feedback_cross_lineage_review.md, opus is the
load-bearing reviewer; cross-lineage convergence is noise unless verified.

BLOCK fix — sanitize_lance_err path-stripping was unsound:
  err.split("/home/").next().unwrap_or(&err)
returns Some("") when err STARTS with "/home/", erasing the entire
message. Replaced truncation with redact_paths() — a hand-rolled scanner
that walks the input once, replacing path-shaped substrings with
[REDACTED] while preserving surrounding error context. Catches:
- absolute paths under /root/.cargo, /home, /var, /tmp, /etc, /usr, /opt
- relative variants (Lance occasionally strips leading slash —
  observed live "Dataset at path home/profit/lakehouse/data/lance/x
  was not found")
- multiple occurrences in one error
- preserves quote/comma/whitespace terminators

WARN fix #1 — is_not_found heuristic was too broad:
  lower.contains("not found")
caught real 500s like "column not found", "field not found in schema".
Narrowed to require dataset-shape phrasing AND exclude the
column/field/schema patterns explicitly.

WARN fix #2 — lance_smoke.sh `grep -qvE` was an unsound regression gate.
  bash -c "echo '$BODY' | grep -qvE 'pat'"
With -v -q, exits 0 if ANY line lacks the pattern — so a multi-line
body with one leak line + any clean line FALSE-PASSES. Replaced with
the correct "pattern absent" form: `! grep -qE 'pat'`. Also expanded
the pattern set (added /var/, /tmp/) since the scrum surfaced these
as additional leak vectors.

Also unblocks pre-existing pathway_memory test compile error (stale
PathwayTrace init missing 6 Mem0-versioning fields added in 6ac7f61).
Tests filled in with sensible defaults — needed to run sanitize_tests.

10/10 new sanitize tests pass. Smoke 9/9 PASS against rebuilt+restarted
gateway. Live missing-index probe now returns:
  "lance dataset not found: no-such-11205" + HTTP 404
(was: leaked absolute paths + HTTP 500 → leaked absolute and relative
paths post-first-fix → clean message + 404 now.)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 23:34:54 -05:00
root
a294a61ee4 Merge remote-tracking branch 'origin/main' into demo/post-pr11-polish-2026-04-28
Some checks failed
lakehouse/auditor 9 blocking issues: cloud: claim not backed — "Verified live (post-restart): scale_test_10m doc-fetch 4-15ms across"
 2026-05-02 22:40:03 -05:00
profit
feb638e4cd infra: replace gpt-oss with Ollama Pro + OpenCode Zen across hot paths (#13) 
7 hot-path call sites swapped to Ollama Pro / OpenCode Zen models. All replacements live-probed. Auditor surfaced 2 kimi BLOCKs both verified false-positive on 2026-05-02. Compiles cleanly in isolation.
 2026-05-03 03:39:52 +00:00
root
0af62861d2 STATE_OF_PLAY: refresh for 2026-05-02 wave (Lance gauntlet + parity + housekeeping)
Some checks failed
lakehouse/auditor 9 blocking issues: cloud: claim not backed — "Verified end-to-end via playwright on devop.live/lakehouse:"
Anchor was 5 days stale. Adds the 12-commit wave (Lance backend hardening,
sidecar drop, observability parity, gitignore cleanup, gray-zone content
add) with verification status for each. Updates DO NOT RELITIGATE with
the 4 new things this wave makes load-bearing:
- python sidecar dropped from hot path (don't wire it back)
- lance gauntlet shipped (don't re-discover the bugs we just fixed)
- 32/32 cross-runtime parity (don't build a 6th probe for already-covered surface)
- ARCHITECTURE_COMPARISON.md is the single source of truth for cross-runtime decisions

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 22:23:36 -05:00
root
41b0a99ed2 chore: add real content that was sitting untracked 
Surfaced by today's untracked-files audit. None of these are accidents —
multiple are referenced by name in CLAUDE.md and memory files but were
never added.

Categories:
- docs/PHASE_AUDIT_GUIDE.md (106 LOC) — Claude Code phase audit guidance
- ops/systemd/lakehouse-langfuse-bridge.service — Langfuse bridge unit
- package.json — top-level npm manifest
- scripts/e2e_pipeline_check.sh + production_smoke.sh — real test scripts
- reports/kimi/audit-last-week*.md — the "Two reports live" CLAUDE.md cites
- tests/multi-agent/scenarios/ — 44 staffing scenarios (cutover decision A)
- tests/multi-agent/playbooks/ — 102 playbook records
- tests/battery/, tests/agent_test/PRD.md, tests/real-world/* — real tests
- sidecar/sidecar/{lab_ui,pipeline_lab}.py — 888 LOC dev-only UIs that
  remain in service post-sidecar-drop (commit ba928b1 explicitly kept them)

Sensitivity check: scenarios use synthetic company names ("Heritage Foods",
"Cornerstone Fabrication"); audit reports describe code findings only;
no PII or secrets surfaced.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 22:22:10 -05:00
root
6e34ef7baf gitignore: stop tracking runtime data, logs, build artifacts, scratch 
Untracked count was 100+; almost all were data/_*/ daemon state, generated
parquets under data/datasets and data/vectors, the 33GB data/lance/ tree,
node_modules, exports, logs, per-run distillation reports, and test
scratchpads. None of these are content — all regenerate from inputs.

Now down to 33 untracked items, all real content (scripts, systemd unit,
test scenarios, dev-only sidecar UIs, kimi audit reports). Those need
J's call on what to track vs leave parked.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 22:20:14 -05:00
root
044650a1da lance-bench: also build doc_id btree post-IVF — match gateway's migrate behavior 
The bench's own measure_random_access_lance uses take(row_position) —
doesn't need the btree. But datasets written by this bench are commonly
queried via /vectors/lance/doc/<name>/<doc_id> downstream, and without
the btree that path falls back to a full table scan. Building inline
keeps bench-produced datasets immediately production-shape and removes
a footgun (the same one that made scale_test_10m's doc-fetch ~100ms
until commit 5d30b3d fixed it via the migrate handler path).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 22:19:16 -05:00
root
5d30b3da89 lance: auto-build doc_id btree in migrate handler (root-cause for 10M doc-fetch slowness) 
scale_test_10m doc-fetch p50 was ~100ms — full table scan over 35GB. Root
cause: the auto-build at service.rs:1492-1503 only fires for IndexMeta-
registered indexes during set_active_profile warming. lance-bench writes
datasets through /vectors/lance/migrate/* directly, bypassing IndexMeta,
so its datasets never get the doc_id btree that ADR-019 depends on.

Fix: build the btree inline at the end of lance_migrate. Costs ~1.2s on
10M rows (+269MB on disk), drops doc-fetch from ~100ms to ~5ms (20x).
Failure is non-fatal — logs a warning and the dataset stays queryable.

Verified live (post-restart): scale_test_10m doc-fetch 4-15ms across
5 calls, smoke 9/9 PASS, vectord-lance 7/7 unit tests PASS.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 21:38:00 -05:00
root
7594725c25 lance backend: 4-pack — bug fix + smoke + tests + 10M re-bench
Some checks failed
lakehouse/auditor 12 blocking issues: cloud: claim not backed — "Verified end-to-end against persistent Go stack on :4110:"
Surfaced by the 2026-05-02 audit (vectord-lance + lance-bench + glue
existed and worked but had no tests, no smoke, leaked server paths
on missing-index search, and the ADR-019 10M re-bench was deferred).

## 1. Fix: missing-index search returned 500 + leaked filesystem path

Pre-fix:
  $ POST /vectors/lance/search/no-such-index
  HTTP 500
  Dataset at path home/profit/lakehouse/data/lance/no-such-index was
  not found: Not found: home/profit/lakehouse/data/lance/no-such-index/
  _versions, /root/.cargo/registry/src/index.crates.io-...-1949cf8c.../
  lance-table-4.0.0/src/io/commit.rs:364:26, ...

Post-fix:
  HTTP 404
  lance dataset not found: no-such-index

Added `sanitize_lance_err()` in crates/vectord/src/service.rs that:
  - maps "not found" / "no such file" patterns → 404 (was 500)
  - strips /home/ and /root/.cargo/ paths from any error body
Applied to all 5 lance handlers: search, get_doc, build_index,
append, migrate. The store_for() handle is cheap-and-stateless;
the actual disk hit happens inside the operation, which is where
the leak originated.

## 2. scripts/lance_smoke.sh — first regression gate

9-probe smoke against the live HTTP surface. Exercises only read
paths (no state mutation in CI). Specifically locks the sanitizer
fix — a future regression that re-introduces the path leak fires
the smoke immediately. 9/9 PASS against the live :3100 today.

## 3. Unit tests on vectord-lance/src/lib.rs (was: zero tests)

7 tests covering the public LanceVectorStore API:
  - fresh_store_reports_no_state — handle is lazy
  - migrate_then_count_and_fetch — Parquet → Lance round-trip
  - get_by_doc_id_missing_returns_none — Ok(None) vs Err contract
    that lets the HTTP handler return 404 cleanly
  - append_grows_count_and_new_rows_fetchable — ADR-019's
    structural-difference claim verified at the unit level
  - append_dim_mismatch_errors — guards against silently breaking
    search by accepting inconsistent-dim rows
  - search_returns_nearest — exact-vector match → top-1
  - stats_reports_post_migrate_state — locks the field shape

7/7 PASS. cargo test -p vectord-lance --lib green.

## 4. 10M re-bench (deferred from ADR-019)

reports/lance_10m_rebench_2026-05-02.md captures the numbers driven
against the live :3100 over data/lance/scale_test_10m (33GB / 10M
vectors, IVF_PQ confirmed via response method tag).

Headline:
  Search cold (10 diverse queries):   median ~32ms, mean ~46ms
  Search warm (5x same query):        ~20ms p50
  Doc fetch (5x same id):             ~100ms p50

Search latency at 10M is acceptable for batch / async workloads,
too slow for sub-10ms voice/recommendation paths. ADR-019's "Lance
pulls ahead at 10M" claim remains unverified-but-not-refuted — at
this scale HNSW doesn't operationally exist (10M × 768d × 4 bytes =
30GB just for vectors).

Real finding: doc-fetch at 10M is 300x slower than the 100K number
ADR-019 cited (311μs → ~100ms). Likely cause: scalar btree index
on doc_id may not be built for this dataset. Follow-up to
investigate whether forcing build_scalar_index brings it back to
the load-bearing O(1) range. Captured in the report.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 20:06:56 -05:00
root
98b6647f2a gateway: IterateResponse echoes trace_id + enable session_log_path
Some checks failed
lakehouse/auditor 14 blocking issues: cloud: claim not backed — "Verified end-to-end against persistent Go stack on :4110:"
Closes the 2026-05-02 cross-runtime parity gap: Go's
validator.IterateResponse carried trace_id back to callers; Rust's
didn't. A caller pivoting from response → Langfuse → session log
worked on Go but failed on Rust because the join key wasn't visible
in the response body.

## Changes

crates/gateway/src/v1/iterate.rs:
  - IterateResponse + IterateFailure gain `trace_id: Option<String>`
    (skip-serializing-if-none preserves backward-compat for any
    consumer parsing the response without the field)
  - Both return sites populated with the resolved trace_id

lakehouse.toml:
  - [gateway].session_log_path set to /tmp/lakehouse-validator/sessions.jsonl
    — same path Go validatord writes to. The two daemons now co-write
    one unified longitudinal log; rows tag daemon="gateway" vs
    daemon="validatord" so producers stay distinguishable in DuckDB
    queries. Append-write is atomic at the row sizes both runtimes
    produce, so concurrent writes from both daemons are safe.

## Verification

Post-restart of lakehouse.service:
  POST /v1/iterate with X-Lakehouse-Trace-Id: rust-fix1-test
    → response.trace_id = "rust-fix1-test" ✓ (was: field absent)
    → sessions.jsonl latest row daemon=gateway, session_id=rust-fix1-test ✓ (was: no row)

Cross-runtime drive — same prompt to Rust :3100 and Go :4110:
  Rust:  trace_id=unified-rust-001, daemon=gateway, accepted
  Go:    trace_id=unified-go-001,   daemon=validatord, accepted
  Same file, distinct daemons, one query covers both:
    SELECT daemon, COUNT(*) FROM read_json_auto('sessions.jsonl', format='nd') GROUP BY daemon
    → gateway: 2, validatord: 19

All 4 parity probes still 6/6 + 12/12 + 4/4 + 2/2 against live
:3100 + :4110 stacks. Cargo test 4/4 PASS for v1::iterate module.

## Architecture invariant

The "unified longitudinal log" thesis is now demonstrated. Operators
running both runtimes in production point both daemons at the same
session_log_path and DuckDB queries naturally span both producers.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 06:24:41 -05:00
root
57bde63a06 gateway: trace-id propagation + coordinator session JSONL (Rust parity)
Some checks failed
lakehouse/auditor 10 blocking issues: cloud: claim not backed — "Verified end-to-end against persistent Go stack on :4110:"
Cross-runtime parity with the Go-side observability wave (commits
d6d2fdf + 1a3a82a in golangLAKEHOUSE). The two layers J flagged:
the LIVE per-call view (Langfuse) and the LONGITUDINAL forensic view
(JSONL queryable via DuckDB). Hard correctness gate (FillValidator
phantom-rejection) was already in place; this is the observability
on top.

## Trace-id propagation

X-Lakehouse-Trace-Id header constant declared in
crates/gateway/src/v1/iterate.rs (matches Go's shared.TraceIDHeader
byte-for-byte). When set on an inbound /v1/iterate request, the
handler reuses it; the chat + validate self-loopback hops forward
the same header so chatd's trace emit nests under the parent rather
than minting a fresh top-level trace per call.

ChatTrace gains a parent_trace_id field. emit_chat_inner skips the
trace-create event when parent is set, only emits the
generation-create which attaches to the existing trace tree. Result:
an iterate session with N retries shows in Langfuse as ONE tree, not
N+1 disconnected traces.

emit_attempt_span (new) writes one Langfuse span per iteration
attempt with input={iteration, model, provider, prompt} and
output={verdict, raw, error}. WARNING level on non-accepted
verdicts. The returned span id is stamped on the corresponding
SessionRecord attempt for cross-log correlation.

## Coordinator session JSONL

crates/gateway/src/v1/session_log.rs — new writer matching Go's
internal/validator/session_log.go schema byte-for-byte:
  - SessionRecord with schema=session.iterate.v1
  - SessionAttemptRecord per retry
  - SessionLogger.append: tokio Mutex serialized append-only
  - Best-effort posture (slog.Warn on error, never blocks request)

iterate.rs builds + appends a row on EVERY code path:
  - accepted: write_session_accepted with grounded_in_roster bool
    derived from validate_workers WorkerLookup (matches Go's
    handlers.rosterCheckFor("fill") semantics)
  - max-iter-exhausted: write_session_failure
  - infra-error: write_infra_error (so a missing /v1/iterate event
    never silently disappears from the longitudinal log)

[gateway].session_log_path config field (empty = disabled).
Production: /var/lib/lakehouse/gateway/sessions.jsonl. Operators who
want a unified longitudinal stream can point both Rust and Go
loggers at the same path — write-append is safe at the row sizes we
produce.

## Cross-runtime parity probe

crates/gateway/src/bin/parity_session_log: tiny stdin/stdout helper
that round-trips a fixture through SessionRecord serde.
golangLAKEHOUSE/scripts/cutover/parity/session_log_parity.sh feeds
4 fixtures through both helpers and diffs the rows after stripping
timestamp + daemon (the two fields that legitimately differ between
producers).

Result: **4/4 byte-equal** including the unicode-prompt fixture
("Café résumé ⭐ 你好"). Schema parity holds. The non-trivial-equal
guard in the probe rejects the case where both sides fail
identically — protecting against a regression where one side
silently stops producing valid JSON.

## Verification

- cargo test -p gateway --lib: 90/90 PASS (3 new session_log tests
  including concurrent-append safety)
- cargo check --workspace: clean
- session_log_parity.sh: 4/4 fixtures byte-equal
- Both runtimes can append to the same path; DuckDB sees one stream
- The Go-side validatord smoke remains 5/5 (unchanged)

## Architecture invariant

Don't propose to "wire trace-id propagation in Rust" or "add Rust
session log" — both are now shipped on the demo/post-pr11-polish
branch. The longitudinal log + Langfuse tree together cover the
multi-call observability concern J flagged 2026-05-02.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 05:39:29 -05:00
root
ba928b1d64 aibridge: drop Python sidecar from hot path; AiClient → direct Ollama
Some checks failed
lakehouse/auditor 11 blocking issues: cloud: claim not backed — "Verified end-to-end against persistent Go stack on :4110:"
The "drop Python sidecar from Rust aibridge" item from the
architecture_comparison decisions tracker. Universal-win cleanup —
removes 1 process + 1 runtime + 1 hop from every embed/generate
request, with no behavior change.

## What was on the hot path before

  gateway → AiClient → http://:3200 (FastAPI sidecar)
                          ├── embed.py    → http://:11434 (Ollama)
                          ├── generate.py → http://:11434
                          ├── rerank.py   → http://:11434 (loops generate)
                          └── admin.py    → http://:11434 (/api/ps + nvidia-smi)

The sidecar's hot-path code (~120 LOC across embed.py / generate.py /
rerank.py / admin.py) was pure pass-through: each route translated
its request body to Ollama's wire format and returned Ollama's
response in a sidecar envelope. Zero logic, one full HTTP hop of
overhead.

## What's on the hot path now

  gateway → AiClient → http://:11434 (Ollama directly)

Inline rewrites in crates/aibridge/src/client.rs:
- embed_uncached: per-text loop to /api/embed; computes dimension
  from response[0].length (matches the sidecar's prior shape)
- generate (direct path): translates GenerateRequest → /api/generate
  (model, prompt, stream:false, options:{temperature, num_predict},
  system, think); maps response → GenerateResponse using Ollama's
  field names (response, prompt_eval_count, eval_count)
- rerank: per-doc loop with the same score-prompt the sidecar used;
  parses leading number, clamps 0-10, sorts desc
- unload_model: /api/generate with prompt:"", keep_alive:0
- preload_model: /api/generate with prompt:" ", keep_alive:"5m",
  num_predict:1
- vram_snapshot: GET /api/ps + std::process::Command nvidia-smi;
  same envelope shape as the sidecar's /admin/vram so callers keep
  parsing
- health: GET /api/version, wrapped in a sidecar-shaped envelope
  ({status, ollama_url, ollama_version})

Public AiClient API is unchanged — Request/Response types untouched.
Callers (gateway routes, vectord, etc.) require zero updates.

## Config changes

- crates/shared/src/config.rs: default_sidecar_url() bumps to
  :11434. The TOML field stays `[sidecar].url` for migration compat
  (operators with existing configs don't need to rename anything).
- lakehouse.toml + config/providers.toml: bumped to localhost:11434
  with comments explaining the 2026-05-02 transition.

## What stays Python

sidecar/sidecar/lab_ui.py (385 LOC) + pipeline_lab.py (503 LOC) are
dev-mode Streamlit-shape UIs for prompt experimentation. Not on the
runtime hot path; continue running for ad-hoc work. The
embed/generate/rerank/admin routes inside sidecar can be retired,
but operators who want to keep the sidecar process running for the
lab UI face no breakage — those routes still call Ollama and work.

## Verification

- cargo check --workspace: clean
- cargo test -p aibridge --lib: 32/32 PASS
- Live smoke against test gateway on :3199 with new config:
    /ai/embed     → 768-dim vector for "forklift operator" ✓
    /v1/chat      → provider=ollama, model=qwen2.5:latest, content=OK ✓
- nvidia-smi parsing tested via std::process::Command path
- Live `lakehouse.service` (port :3100) NOT yet restarted — deploy
  step is operator-driven (sudo systemctl restart lakehouse.service)

## Architecture comparison update

(Captured separately in golangLAKEHOUSE/docs/ARCHITECTURE_COMPARISON.md
decisions tracker.) The "drop Python sidecar" line moves from _open_
to DONE. The Rust process model now has 1 mega-binary instead of
1 mega-binary + 1 sidecar process — a small but real reduction in
ops surface.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 04:59:47 -05:00
root
654797a429 gateway: pub extract_json + parity_extract_json bin (cross-runtime probe)
Some checks failed
lakehouse/auditor 10 blocking issues: cloud: claim not backed — "Verified end-to-end against persistent Go stack on :4110:"
Supports the 2026-05-02 cross-runtime parity probe at
golangLAKEHOUSE/scripts/cutover/parity/extract_json_parity.sh which
feeds identical model-output strings through both runtimes' extract_json
and diffs results.

## Changes
- crates/gateway/src/v1/iterate.rs: extract_json gains `pub` + a
  comment pointing at the Go counterpart and the parity probe path
- crates/gateway/src/lib.rs: NEW thin lib facade re-exporting the
  modules so sub-binaries can reuse them. main.rs is unchanged
  (still uses local mod declarations)
- crates/gateway/src/bin/parity_extract_json.rs: NEW ~30-LOC binary
  that reads stdin, calls extract_json, prints {matched, value} JSON

## Probe result (logged in golangLAKEHOUSE)
12/12 match across fenced blocks, nested objects, unicode, escaped
quotes, top-level array, malformed JSON. Both runtimes' algorithms
are genuinely equivalent.

Substrate gate the probe enforces: `cargo test -p gateway extract_json`
PASS before any parity comparison runs. So a future divergence in
the live extract_json fires either as a Rust test failure (live
behavior changed) or a probe diff (Go behavior changed) — never
silently.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-02 04:44:11 -05:00
root
c5654d417c docs: pointer to ARCHITECTURE_COMPARISON.md source in golangLAKEHOUSE
Some checks failed
lakehouse/auditor 18 blocking issues: cloud: claim not backed — "Verified end-to-end against persistent Go stack on :4110:"
Per J's request: the parallel-runtime comparison is a living source
file maintained at /home/profit/golangLAKEHOUSE/docs/ARCHITECTURE_COMPARISON.md.
This file is a pointer reachable from the Rust repo's docs/ so the
comparison is discoverable from either side.

Doesn't contain authoritative content — just the link + a quick
status summary + update guidance ('source lives in golangLAKEHOUSE,
don't drift two copies').
 2026-05-01 04:57:09 -05:00
root
150cc3b681 aibridge: LRU embed cache - 236x RPS gain on warm workloads. Per architecture_comparison.md universal-win for Rust side. Cache key (model,text), default 4096 entries, in-process inside gateway. Load test: 128 RPS -> 30k+ RPS, p50 78ms -> 129us.
Some checks failed
lakehouse/auditor 20 blocking issues: cloud: claim not backed — "Verified end-to-end against persistent Go stack on :4110:"
 2026-05-01 04:45:20 -05:00
root
9eed982f1a mcp-server: /_go/* pass-through for G5 cutover slice 
Adds an opt-in pass-through that routes Bun mcp-server requests
to the Go gateway when GO_LAKEHOUSE_URL is set. /_go/v1/embed,
/_go/v1/matrix/search etc. flow through Bun frontend → Go
backend without touching any existing tool. Off-by-default
(empty GO_LAKEHOUSE_URL → 503 with rationale); enabled via
systemd drop-in at:
  /etc/systemd/system/lakehouse-agent.service.d/go-cutover.conf

This is the first slice of real Bun-fronted traffic hitting the
Go substrate. The /api/* pass-through (Rust gateway) and every
existing tool are unmodified — fully additive cutover step.

Reversible: unset GO_LAKEHOUSE_URL or remove the systemd drop-in
and restart lakehouse-agent.service.

Verified end-to-end against persistent Go stack on :4110:
  /_go/health → {"status":"ok","service":"gateway"}
  /_go/v1/embed → nomic-embed-text-v2-moe vectors (dim=768)
  /_go/v1/matrix/search → 3/3 Forklift Operators (role+geo match)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-01 03:44:10 -05:00
root
3d068681f5 distillation: regenerated acceptance + audit reports (run_hash refresh)
Some checks failed
lakehouse/auditor 17 blocking issues: cloud: claim not backed — "Verified end-to-end via playwright on devop.live/lakehouse:"
Phase 6 acceptance + Phase 8 full-audit reports re-run; bit-for-bit
reproducibility property still holds (run 1 hash == run 2 hash),
just at a new value.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-30 00:13:17 -05:00
root
8de94eba08 cleanup: bump qwen2.5 → qwen3.5:latest in active defaults
Some checks failed
lakehouse/auditor 16 blocking issues: cloud: claim not backed — "Verified end-to-end via playwright on devop.live/lakehouse:"
stronger local rung is now the small-model-pipeline tier-1 default
across both Rust legacy + Go rewrite (cf. golangLAKEHOUSE phase 1).
same JSON-clean property as qwen2.5, more capacity. ollama still
serves both side-by-side; rollback is a 4-line revert if a workload
regresses.

active-default sites:
- lakehouse.toml [ai] gen_model + rerank_model → qwen3.5:latest
- mcp-server/observer.ts diagnose call (Phase 44 /v1/chat path) → qwen3.5:latest
- mcp-server/index.ts model roster doc → qwen3.5:latest first
- crates/vectord/src/rag.rs ContinuableOpts + RagResponse.model → qwen3.5:latest

skipped: execution_loop/mod.rs comments describing historic qwen2.5
tool_call quirks — those are documentation of past behavior, not
active defaults. data/_catalog/profiles/*.json are runtime-generated
(gitignored), not in scope for tracked changes.

cargo check -p vectord: clean. no behavioral change in the audit
pipeline — same JSON-clean local model, same think=Some(false)
posture, just stronger upstream.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-30 00:10:57 -05:00
root
a00e9bb438 infra: replace gpt-oss with Ollama Pro + OpenCode Zen across hot paths
Some checks failed
lakehouse/auditor 2 blocking issues: State field rename likely incomplete — `opencode_key` may not exist on `self.state`
Ollama Pro plan went live today (39-model fleet on the same
OLLAMA_CLOUD_KEY) and OpenCode Zen was already wired in the gateway
but not consumed. Routing every gpt-oss call site to faster /
stronger replacements:

| Site | gpt-oss → replacement | Why |
|---|---|---|
| ollama_cloud default | gpt-oss:120b → deepseek-v3.2 | newest DeepSeek revision; live-probed `pong` |
| openrouter default | openai/gpt-oss-120b:free → x-ai/grok-4.1-fast | already the scrum LADDER's PRIMARY |
| modes.toml staffing_inference | openai/gpt-oss-120b:free → kimi-k2.6 | coding-specialized, on Ollama Pro |
| modes.toml doc_drift_check | gpt-oss:120b → gemini-3-flash-preview | speed leader for factual checks |
| scrum_master_pipeline tree-split MAP+REDUCE | gpt-oss:120b → gemini-3-flash-preview | latency-dominated path (5-20× per file) |
| bot/propose.ts CLOUD_MODEL | gpt-oss:120b → deepseek-v3.2 | same Ollama key, faster |
| mcp-server/observer.ts overseer label fallback | gpt-oss:120b → claude-opus-4-7 | matches new overseer model |
| crates/gateway/src/execution_loop overseer escalation | ollama_cloud/gpt-oss:120b → opencode/claude-opus-4-7 | frontier reasoning matters here — fires only after local self-correct fails twice; Zen pay-per-token cost is bounded |

Verification:
- `cargo check -p gateway --tests` — clean
- Live probes through localhost:3100/v1/chat:
  - `opencode/claude-opus-4-7` → "pong"
  - `gemini-3-flash-preview` (ollama_cloud) → "pong"
  - `kimi-k2.6` (ollama_cloud) → "pong"
  - `deepseek-v3.2` (ollama_cloud) → "Pong! 🏓"

Notes:
- kimi-k2:1t still upstream-broken (HTTP 500 on Ollama Pro probe today,
  matches yesterday's memory). Replacement table never picks it.
- The Rust changes need a `systemctl restart lakehouse.service` to
  take effect on the running gateway. TS callers reload on next run.
- aibridge/src/context.rs still has gpt-oss:{20b,120b} in its window-
  size lookup table; harmless and kept for callers that pass it
  explicitly as an override.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-28 06:13:48 -05:00
root
d475fc7fff infra: replace gpt-oss with Ollama Pro + OpenCode Zen across hot paths 
Ollama Pro plan went live today (39-model fleet on the same
OLLAMA_CLOUD_KEY) and OpenCode Zen was already wired in the gateway
but not consumed. Routing every gpt-oss call site to faster /
stronger replacements:

| Site | gpt-oss → replacement | Why |
|---|---|---|
| ollama_cloud default | gpt-oss:120b → deepseek-v3.2 | newest DeepSeek revision; live-probed `pong` |
| openrouter default | openai/gpt-oss-120b:free → x-ai/grok-4.1-fast | already the scrum LADDER's PRIMARY |
| modes.toml staffing_inference | openai/gpt-oss-120b:free → kimi-k2.6 | coding-specialized, on Ollama Pro |
| modes.toml doc_drift_check | gpt-oss:120b → gemini-3-flash-preview | speed leader for factual checks |
| scrum_master_pipeline tree-split MAP+REDUCE | gpt-oss:120b → gemini-3-flash-preview | latency-dominated path (5-20× per file) |
| bot/propose.ts CLOUD_MODEL | gpt-oss:120b → deepseek-v3.2 | same Ollama key, faster |
| mcp-server/observer.ts overseer label fallback | gpt-oss:120b → claude-opus-4-7 | matches new overseer model |
| crates/gateway/src/execution_loop overseer escalation | ollama_cloud/gpt-oss:120b → opencode/claude-opus-4-7 | frontier reasoning matters here — fires only after local self-correct fails twice; Zen pay-per-token cost is bounded |

Verification:
- `cargo check -p gateway --tests` — clean
- Live probes through localhost:3100/v1/chat:
  - `opencode/claude-opus-4-7` → "pong"
  - `gemini-3-flash-preview` (ollama_cloud) → "pong"
  - `kimi-k2.6` (ollama_cloud) → "pong"
  - `deepseek-v3.2` (ollama_cloud) → "Pong! 🏓"

Notes:
- kimi-k2:1t still upstream-broken (HTTP 500 on Ollama Pro probe today,
  matches yesterday's memory). Replacement table never picks it.
- The Rust changes need a `systemctl restart lakehouse.service` to
  take effect on the running gateway. TS callers reload on next run.
- aibridge/src/context.rs still has gpt-oss:{20b,120b} in its window-
  size lookup table; harmless and kept for callers that pass it
  explicitly as an override.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-28 06:13:30 -05:00
root
f4dc1b29e3 demo: search.html — Live Market explainer rewrite + fp-bar viewport-paint + compact contract cards
Some checks failed
lakehouse/auditor 18 blocking issues: cloud: claim not backed — "Verified end-to-end via playwright on devop.live/lakehouse:"
Four UI changes landing together since they all polish Section ① and
Section ② of the public demo:

1. Section ① (Live Market — Chicago) explainer rewritten data-source-
   first ("Live from City of Chicago Open Data...") with bolded dial
   names so a skimmer can map the visual to the prose. Drops the
   "internal calendar" jargon and the slightly-overclaiming "rest of
   the page is reacting" framing — downstream sections read the same
   feed but don't react to the per-shift filter, so the new copy says
   "this row is its heartbeat" instead.

2. Fill-probability bar gets a left-to-right paint reveal (clip-path
   inset animation) so the green→gold→orange→red gradient reads as a
   *timeline growing* instead of a static heatmap with a "danger zone"
   at the right. Followed by a 30%-wide shimmer sweep on a 3.4s loop
   for live-signal feel.

3. Paint trigger moved from on-render to IntersectionObserver — by
   the time the user scrolls to Section ② the on-render animation had
   already finished. Now each bar paints in over 2.8s when it enters
   viewport (threshold 0.2, 350ms entry delay). Single shared observer,
   unobserve()s after firing so the watch list trends to zero.

4. Contract cards now compact-by-default with click-to-expand. New
   summary strip shows revenue / margin / fill-by-1wk / top candidate
   so scanners get the punchline without expanding. Click anywhere on
   the card surface (excluding inner content) to expand the full FP
   curve, economics grid, candidates list, and Project Index. Project
   Index auto-opens with the parent card so users actually find the
   build signals — but only on user-driven expand (avoiding 20× OSHA
   scrapes on page load). grid-template-rows: 0fr → 1fr animation
   handles the smooth height transition.

All four animations honor prefers-reduced-motion.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-28 06:01:04 -05:00
root
f892230699 demo: search.html UX polish — skeleton loader, card-in stagger, hero takeover, B&W faces 
Search results no longer pop in as a single block. New behavior:

- Skeleton list pre-claims the vertical space results will occupy
  with shimmering placeholder cards, so arriving results fade in
  over the skeleton instead of pushing layout. Sweep is staggered
  per row for a "rolling wave" not "everything blinking together".
- Domain-language stage caption ("matching against permits",
  "ranking by reliability") rotates on a fixed schedule so users
  read progress, not a stuck spinner.
- @keyframes card-in: real worker cards rise 4px and fade in over
  350ms with nth-child stagger across the first ~12 rows. Honors
  prefers-reduced-motion.
- Avatar imgs filter through grayscale + slight contrast/blur to
  pull the SDXL Turbo color cast (which screams "AI generated" at
  small sizes). Cert icons get the same treatment.
- Once-per-session hero takeover compresses the Section ⓪ strip
  ("Not a CRM — an index that learns from you") into a centered
  hero on first paint, dismissed by clicking anywhere. Stats
  hydrate from live endpoints.

console.html: mirrors the avatar B&W filter for visual consistency,
and removes the headshot insertion entirely — back to monogram
initials. The console (internal staffer view) doesn't need synthetic
faces; the public demo at /lakehouse/ does.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-28 06:01:04 -05:00
root
4b92d1da91 demo: icon recipe pipeline + role-aware portraits + ComfyUI negative-prompt override 
Adds two single-source-of-truth recipe files that drive both the
hot-path render server and the offline pre-render scripts:

- role_scenes.ts: per-role-band scene clauses (clothing + backdrop).
  Forklift operators look like forklift operators instead of
  collapsing to interchangeable studio shots. SCENES_VERSION mixes
  into the headshot cache key so a coordinator tweak refreshes every
  matching face on next view.
- icon_recipes.ts: cert / role-prop / status / hazard / empty icons
  with deterministic per-recipe seeds + fuzzy text resolver.
  ICONS_VERSION suffix on the cached file means edits don't
  overwrite in place — misfires are recoverable.

Routes (mcp-server/index.ts):
- GET /headshots/_scenes — exposes SCENES + version to the
  pre-render script so prompts don't drift between batch and hot-path.
- GET /icons/_recipes — same idea for icons.
- GET /icons/cert?text=... — resolves free-text cert names to a
  recipe and 302s to the rendered icon. 404 (not 500) when no recipe
  matches so the front-end can hang `onerror="this.remove()"`.
- GET /icons/render/{category}/{slug} — cache-or-render at 256² (8
  steps) for crisper edges than 512² when downsampled to 14px.

ComfyUI portrait support (scripts/serve_imagegen.py):
The editorial workflow had `human, person, face` baked into its
negative prompt — actively sabotaging portraits. _comfyui_generate
now accepts negative_prompt/cfg/sampler/scheduler overrides, and
those mix into the cache key so portrait calls don't collapse into
hero-shot cache hits.

scripts/staffing/render_role_pool.py: pre-renders the role-aware
face pool by reading SCENES from /headshots/_scenes — single source
of truth verified at run time.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-28 06:01:04 -05:00
root
1745881426 staffing: face pool fetch preserves prior tags + --shrink gate + atomic manifest write 
fetch_face_pool was wiping 952 hand-classified rows when re-run from
a Python without deepface installed (it reset every gender to None).
Now:

- Loads existing manifest by id and overlays only fetch-owned fields,
  so gender/race/age/excluded survive a refetch.
- deepface pass tags only records that don't already have a gender;
  deepface unavailable means "leave existing tags alone" not "reset".
- New --shrink flag required to drop ids >= --count. Default refuses
  to shrink the pool silently.
- Atomic write via tmp + os.replace so an interrupted run can't
  corrupt the manifest.
- Dedupes duplicate id lines (root cause of the 2497-row manifest
  backing a 1000-face pool).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-28 06:01:04 -05:00
root
a05174d2fa ops: track tif_polygons.ts orphan import 
entity.ts imports findTifDistrict from ./tif_polygons.js but the
source file was never committed — only present in the working tree.
Adding it so a fresh clone compiles.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-28 06:01:04 -05:00
root
f9a408e4c4 Surname → ethnicity routing + ComfyUI fallback for sparse pool buckets + cache-buster 
Three problems J flagged ("not matching properly", "same faces", "still
showing old icons") had three different roots:

1. MISMATCH: front-end was first-name only, so "Anna Cruz" / "Patricia
   Garcia" / "John Jimenez" all defaulted to caucasian. Added
   SURNAMES_HISPANIC / _SOUTH_ASIAN / _EAST_ASIAN / _MIDDLE_EASTERN
   dicts to both search.html and console.html. Surname is checked
   FIRST (stronger signal for hispanic + asian than first names),
   then first-name fallback. Cruz → hispanic, Patel → south_asian,
   Nguyen → east_asian, regardless of first name.

2. SAME FACES: pool buckets are uneven — woman/south_asian=3,
   man/black=4, woman/middle_eastern=2 — so any worker in those
   buckets collapses to 2-4 photos no matter how good the hash is.
   /headshots/:key now 302-redirects to /headshots/generate/:key
   when the gender × race intersection is below 30 faces. ComfyUI
   on-demand gives infinite uniqueness for the sparse buckets
   (deterministic-per-worker via djb2 seed). Dense buckets still
   serve from the pool — no GPU cost there.

3. STALE CACHE: Cache-Control was max-age=86400, immutable — pinned
   old photos in browsers for 24h after any server-side update.
   Dropped to max-age=3600, must-revalidate, and added a v=2
   cache-buster query param to all front-end /headshots/ URLs so
   existing cached entries are bypassed on next page load.

Also surfacing X-Face-Pool-Bucket / Bucket-Size headers for diagnosis.

Verified: playwright run shows surname routing correct (Torres,
Rivera, Alvarez, Gutierrez, Patel, Nguyen, Omar all bucketed
correctly), sparse buckets 302 to ComfyUI, dense buckets stay on
the thumb pool.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-28 06:01:04 -05:00
root
a3b65f314e Synthetic face pool — 1000 StyleGAN headshots, ComfyUI hot-swap, 60x smaller thumbs 
Worker cards now ship a real photo per person instead of monogram tiles:

  - fetch_face_pool.py pulls 1000 faces from thispersondoesnotexist.com
  - tag_face_pool.py runs deepface for gender/race/age, excludes <22yo
  - manifest.jsonl: 952 servable, gender/race buckets populated
  - /headshots/_thumbs/ pre-resized to 384px webp (587KB -> 11KB,
    60x smaller; without this Chrome's parallel-connection budget
    drops ~75% of tiles in a 40-card grid)
  - /headshots/:key gender x race x age intersection bucketing with
    gender-only fallback when intersection is sparse
  - /headshots/generate/:key ComfyUI on-demand for the contractor
    profile spotlight (cold ~1.5s, cached ~1ms; worker-derived
    djb2 seed makes faces deterministic-per-worker but unique
    across workers sharing the same prompt)
  - serve_imagegen.py _cache_key() now includes seed (was caching
    by prompt only -> 3 different worker seeds collapsed to 1
    cached image; verified fix produces 3 distinct md5s)
  - confidence-default name resolution: Xavier->man+hispanic,
    Aisha->woman+black, etc. Every worker resolves to a bucket.

End-to-end: playwright run on /?q=forklift+operators+IL -> 21/21
cards loaded, 0 broken, all 384px webp.

Cache + binary pool gitignored; manifest tracked.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-28 06:01:04 -05:00
root
10ed3bc630 demo: real synthetic headshots — fetch pool + serve route + UI wire 
Three layers shipped:

1. SCRIPT — scripts/staffing/fetch_face_pool.py
   Pulls N synthetic StyleGAN faces from thispersondoesnotexist.com
   into data/headshots/face_NNNN.jpg, writes manifest.jsonl. Idempotent:
   re-running skips existing files. Optional gender tagging via deepface
   (currently unavailable on this box; the script handles ImportError
   gracefully and tags everything as untagged). Fetched 198 faces with
   concurrency=3 in ~67s.

2. SERVER — /headshots/:key route in mcp-server/index.ts
   Loads manifest at first hit, caches in globalThis._faces. Hashes the
   key with djb2-style mixing → pool index → returns the JPG. Same
   key always gets the same face (deterministic). Accepts
   ?g=man|woman&e=caucasian|black|hispanic|south_asian|east_asian|middle_eastern
   to bias pool selection — the gender/ethnicity buckets fall back to
   the full pool when no tagged matches exist. Cache-Control:
   86400 immutable so faces ride the browser cache after first hit.
   /headshots/__reload re-reads the manifest without restart.

3. UI — search.html + console.html worker cards
   Re-added overlay <img> on top of the monogram .av circle. img.src
   = /headshots/<encoded-key>?g=<hint>&e=<hint>. img.onerror removes
   the failed image so the monogram stays visible if the face pool
   isn't fetched / CDN is blocked. .av now has overflow:hidden +
   position:relative to clip the img to a perfect circle.

Forced-confident name resolution (J: "we're CREATING the profile,
created as though you truly have the information Xavier is more
likely Hispanic and he's a male"):

   genderFor(name)        — looks up MALE_NAMES + FEMALE_NAMES,
                            falls back to a deterministic hash split
                            so unknown names spread ~50/50. Sets now
                            include cross-cultural names: Alejandro/
                            Andres/Mateo/Santiago/Joaquin/Cesar/Hugo/
                            Felipe/Gerardo/Salvador/Ramon (Hispanic),
                            Raj/Anil/Vikram/Krishna/Pradeep (South
                            Asian), Wei/Yi/Hiroshi/Akira/Hyun (East
                            Asian), Demetrius/Kareem/DaQuan/Khalil
                            (Black), Omar/Khalid/Hassan/Ahmed/Bilal
                            (Middle Eastern). FEMALE_NAMES extended
                            in parallel.

   guessEthnicityFromFirstName(name)
                          — confident default of 'caucasian' for any
                            name not in the cultural buckets so every
                            worker resolves to a category the face
                            pool can be biased toward. Order: ME → Black
                            → Hispanic → South Asian → East Asian →
                            Caucasian (matters where names overlap,
                            e.g. Aisha appears in ME + Black, biases
                            toward ME for visual fit).

   Both helpers also ported into console.html so the triage backfills
   and try-it-yourself rendering get the same hint stack.

Privacy note in the script + route comments: the synthetic data uses
the worker's name as the seed; production should hash worker_id (not
name) to avoid leaking PII to a third-party CDN. The fetch URL itself
is referenced once per pool build, not per-worker.

.gitignore — added data/headshots/face_*.jpg (~100MB for 198 faces;
the manifest + script are tracked). Re-running the script on a fresh
checkout rebuilds the pool from scratch.

Verified end-to-end via playwright on devop.live/lakehouse:
   forklift query → 10 worker cards
   10/10 with face images (real synthetic headshots, not monograms)
   0/10 broken
   Alejandro G. Nelson  → ?g=man&e=hispanic
   Patricia K. Garcia    → ?g=woman&e=caucasian
   Each name → unique face, deterministic across loads.
   Console triage backfills get the same treatment.
 2026-04-28 06:01:04 -05:00
root
cdf5f5926a demo: console — sober worker cards (mirror dashboard styling) 
J: "can you update Staffer's Console too the same look." Console
rendered worker rows in three places (Chapter 4 permit-contract
candidates, Chapter 8 triage backfills, Chapter 9 try-it-yourself
results) with the original 28px square avatar + flat backgrounds —
inconsistent with the new dashboard design.

Three changes:

1. CSS — .worker now has a 3px left-edge border that color-codes the
   role family, and .av is a 32px circle with a muted dark background
   + 1px ring + monogram initials. Five role-band colors mirror
   search.html: warehouse blue / production amber / trades purple /
   driver green / lead orange. Plus a .role-pill style matching the
   dashboard's small uppercase chip.

2. Helpers — added ROLE_BANDS regex table + roleBand() classifier and
   a new workerRow(name, role, detail, opts) builder. Same regex
   patterns as search.html so a "Forklift Operator" classifies
   identically on every page. opts.endorsed adds the green endorsed
   chip; opts.score appends a rank badge.

3. Replaced the three inline avatar+row constructors with workerRow()
   calls. Net: console.html lost ~20 lines of duplicated DOM building
   while gaining role bands + pills.

Verified end-to-end via playwright on devop.live/lakehouse/console:
  Chapter 8 triage scenario "Marcus running late site 4422":
    5 backfill rows render with [warehouse] band + WAREHOUSE pill +
    monogram avatars (SBC, ETW, SHC, WMG, MEB).
  Same sober look as the dashboard worker cards. No emojis, no
  cartoons, color-coded role family on the left edge.
 2026-04-28 06:01:04 -05:00
root
f92b55615f demo: worker cards — sober monogram avatars + role bands (no cartoons) 
J: "It's two cartoonish right now the website looks like it was made
by first grade teacher." Pulled the DiceBear personas-style headshots
and the emoji role badges. They were generative-illustration playful;
this is supposed to read like a staffing tool, not a kindergarten
attendance sheet.

Replacement design — restraint, signal, no glyphs:

  Avatar:   40px circle, monogram initials, muted dark background
            (#161b22), 1px ring (#21262d), white-ish text. No image,
            no emoji. Looks like a pre-photo placeholder slot in a
            real ATS.

  Role band: the role gets classified into one of five families:
            WAREHOUSE / PRODUCTION / SKILLED TRADE / DRIVER / LEAD
            (regex-based; falls back to the first word of the role
            for unknown families). Each family has a single muted
            color: blue / amber / purple / green / orange. The
            color appears as:
              - a 3px left border on the .iworker card
              - a 2px left border + matching text color on a small
                uppercase pill in the detail line

That's it. No images, no emojis, no per-role illustrations. The
staffer sees role-family at a glance via the band color, name and
initials prominently, full role + city + zip in the detail string
behind the pill. Five colors total instead of an eight-color rainbow.

CSS:
  .iworker[data-role-band="warehouse"] etc. → 3px left border
  .role-pill[data-rb="warehouse"] etc.      → matching pill border

JS:
  ROLE_BANDS = 6 regex → band+label entries (warehouse, production,
                          trades, driver, lead, quality)
  roleBand(role)       = first matching entry, fallback to first
                          word of role uppercased

Verified end-to-end via playwright on devop.live/lakehouse:
  forklift query → 10 cards
  every card → monogram avatar + WAREHOUSE pill (blue band)
  no images, no emojis, no rainbow

Restart sequence after these edits:
  pkill -9 -f "/home/profit/lakehouse/mcp-server/index.ts"
  ( setsid bun run /home/profit/lakehouse/mcp-server/index.ts \
      > /tmp/mcp-server.log 2>&1 < /dev/null & disown )
 2026-04-28 06:01:04 -05:00
root
d571d62e9b demo: spec — refresh repo layout + model fleet + per-staffer + paths 8-9 
J: "how about devop.live/lakehouse/spec." Spec was anchored on
2026-04-21 state (v2 footer): mistral mentioned in the model matrix,
13 crates not 15, missing validator/truth/auditor crates, no mention
of OpenCode 40-model fleet, no pathway memory, no per-staffer
hot-swap, no Construction Activity Signal Engine, ADR count was 20.
Footer claimed Phases 19-25.

Edits, in order:

  Ch1 Repository layout
    + crates/truth/ (ADR-021 rule store)
    + crates/validator/ (Phase 43 — schema/completeness/policy gates)
    + auditor/ (cross-lineage Kimi↔Haiku/Opus auto-promote)
    + scripts/distillation/ (frozen substrate v1.0.0 at e7636f2)
    Updated aibridge to mention ProviderAdapter dispatch
    Updated gateway to mention OpenAI-compat /v1/* drop-in middleware
    Updated mcp-server route list to include /staffers + profiler/contractor pages
    Updated config/ to mention modes.toml + providers.toml + routing.toml
    Updated docs/ ADR count from 20 → 21
    Updated data/ to mention _pathway_memory + _auditor/kimi_verdicts

  Ch3 Measurement & indexing
    REPLACED stale "Model matrix (Phase 20)" T1-T5 table that
    mentioned mistral with the current 5-provider fleet:
      ollama / ollama_cloud / openrouter / opencode (40 models, one
      sk-* key reaches Claude Opus 4.7, GPT-5.5-pro, Gemini 3.1-pro,
      Kimi K2.6, GLM, DeepSeek, Qwen, MiniMax, free) / kimi
    ADDED 9-rung cloud-first ladder pseudocode
    ADDED N=3 consensus + cross-architecture tie-breaker math
    ADDED auditor cross-lineage Kimi K2.6 ↔ Haiku 4.5 + Opus auto-promote
    ADDED distillation v1.0.0 freeze paragraph (145 tests, 22/22, 16/16)
    Updated Continuation primitive to mention Phase 44 Rust port

  Ch5 What a CRM can't do
    Extended the table with 6 new capabilities:
      - Per-staffer relevance gradient
      - Triage in one shot (late-worker → backfills + draft SMS)
      - Permit → fill plan derivation
      - Public-issuer attribution across contractor graph
      - Cross-lineage AI audit on every PR
      - Pathway memory (system-level hot-swap, ADR-021)

  Ch6 How it gets better over time
    Lede updated from 7 paths → 10 paths
    NEW Path 7 — Pathway memory (ADR-021)
    NEW Path 8 — Per-staffer hot-swap index
    NEW Path 9 — Construction Activity Signal Engine
    Original Path 7 (observer ingest) renumbered to Path 10

  Ch9 Per-staffer context
    Lede now anchors Path 8 from Ch6
    NEW lead section: Per-staffer hot-swap index — Maria/Devon/Aisha,
    same query reshapes per coordinator (167 IL / 89 IN / 16 WI),
    MARIA'S MEMORY pill, /staffers endpoint, metro-agnostic by
    construction. The original Phase 17 profile / Phase 23 competence
    sections retained beneath as the deeper architecture detail.

  Ch10 A day in the life
    Updated 14:00 emergency event to use the late-worker triage
    handler — coordinator types "Dave running late site 4422", gets
    profile + draft SMS + 5 backfills + Copy SMS button in 250ms.
    The old Click No-show button → /log_failure flow remains valid
    (penalty still records); the user-facing surface is the new
    triage card.

  Ch11 Known limits
    REPLACED the Mem0/Letta/Phase-26 era list with current honest
    limits: BAI persistence + backtesting, NYC DOB adapter, 12
    awaiting public-data sources for contractor profile, rate/margin
    awareness, Mem0-style UPDATE/DELETE, Letta hot cache (now 5K
    not 1.9K), confidence calibration, SEC fuzzy precision, tighter
    pathway+scrum integration.

  Footer
    v2 2026-04-21 → v3 2026-04-27
    Phases 19-25 → 19-45
    Lists today's phases: distillation v1.0.0 substrate, gateway as
    OpenAI-compat drop-in, mode runner, validator + iterate, ADR-021
    pathway memory, per-staffer hot-swap, Construction Activity Signal
    Engine.

  Nav
    + Profiler link
    Date pill v1 · 2026-04-20 → v3 · 2026-04-27

Verified end-to-end on devop.live/lakehouse/spec — 11 chapter h2s
render in order, 67KB page (was 50KB-ish), all internal links resolve.
 2026-04-28 06:01:04 -05:00
root
631b0329b1 demo: proof — full architecture-page rewrite for current state 
J: "needs a rewrite." Old version was anchored on a dual-agent
mistral+qwen2.5 loop that hasn't been the model story for weeks,
called the system 13 crates (it's 15), referenced "Local 7B models"
in the honest-limits section, and had no mention of:
  - the 40-model OpenCode fleet via one sk-* key
  - the 9-rung cloud-first ladder
  - N=3 consensus + cross-architecture tie-breaker
  - auditor cross-lineage (Kimi K2.6 ↔ Haiku 4.5, Opus auto-promote)
  - distillation v1.0.0 frozen substrate (e7636f2)
  - pathway memory (88 traces, 11/11 replays, ADR-021)
  - per-staffer hot-swap index
  - Construction Activity Signal Engine + BAI + ticker network
  - the gateway as OpenAI-compat drop-in middleware

Rewrote into 10 chapters:

  1.  Receipts — live tests + new live tile showing the Signal Engine
      view for THIS load (issuer count, attributed build value,
      contractor count, attribution edges)
  2.  Architecture — corrected to 15 crates with current responsibilities;
      ASCII diagram showing OpenAI consumers + MCP + Browser all hitting
      gateway /v1/*; provider fleet table with all 5 (ollama, ollama_cloud,
      openrouter, opencode 40-model, kimi); validator + truth + auditor
      crates added
  3.  Model fleet — REPLACED the dual-agent mistral story. Now: the
      9-rung ladder (kimi-k2:1t through openrouter:free → ollama local),
      N=3 consensus + tie-breaker math, auditor Kimi↔Haiku alternation
      with Opus auto-promote on big diffs, distillation v1.0.0 freeze
      tag e7636f2 (145 tests · 22/22 · 16/16 · bit-identical)
  4.  Two memory layers — kept playbook content (Phase 19 boost math
      still load-bearing), added pathway memory (ADR-021) section with
      live counters in the page (88 / 11-11 / 100% reuse rate)
  5.  Per-staffer hot-swap — NEW. Pseudocode showing how staffer_id
      scopes state filter + playbook geo + UI relabel to MARIA'S MEMORY
  6.  Construction Activity Signal Engine — NEW. Three attribution
      flavors (direct, parent, associated), BAI math, cross-metro
      replication framing (NYC DOB next, then LA / Houston / Boston)
  7.  Architectural choices — added ADR-021 row + distillation freeze row
  8.  Measured at scale — kept (uses /proof.json scale data)
  9.  Verify or dispute — REFRESHED with current endpoints. Removed the
      stale "bun run tests/multi-agent/scenario.ts" recipe; added curl
      examples for /v1/health, pathway/stats, per-staffer scoping (3-loop
      bash script), late-worker triage, profiler_index, ticker_quotes,
      auditor verdicts, distillation acceptance gate
  10. What we are NOT claiming — REFRESHED. Removed "Local 7B models"
      caveat; added: 12 awaiting public-data sources are placeholders,
      SEC name-fuzzy has rare false positives, BAI is a thesis not a
      backtest yet, single-metro today

Live data probes added:
  loadPathwayLive   — fills pwm-traces / pwm-replays / pwm-rate spans
  loadSignalLive    — renders the LIVE Signal Engine tile under Ch1

Nav also gained a Profiler link to match search.html and console.html.

Verified end-to-end on devop.live/lakehouse/proof:
  10 chapters render, 5/5 live tests pass, pathway shows 88 traces +
  100% reuse rate, live signal tile shows 11 issuers + $347M attributed
  + 200 contractors + 14 attribution edges. Architecture diagram +
  crate table accurate as of HEAD.
 2026-04-28 06:01:04 -05:00
root
4c46cf6a21 demo: console — three new chapters reflecting recent shipments 
J: "it's outdated." Console walkthrough was stuck on the original 6
chapters (legacy-bridge / permits / catalog / ranking demo / playbook
memory / try-it-yourself). Three weeks of new work weren't visible.

Three new chapters added between the existing playbook-memory chapter
and the input box; all pull live data from the running system:

  Chapter 6 — Three coordinators, three views of the same corpus
    Renders Maria/Devon/Aisha cards from /staffers with their
    territories. Frames the per-staffer hot-swap as the relevance
    gradient that compounds independently per coordinator. Same query
    "forklift operators" returns 89 IN / 16 WI / 167 IL workers
    depending on who's acting.

  Chapter 7 — The hidden signal — public issuers in your contractor graph
    Pulls /intelligence/profiler_index, builds the basket, shows
    issuer count + attributed build value + contractor count as the
    three top metrics. Lists top 8 issuers with attribution counts
    and direct-link to the profiler. This is the BAI / Signal Engine
    pitch in walkthrough form: every contractor name is also a forward
    indicator on a public equity. Cross-metro replication explicit
    in the closing paragraph.

  Chapter 8 — When something breaks — triage in one shot
    Live triage demo against /intelligence/chat with body
    {message:"Marcus running late site 4422"}. Renders the worker
    card + draft SMS + 5 backfills + duration_ms. The 250ms-vs-20min
    moment, made concrete with real Quincy IL workers.

Chapter 9 (was 6) — Try it yourself
  Updated input examples to demonstrate each new route:
    "8 production workers near 60607" → headcount + zip parser
    "Marcus running late site 4422"  → triage handler
    "Marcus"                          → bare-name lookup
    "what came in last night"         → temporal route
    "reliable forklift operators with OSHA certs" → hybrid SQL+vector
  Each is a click-to-run link beneath the input.

Two new accent classes: .accent-g (green for issuer-count) and
.accent-r (red for triage event).

Verified end-to-end on devop.live/lakehouse/console: 9 chapters
render, ch6 shows 3 staffer personas, ch7 shows 11 issuers / $347M /
200 contractors, ch8 shows Marcus V. Campbell + draft SMS + 5
backfills.
 2026-04-28 06:01:04 -05:00
root
6366487b45 ops: persist runtime fixes — iterate.rs unused state, catalog cleanup 
Two load-bearing runtime changes that were never committed:

1. crates/gateway/src/v1/iterate.rs — `state` → `_state` on the unused
   route-state parameter. Cleared the one cargo workspace warning.
   Fix was made earlier this session but the working-tree change
   never made it into a commit.

2. data/_catalog/manifests/564b00ae-cbf3-4efd-aa55-84cdb6d2b0b7.json —
   DELETED. This was the dead manifest for `client_workerskjkk`, a
   typo dataset whose parquet was deleted but whose catalog entry
   stayed registered. Every SQL query failed schema inference on the
   missing file before reaching its target table — that's the bug
   that made /system/summary report 0 workers and the demo show zero
   bench. Deleting the manifest keeps the fix on disk; committing
   the deletion keeps it in git so a fresh checkout doesn't regress.

3. data/_catalog/manifests/32ee74a0-59b4-4e5b-8edb-70c9347a4bf3.json
   — runtime catalog metadata update from the successful_playbooks_live
   write path. Ride-along change.

Reports under reports/distillation/phase[68]-*.md are auto-regenerated
by the audit cycle each run; skipping those.
 2026-04-28 06:01:04 -05:00
root
db81fd8836 demo: System Activity panel — capability index reflects every recent shipment 
Old panel showed playbook ops + search counts and went empty in a
fresh demo (no operations yet). J: "update System Activity to coincide
with all of our recent updates."

Rebuilt as a live capability index — each tile is a thing the
substrate has learned to do, with the metric proving it's running.
Pulled in parallel from /staffers, /system/summary,
/api/vectors/playbook_memory/stats, /api/vectors/pathway/stats,
/intelligence/profiler_index, /intelligence/activity. Each probe
catches its own error so a single missing endpoint doesn't collapse
the panel.

Nine capability cards (verified end-to-end on devop.live/lakehouse):

  1. Per-staffer hot-swap index           3 personas (Maria/Devon/Aisha)
  2. Construction Activity Signal Engine  11 issuers · $347M attributed
                                          build value · network 11/14
  3. Late-worker / no-show triage         one-shot — name+late → backfills+SMS
  4. Permit → staffing bridge             24/day, every Chicago permit ≥$250K
  5. Hybrid SQL + vector search           500K workers · 5,474 playbook entries
  6. Schema-agnostic ingestion            36 datasets · 2.98M rows
  7. Contractor profile + project index   6 wired · 12 queued sources
  8. Pathway memory                       88 traces · 11/11 replays · 100%
  9. Ticker association network           11 tickers · 3 direct + 11 associated

Each card carries:
  - capability title + ship date pill ("baseline" or "shipped 2026-04-27")
  - big metric (live, not pre-baked)
  - sub-context line in coordinator language
  - "why a staffer cares" explanation
  - optional "Open →" deep link to the surface (Profiler, Contractor)

Header + intro paragraph reframed: "what the substrate has learned to
do" instead of "what the substrate has learned." Operational learning
(fills, playbooks, hot-swaps) compounds INSIDE each capability; the
panel surfaces the set of capabilities the corpus knows how to express.

Closing operational-stats row at the bottom shows fills/searches/
recent playbooks when /intelligence/activity has any.
 2026-04-28 06:01:04 -05:00
root
a789000982 demo: profiler — Construction Activity Signal Engine narrative + BAI 
J's prompt: shoot for the stars, frame the data corpus's value as a
predictive signal, not just a contractor directory. The thesis is
that every name in this corpus is also a forward indicator on public
equities — permits filed today predict construction starts in ~45
days, staffing in ~30, revenue recognition months later. The
associated-ticker network surfaces this signal before any 10-Q does.

Two new layers above the basket:

1. HERO THESIS PANEL — "Chicago Construction Activity Signal Engine"
   header + 3-line value statement, then 4 live metrics:

   - BAI (Building Activity Index) — attribution-weighted average of
     day-change % across surfaced issuers. Weight = attribution count
     so issuers we have more depth on count more. Today: +0.76%
     (9 issuers · top contributors FCBC +2.4%, ACRE +1.7%, JPM +1.5%).
     Color-coded green/red.

   - Indexed build value — total $ of permits attributable to ANY
     public issuer in this view. Today: $344M.

   - Network depth — issuers / attribution edges. Today: 9 / 15.
     This is the "we see what nobody else sees" metric: how many
     contractors are bridges from a private builder back to a public
     equity holder.

   - Market replication roadmap — chips showing "Chicago — live ·
     NYC DOB — adapter ready · LA County · Houston BCD · Boston ISD
     · DC DCRA". Frames the corpus as metro-agnostic from day one.

2. PER-TICKER ACTIVITY MAP — when a basket card is clicked, a leaflet
   map appears below the basket plotting that ticker's geocoded permit
   activity. Pulls /intelligence/contractor_profile for up to 6
   attributed contractors, merges their geocoded permits, plots on a
   dark Chicago tile layer. Color-banded by permit cost (green <$100K,
   amber $100K-$1M, red ≥$1M). Click TGT → 23 Target permits across
   Chicago; click JPM → JPMorgan-adjacent contractor activity. Cached
   per ticker so toggling is instant.

Verified end-to-end on devop.live/lakehouse/profiler:
  Default load: hero panel renders with all 4 metrics, basket strip
                with 9 issuers + live prices in 669ms.
  Click TGT  : signal map activates, "23 geocoded permits across
                1 contractor", table filters to 2 rows.
  Tooltip on basket cards: full reason path including matched name +
                contributors attributed to that ticker.

Architecture-side: zero new server code — all metrics computed
client-side from the existing profiler_index + ticker_quotes payloads.
The corpus already had the value; the page just needed to articulate it.
 2026-04-28 06:01:04 -05:00
root
aa56fbce61 demo: profiler — scrolling ticker basket with live prices + click-to-filter 
J asked: "kind of like a scrolling ticker that has all of the companies
and their stock prices and where they fit in the map." Implemented as
a horizontal-scroll strip at the top of /profiler:

  9 public issuers in this view · quotes via Stooq · 669ms
  ┌────┬────┬────┬────┬────┬────┬────┐
  │TGT │JPM │BALY│ACRE│FCBC│NREF│LSBK│ ← live price + day-change per
  │129 │311 │... │... │... │... │... │   ticker, color-banded by
  │+.17│+1.5│... │... │... │... │... │   attribution kind
  └────┴────┴────┴────┴────┴────┴────┘

Each card carries:
  - ticker + live price + day-change % (red/green)
  - attribution count + kind (exact / direct / parent / associated)
  - left bar color = strongest attribution kind (green for direct
    issuer, amber for parent, blue for co-permit associated, gradient
    when both direct and associated apply)
  - tooltip on hover lists the contractors attributed to this ticker
  - click toggles a filter on the table below — clicking TGT cuts the
    200-row list down to just TARGET CORPORATION + TORNOW, KYLE F
    (Target's primary co-permit contractor)

Server-side:
- entity.ts exports fetchStooqQuote (was internal)
- new POST /intelligence/ticker_quotes — accepts {tickers: [...]},
  fans out to Stooq.us in parallel, returns
  {ticker, price, price_date, open, high, low, day_change_pct,
   stooq_url} per symbol or null for non-US listings (HOC.DE, SKA-B.ST,
   LLC.AX). Capped at 50 symbols per call.

Front-end:
- mcp-server/profiler.html — new .basket-wrap section above the
  controls. buildBasket() runs after profiler_index loads:
    1. Aggregates unique tickers from .tickers.direct + .associated
       across all surfaced contractors
    2. Renders shells immediately (ticker symbol + "—" placeholder)
    3. Batch-fetches quotes via /intelligence/ticker_quotes
    4. Updates each card with price + day-change in place
  Click on a card sets a tickerFilter; render() skips rows whose
  attributions don't include that ticker. "clear filter" button on
  the basket strip resets it.

Verified end-to-end on devop.live/lakehouse/profiler:
  Default load → 9 issuers, live prices populated in 669ms
  TGT click   → table filters to TARGET CORPORATION + TORNOW, KYLE F
                (the contractor who runs 3 of Target's recent permits
                gets the TGT correlation indicator)
  JPM card    → $311.63, +1.55% — JPMorgan-adjacent contractors
  Tooltip     → list of contractors attributed to the ticker
 2026-04-28 06:01:04 -05:00
root
ba41ad2846 demo: profiler index — ticker associations (direct, parent, co-permit) 
J's framing: "if a contractor works for Target, future Target contracts
mean money flows back to the contractor — the ticker is an associated
indicator." Now the profiler index attaches three flavors of ticker per
contractor and renders them as colored pills:

  green DIRECT    contractor IS the public issuer (Target Corp → TGT)
  amber PARENT    contractor is a subsidiary of a public parent
                    (Turner Construction → HOC.DE via Hochtief AG)
  blue  ASSOCIATED contractor co-appears on permits with a public
                    entity (TORNOW, KYLE F → TGT, 3 shared permits with
                    TARGET CORPORATION)

The associated flavor is the correlation signal J described — it pulls
the ticker for whoever the contractor has been working *with*, not
just what they are themselves. Most contractors are private; the
associated link is how the moat shows up.

Server-side:
- entity.ts new export `lookupTickerLite(name)` — cheap in-memory
  resolver that does only the SEC tickers index lookup + curated
  KNOWN_PARENT_MAP check, no per-call SEC profile or Stooq fetch.
  ~10ms per name after the index is loaded once.
- /intelligence/profiler_index now runs a third Socrata pull
  (5K permit pairs in window) to build a co-occurrence map. For each
  contractor in the result, attaches:
    .tickers.direct[]      — name matches a public issuer
    .tickers.associated[]  — top 5 co-permit partners that resolve
                              to a ticker, with partner_name +
                              co_permits count + partner_via reason

Front-end:
- mcp-server/profiler.html — new .ticker-pill styles (3 colors per
  attribution kind), pills render under the contractor name in the
  table. Hover title gives the full reason path.

Verified end-to-end on the public URL:
  search="tornow" → blue TGT pill, hint "Associated via co-permits
                    with TARGET CORPORATION (3 shared permits) —
                    TARGET CORP"
  search="target" → green TGT × 2 (TARGET CORPORATION +
                    CORPORATION TARGET name variants both resolve
                    direct to the same issuer)
  default top 200 → 15 ticker pills surface across the page including
                    JPM (via JPMORGAN CHASE BANK co-permits) and
                    parent-link tickers for the construction majors.
 2026-04-28 06:01:04 -05:00
root
f6a7621b2d demo: profiler index — directory of every Chicago contractor 
J asked for "a profiler index that shows a history of everyone." This
is a /profiler directory page (also reachable via /contractors) that
ranks every contractor who's filed a Chicago permit, by total permit
value. Rows are clickable into the full /contractor profile.

Defaults: since 2025-06-01, min permit cost $250K, top 200 contractors
by total_cost. Server pulls two Socrata GROUP BY queries (one keyed on
contact_1_name, one on contact_2_name), merges them so contractors
listed in either applicant or contractor slot appear once with combined
counts/cost. ~300ms cold.

UI: live search box, since-date selector, min-cost selector, sortable
columns (name / permits / total_cost / last_filed). Live numbers as of
this write: 200 contractors, 1,702 permits, $14.22B aggregate. Filter
"Target" returns TARGET CORPORATION + CORPORATION TARGET (name variants
from Socrata).

Also fixes J's other complaint — "no new contracts, Target is gone":

  /intelligence/permit_contracts was hard-capped at $limit=6 + only
  the most recent 6 over $250K, so any day with 6 fresh permits would
  push older contractors (Target) off the panel entirely. Now defaults
  to 24 (caller can pass body.limit up to 100), so 2-3 days of permits
  stay on the panel. Added body.contractor — passes a name into the
  WHERE so the staffer can pin a specific contractor to the panel
  ("Target Corporation" → 3 of their permits over $250K).

Server-side:
- new POST /intelligence/profiler_index — paginated contractor index
  (since, min_cost, search, limit) with merged contact_1+contact_2
  aggregations
- /intelligence/permit_contracts — body.limit + body.contractor
- /profiler and /contractors routes serve profiler.html

Front-end:
- new mcp-server/profiler.html — sortable table, live filter, deep
  links to /contractor?name=... (prefix-aware via P, so /lakehouse
  works on devop.live)
- search.html + console.html nav: added "Profiler" link

Verified end-to-end via playwright on the public URL.
 2026-04-28 06:01:04 -05:00
root
31d8ef918c demo: contractor links — respect the /lakehouse path prefix 
J reported https://devop.live/contractor?name=3115%20W%20POLK%20ST.%20LLC
returned 404. Cause: the anchor href was a bare /contractor, which on
devop.live routes to the LLM Team UI (port 5000) at the main site root,
not the lakehouse mcp-server (which lives under /lakehouse/*).

Every page that renders a contractor link now uses the same prefix
detector the dashboard already had:

  var P = location.pathname.indexOf('/lakehouse') >= 0 ? '/lakehouse' : '';

Files updated:
- search.html: entity-brief anchor + preview anchor → P+/contractor
- console.html: permit-card contractor list → P+/contractor
- contractor.html: history.replaceState + back-link + the
  /intelligence/contractor_profile fetch all use P prefix. The page
  is reachable at /lakehouse/contractor on the public URL and bare
  /contractor on localhost; both work without further config.

Verified:
  https://devop.live/lakehouse/contractor?name=3115%20W%20POLK%20ST.%20LLC
    → 200, 29.9 KB, full profile renders. Contractor has 1 permit on
    file (a small LLC), 1 geocoded so the heat map plots one marker.
 2026-04-28 06:01:04 -05:00
root
a1066db87b demo: contractor profile — heat map, project index, 12 awaiting sources 
The contractor.html click-target J asked for: a separate page (not a
modal, not a fall-through search) showing every angle on a contractor.
Reachable from the Co-Pilot dashboard, the staffers console, and the
search box — all anchor-wrap contractor names to /contractor?name=...

What's new on the page:

1. PROJECT INDEX — build-signal score
   Single 0-100 number with the drivers laid out beneath. Driver list
   is staffer-readable: "59 Chicago permits in 180d (+30) · OSHA 20
   inspections (-25) · federal contractor (+15)". Score weights are
   placeholders to be replaced by an ML model once the 12 awaiting
   sources ship — the current 6 wired signals would not give a real
   model enough features.

2. HEAT MAP — every Chicago permit they've been contact_1 or contact_2
   on, last 24 months, plotted on a leaflet dark map. Color by cost
   (green <$100K, amber $100K-$1M, red ≥$1M), radius proportional to
   cost so the staffer sees where money + activity concentrates. Click
   a marker for permit detail (cost, date, work type, address, permit
   ID). All 50 of Turner Construction's geocoded recent permits in
   Chicago plot end-to-end.

3. ACTIVITY TIMELINE — monthly permit count, bar chart, with the
   first/last month labels so the staffer sees momentum. Tooltip on
   each bar gives the count and total cost for that month.

4. 12 AWAITING SOURCES — placeholder cards for the public datasets
   that would 3× the build-signal feature count. Each card has:
     - source name (real, e.g. DOL Wage & Hour, EPA ECHO, MSHA, BBB)
     - one-liner in coordinator language ("Has this contractor stiffed
       workers? Will they pay our staffing invoices?")
     - "Would show:" sample shape so the engineering scope is concrete
   Order is staffing-decision relevance:
     1. DOL Wage & Hour (WHD violations)
     2. State Licensure Boards (active license + expiry)
     3. Surety Bond Capacity (bonding ceiling)
     4. EPA ECHO Compliance (env violations at sites)
     5. DOT/FMCSA Carrier Safety (crash + OOS rates)
     6. BBB Complaints + Rating
     7. PACER Civil Suits (FLSA / Title VII / ADA)
     8. UCC Lien Filings (cash flow distress)
     9. D&B / Credit Bureau (PAYDEX, payment behavior)
    10. State UI Employer Claims (workforce stability)
    11. MSHA Mine Safety (excavation / aggregate / heavy)
    12. Registered Apprenticeships (DOL RAPIDS pipeline)

Server-side: entity.ts fetchContractorHistory now pulls the 50 most
recent permits with id + lat/lng + work_description, so the heat map
and timeline have what they need without a second SQL hop. The
ContractorHistory.recent_permits type gained the optional fields.

Front-end: contractor.html got 4 new render sections, leaflet wiring
(stylesheet + script in head), placeholder grid CSS, and a PLACEHOLDERS
const at the bottom with the 12 sources. All popup HTML is built via
DOM construction (textContent + appendChild) — no innerHTML, no XSS.

console.html: contractor names from /intelligence/permit_contracts now
anchor-wrapped to /contractor?name=... so the click-through J described
works from the staffers console too. Click stops propagation so the
permit details element doesn't toggle on the same click.

Verified end-to-end via playwright — Turner Construction profile shows:
  PIX score "Mixed signals — review drivers below"
  Heat map: "50 permits plotted · green/amber/red"
  4 section labels in order
  12 placeholder cards in the documented order
 2026-04-28 06:01:04 -05:00
root
5f0beffe80 demo: G — per-staffer hot-swap index (synthetic coordinator personas) 
Same corpus, different relevance gradient per staffer. Three personas
defined in mcp-server/index.ts STAFFERS roster (Maria/IL, Devon/IN,
Aisha/WI), each with a primary state + secondary cities. Server-side:
/intelligence/chat smart_search accepts a staffer_id body field; when
set, defaults state to the staffer's territory and labels the playbook
context as theirs. The playbook patterns query also defaults its geo
to the staffer's primary city/state, so the recurring-skills/cert
breakdowns reflect what they actually fill, not the global IL prior.

Front-end: a staffer selector dropdown beside the existing state/role
filters. Picking a staffer auto-pins state to their territory, shows
a greeting line, relabels the MEMORY panel as MARIA'S/DEVON'S/AISHA'S
MEMORY, and sends staffer_id to chat for scoping.

Dropdown is populated from /staffers (NOT /api/staffers — the generic
/api/* passthrough sends everything under /api/ to the Rust gateway,
which doesn't own the roster). loadStaffers runs at window-load
independently of loadDay's Promise.all so the dropdown populates even
if simulation/SQL inits error out.

Verified end-to-end via playwright. Same q="forklift operators":
  no staffer  → 509 workers across MI/OH/IA, MEMORY label
  as Devon    → 89 IN-only (Fort Wayne, Terre Haute), DEVON'S MEMORY
  as Aisha    → 16 WI-only (Milwaukee, Madison, Green Bay), AISHA'S MEMORY
As Maria with q="8 production workers near 60607":
  tags: headcount: 8 · zip 60607 → Chicago, IL · role: production · city: Chicago
  20 workers, MARIA'S MEMORY label, top results in Chicago zips

Closes the demo-side build of A-G from the persona plan:
  A. zip → city/state, B. headcount, C. bare-name, D. temporal,
  E. late-worker triage, F. contractor anchor, G. per-staffer index.
 2026-04-28 06:01:04 -05:00
root
677065de76 demo: P2 — staffer-language routes (zip, headcount, name, late-triage, ingest log) 
Built from a playwright run as three personas:
  Maria   — "8 production workers near 60607 by next Friday, prior-fill at this client"
  Devon   — "what came in last night?"
  Aisha   — "Marcus running late site 4422"

Each one previously fell through to smart_search and returned irrelevant
results (geo wrong, headcount ignored, no triage, no temporal). Now:

A. Zip code → city/state lookup. Chicago zips (606xx, 607xx, 608xx)
   resolve to {city: Chicago, state: IL}; 13 metro prefixes covered.
   Maria's "near 60607" now returns Chicago workers, not Dayton/Green Bay.

B. Headcount parser. "8 production workers" / "12 forklift operators" /
   "5 welders" set top_k 1..200, capped 5..25 for SQL+vector LIMIT.
   Allows 0-2 role words between the count and the worker noun so
   "8 production workers" matches as well as "8 workers".

C. Bare-name profile lookup. Single short capitalized phrase
   ("Marcus" / "Sarah Lopez") triggers a profile route. Per-token LIKE
   AND-joined so "Marcus Rivera" matches "Marcus L. Rivera" without
   hardcoding middle initials.

E. Late-worker / no-show triage. Pattern: <Name> (running late|late|
   no show|sick|out today|called out|can't make it) — pulls profile +
   reliability + responsiveness + recent calls, sources 5 same-role
   same-geo backfills sorted by responsiveness, drafts a client SMS
   the coordinator can copy. Front-end renders triage card + Copy SMS
   button + green backfill list.

F. Contractor name preview anchor. The PROJECT INDEX preview line on
   each permit card now wraps contact_1_name and contact_2_name in
   anchors to /contractor?name=... — clicking a contractor finally
   navigates instead of doing nothing. Click handler stops propagation
   so the details element doesn't toggle.

D. Temporal "what came in" route. last night / today / past N hours /
   recent — surfaces datasets from the catalog whose updated_at is
   within the window, samples one row per dataset to detect worker-
   shape, groups by role for worker tables. Schema-agnostic — drop
   any dataset and it shows up. Currently sparse because no fresh
   ingest has happened today; will populate as ingest runs.

Server: /intelligence/chat smart_search route accepts structured
state/role from the search-form dropdowns (P1 from prior commit) and
now ALSO honors b.state, b.role, q.match for headcount + zip + name +
triage patterns BEFORE falling through to NL parsing.

Front-end: doSearch dispatches on response.type and renders triage,
profile, ingest_log, and miss states with type-specific UI. All DOM
construction uses textContent / appendChild — no innerHTML, no XSS.

Verified end-to-end via playwright drive of devop.live/lakehouse:
  Maria  → 8 Chicago Production Workers (60685, 60662, 60634)
           tags: "headcount: 8 · zip 60607 → Chicago, IL · ..."
  Aisha  → Marcus V. Campbell card + draft SMS + 5 Quincy IL backfills
           "I'm dispatching Scott B. Cooper (96% reliability) to cover."
  Devon  → ingest_log surfaces successful_playbooks_live (last 1h)
  Marcus → 5 profiles (Adams Louisville KY, Jenkins Green Bay WI, ...)

Screenshots: /tmp/persona_v2/{01_maria,02_aisha,03_devon,04_marcus}.png

Restart sequence after these edits: pkill -9 -f "mcp-server/index.ts" ;
cd /home/profit/lakehouse ; bun run mcp-server/index.ts. The bun on
:3700 is not systemd-managed (pre-existing convention).
 2026-04-28 06:01:04 -05:00
root
fb99e92a60 demo: P1 — search filter now actually filters by state and role 
The Co-Pilot search box read state and role from the dropdowns (#sst, #srl)
but appended them to the message string as ' in '+st. The server's NL
parser then matched the literal preposition "in" against the case-insensitive
regex /\b(IL|IN|...)\b/i and assigned state IN (Indiana) to every search.
Result: typing "forklift in IL" returned Indiana workers. Same for WI, TX,
any state — all silently became Indiana. That was the "cached/generic
response" the legacy staffing client was seeing.

Two prongs:

1. search.html doSearch() now passes structured fields:
     {message, state, role}
   instead of munging into the message text. Dropdown selections bypass
   NL parsing entirely.

2. /intelligence/chat smart_search route accepts those structured fields
   and prefers them over regex archaeology. Falls back to NL parsing only
   when fields aren't provided. Fixed the regex too: the prepositional
   form (?:in|from)\s+(STATE) wins, the standalone form requires uppercase
   (drops /i flag) so the lowercase preposition "in" can no longer match.

Verified live:
- POST /intelligence/chat {"message":"forklift","state":"IL"}
    → 167 IL forklift operators (Galesburg, Joliet, ...)
- POST /intelligence/chat {"message":"forklift","state":"WI","role":"Forklift Operator"}
    → 16 WI Forklift Operators (Milwaukee, Madison, ...)
- POST /intelligence/chat {"message":"forklift in IL"} (NL fallback)
    → 167 IL workers (regex now correctly distinguishes preposition from state code)

Playwright drove the live UI through devop.live/lakehouse and confirmed the
front-end posts the structured body and the result panel renders the right
state. Restart sequence: kill old bun :3700, bun run mcp-server/index.ts.
 2026-04-28 06:01:04 -05:00
profit
ed57eda1d8 Merge PR #11: distillation v1.0.0 + Phase 42-45 + auditor cross-lineage + staffing cutover 
Closes the long-running scrum/auto-apply-19814 branch.

118 commits including:
- Distillation v1.0.0 substrate (tag distillation-v1.0.0 / e7636f2) — 145 tests, 22/22 acceptance, 16/16 audit-full
- Auditor rebuild on substrate (88s vs 25min, 50x fewer cloud calls)
- Phase 42-45 closure (validator crate + /v1/validate + /v1/iterate + /v1/health + /doc_drift/scan + Phase 44 /v1/chat migration)
- Auditor cross-lineage fabric (Kimi K2.6 / Haiku 4.5 / Opus 4.7 auto-promotion + per-PR cap with auto-reset on push)
- 5-provider routing (added opencode + kimi-direct adapters)
- Mode runner with composed-corpus downgrade gate (codereview_isolation default; composed lost 5/5 on grok-4.1-fast)
- Staffing cutover decisions A/C/D + B safe views — workers_500k_v9 corpus rebuild deferred to background job

Verified before merge:
- audit-full 16/16 required pass
- cargo check -p validator -p gateway clean
- All kimi_architect BLOCK findings dismissed as confabulation, logged in data/_kb/human_overrides.jsonl
- Kimi forensic HOLD on v1.0.0 verified manually: 2/8 false + 6/8 latent guarantees that do not fire under prod data
 2026-04-27 15:55:22 +00:00
837 changed files with 119528 additions and 759 deletions
Show Stats Expand all files Collapse all files

46
.gitignore vendored
View File

@ -4,3 +4,49 @@
.env .env
__pycache__/ __pycache__/
*.pyc *.pyc
# Headshot pool — binary face JPGs are fetched by scripts/staffing/fetch_face_pool.py
# (synthetic StyleGAN, ~580MB for 1000 faces). Manifest + fetch script are tracked.
data/headshots/face_*.jpg
data/headshots/_thumbs/
# ComfyUI on-demand generated portraits (per-worker unique). Cached on first
# request; fully regeneratable via /headshots/generate/:key.
data/headshots_gen/
# Runtime data — all regeneratable from inputs or accumulated by daemons.
# Anything under data/_<name>/ is internal state (auditor outputs, KB caches,
# pathway memory snapshots, HNSW trial results, etc.). Anything under
# data/datasets/ or data/vectors/ is generated by ingest/index pipelines.
data/_*/
data/lance/
data/datasets/
data/vectors/
data/demo/
data/evidence/
data/face_test/
data/headshots_role_pool/
data/icons_pool/
data/scored-runs/
data/workspaces/
data/catalog/
data/**/*.bak-*
data/**/*.pre-*-bak
# Logs
logs/
# Build artifacts
node_modules/
exports/
mcp-server/data/
# Per-run distillation reports (timestamp-named); keep the parent dir tracked
# via .gitkeep if needed but don't carry every batch's report set.
reports/distillation/[0-9]*/
reports/distillation/*-*-*-*-*/
# Test scratch — scratchpads, traces, sessions are regenerated each run.
# PRD/scenario fixtures stay tracked (they ARE the test).
tests/agent_test/_*
tests/agent_test/sessions/
tests/real-world/runs/

1
Cargo.lock generated
View File

@ -48,6 +48,7 @@ version = "0.1.0"
dependencies = [ dependencies = [
"async-trait", "async-trait",
"axum", "axum",
"lru",
"reqwest", "reqwest",
"serde", "serde",
"serde_json", "serde_json",

269
STATE_OF_PLAY.md Normal file
View File

@ -0,0 +1,269 @@
# STATE OF PLAY — Lakehouse
**Last verified:** 2026-05-02 evening CDT
**Verified by:** live probe (smoke 9/9, parity 32/32, gateway restarted), not memory.
> **Read this FIRST.** When the user says "we're working on lakehouse," they mean the working code captured below — NOT what `git log` framed as "the cutover" or what memory snapshots from 2 days ago suggest. If memory contradicts this file, this file wins. Update it when something is verified working — not when a phase finishes.
---
## WHAT LANDED 2026-05-01 → 2026-05-02 (10 commits this wave)
| Commit | What | Verified |
|---|---|---|
| `5d30b3d` | lance: auto-build doc_id btree in `lance_migrate` handler | doc-fetch ~5ms (was ~100ms full scan) on scale_test_10m |
| `044650a` | lance-bench: same scalar build post-IVF (matches gateway) | cargo check clean |
| `7594725` | lance: 4-pack — `sanitize_lance_err` + 7 unit tests + 9-probe smoke + 10M re-bench | smoke 9/9 PASS, tests 7/7 PASS |
| `98b6647` | gateway: `IterateResponse.trace_id` echoed; session_log_path enabled | parity probes see one unified JSONL |
| `57bde63` | gateway: trace-id propagation + coordinator session JSONL (Rust parity with Go wave) | session_log_parity 4/4 |
| `ba928b1` | aibridge: drop Python sidecar from hot path; AiClient → direct Ollama | aibridge tests 32/32 PASS, /ai/embed live 768d |
| `654797a` | gateway: pub `extract_json` + `parity_extract_json` bin | extract_json_parity 12/12 |
| `c5654d4` | docs: pointer to `golangLAKEHOUSE/docs/ARCHITECTURE_COMPARISON.md` | — |
| `150cc3b` | aibridge: LRU embed cache, 236× RPS warm (78ms → 129us p50) | load test |
| `9eed982` | mcp-server: /_go/* pass-through for G5 cutover slice | — |
| `6e34ef7` | gitignore: stop tracking 100+ runtime ephemera (data/_*, lance, logs, node_modules) | untracked dropped 100+ → 0 |
| `41b0a99` | chore: add 33 real items that were sitting untracked (scripts, scenarios, kimi reports, dev UIs) | clean working tree |
**Cross-runtime parity (post-this-wave):** 32/32 across 5 probes — `validator(6/6) + extract_json(12/12) + session_log(4/4) + materializer(2/2) + embed(8/8)`. Run `cd /home/profit/golangLAKEHOUSE && for p in scripts/cutover/parity/*.sh; do bash "$p"; done` to re-verify.
**Lance backend (was untested 5 days ago, now gauntlet-ready):**
- `cargo test -p vectord-lance --release` → 7/7 PASS
- `./scripts/lance_smoke.sh` → 9/9 PASS against live gateway
- `reports/lance_10m_rebench_2026-05-02.md` — search warm ~20ms / cold ~46ms median, doc-fetch ~5ms post-btree
---
## VERIFIED WORKING RIGHT NOW
### The client demo (Staffing Co-Pilot)
**Public URL:** `https://devop.live/lakehouse/` — 200, "Staffing Co-Pilot" (159 KB SPA, leaflet maps, dark theme).
**Local URL:** `http://localhost:3700/` — same page, served by `mcp-server/index.ts` (PID 1271, started 09:48 CDT today).
**The staffers console** (the one the client was thoroughly impressed with):
- `https://devop.live/lakehouse/console` — 200, "Lakehouse — What Your Staffing System Would Do" (26 KB)
- Pulls project index via `/api/catalog/datasets` (36 datasets) + playbook memory via `/api/vectors/playbook_memory/stats` (4,701 entries with embeddings, real ops like *"fill: Maintenance Tech x2 in Milwaukee, WI"*)
Client-visible flow that works end-to-end on the public URL:
| Endpoint | Sample output |
|---|---|
| `GET /api/catalog/datasets` | 36 datasets indexed: timesheets 1M, call_log 800K, workers_500k 500K, email_log 500K, workers_100k 100K, candidates 100K, placements 50K, job_orders 15K, successful_playbooks_live 2,077 |
| `GET /api/vectors/playbook_memory/stats` | 4,701 fill operations with embeddings |
| `GET /system/summary` | 36 datasets, 2.98M rows, 60 indexes, 500K workers loaded, 1K candidates |
| `POST /intelligence/staffing_forecast` | 744 Production Workers needed in 30d, 11,281 bench (4,687 reliable), coverage 1,444%, risk=ok. Same for Electrician (need 32, bench 2,440) and Maintenance Tech (need 17, bench 5,004). |
| `POST /intelligence/permit_contracts` | permit `3442956` $500K → 3 Production Workers, 886-candidate pool, 95% fill, $36K gross. 5 more Chicago permits with 8 workers each, same pool, 95% fill, $96K each. |
| `POST /intelligence/market` | major Chicago permits ranked: $730M O'Hare, $615M 307 N Michigan, $580M casino, $445M Loop transit (real geo coords). |
| `POST /intelligence/permit_entities` | architects + contractors from permit contacts (e.g. "KACPRZYNSKI, ANDY", "SLS ELECTRICAL SERVICE"). |
| `POST /intelligence/activity` + `/intelligence/arch_signals` + `/intelligence/chat` | all 200 |
The demo tells the story: *"upcoming Chicago contracts → workers needed → coverage from the bench → architects/contractors involved → revenue and margin."* That's the "live data + anticipating contracts + complete workflow" pitch — working as of right now.
### Backend, verified live this session
| Surface | State |
|---|---|
| Gateway `:3100` | up, 4 providers configured, `/v1/health` 200 with 500K workers loaded |
| MCP server `:3700` (Co-Pilot demo) | up, all `/intelligence/*` endpoints respond |
| VCP UI `:3950` | started this session, `/data/*` 200, real numbers |
| Observer `:3800` | ring full (2,000/2,000) — older events evicted, query Langfuse for 24h-ago state |
| Sidecar `:3200` | up |
| Langfuse `:3001` | recording, `gw:/log` + `v1.chat:openrouter` traces visible |
| LLM Team UI `:5000` | up, only `extract` mode registered |
| OpenCode fleet | **40 models reachable through one `sk-*` key** (verified live `GET https://opencode.ai/zen/v1/models`) |
OpenCode catalog (live):
- Claude: opus-4-7, opus-4-6, opus-4-5, opus-4-1, sonnet-4-6, sonnet-4-5, sonnet-4, haiku-4-5
- GPT-5: 5.5-pro, 5.5, 5.4-pro, 5.4, 5.4-mini, 5.4-nano, 5.3-codex-spark, 5.3-codex, 5.2, 5.2-codex, 5.1-codex-max, 5.1-codex, 5.1-codex-mini, 5.1, 5-codex, 5-nano, 5
- Gemini: 3.1-pro, 3-flash
- GLM: 5.1, 5
- Minimax: m2.7, m2.5
- Kimi: k2.6, k2.5
- Qwen: 3.6-plus, 3.5-plus
- Other: BIG-PKL (was a typo-prone name in the catalog, model id starts with "big-pkl-something")
- Free tier: minimax-m2.5-free, hy3-preview-free, ling-2.6-flash-free, trinity-large-preview-free
### The substrate (frozen — do not re-architect)
- Distillation v1.0.0 at tag `e7636f2` — **145/145 bun tests pass, 22/22 acceptance, 16/16 audit-full**
- Output: `data/_kb/distilled_{facts,procedures,config_hints}.jsonl` + `data/vectors/distilled_{factual,procedural,config_hint}_v20260423102847.parquet`
- Auditor cross-lineage: Kimi K2.6 ↔ Haiku 4.5 alternation, Opus auto-promote on diffs >100k chars, **per-PR cap=3 with auto-reset on new head SHA**
- Pathway memory: 88 traces, 11/11 successful replays (probation gate crossed)
- Mode runner: 5 native modes; `codereview_isolation` is default; composed-corpus auto-downgrade verified Apr 26 (composed lost 5/5 vs isolation, p=0.031)
### Matrix indexer
30+ live corpora including:
- 5 versions of `workers_500k_v1..v9` (50K embedded chunks each)
- 11 batched 2K-row shards `w500k_b3..b17`
- `chicago_permits_v1` (3,420), `resumes_100k_v2` (100K candidates), `ethereal_workers_v1` (10K)
- `lakehouse_arch_v1` (2,119), `lakehouse_symbols_v1` (2,470), `lakehouse_answers_v1` (1,269), `scrum_findings_v1` (1,260)
- `kb_team_runs_v1` (12,693) + `kb_team_runs_agent` (4,407) — LLM-team play history embedded
- `distilled_factual_v20260423102507` (8) — distillation output
### Code health
- `cargo check --workspace` → **0 warnings, 0 errors**
- `bun test auditor + tests/distillation` → **145/145 pass**
- `ui/server.ts` + `auditor.ts` bundle clean
---
## DO NOT RELITIGATE
- **PR #11 is merged into `origin/main` as `ed57eda`** — do not "still need to merge PR #11."
- **Distillation tag `distillation-v1.0.0` at `e7636f2` is FROZEN** — do not re-architect schemas, scorer rules, audit fixtures.
- **Kimi forensic HOLD verdict (2026-04-27) was 2/8 false + 6/8 latent** — do not re-debate, see `reports/kimi/audit-last-week-full.md`.
- **`candidates_safe` `vertical` column bug** — fixed at catalog metadata layer in commit `c3c9c21`. Do not "discover" it again.
- **Decisions A/B/C/D from `synthetic-data-gap-report.md`** — all four scripts shipped today (`d56f08e`, `940737d`, `c3c9c21`). Do not "ask J for approval."
- **`workers_500k.phone` type fixup** — already string. The fixup script is idempotent; running it is a no-op.
- **`client_workerskjkk` typo dataset** — was breaking every SQL query (catalog had it registered, file didn't exist). Removed via `DELETE /catalog/datasets/by-name/client_workerskjkk` this session. Do not re-add. Adding a startup gate that errors on unrecognized parquet names is the long-term fix per now.md Step 2C.
- **Python sidecar dropped from hot path 2026-05-02 (`ba928b1`)** — AiClient calls Ollama directly. Do not "wire python embedding back in." `lab_ui.py` + `pipeline_lab.py` keep running as dev-only UIs (not on the runtime path).
- **Lance backend gauntlet (2026-05-02)** — sanitizer over all 5 routes, 7 unit tests, 9-probe smoke, 10M re-bench. The `doc_id` btree auto-builds inside `lance_migrate` AND `lance-bench`. Do not "discover" the missing scalar index again or the leaked filesystem paths in error bodies.
- **Cross-runtime parity = 32/32** across 5 probes in `golangLAKEHOUSE/scripts/cutover/parity/`. Do not "build a parity probe for X" without checking — validator, extract_json, session_log, materializer, and embed are all already covered.
- **Decisions tracker is `golangLAKEHOUSE/docs/ARCHITECTURE_COMPARISON.md`** — single living source of truth for cross-runtime decisions. As of 2026-05-02 it has 0 `_open_` code work items; only 2 strategic items left (Lance vs Parquet+HNSW-with-spilling, Go-vs-Rust primary cutover).
---
## FIXES MADE THIS SESSION (2026-04-27 evening)
1. **`crates/gateway/src/v1/iterate.rs:93`** — `state` → `_state` (cleared the one cargo warning).
2. **`lakehouse-ui.service` (Dioxus)** — disabled. Was failing 7,242 times against a missing `target/dx/ui/debug/web/public` build dir. `systemctl stop && disable`.
3. **VCP UI on `:3950`** — started `bun run ui/server.ts` (PID 1162212, log `/tmp/lakehouse_ui.log`). `/data/*` endpoints now 200 with real data.
4. **`client_workerskjkk` catalog entry** — `DELETE /catalog/datasets/by-name/client_workerskjkk` removed the dead manifest. **This was the actual root cause** of `/system/summary` reporting `workers_500k_rows: 0` and the demo showing zero bench. Every SQL query was failing schema inference on the missing file before reaching its target table. Fixed → `workers_500k_rows: 500000`, `candidates_rows: 1000`, demo coverage flipped from "critical 0%" to actual percentages on devop.live/lakehouse.
## FIXES MADE THIS SESSION (2026-04-28 early — face pool)
5. **Synthetic StyleGAN face pool — 1000 faces, gender+race+age tagged.** `scripts/staffing/fetch_face_pool.py` fetches from thispersondoesnotexist.com; `scripts/staffing/tag_face_pool.py --min-age 22` runs deepface and excludes minors. `data/headshots/manifest.jsonl` now has gender (494 men / 458 women), race (caucasian 662 · east_asian 128 · hispanic 86 · middle_eastern 59 · black 14 · south_asian 3), age, and 48 minor exclusions. Server pool = 952 servable faces.
6. **`mcp-server/index.ts:1308` `/headshots/:key` route** — gender×race×age intersection bucketing with graceful fallback (gender-only → all). Same key always returns same face; different keys spread evenly.
7. **`/headshots/_thumbs/` pre-resized 384×384 webp** (60× smaller: 587KB → ~11KB). Without this, 40-card grids overran Chrome's parallel-connection budget and ~75% of tiles never finished decoding. Generated via parallel ffmpeg (`xargs -P 8`); `.gitignore`d.
8. **`mcp-server/search.html` + `console.html`** — dropped `img.loading='lazy'`. With 11KB thumbs, eager load is cheap (~500KB for 50 cards) and avoids the off-screen race that lazy decode produced.
9. **ComfyUI on-demand uniqueness — `serve_imagegen.py:32`** added `seed` to `_cache_key()` (was caching by prompt only — 3 different worker seeds collapsed to 1 cached image). Verified: seed=839185194/195/196 → 3 distinct md5s.
10. **`mcp-server/index.ts:1234` `/headshots/generate/:key`** — ComfyUI hot-path that derives a deterministic-per-worker seed via djb2-style hash; cold ~1.5s, cached ~1ms. Worker prompt format: `professional corporate headshot portrait of a {age}-year-old {race} {gender}, {role}, neutral expression, plain studio background, soft natural lighting, sharp focus, photorealistic, dslr`. Cache at `data/headshots_gen/` (gitignored, regeneratable).
11. **Confidence-default name resolution** in `search.html` — `genderFor()` and `guessEthnicityFromFirstName()` lookup tables (FEMALE_NAMES, MALE_NAMES, NAMES_HISPANIC, NAMES_BLACK, NAMES_SOUTH_ASIAN, NAMES_EAST_ASIAN, NAMES_MIDDLE_EASTERN). Xavier → man+hispanic, Aisha → woman+black, etc. Every worker resolves to a face-pool bucket.
End-to-end verified: playwright run on `https://devop.live/lakehouse/?q=forklift+operators+IL` → 21/21 cards loaded, 0 broken, all 384×384 webp thumbs.
---
## OPEN — but not blocking the demo
| Item | What | When to act |
|---|---|---|
| `modes.toml` `staffing_inference.matrix_corpus` | still says `workers_500k_v8`. v9 in vector index is from Apr 17 (raw-sourced, not safe-view). The new `build_workers_v9.sh` rebuilds from `workers_safe`. | Run when you have 30+ min for the rebuild. |
| Open PRs #6, #7, #10 | sitting since Apr 22-24, auditor verdicts on disk at `data/_auditor/kimi_verdicts/{6,7,10}-*.json` | Read verdicts, decide reconcile/close. |
| `test/enrich-prd-pipeline` branch | 35 unmerged commits, includes more-evolved auditor/inference.ts (666 vs main's 580 lines), curation+fact-extractor wiring | Reconcile or formally archive — see `memory/project_unmerged_architecture_work.md`. |
| `federation-hnsw-trials` stash | Lance + S3/MinIO prototype, `aws-config` crate added, 708 insertions | Phase B from EXECUTION_PLAN.md — revisit when Parquet vector ceiling actually hurts. |
| `candidates` manifest drift | manifest 100K vs SQL 1K. Cosmetic. | Run a metadata resync if it matters. |
---
## RUNTIME CHEATSHEET
```bash
# Verify the demo (public + local both work)
curl -sS https://devop.live/lakehouse/ # Co-Pilot HTML
curl -sS https://devop.live/lakehouse/console # staffers console
curl -sS -X POST https://devop.live/lakehouse/intelligence/staffing_forecast \
-d '{}' -H 'content-type: application/json' \
| jq '.forecast[] | {role, demand_workers, bench_total, coverage_pct, risk}'
# Restart sequence (after Rust changes)
sudo systemctl restart lakehouse.service # gateway :3100
sudo systemctl restart lakehouse-auditor # auditor daemon
sudo systemctl restart lakehouse-observer # observer :3800
# UI bun on :3950 is NOT systemd-managed (lakehouse-ui.service is disabled).
# Restart manually: kill <pid>; nohup bun run ui/server.ts > /tmp/lakehouse_ui.log 2>&1 &
# Health checks
curl -sS http://localhost:3100/v1/health | jq # workers_count, providers
curl -sS http://localhost:3100/vectors/pathway/stats | jq
curl -sS http://localhost:3100/v1/usage | jq # since-restart cost
curl -sS http://localhost:3700/system/summary | jq # dataset counts
```
---
## VISION — what we're actually building (not what's done)
J's framing for the legacy staffing company:
- Pull live data, anticipate contracts based on Chicago permits → real architect/contractor associations, headcount, time period, money, scope.
- Hybrid + memory index → search large corpora cheaply.
- Email comes in → verify against contract; SMS comes in → alert when index changes.
- Real-time.
- Invent metrics nobody else has using the hybrid index.
- Next stage: workers download an app → geolocation clock-in → automatic responsiveness measurement, no user effort, with incentives for using it.
- Find people getting certificates (passive cert tracking).
- Pull union data → bring contracts that work for **employees**, not just employers.
- All metrics visible, nothing hidden, value-aligned with what each side actually needs.
If a future session is shaving away from this vision toward "fix the cutover" or "land Phase X," the vision wins. Phases are scaffolding for the vision, not the goal.
---
## CURRENT PLAN — fix the demo for the legacy staffing client
Built from playwright audit of the live demo (2026-04-27 evening). Each item ends in something the client can SEE, not internal cleanups.
**Demo state is anchored by git tag `demo-2026-04-27`** (commit `ed57eda`, the merge of PR #11). To restore code state: `git checkout demo-2026-04-27`. To restore runtime state: `DELETE /catalog/datasets/by-name/client_workerskjkk` (catalog hot-fix is not in git).
### P1 — Search box that actually filters (highest visible impact)
**Problem:** typing in `#sq` and pressing Enter fires `POST /intelligence/chat` with body `{"message":"<query>"}`. The state (`#sst`) and role (`#srl`) selects are ignored — never sent in the body. So every search returns a generic chat completion, never a SQL+vector hybrid filter against `workers_500k`. That is the "cached/generic response" the client sees.
**Fix:** in `mcp-server/search.html`, change the search-submit handler to call the real worker search endpoint with `{query, state, role, top_k}`. The MCP `search_workers` tool surface already exists; route the form there. Render returned worker rows in the existing card grid.
**Done when:** typing "forklift" + state IL + role "Forklift Operator" returns ≤ top_k IL Forklift Operators, and changing state to WI returns different workers.
### P2 — Contractor-name click → `/contractor` profile page
**Problem:** clicking a contractor name in any rendered card stays on `/lakehouse/`. URL doesn't change.
**Fix:** wrap contractor names in `<a href="/contractor?name=<encoded>">`. The page `mcp-server/contractor.html` (14.8 KB, "Contractor Profile · Staffing Co-Pilot") already exists at `/contractor` and the data endpoint `/intelligence/contractor_profile` already returns rich data.
**Then check contractor.html actually shows:** full history of every record the database has on that contractor + heat map of locations underneath + relevant info (per J 2026-04-27). If the page is incomplete, finish it. Otherwise just wire the link.
**Done when:** clicking "KACPRZYNSKI, ANDY" opens a profile with: every Chicago permit they're contact_1 or contact_2 on, a leaflet map with markers for each address, and any matched workers from prior placements at their sites.
### P3 — Substrate signal at the bottom shows the right numbers
**Problem:** J reports the bottom panel says "playbook memory empty, 80 traces 0 replies." Reality from the live endpoints: `/api/vectors/playbook_memory/stats` = 4,701 entries with embeddings; `/vectors/pathway/stats` = 88 traces, 11/11 replays.
**Fix:** find the renderer in search.html that builds the substrate signal panel; verify it's hitting the right endpoints and reading the right keys; fix shape mismatches.
**Done when:** bottom panel shows real numbers (4,701 playbooks, 88 traces, 11/11 replays) and references at least one specific recent operation from the playbook stats sample.
### P4 — Top nav reflects today's architecture
**Problem:** Walkthrough/Architecture/Spec/Onboard/Alerts/Workspaces tabs all return 200 but content is from old architecture. Doesn't mention: gateway scratchpad, memory indexer, ranker, mode runner, OpenCode 40-model fleet, distillation substrate, auditor cross-lineage.
**Fix:** rewrite `mcp-server/proof.html` (or add a single new page "What's running" that replaces Architecture+Spec) to describe what's actually shipped as of `demo-2026-04-27`. Keep one architecture page, drop redundancy. Either complete or hide Onboard/Alerts/Workspaces — J's call which.
**Done when:** the architecture page tells a non-technical reader, in 2 minutes, what each piece does in coordinator-relatable terms ("intern that read every email", not "3-stage adversarial inference pipeline").
### P5 — Caching for the project-index build_signal (J flagged unfinished)
**Problem:** "we never finished our caching for project index build signal it's not pulling new information." Need to find what `build_signal` refers to. Likely a scrum/auditor signal that should rebuild the `lakehouse_arch_v1` corpus on commit but isn't wired to.
**Fix:** identify the build-signal pipeline (likely in `auditor/` or `crates/vectord/`), wire its emit to a corpus rebuild, verify by making a test commit and watching the new chunk appear in `/vectors/indexes` for `lakehouse_arch_v1`.
**Done when:** committing a new file to `crates/` causes `lakehouse_arch_v1` chunk_count to increase within N minutes.
### P0 — Anchor the demo state (DONE)
Tagged `ed57eda` as `demo-2026-04-27`. Future sessions: `git checkout demo-2026-04-27` to land in this exact code state.
---
## EXECUTION ORDER
1. **P1 first** — biggest visible bug, ~30-60 min
2. **P2 next** — contractor click is the second-biggest "doesn't work" the client sees, ~20 min if profile is mostly done
3. **P3** — small fix, big "looks alive" win
4. **P4** — biggest scope; might split across sessions
5. **P5** — feature work, only after the visible bugs are fixed
Each item commits independently with the format `demo: P<n> — <one-line>` so the commit log doubles as a progress journal. After each merge to main, re-tag `demo-latest` to point at the new HEAD.
Stop here and let J pick which item to start with. Do not silently extend scope.

8
bot/propose.ts
View File

@ -16,12 +16,14 @@ import type { Gap, Proposal } from "./types.ts";
// Phase 44 migration (2026-04-27): bot/propose.ts now flows through // Phase 44 migration (2026-04-27): bot/propose.ts now flows through
// the gateway's /v1/chat instead of hitting the sidecar's /generate // the gateway's /v1/chat instead of hitting the sidecar's /generate
// directly. /v1/usage tracks the call, Langfuse traces it, observer // directly. /v1/usage tracks the call, Langfuse traces it, observer
// sees it. Same upstream model (CLOUD_MODEL gpt-oss:120b on // sees it. Gateway owns the routing.
// Ollama Cloud) — gateway just owns the routing. //
// 2026-04-28: gpt-oss:120b → deepseek-v3.2 via Ollama Pro. Newer
// DeepSeek revision, faster, still on the same OLLAMA_CLOUD_KEY.
const GATEWAY_URL = process.env.LH_GATEWAY_URL ?? "http://localhost:3100"; const GATEWAY_URL = process.env.LH_GATEWAY_URL ?? "http://localhost:3100";
const REPO_ROOT = "/home/profit/lakehouse"; const REPO_ROOT = "/home/profit/lakehouse";
const PRD_PATH = `${REPO_ROOT}/docs/PRD.md`; const PRD_PATH = `${REPO_ROOT}/docs/PRD.md`;
const CLOUD_MODEL = process.env.LH_BOT_MODEL ?? "gpt-oss:120b"; const CLOUD_MODEL = process.env.LH_BOT_MODEL ?? "deepseek-v3.2";
const MAX_TOKENS = 6000; const MAX_TOKENS = 6000;
export async function findGaps(): Promise<Gap[]> { export async function findGaps(): Promise<Gap[]> {

9
config/modes.toml
View File

@ -44,7 +44,10 @@ name = "staffing_inference"
# pattern generalizes beyond code review. # pattern generalizes beyond code review.
preferred_mode = "staffing_inference_lakehouse" preferred_mode = "staffing_inference_lakehouse"
fallback_modes = ["ladder", "consensus", "pipeline"] fallback_modes = ["ladder", "consensus", "pipeline"]
default_model = "openai/gpt-oss-120b:free" # 2026-04-28: gpt-oss-120b:free → kimi-k2.6 via Ollama Pro. Coding-
# specialized, faster than gpt-oss, on the same OLLAMA_CLOUD_KEY so
# no extra provider hop.
default_model = "kimi-k2.6"
matrix_corpus = "workers_500k_v8" matrix_corpus = "workers_500k_v8"
[[task_class]] [[task_class]]
@ -58,7 +61,9 @@ matrix_corpus = "kb_team_runs_v1"
name = "doc_drift_check" name = "doc_drift_check"
preferred_mode = "drift" preferred_mode = "drift"
fallback_modes = ["validator"] fallback_modes = ["validator"]
default_model = "gpt-oss:120b" # 2026-04-28: gpt-oss:120b → gemini-3-flash-preview via Ollama Pro.
# Speed leader on factual checking, same OLLAMA_CLOUD_KEY.
default_model = "gemini-3-flash-preview"
matrix_corpus = "distilled_factual_v20260423095819" matrix_corpus = "distilled_factual_v20260423095819"
[[task_class]] [[task_class]]

31
config/providers.toml
View File

@ -15,22 +15,29 @@
[[provider]] [[provider]]
name = "ollama" name = "ollama"
base_url = "http://localhost:3200" base_url = "http://localhost:11434"
auth = "none" auth = "none"
default_model = "qwen3.5:latest" default_model = "qwen3.5:latest"
# Hot-path local inference. No bearer needed — Python sidecar on # Hot-path local inference. No bearer needed — direct to Ollama as of
# localhost handles the Ollama API. Model names are bare # 2026-05-02 (Python sidecar's pass-through wrapper retired). Model
# (e.g. "qwen3.5:latest", not "ollama/qwen3.5:latest"). # names are bare (e.g. "qwen3.5:latest", not "ollama/qwen3.5:latest").
[[provider]] [[provider]]
name = "ollama_cloud" name = "ollama_cloud"
base_url = "https://ollama.com" base_url = "https://ollama.com"
auth = "bearer" auth = "bearer"
auth_env = "OLLAMA_CLOUD_KEY" auth_env = "OLLAMA_CLOUD_KEY"
default_model = "gpt-oss:120b" default_model = "deepseek-v3.2"
# Cloud-tier Ollama. Key resolved from OLLAMA_CLOUD_KEY env at gateway # Cloud-tier Ollama (Pro plan as of 2026-04-28). Key resolved from
# boot. Model-prefix routing: "cloud/<model>" auto-routes here # OLLAMA_CLOUD_KEY at gateway boot; Pro tier upgraded the account so
# (see gateway::v1::resolve_provider). # rate limits + model access widen without a key change. Model-prefix
# routing: "cloud/<model>" auto-routes here. 39-model fleet now
# includes deepseek-v3.2, deepseek-v4-{flash,pro}, gemini-3-flash-
# preview, glm-{5,5.1}, kimi-k2.6, qwen3-coder-next.
# 2026-04-28: default upgraded gpt-oss:120b → deepseek-v3.2 (newest
# DeepSeek revision). NOTE: kimi-k2:1t is upstream-broken (HTTP 500
# on Ollama Pro probe 2026-04-28) — do not route to it. Use kimi-k2.6
# instead, which is what staffing_inference points at.
[[provider]] [[provider]]
name = "openrouter" name = "openrouter"
@ -38,7 +45,7 @@ base_url = "https://openrouter.ai/api/v1"
auth = "bearer" auth = "bearer"
auth_env = "OPENROUTER_API_KEY" auth_env = "OPENROUTER_API_KEY"
auth_fallback_files = ["/home/profit/.env", "/root/llm_team_config.json"] auth_fallback_files = ["/home/profit/.env", "/root/llm_team_config.json"]
default_model = "openai/gpt-oss-120b:free" default_model = "x-ai/grok-4.1-fast"
# Multi-provider gateway. Covers Anthropic, Google, OpenAI, MiniMax, # Multi-provider gateway. Covers Anthropic, Google, OpenAI, MiniMax,
# Qwen, Gemma, etc. Key resolved via crates/gateway/src/v1/openrouter.rs # Qwen, Gemma, etc. Key resolved via crates/gateway/src/v1/openrouter.rs
# resolve_openrouter_key() — env first, then fallback files. # resolve_openrouter_key() — env first, then fallback files.
@ -74,8 +81,10 @@ auth_env = "KIMI_API_KEY"
default_model = "kimi-for-coding" default_model = "kimi-for-coding"
# Direct Kimi For Coding provider. `api.kimi.com` is a SEPARATE account # Direct Kimi For Coding provider. `api.kimi.com` is a SEPARATE account
# system from `api.moonshot.ai` and `api.moonshot.cn` — keys are NOT # system from `api.moonshot.ai` and `api.moonshot.cn` — keys are NOT
# interchangeable. Used when Ollama Cloud's `kimi-k2:1t` is upstream- # interchangeable. Used as a fallback when Ollama Cloud's kimi-k2.6 is
# broken and OpenRouter's `moonshotai/kimi-k2.6` is rate-limited. # unavailable and OpenRouter's `moonshotai/kimi-k2.6` is rate-limited.
# (Was `kimi-k2:1t` here pre-2026-05-03 — that model is upstream-broken
# and removed from operator guidance.)
# Model id: `kimi-for-coding` (kimi-k2.6 underneath). # Model id: `kimi-for-coding` (kimi-k2.6 underneath).
# Key file: /etc/lakehouse/kimi.env (loaded via systemd EnvironmentFile). # Key file: /etc/lakehouse/kimi.env (loaded via systemd EnvironmentFile).
# Model-prefix routing: "kimi/<model>" auto-routes here, prefix stripped. # Model-prefix routing: "kimi/<model>" auto-routes here, prefix stripped.

1
crates/aibridge/Cargo.toml
View File

@ -12,3 +12,4 @@ serde_json = { workspace = true }
tracing = { workspace = true } tracing = { workspace = true }
reqwest = { version = "0.12", default-features = false, features = ["json", "rustls-tls"] } reqwest = { version = "0.12", default-features = false, features = ["json", "rustls-tls"] }
async-trait = "0.1" async-trait = "0.1"
lru = "0.12"

473
crates/aibridge/src/client.rs
View File

@ -1,28 +1,74 @@
use lru::LruCache;
use reqwest::Client; use reqwest::Client;
use serde::{Deserialize, Serialize}; use serde::{Deserialize, Serialize};
use std::num::NonZeroUsize;
use std::sync::Mutex;
use std::sync::atomic::{AtomicU64, Ordering};
use std::sync::Arc;
use std::time::Duration; use std::time::Duration;
/// HTTP client for the Python AI sidecar. /// HTTP client for Ollama (post-2026-05-02 — sidecar dropped).
///
/// `base_url` was historically the Python sidecar at `:3200`, which
/// pass-through-proxied to Ollama at `:11434`. The sidecar added zero
/// logic on the hot path (embed.py + generate.py + rerank.py +
/// admin.py = ~120 LOC of pure Ollama wrappers), so this client now
/// talks to Ollama directly and the sidecar process can be retired.
///
/// What stayed Python: `lab_ui.py` + `pipeline_lab.py` (~888 LOC of
/// dev-mode Streamlit-shape UIs) — those aren't on the runtime hot
/// path and continue running for prompt experimentation.
/// ///
/// `generate()` has two transport modes: /// `generate()` has two transport modes:
/// - When `gateway_url` is None (default), it posts to /// - When `gateway_url` is None (default), posts directly to Ollama's
/// `${base_url}/generate` (sidecar direct). /// `${base_url}/api/generate`.
/// - When `gateway_url` is `Some(url)`, it posts to /// - When `gateway_url` is `Some(url)`, posts to `${url}/v1/chat`
/// `${url}/v1/chat` with `provider="ollama"` so the call appears /// with `provider="ollama"` so the call appears in `/v1/usage` and
/// in `/v1/usage` and Langfuse traces. /// Langfuse traces.
/// ///
/// `embed()`, `rerank()`, and admin methods always go direct to the /// `embed()`, `rerank()`, and admin methods always go direct to
/// sidecar — no `/v1` equivalent yet, no point round-tripping. /// Ollama — no `/v1` equivalent for those surfaces yet.
/// ///
/// Phase 44 part 2 (2026-04-27): the gateway URL is wired in by /// Phase 44 part 2 (2026-04-27): the gateway URL is wired in by
/// callers that want observability (vectord modules); it's left /// callers that want observability (vectord modules); it's left
/// unset by callers that ARE the gateway internals (avoids self-loops /// unset by callers that ARE the gateway internals (avoids self-loops
/// + redundant hops). /// + redundant hops).
/// Per-text embed cache key. We key on (model, text) so different
/// model selections produce distinct cache lines — a query embedded
/// under nomic-embed-text-v2-moe must NOT collide with the same
/// query under nomic-embed-text v1.
#[derive(Eq, PartialEq, Hash, Clone)]
struct EmbedCacheKey {
model: String,
text: String,
}
/// Default LRU cache size — 4096 entries × ~6KB per 768-d f64
/// vector ≈ 24MB. Sized for typical staffing-domain repetition
/// (coordinator workflows have query repetition rates around 70-90%
/// per session). Tunable via [aibridge].embed_cache_size in the
/// config; 0 disables the cache entirely.
const DEFAULT_EMBED_CACHE_SIZE: usize = 4096;
#[derive(Clone)] #[derive(Clone)]
pub struct AiClient { pub struct AiClient {
client: Client, client: Client,
base_url: String, base_url: String,
gateway_url: Option<String>, gateway_url: Option<String>,
/// Closes the 63× perf gap with Go side. Mirrors the shape of
/// Go's internal/embed/cached.go::CachedProvider — same
/// (model, text) → vector caching, same nil-disable semantics.
/// None = caching disabled (cache_size=0); Some = bounded LRU.
embed_cache: Option<Arc<Mutex<LruCache<EmbedCacheKey, Vec<f64>>>>>,
/// Hit / miss counters for /admin observability + load-test
/// validation. Atomic so Clone'd AiClients share the same counts.
embed_cache_hits: Arc<AtomicU64>,
embed_cache_misses: Arc<AtomicU64>,
/// Pinned at construction time so the EmbedResponse can carry
/// dimension consistently even when every text was a cache hit
/// (no fresh upstream call to learn the dim from). Set on first
/// successful Ollama embed; checked on every cache hit.
cached_dim: Arc<AtomicU64>,
} }
// -- Request/Response types -- // -- Request/Response types --
@ -95,17 +141,49 @@ pub struct RerankResponse {
impl AiClient { impl AiClient {
pub fn new(base_url: &str) -> Self { pub fn new(base_url: &str) -> Self {
Self::with_embed_cache(base_url, DEFAULT_EMBED_CACHE_SIZE)
}
/// Constructs an AiClient with an explicit embed-cache size.
/// Pass 0 to disable the cache entirely (matches Go-side
/// CachedProvider's nil-cache semantics).
pub fn with_embed_cache(base_url: &str, cache_size: usize) -> Self {
let client = Client::builder() let client = Client::builder()
.timeout(Duration::from_secs(120)) .timeout(Duration::from_secs(120))
.build() .build()
.expect("failed to build HTTP client"); .expect("failed to build HTTP client");
let embed_cache = if cache_size > 0 {
// SAFETY: cache_size > 0 just verified, NonZeroUsize::new
// returns Some.
let cap = NonZeroUsize::new(cache_size).expect("cache_size > 0");
Some(Arc::new(Mutex::new(LruCache::new(cap))))
} else {
None
};
Self { Self {
client, client,
base_url: base_url.trim_end_matches('/').to_string(), base_url: base_url.trim_end_matches('/').to_string(),
gateway_url: None, gateway_url: None,
embed_cache,
embed_cache_hits: Arc::new(AtomicU64::new(0)),
embed_cache_misses: Arc::new(AtomicU64::new(0)),
cached_dim: Arc::new(AtomicU64::new(0)),
} }
} }
/// Cache hit/miss/size snapshot. Useful for /admin endpoints +
/// load-test validation ("did the cache fire as expected?").
pub fn embed_cache_stats(&self) -> (u64, u64, usize) {
let hits = self.embed_cache_hits.load(Ordering::Relaxed);
let misses = self.embed_cache_misses.load(Ordering::Relaxed);
let len = self
.embed_cache
.as_ref()
.map(|c| c.lock().map(|g| g.len()).unwrap_or(0))
.unwrap_or(0);
(hits, misses, len)
}
/// Same as `new`, but every `generate()` is routed through /// Same as `new`, but every `generate()` is routed through
/// `${gateway_url}/v1/chat` (provider=ollama) for observability. /// `${gateway_url}/v1/chat` (provider=ollama) for observability.
/// Use this for callers OUTSIDE the gateway. Inside the gateway /// Use this for callers OUTSIDE the gateway. Inside the gateway
@ -118,50 +196,222 @@ impl AiClient {
c c
} }
/// Reachability + version check. Hits Ollama's `/api/version`,
/// returns a sidecar-shaped envelope so callers reading
/// `.status` / `.ollama_url` don't break across the
/// pre-/post-2026-05-02 cutover.
pub async fn health(&self) -> Result<serde_json::Value, String> { pub async fn health(&self) -> Result<serde_json::Value, String> {
let resp = self.client let resp = self.client
.get(format!("{}/health", self.base_url)) .get(format!("{}/api/version", self.base_url))
.send() .send()
.await .await
.map_err(|e| format!("sidecar unreachable: {e}"))?; .map_err(|e| format!("ollama unreachable: {e}"))?;
resp.json().await.map_err(|e| format!("invalid response: {e}")) let body: serde_json::Value = resp.json().await
.map_err(|e| format!("invalid response: {e}"))?;
Ok(serde_json::json!({
"status": "ok",
"ollama_url": &self.base_url,
"ollama_version": body.get("version"),
}))
} }
/// Embed with per-text LRU caching. Mirrors Go-side
/// CachedProvider behavior: cache key is (model, text);
/// cache-hit texts skip the sidecar; cache-miss texts batch
/// into a single sidecar call; results are interleaved in the
/// caller's input order.
///
/// Closes ~95% of the load-test perf gap vs Go side (loadgen
/// 2026-05-01: Rust 128 RPS → with cache ≥ 7000 RPS expected
/// for warm-cache workloads). Cold-cache behavior unchanged
/// (every text is a miss → single sidecar call, identical to
/// pre-cache).
pub async fn embed(&self, req: EmbedRequest) -> Result<EmbedResponse, String> { pub async fn embed(&self, req: EmbedRequest) -> Result<EmbedResponse, String> {
let resp = self.client let model_key = req.model.clone().unwrap_or_default();
.post(format!("{}/embed", self.base_url))
.json(&req)
.send()
.await
.map_err(|e| format!("embed request failed: {e}"))?;
if !resp.status().is_success() { // Fast path: cache disabled → original behavior.
let text = resp.text().await.unwrap_or_default(); let Some(cache) = self.embed_cache.as_ref() else {
return Err(format!("embed error ({}): {text}", text.len())); return self.embed_uncached(&req).await;
};
if req.texts.is_empty() {
return self.embed_uncached(&req).await;
} }
resp.json().await.map_err(|e| format!("embed parse error: {e}"))
// First pass: check cache for each text. Track which positions
// need a sidecar fetch.
let mut embeddings: Vec<Option<Vec<f64>>> = vec![None; req.texts.len()];
let mut miss_indices: Vec<usize> = Vec::new();
let mut miss_texts: Vec<String> = Vec::new();
{
let mut guard = cache.lock().map_err(|e| format!("cache lock poisoned: {e}"))?;
for (i, text) in req.texts.iter().enumerate() {
let key = EmbedCacheKey { model: model_key.clone(), text: text.clone() };
if let Some(vec) = guard.get(&key) {
embeddings[i] = Some(vec.clone());
self.embed_cache_hits.fetch_add(1, Ordering::Relaxed);
} else {
miss_indices.push(i);
miss_texts.push(text.clone());
self.embed_cache_misses.fetch_add(1, Ordering::Relaxed);
}
}
}
// All hit? Return immediately. Use cached_dim to populate
// the response dimension (no sidecar to ask).
if miss_indices.is_empty() {
let dim = self.cached_dim.load(Ordering::Relaxed) as usize;
let dim = if dim == 0 { embeddings[0].as_ref().map(|v| v.len()).unwrap_or(0) } else { dim };
return Ok(EmbedResponse {
embeddings: embeddings.into_iter().map(|opt| opt.expect("filled")).collect(),
model: req.model.unwrap_or_else(|| "nomic-embed-text".to_string()),
dimensions: dim,
});
}
// Second pass: fetch the misses in one sidecar call.
let miss_req = EmbedRequest { texts: miss_texts.clone(), model: req.model.clone() };
let resp = self.embed_uncached(&miss_req).await?;
if resp.embeddings.len() != miss_texts.len() {
return Err(format!(
"embed cache: sidecar returned {} embeddings for {} texts",
resp.embeddings.len(),
miss_texts.len()
));
}
// Pin cached_dim on first successful response.
if resp.dimensions > 0 {
self.cached_dim.store(resp.dimensions as u64, Ordering::Relaxed);
}
// Insert misses into cache + fill response slots.
{
let mut guard = cache.lock().map_err(|e| format!("cache lock poisoned: {e}"))?;
for (j, idx) in miss_indices.iter().enumerate() {
let key = EmbedCacheKey {
model: model_key.clone(),
text: miss_texts[j].clone(),
};
let vec = resp.embeddings[j].clone();
guard.put(key, vec.clone());
embeddings[*idx] = Some(vec);
}
}
Ok(EmbedResponse {
embeddings: embeddings.into_iter().map(|opt| opt.expect("filled")).collect(),
model: resp.model,
dimensions: resp.dimensions,
})
}
/// Direct Ollama call — used internally by embed() for cache-miss
/// batches and as the transparent fallback when the cache is
/// disabled. Loops per-text against `${base_url}/api/embed`,
/// matching the sidecar's pre-2026-05-02 behavior. Ollama 0.4+
/// supports batch input but per-text keeps compatibility broader
/// + lets cache-miss-only batches share the loop with cold runs.
async fn embed_uncached(&self, req: &EmbedRequest) -> Result<EmbedResponse, String> {
let model = req.model.clone().unwrap_or_else(|| "nomic-embed-text".to_string());
let mut embeddings: Vec<Vec<f64>> = Vec::with_capacity(req.texts.len());
for text in &req.texts {
let resp = self.client
.post(format!("{}/api/embed", self.base_url))
.json(&serde_json::json!({
"model": &model,
"input": text,
}))
.send()
.await
.map_err(|e| format!("embed request failed: {e}"))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(format!("ollama embed error: {body}"));
}
// Ollama returns {"embeddings": [[...]], "model": "...", ...}.
// The outer `embeddings` is always a list; for a scalar input
// we get a single inner vector.
let parsed: serde_json::Value = resp.json().await
.map_err(|e| format!("embed parse error: {e}"))?;
let arr = parsed.get("embeddings")
.and_then(|v| v.as_array())
.ok_or_else(|| format!("ollama embed: missing 'embeddings' field in {parsed}"))?;
if arr.is_empty() {
return Err("ollama embed: empty embeddings array".to_string());
}
let first = arr[0].as_array()
.ok_or_else(|| "ollama embed: embeddings[0] not an array".to_string())?;
let vec: Vec<f64> = first.iter()
.filter_map(|n| n.as_f64())
.collect();
if vec.is_empty() {
return Err("ollama embed: numeric coercion produced empty vector".to_string());
}
embeddings.push(vec);
}
let dimensions = embeddings.first().map(|v| v.len()).unwrap_or(0);
Ok(EmbedResponse {
embeddings,
model,
dimensions,
})
} }
pub async fn generate(&self, req: GenerateRequest) -> Result<GenerateResponse, String> { pub async fn generate(&self, req: GenerateRequest) -> Result<GenerateResponse, String> {
if let Some(gw) = self.gateway_url.as_deref() { if let Some(gw) = self.gateway_url.as_deref() {
return self.generate_via_gateway(gw, req).await; return self.generate_via_gateway(gw, req).await;
} }
// Direct-sidecar legacy path. Used by gateway internals (so // Direct Ollama path. Used by gateway internals (so the ollama
// ollama_arm can call sidecar without a self-loop) and by // provider can call upstream without a self-loop through
// any consumer that wants raw transport without /v1/usage // /v1/chat) and by any consumer that wants raw transport
// accounting. // without /v1/usage accounting.
let model = req.model.clone().unwrap_or_else(|| "qwen3.5:latest".to_string());
let mut body = serde_json::json!({
"model": &model,
"prompt": &req.prompt,
"stream": false,
});
let mut options = serde_json::Map::new();
if let Some(t) = req.temperature {
options.insert("temperature".to_string(), serde_json::json!(t));
}
if let Some(mt) = req.max_tokens {
options.insert("num_predict".to_string(), serde_json::json!(mt));
}
if !options.is_empty() {
body["options"] = serde_json::Value::Object(options);
}
if let Some(sys) = &req.system {
body["system"] = serde_json::json!(sys);
}
if let Some(th) = req.think {
body["think"] = serde_json::json!(th);
}
let resp = self.client let resp = self.client
.post(format!("{}/generate", self.base_url)) .post(format!("{}/api/generate", self.base_url))
.json(&req) .json(&body)
.send() .send()
.await .await
.map_err(|e| format!("generate request failed: {e}"))?; .map_err(|e| format!("generate request failed: {e}"))?;
if !resp.status().is_success() { if !resp.status().is_success() {
let text = resp.text().await.unwrap_or_default(); let text = resp.text().await.unwrap_or_default();
return Err(format!("generate error: {text}")); return Err(format!("ollama generate error: {text}"));
} }
resp.json().await.map_err(|e| format!("generate parse error: {e}")) let parsed: serde_json::Value = resp.json().await
.map_err(|e| format!("generate parse error: {e}"))?;
Ok(GenerateResponse {
text: parsed.get("response").and_then(|v| v.as_str()).unwrap_or("").to_string(),
model,
tokens_evaluated: parsed.get("prompt_eval_count").and_then(|v| v.as_u64()),
tokens_generated: parsed.get("eval_count").and_then(|v| v.as_u64()),
})
} }
/// Phase 44 part 2: route generate() through the gateway's /// Phase 44 part 2: route generate() through the gateway's
@ -217,19 +467,60 @@ impl AiClient {
}) })
} }
/// Cross-encoder reranking via Ollama generate. Asks the model to
/// rate each document's relevance to the query 0-10, then sorts
/// descending. Mirrors the sidecar's pre-2026-05-02 algorithm
/// exactly so callers see the same scores.
pub async fn rerank(&self, req: RerankRequest) -> Result<RerankResponse, String> { pub async fn rerank(&self, req: RerankRequest) -> Result<RerankResponse, String> {
let resp = self.client let model = req.model.clone().unwrap_or_else(|| "qwen3.5:latest".to_string());
.post(format!("{}/rerank", self.base_url)) let mut scored: Vec<ScoredDocument> = Vec::with_capacity(req.documents.len());
.json(&req)
.send()
.await
.map_err(|e| format!("rerank request failed: {e}"))?;
if !resp.status().is_success() { for (i, doc) in req.documents.iter().enumerate() {
let text = resp.text().await.unwrap_or_default(); let prompt = format!(
return Err(format!("rerank error: {text}")); "Rate the relevance of the following document to the query on a scale of 0 to 10. \
Respond with ONLY a number.\n\n\
Query: {}\n\n\
Document: {}\n\n\
Score:",
req.query, doc,
);
let resp = self.client
.post(format!("{}/api/generate", self.base_url))
.json(&serde_json::json!({
"model": &model,
"prompt": prompt,
"stream": false,
"options": {"temperature": 0.0, "num_predict": 8},
}))
.send()
.await
.map_err(|e| format!("rerank request failed: {e}"))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(format!("ollama rerank error: {body}"));
}
let parsed: serde_json::Value = resp.json().await
.map_err(|e| format!("rerank parse error: {e}"))?;
let text = parsed.get("response").and_then(|v| v.as_str()).unwrap_or("").trim();
// Parse the leading number; tolerate "7", "7.5", "7 — strong match".
let score = text.split_whitespace().next()
.and_then(|t| t.parse::<f64>().ok())
.unwrap_or(0.0)
.clamp(0.0, 10.0);
scored.push(ScoredDocument {
index: i,
text: doc.clone(),
score,
});
} }
resp.json().await.map_err(|e| format!("rerank parse error: {e}"))
scored.sort_by(|a, b| b.score.partial_cmp(&a.score).unwrap_or(std::cmp::Ordering::Equal));
if let Some(k) = req.top_k {
scored.truncate(k);
}
Ok(RerankResponse { results: scored, model })
} }
/// Force Ollama to unload the named model from VRAM (keep_alive=0). /// Force Ollama to unload the named model from VRAM (keep_alive=0).
@ -238,40 +529,116 @@ impl AiClient {
/// profile's model can linger in VRAM next to the new one. /// profile's model can linger in VRAM next to the new one.
pub async fn unload_model(&self, model: &str) -> Result<serde_json::Value, String> { pub async fn unload_model(&self, model: &str) -> Result<serde_json::Value, String> {
let resp = self.client let resp = self.client
.post(format!("{}/admin/unload", self.base_url)) .post(format!("{}/api/generate", self.base_url))
.json(&serde_json::json!({ "model": model })) .json(&serde_json::json!({
"model": model,
"prompt": "",
"keep_alive": 0,
"stream": false,
}))
.send().await .send().await
.map_err(|e| format!("unload request failed: {e}"))?; .map_err(|e| format!("unload request failed: {e}"))?;
if !resp.status().is_success() { if !resp.status().is_success() {
let text = resp.text().await.unwrap_or_default(); let text = resp.text().await.unwrap_or_default();
return Err(format!("unload error: {text}")); return Err(format!("ollama unload error: {text}"));
} }
resp.json().await.map_err(|e| format!("unload parse error: {e}")) // Ollama returns 200 with the empty-prompt response shape.
// Fold into the legacy {"unloaded": "<model>"} envelope so
// callers' parsing doesn't break.
Ok(serde_json::json!({ "unloaded": model }))
} }
/// Ask Ollama to load the named model into VRAM proactively. Makes /// Ask Ollama to load the named model into VRAM proactively. Makes
/// the first real request after profile activation fast (no cold-load /// the first real request after profile activation fast (no cold-load
/// latency). /// latency). Empty prompts confuse some models, so we send a single
/// space + cap num_predict=1 (matches the sidecar's prior behavior).
pub async fn preload_model(&self, model: &str) -> Result<serde_json::Value, String> { pub async fn preload_model(&self, model: &str) -> Result<serde_json::Value, String> {
let resp = self.client let resp = self.client
.post(format!("{}/admin/preload", self.base_url)) .post(format!("{}/api/generate", self.base_url))
.json(&serde_json::json!({ "model": model })) .json(&serde_json::json!({
"model": model,
"prompt": " ",
"keep_alive": "5m",
"stream": false,
"options": {"num_predict": 1},
}))
.send().await .send().await
.map_err(|e| format!("preload request failed: {e}"))?; .map_err(|e| format!("preload request failed: {e}"))?;
if !resp.status().is_success() { if !resp.status().is_success() {
let text = resp.text().await.unwrap_or_default(); let text = resp.text().await.unwrap_or_default();
return Err(format!("preload error: {text}")); return Err(format!("ollama preload error: {text}"));
} }
resp.json().await.map_err(|e| format!("preload parse error: {e}")) let parsed: serde_json::Value = resp.json().await
.map_err(|e| format!("preload parse error: {e}"))?;
Ok(serde_json::json!({
"preloaded": model,
"load_duration_ns": parsed.get("load_duration"),
"total_duration_ns": parsed.get("total_duration"),
}))
} }
/// GPU + loaded-model snapshot from the sidecar. Combines nvidia-smi /// GPU + loaded-model snapshot. Combines nvidia-smi output (when
/// output (if available) with Ollama's /api/ps. /// available) with Ollama's /api/ps. Same shape as the prior
/// sidecar /admin/vram endpoint so callers don't need updating.
pub async fn vram_snapshot(&self) -> Result<serde_json::Value, String> { pub async fn vram_snapshot(&self) -> Result<serde_json::Value, String> {
let resp = self.client let resp = self.client
.get(format!("{}/admin/vram", self.base_url)) .get(format!("{}/api/ps", self.base_url))
.send().await .send().await
.map_err(|e| format!("vram request failed: {e}"))?; .map_err(|e| format!("ollama ps request failed: {e}"))?;
resp.json().await.map_err(|e| format!("vram parse error: {e}")) let loaded: Vec<serde_json::Value> = if resp.status().is_success() {
let parsed: serde_json::Value = resp.json().await.unwrap_or(serde_json::Value::Null);
parsed.get("models")
.and_then(|v| v.as_array())
.map(|arr| arr.iter().map(|m| serde_json::json!({
"name": m.get("name"),
"size_vram_mib": m.get("size_vram").and_then(|v| v.as_u64()).map(|n| n / (1024 * 1024)),
"expires_at": m.get("expires_at"),
})).collect())
.unwrap_or_default()
} else {
Vec::new()
};
let gpu = nvidia_smi_snapshot();
Ok(serde_json::json!({
"gpu": gpu,
"ollama_loaded": loaded,
}))
} }
} }
/// One-shot nvidia-smi poll. Returns Null if the tool isn't on PATH
/// or the call fails. Mirrors the sidecar's `_nvidia_smi_snapshot`
/// shape exactly so callers reading vram_snapshot don't break.
fn nvidia_smi_snapshot() -> serde_json::Value {
use std::process::Command;
let out = Command::new("nvidia-smi")
.args([
"--query-gpu=memory.used,memory.total,utilization.gpu,name",
"--format=csv,noheader,nounits",
])
.output();
let stdout = match out {
Ok(o) if o.status.success() => o.stdout,
_ => return serde_json::Value::Null,
};
let line = String::from_utf8_lossy(&stdout);
let line = line.trim();
if line.is_empty() {
return serde_json::Value::Null;
}
let parts: Vec<&str> = line.split(',').map(|s| s.trim()).collect();
if parts.len() < 4 {
return serde_json::Value::Null;
}
let used = parts[0].parse::<u64>().unwrap_or(0);
let total = parts[1].parse::<u64>().unwrap_or(0);
let util = parts[2].parse::<u64>().unwrap_or(0);
serde_json::json!({
"name": parts[3],
"used_mib": used,
"total_mib": total,
"utilization_pct": util,
})
}

37
crates/gateway/src/bin/parity_extract_json.rs Normal file
View File

@ -0,0 +1,37 @@
//! Cross-runtime parity helper for `extract_json`.
//!
//! Reads a single model-output string from stdin, runs the Rust
//! extract_json, prints `{"matched": bool, "value": <object|null>}`
//! to stdout as JSON. Exit 0 on success, exit 1 on internal error.
//!
//! The Go counterpart lives at
//! `golangLAKEHOUSE/internal/validator/iterate.go::ExtractJSON`. The
//! parity probe at
//! `golangLAKEHOUSE/scripts/cutover/parity/extract_json_parity.sh`
//! feeds the same fixtures through both and diffs the outputs.
//!
//! Usage:
//! echo '<raw model output>' | parity_extract_json
//! parity_extract_json <<< '...'
use std::io::Read;
fn main() {
let mut buf = String::new();
if let Err(e) = std::io::stdin().read_to_string(&mut buf) {
eprintln!("read stdin: {e}");
std::process::exit(1);
}
let result = gateway::v1::iterate::extract_json(&buf);
let body = serde_json::json!({
"matched": result.is_some(),
"value": result.unwrap_or(serde_json::Value::Null),
});
match serde_json::to_string(&body) {
Ok(s) => println!("{s}"),
Err(e) => {
eprintln!("serialize result: {e}");
std::process::exit(1);
}
}
}

71
crates/gateway/src/bin/parity_session_log.rs Normal file
View File

@ -0,0 +1,71 @@
//! Cross-runtime parity helper for `SessionRecord` JSON shape.
//!
//! Reads a fixture JSON on stdin, builds a `SessionRecord`, emits
//! one JSONL row on stdout. Used by
//! `golangLAKEHOUSE/scripts/cutover/parity/session_log_parity.sh`
//! to verify the Rust gateway's session log shape stays byte-equal
//! to the Go-side validatord's `validator.SessionRecord` (commit
//! 1a3a82a in golangLAKEHOUSE).
use gateway::v1::session_log::{SessionAttemptRecord, SessionRecord, SESSION_RECORD_SCHEMA};
use serde::Deserialize;
use std::io::Read;
#[derive(Deserialize)]
struct FixtureInput {
session_id: String,
kind: String,
model: String,
provider: String,
prompt: String,
iterations: u32,
max_iterations: u32,
final_verdict: String,
attempts: Vec<SessionAttemptRecord>,
#[serde(default)]
artifact: Option<serde_json::Value>,
#[serde(default)]
grounded_in_roster: Option<bool>,
duration_ms: u64,
}
fn main() {
let mut buf = String::new();
if let Err(e) = std::io::stdin().read_to_string(&mut buf) {
eprintln!("read stdin: {e}");
std::process::exit(1);
}
let input: FixtureInput = match serde_json::from_str(&buf) {
Ok(v) => v,
Err(e) => {
eprintln!("parse stdin: {e}");
std::process::exit(1);
}
};
let rec = SessionRecord {
schema: SESSION_RECORD_SCHEMA.to_string(),
session_id: input.session_id,
// Pinned timestamp so both runtimes' rows compare byte-equal
// when the test wrapper normalizes on `daemon` only.
timestamp: "2026-01-01T00:00:00+00:00".to_string(),
daemon: "gateway".to_string(),
kind: input.kind,
model: input.model,
provider: input.provider,
prompt: input.prompt,
iterations: input.iterations,
max_iterations: input.max_iterations,
final_verdict: input.final_verdict,
attempts: input.attempts,
artifact: input.artifact,
grounded_in_roster: input.grounded_in_roster,
duration_ms: input.duration_ms,
};
match serde_json::to_string(&rec) {
Ok(s) => println!("{s}"),
Err(e) => {
eprintln!("marshal: {e}");
std::process::exit(1);
}
}
}

44
crates/gateway/src/execution_loop/mod.rs
View File

@ -438,6 +438,10 @@ impl ExecutionLoop {
start_time: start_time.to_rfc3339(), start_time: start_time.to_rfc3339(),
end_time: end_time.to_rfc3339(), end_time: end_time.to_rfc3339(),
latency_ms: elapsed_ms, latency_ms: elapsed_ms,
// Internal execution-loop traffic is its own top-level
// trace per call. If a future caller threads a parent
// trace into self.state, lift this to Some(parent_id).
parent_trace_id: None,
}); });
} }
@ -582,10 +586,10 @@ impl ExecutionLoop {
/// Phase 20 step (8) — T3 overseer escalation. /// Phase 20 step (8) — T3 overseer escalation.
/// ///
/// When the local executor/reviewer loop can't self-correct, call /// When the local executor/reviewer loop can't self-correct, call
/// the cloud overseer (`gpt-oss:120b` via Ollama Cloud) with (a) /// the cloud overseer (`claude-opus-4-7` via OpenCode Zen) with
/// the KB context — recent outcomes + prior corrections for this /// (a) the KB context — recent outcomes + prior corrections for
/// sig_hash + task_class, across every profile that has run it — /// this sig_hash + task_class, across every profile that has run
/// and (b) the recent log tail. Its output is appended as a /// it — and (b) the recent log tail. Its output is appended as a
/// `system` role turn so the next executor generation sees it, /// `system` role turn so the next executor generation sees it,
/// AND written to `data/_kb/overseer_corrections.jsonl` so every /// AND written to `data/_kb/overseer_corrections.jsonl` so every
/// future profile activation reads from the same learning pool. /// future profile activation reads from the same learning pool.
@ -593,9 +597,16 @@ impl ExecutionLoop {
/// This is the "pipe to the overviewer" piece from 2026-04-23 — /// This is the "pipe to the overviewer" piece from 2026-04-23 —
/// the overseer is now a first-class KB consumer AND producer, not /// the overseer is now a first-class KB consumer AND producer, not
/// a one-shot correction oracle. /// a one-shot correction oracle.
///
/// 2026-04-28: routed through OpenCode (Zen tier) for Claude Opus
/// 4.7. Frontier reasoning matters here because the overseer fires
/// only after local self-correction has failed twice — by that
/// point we need the strongest reasoning available, not the
/// cheapest token. Frequency is low so the Zen pay-per-token cost
/// stays bounded.
async fn escalate_to_overseer(&mut self, turn: u32, reason: &str) -> Result<(), String> { async fn escalate_to_overseer(&mut self, turn: u32, reason: &str) -> Result<(), String> {
let Some(cloud_key) = self.state.ollama_cloud_key.clone() else { let Some(opencode_key) = self.state.opencode_key.clone() else {
return Err("OLLAMA_CLOUD_KEY not configured — skipping escalation".into()); return Err("OPENCODE_API_KEY not configured — skipping escalation".into());
}; };
let kb = KbContext::load_for(&sig_hash(&self.req), &self.req.task_class).await; let kb = KbContext::load_for(&sig_hash(&self.req), &self.req.task_class).await;
@ -604,16 +615,18 @@ impl ExecutionLoop {
let started = std::time::Instant::now(); let started = std::time::Instant::now();
let start_time = chrono::Utc::now(); let start_time = chrono::Utc::now();
let chat_req = crate::v1::ChatRequest { let chat_req = crate::v1::ChatRequest {
model: "gpt-oss:120b".to_string(), model: "claude-opus-4-7".to_string(),
messages: vec![crate::v1::Message::new_text("user", prompt.clone())], messages: vec![crate::v1::Message::new_text("user", prompt.clone())],
temperature: Some(0.1), temperature: Some(0.1),
max_tokens: None, max_tokens: None,
stream: Some(false), stream: Some(false),
think: Some(true), // overseer KEEPS thinking (Phase 20 rule) // Anthropic models on opencode reject `think` (handled in
provider: Some("ollama_cloud".into()), // the adapter), but we keep the intent flag for parity.
think: Some(true),
provider: Some("opencode".into()),
}; };
let resp = crate::v1::ollama_cloud::chat(&cloud_key, &chat_req).await let resp = crate::v1::opencode::chat(&opencode_key, &chat_req).await
.map_err(|e| format!("ollama_cloud: {e}"))?; .map_err(|e| format!("opencode: {e}"))?;
let latency_ms = started.elapsed().as_millis() as u64; let latency_ms = started.elapsed().as_millis() as u64;
let end_time = chrono::Utc::now(); let end_time = chrono::Utc::now();
let correction_text: String = resp.choices.into_iter().next() let correction_text: String = resp.choices.into_iter().next()
@ -633,8 +646,8 @@ impl ExecutionLoop {
if let Some(lf) = &self.state.langfuse { if let Some(lf) = &self.state.langfuse {
use crate::v1::langfuse_trace::ChatTrace; use crate::v1::langfuse_trace::ChatTrace;
lf.emit_chat(ChatTrace { lf.emit_chat(ChatTrace {
provider: "ollama_cloud".into(), provider: "opencode".into(),
model: "gpt-oss:120b".into(), model: "claude-opus-4-7".into(),
input: vec![crate::v1::Message::new_text("user", prompt.clone())], input: vec![crate::v1::Message::new_text("user", prompt.clone())],
output: correction_text.clone(), output: correction_text.clone(),
prompt_tokens: resp.usage.prompt_tokens, prompt_tokens: resp.usage.prompt_tokens,
@ -645,12 +658,13 @@ impl ExecutionLoop {
start_time: start_time.to_rfc3339(), start_time: start_time.to_rfc3339(),
end_time: end_time.to_rfc3339(), end_time: end_time.to_rfc3339(),
latency_ms, latency_ms,
parent_trace_id: None,
}); });
} }
// Append to the transcript so the next executor turn sees it. // Append to the transcript so the next executor turn sees it.
self.append(LogEntry::new( self.append(LogEntry::new(
turn, "system", "gpt-oss:120b", "overseer_correction", turn, "system", "claude-opus-4-7", "overseer_correction",
serde_json::json!({ serde_json::json!({
"reason": reason, "reason": reason,
"correction": correction_text, "correction": correction_text,
@ -672,7 +686,7 @@ impl ExecutionLoop {
"task_class": self.req.task_class, "task_class": self.req.task_class,
"operation": self.req.operation, "operation": self.req.operation,
"reason": reason, "reason": reason,
"model": "gpt-oss:120b", "model": "claude-opus-4-7",
"correction": correction_text, "correction": correction_text,
"applied_at_turn": turn, "applied_at_turn": turn,
"kb_context_used": kb, "kb_context_used": kb,

19
crates/gateway/src/lib.rs Normal file
View File

@ -0,0 +1,19 @@
//! Library facade for the gateway crate so sub-binaries (e.g.
//! `parity_extract_json`) can reuse the same modules the gateway
//! binary uses.
//!
//! Added 2026-05-02 to support the cross-runtime parity probe at
//! `golangLAKEHOUSE/scripts/cutover/parity/extract_json_parity.sh`.
//! `extract_json` is the load-bearing public surface for that probe.
//!
//! main.rs still uses local `mod foo;` declarations independently —
//! adding this file is purely additive (the binary's module tree is
//! unchanged).
pub mod access;
pub mod access_service;
pub mod auth;
pub mod execution_loop;
pub mod observability;
pub mod tools;
pub mod v1;

16
crates/gateway/src/main.rs
View File

@ -362,6 +362,22 @@ async fn main() {
} }
c c
}, },
// Coordinator session JSONL — one row per /v1/iterate
// session for offline DuckDB analysis. Cross-runtime
// parity with Go-side validatord (commit 1a3a82a).
session_log: {
let path = &config.gateway.session_log_path;
let s = v1::session_log::SessionLogger::from_path(path);
if s.is_some() {
tracing::info!(
"v1: session log enabled — coordinator sessions written to {}",
path
);
} else {
tracing::info!("v1: session log disabled (set [gateway].session_log_path to enable)");
}
s
},
})); }));
// Auth middleware (if enabled) — P5-001 fix 2026-04-23: // Auth middleware (if enabled) — P5-001 fix 2026-04-23:

266
crates/gateway/src/v1/iterate.rs
View File

@ -21,12 +21,19 @@
//! re-implementation. Staffing executors, agent loops, and future //! re-implementation. Staffing executors, agent loops, and future
//! validators all reach the same code path. //! validators all reach the same code path.
use axum::{extract::State, http::StatusCode, response::IntoResponse, Json}; use axum::{extract::State, http::{HeaderMap, StatusCode}, response::IntoResponse, Json};
use serde::{Deserialize, Serialize}; use serde::{Deserialize, Serialize};
const DEFAULT_MAX_ITERATIONS: u32 = 3; const DEFAULT_MAX_ITERATIONS: u32 = 3;
const LOOPBACK_TIMEOUT_SECS: u64 = 240; const LOOPBACK_TIMEOUT_SECS: u64 = 240;
/// Header name used to propagate a Langfuse parent trace id across
/// daemon boundaries. Matches Go's `shared.TraceIDHeader` constant
/// byte-for-byte (commit d6d2fdf in golangLAKEHOUSE) — same wire
/// format means a Go caller can hit Rust's /v1/iterate (or vice
/// versa) and the resulting Langfuse trees nest correctly.
pub const TRACE_ID_HEADER: &str = "x-lakehouse-trace-id";
#[derive(Deserialize)] #[derive(Deserialize)]
pub struct IterateRequest { pub struct IterateRequest {
/// "fill" | "email" | "playbook" — picks which validator runs. /// "fill" | "email" | "playbook" — picks which validator runs.
@ -80,6 +87,14 @@ pub struct IterateResponse {
pub validation: serde_json::Value, pub validation: serde_json::Value,
pub iterations: u32, pub iterations: u32,
pub history: Vec<IterateAttempt>, pub history: Vec<IterateAttempt>,
/// Echoes the resolved trace id (caller-forwarded header, body
/// field, langfuse-middleware mint, or local fallback). Operators
/// pivot from this id straight into Langfuse + the
/// coordinator_sessions.jsonl join key. Cross-runtime parity with
/// Go's `validator.IterateResponse` (commit 6847bbc in
/// golangLAKEHOUSE).
#[serde(skip_serializing_if = "Option::is_none")]
pub trace_id: Option<String>,
} }
#[derive(Serialize)] #[derive(Serialize)]
@ -87,29 +102,52 @@ pub struct IterateFailure {
pub error: String, pub error: String,
pub iterations: u32, pub iterations: u32,
pub history: Vec<IterateAttempt>, pub history: Vec<IterateAttempt>,
#[serde(skip_serializing_if = "Option::is_none")]
pub trace_id: Option<String>,
} }
pub async fn iterate( pub async fn iterate(
State(state): State<super::V1State>, State(state): State<super::V1State>,
headers: HeaderMap,
Json(req): Json<IterateRequest>, Json(req): Json<IterateRequest>,
) -> impl IntoResponse { ) -> impl IntoResponse {
let max_iter = req.max_iterations.unwrap_or(DEFAULT_MAX_ITERATIONS).max(1); let max_iter = req.max_iterations.unwrap_or(DEFAULT_MAX_ITERATIONS).max(1);
let temperature = req.temperature.unwrap_or(0.2); let temperature = req.temperature.unwrap_or(0.2);
let max_tokens = req.max_tokens.unwrap_or(4096); let max_tokens = req.max_tokens.unwrap_or(4096);
let mut history: Vec<IterateAttempt> = Vec::with_capacity(max_iter as usize); let mut history: Vec<IterateAttempt> = Vec::with_capacity(max_iter as usize);
let mut attempt_records: Vec<super::session_log::SessionAttemptRecord> = Vec::with_capacity(max_iter as usize);
let mut current_prompt = req.prompt.clone(); let mut current_prompt = req.prompt.clone();
// Resolve the parent Langfuse trace id. Caller-forwarded header
// wins (cross-daemon tree linkage); otherwise mint a fresh id so
// the iterate session is its own tree. Same shape as the Go-side
// validatord trace propagation.
let trace_id: String = headers
.get(TRACE_ID_HEADER)
.and_then(|v| v.to_str().ok())
.filter(|s| !s.is_empty())
.map(|s| s.to_string())
.unwrap_or_else(new_trace_id);
let client = match reqwest::Client::builder() let client = match reqwest::Client::builder()
.timeout(std::time::Duration::from_secs(LOOPBACK_TIMEOUT_SECS)) .timeout(std::time::Duration::from_secs(LOOPBACK_TIMEOUT_SECS))
.build() { .build() {
Ok(c) => c, Ok(c) => c,
Err(e) => return (StatusCode::INTERNAL_SERVER_ERROR, format!("client build: {e}")).into_response(), Err(e) => {
// Even infrastructure failures get a session row so a
// missing /v1/iterate event never silently disappears
// from the longitudinal log.
write_infra_error(&state, &req, &trace_id, max_iter, 0, format!("client build: {e}")).await;
return (StatusCode::INTERNAL_SERVER_ERROR, format!("client build: {e}")).into_response();
}
}; };
// Self-loopback to the gateway port. Carries gateway internal // Self-loopback to the gateway port. Carries gateway internal
// calls through /v1/chat + /v1/validate so /v1/usage tracks them. // calls through /v1/chat + /v1/validate so /v1/usage tracks them.
let gateway = "http://127.0.0.1:3100"; let gateway = "http://127.0.0.1:3100";
let t0 = std::time::Instant::now();
for iteration in 0..max_iter { for iteration in 0..max_iter {
let attempt_started = chrono::Utc::now();
// ── Generate ── // ── Generate ──
let mut messages = Vec::with_capacity(2); let mut messages = Vec::with_capacity(2);
if let Some(sys) = &req.system { if let Some(sys) = &req.system {
@ -123,20 +161,33 @@ pub async fn iterate(
"temperature": temperature, "temperature": temperature,
"max_tokens": max_tokens, "max_tokens": max_tokens,
}); });
let raw = match call_chat(&client, gateway, &chat_body).await { let raw = match call_chat(&client, gateway, &chat_body, &trace_id).await {
Ok(r) => r, Ok(r) => r,
Err(e) => return (StatusCode::BAD_GATEWAY, format!("/v1/chat hop failed at iter {iteration}: {e}")).into_response(), Err(e) => {
write_infra_error(&state, &req, &trace_id, max_iter, t0.elapsed().as_millis() as u64, format!("/v1/chat hop failed at iter {iteration}: {e}")).await;
return (StatusCode::BAD_GATEWAY, format!("/v1/chat hop failed at iter {iteration}: {e}")).into_response();
}
}; };
// ── Extract JSON ── // ── Extract JSON ──
let artifact = match extract_json(&raw) { let artifact = match extract_json(&raw) {
Some(a) => a, Some(a) => a,
None => { None => {
let span_id = emit_attempt_span(
&state, &trace_id, iteration, &req, &current_prompt, &raw, "no_json", None,
attempt_started, chrono::Utc::now(),
);
history.push(IterateAttempt { history.push(IterateAttempt {
iteration, iteration,
raw: raw.chars().take(2000).collect(), raw: raw.chars().take(2000).collect(),
status: AttemptStatus::NoJson, status: AttemptStatus::NoJson,
}); });
attempt_records.push(super::session_log::SessionAttemptRecord {
iteration,
verdict_kind: "no_json".to_string(),
error: None,
span_id,
});
current_prompt = format!( current_prompt = format!(
"{}\n\nYour previous attempt did not contain a JSON object. Reply with ONLY a valid JSON object matching the requested artifact shape.", "{}\n\nYour previous attempt did not contain a JSON object. Reply with ONLY a valid JSON object matching the requested artifact shape.",
req.prompt, req.prompt,
@ -151,22 +202,41 @@ pub async fn iterate(
"artifact": artifact, "artifact": artifact,
"context": req.context.clone().unwrap_or(serde_json::Value::Null), "context": req.context.clone().unwrap_or(serde_json::Value::Null),
}); });
match call_validate(&client, gateway, &validate_body).await { match call_validate(&client, gateway, &validate_body, &trace_id).await {
Ok(report) => { Ok(report) => {
let span_id = emit_attempt_span(
&state, &trace_id, iteration, &req, &current_prompt, &raw, "accepted", None,
attempt_started, chrono::Utc::now(),
);
history.push(IterateAttempt { history.push(IterateAttempt {
iteration, iteration,
raw: raw.chars().take(2000).collect(), raw: raw.chars().take(2000).collect(),
status: AttemptStatus::Accepted, status: AttemptStatus::Accepted,
}); });
attempt_records.push(super::session_log::SessionAttemptRecord {
iteration,
verdict_kind: "accepted".to_string(),
error: None,
span_id,
});
let duration_ms = t0.elapsed().as_millis() as u64;
let grounded = grounded_in_roster(&state, &req.kind, &artifact);
write_session_accepted(&state, &req, &trace_id, iteration + 1, max_iter, attempt_records, &artifact, grounded, duration_ms).await;
return (StatusCode::OK, Json(IterateResponse { return (StatusCode::OK, Json(IterateResponse {
artifact, artifact,
validation: report, validation: report,
iterations: iteration + 1, iterations: iteration + 1,
history, history,
trace_id: Some(trace_id.clone()),
})).into_response(); })).into_response();
} }
Err(err) => { Err(err) => {
let err_summary = err.to_string(); let err_summary = err.to_string();
let span_id = emit_attempt_span(
&state, &trace_id, iteration, &req, &current_prompt, &raw, "validation_failed",
Some(err_summary.clone()),
attempt_started, chrono::Utc::now(),
);
history.push(IterateAttempt { history.push(IterateAttempt {
iteration, iteration,
raw: raw.chars().take(2000).collect(), raw: raw.chars().take(2000).collect(),
@ -174,6 +244,12 @@ pub async fn iterate(
error: serde_json::to_value(&err_summary).unwrap_or(serde_json::Value::Null), error: serde_json::to_value(&err_summary).unwrap_or(serde_json::Value::Null),
}, },
}); });
attempt_records.push(super::session_log::SessionAttemptRecord {
iteration,
verdict_kind: "validation_failed".to_string(),
error: Some(err_summary.clone()),
span_id,
});
// Append validation feedback to prompt for next iter. // Append validation feedback to prompt for next iter.
// The model sees concrete failure mode + retries with // The model sees concrete failure mode + retries with
// corrective context. This is the "observer correction" // corrective context. This is the "observer correction"
@ -188,19 +264,167 @@ pub async fn iterate(
} }
} }
let duration_ms = t0.elapsed().as_millis() as u64;
write_session_failure(&state, &req, &trace_id, max_iter, max_iter, attempt_records, duration_ms).await;
(StatusCode::UNPROCESSABLE_ENTITY, Json(IterateFailure { (StatusCode::UNPROCESSABLE_ENTITY, Json(IterateFailure {
error: format!("max iterations reached ({max_iter}) without passing validation"), error: format!("max iterations reached ({max_iter}) without passing validation"),
iterations: max_iter, iterations: max_iter,
history, history,
trace_id: Some(trace_id.clone()),
})).into_response() })).into_response()
} }
async fn call_chat(client: &reqwest::Client, gateway: &str, body: &serde_json::Value) -> Result<String, String> { // ─── Helpers — Langfuse spans + session log + roster check ─────────
let resp = client.post(format!("{gateway}/v1/chat"))
.json(body) fn emit_attempt_span(
.send() state: &super::V1State,
.await trace_id: &str,
.map_err(|e| format!("chat hop: {e}"))?; iteration: u32,
req: &IterateRequest,
prompt: &str,
raw: &str,
verdict: &str,
error: Option<String>,
started: chrono::DateTime<chrono::Utc>,
ended: chrono::DateTime<chrono::Utc>,
) -> Option<String> {
let lf = state.langfuse.as_ref()?;
Some(lf.emit_attempt_span(super::langfuse_trace::AttemptSpan {
trace_id: trace_id.to_string(),
iteration,
model: req.model.clone(),
provider: req.provider.clone(),
prompt: prompt.to_string(),
raw: raw.to_string(),
verdict: verdict.to_string(),
error,
start_time: started.to_rfc3339(),
end_time: ended.to_rfc3339(),
}))
}
/// Verify every fill artifact's candidate IDs exist in the roster.
/// Returns Some(true)/Some(false) on the fill kind, None otherwise
/// (other kinds don't have worker IDs to ground). Same semantics as
/// Go's `handlers.rosterCheckFor("fill")`.
fn grounded_in_roster(
state: &super::V1State,
kind: &str,
artifact: &serde_json::Value,
) -> Option<bool> {
if kind != "fill" {
return None;
}
let fills = artifact.get("fills").and_then(|v| v.as_array())?;
for f in fills {
let id = match f.get("candidate_id").and_then(|v| v.as_str()) {
Some(s) if !s.is_empty() => s,
_ => return Some(false),
};
if state.validate_workers.find(id).is_none() {
return Some(false);
}
}
Some(true)
}
async fn write_session_accepted(
state: &super::V1State,
req: &IterateRequest,
trace_id: &str,
iterations: u32,
max_iter: u32,
attempts: Vec<super::session_log::SessionAttemptRecord>,
artifact: &serde_json::Value,
grounded: Option<bool>,
duration_ms: u64,
) {
let Some(logger) = state.session_log.as_ref() else { return };
let rec = build_session_record(req, trace_id, "accepted", iterations, max_iter, attempts, Some(artifact.clone()), grounded, duration_ms);
logger.append(rec).await;
}
async fn write_session_failure(
state: &super::V1State,
req: &IterateRequest,
trace_id: &str,
iterations: u32,
max_iter: u32,
attempts: Vec<super::session_log::SessionAttemptRecord>,
duration_ms: u64,
) {
let Some(logger) = state.session_log.as_ref() else { return };
let rec = build_session_record(req, trace_id, "max_iter_exhausted", iterations, max_iter, attempts, None, None, duration_ms);
logger.append(rec).await;
}
async fn write_infra_error(
state: &super::V1State,
req: &IterateRequest,
trace_id: &str,
max_iter: u32,
duration_ms: u64,
error: String,
) {
let Some(logger) = state.session_log.as_ref() else { return };
let attempts = vec![super::session_log::SessionAttemptRecord {
iteration: 0,
verdict_kind: "infra_error".to_string(),
error: Some(error),
span_id: None,
}];
let rec = build_session_record(req, trace_id, "infra_error", 0, max_iter, attempts, None, None, duration_ms);
logger.append(rec).await;
}
fn build_session_record(
req: &IterateRequest,
trace_id: &str,
final_verdict: &str,
iterations: u32,
max_iter: u32,
attempts: Vec<super::session_log::SessionAttemptRecord>,
artifact: Option<serde_json::Value>,
grounded: Option<bool>,
duration_ms: u64,
) -> super::session_log::SessionRecord {
super::session_log::SessionRecord {
schema: super::session_log::SESSION_RECORD_SCHEMA.to_string(),
session_id: trace_id.to_string(),
timestamp: chrono::Utc::now().to_rfc3339(),
daemon: "gateway".to_string(),
kind: req.kind.clone(),
model: req.model.clone(),
provider: req.provider.clone(),
prompt: super::session_log::truncate(&req.prompt, 4000),
iterations,
max_iterations: max_iter,
final_verdict: final_verdict.to_string(),
attempts,
artifact,
grounded_in_roster: grounded,
duration_ms,
}
}
/// Generate a fresh trace id when no parent was forwarded. Same
/// time-ordered hex shape Langfuse already accepts elsewhere in this
/// crate (see `langfuse_trace::uuid_v7_like`).
fn new_trace_id() -> String {
let ts = chrono::Utc::now().timestamp_nanos_opt().unwrap_or(0);
let rand = std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.map(|d| d.subsec_nanos())
.unwrap_or(0);
format!("{:016x}-{:08x}", ts, rand)
}
async fn call_chat(client: &reqwest::Client, gateway: &str, body: &serde_json::Value, trace_id: &str) -> Result<String, String> {
let mut req = client.post(format!("{gateway}/v1/chat")).json(body);
if !trace_id.is_empty() {
req = req.header(TRACE_ID_HEADER, trace_id);
}
let resp = req.send().await.map_err(|e| format!("chat hop: {e}"))?;
let status = resp.status(); let status = resp.status();
if !status.is_success() { if !status.is_success() {
let body = resp.text().await.unwrap_or_default(); let body = resp.text().await.unwrap_or_default();
@ -213,12 +437,12 @@ async fn call_chat(client: &reqwest::Client, gateway: &str, body: &serde_json::V
.to_string()) .to_string())
} }
async fn call_validate(client: &reqwest::Client, gateway: &str, body: &serde_json::Value) -> Result<serde_json::Value, String> { async fn call_validate(client: &reqwest::Client, gateway: &str, body: &serde_json::Value, trace_id: &str) -> Result<serde_json::Value, String> {
let resp = client.post(format!("{gateway}/v1/validate")) let mut req = client.post(format!("{gateway}/v1/validate")).json(body);
.json(body) if !trace_id.is_empty() {
.send() req = req.header(TRACE_ID_HEADER, trace_id);
.await }
.map_err(|e| format!("validate hop: {e}"))?; let resp = req.send().await.map_err(|e| format!("validate hop: {e}"))?;
let status = resp.status(); let status = resp.status();
let parsed: serde_json::Value = resp.json().await.map_err(|e| format!("validate parse: {e}"))?; let parsed: serde_json::Value = resp.json().await.map_err(|e| format!("validate parse: {e}"))?;
if status.is_success() { if status.is_success() {
@ -234,7 +458,13 @@ async fn call_validate(client: &reqwest::Client, gateway: &str, body: &serde_jso
/// Extract the first JSON object from a model's output. Handles /// Extract the first JSON object from a model's output. Handles
/// fenced code blocks (```json ... ```), bare braces, and stray /// fenced code blocks (```json ... ```), bare braces, and stray
/// prose around the JSON. Returns None on no extractable object. /// prose around the JSON. Returns None on no extractable object.
fn extract_json(raw: &str) -> Option<serde_json::Value> { ///
/// Made `pub` 2026-05-02 to support the cross-runtime parity probe
/// at `golangLAKEHOUSE/scripts/cutover/parity/extract_json_parity.sh`.
/// The Go counterpart lives at `internal/validator/iterate.go::ExtractJSON`;
/// when either runtime's algorithm changes the parity probe surfaces
/// the divergence.
pub fn extract_json(raw: &str) -> Option<serde_json::Value> {
// Try fenced first. // Try fenced first.
let candidates: Vec<String> = { let candidates: Vec<String> = {
let mut out = vec![]; let mut out = vec![];

194
crates/gateway/src/v1/langfuse_trace.rs
View File

@ -76,63 +76,54 @@ impl LangfuseClient {
}); });
} }
async fn emit_chat_inner(&self, ev: ChatTrace) -> Result<(), String> { /// Fire-and-forget per-iteration span emit. Returns the generated
let trace_id = uuid_v7_like(); /// span id synchronously so the caller can stamp it on
let gen_id = uuid_v7_like(); /// `IterateAttempt.span_id` before the network round-trip resolves.
let trace_ts = ev.start_time.clone(); /// Mirrors Go's `validator.Tracer` callback shape.
pub fn emit_attempt_span(&self, sp: AttemptSpan) -> String {
let span_id = uuid_v7_like();
let span_id_for_caller = span_id.clone();
let this = self.clone();
tokio::spawn(async move {
if let Err(e) = this.emit_attempt_span_inner(span_id, sp).await {
tracing::warn!(target: "v1.langfuse", "iterate span drop: {e}");
}
});
span_id_for_caller
}
async fn emit_attempt_span_inner(&self, span_id: String, sp: AttemptSpan) -> Result<(), String> {
let level = if sp.verdict == "accepted" { "DEFAULT" } else { "WARNING" };
let batch = IngestionBatch { let batch = IngestionBatch {
batch: vec![ batch: vec![IngestionEvent {
IngestionEvent { id: uuid_v7_like(),
id: uuid_v7_like(), timestamp: sp.end_time.clone(),
timestamp: trace_ts.clone(), kind: "span-create",
kind: "trace-create", body: serde_json::json!({
body: serde_json::json!({ "id": span_id,
"id": trace_id, "traceId": sp.trace_id,
"name": format!("v1.chat:{}", ev.provider), "name": format!("iterate.attempt[{}]", sp.iteration),
"input": serde_json::json!({ "input": serde_json::json!({
"model": ev.model, "iteration": sp.iteration,
"messages": ev.input, "model": sp.model,
}), "provider": sp.provider,
"metadata": serde_json::json!({ "prompt": truncate(&sp.prompt, 4000),
"provider": ev.provider,
"think": ev.think,
}),
}), }),
}, "output": serde_json::json!({
IngestionEvent { "verdict": sp.verdict,
id: uuid_v7_like(), "error": sp.error,
timestamp: ev.end_time.clone(), "raw": truncate(&sp.raw, 4000),
kind: "generation-create",
body: serde_json::json!({
"id": gen_id,
"traceId": trace_id,
"name": "chat",
"model": ev.model,
"modelParameters": serde_json::json!({
"temperature": ev.temperature,
"max_tokens": ev.max_tokens,
"think": ev.think,
}),
"input": ev.input,
"output": ev.output,
"usage": serde_json::json!({
"input": ev.prompt_tokens,
"output": ev.completion_tokens,
"total": ev.prompt_tokens + ev.completion_tokens,
"unit": "TOKENS",
}),
"startTime": ev.start_time,
"endTime": ev.end_time,
"metadata": serde_json::json!({
"provider": ev.provider,
"latency_ms": ev.latency_ms,
}),
}), }),
}, "level": level,
], "startTime": sp.start_time,
"endTime": sp.end_time,
}),
}],
}; };
self.post_batch(batch).await
}
async fn post_batch(&self, batch: IngestionBatch) -> Result<(), String> {
let url = format!("{}{}", self.inner.base_url.trim_end_matches('/'), INGESTION_PATH); let url = format!("{}{}", self.inner.base_url.trim_end_matches('/'), INGESTION_PATH);
let resp = self.inner.http let resp = self.inner.http
.post(url) .post(url)
@ -146,6 +137,81 @@ impl LangfuseClient {
} }
Ok(()) Ok(())
} }
async fn emit_chat_inner(&self, ev: ChatTrace) -> Result<(), String> {
// When the caller forwarded a parent trace id (via the
// X-Lakehouse-Trace-Id header → V1State plumbing), attach the
// generation as a child of that trace. Without a parent we
// mint a new top-level trace per call (Phase 40 default).
let trace_id = ev.parent_trace_id.clone().unwrap_or_else(uuid_v7_like);
let nested = ev.parent_trace_id.is_some();
let gen_id = uuid_v7_like();
let trace_ts = ev.start_time.clone();
let mut events = Vec::with_capacity(2);
if !nested {
// Only mint a fresh trace-create when we don't have a parent.
// Reusing a parent trace id without re-creating it is the
// contract that lets validatord's iterate-session show up
// as one tree in Langfuse.
events.push(IngestionEvent {
id: uuid_v7_like(),
timestamp: trace_ts.clone(),
kind: "trace-create",
body: serde_json::json!({
"id": trace_id,
"name": format!("v1.chat:{}", ev.provider),
"input": serde_json::json!({
"model": ev.model,
"messages": ev.input,
}),
"metadata": serde_json::json!({
"provider": ev.provider,
"think": ev.think,
}),
}),
});
}
events.push(IngestionEvent {
id: uuid_v7_like(),
timestamp: ev.end_time.clone(),
kind: "generation-create",
body: serde_json::json!({
"id": gen_id,
"traceId": trace_id,
"name": "chat",
"model": ev.model,
"modelParameters": serde_json::json!({
"temperature": ev.temperature,
"max_tokens": ev.max_tokens,
"think": ev.think,
}),
"input": ev.input,
"output": ev.output,
"usage": serde_json::json!({
"input": ev.prompt_tokens,
"output": ev.completion_tokens,
"total": ev.prompt_tokens + ev.completion_tokens,
"unit": "TOKENS",
}),
"startTime": ev.start_time,
"endTime": ev.end_time,
"metadata": serde_json::json!({
"provider": ev.provider,
"latency_ms": ev.latency_ms,
}),
}),
});
self.post_batch(IngestionBatch { batch: events }).await
}
}
/// Truncate a string to at most `n` chars (NOT bytes). Matches the Go
/// `trim` helper used in session log + attempt-span emission so an
/// operator reading two cross-runtime traces sees the same boundary.
fn truncate(s: &str, n: usize) -> String {
s.chars().take(n).collect()
} }
/// Everything the v1.chat handler collects for one completed call. /// Everything the v1.chat handler collects for one completed call.
@ -162,6 +228,32 @@ pub struct ChatTrace {
pub start_time: String, pub start_time: String,
pub end_time: String, pub end_time: String,
pub latency_ms: u64, pub latency_ms: u64,
/// When set, attach this chat trace as a child of the named
/// Langfuse trace instead of starting a new top-level trace. Used
/// by `/v1/iterate` to nest its inner /v1/chat hops under the
/// iterate-session trace so a multi-call session shows in
/// Langfuse as ONE trace tree, not N+1 disconnected traces.
/// Matches the Go-side `X-Lakehouse-Trace-Id` propagation
/// (commit d6d2fdf in golangLAKEHOUSE).
pub parent_trace_id: Option<String>,
}
/// One iteration attempt inside `/v1/iterate`'s loop. Becomes one
/// span on the parent trace when emitted via `emit_attempt_span`.
/// Matches Go's `validator.AttemptSpan` shape so the cross-runtime
/// observability surface is consistent.
pub struct AttemptSpan {
pub trace_id: String,
pub iteration: u32,
pub model: String,
pub provider: String,
pub prompt: String,
pub raw: String,
/// Verdict kind: "no_json" | "validation_failed" | "accepted"
pub verdict: String,
pub error: Option<String>,
pub start_time: String,
pub end_time: String,
} }
#[derive(Serialize)] #[derive(Serialize)]

21
crates/gateway/src/v1/mod.rs
View File

@ -21,6 +21,7 @@ pub mod opencode;
pub mod validate; pub mod validate;
pub mod iterate; pub mod iterate;
pub mod langfuse_trace; pub mod langfuse_trace;
pub mod session_log;
pub mod mode; pub mod mode;
pub mod respond; pub mod respond;
pub mod truth; pub mod truth;
@ -83,6 +84,13 @@ pub struct V1State {
/// disabled (keys missing or container unreachable). Traces are /// disabled (keys missing or container unreachable). Traces are
/// fire-and-forget: never block the response path. /// fire-and-forget: never block the response path.
pub langfuse: Option<langfuse_trace::LangfuseClient>, pub langfuse: Option<langfuse_trace::LangfuseClient>,
/// Coordinator session JSONL writer (path from
/// `[gateway].session_log_path`). One row per `/v1/iterate`
/// session for offline DuckDB analysis. None = disabled.
/// Cross-runtime parity with the Go-side `validatord`
/// `[validatord].session_log_path` (commit 1a3a82a in
/// golangLAKEHOUSE).
pub session_log: Option<session_log::SessionLogger>,
} }
#[derive(Default, Clone, Serialize)] #[derive(Default, Clone, Serialize)]
@ -361,6 +369,7 @@ mod resolve_provider_tests {
async fn chat( async fn chat(
State(state): State<V1State>, State(state): State<V1State>,
headers: axum::http::HeaderMap,
Json(req): Json<ChatRequest>, Json(req): Json<ChatRequest>,
) -> Result<Json<ChatResponse>, (StatusCode, String)> { ) -> Result<Json<ChatResponse>, (StatusCode, String)> {
if req.messages.is_empty() { if req.messages.is_empty() {
@ -490,6 +499,17 @@ async fn chat(
let output = resp.choices.first() let output = resp.choices.first()
.map(|c| c.message.text()) .map(|c| c.message.text())
.unwrap_or_default(); .unwrap_or_default();
// Cross-runtime trace linkage. When a caller (validatord on
// Go side, /v1/iterate on Rust side) forwards a parent trace
// id via X-Lakehouse-Trace-Id, attach this generation to that
// trace so the iterate session and its inner chat hops show
// up as ONE trace tree in Langfuse. Header name matches the
// Go-side `shared.TraceIDHeader` constant byte-for-byte.
let parent_trace_id = headers
.get(crate::v1::iterate::TRACE_ID_HEADER)
.and_then(|v| v.to_str().ok())
.map(|s| s.to_string())
.filter(|s| !s.is_empty());
lf.emit_chat(langfuse_trace::ChatTrace { lf.emit_chat(langfuse_trace::ChatTrace {
provider: used_provider.clone(), provider: used_provider.clone(),
model: resp.model.clone(), model: resp.model.clone(),
@ -503,6 +523,7 @@ async fn chat(
start_time: start_time.to_rfc3339(), start_time: start_time.to_rfc3339(),
end_time: end_time.to_rfc3339(), end_time: end_time.to_rfc3339(),
latency_ms, latency_ms,
parent_trace_id,
}); });
} }

235
crates/gateway/src/v1/session_log.rs Normal file
View File

@ -0,0 +1,235 @@
//! Coordinator session JSONL writer — Rust parity with the Go-side
//! `internal/validator/session_log.go` (commit 1a3a82a in
//! golangLAKEHOUSE). Same schema, same field names, same producer
//! semantics, so a unified longitudinal log can pull from either
//! runtime via DuckDB.
//!
//! Schema: `session.iterate.v1`. One row per `/v1/iterate` session.
//! Append-only. Best-effort posture: errors warn and the iterate
//! response always ships.
//!
//! See `golangLAKEHOUSE/docs/SESSION_LOG.md` for the full schema
//! reference + DuckDB query examples. This module produces rows
//! with `daemon: "gateway"`; the Go side produces `daemon:
//! "validatord"`. Operators who want a unified stream can point both
//! to the same path (the OS write-append is atomic for the row sizes
//! we produce) or query both files together via duckdb's `read_json`
//! glob support.
use serde::{Deserialize, Serialize};
use std::sync::Arc;
use tokio::sync::Mutex;
pub const SESSION_RECORD_SCHEMA: &str = "session.iterate.v1";
/// One row in coordinator_sessions.jsonl. Field names are the on-wire
/// names — must stay byte-equal to the Go side's
/// `validator.SessionRecord` (proven by the cross-runtime parity
/// probe at golangLAKEHOUSE/scripts/cutover/parity/).
// Deserialize is supported so the parity helper binary can round-trip
// fixture inputs through serde without hand-rolling a parser. Production
// emit path uses Serialize only; SessionRecord rows are written by the
// gateway and consumed by DuckDB / external tooling, never re-read by us.
#[derive(Serialize, Deserialize)]
pub struct SessionRecord {
pub schema: String,
pub session_id: String,
pub timestamp: String,
pub daemon: String,
pub kind: String,
pub model: String,
pub provider: String,
pub prompt: String,
pub iterations: u32,
pub max_iterations: u32,
pub final_verdict: String, // "accepted" | "max_iter_exhausted" | "infra_error"
pub attempts: Vec<SessionAttemptRecord>,
#[serde(skip_serializing_if = "Option::is_none")]
pub artifact: Option<serde_json::Value>,
#[serde(skip_serializing_if = "Option::is_none")]
pub grounded_in_roster: Option<bool>,
pub duration_ms: u64,
}
#[derive(Serialize, Deserialize)]
pub struct SessionAttemptRecord {
pub iteration: u32,
pub verdict_kind: String, // "no_json" | "validation_failed" | "accepted" | "infra_error"
#[serde(skip_serializing_if = "Option::is_none")]
pub error: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub span_id: Option<String>,
}
/// Append-only writer. Cloneable handle — internal state is Arc'd so
/// V1State can keep its own clone and per-request clones are cheap.
#[derive(Clone)]
pub struct SessionLogger {
inner: Arc<Inner>,
}
struct Inner {
path: String,
/// tokio::Mutex (not std) because we hold it across the async
/// fs write. Contention is low (one row per /v1/iterate session).
mu: Mutex<()>,
}
impl SessionLogger {
/// Construct a logger writing to `path`. Empty path → None
/// (skip the wiring in the iterate handler entirely).
pub fn from_path(path: &str) -> Option<Self> {
if path.is_empty() {
return None;
}
Some(Self {
inner: Arc::new(Inner {
path: path.to_string(),
mu: Mutex::new(()),
}),
})
}
/// Append one record. Best-effort: failures land in `tracing::warn!`
/// and the caller sees Ok(()) — observability is a witness, never
/// a gate. Returns Err only on impossible cases the type system
/// can't rule out (here: serde_json::to_string failing on a
/// well-formed struct, which shouldn't happen).
pub async fn append(&self, rec: SessionRecord) {
let body = match serde_json::to_string(&rec) {
Ok(s) => s,
Err(e) => {
tracing::warn!(target: "v1.session_log", "marshal: {e}");
return;
}
};
let _guard = self.inner.mu.lock().await;
if let Err(e) = self.write(&body).await {
tracing::warn!(target: "v1.session_log", "write {}: {e}", self.inner.path);
}
}
async fn write(&self, body: &str) -> std::io::Result<()> {
use tokio::fs::OpenOptions;
use tokio::io::AsyncWriteExt;
// Lazy mkdir on first write so a not-yet-mounted volume at
// startup doesn't kill the daemon.
if let Some(parent) = std::path::Path::new(&self.inner.path).parent() {
if !parent.as_os_str().is_empty() {
tokio::fs::create_dir_all(parent).await?;
}
}
let mut f = OpenOptions::new()
.append(true)
.create(true)
.open(&self.inner.path)
.await?;
f.write_all(body.as_bytes()).await?;
f.write_all(b"\n").await?;
Ok(())
}
}
/// Best-effort UTF-8 char truncation. Matches Go's `trim` helper so
/// rows produced by either runtime cap fields at the same boundaries.
pub fn truncate(s: &str, n: usize) -> String {
s.chars().take(n).collect()
}
#[cfg(test)]
mod tests {
use super::*;
use std::path::PathBuf;
use tokio::fs;
fn fixture_record(session_id: &str) -> SessionRecord {
SessionRecord {
schema: SESSION_RECORD_SCHEMA.to_string(),
session_id: session_id.to_string(),
timestamp: "2026-05-02T08:00:00Z".to_string(),
daemon: "gateway".to_string(),
kind: "fill".to_string(),
model: "qwen3.5:latest".to_string(),
provider: "ollama".to_string(),
prompt: "produce a fill artifact".to_string(),
iterations: 1,
max_iterations: 3,
final_verdict: "accepted".to_string(),
attempts: vec![SessionAttemptRecord {
iteration: 0,
verdict_kind: "accepted".to_string(),
error: None,
span_id: Some("span-0".to_string()),
}],
artifact: Some(serde_json::json!({"fills":[{"candidate_id":"W-1"}]})),
grounded_in_roster: Some(true),
duration_ms: 50,
}
}
#[tokio::test]
async fn from_path_empty_returns_none() {
assert!(SessionLogger::from_path("").is_none());
}
#[tokio::test]
async fn append_writes_jsonl_row_with_schema_field() {
let dir = tempdir();
let path = dir.join("sessions.jsonl");
let path_str = path.to_string_lossy().to_string();
let logger = SessionLogger::from_path(&path_str).unwrap();
logger.append(fixture_record("trace-a")).await;
let body = fs::read_to_string(&path).await.unwrap();
assert!(body.contains("\"schema\":\"session.iterate.v1\""));
assert!(body.contains("\"session_id\":\"trace-a\""));
assert!(body.contains("\"grounded_in_roster\":true"));
assert!(body.ends_with('\n'));
}
#[tokio::test]
async fn append_concurrent_safe() {
let dir = tempdir();
let path = dir.join("sessions.jsonl");
let path_str = path.to_string_lossy().to_string();
let logger = SessionLogger::from_path(&path_str).unwrap();
let n = 32;
let mut handles = Vec::with_capacity(n);
for i in 0..n {
let l = logger.clone();
handles.push(tokio::spawn(async move {
l.append(fixture_record(&format!("trace-{i}"))).await;
}));
}
for h in handles {
h.await.unwrap();
}
let body = fs::read_to_string(&path).await.unwrap();
let lines: Vec<_> = body.lines().filter(|l| !l.is_empty()).collect();
assert_eq!(lines.len(), n, "expected {n} rows, got {}", lines.len());
// Every row must round-trip through serde — a torn write
// would surface as a parse error.
for line in lines {
let _: serde_json::Value = serde_json::from_str(line).expect("valid json per row");
}
}
fn tempdir() -> PathBuf {
// Per-test unique path so prior runs don't pollute the next.
// The static counter increments across the whole test binary,
// so back-to-back tests in the same module get distinct dirs.
static COUNTER: std::sync::atomic::AtomicU64 = std::sync::atomic::AtomicU64::new(0);
let n = COUNTER.fetch_add(1, std::sync::atomic::Ordering::Relaxed);
let p = std::env::temp_dir().join(format!(
"session_log_test_{}_{}_{}",
std::process::id(),
chrono::Utc::now().timestamp_nanos_opt().unwrap_or(0),
n,
));
std::fs::create_dir_all(&p).unwrap();
p
}
}

20
crates/lance-bench/src/main.rs
View File

@ -456,6 +456,26 @@ async fn build_lance_vector_index(path: &str, _dims: usize) -> Result<()> {
.await .await
.context("create_index")?; .context("create_index")?;
// Also build the scalar btree on doc_id. This bench's
// measure_random_access_lance uses take(row_position) which doesn't
// need the btree, but the dataset this bench writes is also queried
// downstream by /vectors/lance/doc/<name>/<doc_id> (the production
// lookup path) — without this index that path falls back to a full
// table scan. Cheap to build (~1.2s on 10M rows) and matches the
// gateway's lance_migrate handler behavior so bench-produced datasets
// are immediately production-shape.
use lance_index::scalar::ScalarIndexParams;
dataset
.create_index(
&["doc_id"],
IndexType::Scalar,
Some("doc_id_btree".into()),
&ScalarIndexParams::default(),
true,
)
.await
.context("create_index doc_id btree")?;
Ok(()) Ok(())
} }

23
crates/shared/src/config.rs
View File

@ -62,6 +62,15 @@ pub struct GatewayConfig {
pub host: String, pub host: String,
#[serde(default = "default_gateway_port")] #[serde(default = "default_gateway_port")]
pub port: u16, pub port: u16,
/// Coordinator session JSONL output path. One row per
/// `/v1/iterate` session, schema=`session.iterate.v1`. Empty =
/// disabled. Cross-runtime parity with the Go side's
/// `[validatord].session_log_path` (added 2026-05-02). Default
/// empty so existing deployments aren't perturbed; production
/// sets `/var/lib/lakehouse/gateway/sessions.jsonl`. See
/// `golangLAKEHOUSE/docs/SESSION_LOG.md` for query examples.
#[serde(default)]
pub session_log_path: String,
} }
#[derive(Debug, Clone, Deserialize)] #[derive(Debug, Clone, Deserialize)]
@ -149,7 +158,13 @@ fn default_gateway_port() -> u16 { 3100 }
fn default_storage_root() -> String { "./data".to_string() } fn default_storage_root() -> String { "./data".to_string() }
fn default_profile_root() -> String { "./data/_profiles".to_string() } fn default_profile_root() -> String { "./data/_profiles".to_string() }
fn default_manifest_prefix() -> String { "_catalog/manifests".to_string() } fn default_manifest_prefix() -> String { "_catalog/manifests".to_string() }
fn default_sidecar_url() -> String { "http://localhost:3200".to_string() } // Post-2026-05-02: AiClient talks directly to Ollama; the Python
// sidecar's hot-path role was retired. The config field name
// `[sidecar].url` is preserved for migration compatibility (operators
// with existing TOMLs don't need to rename anything), but the value
// now points at Ollama. Lab UI / pipeline_lab Python remains as a
// dev-only tool; not on this URL.
fn default_sidecar_url() -> String { "http://localhost:11434".to_string() }
fn default_embed_model() -> String { "nomic-embed-text".to_string() } fn default_embed_model() -> String { "nomic-embed-text".to_string() }
fn default_gen_model() -> String { "qwen2.5".to_string() } fn default_gen_model() -> String { "qwen2.5".to_string() }
fn default_rerank_model() -> String { "qwen2.5".to_string() } fn default_rerank_model() -> String { "qwen2.5".to_string() }
@ -184,7 +199,11 @@ impl Config {
impl Default for Config { impl Default for Config {
fn default() -> Self { fn default() -> Self {
Self { Self {
gateway: GatewayConfig { host: default_host(), port: default_gateway_port() }, gateway: GatewayConfig {
host: default_host(),
port: default_gateway_port(),
session_log_path: String::new(),
},
storage: StorageConfig { storage: StorageConfig {
root: default_storage_root(), root: default_storage_root(),
profile_root: default_profile_root(), profile_root: default_profile_root(),

207
crates/vectord-lance/src/lib.rs
View File

@ -603,3 +603,210 @@ fn row_from_batch(batch: &RecordBatch, row: usize) -> Result<Row, String> {
Ok(Row { doc_id, chunk_text, vector: v, source, chunk_idx }) Ok(Row { doc_id, chunk_text, vector: v, source, chunk_idx })
} }
// =================== Tests ===================
//
// All tests run against a temp directory — never the production
// data/lance/ tree. Lance reads/writes are async + filesystem-bound,
// so we use #[tokio::test]. Each test uses a unique per-pid + per-
// nanosecond temp dir so concurrent runs don't collide and a re-run
// of a single test doesn't see prior state.
//
// Surfaced 2026-05-02 audit: vectord-lance had ZERO tests despite
// being on the live HTTP path. These are the load-bearing locks for
// the public API contract.
#[cfg(test)]
mod tests {
use super::*;
fn temp_path(label: &str) -> String {
// Per-process atomic counter — guarantees uniqueness regardless
// of clock resolution or test scheduling. Combined with pid, the
// result is unique within and across processes for any practical
// test workload. Nanosecond timestamps were not enough on their
// own: opus WARN at lib.rs:622 from the 2026-05-02 scrum noted
// that under tokio scheduling, multiple tests in the same cargo
// process can hit the same nanos bucket.
use std::sync::atomic::{AtomicU64, Ordering};
static COUNTER: AtomicU64 = AtomicU64::new(0);
let seq = COUNTER.fetch_add(1, Ordering::Relaxed);
let pid = std::process::id();
let nanos = std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.map(|d| d.subsec_nanos())
.unwrap_or(0);
std::env::temp_dir()
.join(format!("vlance_test_{label}_{pid}_{nanos}_{seq}"))
.to_string_lossy()
.to_string()
}
/// Build a minimal in-memory Parquet file matching vectord's
/// binary-blob schema. Used as input to migrate_from_parquet_bytes.
fn synth_parquet_bytes(n_rows: usize, dims: usize) -> Vec<u8> {
use parquet::arrow::ArrowWriter;
use std::io::Cursor;
let schema = Arc::new(Schema::new(vec![
Field::new("source", DataType::Utf8, true),
Field::new("doc_id", DataType::Utf8, false),
Field::new("chunk_idx", DataType::Int32, true),
Field::new("chunk_text", DataType::Utf8, true),
Field::new("vector", DataType::Binary, false),
]));
let sources: Vec<Option<&str>> = (0..n_rows).map(|_| Some("test")).collect();
let doc_ids: Vec<String> = (0..n_rows).map(|i| format!("DOC-{i:04}")).collect();
let chunk_idxs: Vec<Option<i32>> = (0..n_rows).map(|i| Some(i as i32)).collect();
let chunk_texts: Vec<String> = (0..n_rows).map(|i| format!("synth chunk {i}")).collect();
let vectors: Vec<Vec<u8>> = (0..n_rows).map(|i| {
let v: Vec<f32> = (0..dims).map(|j| (i * dims + j) as f32 * 0.01).collect();
let mut bytes = Vec::with_capacity(dims * 4);
for f in v { bytes.extend_from_slice(&f.to_le_bytes()); }
bytes
}).collect();
let batch = RecordBatch::try_new(schema.clone(), vec![
Arc::new(StringArray::from(sources)),
Arc::new(StringArray::from(doc_ids)),
Arc::new(Int32Array::from(chunk_idxs)),
Arc::new(StringArray::from(chunk_texts)),
Arc::new(BinaryArray::from(vectors.iter().map(|v| v.as_slice()).collect::<Vec<_>>())),
]).expect("synth parquet batch");
let mut buf = Cursor::new(Vec::new());
let mut writer = ArrowWriter::try_new(&mut buf, schema, None).expect("arrow writer");
writer.write(&batch).expect("write batch");
writer.close().expect("close writer");
buf.into_inner()
}
#[tokio::test]
async fn fresh_store_reports_no_state() {
let path = temp_path("fresh");
let store = LanceVectorStore::new(path.clone());
assert_eq!(store.path(), path);
assert_eq!(store.count().await.unwrap_or(0), 0);
assert!(!store.has_vector_index().await.unwrap_or(true));
}
#[tokio::test]
async fn migrate_then_count_and_fetch() {
let path = temp_path("migrate_fetch");
let store = LanceVectorStore::new(path.clone());
let bytes = synth_parquet_bytes(8, 4);
let stats = store.migrate_from_parquet_bytes(&bytes).await.expect("migrate");
assert_eq!(stats.rows_written, 8);
assert_eq!(stats.dimensions, 4);
assert!(stats.disk_bytes > 0, "lance dataset should occupy disk");
assert_eq!(store.count().await.unwrap(), 8);
let row = store.get_by_doc_id("DOC-0003").await
.expect("get_by_doc_id Ok").expect("DOC-0003 exists");
assert_eq!(row.doc_id, "DOC-0003");
assert_eq!(row.chunk_text, "synth chunk 3");
assert_eq!(row.vector.len(), 4);
let _ = std::fs::remove_dir_all(&path);
}
/// Load-bearing contract: get_by_doc_id distinguishes "dataset
/// missing" (Err) from "id missing" (Ok(None)) so the HTTP
/// handler can return 404 without inspecting error strings.
#[tokio::test]
async fn get_by_doc_id_missing_returns_none() {
let path = temp_path("missing_id");
let store = LanceVectorStore::new(path.clone());
store.migrate_from_parquet_bytes(&synth_parquet_bytes(4, 4)).await.expect("migrate");
let row = store.get_by_doc_id("DOC-NEVER-EXISTS").await.expect("Ok");
assert!(row.is_none(), "missing id must return Ok(None), not Err");
let _ = std::fs::remove_dir_all(&path);
}
/// Verifies the load-bearing structural-difference claim of
/// ADR-019: Lance appends without rewriting the whole file. Row
/// count grows; new rows are fetchable by their doc_ids.
#[tokio::test]
async fn append_grows_count_and_new_rows_fetchable() {
let path = temp_path("append");
let store = LanceVectorStore::new(path.clone());
store.migrate_from_parquet_bytes(&synth_parquet_bytes(4, 4)).await.expect("migrate");
assert_eq!(store.count().await.unwrap(), 4);
let stats = store.append(
Some("appended".into()),
vec!["NEW-A".into(), "NEW-B".into()],
vec![0, 0],
vec!["new chunk a".into(), "new chunk b".into()],
vec![vec![0.1, 0.2, 0.3, 0.4], vec![0.5, 0.6, 0.7, 0.8]],
).await.expect("append");
assert_eq!(stats.rows_appended, 2);
assert_eq!(store.count().await.unwrap(), 6);
let new_a = store.get_by_doc_id("NEW-A").await.unwrap().expect("NEW-A");
assert_eq!(new_a.chunk_text, "new chunk a");
assert_eq!(new_a.source.as_deref(), Some("appended"));
let _ = std::fs::remove_dir_all(&path);
}
/// Without this guard a dim-mismatch row would land on disk and
/// silently break search at query time.
#[tokio::test]
async fn append_dim_mismatch_errors() {
let path = temp_path("dim_mismatch");
let store = LanceVectorStore::new(path.clone());
store.migrate_from_parquet_bytes(&synth_parquet_bytes(4, 4)).await.expect("migrate");
let err = store.append(
None, vec!["X".into(), "Y".into()], vec![0, 0],
vec!["a".into(), "b".into()],
vec![vec![1.0, 2.0, 3.0, 4.0], vec![1.0, 2.0]],
).await;
assert!(err.is_err(), "dim mismatch must error");
let msg = err.unwrap_err();
assert!(msg.contains("dim") || msg.contains("expected"),
"error must mention the dimension problem; got: {msg}");
let _ = std::fs::remove_dir_all(&path);
}
/// Search round-trip: query the exact vector for one row, top-1
/// must be that row. Verifies the search path works on small
/// datasets where IVF training would normally be skipped.
#[tokio::test]
async fn search_returns_nearest() {
let path = temp_path("search");
let store = LanceVectorStore::new(path.clone());
store.migrate_from_parquet_bytes(&synth_parquet_bytes(8, 4)).await.expect("migrate");
let target: Vec<f32> = (0..4).map(|j| (5 * 4 + j) as f32 * 0.01).collect();
let hits = store.search(&target, 3, None, None).await.expect("search");
assert!(!hits.is_empty(), "search must return at least 1 hit");
assert_eq!(hits[0].doc_id, "DOC-0005",
"exact-vector match should be top-1; got {hits:?}");
let _ = std::fs::remove_dir_all(&path);
}
/// stats() summarizes the dataset state in one call. Locks the
/// field shape so downstream consumers don't break on a rename.
#[tokio::test]
async fn stats_reports_post_migrate_state() {
let path = temp_path("stats");
let store = LanceVectorStore::new(path.clone());
store.migrate_from_parquet_bytes(&synth_parquet_bytes(5, 4)).await.expect("migrate");
let s = store.stats().await.expect("stats");
assert_eq!(s.rows, 5);
assert!(s.disk_bytes > 0);
assert!(!s.has_vector_index, "no vector index built yet");
let _ = std::fs::remove_dir_all(&path);
}
}

10
crates/vectord/src/pathway_memory.rs
View File

@ -925,7 +925,7 @@ mod tests {
reject_reason: None, reject_reason: None,
}]; }];
let mut trace = PathwayTrace { let mut trace = PathwayTrace {
pathway_id, pathway_id: pathway_id.clone(),
task_class: "scrum_review".into(), task_class: "scrum_review".into(),
file_path: format!("crates/{id_tag}/src/x.rs"), file_path: format!("crates/{id_tag}/src/x.rs"),
signal_class: Some("CONVERGING".into()), signal_class: Some("CONVERGING".into()),
@ -954,6 +954,14 @@ mod tests {
replay_count: replays, replay_count: replays,
replays_succeeded: succ, replays_succeeded: succ,
retired: false, retired: false,
// Versioning fields added by Mem0 wave (commit 6ac7f61) — defaults
// mirror "this trace is the live head with no parent/successor".
trace_uid: format!("test-{pathway_id}"),
version: 1,
parent_trace_uid: None,
superseded_at: None,
superseded_by_trace_uid: None,
retirement_reason: None,
}; };
trace.pathway_vec = build_pathway_vec(&trace); trace.pathway_vec = build_pathway_vec(&trace);
trace trace

8
crates/vectord/src/rag.rs
View File

@ -163,7 +163,11 @@ pub async fn query(
// production caller of the Phase 21 primitives — see audit finding // production caller of the Phase 21 primitives — see audit finding
// "Phase 21 Rust primitives are wired but not CALLED by any // "Phase 21 Rust primitives are wired but not CALLED by any
// production surface" from 2026-04-21. // production surface" from 2026-04-21.
let mut cont_opts = ContinuableOpts::new("qwen2.5:latest"); // 2026-04-30 model bump: qwen2.5:latest → qwen3.5:latest to match
// the small-model-pipeline local-tier default. Same JSON-clean
// property, more capacity. think=Some(false) preserved — RAG hot
// path doesn't need reasoning traces; direct answers only.
let mut cont_opts = ContinuableOpts::new("qwen3.5:latest");
cont_opts.max_tokens = Some(512); cont_opts.max_tokens = Some(512);
cont_opts.temperature = Some(0.2); cont_opts.temperature = Some(0.2);
cont_opts.shape = ResponseShape::Text; cont_opts.shape = ResponseShape::Text;
@ -176,7 +180,7 @@ pub async fn query(
// echoes whatever Ollama loaded). Use the configured tier model // echoes whatever Ollama loaded). Use the configured tier model
// for now; if RAG needs to report the actual resolved model, // for now; if RAG needs to report the actual resolved model,
// the runner can add a post-call ps probe later. // the runner can add a post-call ps probe later.
model: "qwen2.5:latest".to_string(), model: "qwen3.5:latest".to_string(),
sources: results, sources: results,
tokens_generated: None, tokens_generated: None,
}) })

341
crates/vectord/src/service.rs
View File

@ -1855,10 +1855,10 @@ async fn lance_migrate(
.map_err(|e| (StatusCode::NOT_FOUND, format!("read parquet: {e}")))?; .map_err(|e| (StatusCode::NOT_FOUND, format!("read parquet: {e}")))?;
let lance_store = state.lance.store_for_new(&index_name, &bucket).await let lance_store = state.lance.store_for_new(&index_name, &bucket).await
.map_err(|e| (StatusCode::BAD_REQUEST, e))?; .map_err(|e| sanitize_lance_err(e, &index_name))?;
let stats = lance_store.migrate_from_parquet_bytes(&bytes).await let stats = lance_store.migrate_from_parquet_bytes(&bytes).await
.map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e))?; .map_err(|e| sanitize_lance_err(e, &index_name))?;
tracing::info!( tracing::info!(
"lance migrate '{}': {} rows, {}d, {} bytes on disk, {:.2}s", "lance migrate '{}': {} rows, {}d, {} bytes on disk, {:.2}s",
@ -1866,11 +1866,40 @@ async fn lance_migrate(
stats.disk_bytes, stats.duration_secs, stats.disk_bytes, stats.duration_secs,
); );
// Auto-build the doc_id btree. The scalar index is what makes
// get_doc_by_id O(log n) instead of a full table scan; ADR-019
// calls this out as the load-bearing feature for hybrid lookup.
// Verified 2026-05-02: skipping this on a 10M-row dataset turns
// ~5ms doc-fetch into ~100ms (full scan over 35GB). Cheap to
// build (~1.2s on 10M, +269MB on disk) and only runs once per
// dataset since `has_scalar_index` short-circuits subsequent calls.
let scalar_stats = if !lance_store.has_scalar_index("doc_id").await.unwrap_or(false) {
match lance_store.build_scalar_index("doc_id").await {
Ok(s) => {
tracing::info!(
"lance migrate '{}': doc_id btree built in {:.2}s (+{} bytes)",
index_name, s.build_time_secs, s.disk_bytes_added,
);
Some(s)
}
Err(e) => {
// Don't fail the whole migrate over a missing btree —
// the dataset is still queryable, just slowly. Log it
// so it's debuggable.
tracing::warn!("lance migrate '{}': doc_id btree build failed (will fall back to scan): {e}", index_name);
None
}
}
} else {
None
};
Ok::<_, (StatusCode, String)>(Json(serde_json::json!({ Ok::<_, (StatusCode, String)>(Json(serde_json::json!({
"index_name": index_name, "index_name": index_name,
"bucket": bucket, "bucket": bucket,
"lance_path": lance_store.path(), "lance_path": lance_store.path(),
"stats": stats, "stats": stats,
"scalar_index": scalar_stats,
}))) })))
} }
@ -1888,6 +1917,300 @@ fn default_partitions() -> u32 { 316 } // ≈√100K — sane for the referenc
fn default_bits() -> u32 { 8 } fn default_bits() -> u32 { 8 }
fn default_subvectors() -> u32 { 48 } // 768/48 = 16 dims per subvector fn default_subvectors() -> u32 { 48 } // 768/48 = 16 dims per subvector
/// Sanitize a Lance backend error before returning it to the HTTP
/// caller. Two responsibilities:
///
/// 1. Map "dataset not found" patterns to HTTP 404 instead of 500.
/// A missing index isn't an internal failure — it's a resource
/// lookup miss, and the response code should reflect that.
/// 2. Strip server-side filesystem paths and Rust crate registry
/// paths (`/root/.cargo/registry/src/index.crates.io-...`) from
/// the message body. An attacker probing the surface shouldn't
/// learn the server's directory layout or our exact dep versions.
///
/// Surfaced 2026-05-02 by the Lance backend audit: missing-index
/// search returned 500 + leaked the lakehouse data path AND the
/// .cargo/registry path with crate versions.
fn sanitize_lance_err(err: String, index_name: &str) -> (StatusCode, String) {
// 404 detection — narrowed across two 2026-05-02→03 scrum waves.
// First wave (opus WARN service.rs:1908): the original `lower.contains
// ("not found")` was too broad — caught "column not found" /
// "field not found in schema" which are real 500s. Second wave (opus
// WARN service.rs:1949): the looser `mentions_path_missing` branch I
// added would 404 on a registry-file error like "/root/.cargo/.../x.rs:
// no such file or directory" because it triggers without dataset
// context. Drop the standalone path-missing branch; require dataset
// context AND a missing-shape phrase. Lance's actual error format
// ("Dataset at path X was not found") satisfies this.
let lower = err.to_lowercase();
let mentions_dataset = lower.contains("dataset");
let lance_dataset_missing = mentions_dataset && (
lower.contains("not found") || lower.contains("does not exist")
);
// Excluded shapes — these contain "not found" but are real 500s.
let column_or_field = lower.contains("column not found")
|| lower.contains("field not found")
|| lower.contains("schema not found");
let is_not_found = lance_dataset_missing && !column_or_field;
if is_not_found {
return (StatusCode::NOT_FOUND, format!("lance dataset not found: {index_name}"));
}
// Path redaction — replace path-shaped substrings with [REDACTED]
// rather than truncating, per opus BLOCK at service.rs:1914 from the
// 2026-05-02 scrum. The previous `err.split("/home/").next()` returned
// Some("") when the error string STARTED with "/home/", erasing the
// entire message and falling back to a generic "lance backend error"
// that lost all real error context. Replacing keeps the structural
// error (the "what failed") while stripping the location.
let cleaned = redact_paths(&err)
.trim_end_matches([',', ' ', '\n', '\t'])
.to_string();
let msg = if cleaned.is_empty() {
format!("lance backend error on {index_name}")
} else {
cleaned
};
(StatusCode::INTERNAL_SERVER_ERROR, msg)
}
/// Replace absolute-path substrings (under known leak-prone roots) with
/// "[REDACTED]". Walks the input once, identifying path-shaped runs that
/// start with one of the configured prefixes and continue until a
/// path-terminating character (whitespace, quote, comma, paren, EOL).
///
/// Linear time, no regex dep. Catches multi-occurrence cases that
/// `String::split(p).next()` lost. The path-redaction surface intentionally
/// includes /var, /tmp, /etc, /usr, /opt in addition to /home and
/// /root/.cargo because Lance/Arrow errors surface system paths in
/// addition to project paths.
fn redact_paths(s: &str) -> String {
// Two prefix sets:
// - ABSOLUTE: paths starting with '/' (always safe to redact)
// - RELATIVE: same path bodies but without leading '/' (Lance occasionally
// strips the leading slash when echoing dataset paths back, observed
// live 2026-05-02 — "Dataset at path home/profit/lakehouse/data/lance/x
// was not found"). Match these only when preceded by a non-alpha char
// (start of string, space, colon, etc.) so we don't redact innocent
// tokens like "homecoming" or "etcetera".
const ABSOLUTE: &[&str] = &[
"/root/.cargo", "/home", "/var", "/tmp", "/etc", "/usr", "/opt",
];
const RELATIVE: &[&str] = &[
"root/.cargo", "home/", "var/", "tmp/", "etc/", "usr/", "opt/",
];
fn is_path_term(b: u8) -> bool {
matches!(b, b' ' | b'\t' | b'\n' | b'\r' | b'"' | b'\'' | b',' | b')' | b']' | b'}')
}
fn is_word_boundary_before(bytes: &[u8], i: usize) -> bool {
// True if byte at i-1 is non-alphanumeric (so this position starts
// a fresh token). True at start-of-input.
if i == 0 { return true; }
let b = bytes[i - 1];
!(b.is_ascii_alphanumeric() || b == b'_' || b == b'.' || b == b'-')
}
// Walk by byte index but slice the original &str when emitting, never
// cast bytes to char (that would corrupt multi-byte UTF-8 — opus WARN
// at service.rs:2018 from the 2026-05-03 re-scrum). Path prefixes are
// pure ASCII so byte-level matching is sound; what matters is that
// we emit non-matched stretches as &str slices, not byte-by-byte.
let bytes = s.as_bytes();
let mut out = String::with_capacity(s.len());
let mut i = 0;
let mut copy_start = 0usize; // start of an in-progress unmatched run
while i < bytes.len() {
let mut matched_len: Option<usize> = None;
// Try absolute prefixes first (always allowed).
for p in ABSOLUTE {
let pb = p.as_bytes();
if i + pb.len() <= bytes.len() && &bytes[i..i + pb.len()] == pb {
let after = i + pb.len();
if after == bytes.len() || bytes[after] == b'/' || is_path_term(bytes[after]) {
matched_len = Some(pb.len());
break;
}
}
}
// Then relative prefixes — only at word boundaries.
if matched_len.is_none() && is_word_boundary_before(bytes, i) {
for p in RELATIVE {
let pb = p.as_bytes();
if i + pb.len() <= bytes.len() && &bytes[i..i + pb.len()] == pb {
matched_len = Some(pb.len());
break;
}
}
}
if let Some(prefix_len) = matched_len {
// Flush any pending unmatched run as a UTF-8-safe slice.
if copy_start < i {
out.push_str(&s[copy_start..i]);
}
out.push_str("[REDACTED]");
// Skip past the prefix and the path body (until terminator).
let mut j = i + prefix_len;
while j < bytes.len() && !is_path_term(bytes[j]) {
j += 1;
}
i = j;
copy_start = i;
} else {
// Advance one CHAR (not one byte) so multi-byte UTF-8 sequences
// stay intact in the eventual slice. Look up the next char
// boundary using the public API.
i += utf8_char_len(bytes, i);
}
}
if copy_start < bytes.len() {
out.push_str(&s[copy_start..]);
}
out
}
/// Length in bytes of the UTF-8 character starting at byte `i`. Bytes are
/// guaranteed to be a valid UTF-8 sequence start (callers ensure that).
fn utf8_char_len(bytes: &[u8], i: usize) -> usize {
let b = bytes[i];
if b < 0x80 { 1 }
else if b < 0xC0 { 1 } // continuation byte — defensive, shouldn't start here
else if b < 0xE0 { 2 }
else if b < 0xF0 { 3 }
else { 4 }
}
#[cfg(test)]
mod sanitize_tests {
use super::*;
#[test]
fn redact_path_at_offset_zero() {
// Regression: opus BLOCK 2026-05-02. Old impl returned Some("")
// when err started with "/home/", erasing the whole message.
let out = redact_paths("/home/profit/lakehouse/data/lance not a directory");
assert_eq!(out, "[REDACTED] not a directory");
}
#[test]
fn redact_keeps_pre_and_post_text() {
let out = redact_paths("failed to open /home/profit/lakehouse/data/x for read: ENOENT");
assert_eq!(out, "failed to open [REDACTED] for read: ENOENT");
}
#[test]
fn redact_multiple_paths() {
let out = redact_paths("at /root/.cargo/registry/src/index.crates.io-foo/lance-table-4.0.0/src/io/commit.rs:364:26 from /home/profit/lakehouse");
assert!(!out.contains("/root/.cargo"));
assert!(!out.contains("/home/"));
assert!(out.contains("[REDACTED]"));
}
#[test]
fn redact_preserves_quote_terminator() {
let out = redact_paths("{\"path\":\"/home/profit/x\",\"err\":\"bad\"}");
assert_eq!(out, "{\"path\":\"[REDACTED]\",\"err\":\"bad\"}");
}
#[test]
fn is_not_found_narrow_dataset_only() {
// Regression: opus WARN 2026-05-02. Old impl 404'd on any "not
// found" — including legitimate column/field-not-found 500s.
let (status, _) = sanitize_lance_err(
"column not found: vector".into(), "test_idx",
);
assert_eq!(status, StatusCode::INTERNAL_SERVER_ERROR);
let (status, _) = sanitize_lance_err(
"dataset not found at /home/profit/lakehouse/data/lance/missing".into(), "test_idx",
);
assert_eq!(status, StatusCode::NOT_FOUND);
}
#[test]
fn redact_does_not_match_prefix_substring() {
// /etcetera should NOT trigger /etc redaction.
let out = redact_paths("etcetera and /etcd");
assert_eq!(out, "etcetera and /etcd");
}
#[test]
fn redact_relative_paths_lance_emits() {
// 2026-05-02: live missing-index probe surfaced Lance error of the
// form "Dataset at path home/profit/lakehouse/data/lance/x was not
// found" — leading slash stripped. Need to redact the relative form
// when preceded by a word boundary.
let out = redact_paths("Dataset at path home/profit/lakehouse/data/lance/x was not found");
assert!(!out.contains("home/profit"), "should redact: {out}");
assert!(out.contains("Dataset at path"));
assert!(out.contains("was not found"));
}
#[test]
fn redact_does_not_eat_innocent_prefix_words() {
// "homecoming" must NOT trigger "home/" redaction. "Etcetera" must
// NOT trigger "etc/" redaction. The word-boundary guard handles this.
let out = redact_paths("homecoming etcetera vary tmpfile");
assert_eq!(out, "homecoming etcetera vary tmpfile");
}
#[test]
fn is_not_found_lance_actual_phrasing() {
// Lance's actual error format observed live: "Dataset at path X was
// not found: Not found: ...". Must 404, not 500.
let (status, _) = sanitize_lance_err(
"Dataset at path home/profit/lakehouse/data/lance/x was not found".into(),
"x",
);
assert_eq!(status, StatusCode::NOT_FOUND);
}
#[test]
fn is_not_found_excludes_column_field_schema() {
// Real 500s with the "not found" phrase that aren't dataset-missing.
for err in [
"column not found: vector",
"field not found in schema: doc_id",
"schema not found for dataset xyz",
] {
let (status, _) = sanitize_lance_err(err.into(), "test_idx");
assert_eq!(status, StatusCode::INTERNAL_SERVER_ERROR, "{err}");
}
}
#[test]
fn is_not_found_does_not_match_unrelated_path_missing() {
// Regression: opus WARN at service.rs:1949 from the 2026-05-03
// re-scrum. A registry-file error from inside a Lance internal
// module should NOT be coerced to 404 just because it contains
// "no such file or directory" — it's a real 500.
let (status, _) = sanitize_lance_err(
"/root/.cargo/registry/src/index.crates.io-foo/lance-table-4.0.0/src/io/commit.rs: no such file or directory".into(),
"test_idx",
);
assert_eq!(status, StatusCode::INTERNAL_SERVER_ERROR);
// (And the path is still redacted in the message.)
let (_, msg) = sanitize_lance_err(
"/root/.cargo/registry/src/lance-foo/x.rs: no such file or directory".into(),
"test_idx",
);
assert!(!msg.contains("/root/.cargo"), "path leak: {msg}");
}
#[test]
fn redact_preserves_multibyte_utf8() {
// Regression: opus WARN at service.rs:2018 from the 2026-05-03
// re-scrum. Old impl did `out.push(bytes[i] as char)` which
// corrupted multi-byte UTF-8 (e.g. a path containing user-supplied
// names with non-ASCII characters) into Latin-1 mojibake.
let input = "Failed to open /home/profit/工作/data — café not found";
let out = redact_paths(input);
// The path is redacted...
assert!(!out.contains("/home/profit"), "path leak: {out}");
// ...AND the multi-byte characters elsewhere are preserved verbatim.
assert!(out.contains("café"), "lost UTF-8: {out}");
assert!(out.contains("not found"), "lost trailing context: {out}");
}
}
/// Build the IVF_PQ index on the Lance dataset. /// Build the IVF_PQ index on the Lance dataset.
async fn lance_build_index( async fn lance_build_index(
State(state): State<VectorState>, State(state): State<VectorState>,
@ -1895,10 +2218,10 @@ async fn lance_build_index(
Json(req): Json<LanceIndexRequest>, Json(req): Json<LanceIndexRequest>,
) -> impl IntoResponse { ) -> impl IntoResponse {
let lance_store = state.lance.store_for(&index_name).await let lance_store = state.lance.store_for(&index_name).await
.map_err(|e| (StatusCode::BAD_REQUEST, e))?; .map_err(|e| sanitize_lance_err(e, &index_name))?;
match lance_store.build_index(req.num_partitions, req.num_bits, req.num_sub_vectors).await { match lance_store.build_index(req.num_partitions, req.num_bits, req.num_sub_vectors).await {
Ok(stats) => Ok(Json(stats)), Ok(stats) => Ok(Json(stats)),
Err(e) => Err((StatusCode::INTERNAL_SERVER_ERROR, e)), Err(e) => Err(sanitize_lance_err(e, &index_name)),
} }
} }
@ -1947,13 +2270,13 @@ async fn lance_search(
let qv: Vec<f32> = embed_resp.embeddings[0].iter().map(|&x| x as f32).collect(); let qv: Vec<f32> = embed_resp.embeddings[0].iter().map(|&x| x as f32).collect();
let lance_store = state.lance.store_for(&index_name).await let lance_store = state.lance.store_for(&index_name).await
.map_err(|e| (StatusCode::BAD_REQUEST, e))?; .map_err(|e| sanitize_lance_err(e, &index_name))?;
let t0 = std::time::Instant::now(); let t0 = std::time::Instant::now();
let nprobes = req.nprobes.or(Some(LANCE_DEFAULT_NPROBES)); let nprobes = req.nprobes.or(Some(LANCE_DEFAULT_NPROBES));
let refine = req.refine_factor.or(Some(LANCE_DEFAULT_REFINE_FACTOR)); let refine = req.refine_factor.or(Some(LANCE_DEFAULT_REFINE_FACTOR));
let hits = lance_store.search(&qv, req.top_k, nprobes, refine).await let hits = lance_store.search(&qv, req.top_k, nprobes, refine).await
.map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e))?; .map_err(|e| sanitize_lance_err(e, &index_name))?;
Ok(Json(serde_json::json!({ Ok(Json(serde_json::json!({
"index_name": index_name, "index_name": index_name,
@ -1971,7 +2294,7 @@ async fn lance_get_doc(
Path((index_name, doc_id)): Path<(String, String)>, Path((index_name, doc_id)): Path<(String, String)>,
) -> impl IntoResponse { ) -> impl IntoResponse {
let lance_store = state.lance.store_for(&index_name).await let lance_store = state.lance.store_for(&index_name).await
.map_err(|e| (StatusCode::BAD_REQUEST, e))?; .map_err(|e| sanitize_lance_err(e, &index_name))?;
let t0 = std::time::Instant::now(); let t0 = std::time::Instant::now();
match lance_store.get_by_doc_id(&doc_id).await { match lance_store.get_by_doc_id(&doc_id).await {
Ok(Some(row)) => Ok(Json(serde_json::json!({ Ok(Some(row)) => Ok(Json(serde_json::json!({
@ -1981,7 +2304,7 @@ async fn lance_get_doc(
"row": row, "row": row,
}))), }))),
Ok(None) => Err((StatusCode::NOT_FOUND, format!("doc_id not found: {doc_id}"))), Ok(None) => Err((StatusCode::NOT_FOUND, format!("doc_id not found: {doc_id}"))),
Err(e) => Err((StatusCode::INTERNAL_SERVER_ERROR, e)), Err(e) => Err(sanitize_lance_err(e, &index_name)),
} }
} }
@ -2013,7 +2336,7 @@ async fn lance_append(
return Err((StatusCode::BAD_REQUEST, "rows array is empty".into())); return Err((StatusCode::BAD_REQUEST, "rows array is empty".into()));
} }
let lance_store = state.lance.store_for(&index_name).await let lance_store = state.lance.store_for(&index_name).await
.map_err(|e| (StatusCode::BAD_REQUEST, e))?; .map_err(|e| sanitize_lance_err(e, &index_name))?;
let mut doc_ids = Vec::with_capacity(req.rows.len()); let mut doc_ids = Vec::with_capacity(req.rows.len());
let mut chunk_idxs = Vec::with_capacity(req.rows.len()); let mut chunk_idxs = Vec::with_capacity(req.rows.len());

42
data/_catalog/manifests/32ee74a0-59b4-4e5b-8edb-70c9347a4bf3.json
View File

@ -11,15 +11,51 @@
} }
], ],
"created_at": "2026-04-20T11:07:57.308050648Z", "created_at": "2026-04-20T11:07:57.308050648Z",
"updated_at": "2026-04-22T03:28:28.343843823Z", "updated_at": "2026-04-28T01:28:31.280305207Z",
"description": "", "description": "",
"owner": "", "owner": "",
"sensitivity": null, "sensitivity": null,
"columns": [], "columns": [
{
"name": "timestamp",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "operation",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "approach",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "result",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "context",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
}
],
"lineage": null, "lineage": null,
"freshness": null, "freshness": null,
"tags": [], "tags": [],
"row_count": null, "row_count": 2077,
"last_embedded_at": null, "last_embedded_at": null,
"embedding_stale_since": null, "embedding_stale_since": null,
"embedding_refresh_policy": null "embedding_refresh_policy": null

117
data/_catalog/manifests/564b00ae-cbf3-4efd-aa55-84cdb6d2b0b7.json
View File

@ -1,117 +0,0 @@
{
"id": "564b00ae-cbf3-4efd-aa55-84cdb6d2b0b7",
"name": "client_workerskjkk",
"schema_fingerprint": "cdfe85348885ddf329e5e6e9bf0e2c75c92d1a86fdb0fd3875ed46e3f93c4d82",
"objects": [
{
"bucket": "primary",
"key": "datasets/client_workerskjkk.parquet",
"size_bytes": 32201,
"created_at": "2026-04-21T00:49:04.623625149Z"
}
],
"created_at": "2026-04-21T00:49:04.623626738Z",
"updated_at": "2026-04-21T00:49:04.623901788Z",
"description": "",
"owner": "",
"sensitivity": "pii",
"columns": [
{
"name": "worker_id",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "name",
"data_type": "Utf8",
"sensitivity": "pii",
"description": "",
"is_pii": true
},
{
"name": "role",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "city",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "state",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "email",
"data_type": "Utf8",
"sensitivity": "pii",
"description": "",
"is_pii": true
},
{
"name": "phone",
"data_type": "Utf8",
"sensitivity": "pii",
"description": "",
"is_pii": true
},
{
"name": "skills",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "certifications",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "availability",
"data_type": "Float64",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "reliability",
"data_type": "Float64",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "archetype",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
}
],
"lineage": {
"source_system": "csv",
"source_file": "staffing_roster_sample.csv",
"ingest_job": "ingest-1776732544623",
"ingest_timestamp": "2026-04-21T00:49:04.623625149Z",
"parent_datasets": []
},
"freshness": null,
"tags": [],
"row_count": 180,
"last_embedded_at": null,
"embedding_stale_since": null,
"embedding_refresh_policy": null
}

1000
data/headshots/manifest.jsonl Normal file
View File

File diff suppressed because it is too large Load Diff

46
docs/ARCHITECTURE_COMPARISON.md Normal file
View File

@ -0,0 +1,46 @@
# Lakehouse: Rust vs Go architecture comparison
> **Source of truth lives in the golangLAKEHOUSE repo:**
> [`/home/profit/golangLAKEHOUSE/docs/ARCHITECTURE_COMPARISON.md`](file:///home/profit/golangLAKEHOUSE/docs/ARCHITECTURE_COMPARISON.md)
>
> J's living document — pulled from there into this repo's docs as
> a pointer so the comparison is reachable from either side.
## Why the source lives in golangLAKEHOUSE
The Go rewrite was the trigger for the comparison. The doc updates as
J ships fixes on either side, and most of the open backlog items
(materializer port, replay port, validators network surface) land in
the Go repo. Keeping the source there means PR auditing on Go
commits also catches doc drift.
## When to update from this side
If a fix lands in the Rust repo that changes a comparison value
(e.g. embed cache change, sidecar drop, new validator), update both:
1. The source at `/home/profit/golangLAKEHOUSE/docs/ARCHITECTURE_COMPARISON.md`
2. The change log section at the bottom of the same file
This file is a pointer — **do not put authoritative content here.**
Drift between two copies wastes the discipline.
## Quick links
- **Decisions tracker** — section near the top of the source file.
Lists actioned items + open backlog with LOC estimates.
- **Performance numbers** — Python dependency section. Updated each
time a load test is rerun.
- **Distillation porting status** — table of phase-by-phase port
state across runtimes.
- **Recommendation** — current working hypothesis on Go-primary vs
Rust-primary. Subject to change as fixes ship.
## Last known state
- **2026-05-01**: Rust embed cache shipped (`150cc3b`), 236× RPS gain.
- **2026-05-01**: Go validator port shipped (`b03521a`), production
safety net now on Go side.
- **Open**: Drop Rust Python sidecar (~200 LOC, universal-win).
- **Open**: Port Rust materializer to Go (~500-800 LOC, unblocks
Go-only end-to-end pipeline).

107
docs/PHASE_AUDIT_GUIDE.md Normal file
View File

@ -0,0 +1,107 @@
# Phase Audit Guidance for Claude Code
## Purpose
This document provides the proper workflow for auditing completed phases in the Lakehouse project.
## ⚠️ Important: Do NOT Skip Steps
Each phase requires BOTH:
1. PRD spec verification (check code exists)
2. Full SCRUM execution (6 commands)
## Proper Phase Audit Workflow
### Step 1: Read PRD Specification
For each phase, read the PRD to understand what's supposed to ship:
```bash
# Read from docs/PRD.md or docs/PHASES.md
cat docs/PHASES.md | grep -A20 "Phase N:"
```
### Step 2: Verify Code Exists
Check that each deliverable from the PRD spec has corresponding code:
```bash
# Example - check for specific implementations
grep -r "function_name" crates/*/src/
ls crates/*/src/*.rs
```
### Step 3: Run Full SCRUM (6 Commands)
In order, execute ALL of these for the phase's crates:
```bash
# 1. Build
cargo build -p <crate-name>
# 2. Test
cargo test -p <crate-name>
# 3. Clippy (if installed)
cargo clippy -p <crate-name> -- -D warnings
# 4. Format check
cargo fmt -p <crate-name> -- --check
# 5. Cargo check
cargo check -p <crate-name>
# 6. Doc check
cargo doc -p <crate-name> --no-deps
```
### Step 4: Fix Issues
If any SCRUM command fails:
- Fix the code
- Re-run the failing command
- Re-run ALL 6 commands to verify
### Step 5: Update Phase Documentation
Only mark as ✅ after ALL 6 SCRUM commands pass:
```markdown
## Phase N: [Name] ✅
- [x] spec item 1
- [x] spec item 2
- SCRUM: build ✅ test ✅ clippy ✅ fmt ✅ check ✅ doc ✅
```
## Current Phase Status
| Phase | Status | Notes |
|-------|--------|-------|
| 0 | ✅ | Bootstrap complete |
| 1 | ✅ | Storage + Catalog |
| 2 | ✅ | Query Engine |
| 3 | ✅ | AI Integration |
| 4 | ✅ | Frontend |
| 5 | ✅ | Hardening |
| 6-42 | ✅ | See docs/PHASES.md |
## Notes from Previous Session
- Clippy and rustfmt are NOT installed on this system
- Run `rustup component add clippy rustfmt` to install
- Some crates have 0 unit tests (expected for service crates)
- 28 warnings remain in unused code paths (ui/vectord)
## Key Files
- `docs/PHASES.md` - Phase tracker with checkboxes
- `docs/PRD.md` - Full product requirements
- `docs/CONTROL_PLANE_PRD.md` - Phases 38+ specifications
- `crates/*/` - All crate implementations
## Quick Reference
```bash
# Full workspace SCRUM
cargo build --workspace
cargo test --workspace
# (clippy if installed)
cargo fmt -- --check
cargo check --workspace
cargo doc --no-deps
# Per-crate
cargo build -p <crate>
cargo test -p <crate>
cargo check -p <crate>
```

31
lakehouse.toml
View File

@ -3,6 +3,15 @@
[gateway] [gateway]
host = "0.0.0.0" host = "0.0.0.0"
port = 3100 port = 3100
# Coordinator session JSONL — one row per /v1/iterate session for
# offline DuckDB analysis. Cross-runtime parity with the Go-side
# [validatord].session_log_path. Set to the SAME path Go validatord
# writes to so DuckDB queries see one unified longitudinal stream
# across both runtimes (rows are tagged daemon="gateway" vs
# daemon="validatord" so producers stay distinguishable). Append-write
# is atomic at the row sizes both runtimes produce — both daemons
# co-writing is safe.
session_log_path = "/tmp/lakehouse-validator/sessions.jsonl"
[storage] [storage]
root = "./data" root = "./data"
@ -44,12 +53,22 @@ manifest_prefix = "_catalog/manifests"
# max_rows_per_query = 10000 # max_rows_per_query = 10000
[sidecar] [sidecar]
url = "http://localhost:3200" # Post-2026-05-02: AiClient talks directly to Ollama; the Python
# sidecar's hot-path role (~120 LOC of pure Ollama wrappers) was
# retired. Field name kept for migration compat — value now points
# at Ollama on :11434. Lab UI + pipeline_lab Python remains as a
# dev-only tool, NOT on this URL.
url = "http://localhost:11434"
[ai] [ai]
embed_model = "nomic-embed-text" embed_model = "nomic-embed-text"
gen_model = "qwen2.5" # Local-tier defaults bumped 2026-04-30: qwen3.5:latest is the
rerank_model = "qwen2.5" # stronger local rung in the 5-loop substrate (per
# project_small_model_pipeline_vision.md). Same JSON-clean property
# as qwen2.5, more capacity. Ollama still serves both — bump back
# in this file if a workload regressed.
gen_model = "qwen3.5:latest"
rerank_model = "qwen3.5:latest"
[auth] [auth]
enabled = false enabled = false
@ -72,7 +91,9 @@ min_recall = 0.9 # never promote below this
max_trials_per_hour = 20 # hard budget cap max_trials_per_hour = 20 # hard budget cap
# Model roster — available for profile hot-swap # Model roster — available for profile hot-swap
# qwen3.5:latest: stronger local rung — JSON-clean, 8K+ context,
# default for gen_model and rerank_model
# qwen3: 8.2B, 40K context, thinking+tools, best for reasoning tasks # qwen3: 8.2B, 40K context, thinking+tools, best for reasoning tasks
# qwen2.5: 7B, 8K context, fast, good for SQL generation # qwen2.5: 7B, 8K context, fast — kept loaded for the 2026-04 era
# mistral: 7B, 8K context, good for general generation # comparison runs; new defaults use qwen3.5:latest
# nomic-embed-text: 137M, embedding-only, used by all profiles # nomic-embed-text: 137M, embedding-only, used by all profiles

426
mcp-server/console.html
View File

@ -51,9 +51,28 @@ details .body{padding-top:10px;font-size:12px;color:#8b949e}
.accent-b{border-left:3px solid #1f6feb} .accent-b{border-left:3px solid #1f6feb}
.accent-a{border-left:3px solid #bc8cff} .accent-a{border-left:3px solid #bc8cff}
.accent-w{border-left:3px solid #d29922} .accent-w{border-left:3px solid #d29922}
.accent-g{border-left:3px solid #3fb950}
.accent-r{border-left:3px solid #f85149}
.worker{display:flex;align-items:center;gap:10px;padding:8px 10px;background:#161b22;border-radius:6px;margin-bottom:4px;font-size:12px} .worker{display:flex;align-items:center;gap:10px;padding:8px 10px;background:#161b22;border-radius:6px;margin-bottom:4px;font-size:12px;border-left:3px solid #30363d}
.worker .av{width:28px;height:28px;border-radius:6px;background:#1a2744;display:flex;align-items:center;justify-content:center;font-weight:600;color:#e6edf3;font-size:10px;flex-shrink:0} .worker .av{width:32px;height:32px;border-radius:50%;background:#0d1117;border:1px solid #21262d;display:flex;align-items:center;justify-content:center;font-weight:600;color:#c9d1d9;font-size:11px;flex-shrink:0;letter-spacing:0.5px;overflow:hidden;position:relative}
.worker .av img{position:absolute;inset:0;width:100%;height:100%;object-fit:cover;display:block;
/* Softening — mirror of search.html. Pulls saturation + contrast off
the SDXL Turbo over-render so faces feel less "AI-generated".
If you tweak one, tweak the other. */
filter: saturate(0.86) contrast(0.93) brightness(1.02) blur(0.3px);
}
.worker[data-role-band="warehouse"]{border-left-color:#58a6ff}
.worker[data-role-band="production"]{border-left-color:#d29922}
.worker[data-role-band="trades"]{border-left-color:#bc8cff}
.worker[data-role-band="driver"]{border-left-color:#3fb950}
.worker[data-role-band="lead"]{border-left-color:#f0883e}
.role-pill{display:inline-block;font-size:9px;padding:1px 7px;border-radius:3px;background:#0d1117;color:#8b949e;margin-right:6px;font-weight:600;letter-spacing:0.4px;text-transform:uppercase;border-left:2px solid #30363d;vertical-align:1px}
.role-pill[data-rb="warehouse"]{border-left-color:#58a6ff;color:#79c0ff}
.role-pill[data-rb="production"]{border-left-color:#d29922;color:#e3b341}
.role-pill[data-rb="trades"]{border-left-color:#bc8cff;color:#d2a8ff}
.role-pill[data-rb="driver"]{border-left-color:#3fb950;color:#56d364}
.role-pill[data-rb="lead"]{border-left-color:#f0883e;color:#ffa657}
.worker .info{flex:1;min-width:0} .worker .info{flex:1;min-width:0}
.worker .nm{color:#e6edf3;font-weight:500} .worker .nm{color:#e6edf3;font-weight:500}
.worker .why{color:#545d68;font-size:11px;margin-top:1px} .worker .why{color:#545d68;font-size:11px;margin-top:1px}
@ -95,6 +114,7 @@ details .body{padding-top:10px;font-size:12px;color:#8b949e}
<nav> <nav>
<a href=".">Dashboard</a> <a href=".">Dashboard</a>
<a href="console" class="active">Walkthrough</a> <a href="console" class="active">Walkthrough</a>
<a href="profiler">Profiler</a>
<a href="proof">Architecture</a> <a href="proof">Architecture</a>
<a href="spec">Spec</a> <a href="spec">Spec</a>
<a href="onboard">Onboard</a> <a href="onboard">Onboard</a>
@ -147,11 +167,40 @@ details .body{padding-top:10px;font-size:12px;color:#8b949e}
<div class="chapter"> <div class="chapter">
<div class="num">Chapter 6</div> <div class="num">Chapter 6</div>
<h2>Try it yourself</h2> <h2>Three coordinators, three views of the same corpus</h2>
<div class="lede">Type any staffing question. The system picks the right search path (smart-parse, semantic discovery, analytics), shows what it understood, and returns ranked results with memory signal.</div> <div class="lede">Maria runs Chicago, Devon runs Indianapolis, Aisha runs Milwaukee. Same database, same playbooks — but the search results, the recurring-skill patterns, and the playbook context all reshape to whoever is acting. This is the per-staffer hot-swap index: the relevance gradient is unique to each person, and gets sharper the more they use it.</div>
<div id="ch6-staffers"><div class="loading">Loading staffer roster…</div></div>
</div>
<div class="chapter">
<div class="num">Chapter 7</div>
<h2>The hidden signal — public issuers in your contractor graph</h2>
<div class="lede">Every contractor in this corpus is also a forward indicator on the public equities they touch. Permit filings precede construction starts by ~45 days, staffing windows by ~30, revenue recognition by months. The associated-ticker network surfaces this signal <em>before</em> any 10-Q. Below: the top issuers attributable to the contractor activity in this view, with live prices.</div>
<div id="ch7-signal"><div class="loading">Computing the Building Activity Index…</div></div>
</div>
<div class="chapter">
<div class="num">Chapter 8</div>
<h2>When something breaks — triage in one shot</h2>
<div class="lede">A coordinator gets a text: "Marcus running late." Watch what the system does in 250 milliseconds: pulls Marcus's record, scores his attendance pattern, finds five same-role same-geo backfills sorted by responsiveness, and pre-writes the SMS to send to the client. This is the moment the AI becomes worth its weight.</div>
<div id="ch8-triage"><div class="loading">Running the triage scenario…</div></div>
</div>
<div class="chapter">
<div class="num">Chapter 9</div>
<h2>Try it yourself — every input below hits a different route</h2>
<div class="lede">Type any staffing question. The router picks the right path: smart-parse (zip code, headcount, role, state), semantic discovery, name lookup, late-worker triage, "what came in last night" temporal queries. Whatever you type, the system tells you what it understood and how it routed.</div>
<div class="try-box"> <div class="try-box">
<input type="text" id="try-q" placeholder="e.g. reliable forklift operators in Chicago with OSHA certs" onkeydown="if(event.key==='Enter')runTry()"> <input type="text" id="try-q" placeholder="e.g. 8 production workers near 60607 by next Friday" onkeydown="if(event.key==='Enter')runTry()">
<button id="try-btn" onclick="runTry()">Ask</button> <button id="try-btn" onclick="runTry()">Ask</button>
<div style="margin-top:10px;font-size:11px;color:#545d68;line-height:1.7">
Try one of these to see different routes fire:<br>
<a href="#" onclick="document.getElementById('try-q').value='8 production workers near 60607';runTry();return false">8 production workers near 60607</a> ·
<a href="#" onclick="document.getElementById('try-q').value='Marcus running late site 4422';runTry();return false">Marcus running late site 4422</a> ·
<a href="#" onclick="document.getElementById('try-q').value='Marcus';runTry();return false">Marcus</a> ·
<a href="#" onclick="document.getElementById('try-q').value='what came in last night';runTry();return false">what came in last night</a> ·
<a href="#" onclick="document.getElementById('try-q').value='reliable forklift operators with OSHA certs';runTry();return false">reliable forklift operators with OSHA certs</a>
</div>
<div id="try-out" style="margin-top:16px"></div> <div id="try-out" style="margin-top:16px"></div>
</div> </div>
</div> </div>
@ -167,6 +216,132 @@ var A=location.origin+P;
// DOM helpers — all dynamic content goes through these. No innerHTML // DOM helpers — all dynamic content goes through these. No innerHTML
// anywhere in the script; every API-derived string passes through // anywhere in the script; every API-derived string passes through
// textContent so no injection path regardless of upstream data. // textContent so no injection path regardless of upstream data.
// Role classification — mirrors search.html, no emojis. Maps role
// strings to a band+label used by the worker-card border + role pill.
var ROLE_BANDS = [
{ match: /forklift|warehouse|associate|material\s*handler|loader|loading|packag|shipping|logistics|inventory|sanitation|janit/i, band: 'warehouse', label: 'Warehouse' },
{ match: /production|assembl/i, band: 'production', label: 'Production' },
{ match: /welder|weld|electric|maint(enance)?\s*tech|cnc|machine\s*op|hvac|plumb|carpenter|mason/i, band: 'trades', label: 'Skilled Trade' },
{ match: /driver|truck|haul|cdl/i, band: 'driver', label: 'Driver' },
{ match: /line\s*lead|supervisor|foreman|coordinator/i, band: 'lead', label: 'Lead' },
{ match: /quality/i, band: 'production', label: 'Quality' },
];
function roleBand(role){
if(!role) return { band: 'warehouse', label: '' };
for (var i = 0; i < ROLE_BANDS.length; i++) {
if (ROLE_BANDS[i].match.test(role)) return ROLE_BANDS[i];
}
return { band: 'warehouse', label: role.split(' ')[0].toUpperCase().slice(0, 12) };
}
// Build a sober worker card: monogram avatar + colored role band on
// the left edge + uppercase role pill in the detail line. Used by
// every chapter that renders worker rows. `name` and `role` drive the
// classification; `detail` is the full text after the pill.
// Quick first-name → gender hint for face-pool selection. Same lookup
// idea as the dashboard; if the name is unknown, the server falls back
// to the full pool. Trimmed table — covers the most common names that
// appear in the synthetic worker data.
var FEMALE_NAMES = new Set(['Mary','Patricia','Jennifer','Linda','Elizabeth','Barbara','Susan','Jessica','Sarah','Karen','Lisa','Nancy','Betty','Sandra','Margaret','Ashley','Kimberly','Emily','Donna','Michelle','Carol','Amanda','Melissa','Deborah','Stephanie','Dorothy','Rebecca','Sharon','Laura','Cynthia','Amy','Kathleen','Angela','Shirley','Brenda','Emma','Anna','Pamela','Nicole','Samantha','Katherine','Christine','Helen','Debra','Rachel','Carolyn','Janet','Maria','Catherine','Heather','Diane','Olivia','Julie','Joyce','Victoria','Ruth','Virginia','Lauren','Kelly','Christina','Joan','Evelyn','Judith','Andrea','Hannah','Megan','Cheryl','Jacqueline','Martha','Madison','Teresa','Gloria','Sara','Janice','Ann','Kathryn','Abigail','Sophia','Frances','Jean','Alice','Judy','Isabella','Julia','Grace','Amber','Denise','Danielle','Marilyn','Beverly','Charlotte','Natalie','Theresa','Diana','Brittany','Kayla','Alexis','Lori','Marie','Carmen','Aisha','Rosa','Mia','Audrey','Erin','Tina','Vanessa','Tara','Wendy','Tanya','Maya','Crystal','Yvonne','Kara','Shannon','Brianna','Faith','Caroline','Carla','Tracey','Tracy','Rita','Dawn','Tiffany','Stacy','Stacey','Gina','Bonnie','Tammy','Joanne','Jamie','Tonya','Alyssa','Ariana','Elena','Ellie','Erica','Erika','Felicia','Holly','Jenna','Jenny','Krista','Kristen','Kristin','Krystal','Lana','Leah','Lucy','Mallory','Melinda','Meredith','Misty','Monica','Naomi','Paige','Paula','Renee','Rhonda','Robin','Roxanne','Selena','Sierra','Skylar','Sonia','Stella','Tamara','Veronica','Vivian','Whitney','Yolanda','Zoe']);
var MALE_NAMES = new Set(['James','Robert','John','Michael','David','William','Richard','Joseph','Thomas','Charles','Christopher','Daniel','Matthew','Anthony','Mark','Donald','Steven','Paul','Andrew','Joshua','Kenneth','Kevin','Brian','George','Edward','Ronald','Timothy','Jason','Jeffrey','Ryan','Jacob','Gary','Nicholas','Eric','Jonathan','Stephen','Larry','Justin','Scott','Brandon','Benjamin','Samuel','Gregory','Frank','Alexander','Raymond','Patrick','Jack','Dennis','Jerry','Tyler','Aaron','Jose','Adam','Henry','Nathan','Douglas','Zachary','Peter','Kyle','Walter','Ethan','Jeremy','Harold','Keith','Christian','Roger','Noah','Gerald','Carl','Terry','Sean','Austin','Arthur','Lawrence','Jesse','Dylan','Bryan','Joe','Jordan','Billy','Bruce','Albert','Willie','Gabriel','Logan','Alan','Juan','Wayne','Roy','Ralph','Randy','Eugene','Vincent','Russell','Elijah','Louis','Bobby','Philip','Johnny','Marcus','Antonio','Carlos','Diego','Hector','Jorge','Julio','Manuel','Miguel','Pedro','Raul','Ricardo','Roberto','Sergio','Victor','Jamal','Xavier','DeShawn','Dwayne','Jermaine','Malik','Tyrone','Devon','Andre','Brent','Calvin','Casey','Cody','Cole','Cory','Dale','Damon','Darius','Darrell','Dean','Derek','Drew','Earl','Eddie','Floyd','Glenn','Greg','Howard','Ivan','Jared','Jay','Jeff','Joel','Lance','Lee','Leonard','Lloyd','Mario','Martin','Mason','Maurice','Max','Mitchell','Morgan','Nick','Norman','Oliver','Owen','Pete','Quincy','Rafael','Reggie','Rex','Ricky','Russ','Shane','Shaun','Stanley','Steve','Theodore','Todd','Travis','Trevor','Troy','Wade','Warren','Wesley']);
function guessGenderFromFirstName(n){
if(!n) return null;
var clean=n.replace(/[^A-Za-z]/g,'');
if(!clean) return null;
var c=clean[0].toUpperCase()+clean.slice(1).toLowerCase();
if(FEMALE_NAMES.has(c)) return 'woman';
if(MALE_NAMES.has(c)) return 'man';
return null;
}
function genderFor(name){
var g = guessGenderFromFirstName(name);
if(g) return g;
if(!name) return 'man';
var s=String(name); var h=0;
for(var i=0;i<s.length;i++) h=(h*31+s.charCodeAt(i))|0;
return (Math.abs(h)&1)?'man':'woman';
}
// Confident first-name → ethnicity. Synthetic data — we own the call.
var NAMES_SOUTH_ASIAN_C=new Set(['Raj','Anil','Rohan','Vikram','Arjun','Sanjay','Ravi','Krishna','Pradeep','Sunil','Amit','Deepak','Ashok','Manoj','Rahul','Vijay','Suresh','Naveen','Anand','Nikhil','Aditya','Karan','Rajesh','Priya','Anjali','Neha','Kavya','Pooja','Divya','Meera','Lakshmi','Rani','Asha','Saanvi','Aanya','Aaradhya','Shreya','Riya','Tanvi','Ishita','Aarav','Ishaan','Shivani']);
var NAMES_EAST_ASIAN_C=new Set(['Wei','Mei','Yi','Jin','Chen','Lin','Liu','Wang','Zhang','Yang','Wu','Zhao','Sun','Hiroshi','Yuki','Akira','Kenji','Sakura','Aiko','Haruto','Sora','Hyun','Eun','Yoon','Kai','Long','Hong','Xiu','Lan','Hua','Hao','Tao','Bao','Cheng','Feng','Jian','Dong','Bin','Min','Lei','Hui','Yu','Xin','Ying','Zhen','Yuan','Yan']);
var NAMES_HISPANIC_C=new Set(['Carmen','Carlos','Maria','Diego','Hector','Jorge','Julio','Manuel','Miguel','Pedro','Raul','Ricardo','Roberto','Sergio','Antonio','Esperanza','Luz','Sofia','Lucia','Isabella','Camila','Valentina','Mariana','Elena','Rosa','Catalina','Esteban','Fernando','Eduardo','Javier','Alejandro','Andres','Mateo','Santiago','Sebastian','Emilio','Tomas','Cristina','Daniela','Gabriela','Ximena','Adriana','Beatriz','Pilar','Mercedes','Xavier','Marisol','Guadalupe','Lupita','Inez','Itzel','Yesenia','Joaquin','Ignacio','Rafael','Salvador','Cesar','Arturo','Armando','Hugo','Marco','Alejandra','Felipe','Gerardo','Jaime','Leonardo','Luis','Pablo','Ramon']);
var NAMES_BLACK_C=new Set(['DeShawn','Jamal','Aisha','Latoya','Tyrone','Malik','Imani','Keisha','Tariq','Lakisha','Kenya','Tamika','Andre','Marcus','Demetrius','Jermaine','Reggie','Tyrese','Darius','Trevon','Kareem','Damon','Jalen','Jaylen','Dwayne','DaQuan','Aaliyah','Kiara','Janelle','Jasmine','Tanisha','Maurice','Tyrell','Kwame','Khalil','Terrell','Cedric','Nia','Zuri','Jada','Ebony','Dominique']);
var NAMES_MIDDLE_EASTERN_C=new Set(['Layla','Omar','Khalid','Fatima','Yasmin','Hassan','Hussein','Ahmed','Mohamed','Mohammed','Ali','Karim','Yusuf','Yara','Nadia','Zainab','Rania','Samira','Mariam','Salma','Ibrahim','Mahmoud','Saif','Anwar','Bilal','Faisal','Hamza','Imran','Sami','Wael','Zaid','Amira','Iman','Lina','Mona','Noor','Rana','Soha','Zara']);
// Surname → ethnicity. Surname is more diagnostic than first name
// for hispanic and asian — "Anna Cruz" is hispanic via surname.
var SURNAMES_HISPANIC_C=new Set(['Garcia','Rodriguez','Martinez','Hernandez','Lopez','Gonzalez','Perez','Sanchez','Ramirez','Torres','Flores','Rivera','Gomez','Diaz','Reyes','Cruz','Morales','Ortiz','Gutierrez','Chavez','Ramos','Ruiz','Alvarez','Mendoza','Vasquez','Castillo','Jimenez','Moreno','Romero','Herrera','Medina','Aguilar','Vargas','Castro','Fernandez','Guzman','Munoz','Salazar','Ortega','Delgado','Estrada','Ayala','Pena','Cabrera','Alvarado','Espinoza','Padilla','Cardenas','Cortes','Ibarra','Vega','Soto','Lara','Navarro','Campos','Acosta','Rios','Marquez','Sandoval','Maldonado','Solis','Rojas','Mejia','Beltran','Cervantes','Lozano','Carrillo','Trevino','Robles','Tapia','Lugo']);
var SURNAMES_SOUTH_ASIAN_C=new Set(['Patel','Singh','Kumar','Sharma','Gupta','Shah','Mehta','Desai','Joshi','Reddy','Nair','Iyer','Verma','Agarwal','Kapoor','Chopra','Malhotra','Banerjee','Chatterjee','Mukherjee','Das','Sen','Bose','Roy','Sinha','Trivedi','Pandey','Mishra','Tiwari','Yadav','Chauhan','Rana','Thakur','Pillai','Menon','Krishnan','Rao','Naidu','Pradhan','Acharya','Devi','Kaur']);
var SURNAMES_EAST_ASIAN_C=new Set(['Chen','Wang','Li','Liu','Yang','Huang','Zhao','Wu','Zhou','Xu','Zhu','Sun','Ma','Lin','Lee','Kim','Park','Choi','Jung','Kang','Cho','Yoon','Han','Lim','Oh','Nakamura','Tanaka','Suzuki','Yamamoto','Sato','Watanabe','Takahashi','Kobayashi','Yoshida','Saito','Nguyen','Tran','Le','Pham','Hoang','Phan','Vu','Vo','Dang','Bui','Do','Ngo','Truong','Mai','Cao','Wong','Tang','Tan','Cheng','Lau','Leung','Ng','Cheung','Yip','Hsu','Tsai','Hsieh']);
var SURNAMES_MIDDLE_EASTERN_C=new Set(['Khan','Ahmed','Hussein','Hassan','Ali','Mahmoud','Mohamed','Mohammed','Saleh','Aziz','Karim','Hamad','Najjar','Haddad','Khoury','Mansour','Rahman','Iqbal','Malik','Sheikh','Siddiqui','Qureshi','Saeed']);
function guessEthnicityFromName(first, last){
if(last){
var s=last.replace(/[^A-Za-z]/g,'');
if(s){
var sc=s[0].toUpperCase()+s.slice(1).toLowerCase();
if(SURNAMES_HISPANIC_C.has(sc)) return 'hispanic';
if(SURNAMES_MIDDLE_EASTERN_C.has(sc)) return 'middle_eastern';
if(SURNAMES_SOUTH_ASIAN_C.has(sc)) return 'south_asian';
if(SURNAMES_EAST_ASIAN_C.has(sc)) return 'east_asian';
}
}
if(first){
var clean=first.replace(/[^A-Za-z]/g,'');
if(clean){
var c=clean[0].toUpperCase()+clean.slice(1).toLowerCase();
if(NAMES_MIDDLE_EASTERN_C.has(c)) return 'middle_eastern';
if(NAMES_BLACK_C.has(c)) return 'black';
if(NAMES_HISPANIC_C.has(c)) return 'hispanic';
if(NAMES_SOUTH_ASIAN_C.has(c)) return 'south_asian';
if(NAMES_EAST_ASIAN_C.has(c)) return 'east_asian';
}
}
return 'caucasian';
}
function guessEthnicityFromFirstName(n){
if(!n) return 'caucasian';
var clean=n.replace(/[^A-Za-z]/g,''); if(!clean) return 'caucasian';
var c=clean[0].toUpperCase()+clean.slice(1).toLowerCase();
if(NAMES_MIDDLE_EASTERN_C.has(c)) return 'middle_eastern';
if(NAMES_BLACK_C.has(c)) return 'black';
if(NAMES_HISPANIC_C.has(c)) return 'hispanic';
if(NAMES_SOUTH_ASIAN_C.has(c)) return 'south_asian';
if(NAMES_EAST_ASIAN_C.has(c)) return 'east_asian';
return 'caucasian';
}
function workerRow(name, role, detail, opts){
opts = opts || {};
var band = roleBand(role||'');
var w = el('div','worker');
if(band.band) w.dataset.roleBand = band.band;
var initials = (name||'?').split(' ').map(function(s){return (s[0]||'').toUpperCase()}).join('').substring(0,2);
var av = el('div','av',initials);
// Headshot insertion removed 2026-04-28. The .av element stays as
// a monogram-initials avatar.
w.appendChild(av);
var info = el('div','info');
var nm = el('div','nm', name||'?');
if(opts.endorsed){
nm.appendChild(el('span','boost-chip',opts.endorsed));
}
info.appendChild(nm);
var why = el('div','why');
if(band.label){
var pill = document.createElement('span'); pill.className='role-pill';
pill.dataset.rb = band.band;
pill.textContent = band.label;
why.appendChild(pill);
}
why.appendChild(document.createTextNode(detail||''));
info.appendChild(why);
w.appendChild(info);
if(opts.score){
w.appendChild(el('div','score', opts.score));
}
return w;
}
function el(tag, cls, text){ function el(tag, cls, text){
var e=document.createElement(tag); var e=document.createElement(tag);
if(cls) e.className=cls; if(cls) e.className=cls;
@ -191,6 +366,9 @@ window.addEventListener('load',function(){
loadChapter3(); loadChapter3();
loadChapter4(); loadChapter4();
loadChapter5(); loadChapter5();
loadChapter6();
loadChapter7();
loadChapter8();
}); });
// ─── Chapter 1 ──────────────────────────────────────────── // ─── Chapter 1 ────────────────────────────────────────────
@ -306,6 +484,30 @@ function loadChapter4(){
addr.style.cssText='color:#8b949e;font-size:12px;margin-top:2px'; addr.style.cssText='color:#8b949e;font-size:12px;margin-top:2px';
card.appendChild(addr); card.appendChild(addr);
// Contractor names link to the full /contractor profile page —
// heat map, project index, history, 12 awaiting public-data
// sources. The staffer click-through J asked for.
if(p.contact_1_name || p.contact_2_name){
var contractors=document.createElement('div');
contractors.style.cssText='color:#8b949e;font-size:12px;margin-top:4px';
contractors.appendChild(document.createTextNode('Contractors: '));
var seen=[];
[p.contact_1_name, p.contact_2_name].forEach(function(n,i){
if(!n || seen.indexOf(n)>=0) return;
seen.push(n);
if(seen.length>1) contractors.appendChild(document.createTextNode(' · '));
var a=document.createElement('a');
a.href=P+'/contractor?name='+encodeURIComponent(n);
a.target='_blank';
a.rel='noopener';
a.style.cssText='color:#58a6ff;text-decoration:none;border-bottom:1px dotted #58a6ff44';
a.title='Open full contractor profile';
a.textContent=n;
contractors.appendChild(a);
});
card.appendChild(contractors);
}
card.appendChild(el('div','step-label','STEP 1 · Derive staffing need')); card.appendChild(el('div','step-label','STEP 1 · Derive staffing need'));
var s1=el('div','step-body'); var s1=el('div','step-body');
s1.appendChild(document.createTextNode('Industry heuristic: ~1 worker per $150K of permit cost, capped 2-8. Resulting contract: ')); s1.appendChild(document.createTextNode('Industry heuristic: ~1 worker per $150K of permit cost, capped 2-8. Resulting contract: '));
@ -321,21 +523,13 @@ function loadChapter4(){
var list=document.createElement('div');list.style.marginTop='6px'; var list=document.createElement('div');list.style.marginTop='6px';
(prop.candidates||[]).slice(0,5).forEach(function(cand,i){ (prop.candidates||[]).slice(0,5).forEach(function(cand,i){
var w=el('div','worker'); var detail = cand.doc_id+' · '+(cand.playbook_boost>0?'boosted +'+cand.playbook_boost.toFixed(3)+' by memory · ':'')+'semantic score '+(cand.score||0).toFixed(3);
var initials=(cand.name||'?').split(' ').map(function(s){return (s[0]||'').toUpperCase()}).join('').substring(0,2); var endorsed = (cand.playbook_boost||0) > 0
w.appendChild(el('div','av',initials)); ? 'Endorsed · '+((cand.playbook_citations||[]).length)+' past fill'+((cand.playbook_citations||[]).length!==1?'s':'')
var info=el('div','info'); : null;
var nm=el('div','nm',cand.name||cand.doc_id||'?'); list.appendChild(workerRow(cand.name||cand.doc_id||'?', prop.role||'', detail, {
if((cand.playbook_boost||0)>0){ endorsed: endorsed, score: '#'+(i+1)
var ncit=(cand.playbook_citations||[]).length; }));
nm.appendChild(el('span','boost-chip','Endorsed · '+ncit+' past fill'+(ncit!==1?'s':'')));
}
info.appendChild(nm);
var why=cand.doc_id+' · '+(cand.playbook_boost>0?'boosted +'+cand.playbook_boost.toFixed(3)+' by memory · ':'')+'semantic score '+(cand.score||0).toFixed(3);
info.appendChild(el('div','why',why));
w.appendChild(info);
w.appendChild(el('div','score','#'+(i+1)));
list.appendChild(w);
}); });
card.appendChild(list); card.appendChild(list);
@ -407,7 +601,182 @@ function loadChapter5(){
}); });
} }
// ─── Chapter 6 ──────────────────────────────────────────── // ─── Chapter 6 — per-staffer hot-swap ─────────────────────
function loadChapter6(){
apiGet('/staffers').then(function(r){
var host=document.getElementById('ch6-staffers');host.textContent='';
var staffers=(r&&r.staffers)||[];
if(!staffers.length){
host.appendChild(el('div','err','No staffer roster — /staffers returned empty.'));
return;
}
var grid=document.createElement('div'); grid.className='grid'; grid.style.gridTemplateColumns='repeat(auto-fit,minmax(280px,1fr))';
staffers.forEach(function(s){
var card=el('div','card accent-b');
var name=el('div',null,s.name);
name.style.cssText='font-size:18px;font-weight:700;color:#e6edf3;letter-spacing:-0.3px';
card.appendChild(name);
var role=el('div',null,s.display||'');
role.style.cssText='font-size:11px;color:#545d68;text-transform:uppercase;letter-spacing:1.2px;margin-top:2px';
card.appendChild(role);
var ter=el('div',null,'Territory: '+s.territory.state+' · '+s.territory.cities.slice(0,3).join(', ')+'…');
ter.style.cssText='color:#8b949e;font-size:12px;margin-top:8px';
card.appendChild(ter);
var greet=el('div',null,s.greeting||'');
greet.style.cssText='color:#c9d1d9;font-size:11px;margin-top:6px;line-height:1.5;border-top:1px dashed #1f2631;padding-top:6px';
card.appendChild(greet);
grid.appendChild(card);
});
host.appendChild(grid);
var narr=el('div','narr');
narr.appendChild(el('strong',null,'What this means for a staffer. '));
narr.appendChild(document.createTextNode('Same query — "forklift operators" — returns 89 Indiana workers when Devon is acting, 16 Wisconsin workers when Aisha is acting, 167 Illinois workers when Maria is acting. The MEMORY panel relabels itself with whoever\'s viewing. The corpus stays intact; the relevance gradient is per coordinator. As they each accumulate fills, their slice of the playbook compounds independently.'));
host.appendChild(narr);
}).catch(function(e){
var h=document.getElementById('ch6-staffers');h.textContent='';h.appendChild(el('div','err','Staffer roster unavailable: '+(e.message||e)));
});
}
// ─── Chapter 7 — Construction Activity Signal Engine ──────
function loadChapter7(){
Promise.all([
api('/intelligence/profiler_index',{limit:200}),
]).then(function(rs){
var prof=rs[0]||{};
var rows=prof.contractors||[];
var host=document.getElementById('ch7-signal');host.textContent='';
// Aggregate basket
var byTicker={};
rows.forEach(function(r){
var ts=(r.tickers&&r.tickers.direct?r.tickers.direct:[]).concat(r.tickers&&r.tickers.associated?r.tickers.associated:[]);
ts.forEach(function(t){
if(!t||!t.ticker) return;
if(!byTicker[t.ticker]) byTicker[t.ticker]={ticker:t.ticker,count:0,kinds:new Set()};
byTicker[t.ticker].count++;
byTicker[t.ticker].kinds.add(t.via);
});
});
var basket=Object.values(byTicker).sort(function(a,b){return b.count-a.count});
var attribCost=0;
rows.forEach(function(r){
var ts=(r.tickers&&r.tickers.direct?r.tickers.direct:[]).concat(r.tickers&&r.tickers.associated?r.tickers.associated:[]);
if(ts.length>0) attribCost += (r.total_cost||0);
});
var totalAttrib = basket.reduce(function(s,b){return s+b.count},0);
if(!basket.length){
host.appendChild(el('div','loading','No public-issuer attributions in this view yet.'));
return;
}
// Top-line metric strip
var grid=document.createElement('div');grid.className='grid';
var c1=el('div','card accent-g');
var b1=el('div',null,basket.length); b1.style.cssText='font-size:30px;font-weight:800;color:#3fb950;line-height:1';
c1.appendChild(b1);
var l1=el('div',null,'Public issuers in scope'); l1.style.cssText='font-size:10px;color:#545d68;text-transform:uppercase;letter-spacing:1.2px;margin-top:8px;font-weight:600';
c1.appendChild(l1);
var s1=el('div',null,totalAttrib+' attribution edges across the contractor graph'); s1.style.cssText='font-size:12px;color:#8b949e;margin-top:4px';
c1.appendChild(s1);
grid.appendChild(c1);
var c2=el('div','card accent-b');
var bav = attribCost>=1e9?'$'+(attribCost/1e9).toFixed(2)+'B':attribCost>=1e6?'$'+(attribCost/1e6).toFixed(0)+'M':'$'+Math.round(attribCost/1e3)+'K';
var b2=el('div',null,bav); b2.style.cssText='font-size:30px;font-weight:800;color:#58a6ff;line-height:1';
c2.appendChild(b2);
var l2=el('div',null,'Attributed build value'); l2.style.cssText='font-size:10px;color:#545d68;text-transform:uppercase;letter-spacing:1.2px;margin-top:8px;font-weight:600';
c2.appendChild(l2);
var s2=el('div',null,'Permits with at least one wired public-issuer thread'); s2.style.cssText='font-size:12px;color:#8b949e;margin-top:4px';
c2.appendChild(s2);
grid.appendChild(c2);
var c3=el('div','card accent-l');
var b3=el('div',null,rows.length); b3.style.cssText='font-size:30px;font-weight:800;color:#bc8cff;line-height:1';
c3.appendChild(b3);
var l3=el('div',null,'Contractors indexed'); l3.style.cssText='font-size:10px;color:#545d68;text-transform:uppercase;letter-spacing:1.2px;margin-top:8px;font-weight:600';
c3.appendChild(l3);
var s3=el('div',null,'Each is also a heat map of where they work'); s3.style.cssText='font-size:12px;color:#8b949e;margin-top:4px';
c3.appendChild(s3);
grid.appendChild(c3);
host.appendChild(grid);
// Top issuer table
var tHdr=document.createElement('div');tHdr.style.cssText='color:#545d68;font-size:11px;text-transform:uppercase;letter-spacing:1.4px;font-weight:600;margin:14px 0 8px';
tHdr.textContent='Top public issuers attributable in this view';
host.appendChild(tHdr);
basket.slice(0,8).forEach(function(b){
var row=el('div','row');
var left=document.createElement('div');left.style.flex='1';left.style.minWidth='0';
var tk=el('div','title',b.ticker);
tk.style.cssText+='font-family:ui-monospace,monospace;color:#3fb950';
left.appendChild(tk);
var kinds=Array.from(b.kinds);
var meta=el('div','meta',b.count+' attribution'+(b.count===1?'':'s')+' · '+kinds.join('+'));
left.appendChild(meta);
row.appendChild(left);
var right=document.createElement('div');right.style.cssText='font-size:11px;color:#58a6ff';
var a=document.createElement('a');a.href=P+'/profiler';a.target='_blank';a.style.color='#58a6ff';a.style.textDecoration='none';
a.textContent='see in profiler →';
right.appendChild(a);
row.appendChild(right);
host.appendChild(row);
});
var narr=el('div','narr');
narr.appendChild(el('strong',null,'What this means for the business. '));
narr.appendChild(document.createTextNode('The data corpus is also a market-signal engine. When a contractor co-files permits with a public company, that contractor inherits the ticker as an associated indicator. Permit volume changes precede earnings calls by months. As we add cities (NYC DOB next, then LA / Houston / Boston) the network compounds — and we own a piece of the signal that nobody else has.'));
host.appendChild(narr);
}).catch(function(e){
var h=document.getElementById('ch7-signal');h.textContent='';h.appendChild(el('div','err','Signal engine unavailable: '+(e.message||e)));
});
}
// ─── Chapter 8 — Triage in one shot ───────────────────────
function loadChapter8(){
api('/intelligence/chat',{message:'Marcus running late site 4422'}).then(function(d){
var host=document.getElementById('ch8-triage');host.textContent='';
if(d.type!=='triage'){
host.appendChild(el('div','err','Triage route did not fire. Got type=' + (d.type||'?')));
return;
}
// Worker card
var wc=el('div','card accent-r');
var lbl=el('div',null,'⚠ TRIAGE EVENT'); lbl.style.cssText='font-size:10px;color:#f85149;text-transform:uppercase;letter-spacing:1.2px;font-weight:700;margin-bottom:8px';
wc.appendChild(lbl);
var nm=el('div',null,d.worker.name); nm.style.cssText='font-size:18px;font-weight:700;color:#e6edf3';
wc.appendChild(nm);
var loc=el('div',null,(d.worker.role||'?')+' · '+(d.worker.city||'')+', '+(d.worker.state||''));
loc.style.cssText='font-size:12px;color:#8b949e;margin-top:2px';
wc.appendChild(loc);
var stats=document.createElement('div');stats.style.cssText='display:flex;gap:14px;font-size:11px;color:#8b949e;margin-top:8px;flex-wrap:wrap';
[['Reliability',Math.round((d.worker.rel||0)*100)+'%'],['Responsiveness',Math.round((d.worker.resp||0)*100)+'%'],['Availability',Math.round((d.worker.avail||0)*100)+'%']].forEach(function(p){
var s=document.createElement('span');
var l=document.createElement('span');l.textContent=p[0]+': ';
var b=document.createElement('b');b.style.color='#e6edf3';b.textContent=p[1];
s.appendChild(l);s.appendChild(b);stats.appendChild(s);
});
wc.appendChild(stats);
host.appendChild(wc);
// Draft SMS
var smsLabel=el('div',null,'DRAFT SMS — TO CLIENT'); smsLabel.style.cssText='font-size:10px;color:#d29922;text-transform:uppercase;letter-spacing:1.2px;font-weight:700;margin:14px 0 4px';
host.appendChild(smsLabel);
var smsBox=el('div',null,d.draft_sms||'');
smsBox.style.cssText='background:#0d1117;border:1px solid #21262d;border-radius:6px;padding:10px 12px;font-family:ui-monospace,monospace;font-size:12px;color:#e6edf3;line-height:1.5;white-space:pre-wrap';
host.appendChild(smsBox);
// Backfills
if((d.backfills||[]).length){
var bfHdr=document.createElement('div');bfHdr.style.cssText='font-size:11px;color:#3fb950;text-transform:uppercase;letter-spacing:1.2px;font-weight:600;margin:14px 0 8px';
bfHdr.textContent='✓ '+d.backfills.length+' local '+(d.worker.role||'workers')+' available — sorted by responsiveness';
host.appendChild(bfHdr);
d.backfills.slice(0,5).forEach(function(c){
var detail=(c.role||'?')+' · '+(c.city||'')+', '+(c.state||'')+' · rel '+Math.round((c.rel||0)*100)+'% · resp '+Math.round((c.resp||0)*100)+'%';
host.appendChild(workerRow(c.name||'?', c.role||'', detail));
});
}
var narr=el('div','narr');
narr.appendChild(el('strong',null,'What this means for a coordinator. '));
narr.appendChild(document.createTextNode('A normal afternoon: text rolls in, coordinator opens 3 tabs to look up the worker, checks the bench by hand, drafts a message. 20 minutes. Here: the system pulled the profile, scored attendance, surfaced 5 same-role same-geo backfills sorted by who actually answers their phone, and pre-wrote the client-facing SMS. The coordinator clicks send. ' + d.duration_ms + 'ms.'));
host.appendChild(narr);
}).catch(function(e){
var h=document.getElementById('ch8-triage');h.textContent='';h.appendChild(el('div','err','Triage demo unavailable: '+(e.message||e)));
});
}
// ─── Chapter 9 (was 6) — Try it yourself ──────────────────
function runTry(){ function runTry(){
var q=document.getElementById('try-q').value.trim();if(!q)return; var q=document.getElementById('try-q').value.trim();if(!q)return;
var btn=document.getElementById('try-btn'),out=document.getElementById('try-out'); var btn=document.getElementById('try-btn'),out=document.getElementById('try-out');
@ -437,23 +806,16 @@ function runTry(){
var workers=d.sql_results||d.vector_results||d.results||[]; var workers=d.sql_results||d.vector_results||d.results||[];
workers.slice(0,5).forEach(function(w,i){ workers.slice(0,5).forEach(function(w,i){
var row=el('div','worker');
var nm=w.name||(w.text||'').split('—')[0].trim()||w.doc_id||'?'; var nm=w.name||(w.text||'').split('—')[0].trim()||w.doc_id||'?';
var initials=nm.split(' ').map(function(s){return (s[0]||'').toUpperCase()}).join('').substring(0,2);
row.appendChild(el('div','av',initials));
var info=el('div','info');
var n=el('div','nm',nm);
if((w.playbook_boost||0)>0){
n.appendChild(el('span','boost-chip','Endorsed · '+((w.playbook_citations||[]).length||'?')+' past fill(s)'));
}
info.appendChild(n);
var bits=[]; var bits=[];
if(w.role) bits.push(w.role); if(w.role) bits.push(w.role);
if(w.city&&w.state) bits.push(w.city+', '+w.state); if(w.city&&w.state) bits.push(w.city+', '+w.state);
if(w.rel!==undefined) bits.push('reliability '+Math.round(w.rel*100)+'%'); if(w.rel!==undefined) bits.push('reliability '+Math.round(w.rel*100)+'%');
if(w.avail!==undefined) bits.push('availability '+Math.round(w.avail*100)+'%'); if(w.avail!==undefined) bits.push('availability '+Math.round(w.avail*100)+'%');
info.appendChild(el('div','why',bits.join(' · ')||'AI semantic match')); var endorsed = (w.playbook_boost||0) > 0
row.appendChild(info); ? 'Endorsed · '+((w.playbook_citations||[]).length||'?')+' past fill(s)'
: null;
var row = workerRow(nm, w.role||'', bits.join(' · ')||'AI semantic match', { endorsed: endorsed });
row.appendChild(el('div','score','#'+(i+1))); row.appendChild(el('div','score','#'+(i+1)));
card.appendChild(row); card.appendChild(row);
}); });

606
mcp-server/contractor.html Normal file
View File

@ -0,0 +1,606 @@
<!DOCTYPE html>
<html><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
<title>Contractor Profile · Staffing Co-Pilot</title>
<link rel="stylesheet" href="https://unpkg.com/leaflet@1.9.4/dist/leaflet.css">
<script src="https://unpkg.com/leaflet@1.9.4/dist/leaflet.js"></script>
<style>
*{margin:0;padding:0;box-sizing:border-box}
html,body{overflow-x:hidden}
body{font-family:'Inter',-apple-system,system-ui,sans-serif;background:#090c10;color:#b0b8c4;font-size:14px;line-height:1.6}
.bar{background:#0d1117;padding:0 24px;height:56px;border-bottom:1px solid #171d27;display:flex;justify-content:space-between;align-items:center}
.bar h1{font-size:14px;font-weight:600;color:#e6edf3}
.bar a{color:#545d68;text-decoration:none;font-size:12px;padding:6px 14px;border-radius:6px}
.bar a:hover{color:#e6edf3;background:#161b22}
.content{max-width:1100px;margin:0 auto;padding:24px 20px 40px}
.search-box{background:#0d1117;border:1px solid #21262d;border-radius:10px;padding:16px;margin-bottom:24px;display:flex;gap:10px}
.search-box input{flex:1;padding:12px 16px;background:#161b22;border:1px solid #21262d;border-radius:8px;color:#e6edf3;font-size:14px;outline:none}
.search-box input:focus{border-color:#388bfd}
.search-box button{padding:12px 24px;background:#1f6feb;border:none;border-radius:8px;color:#fff;font-weight:600;cursor:pointer}
.hero{background:#0d1117;border:1px solid #171d27;border-radius:12px;padding:24px;margin-bottom:16px}
.hero h2{color:#e6edf3;font-size:22px;font-weight:700;letter-spacing:-0.5px;margin-bottom:6px}
.hero .ticker-row{display:flex;align-items:center;gap:10px;margin-top:10px;flex-wrap:wrap}
.hero .ticker{font-family:ui-monospace,SFMono-Regular,monospace;background:#161b22;padding:4px 10px;border-radius:6px;color:#3fb950;border:1px solid #3fb95066;font-weight:600;font-size:12px}
.hero .meta{font-size:12px;color:#8b949e}
.grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(320px,1fr));gap:14px}
.card{background:#0d1117;border:1px solid #171d27;border-radius:10px;padding:16px}
.card h3{font-size:11px;color:#545d68;text-transform:uppercase;letter-spacing:1.2px;margin-bottom:10px;font-weight:600}
.card .big{font-size:24px;font-weight:700;color:#e6edf3;letter-spacing:-0.5px;margin-bottom:4px}
.card .sub{font-size:11px;color:#8b949e;line-height:1.5}
.card a{color:#58a6ff;text-decoration:none;font-size:11px}
.row{display:flex;justify-content:space-between;align-items:baseline;padding:6px 0;border-bottom:1px dashed #1f2631;font-size:11px}
.row:last-child{border:none}
.row .l{color:#8b949e}
.row .v{color:#e6edf3;font-family:ui-monospace,monospace;font-variant-numeric:tabular-nums}
.chip{display:inline-block;padding:3px 8px;border-radius:9px;font-size:10px;font-weight:600;margin-right:6px;margin-bottom:4px}
.ld{color:#3d444d;text-align:center;padding:60px;font-size:13px}
.empty{color:#545d68;font-size:11px;font-style:italic;line-height:1.5}
.wide{grid-column:1/-1}
.heatmap{height:380px;border-radius:8px;border:1px solid #1f2631;overflow:hidden;margin-top:10px}
.heatmap .leaflet-container{background:#0a0d12}
.timeline{margin-top:10px;display:flex;align-items:flex-end;gap:2px;height:80px;padding:6px 0;border-bottom:1px solid #1f2631}
.timeline .tbar{flex:1;background:#1f6feb;min-height:2px;border-radius:2px 2px 0 0;position:relative;cursor:help}
.timeline .tbar:hover{background:#58a6ff}
.timeline-axis{display:flex;justify-content:space-between;font-size:10px;color:#545d68;padding-top:4px;font-family:ui-monospace,monospace}
.placeholder-grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(280px,1fr));gap:10px;margin-top:14px}
.ph-card{background:#0a0d12;border:1px dashed #21262d;border-radius:8px;padding:12px 14px;position:relative}
.ph-card h4{font-size:11px;color:#8b949e;font-weight:600;margin-bottom:4px;display:flex;align-items:center;gap:6px}
.ph-card h4 .badge{font-size:9px;padding:2px 6px;border-radius:8px;background:#161b22;color:#d29922;border:1px solid #d2992244;font-weight:600;letter-spacing:0.5px;text-transform:uppercase}
.ph-card .why{font-size:11px;color:#e6edf3;line-height:1.5;margin-bottom:6px}
.ph-card .would{font-size:10px;color:#545d68;font-family:ui-monospace,monospace;line-height:1.5;border-top:1px dashed #1f2631;padding-top:6px;margin-top:6px}
.section-label{font-size:10px;color:#545d68;text-transform:uppercase;letter-spacing:1.4px;font-weight:600;margin:24px 0 8px}
@media(max-width:640px){.bar{padding:0 14px}.content{padding:14px}.hero{padding:16px}.hero h2{font-size:18px}.card{padding:12px}}
</style>
</head><body>
<div class="bar">
<h1>Staffing Co-Pilot · Contractor Profile</h1>
<a href="/">← Dashboard</a>
</div>
<div class="content">
<div class="search-box">
<input id="q" type="text" placeholder="Type a contractor name (e.g., Turner Construction Company)" onkeydown="if(event.key==='Enter')lookup()">
<button onclick="lookup()">Look up</button>
</div>
<div id="out"><div class="ld">Type a name above to load the full portfolio across every wired data source.</div></div>
</div>
<script>
function $(id){return document.getElementById(id)}
// Path prefix detection — devop.live serves this page under /lakehouse,
// localhost:3700 serves it at root. URL rewrites must preserve whatever
// prefix the user reached the page through, otherwise the back-link and
// browser refresh break.
var P=location.pathname.indexOf('/lakehouse')>=0?'/lakehouse':'';
// Bootstrap from URL: /contractor?name=Turner+Construction
window.addEventListener('load', function(){
var name = new URLSearchParams(location.search).get('name');
if(name){
$('q').value = name;
lookup();
}
// Back link respects the prefix too
var back=document.querySelector('.bar a');
if(back) back.href=P+'/';
});
function lookup(){
var name = $('q').value.trim();
if(!name){ $('out').textContent = ''; return; }
history.replaceState({}, '', P+'/contractor?name='+encodeURIComponent(name));
var out = $('out');
out.textContent = '';
var ld = document.createElement('div');
ld.className = 'ld';
ld.textContent = 'Pulling OSHA, SEC, Stooq, Chicago history, USASpending… (~5-10s on cold cache)';
out.appendChild(ld);
fetch(P+'/intelligence/contractor_profile',{
method:'POST',
headers:{'Content-Type':'application/json'},
body:JSON.stringify({name:name})
}).then(function(r){return r.json()}).then(function(d){
render(d);
}).catch(function(e){
out.textContent = '';
var err = document.createElement('div');
err.className = 'ld';
err.style.color = '#f85149';
err.textContent = 'profile failed: '+e.message;
out.appendChild(err);
});
}
function render(d){
var out = $('out');
out.textContent = '';
// ─── Hero — name, ticker, parent ─────────────
var hero = document.createElement('div');
hero.className = 'hero';
var h2 = document.createElement('h2');
h2.textContent = d.display_name;
hero.appendChild(h2);
var sub = document.createElement('div');
sub.className = 'meta';
sub.textContent = 'Internal ticker: '+(d.ticker||'?')+' · profile generated '+new Date(d.generated_at).toLocaleTimeString();
hero.appendChild(sub);
var trow = document.createElement('div');
trow.className = 'ticker-row';
// Direct ticker
var s = d.stock;
if(s && s.status==='ok'){
var tk = document.createElement('span');
tk.className = 'ticker';
tk.textContent = s.ticker;
trow.appendChild(tk);
var px = document.createElement('span');
px.className = 'meta';
px.textContent = (s.company_name||'')+(s.exchange?' · '+s.exchange:'')+(s.price?' · $'+s.price.toFixed(2):'');
if(s.day_change_pct!=null && !isNaN(s.day_change_pct)){
var ch = (s.day_change_pct>=0?'+':'')+s.day_change_pct.toFixed(2)+'%';
var chSpan = document.createElement('span');
chSpan.style.color = s.day_change_pct>=0?'#3fb950':'#f85149';
chSpan.style.marginLeft = '6px';
chSpan.textContent = ch;
px.appendChild(chSpan);
}
trow.appendChild(px);
} else {
var noTk = document.createElement('span');
noTk.className = 'meta';
noTk.textContent = 'Private — no direct US ticker';
trow.appendChild(noTk);
}
// Parent link
var pl = d.parent_link;
if(pl && pl.status==='ok'){
var arrow = document.createElement('span');
arrow.className = 'meta';
arrow.style.color = '#545d68';
arrow.textContent = ' → parent ';
trow.appendChild(arrow);
var pTk = document.createElement('span');
pTk.className = 'ticker';
pTk.style.color = '#d29922';
pTk.style.borderColor = '#d2992266';
pTk.textContent = pl.parent_ticker || '?';
pTk.title = pl.link_source || '';
trow.appendChild(pTk);
var pName = document.createElement('span');
pName.className = 'meta';
pName.textContent = pl.parent_name+(pl.parent_exchange?' · '+pl.parent_exchange:'')+(pl.parent_country?' · '+pl.parent_country:'');
trow.appendChild(pName);
} else if(pl && pl.status==='no_link'){
var pp = document.createElement('span');
pp.className = 'meta';
pp.style.fontStyle = 'italic';
pp.textContent = ' · '+(pl.reason||'no public parent identified');
trow.appendChild(pp);
}
hero.appendChild(trow);
out.appendChild(hero);
// ─── Grid of cards ─────────────────────────────
var grid = document.createElement('div');
grid.className = 'grid';
// OSHA
var oCard = card('OSHA SAFETY HISTORY (NATIONAL)');
var osha = d.osha || {};
if(osha.status==='ok'){
big(oCard, osha.inspection_count + ' inspections', 'most recent '+(osha.most_recent_date||'?'));
rowEl(oCard, 'States seen', (osha.states_seen||[]).join(', ') || '?');
rowEl(oCard, 'Most recent', osha.most_recent_date||'?');
if(osha.recent_inspections && osha.recent_inspections.length){
var rep = document.createElement('div');
rep.style.marginTop = '8px';
rep.style.fontSize = '10px';
rep.style.color = '#545d68';
rep.textContent = 'Recent inspections:';
oCard.appendChild(rep);
osha.recent_inspections.slice(0,5).forEach(function(i){
var r = document.createElement('div');
r.style.fontSize = '10px';
r.style.color = '#8b949e';
r.style.fontFamily = 'ui-monospace,monospace';
r.style.padding = '2px 0';
var a = document.createElement('a');
a.href = i.detail_url;
a.target = '_blank';
a.textContent = i.id;
r.appendChild(a);
r.appendChild(document.createTextNode(' · '+i.date+' · '+i.state+' · '+i.type+' · '+i.scope));
oCard.appendChild(r);
});
}
} else if(osha.status==='no_match'){
big(oCard, 'No inspections', 'clean record');
} else {
empty(oCard, 'OSHA fetch error: '+(osha.error||'unknown'));
}
grid.appendChild(oCard);
// Chicago history
var hCard = card('CHICAGO PERMIT HISTORY (24mo + LIFETIME)');
var hist = d.history || {};
if(hist.status==='ok'){
big(hCard, hist.permits_historical_total+' permits all-time',
hist.permits_last_180d+' in last 180d · '+hist.permits_last_24mo+' in 24mo · trend: '+hist.trend);
rowEl(hCard, 'Cost (24mo)', hist.total_cost_last_24mo>=1e6 ? '$'+(hist.total_cost_last_24mo/1e6).toFixed(1)+'M' : '$'+Math.round(hist.total_cost_last_24mo/1e3)+'K');
if(hist.recent_permits && hist.recent_permits.length){
var rh = document.createElement('div');
rh.style.marginTop = '8px';
rh.style.fontSize = '10px';
rh.style.color = '#545d68';
rh.textContent = 'Recent Chicago permits:';
hCard.appendChild(rh);
hist.recent_permits.slice(0,5).forEach(function(p){
var r = document.createElement('div');
r.style.fontSize = '10px';
r.style.color = '#8b949e';
r.style.padding = '2px 0';
r.textContent = '· '+(p.date||'?')+' · '+p.work_type+' · $'+(p.cost||0).toLocaleString()+' · '+p.address;
hCard.appendChild(r);
});
}
} else {
empty(hCard, 'Chicago history error');
}
grid.appendChild(hCard);
// Federal contracts
var fCard = card('FEDERAL CONTRACTS (USASpending.gov)');
var fed = d.federal || {};
if(fed.status==='ok' && fed.total_awards_count>0){
var dollars = fed.total_awards_value>=1e9 ? '$'+(fed.total_awards_value/1e9).toFixed(2)+'B'
: fed.total_awards_value>=1e6 ? '$'+(fed.total_awards_value/1e6).toFixed(1)+'M'
: '$'+Math.round(fed.total_awards_value/1e3)+'K';
big(fCard, dollars, fed.total_awards_count+' awards · most recent '+(fed.most_recent_award_date||'?'));
if(fed.top_agencies && fed.top_agencies.length){
var ta = document.createElement('div');
ta.style.marginTop = '6px';
ta.style.fontSize = '10px';
ta.style.color = '#545d68';
ta.textContent = 'Top awarding agencies:';
fCard.appendChild(ta);
fed.top_agencies.forEach(function(a){
var r = document.createElement('div');
r.style.fontSize = '11px';
r.style.color = '#8b949e';
r.style.padding = '3px 0';
var dollars2 = a.value>=1e6 ? '$'+(a.value/1e6).toFixed(1)+'M' : '$'+Math.round(a.value/1e3)+'K';
r.textContent = '· '+a.agency+' — '+dollars2;
fCard.appendChild(r);
});
}
if(fed.source_url){
var lnk = document.createElement('a');
lnk.href = fed.source_url;
lnk.target = '_blank';
lnk.style.display = 'inline-block';
lnk.style.marginTop = '8px';
lnk.textContent = 'View on usaspending.gov ↗';
fCard.appendChild(lnk);
}
} else if(fed.status==='no_match'){
big(fCard, 'No federal contracts', 'on file under this name');
} else {
empty(fCard, 'usaspending error');
}
grid.appendChild(fCard);
// Debarment + NLRB combined
var rCard = card('DEBARMENT + LABOR ACTIONS');
var deb = d.debarment || {};
var nlrb = d.nlrb || {};
rowEl(rCard, 'SAM.gov excluded', deb.status==='needs_setup' ? 'awaiting API key' : (deb.sam_excluded?'YES':'no'));
rowEl(rCard, 'IDOL debarred', deb.status==='needs_setup' ? 'awaiting scrape' : (deb.idol_debarred?'YES':'no'));
rowEl(rCard, 'NLRB cases', nlrb.status==='needs_setup' ? 'awaiting scrape' : (nlrb.total_cases||0));
if(deb.status==='needs_setup' || nlrb.status==='needs_setup'){
var dn = document.createElement('div');
dn.className = 'empty';
dn.style.marginTop = '8px';
dn.textContent = 'Both sources pending wire-up: '+(deb.reason||nlrb.reason||'');
rCard.appendChild(dn);
}
grid.appendChild(rCard);
// ILSOS
var iCard = card('CORPORATE REGISTRY (Illinois SoS)');
var ilsos = d.ilsos || {};
if(ilsos.status==='source_unreachable'){
rowEl(iCard, 'Status', 'source blocked at our ASN');
var en = document.createElement('div');
en.className = 'empty';
en.style.marginTop = '8px';
en.textContent = ilsos.reason||'';
iCard.appendChild(en);
} else if(ilsos.status==='ok'){
rowEl(iCard, 'Entity name', ilsos.entity_name||'?');
rowEl(iCard, 'File #', ilsos.file_number||'?');
rowEl(iCard, 'Status', ilsos.status_text||'?');
rowEl(iCard, 'Formed', ilsos.formation_date||'?');
rowEl(iCard, 'Registered agent', ilsos.registered_agent||'?');
} else {
empty(iCard, 'no ILSOS data');
}
grid.appendChild(iCard);
out.appendChild(grid);
// ─── Project Index summary — the staffer-facing build-signal score ──
var pixHeader = document.createElement('div');
pixHeader.className = 'section-label';
pixHeader.textContent = '◆ Project Index — build-signal score';
out.appendChild(pixHeader);
var pixCard = document.createElement('div');
pixCard.className = 'card wide';
// Score is a simple weighted blend of the wired signals — designed to
// be replaced with a real model once enough placeholders are wired.
var hist2 = d.history || {};
var pixScore = 0;
var pixDrivers = [];
if(hist2.permits_last_180d){ pixScore += Math.min(hist2.permits_last_180d * 5, 30); pixDrivers.push(hist2.permits_last_180d+' Chicago permits in 180d (+'+Math.min(hist2.permits_last_180d*5,30)+')'); }
if(hist2.trend === 'rising'){ pixScore += 10; pixDrivers.push('permit trend rising (+10)'); }
if(d.osha && d.osha.status==='ok' && d.osha.inspection_count>0){ pixScore -= Math.min(d.osha.inspection_count*5, 25); pixDrivers.push(d.osha.inspection_count+' OSHA inspections (-'+Math.min(d.osha.inspection_count*5,25)+')'); }
if(d.federal && d.federal.status==='ok' && d.federal.total_awards_count>0){ pixScore += 15; pixDrivers.push('federally-vetted contractor (+15)'); }
if(d.debarment && d.debarment.sam_excluded){ pixScore -= 50; pixDrivers.push('SAM.gov excluded (-50)'); }
if(d.stock && d.stock.status==='ok'){ pixScore += 5; pixDrivers.push('public ticker (+5)'); }
pixScore = Math.max(0, Math.min(100, 50 + pixScore));
var pixColor = pixScore >= 70 ? '#3fb950' : pixScore >= 40 ? '#d29922' : '#f85149';
var pixHero = document.createElement('div');
pixHero.style.cssText = 'display:flex;align-items:baseline;gap:14px;margin-bottom:8px';
var pixBig = document.createElement('span');
pixBig.style.cssText = 'font-size:42px;font-weight:700;color:'+pixColor+';letter-spacing:-1px';
pixBig.textContent = pixScore;
pixHero.appendChild(pixBig);
var pixLabel = document.createElement('span');
pixLabel.style.cssText = 'font-size:12px;color:#8b949e';
pixLabel.textContent = pixScore >= 70 ? 'Strong staffing partner — wired signals positive' : pixScore >= 40 ? 'Mixed signals — review drivers below' : 'Caution — wired signals negative';
pixHero.appendChild(pixLabel);
pixCard.appendChild(pixHero);
if(pixDrivers.length){
var pixDrv = document.createElement('div');
pixDrv.style.cssText = 'font-size:11px;color:#8b949e;line-height:1.7;font-family:ui-monospace,monospace';
pixDrv.textContent = pixDrivers.join(' · ');
pixCard.appendChild(pixDrv);
}
var pixFoot = document.createElement('div');
pixFoot.style.cssText = 'font-size:10px;color:#545d68;margin-top:8px;font-style:italic;line-height:1.5';
pixFoot.textContent = 'Score is a placeholder weighted blend of the 6 wired signals above. Real ML model lands once 12 awaiting sources below ship — that gives the index 18 features instead of 6.';
pixCard.appendChild(pixFoot);
out.appendChild(pixCard);
// ─── Heat map — every Chicago permit they're contact_1 or contact_2 on ─
var mapHeader = document.createElement('div');
mapHeader.className = 'section-label';
mapHeader.textContent = '◆ Where they\'ve worked — Chicago permits, last 24 months';
out.appendChild(mapHeader);
var mapCard = document.createElement('div');
mapCard.className = 'card wide';
var mapDiv = document.createElement('div');
mapDiv.className = 'heatmap';
mapDiv.id = 'cmap';
mapCard.appendChild(mapDiv);
var mapHint = document.createElement('div');
mapHint.style.cssText = 'font-size:11px;color:#545d68;margin-top:8px';
mapHint.textContent = 'Loading geo from chicago_permits…';
mapCard.appendChild(mapHint);
out.appendChild(mapCard);
// Plot the recent_permits embedded in the contractor profile (now
// includes lat/lng/permit_id/description per the entity.ts change).
// Color by cost: green <$100K, amber $100K-$1M, red ≥$1M.
var permits = (hist2.recent_permits||[]).filter(function(p){return p.lat&&p.lng});
if(!permits.length){
mapHint.textContent = 'No geocoded permits in the contractor history (Socrata may not have lat/lng for these records).';
} else {
// Construct map only after the div is in the DOM; defer one tick.
setTimeout(function(){
var map = L.map('cmap', {zoomControl:true, attributionControl:false}).setView([41.88,-87.63], 11);
L.tileLayer('https://{s}.basemaps.cartocdn.com/dark_all/{z}/{x}/{y}{r}.png',{maxZoom:19}).addTo(map);
var bounds = [];
var costs = permits.map(function(p){return Number(p.cost)||0});
var maxCost = Math.max.apply(null, costs.concat([1]));
permits.forEach(function(p){
var c = Number(p.cost)||0;
var radius = 4 + (c/maxCost)*16;
var color = c >= 1000000 ? '#f85149' : c >= 100000 ? '#d29922' : '#3fb950';
var marker = L.circleMarker([p.lat,p.lng],{radius:radius, color:color, weight:1, fillOpacity:0.55});
// Build popup via DOM (no innerHTML — keeps the XSS hook happy)
var pop = document.createElement('div');
pop.style.cssText = 'font-family:ui-monospace,monospace;font-size:11px;color:#0a0d12;min-width:160px';
var costRow = document.createElement('div');
costRow.style.cssText = 'font-weight:700;margin-bottom:4px';
costRow.textContent = '$'+c.toLocaleString()+' · '+(p.date||'?');
pop.appendChild(costRow);
var wt = document.createElement('div');
wt.textContent = p.work_type||'?';
pop.appendChild(wt);
var addr = document.createElement('div');
addr.style.color = '#545d68';
addr.textContent = p.address||'?';
pop.appendChild(addr);
if(p.permit_id){
var pid = document.createElement('div');
pid.style.cssText = 'color:#545d68;margin-top:4px;font-size:10px';
pid.textContent = 'permit '+p.permit_id;
pop.appendChild(pid);
}
marker.bindPopup(pop);
marker.addTo(map);
bounds.push([p.lat, p.lng]);
});
if(bounds.length>1) map.fitBounds(bounds, {padding:[24,24]});
mapHint.textContent = permits.length+' permits plotted · green <$100K, amber $100K-$1M, red ≥$1M · radius: relative cost';
}, 50);
}
// ─── History timeline — monthly permit volume + cost trend ─────────
if(hist2.recent_permits && hist2.recent_permits.length){
var tlHeader = document.createElement('div');
tlHeader.className = 'section-label';
tlHeader.textContent = '◆ Activity timeline — Chicago permits by month';
out.appendChild(tlHeader);
var tlCard = document.createElement('div');
tlCard.className = 'card wide';
// Bucket by year-month
var buckets = {};
hist2.recent_permits.forEach(function(p){
var d = (p.date||'').substring(0,7); // YYYY-MM
if(!d) return;
buckets[d] = buckets[d] || {count:0, cost:0};
buckets[d].count++;
buckets[d].cost += Number(p.cost)||0;
});
var months = Object.keys(buckets).sort();
if(months.length){
var maxC = Math.max.apply(null, months.map(function(m){return buckets[m].count}));
var tl = document.createElement('div'); tl.className='timeline';
months.forEach(function(m){
var b = buckets[m];
var bar = document.createElement('div'); bar.className='tbar';
bar.style.height = Math.max(2, Math.round(b.count/maxC*72)) + 'px';
bar.title = m+' · '+b.count+' permit'+(b.count===1?'':'s')+' · $'+Math.round(b.cost).toLocaleString();
tl.appendChild(bar);
});
tlCard.appendChild(tl);
var ax = document.createElement('div'); ax.className='timeline-axis';
var first = document.createElement('span'); first.textContent = months[0];
var last = document.createElement('span'); last.textContent = months[months.length-1];
ax.appendChild(first); ax.appendChild(last);
tlCard.appendChild(ax);
}
out.appendChild(tlCard);
}
// ─── 12 awaiting-source placeholders ──────────────────────────────
// Each one names a real public data source that would feed the
// build-signal index, with a one-line "why a staffer cares" framing
// and a sample shape of what the panel would show once wired.
var phHeader = document.createElement('div');
phHeader.className = 'section-label';
phHeader.textContent = '◆ 12 awaiting sources — what plugs in next';
out.appendChild(phHeader);
var phGrid = document.createElement('div');
phGrid.className = 'placeholder-grid';
PLACEHOLDERS.forEach(function(p){
var c = document.createElement('div'); c.className='ph-card';
var h = document.createElement('h4');
var name = document.createElement('span'); name.textContent = p.name;
var badge = document.createElement('span'); badge.className='badge'; badge.textContent='AWAITING';
h.appendChild(name); h.appendChild(badge);
c.appendChild(h);
var why = document.createElement('div'); why.className='why'; why.textContent = p.why;
c.appendChild(why);
var would = document.createElement('div'); would.className='would';
would.textContent = 'Would show: ' + p.would;
c.appendChild(would);
phGrid.appendChild(c);
});
out.appendChild(phGrid);
// Roadmap footer
var foot = document.createElement('div');
foot.style.marginTop = '20px';
foot.style.fontSize = '10px';
foot.style.color = '#484f58';
foot.style.lineHeight = '1.6';
foot.textContent = 'Wired: OSHA Enforcement · SEC EDGAR + Stooq · Chicago Socrata permits (lat/lng) · USASpending.gov · curated parent-ticker map · ILSOS (datacenter ASN blocked). 12 awaiting sources above are real public datasets that would 3× the feature count of the build-signal index — each one labeled with the one-liner the staffer would ask before placing a worker.';
out.appendChild(foot);
}
// Twelve real public data sources, framed in coordinator language.
// Each is a placeholder; the panel renders them as "AWAITING" with a
// description of what they'd add once wired. Order is roughly: highest
// staffing-decision relevance first.
var PLACEHOLDERS = [
{
name: 'DOL Wage & Hour (WHD)',
why: 'Has this contractor stiffed workers before? WHD posts every back-wage settlement and unpaid-overtime case.',
would: 'cases last 24mo · total back wages owed · status by state · most recent settlement date · whether the workers got paid',
},
{
name: 'State Licensure Boards',
why: 'Is the contractor legally allowed to do this work today, in this state?',
would: 'license # · status (active / expired / suspended) · trade scope · expiration date · disciplinary history',
},
{
name: 'Surety Bond Capacity',
why: 'How big a job can this contractor actually take? Bond ceiling = upper bound on what they\'re bonded for.',
would: 'bonding company · single-contract ceiling · aggregate cap · current utilization · recent bond denials',
},
{
name: 'EPA ECHO Compliance',
why: 'If a worker shows up to a site with hazmat issues, that\'s the staffing company\'s problem too.',
would: 'facility-level violations · last enforcement action · pollutants · whether OSHA escalated',
},
{
name: 'DOT/FMCSA Carrier Safety',
why: 'For warehouses with on-site driving or carriers we cross-staff: crash rate, driver out-of-service rate, IFTA filings.',
would: 'crash rate per million miles · driver OOS % · vehicle OOS % · safety rating · last compliance review',
},
{
name: 'BBB Complaints + Rating',
why: 'What do this contractor\'s own employees say happens to them? BBB aggregates complaints from workers and clients.',
would: 'rating · complaint count last 36mo · complaint categories (pay, safety, ghosted) · response rate',
},
{
name: 'PACER Civil Suits (Federal)',
why: 'Are they being sued for FLSA, discrimination, or wrongful termination? Filings predate enforcement actions.',
would: 'open suits · FLSA / Title VII / ADA breakdowns · counterparties · year-over-year filing rate',
},
{
name: 'UCC Lien Filings',
why: 'When a contractor stops paying suppliers, mechanics liens hit the public record. Cash-flow distress signal.',
would: 'open liens · total face value · filers (suppliers, banks) · last filing · whether resolved',
},
{
name: 'D&B / Credit Bureau',
why: 'Will they pay our staffing invoices? D&B PAYDEX score is the standard.',
would: 'PAYDEX (1-100) · days-beyond-terms · credit limit recommendation · UCC link · trade payment trend',
},
{
name: 'State UI Employer Claims',
why: 'Workforce stability proxy. A spike in unemployment claims at this employer = layoffs or churn we should know about.',
would: 'claims filed against this employer last 12mo · approval rate · separation-reason breakdown',
},
{
name: 'MSHA Mine Safety',
why: 'For excavation, demolition, materials, aggregate — MSHA owns the citation history.',
would: 'citations · S&S violations · most recent fatality / serious injury · pattern-of-violation flag',
},
{
name: 'Registered Apprenticeships (DOL RAPIDS)',
why: 'A contractor with active apprenticeship programs has built a workforce pipeline — different staffing partnership story than one without.',
would: 'active programs · apprentice count · trades covered · graduation rate · ethnic/gender diversity reported',
},
];
function card(title){
var c = document.createElement('div');
c.className = 'card';
var h = document.createElement('h3');
h.textContent = title;
c.appendChild(h);
return c;
}
function big(c, value, sub){
var b = document.createElement('div'); b.className='big'; b.textContent=value;
var s = document.createElement('div'); s.className='sub'; s.textContent=sub;
c.appendChild(b); c.appendChild(s);
}
function rowEl(c, label, value){
var r = document.createElement('div'); r.className='row';
var l = document.createElement('span'); l.className='l'; l.textContent=label;
var v = document.createElement('span'); v.className='v'; v.textContent=value||'—';
r.appendChild(l); r.appendChild(v); c.appendChild(r);
}
function empty(c, msg){
var e = document.createElement('div'); e.className='empty'; e.textContent=msg;
c.appendChild(e);
}
</script>
</body></html>

2821
mcp-server/entity.ts Normal file
View File

File diff suppressed because it is too large Load Diff

123
mcp-server/icon_recipes.ts Normal file
View File

@ -0,0 +1,123 @@
// Visual filler iconography rendered through ComfyUI. Distinct from
// role_scenes.ts (which renders portraits) — these are object/badge
// style renders that fill dead space on worker cards: cert pills,
// role-prop chips, hazard indicators, empty-state heroes.
//
// Layout on disk:
// data/icons_pool/{category}/{slug}.webp
//
// Cache invalidation:
// ICONS_VERSION mixes into the on-disk filename (slug includes
// version). Bump it after editing a recipe so prior renders are
// ignored on next view.
export type IconCategory = "cert" | "role_prop" | "status" | "hazard" | "empty";
export interface IconRecipe {
slug: string;
category: IconCategory;
// Text label that appears next to / under the icon. The front-end
// already renders this text in cert pills; the icon is supplementary.
display: string;
// Full diffusion prompt. Style guidance baked in. SDXL Turbo at 8
// steps reliably produces clean macro photography, so default to
// photographic prop shots over flat-vector illustrations (the model
// hallucinates noise into flat-vector geometry at low step counts).
prompt: string;
// Negative prompt — what NOT to render. Crucial for icons because
// SDXL likes to add hands/text/people unprompted.
negative?: string;
}
// Default negative prompt baked into every icon render unless the
// recipe overrides. Empirically, these terms are the top SDXL Turbo
// off-style failures.
export const DEFAULT_NEGATIVE =
"people, hands, faces, blurry, low quality, watermark, signature, "
+ "logos, copyright, distorted text, garbled letters, multiple objects";
// TODO J — review and tune the prompts here. Each one is what diffusion
// sees verbatim. The visual decision: photographic prop shots (macro
// photo of an actual badge / placard / sticker) vs flat-icon vector
// style. Default below is photographic — matches the worker headshot
// aesthetic. Flip a recipe to flat-vector by replacing "macro photograph"
// with "flat icon illustration on solid color background, minimal vector".
//
// Visual cues that work well in SDXL Turbo at 8 steps:
// - "macro photograph", "isolated on plain background", "studio lighting"
// - Concrete colors ("orange and black warning diamond") not adjectives
// - Avoid: small text in the prompt (model garbles it), specific brand
// names (creates fake logos), detailed scene composition
const CERT_ICONS: IconRecipe[] = [
{ slug: "osha-10", category: "cert", display: "OSHA-10",
prompt: "macro photograph of a circular yellow safety badge with a black hard hat icon at center, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "osha-30", category: "cert", display: "OSHA-30",
prompt: "macro photograph of a circular orange safety badge with a black hard hat icon at center, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "first-aid-cpr", category: "cert", display: "First Aid/CPR",
prompt: "macro photograph of a small enamel pin badge featuring a bold red cross on a white circular background, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "hazmat", category: "cert", display: "Hazmat",
prompt: "macro photograph of a HAZMAT warning placard, bold orange and black diamond shape with a flame icon, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "forklift", category: "cert", display: "Forklift",
prompt: "macro photograph of a yellow industrial forklift safety badge with a forklift silhouette icon, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "reach-truck", category: "cert", display: "Reach Truck",
prompt: "macro photograph of a navy blue industrial certification badge with a warehouse reach-truck silhouette icon, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "order-picker", category: "cert", display: "Order Picker",
prompt: "macro photograph of a green industrial certification badge with a warehouse order-picker silhouette icon, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "lockout-tagout", category: "cert", display: "Lockout/Tagout",
prompt: "macro photograph of a bright red padlock tag with a danger warning, hanging on a metal industrial valve, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "msds", category: "cert", display: "MSDS",
prompt: "macro photograph of a folded chemical safety data sheet booklet with chemical hazard pictograms visible on cover, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "confined-space", category: "cert", display: "Confined Space",
prompt: "macro photograph of a yellow confined space warning sign featuring a manhole entry icon, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "servsafe", category: "cert", display: "ServSafe",
prompt: "macro photograph of a dark green food safety certification badge featuring a stylized chef hat icon, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "fire-safety", category: "cert", display: "Fire Safety",
prompt: "macro photograph of a red enamel pin badge featuring a flame icon and a fire extinguisher silhouette, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "iso-9001", category: "cert", display: "ISO 9001",
prompt: "macro photograph of a deep blue circular quality-management certification seal with embossed metallic ring, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
];
// Role-band visual chips — small icons that go in the role pill area.
// One per band, optional inline supplement to the existing colored pill.
const ROLE_PROP_ICONS: IconRecipe[] = [
{ slug: "warehouse", category: "role_prop", display: "Warehouse",
prompt: "macro photograph of a yellow hard hat with a high-visibility safety vest folded behind it, isolated on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "production", category: "role_prop", display: "Production",
prompt: "macro photograph of a navy blue work shirt and protective safety glasses on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "trades", category: "role_prop", display: "Trades",
prompt: "macro photograph of a leather work glove and a small adjustable wrench on a neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "driver", category: "role_prop", display: "Driver",
prompt: "macro photograph of a navy delivery driver baseball cap and a clipboard manifest on a neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
{ slug: "lead", category: "role_prop", display: "Lead",
prompt: "macro photograph of a tablet showing a bar chart and a high-vis vest folded beside it on neutral grey backdrop, photorealistic, sharp focus, studio lighting" },
];
export const ICONS: Record<string, IconRecipe> = Object.fromEntries(
[...CERT_ICONS, ...ROLE_PROP_ICONS].map((r) => [`${r.category}/${r.slug}`, r]),
);
// v2 — 256×256 canvas, intended to be displayed monochrome via CSS
// `filter: grayscale(1)`. Smaller canvas, tighter crops, crisper at
// 14px display size.
export const ICONS_VERSION = "v2";
// Map a free-form cert string from the data ("First Aid/CPR",
// "OSHA-10", "Lockout/Tagout") to the canonical slug used here.
// Returns null if no recipe matches.
export function certToSlug(cert: string): string | null {
const c = (cert || "").trim().toLowerCase().replace(/\s+/g, "-");
if (c === "osha-10") return "osha-10";
if (c === "osha-30") return "osha-30";
if (c.startsWith("first") || c.includes("cpr")) return "first-aid-cpr";
if (c === "hazmat" || c.startsWith("hazwoper")) return "hazmat";
if (c === "forklift" || c.startsWith("pit")) return "forklift";
if (c.startsWith("reach")) return "reach-truck";
if (c.startsWith("order")) return "order-picker";
if (c.startsWith("lockout") || c.includes("tagout")) return "lockout-tagout";
if (c === "msds" || c.startsWith("ghs")) return "msds";
if (c.startsWith("confined")) return "confined-space";
if (c === "servsafe") return "servsafe";
if (c.startsWith("fire")) return "fire-safety";
if (c.startsWith("iso")) return "iso-9001";
return null;
}

1132
mcp-server/index.ts
View File

File diff suppressed because it is too large Load Diff

18
mcp-server/observer.ts
View File

@ -146,15 +146,16 @@ async function persistOp(op: ObservedOp) {
// ─── LLM Team escalation (code_review mode) ─── // ─── LLM Team escalation (code_review mode) ───
// //
// When recent failures on a single sig_hash cross a threshold the // When recent failures on a single sig_hash cross a threshold the
// local qwen2.5 analysis is probably insufficient. J's 2026-04-24 // local-model analysis is probably insufficient. J's 2026-04-24
// direction: "the observer would trigger to give more context" — // direction: "the observer would trigger to give more context" —
// route failure clusters to LLM Team's specialized code_review mode // route failure clusters to LLM Team's specialized code_review mode
// (via /api/run) so richer structured signal lands in the KB for // (via /api/run) so richer structured signal lands in the KB for
// scrum + auditor + playbook memory to consume next pass. // scrum + auditor + playbook memory to consume next pass.
// //
// Non-destructive: runs in parallel to the existing qwen2.5 analysis, // Non-destructive: runs in parallel to the existing local diagnose
// never replaces it. Writes to data/_kb/observer_escalations.jsonl // call (qwen3.5:latest after the 2026-04-30 bump), never replaces
// as a dedicated audit surface. // it. Writes to data/_kb/observer_escalations.jsonl as a dedicated
// audit surface.
const LLM_TEAM = process.env.LH_LLM_TEAM_URL ?? "http://localhost:5000"; const LLM_TEAM = process.env.LH_LLM_TEAM_URL ?? "http://localhost:5000";
const LLM_TEAM_ESCALATIONS = "/home/profit/lakehouse/data/_kb/observer_escalations.jsonl"; const LLM_TEAM_ESCALATIONS = "/home/profit/lakehouse/data/_kb/observer_escalations.jsonl";
@ -542,7 +543,7 @@ async function analyzeErrors() {
if (failures.length === 0) return; if (failures.length === 0) return;
// NEW 2026-04-24: escalate recurring sig_hash clusters to LLM Team // NEW 2026-04-24: escalate recurring sig_hash clusters to LLM Team
// code_review mode. Runs in parallel to the local qwen2.5 analysis // code_review mode. Runs in parallel to the local diagnose call
// below — non-blocking, richer downstream signal for scrum/auditor. // below — non-blocking, richer downstream signal for scrum/auditor.
maybeEscalate(failures).catch(() => {}); maybeEscalate(failures).catch(() => {});
@ -552,13 +553,14 @@ async function analyzeErrors() {
// Ask local model to diagnose. Phase 44 migration (2026-04-27): // Ask local model to diagnose. Phase 44 migration (2026-04-27):
// /v1/chat instead of legacy /ai/generate so /v1/usage tracks the // /v1/chat instead of legacy /ai/generate so /v1/usage tracks the
// call + Langfuse traces it. Same upstream model (qwen2.5 local). // call + Langfuse traces it. 2026-04-30 model bump: qwen2.5 →
// qwen3.5:latest to match the small-model-pipeline local-tier default.
try { try {
const resp = await fetch(`${LAKEHOUSE}/v1/chat`, { const resp = await fetch(`${LAKEHOUSE}/v1/chat`, {
method: "POST", method: "POST",
headers: { "Content-Type": "application/json" }, headers: { "Content-Type": "application/json" },
body: JSON.stringify({ body: JSON.stringify({
model: "qwen2.5", model: "qwen3.5:latest",
provider: "ollama", provider: "ollama",
messages: [{ messages: [{
role: "user", role: "user",
@ -769,7 +771,7 @@ async function tailOverseerCorrections(): Promise<number> {
try { row = JSON.parse(line); } catch { continue; } try { row = JSON.parse(line); } catch { continue; }
const op: ObservedOp = { const op: ObservedOp = {
timestamp: row.created_at ?? new Date().toISOString(), timestamp: row.created_at ?? new Date().toISOString(),
endpoint: `overseer:${row.model ?? "gpt-oss:120b"}`, endpoint: `overseer:${row.model ?? "claude-opus-4-7"}`,
input_summary: `${row.task_class ?? "?"}: ${row.reason ?? "escalation"}`, input_summary: `${row.task_class ?? "?"}: ${row.reason ?? "escalation"}`,
// Correction itself is neither success nor failure — it's a // Correction itself is neither success nor failure — it's a
// mitigation attempt. We mark success=true so analyzeErrors // mitigation attempt. We mark success=true so analyzeErrors

599
mcp-server/profiler.html Normal file
View File

@ -0,0 +1,599 @@
<!DOCTYPE html>
<html><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
<title>Profiler Index · Staffing Co-Pilot</title>
<link rel="stylesheet" href="https://unpkg.com/leaflet@1.9.4/dist/leaflet.css">
<script src="https://unpkg.com/leaflet@1.9.4/dist/leaflet.js"></script>
<style>
*{margin:0;padding:0;box-sizing:border-box}
html,body{overflow-x:hidden}
body{font-family:'Inter',-apple-system,system-ui,sans-serif;background:#090c10;color:#b0b8c4;font-size:14px;line-height:1.6}
.bar{background:#0d1117;padding:0 24px;height:56px;border-bottom:1px solid #171d27;display:flex;justify-content:space-between;align-items:center}
.bar h1{font-size:14px;font-weight:600;color:#e6edf3}
.bar nav a{color:#545d68;text-decoration:none;font-size:12px;padding:6px 14px;border-radius:6px;margin-left:4px}
.bar nav a:hover{color:#e6edf3;background:#161b22}
.content{max-width:1200px;margin:0 auto;padding:24px 20px 40px}
.controls{background:#0d1117;border:1px solid #171d27;border-radius:10px;padding:16px;margin-bottom:14px;display:flex;gap:10px;align-items:center;flex-wrap:wrap}
.controls input,.controls select{padding:9px 12px;background:#161b22;border:1px solid #21262d;border-radius:6px;color:#e6edf3;font-size:13px;outline:none}
.controls input:focus,.controls select:focus{border-color:#388bfd}
.controls input.s{flex:1;min-width:240px}
.controls .meta{font-size:11px;color:#8b949e;margin-left:auto}
.summary{background:#0d1117;border:1px solid #171d27;border-radius:10px;padding:14px 16px;margin-bottom:14px;font-size:12px;color:#8b949e}
.summary b{color:#e6edf3;font-weight:600}
table{width:100%;border-collapse:collapse;background:#0d1117;border:1px solid #171d27;border-radius:10px;overflow:hidden}
th{font-size:10px;color:#545d68;text-transform:uppercase;letter-spacing:1.2px;font-weight:600;text-align:left;padding:12px;background:#0a0d12;border-bottom:1px solid #171d27;cursor:pointer;user-select:none}
th:hover{color:#e6edf3}
th .arrow{font-size:9px;margin-left:4px;color:#388bfd}
td{padding:11px 12px;border-bottom:1px solid #1f2631;font-size:13px}
tr:last-child td{border-bottom:none}
tr:hover td{background:#0a0d12}
td.name a{color:#58a6ff;text-decoration:none;font-weight:600}
td.name a:hover{text-decoration:underline}
td.right{text-align:right;font-family:ui-monospace,monospace;font-variant-numeric:tabular-nums}
td.role{font-size:10px;color:#8b949e}
td.role .pill{display:inline-block;padding:2px 7px;border-radius:9px;font-size:9px;font-weight:600;background:#161b22;border:1px solid #21262d;color:#8b949e;margin-right:4px;text-transform:uppercase;letter-spacing:0.5px}
.tickers{display:flex;gap:4px;flex-wrap:wrap;margin-top:3px}
.ticker-pill{display:inline-block;padding:1px 7px;border-radius:5px;font-size:10px;font-weight:700;font-family:ui-monospace,SFMono-Regular,monospace;letter-spacing:0.3px;cursor:help}
.ticker-pill.direct{background:#0d2818;border:1px solid #2ea04388;color:#3fb950}
.ticker-pill.parent{background:#1a1410;border:1px solid #d2992288;color:#d29922}
.ticker-pill.associated{background:#0d1830;border:1px solid #58a6ff66;color:#58a6ff}
.ticker-pill.exact{background:#0d2818;border:1px solid #2ea043;color:#3fb950}
/* Hero — the thesis panel that frames the data corpus's value. */
.thesis{background:linear-gradient(135deg,#0d2818 0%,#0d1830 50%,#1a1410 100%);border:1px solid #2ea04344;border-radius:12px;padding:18px 22px;margin-bottom:14px;position:relative;overflow:hidden}
.thesis::before{content:'';position:absolute;top:0;left:0;right:0;height:2px;background:linear-gradient(90deg,#3fb950 0%,#58a6ff 50%,#d29922 100%)}
.thesis h2{font-size:18px;color:#e6edf3;font-weight:700;letter-spacing:-0.4px;margin-bottom:6px}
.thesis .sub{font-size:12px;color:#8b949e;line-height:1.6;margin-bottom:14px;max-width:880px}
.thesis .sub b{color:#3fb950;font-weight:600}
.bai-row{display:flex;gap:24px;align-items:baseline;flex-wrap:wrap;margin-bottom:14px}
.bai-block{display:flex;flex-direction:column;gap:2px}
.bai-label{font-size:9px;color:#545d68;text-transform:uppercase;letter-spacing:1.4px;font-weight:700}
.bai-value{font-size:26px;font-weight:700;color:#e6edf3;font-family:ui-monospace,monospace;letter-spacing:-0.5px;font-variant-numeric:tabular-nums}
.bai-value.up{color:#3fb950}
.bai-value.down{color:#f85149}
.bai-sub{font-size:10px;color:#8b949e;margin-top:1px}
.markets-strip{display:flex;gap:6px;flex-wrap:wrap;font-size:10px}
.market-pill{padding:3px 9px;border-radius:9px;font-weight:600;border:1px solid;letter-spacing:0.4px}
.market-pill.live{background:#0d2818;border-color:#3fb950;color:#3fb950}
.market-pill.next{background:#0d1830;border-color:#58a6ff;color:#58a6ff}
.market-pill.queue{background:#161b22;border-color:#21262d;color:#545d68}
.market-pill.queue::before{content:'· '}
/* Map panel below basket — populates when a ticker is selected. */
.signal-map-wrap{display:none;background:#0d1117;border:1px solid #171d27;border-radius:10px;padding:14px;margin-bottom:14px}
.signal-map-wrap.active{display:block}
.signal-map-header{display:flex;justify-content:space-between;align-items:baseline;margin-bottom:10px}
.signal-map-title{font-size:11px;color:#545d68;text-transform:uppercase;letter-spacing:1.2px;font-weight:600}
.signal-map-title b{color:#58a6ff;font-family:ui-monospace,monospace}
.signal-map-meta{font-size:11px;color:#8b949e}
.signal-map{height:340px;border-radius:8px;border:1px solid #1f2631;overflow:hidden}
.signal-map .leaflet-container{background:#0a0d12}
/* Scrolling ticker basket — top strip showing every public issuer
the profiler index has surfaced, with live price + day-change. */
.basket-wrap{background:#0a0d12;border:1px solid #171d27;border-radius:10px;margin-bottom:14px;overflow:hidden;position:relative}
.basket-label{padding:10px 16px 4px;font-size:10px;color:#545d68;text-transform:uppercase;letter-spacing:1.3px;font-weight:600;display:flex;justify-content:space-between;align-items:baseline}
.basket-label .meta{font-weight:400;color:#3d444d;font-size:10px;text-transform:none;letter-spacing:0}
.basket-track{display:flex;gap:0;overflow-x:auto;scroll-behavior:smooth;padding:6px 8px 12px;scrollbar-width:thin;scrollbar-color:#21262d transparent}
.basket-track::-webkit-scrollbar{height:6px}
.basket-track::-webkit-scrollbar-thumb{background:#21262d;border-radius:3px}
.basket-track::-webkit-scrollbar-thumb:hover{background:#388bfd}
.bk-card{flex:0 0 auto;min-width:140px;background:#0d1117;border:1px solid #21262d;border-radius:8px;padding:10px 12px;margin:0 4px;cursor:pointer;transition:all 0.12s;position:relative}
.bk-card:hover{border-color:#58a6ff;background:#0d1a30;transform:translateY(-1px)}
.bk-card.selected{border-color:#58a6ff;background:#0d1a30;box-shadow:0 0 0 1px #58a6ff;}
.bk-card .tk{font-family:ui-monospace,SFMono-Regular,monospace;font-size:13px;font-weight:700;color:#e6edf3;letter-spacing:0.3px}
.bk-card .px{font-family:ui-monospace,SFMono-Regular,monospace;font-size:14px;font-weight:600;color:#e6edf3;margin-top:3px;font-variant-numeric:tabular-nums}
.bk-card .ch{font-family:ui-monospace,monospace;font-size:11px;margin-top:1px;font-variant-numeric:tabular-nums}
.bk-card .ch.up{color:#3fb950}
.bk-card .ch.down{color:#f85149}
.bk-card .ch.flat{color:#545d68}
.bk-card .meta{font-size:9px;color:#545d68;margin-top:5px;text-transform:uppercase;letter-spacing:0.6px}
.bk-card .kind-bar{position:absolute;left:0;top:0;bottom:0;width:3px;border-radius:8px 0 0 8px}
.bk-card .kind-bar.exact,.bk-card .kind-bar.direct{background:#3fb950}
.bk-card .kind-bar.parent{background:#d29922}
.bk-card .kind-bar.associated{background:#58a6ff}
.bk-card .kind-bar.mixed{background:linear-gradient(180deg,#3fb950 0%,#58a6ff 100%)}
.bk-card.no-quote .px{color:#545d68}
.basket-empty{padding:18px;font-size:11px;color:#545d68;font-style:italic;text-align:center}
.basket-clear{margin-left:8px;font-size:10px;color:#58a6ff;cursor:pointer;border:none;background:none;text-decoration:underline}
.cost-band-1{color:#3fb950}
.cost-band-2{color:#d29922}
.cost-band-3{color:#f85149}
.loading{text-align:center;padding:60px;font-size:13px;color:#3d444d}
.empty{text-align:center;padding:40px;font-size:12px;color:#545d68;font-style:italic}
.foot{margin-top:14px;font-size:10px;color:#484f58;line-height:1.6}
@media(max-width:640px){.bar{padding:0 14px}.content{padding:14px}th,td{padding:8px 6px;font-size:11px}}
</style>
</head><body>
<div class="bar">
<h1>Staffing Co-Pilot · Profiler Index</h1>
<nav>
<a href="" id="back-dashboard">← Dashboard</a>
<a href="" id="back-console">Console</a>
</nav>
</div>
<div class="content">
<!-- Hero thesis — frames what this data corpus actually is. The
profiler index isn't just a contractor directory; it's a
construction-activity signal that surfaces public issuers months
before quarterly earnings does. Each metric here is computed
from the live data, not pre-baked. -->
<div class="thesis" id="thesis">
<h2>Chicago Construction Activity Signal Engine</h2>
<div class="sub">
Every contractor name in this corpus is also a forward indicator on the public equities they touch. Permits filed today predict construction starts ~45 days out, staffing windows ~2 weeks before that, and revenue recognition months later. The associated-ticker network surfaces this signal <b>before</b> it lands in any 10-Q.
</div>
<div class="bai-row">
<div class="bai-block">
<span class="bai-label">Building Activity Index — today</span>
<span class="bai-value" id="bai-value">—</span>
<span class="bai-sub" id="bai-sub">awaiting basket prices</span>
</div>
<div class="bai-block">
<span class="bai-label">Indexed build value</span>
<span class="bai-value" id="bav-value">—</span>
<span class="bai-sub" id="bav-sub">across surfaced issuers</span>
</div>
<div class="bai-block">
<span class="bai-label">Network depth</span>
<span class="bai-value" id="net-value">—</span>
<span class="bai-sub" id="net-sub">issuers · attributions</span>
</div>
<div class="bai-block" style="flex:1;min-width:240px">
<span class="bai-label">Market replication roadmap</span>
<div class="markets-strip" style="margin-top:4px">
<span class="market-pill live">Chicago — live</span>
<span class="market-pill next">NYC DOB — adapter ready</span>
<span class="market-pill queue">LA County · Houston BCD · Boston ISD · DC DCRA</span>
</div>
</div>
</div>
</div>
<div class="basket-wrap" id="basket-wrap" style="display:none">
<div class="basket-label">
<span><span id="bk-count">0</span> public issuers in this view <span class="meta" id="bk-meta"></span></span>
<button class="basket-clear" id="bk-clear" style="display:none" type="button">clear filter</button>
</div>
<div class="basket-track" id="basket"></div>
</div>
<!-- Per-ticker permit map — shows where the selected issuer's
attributed contractor activity is actually happening. Same
leaflet pattern as the contractor profile, scoped to one ticker. -->
<div class="signal-map-wrap" id="signal-map-wrap">
<div class="signal-map-header">
<span class="signal-map-title">Where <b id="signal-map-ticker">—</b> activity is happening</span>
<span class="signal-map-meta" id="signal-map-meta">—</span>
</div>
<div class="signal-map" id="signal-map"></div>
</div>
<div class="controls">
<input class="s" id="q" type="text" placeholder="Filter by contractor name (e.g., Target, Turner)" autocomplete="off">
<select id="since">
<option value="2025-06-01">Since June 2025</option>
<option value="2024-01-01">Since 2024</option>
<option value="2020-01-01">Since 2020 (deeper history)</option>
</select>
<select id="min-cost">
<option value="500000">$500K+</option>
<option value="250000" selected>$250K+</option>
<option value="100000">$100K+</option>
<option value="50000">$50K+</option>
</select>
<span class="meta" id="meta">Loading…</span>
</div>
<div class="summary" id="summary" style="display:none"></div>
<div id="result"><div class="loading">Loading the directory from Chicago Socrata…</div></div>
<div class="foot">Aggregations sourced live from data.cityofchicago.org (Building Permits dataset ydr8-5enu). Contractor names appear when listed as contact_1 or contact_2 on a permit. Click any name to open the full profile — heat map, project index, history, 12 awaiting public-data sources.</div>
</div>
<script>
var P=location.pathname.indexOf('/lakehouse')>=0?'/lakehouse':'';
document.getElementById('back-dashboard').href = P+'/';
document.getElementById('back-console').href = P+'/console';
var sortKey='total_cost', sortDir='desc';
var lastRows=[];
var tickerFilter=null; // selected ticker for filtering the table
var lastQuotes={}; // ticker → quote (price, day_change_pct)
var lastBasket=[]; // basket rows aggregated from lastRows
var signalMap=null; // leaflet map instance for the per-ticker view
function clearChildren(el){ while(el.firstChild) el.removeChild(el.firstChild); }
function fmt$(n){
if(n>=1e9) return '$'+(n/1e9).toFixed(2)+'B';
if(n>=1e6) return '$'+(n/1e6).toFixed(1)+'M';
if(n>=1e3) return '$'+(n/1e3).toFixed(0)+'K';
return '$'+Math.round(n||0).toLocaleString();
}
function costClass(n){
if(n>=1e7) return 'cost-band-3';
if(n>=1e6) return 'cost-band-2';
return 'cost-band-1';
}
function load(){
var search=document.getElementById('q').value.trim();
var since=document.getElementById('since').value;
var minCost=parseInt(document.getElementById('min-cost').value,10);
document.getElementById('meta').textContent='Loading…';
var host=document.getElementById('result'); clearChildren(host);
var loading=document.createElement('div'); loading.className='loading';
loading.textContent='Aggregating from Chicago Socrata…';
host.appendChild(loading);
fetch(P+'/intelligence/profiler_index',{
method:'POST',
headers:{'Content-Type':'application/json'},
body:JSON.stringify({since:since,min_cost:minCost,search:search,limit:200})
}).then(function(r){return r.json()}).then(function(d){
lastRows = d.contractors||[];
document.getElementById('meta').textContent=lastRows.length+' contractors · '+(d.duration_ms||0)+'ms';
// Build the ticker basket from the surfaced rows
buildBasket();
var totalCost = lastRows.reduce(function(s,r){return s+(r.total_cost||0)},0);
var totalPermits = lastRows.reduce(function(s,r){return s+(r.permits||0)},0);
var sumDiv=document.getElementById('summary');
sumDiv.style.display='block';
clearChildren(sumDiv);
var b1=document.createElement('b'); b1.textContent=lastRows.length.toLocaleString();
sumDiv.appendChild(b1);
sumDiv.appendChild(document.createTextNode(' contractors · '));
var b2=document.createElement('b'); b2.textContent=totalPermits.toLocaleString();
sumDiv.appendChild(b2);
sumDiv.appendChild(document.createTextNode(' total permits · '));
var b3=document.createElement('b'); b3.textContent=fmt$(totalCost);
sumDiv.appendChild(b3);
sumDiv.appendChild(document.createTextNode(' aggregate value · since '+(d.since||'?')+' · min permit cost '+fmt$(d.min_cost||0)));
render();
}).catch(function(e){
document.getElementById('meta').textContent='error';
var host=document.getElementById('result'); clearChildren(host);
var er=document.createElement('div'); er.className='empty'; er.style.color='#f85149';
er.textContent='Profiler index error: '+e.message;
host.appendChild(er);
});
}
// Aggregate every public ticker the profiler index surfaced, with a
// kind hierarchy (exact > direct > parent > associated) and the count
// of contractors each ticker is attributed to. Then fetch live quotes
// in one batch and render the scrolling basket.
function buildBasket(){
var byTicker = {};
lastRows.forEach(function(r){
var ts = (r.tickers && r.tickers.direct ? r.tickers.direct : []).concat(r.tickers && r.tickers.associated ? r.tickers.associated : []);
ts.forEach(function(t){
if(!t || !t.ticker) return;
if(!byTicker[t.ticker]) byTicker[t.ticker] = {ticker:t.ticker, kinds:new Set(), count:0, contractors:[], matched_name:t.matched_name||t.partner_name||null};
byTicker[t.ticker].kinds.add(t.via);
byTicker[t.ticker].count++;
if(byTicker[t.ticker].contractors.length < 5) byTicker[t.ticker].contractors.push(r.name);
});
});
var basketRows = Object.values(byTicker)
.map(function(b){
// Pick a single 'kind' for the bar color: direct/exact wins, then parent, then associated.
var k = b.kinds.has('exact')?'exact':b.kinds.has('direct')?'direct':b.kinds.has('parent')?'parent':b.kinds.has('associated')?'associated':'mixed';
if(b.kinds.size>1 && (b.kinds.has('exact')||b.kinds.has('direct')) && b.kinds.has('associated')) k='mixed';
return Object.assign({}, b, {kinds:Array.from(b.kinds), kind:k});
})
.sort(function(a,b){return b.count - a.count});
var wrap = document.getElementById('basket-wrap');
var track = document.getElementById('basket');
clearChildren(track);
if(!basketRows.length){
wrap.style.display='block';
var emp=document.createElement('div'); emp.className='basket-empty';
emp.textContent='No public issuers in this view. Try a wider filter or "since 2020" history.';
track.appendChild(emp);
document.getElementById('bk-count').textContent='0';
document.getElementById('bk-meta').textContent='';
return;
}
wrap.style.display='block';
document.getElementById('bk-count').textContent=basketRows.length;
document.getElementById('bk-meta').textContent='loading prices…';
// Render shells immediately, then fill in prices when the batch returns
basketRows.forEach(function(b){
var card=document.createElement('div'); card.className='bk-card no-quote';
card.dataset.ticker=b.ticker;
var bar=document.createElement('div'); bar.className='kind-bar '+b.kind; card.appendChild(bar);
var tk=document.createElement('div'); tk.className='tk'; tk.textContent=b.ticker; card.appendChild(tk);
var px=document.createElement('div'); px.className='px'; px.textContent='—'; card.appendChild(px);
var ch=document.createElement('div'); ch.className='ch flat'; ch.textContent=' '; card.appendChild(ch);
var meta=document.createElement('div'); meta.className='meta';
meta.textContent=b.count+' attribution'+(b.count===1?'':'s')+' · '+b.kinds.join('+');
card.appendChild(meta);
card.title=(b.matched_name||b.ticker)+'\n'+b.contractors.slice(0,5).join('\n')+(b.count>5?'\n…':'');
card.onclick=function(){
tickerFilter = (tickerFilter===b.ticker) ? null : b.ticker;
Array.prototype.forEach.call(track.children, function(c){
c.classList.toggle('selected', c.dataset && c.dataset.ticker===tickerFilter);
});
document.getElementById('bk-clear').style.display = tickerFilter ? 'inline' : 'none';
showSignalMap(tickerFilter);
render();
};
track.appendChild(card);
});
lastBasket = basketRows;
// Update the hero panel right away with what we know without prices
updateThesisMetrics();
// Batch-fetch quotes and update each card + thesis
fetch(P+'/intelligence/ticker_quotes',{
method:'POST',headers:{'Content-Type':'application/json'},
body:JSON.stringify({tickers:basketRows.map(function(b){return b.ticker})})
}).then(function(r){return r.json()}).then(function(qd){
var quotes=qd.quotes||{};
lastQuotes = quotes;
document.getElementById('bk-meta').textContent='quotes via Stooq · '+(qd.duration_ms||0)+'ms';
Array.prototype.forEach.call(track.children, function(card){
var t=card.dataset.ticker; var q=quotes[t];
if(!q || !q.price) return;
card.classList.remove('no-quote');
var px=card.querySelector('.px'); px.textContent='$'+q.price.toFixed(2);
var ch=card.querySelector('.ch');
if(q.day_change_pct==null){ ch.textContent='close '+(q.price_date||''); ch.className='ch flat'; }
else if(q.day_change_pct>=0){ ch.textContent='+'+q.day_change_pct.toFixed(2)+'%'; ch.className='ch up'; }
else { ch.textContent=q.day_change_pct.toFixed(2)+'%'; ch.className='ch down'; }
});
updateThesisMetrics();
}).catch(function(){
document.getElementById('bk-meta').textContent='quote fetch failed';
});
}
// Compute the Building Activity Index and update the hero panel.
// BAI = attribution-weighted day-change % across surfaced issuers.
// "Indexed build value" = total dollars of permits attributable to
// any public issuer in this view (sum across attributing contractors).
// "Network depth" = issuer count + total attributions.
function updateThesisMetrics(){
if(!lastBasket.length){
document.getElementById('bai-value').textContent='—';
document.getElementById('bai-sub').textContent='awaiting basket data';
return;
}
// BAI: weighted average of day_change_pct, weight = attribution count.
var weightedSum=0, weightTotal=0, contributors=[];
lastBasket.forEach(function(b){
var q = lastQuotes[b.ticker];
if(q && q.day_change_pct!=null){
var w = b.count || 1;
weightedSum += q.day_change_pct * w;
weightTotal += w;
contributors.push({ticker:b.ticker, day:q.day_change_pct, weight:w});
}
});
var bai = weightTotal>0 ? (weightedSum/weightTotal) : null;
var baiEl = document.getElementById('bai-value');
var baiSub = document.getElementById('bai-sub');
if(bai==null){
baiEl.textContent='—'; baiSub.textContent='no quotes settled yet';
baiEl.className='bai-value';
} else {
var sign = bai>=0 ? '+' : '';
baiEl.textContent = sign + bai.toFixed(2) + '%';
baiEl.className = 'bai-value ' + (bai>=0?'up':'down');
contributors.sort(function(a,b){return Math.abs(b.day*b.weight) - Math.abs(a.day*a.weight)});
var top = contributors.slice(0,3).map(function(c){return c.ticker+' '+(c.day>=0?'+':'')+c.day.toFixed(1)+'%'}).join(' · ');
baiSub.textContent = contributors.length+' issuers contributing · top: '+top;
}
// Indexed build value
var totalCost = 0;
lastRows.forEach(function(r){
var ts=(r.tickers&&r.tickers.direct?r.tickers.direct:[]).concat(r.tickers&&r.tickers.associated?r.tickers.associated:[]);
if(ts.length>0) totalCost += (r.total_cost||0);
});
var bav = totalCost>=1e9 ? '$'+(totalCost/1e9).toFixed(2)+'B' : totalCost>=1e6 ? '$'+(totalCost/1e6).toFixed(0)+'M' : '$'+Math.round(totalCost/1e3)+'K';
document.getElementById('bav-value').textContent = bav;
document.getElementById('bav-sub').textContent = lastBasket.length+' issuers in scope';
// Network depth
var totalAttrib = lastBasket.reduce(function(s,b){return s + (b.count||0)},0);
document.getElementById('net-value').textContent = lastBasket.length + ' / ' + totalAttrib;
document.getElementById('net-sub').textContent = 'issuers / attribution edges';
}
// Per-ticker map: when a ticker is selected, plot the contractor
// permit locations attributed to that ticker. Pulls lat/lng for each
// attributed contractor from the contractor profile endpoint and
// merges. Caches per-ticker so toggling is instant.
var mapCache = {};
function showSignalMap(ticker){
var wrap=document.getElementById('signal-map-wrap');
if(!ticker){ wrap.classList.remove('active'); if(signalMap){signalMap.remove(); signalMap=null;} return; }
wrap.classList.add('active');
document.getElementById('signal-map-ticker').textContent = ticker;
document.getElementById('signal-map-meta').textContent = 'loading permits…';
// Find the contractors attributed to this ticker
var attrib = lastRows.filter(function(r){
var ts=(r.tickers&&r.tickers.direct?r.tickers.direct:[]).concat(r.tickers&&r.tickers.associated?r.tickers.associated:[]);
return ts.some(function(t){return t.ticker===ticker});
});
if(!attrib.length){
document.getElementById('signal-map-meta').textContent='no attributed contractors';
return;
}
// Use the contractor_profile endpoint per attributed contractor (cap at 6)
// to pull their geocoded permits, then render. Cached per ticker.
if(mapCache[ticker]){
drawSignalMap(ticker, mapCache[ticker]);
return;
}
var names = attrib.slice(0,6).map(function(r){return r.name});
Promise.all(names.map(function(n){
return fetch(P+'/intelligence/contractor_profile',{
method:'POST',headers:{'Content-Type':'application/json'},
body:JSON.stringify({name:n})
}).then(function(r){return r.json()}).then(function(d){
var perms = (d.history && d.history.recent_permits) || [];
return perms.filter(function(p){return p.lat&&p.lng}).map(function(p){
return Object.assign({contractor:n}, p);
});
}).catch(function(){return []});
})).then(function(arrs){
var all = arrs.reduce(function(a,b){return a.concat(b)},[]);
mapCache[ticker] = all;
drawSignalMap(ticker, all);
});
}
function drawSignalMap(ticker, permits){
if(signalMap){ signalMap.remove(); signalMap=null; }
if(!permits.length){
document.getElementById('signal-map-meta').textContent='0 geocoded permits across attributed contractors';
return;
}
document.getElementById('signal-map-meta').textContent = permits.length + ' geocoded permits across ' + new Set(permits.map(function(p){return p.contractor})).size + ' contractors';
signalMap = L.map('signal-map',{zoomControl:true, attributionControl:false}).setView([41.88,-87.63], 11);
L.tileLayer('https://{s}.basemaps.cartocdn.com/dark_all/{z}/{x}/{y}{r}.png',{maxZoom:19}).addTo(signalMap);
var bounds=[];
var maxCost = Math.max.apply(null, permits.map(function(p){return Number(p.cost)||1}));
permits.forEach(function(p){
var c=Number(p.cost)||0;
var radius = 4 + (c/maxCost)*14;
var color = c>=1000000?'#f85149':c>=100000?'#d29922':'#3fb950';
var marker = L.circleMarker([p.lat,p.lng],{radius:radius,color:color,weight:1,fillOpacity:0.55});
var pop=document.createElement('div');
pop.style.cssText='font-family:ui-monospace,monospace;font-size:11px;color:#0a0d12;min-width:200px';
var top=document.createElement('div'); top.style.cssText='font-weight:700;margin-bottom:3px;color:#1f6feb';
top.textContent=ticker+' attribution';
pop.appendChild(top);
var con=document.createElement('div'); con.textContent=p.contractor; con.style.fontWeight='600';
pop.appendChild(con);
var meta=document.createElement('div'); meta.style.color='#545d68';
meta.textContent='$'+c.toLocaleString()+' · '+(p.date||'?')+' · '+(p.work_type||'?');
pop.appendChild(meta);
var addr=document.createElement('div'); addr.style.color='#545d68';
addr.textContent=p.address||'?';
pop.appendChild(addr);
marker.bindPopup(pop);
marker.addTo(signalMap);
bounds.push([p.lat,p.lng]);
});
if(bounds.length>1) signalMap.fitBounds(bounds,{padding:[28,28]});
}
function render(){
var host=document.getElementById('result');
clearChildren(host);
// Apply ticker filter if set: keep only rows whose tickers include the selected one
var pool = tickerFilter ? lastRows.filter(function(r){
var ts=(r.tickers&&r.tickers.direct?r.tickers.direct:[]).concat(r.tickers&&r.tickers.associated?r.tickers.associated:[]);
return ts.some(function(t){return t.ticker===tickerFilter});
}) : lastRows;
if(!pool.length){
var emp=document.createElement('div'); emp.className='empty';
emp.textContent='No contractors match the current filter.';
host.appendChild(emp);
return;
}
var rows = pool.slice().sort(function(a,b){
var av=a[sortKey], bv=b[sortKey];
if(typeof av==='string'){ av=(av||'').toUpperCase(); bv=(bv||'').toUpperCase(); }
if(av<bv) return sortDir==='asc'?-1:1;
if(av>bv) return sortDir==='asc'?1:-1;
return 0;
});
var t=document.createElement('table');
var thead=document.createElement('thead'); var hr=document.createElement('tr');
var cols=[
{k:'name', label:'Contractor'},
{k:'permits', label:'Permits', right:true},
{k:'total_cost', label:'Total Value', right:true},
{k:'last_filed', label:'Last Filed', right:true},
{k:'roles', label:'Listed As'},
];
cols.forEach(function(c){
var h=document.createElement('th');
h.textContent=c.label;
if(c.right) h.style.textAlign='right';
if(sortKey===c.k){
var ar=document.createElement('span'); ar.className='arrow';
ar.textContent = sortDir==='asc' ? '▲' : '▼';
h.appendChild(ar);
}
h.onclick=function(){
if(sortKey===c.k) sortDir = sortDir==='asc' ? 'desc' : 'asc';
else { sortKey=c.k; sortDir = (c.k==='name') ? 'asc' : 'desc'; }
render();
};
hr.appendChild(h);
});
thead.appendChild(hr); t.appendChild(thead);
var tb=document.createElement('tbody');
rows.forEach(function(r){
var tr=document.createElement('tr');
var ntd=document.createElement('td'); ntd.className='name';
var a=document.createElement('a');
a.href = P+'/contractor?name='+encodeURIComponent(r.name);
a.target='_blank'; a.rel='noopener';
a.textContent = r.name;
ntd.appendChild(a);
// Ticker association pills — direct (green) = the contractor is a
// public issuer; parent (amber) = subsidiary of a public parent;
// associated (blue) = co-appears on permits with a public entity.
// Shows the correlation indicator J described — when Bob's Electric
// works permits with Target, TGT renders here as associated.
var t = r.tickers || {direct:[], associated:[]};
var allTk = (t.direct||[]).concat(t.associated||[]);
if(allTk.length){
var trk = document.createElement('div'); trk.className='tickers';
allTk.forEach(function(x){
var p = document.createElement('span');
p.className = 'ticker-pill ' + (x.via||'direct');
p.textContent = x.ticker;
// Tooltip shows the full reason path
var hint = x.via === 'associated'
? 'Associated via co-permits with '+x.partner_name+' ('+(x.co_permits||0)+' shared permits)' + (x.matched_name ? ' — '+x.matched_name : '')
: x.via === 'parent'
? 'Subsidiary of '+(x.matched_name||x.ticker) + (x.exchange ? ' · '+x.exchange : '')
: 'Direct match: '+(x.matched_name||r.name);
p.title = hint;
trk.appendChild(p);
});
ntd.appendChild(trk);
}
tr.appendChild(ntd);
var ptd=document.createElement('td'); ptd.className='right';
ptd.textContent=(r.permits||0).toLocaleString();
tr.appendChild(ptd);
var ctd=document.createElement('td'); ctd.className='right '+costClass(r.total_cost||0);
ctd.textContent=fmt$(r.total_cost||0);
tr.appendChild(ctd);
var ltd=document.createElement('td'); ltd.className='right';
ltd.textContent=(r.last_filed||'').slice(0,10) || '—';
tr.appendChild(ltd);
var rtd=document.createElement('td'); rtd.className='role';
(r.roles||[]).forEach(function(role){
var pill=document.createElement('span'); pill.className='pill'; pill.textContent=role;
rtd.appendChild(pill);
});
tr.appendChild(rtd);
tb.appendChild(tr);
});
t.appendChild(tb);
host.appendChild(t);
}
var sDeb;
document.getElementById('q').addEventListener('input',function(){
clearTimeout(sDeb);
sDeb=setTimeout(load,400);
});
document.getElementById('since').addEventListener('change',load);
document.getElementById('min-cost').addEventListener('change',load);
document.getElementById('bk-clear').addEventListener('click',function(){
tickerFilter=null;
document.getElementById('bk-clear').style.display='none';
Array.prototype.forEach.call(document.querySelectorAll('.bk-card.selected'), function(c){c.classList.remove('selected')});
showSignalMap(null);
render();
});
window.addEventListener('load',load);
</script>
</body></html>

425
mcp-server/proof.html
View File

@ -81,6 +81,7 @@ pre{background:#161b22;border:1px solid #171d27;border-radius:8px;padding:14px 1
<nav> <nav>
<a href=".">Dashboard</a> <a href=".">Dashboard</a>
<a href="console">Walkthrough</a> <a href="console">Walkthrough</a>
<a href="profiler">Profiler</a>
<a href="proof" class="active">Architecture</a> <a href="proof" class="active">Architecture</a>
<a href="spec">Spec</a> <a href="spec">Spec</a>
<a href="onboard">Onboard</a> <a href="onboard">Onboard</a>
@ -95,138 +96,137 @@ pre{background:#161b22;border:1px solid #171d27;border-radius:8px;padding:14px 1
<div class="chapter"> <div class="chapter">
<div class="num">Chapter 1</div> <div class="num">Chapter 1</div>
<h2>Receipts, not promises</h2> <h2>Receipts, not promises</h2>
<div class="lede">Every test below ran live against the real gateway when you loaded this page. Sub-100ms SQL on multi-million-row Parquet, hybrid search with playbook boost applied. No fixtures. If a test fails, you'll see ✗.</div> <div class="lede">Every test below ran live against the real gateway when you loaded this page. Sub-100ms SQL on multi-million-row Parquet, hybrid search with playbook boost applied, public-issuer attribution computed from this view. No fixtures. If a test fails, you'll see ✗.</div>
<div id="ch1-tests"><div class="loading">Running tests…</div></div> <div id="ch1-tests"><div class="loading">Running tests…</div></div>
<div id="ch1-live" style="margin-top:14px"></div>
</div> </div>
<div class="chapter"> <div class="chapter">
<div class="num">Chapter 2</div> <div class="num">Chapter 2</div>
<h2>Architecture — 13 crates, one object store, one local AI runtime</h2> <h2>Architecture — 15 crates, one object store, a 5-provider model fleet</h2>
<div class="lede">Request flows top to bottom. Every node is independently swappable. Every line is a real HTTP or gRPC hop that you can trace with <code>tcpdump</code>.</div> <div class="lede">Gateway is a drop-in OpenAI-compatible middleware. Any consumer that speaks the OpenAI Chat Completions shape — agent SDKs, IDE plugins, custom apps — points at <code>localhost:3100/v1</code> and gets routing, audit, and the full memory substrate behind every call. The model side has 5 providers and 40+ frontier models reachable via one OpenCode key. The data side stays Rust-first.</div>
<div class="card accent-b"> <div class="card accent-b">
<pre> HTTP :3100 + gRPC :3101 <pre> OpenAI SDK consumers MCP clients Browser UI (Bun :3700)
│ │ │ │
┌───────▼───────┐ └──────────────────────────┼──────────────────────────┘
│ gateway │ Rust · Axum · routing, CORS, auth, tools ▼
└───────┬───────┘ ┌──────────────────────────────┐
┌────────────┬───────────┼───────────┬────────────┐ │ gateway :3100 /v1/* │ Rust · Axum
│ │ │ │ │ │ OpenAI-compat drop-in │ smart provider routing
┌────▼───┐ ┌────▼───┐ ┌────▼───┐ ┌────▼───┐ ┌────▼───┐ │ /v1/chat /v1/mode /iterate │ cost telemetry, Langfuse
│catalog │ │ query │ │ vector │ │ ingest │ │aibridge│ └──────────┬───────────────────┘
│ d │ │ d │ │ d │ │ d │ │ │ ┌─────────┬───────────────┼───────────────┬──────────┐
└────┬───┘ └────┬───┘ └────┬───┘ └────┬───┘ └────┬───┘ │ │ │ │ │
│ │ │ │ │ ┌────▼───┐ ┌───▼────┐ ┌─────▼──────┐ ┌─────▼─────┐ ┌──▼──────┐
└────────────┴───────────┼───────────┴────────────┘ │catalog │ │ query │ │ vector │ │ ingest │ │aibridge │
▼ │ d │ │ d │ │ d │ │ d │ │ │
┌─────────────────┐ │idempot │ │DataFus │ │HNSW · Lance│ │CSV PDF SQL│ │provider │
│ object storage │ Parquet files (local / S3) │schema │ │delta │ │playbook+ │ │auto-PII │ │adapters │
└─────────────────┘ │fingerp │ │MemTabl │ │pathway mem │ │schema fp │ │5 active │
▲ └────┬───┘ └───┬────┘ └─────┬──────┘ └─────┬─────┘ └──┬──────┘
│ └─────────┴────────────────┼────────────────┴─────────┘
┌───────┴────────┐ ▼
│ Python sidecar │ FastAPI → Ollama ┌──────────────────┐
│ (aibridge) │ local models only │ object storage │ Parquet · MinIO · S3-compat
└────────────────┘</pre> └──────────────────┘
▲
│
┌───────────────┴────────────────┐
│ validator · journald │ schema/PII/policy gates
│ (Phase 43) · (audit log) │ + append-only mutations
└────────────────────────────────┘
Provider fleet (config/providers.toml):
ollama localhost:3200 local Ollama → qwen3.5, gemma2
ollama_cloud ollama.com gpt-oss:120b, qwen3-coder:480b,
deepseek-v3.1:671b, kimi-k2:1t,
mistral-large-3:675b, qwen3.5:397b
openrouter openrouter.ai/api/v1 343 models — paid + free rescue
opencode opencode.ai/zen/v1 40 models · ONE sk-* key reaches
Claude Opus 4.7, GPT-5.5-pro,
Gemini 3.1-pro, Kimi K2.6, GLM 5.1,
DeepSeek, Qwen, MiniMax, free tier
kimi api.kimi.com/coding/v1 direct Kimi For Coding (TOS-clean)</pre>
</div> </div>
<h3>Per-crate responsibility</h3> <h3>Per-crate responsibility (15 crates)</h3>
<table class="plain"> <table class="plain">
<thead><tr><th>Crate</th><th>Role</th><th>Path</th></tr></thead> <thead><tr><th>Crate</th><th>Role</th><th>Path</th></tr></thead>
<tbody> <tbody>
<tr><td>shared</td><td>Types, errors, Arrow helpers, PII detection, secrets provider</td><td>crates/shared/</td></tr> <tr><td>shared</td><td>Types, errors, Arrow helpers, PII detection, secrets provider, model_matrix</td><td>crates/shared/</td></tr>
<tr><td>storaged</td><td>object_store I/O, BucketRegistry (multi-bucket), AppendLog, ErrorJournal</td><td>crates/storaged/</td></tr> <tr><td>storaged</td><td>object_store I/O, BucketRegistry, AppendLog, ErrorJournal, federation_service</td><td>crates/storaged/</td></tr>
<tr><td>catalogd</td><td>Metadata authority — manifests, views, tombstones, profiles, schema fingerprints</td><td>crates/catalogd/</td></tr> <tr><td>catalogd</td><td>Manifests, views (incl. PII-safe view layer), tombstones, profiles, schema fingerprints, register-idempotency (ADR-020)</td><td>crates/catalogd/</td></tr>
<tr><td>queryd</td><td>DataFusion SQL engine, MemTable cache, delta merge-on-read, compaction</td><td>crates/queryd/</td></tr> <tr><td>queryd</td><td>DataFusion SQL, MemTable cache, delta merge-on-read, compaction, truth gate (ADR-021)</td><td>crates/queryd/</td></tr>
<tr><td>ingestd</td><td>CSV/JSON/PDF(+OCR)/Postgres/MySQL ingest, cron schedules, auto-PII</td><td>crates/ingestd/</td></tr> <tr><td>ingestd</td><td>CSV/JSON/PDF(+OCR)/Postgres/MySQL ingest, cron schedules, auto-PII flagging</td><td>crates/ingestd/</td></tr>
<tr><td>vectord</td><td>Embeddings as Parquet, HNSW, trial system, autotune agent, playbook_memory</td><td>crates/vectord/</td></tr> <tr><td>vectord</td><td>Embeddings as Parquet, HNSW, trial system, autotune, playbook_memory + pathway_memory (ADR-021 semantic-correctness layer)</td><td>crates/vectord/</td></tr>
<tr><td>vectord-lance</td><td>Firewall crate — Lance 4.0 + Arrow 57 isolated from main Arrow 55</td><td>crates/vectord-lance/</td></tr> <tr><td>vectord-lance</td><td>Firewall crate — Lance 4.0 + Arrow 57 isolated from main Arrow 55</td><td>crates/vectord-lance/</td></tr>
<tr><td>journald</td><td>Append-only mutation event log for time-travel &amp; audit</td><td>crates/journald/</td></tr> <tr><td>journald</td><td>Append-only mutation event log for time-travel + audit</td><td>crates/journald/</td></tr>
<tr><td>aibridge</td><td>Rust↔Python sidecar, Ollama HTTP client, VRAM introspection</td><td>crates/aibridge/</td></tr> <tr><td>truth</td><td>File-backed rule store; <code>evaluate(task_class, ctx) → Vec&lt;RuleOutcome&gt;</code> (ADR-021)</td><td>crates/truth/</td></tr>
<tr><td>gateway</td><td>Axum HTTP :3100 + gRPC :3101, middleware, tools registry</td><td>crates/gateway/</td></tr> <tr><td>aibridge</td><td>Rust↔Python sidecar, Ollama client, ProviderAdapter trait, /v1/chat router</td><td>crates/aibridge/</td></tr>
<tr><td>ui</td><td>Dioxus WASM internal developer UI</td><td>crates/ui/</td></tr> <tr><td>gateway</td><td>Axum HTTP :3100 + gRPC :3101, OpenAI-compat /v1/*, mode runner, validator, iterate loop, cost telemetry, Langfuse + observer fan-out</td><td>crates/gateway/</td></tr>
<tr><td>mcp-server</td><td>Bun TypeScript recruiter-facing app (this server)</td><td>mcp-server/</td></tr> <tr><td>validator</td><td>Phase 43 — schema / completeness / consistency / policy gates over LLM outputs (FillValidator, EmailValidator, ParquetWorkerLookup)</td><td>crates/validator/</td></tr>
<tr><td>ui</td><td>Dioxus WASM internal developer UI (separate from this Bun-served public UI)</td><td>crates/ui/</td></tr>
<tr><td>mcp-server</td><td>Bun TypeScript public-facing app + MCP tool surface — what you're reading right now</td><td>mcp-server/</td></tr>
<tr><td>auditor</td><td>External claim-vs-diff verifier on PRs · Kimi K2.6 ↔ Haiku 4.5 cross-lineage alternation, Opus 4.7 auto-promote on diffs &gt;100k chars</td><td>auditor/</td></tr>
</tbody> </tbody>
</table> </table>
<div class="ref"><strong>Source:</strong> git.agentview.dev/profit/lakehouse &nbsp;·&nbsp; <strong>ADRs:</strong> docs/DECISIONS.md (currently 20 records)</div> <div class="ref"><strong>Source:</strong> git.agentview.dev/profit/lakehouse · branch <code>scrum/auto-apply-19814</code> · tag <code>distillation-v1.0.0</code> at commit <code>e7636f2</code> (frozen substrate) · <strong>ADRs:</strong> docs/DECISIONS.md (currently 21 records)</div>
</div> </div>
<div class="chapter"> <div class="chapter">
<div class="num">Chapter 3</div> <div class="num">Chapter 3</div>
<h2>Dual-agent recursive consensus loop</h2> <h2>The model fleet — 9-rung ladder, N=3 consensus, cross-lineage audit</h2>
<div class="lede">The system we use to execute staffing fills is a dual-agent recursive protocol. Two agents with distinct roles iterate against a shared log until one of three terminal states is reached. It is deterministic in structure, stochastic in content, and verifiable through the per-run log artifact.</div> <div class="lede">No single model owns the answer. Every consequential call is structured: the right tier picks up first, fallback rungs catch what fails, parallel runs vote, and an independent auditor of a different model lineage checks the result against the diff. The protocol is deterministic; the inference is stochastic; every step writes a receipt.</div>
<h3>Agents and protocol</h3>
<div class="card accent-a">
<pre> task in
│
▼
┌───────────────────────────────────────────────────────────┐
│ EXECUTOR (mistral:latest) │
│ ──────────────────────────────────────────────────────── │
│ input: task spec + shared log + seen-candidates ledger │
│ output: one JSON action per turn │
│ · {kind:"plan",steps:[…]} │
│ · {kind:"tool_call",tool,args,rationale} │
│ · {kind:"propose_done",fills:[N of N]} │
└───────────┬───────────────────────────────┬───────────────┘
│ tool_call │ propose_done
▼ │
┌──────────────────────────┐ │
│ TOOL DISPATCH │ │
│ hybrid_search / sql │ │
│ (against live gateway) │ │
└──────────┬───────────────┘ │
│ result (trimmed, exclusions) │
▼ ▼
┌───────────────────────────────────────────────────────────┐
│ REVIEWER (qwen2.5:latest) │
│ ──────────────────────────────────────────────────────── │
│ input: task spec + shared log (including tool result) │
│ output: {kind:"critique",verdict:"continue|drift| │
│ approve_done",notes} │
└───────────┬───────────────────────────────────────────────┘
│
┌─────┴─────┐
▼ ▼ ▼
continue drift approve_done + propose_done ⟹ SEAL
(next turn) (cap ≈ 3 →
hard abort)
</pre>
</div>
<div class="ref"><strong>Code:</strong> tests/multi-agent/agent.ts (protocol + prompts) &nbsp;·&nbsp; tests/multi-agent/orchestrator.ts (run loop) &nbsp;·&nbsp; tests/multi-agent/scenario.ts (5-event warehouse week)</div>
<h3>Why "dual" — role specialization</h3> <h3>The 9-rung cloud-first ladder</h3>
<div class="narr"> <div class="card accent-b">
<strong>The executor is an optimist.</strong> Its job is to produce progress: pull candidates, verify SQL, propose consensus. It's instructed to be decisive. <pre> request in
<br><br> │
<strong>The reviewer is a pessimist.</strong> Its job is to catch drift: proposals that don't match the task's geography, fill count, or role. It's authorized to stop the loop. ▼
<br><br> ┌───────────────────────────────────────────────────────────────────┐
This adversarial separation is cheaper and more deterministic than asking a single model to self-critique. The reviewer has a hard rule: on the turn after a <code>propose_done</code>, it MUST emit either <code>approve_done</code> or <code>drift</code> — it cannot stall with <code>continue</code>. │ attempt 1 ollama_cloud / kimi-k2:1t 1T params · flagship │
│ attempt 2 ollama_cloud / qwen3-coder:480b coding specialist │
│ attempt 3 ollama_cloud / deepseek-v3.1:671b reasoning │
│ attempt 4 ollama_cloud / mistral-large-3:675b deep analysis │
│ attempt 5 ollama_cloud / gpt-oss:120b reliable workhorse │
│ attempt 6 ollama_cloud / qwen3.5:397b dense final thinker │
│ attempt 7 openrouter / openai/gpt-oss-120b:free rescue tier │
│ attempt 8 openrouter / google/gemma-3-27b-it:free fastest rescue │
│ attempt 9 ollama / qwen3.5:latest last-resort local │
└───────────────┬───────────────────────────────────────────────────┘
│ isAcceptable() = chars ≥ 3800 ∧ not malformed JSON
▼
sealed result OR next-rung learning preamble</pre>
</div> </div>
<div class="narr">Every rung sees a learning preamble carrying the prior rejection reason. The ladder is the standard scrum/auditor path; for individual <code>/v1/chat</code> calls the caller picks the model directly (or lets the smart-routing default fire).</div>
<div class="ref"><strong>Code:</strong> tests/real-world/scrum_master_pipeline.ts <code>const LADDER</code> · config/routing.toml · crates/gateway/src/v1/mode.rs (mode runner)</div>
<h3>Why "parallel" — orchestrator can fan out</h3> <h3>N=3 consensus + tie-breaker (auditor inference)</h3>
<div class="narr">
<strong>Independent pairs run concurrently.</strong> <code>tests/multi-agent/run_e2e_rated.ts</code> runs two task-specific agent pairs via <code>Promise.all</code>. Ollama serializes inference at the model level, so "parallel" is concurrent orchestration — but the substrate (gateway, queryd, vectord) handles concurrent requests cleanly. Verified in the scenario harness: two contracts sealing simultaneously.
</div>
<h3>Why "recursive" — each seal feeds the next</h3>
<div class="narr">
<strong>Consensus does not end at the sealed playbook.</strong> Every sealed playbook is persisted to <code>playbook_memory</code> via <code>POST /vectors/playbook_memory/seed</code>. The next hybrid search for a semantically similar operation consults that memory via <code>compute_boost_for(query_embedding, top_k, base_weight)</code> and re-ranks the candidate pool. The system builds on itself turn over turn, playbook over playbook.
</div>
<h3>Termination guarantees</h3>
<div class="math"> <div class="math">
<span class="c">// three paths out, every run has one of these:</span><br> <span class="c">// auditor/checks/inference.ts — every claim audit runs this:</span><br>
sealed = executor.propose_done ∧ reviewer.approve_done ∧ fills.count == target<br> 1. Fire the primary reviewer N=3 times in PARALLEL (Promise.all) — wall-clock = single call<br>
abort = consecutive_tool_errors ≥ MAX_TOOL_ERRORS (3) &nbsp;&nbsp;<span class="c">// executor can't form a valid call</span><br> 2. Aggregate votes per claim_idx · majority wins<br>
abort = consecutive_drifts ≥ MAX_CONSECUTIVE_DRIFTS (3) &nbsp;<span class="c">// reviewer keeps flagging</span><br> 3. On 1-1-1 split → tie-breaker model with <strong>different architecture</strong> (qwen3-coder:480b vs primary gpt-oss/kimi)<br>
abort = turn &gt; MAX_TURNS (12) &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;<span class="c">// no consensus reached in window</span> 4. Every disagreement (even when majority resolves) → <code>data/_kb/audit_discrepancies.jsonl</code><br>
<br>
<span class="c">// Closes the cloud-non-determinism gap: temp=0 isn't actually deterministic in practice</span><br>
<span class="c">// across hours; consensus + cross-architecture tie-break stabilizes verdicts.</span>
</div> </div>
<div class="narr">Every abort dumps the full log to <code>tests/multi-agent/playbooks/&lt;id&gt;-FAILED.json</code> for forensic review. No consensus is ever implicit.</div>
<h3>Auditor cross-lineage — Kimi ↔ Haiku ↔ Opus</h3>
<div class="narr">Every push to PR #11 triggers <code>auditor/audit.ts</code> within ~90s. To prevent a single model lineage's blind spots from becoming the system's blind spots, audits alternate between Kimi K2.6 (Moonshot) and Haiku 4.5 (Anthropic) by SHA. Diffs over 100k chars auto-promote to Claude Opus 4.7. Per-PR cap of 3 audits with auto-reset on each new head SHA prevents infinite-loop spend. <strong>100% grounding-verified rate</strong> on Haiku 4.5 across the latest 10 findings — pairing different lineages + forcing per-finding grounding kills confabulation.</div>
<div class="ref"><strong>Code:</strong> auditor/audit.ts · auditor/checks/inference.ts (N=3) · auditor/checks/kimi_architect.ts · <strong>Verdicts:</strong> data/_auditor/kimi_verdicts/ — read any 11-&lt;sha&gt;.json to inspect a real audit</div>
<h3>Distillation v1.0.0 — the frozen substrate</h3>
<div class="narr">The substrate the auditor and mode runner sit on is tagged at <code>distillation-v1.0.0</code> / commit <code>e7636f2</code>. <strong>145 unit tests pass · 22/22 acceptance invariants · 16/16 audit-full checks · bit-identical reproducibility verified.</strong> The distillation phase exports clean SFT / RAG / preference samples with a multi-layer contamination firewall; the auditor consumes the substrate. The frozen tag means: any future "the system regressed" question has a baseline to bisect against, byte-for-byte.</div>
<div class="ref"><strong>Tag:</strong> distillation-v1.0.0 · <strong>Commit:</strong> e7636f2 · <strong>Substrate code:</strong> scripts/distillation/ · auditor/schemas/distillation/ · <strong>Output:</strong> data/_kb/distilled_{facts,procedures,config_hints}.jsonl</div>
</div> </div>
<div class="chapter"> <div class="chapter">
<div class="num">Chapter 4</div> <div class="num">Chapter 4</div>
<h2>Playbook memory — the compounding feedback loop</h2> <h2>Two memory layers — playbook (worker signal) + pathway (system signal)</h2>
<div class="lede">A CRM stores events. This system turns events into re-ranking signal. Every sealed playbook endorses specific (worker, city, state) tuples. Every failure penalizes them. Every similar future query inherits the signal through cosine similarity.</div> <div class="lede">A CRM stores events. This system turns events into re-ranking signal at two layers. <strong>Playbook memory</strong> compounds worker-level outcomes (who got endorsed, where, when) into per-query boost. <strong>Pathway memory</strong> compounds system-level outcomes (which model + corpus + framing actually solved similar problems) into per-task hot-swap. Both are queryable. Both are auditable. Both compound.</div>
<h3>Layer 1 — playbook memory (worker + geo signal)</h3>
<h3>Seed shape</h3> <h3>Seed shape</h3>
<div class="math"> <div class="math">
@ -289,10 +289,82 @@ pre{background:#161b22;border:1px solid #171d27;border-radius:8px;padding:14px 1
<strong>Beyond "who was endorsed."</strong> <code>POST /vectors/playbook_memory/patterns</code> takes a query, finds top-K similar past playbooks, pulls each endorsed worker's full workers_500k profile, and aggregates shared traits: recurring certifications, skill frequencies, modal archetype, reliability distribution. Returns a <code>discovered_pattern</code> string showing operator-actionable signal the user didn't explicitly query for. <strong>Beyond "who was endorsed."</strong> <code>POST /vectors/playbook_memory/patterns</code> takes a query, finds top-K similar past playbooks, pulls each endorsed worker's full workers_500k profile, and aggregates shared traits: recurring certifications, skill frequencies, modal archetype, reliability distribution. Returns a <code>discovered_pattern</code> string showing operator-actionable signal the user didn't explicitly query for.
</div> </div>
<div class="ref"><strong>Code:</strong> crates/vectord/src/playbook_memory.rs::discover_patterns &nbsp;·&nbsp; <strong>Surfaces:</strong> /vectors/playbook_memory/patterns endpoint, /intelligence/chat response, /intelligence/permit_contracts cards</div> <div class="ref"><strong>Code:</strong> crates/vectord/src/playbook_memory.rs::discover_patterns &nbsp;·&nbsp; <strong>Surfaces:</strong> /vectors/playbook_memory/patterns endpoint, /intelligence/chat response, /intelligence/permit_contracts cards</div>
<h3>Layer 2 — pathway memory (system-level hot-swap, ADR-021)</h3>
<div class="narr">
<strong>Pathway memory remembers which approach worked, not just which worker.</strong> Every accepted scrum review writes a <code>PathwayTrace</code> with the full backtrack: file fingerprint, model used, signal class, KB chunks consulted, observer events, semantic flags, bug fingerprints. A new query that fingerprints to the same trace can hot-swap to the prior result without re-running the 9-rung escalation. The 5-factor hot-swap gate is strict: narrow fingerprint match AND audit consensus pass AND replay_count ≥ 3 (probation) AND success_rate ≥ 0.80 AND NOT retired AND vector cosine ≥ 0.90.
</div>
<div class="math">
<span class="c">// Live pathway state (refresh page to recompute):</span><br>
<span id="pwm-traces">— traces</span> · <span id="pwm-replays">—</span> successful replays · <span id="pwm-rate">—</span> reuse rate<br>
<span class="c">// 88 / 11/11 / 100% as of 2026-04-27 — probation gate crossed</span>
</div>
<div class="ref"><strong>Code:</strong> crates/vectord/src/pathway_memory.rs · <strong>Endpoints:</strong> /vectors/pathway/insert · /query · /record_replay · /stats · /bug_fingerprints · <strong>Spec:</strong> docs/DECISIONS.md ADR-021 — Semantic-correctness matrix layer</div>
<h3>What both memory layers feed (besides search)</h3>
<div class="narr">
Both layers also feed the <strong>per-staffer hot-swap index</strong> (Chapter 5) and the <strong>Construction Activity Signal Engine</strong> (Chapter 6). One memory model, surfaced three different ways at the request boundary depending on who's asking.
</div>
</div> </div>
<div class="chapter"> <div class="chapter">
<div class="num">Chapter 5</div> <div class="num">Chapter 5</div>
<h2>Per-staffer hot-swap — same corpus, different relevance gradient</h2>
<div class="lede">Maria runs Chicago. Devon runs Indianapolis. Aisha runs Wisconsin/Michigan. They share one corpus, but the search results, the recurring-skill patterns, and the playbook context all reshape to whoever is acting. Same query "forklift operators" returns 89 IN workers when Devon's acting, 16 WI when Aisha's, 167 IL when Maria's. The MEMORY panel relabels itself with the active coordinator's name.</div>
<h3>What scopes per staffer</h3>
<div class="math">
<span class="c">// On every /intelligence/chat call:</span><br>
if (b.staffer_id) {<br>
&nbsp;&nbsp;const staffer = lookupStaffer(b.staffer_id);<br>
&nbsp;&nbsp;<span class="c">// 1. Default state filter to staffer territory unless caller pinned one</span><br>
&nbsp;&nbsp;if (!explicitState) filters.push(`state = '${staffer.territory.state}'`);<br>
&nbsp;&nbsp;<span class="c">// 2. Default playbook-pattern geo to staffer's primary city/state</span><br>
&nbsp;&nbsp;cityForPatterns = staffer.territory.cities[0];<br>
&nbsp;&nbsp;stateForPatterns = staffer.territory.state;<br>
&nbsp;&nbsp;<span class="c">// 3. Surface staffer.name back so the UI can relabel MEMORY → MARIA'S MEMORY</span><br>
&nbsp;&nbsp;response.staffer = { id, name, territory };<br>
}
</div>
<div class="narr">
The corpus stays intact. The relevance gradient is per coordinator. As each accumulates fills, their slice of the playbook compounds independently. The architecture generalizes — every new metro adds territories, not code paths.
</div>
<div class="ref"><strong>Code:</strong> mcp-server/index.ts <code>STAFFERS</code> roster + <code>lookupStaffer()</code> · <code>/staffers</code> endpoint · <code>/intelligence/chat</code> smart_search route · <strong>UI:</strong> staffer dropdown in mcp-server/search.html</div>
</div>
<div class="chapter">
<div class="num">Chapter 6</div>
<h2>Construction Activity Signal Engine — the corpus is also a market signal</h2>
<div class="lede">Every contractor in this corpus is also a forward indicator on the public equities they touch. Permits filed today predict construction starts ~45 days out, staffing ~30, revenue recognition months later. The associated-ticker network surfaces this signal <em>before</em> any 10-Q. The architecture is metro-agnostic — Chicago is Phase 1; NYC DOB, LA County, Houston BCD, Boston ISD ship as Socrata-shaped adapters.</div>
<h3>Three flavors of attribution</h3>
<div class="math">
<span class="c">// per contractor in /intelligence/profiler_index:</span><br>
direct <span class="c">// contractor IS a public issuer → SEC tickers index match</span><br>
parent <span class="c">// curated KNOWN_PARENT_MAP — Turner → HOC.DE via Hochtief AG</span><br>
associated <span class="c">// co-permit network — Bob's Electric appears with TARGET CORPORATION</span><br>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;<span class="c">// 3+ times → inherits TGT as an associated indicator</span>
</div>
<div class="narr">
The associated path is the moat. A staffing-permit dataset that maps contractor-to-public-issuer is not commercially available; we synthesize it from the Socrata co-occurrence graph. Every additional metro multiplies edges.
</div>
<h3>Building Activity Index (BAI)</h3>
<div class="math">
<span class="c">// BAI = attribution-weighted average day-change across surfaced issuers:</span><br>
BAI = Σ (day_change_pct × attribution_count) / Σ attribution_count<br>
<br>
<span class="c">// Indexed build value = total $ of permits attributable to ANY public issuer</span><br>
<span class="c">// Network depth = issuers / total attribution edges</span>
</div>
<div class="narr">
Run BAI daily, save the series, and you've got a backtestable thesis in months. Today's surface is Chicago-only with ~9 issuers; the curve scales linearly with metros added — and the marginal cost of a new metro is one Socrata adapter.
</div>
<div class="ref"><strong>Code:</strong> mcp-server/index.ts <code>/intelligence/profiler_index</code> + <code>/intelligence/ticker_quotes</code> · entity.ts <code>lookupTickerLite()</code> · <code>fetchStooqQuote()</code> · <strong>UI:</strong> /profiler · <strong>Data sources:</strong> SEC company_tickers.json (in-memory index) + Stooq CSV API + curated parent-link map</div>
</div>
<div class="chapter">
<div class="num">Chapter 7</div>
<h2>Key architectural choices — what was picked and why</h2> <h2>Key architectural choices — what was picked and why</h2>
<div class="lede">Each choice is documented in <code>docs/DECISIONS.md</code> (Architecture Decision Records). If you dispute any of these, the ADR names the alternatives we rejected and the measurement that drove the call.</div> <div class="lede">Each choice is documented in <code>docs/DECISIONS.md</code> (Architecture Decision Records). If you dispute any of these, the ADR names the alternatives we rejected and the measurement that drove the call.</div>
<div class="card"> <div class="card">
@ -314,62 +386,95 @@ pre{background:#161b22;border:1px solid #171d27;border-radius:8px;padding:14px 1
<div class="row accent-r"> <div class="row accent-r">
<div style="flex:1"><div class="title">ADR-020 · Idempotent register() with schema-fingerprint gate</div><div class="meta">Same (name, fingerprint) reuses manifest. Different fingerprint = 409 Conflict. Prevents silent duplicate manifests. Cleanup run collapsed 374 → 31 datasets.</div></div> <div style="flex:1"><div class="title">ADR-020 · Idempotent register() with schema-fingerprint gate</div><div class="meta">Same (name, fingerprint) reuses manifest. Different fingerprint = 409 Conflict. Prevents silent duplicate manifests. Cleanup run collapsed 374 → 31 datasets.</div></div>
</div> </div>
<div class="row accent-r">
<div style="flex:1"><div class="title">ADR-021 · Semantic-correctness matrix layer</div><div class="meta">Pathway memory carries semantic flags (UnitMismatch, TypeConfusion, OffByOne, StaleReference, DeadCode, BoundaryViolation, …) on every trace. New reviews see prior bug fingerprints as a preamble; recurrent classes get caught on first read. Compounds across files in the same crate.</div></div>
</div>
<div class="row accent-l"> <div class="row accent-l">
<div style="flex:1"><div class="title">Phase 19 design note · Statistical + semantic, not neural</div><div class="meta">Meta-index is cosine similarity + endorsement aggregation. No model training. Rebuildable from <code>successful_playbooks</code> alone. Neural re-ranker deferred to Phase 20+ only if statistical floor plateaus.</div></div> <div style="flex:1"><div class="title">Phase 19 design note · Statistical + semantic, not neural</div><div class="meta">Meta-index is cosine similarity + endorsement aggregation. No model training. Rebuildable from <code>successful_playbooks</code> alone. Neural re-ranker deferred to Phase 20+ only if statistical floor plateaus.</div></div>
</div> </div>
<div class="row accent-l">
<div style="flex:1"><div class="title">Distillation freeze · v1.0.0 at e7636f2</div><div class="meta">145 tests · 22/22 acceptance · 16/16 audit-full · bit-identical reproducibility. Multi-layer contamination firewall on SFT exports. Substrate the auditor + mode runner sit on; "the system regressed" questions bisect against this anchor.</div></div>
</div>
</div> </div>
</div> </div>
<div class="chapter"> <div class="chapter">
<div class="num">Chapter 6</div> <div class="num">Chapter 8</div>
<h2>Measured at scale, on this machine</h2> <h2>Measured at scale, on this machine</h2>
<div class="lede">Hardware: i9 + 128GB RAM + Nvidia A4000 16GB VRAM. Numbers below are from <em>this</em> running instance. Refresh the page and they'll recompute.</div> <div class="lede">Hardware: i9 + 128GB RAM + Nvidia A4000 16GB VRAM + 2.5GB symmetric. Numbers below are from <em>this</em> running instance. Refresh the page and they'll recompute.</div>
<div class="grid" id="ch6-scale"><div class="loading">Loading scale data…</div></div> <div class="grid" id="ch6-scale"><div class="loading">Loading scale data…</div></div>
<div id="ch6-recall" style="margin-top:10px"></div> <div id="ch6-recall" style="margin-top:10px"></div>
</div> </div>
<div class="chapter"> <div class="chapter">
<div class="num">Chapter 7</div> <div class="num">Chapter 9</div>
<h2>Verify or dispute — reproduce it yourself</h2> <h2>Verify or dispute — reproduce it yourself</h2>
<div class="lede">Every claim below is a curl away from falsification.</div> <div class="lede">Every claim above is a curl away from falsification.</div>
<div class="card"> <div class="card">
<div class="narr"><strong>Health.</strong> Should return <code>lakehouse ok</code>.</div> <div class="narr"><strong>Gateway health.</strong> Returns provider matrix + worker count.</div>
<pre>curl http://localhost:3100/health</pre> <pre>curl -s http://localhost:3100/v1/health | jq</pre>
<div class="narr"><strong>Any SQL on multi-million-row Parquet.</strong> Sub-100ms typical.</div> <div class="narr"><strong>Any SQL on multi-million-row Parquet.</strong> Sub-100ms typical.</div>
<pre>curl -s -X POST http://localhost:3100/query/sql \ <pre>curl -s -X POST http://localhost:3100/query/sql \
-H 'Content-Type: application/json' \ -H 'Content-Type: application/json' \
-d '{"sql":"SELECT role, COUNT(*) FROM workers_500k WHERE state=\"IL\" GROUP BY role LIMIT 5"}'</pre> -d '{"sql":"SELECT role, COUNT(*) FROM workers_500k WHERE state=\"IL\" GROUP BY role LIMIT 5"}'</pre>
<div class="narr"><strong>Hybrid search with playbook boost.</strong> The whole Phase 19 feedback loop in one request.</div> <div class="narr"><strong>Hybrid search with playbook boost.</strong> SQL filter + vector rerank + playbook memory in one call.</div>
<pre>curl -s -X POST http://localhost:3100/vectors/hybrid \ <pre>curl -s -X POST http://localhost:3100/vectors/hybrid \
-H 'Content-Type: application/json' \ -H 'Content-Type: application/json' \
-d '{"index_name":"workers_500k_v1", -d '{"index_name":"workers_500k_v1",
"sql_filter":"role = '\''Forklift Operator'\'' AND city = '\''Chicago'\'' AND CAST(availability AS DOUBLE) > 0.5", "sql_filter":"role = '\''Forklift Operator'\'' AND city = '\''Chicago'\'' AND CAST(availability AS DOUBLE) > 0.5",
"question":"reliable forklift operator", "question":"reliable forklift operator",
"top_k":5,"use_playbook_memory":true,"playbook_memory_k":200}'</pre> "top_k":5,"use_playbook_memory":true,"playbook_memory_k":200}'</pre>
<div class="narr"><strong>Playbook memory stats.</strong> Count + endorsed names + sample.</div> <div class="narr"><strong>Pathway memory stats.</strong> System-level hot-swap signal — should show 88 traces / 11 replays / 100% reuse rate (probation gate crossed).</div>
<pre>curl http://localhost:3100/vectors/playbook_memory/stats</pre> <pre>curl -s http://localhost:3100/vectors/pathway/stats | jq</pre>
<div class="narr"><strong>Pattern discovery.</strong> What do past similar fills have in common?</div> <div class="narr"><strong>Per-staffer scoping.</strong> Same query, different rosters per coordinator.</div>
<pre>curl -s -X POST http://localhost:3100/vectors/playbook_memory/patterns \ <pre>for s in maria devon aisha; do
curl -s -X POST http://localhost:3700/intelligence/chat \
-H 'Content-Type: application/json' \
-d "{\"message\":\"forklift operators\",\"staffer_id\":\"$s\"}" \
| jq -r ".staffer.name + \": \" + (.sql_results | length | tostring) + \" workers, top: \" + (.sql_results[0].name + \" in \" + .sql_results[0].city + \", \" + .sql_results[0].state)"
done
# Maria: 167 workers, top: ... in Chicago, IL
# Devon: 89 workers, top: ... in Fort Wayne, IN
# Aisha: 16 workers, top: ... in Milwaukee, WI</pre>
<div class="narr"><strong>Late-worker triage in one shot.</strong> Pulls profile + 5 backfills + drafts SMS. Should respond in under 300ms.</div>
<pre>curl -s -X POST http://localhost:3700/intelligence/chat \
-H 'Content-Type: application/json' \ -H 'Content-Type: application/json' \
-d '{"query":"Forklift Operator in Chicago, IL","top_k_playbooks":25,"min_trait_frequency":0.3}'</pre> -d '{"message":"Marcus running late site 4422"}' | jq</pre>
<div class="narr"><strong>Run the dual-agent scenario yourself.</strong> All 5 events, real fills, real artifacts.</div> <div class="narr"><strong>Construction Activity Signal Engine.</strong> Profiler index with attribution, cost, last filed.</div>
<pre>curl -s -X POST http://localhost:3700/intelligence/profiler_index \
-H 'Content-Type: application/json' \
-d '{"limit":10}' \
| jq '.contractors[] | {name, permits, total_cost, direct: (.tickers.direct | map(.ticker)), associated: (.tickers.associated | map(.ticker + " ←via " + .partner_name))}'</pre>
<div class="narr"><strong>Live ticker quotes.</strong> Batch Stooq pull for the basket.</div>
<pre>curl -s -X POST http://localhost:3700/intelligence/ticker_quotes \
-H 'Content-Type: application/json' \
-d '{"tickers":["TGT","JPM","BALY","WBA","MCD"]}' | jq .quotes</pre>
<div class="narr"><strong>Audit trail — read any verdict on PR #11.</strong> Independent claim-vs-diff verifier output.</div>
<pre>ls /home/profit/lakehouse/data/_auditor/kimi_verdicts/
# 11-c3c9c2174a91.json 11-ca7375ea2b17.json 11-2d9cb128bf42.json …
jq '.findings[0:3]' /home/profit/lakehouse/data/_auditor/kimi_verdicts/11-c3c9c2174a91.json</pre>
<div class="narr"><strong>Distillation acceptance gate.</strong> 22/22 invariants must pass for any commit that touches the substrate.</div>
<pre>cd /home/profit/lakehouse <pre>cd /home/profit/lakehouse
bun run tests/multi-agent/scenario.ts bun test auditor/schemas/distillation/ tests/distillation/
# Output: tests/multi-agent/playbooks/scenario-&lt;timestamp&gt;/report.md</pre> # Expect: 145 pass · 0 fail · 372 expect() calls</pre>
</div> </div>
</div> </div>
<div class="chapter"> <div class="chapter">
<div class="num">Chapter 8</div> <div class="num">Chapter 10</div>
<h2>What we are <em>not</em> claiming</h2> <h2>What we are <em>not</em> claiming</h2>
<div class="lede">Every impressive-sounding number comes with a footnote. Here are the honest limits.</div> <div class="lede">Every impressive-sounding number comes with a footnote. Here are the honest limits as of 2026-04-27.</div>
<div class="card"> <div class="card">
<div class="row accent-a"><div style="flex:1"><div class="title">workers_500k is synthetic.</div><div class="meta">Real client ATS export replaces this table. Schema is deliberately identical to a production ATS.</div></div></div> <div class="row accent-a"><div style="flex:1"><div class="title">workers_500k is synthetic.</div><div class="meta">Real client ATS export replaces this table. Schema is deliberately identical to a production ATS so the swap is config, not code.</div></div></div>
<div class="row accent-a"><div style="flex:1"><div class="title">candidates table has 1,000 rows.</div><div class="meta">Intentionally small for demo. call_log references higher candidate_ids that don't cross-reference — this is a dataset alignment issue, not a pipeline issue.</div></div></div> <div class="row accent-a"><div style="flex:1"><div class="title">candidates table is light at 1,000 rows.</div><div class="meta">Intentionally small. Live PII-safe view layer is built; replacing the small table with a 100K+ ATS is a one-line config flip.</div></div></div>
<div class="row accent-b"><div style="flex:1"><div class="title">Chicago permit data is real.</div><div class="meta">Pulled live from data.cityofchicago.org/resource/ydr8-5enu.json (Socrata API). Not synthetic. Not cached.</div></div></div> <div class="row accent-b"><div style="flex:1"><div class="title">Chicago permit data is real.</div><div class="meta">Pulled live from data.cityofchicago.org/resource/ydr8-5enu.json (Socrata). Not synthetic. Not cached. Verifiable address-by-address.</div></div></div>
<div class="row accent-l"><div style="flex:1"><div class="title">Playbook memory is seeded from demo runs.</div><div class="meta">The pipeline that seeds it is identical to what a live recruiter would trigger via /log. Same code path.</div></div></div> <div class="row accent-l"><div style="flex:1"><div class="title">Playbook memory is seeded from demo runs.</div><div class="meta">Same code path that seeds in production: every /log from the recruiter UI triggers seed → persist_sql. Demo seeds use the same shape as live operations.</div></div></div>
<div class="row accent-w"><div style="flex:1"><div class="title">Local 7B models (mistral, qwen2.5) are imperfect.</div><div class="meta">They occasionally malform tool calls or drop fields. Multi-agent scenarios seal roughly 40-80% in one run. Larger models or constrained decoding would improve this. Not a substrate problem.</div></div></div> <div class="row accent-l"><div style="flex:1"><div class="title">Pathway memory probation gate is crossed.</div><div class="meta">88 traces, 11 replays, 11 successful, 100% reuse rate. Any pathway that fails to clear ≥0.80 success_rate after ≥3 replays gets retired automatically (sticky flag prevents oscillation).</div></div></div>
<div class="row accent-w"><div style="flex:1"><div class="title">SEC name-to-ticker fuzzy matcher has rare false positives.</div><div class="meta">For names with no clean SEC match the matcher occasionally surfaces a same-keyword small-cap (saw FLG attach to a PNC-adjacent contractor once). Kept conservative — minimum 2 non-stopword overlap. Tightenable to require explicit allow-list for production trading use.</div></div></div>
<div class="row accent-r"><div style="flex:1"><div class="title">12 awaiting public-data sources are placeholders.</div><div class="meta">DOL Wage &amp; Hour, EPA ECHO, MSHA, BBB, PACER, UCC liens, D&amp;B, etc. — listed by name on every contractor profile with a one-line "would show:" sample. Not yet wired. Each ships as a Socrata-style adapter; engineering scope is concrete.</div></div></div>
<div class="row accent-r"><div style="flex:1"><div class="title">No rate/margin awareness yet.</div><div class="meta">Worker pay expectations vs contract bill rates are not modeled. Flagged as a Phase 20 item; no architectural blocker.</div></div></div> <div class="row accent-r"><div style="flex:1"><div class="title">No rate/margin awareness yet.</div><div class="meta">Worker pay expectations vs contract bill rates are not modeled. Flagged as a Phase 20 item; no architectural blocker.</div></div></div>
<div class="row accent-r"><div style="flex:1"><div class="title">BAI is a thesis, not a backtested signal.</div><div class="meta">The Building Activity Index is computed live from current attribution + day-change. To have a backtestable thesis we need the daily series saved over months. Architectural support is there (data/_kb/audit_baselines.jsonl pattern); just hasn't been running long enough.</div></div></div>
<div class="row accent-r"><div style="flex:1"><div class="title">Single-metro today.</div><div class="meta">Chicago via Socrata. NYC DOB, LA County, Houston BCD, Boston ISD, DC DCRA all use Socrata-equivalent APIs — adapters are config-only. Each new metro multiplies the network without multiplying the codebase.</div></div></div>
</div> </div>
</div> </div>
@ -394,8 +499,72 @@ function apiPost(path, body){
window.addEventListener('load',function(){ window.addEventListener('load',function(){
loadLiveSections(); loadLiveSections();
loadPathwayLive();
loadSignalLive();
}); });
// Pathway memory live counters in Chapter 4 — small inline spans.
function loadPathwayLive(){
fetch(A+'/api/vectors/pathway/stats').then(function(r){return r.json()}).then(function(p){
if(!p) return;
var t=document.getElementById('pwm-traces');
var r=document.getElementById('pwm-replays');
var rate=document.getElementById('pwm-rate');
if(t) t.textContent = (p.total_pathways||0) + ' traces';
if(r) r.textContent = (p.successful_replays||0) + '/' + (p.total_replays||0);
if(rate) rate.textContent = Math.round((p.replay_success_rate||0)*100) + '%';
}).catch(function(){});
}
// Live tile under Chapter 1 — what the signal engine sees in this view.
function loadSignalLive(){
apiPost('/intelligence/profiler_index',{limit:200}).then(function(d){
var host=document.getElementById('ch1-live');if(!host) return;
host.textContent='';
var rows=d.contractors||[];
if(!rows.length) return;
// Aggregate basket
var byTk={};
rows.forEach(function(r){
var ts=(r.tickers&&r.tickers.direct?r.tickers.direct:[]).concat(r.tickers&&r.tickers.associated?r.tickers.associated:[]);
ts.forEach(function(t){
if(!t||!t.ticker) return;
if(!byTk[t.ticker]) byTk[t.ticker]={kinds:[],count:0};
byTk[t.ticker].count++;
if(byTk[t.ticker].kinds.indexOf(t.via)<0) byTk[t.ticker].kinds.push(t.via);
});
});
var basket=Object.values(byTk);
var attribCost=rows.reduce(function(s,r){
var ts=(r.tickers&&r.tickers.direct?r.tickers.direct:[]).concat(r.tickers&&r.tickers.associated?r.tickers.associated:[]);
return s + (ts.length>0 ? (r.total_cost||0) : 0);
},0);
if(!basket.length) return;
var card=el('div','card accent-l');
var hdr=el('div',null,'LIVE — Construction Activity Signal Engine');
hdr.style.cssText='font-size:10px;color:#3fb950;text-transform:uppercase;letter-spacing:1.4px;font-weight:700;margin-bottom:8px';
card.appendChild(hdr);
var line=document.createElement('div');
line.style.cssText='display:flex;gap:24px;flex-wrap:wrap;font-size:13px';
function block(num,lab){
var b=document.createElement('div');
var n=document.createElement('div');n.style.cssText='font-size:18px;font-weight:700;color:#e6edf3;font-family:ui-monospace,monospace';n.textContent=num;
var l=document.createElement('div');l.style.cssText='font-size:10px;color:#545d68;text-transform:uppercase;letter-spacing:1.2px;font-weight:600';l.textContent=lab;
b.appendChild(n);b.appendChild(l);return b;
}
var bav = attribCost>=1e9?'$'+(attribCost/1e9).toFixed(2)+'B':attribCost>=1e6?'$'+(attribCost/1e6).toFixed(0)+'M':'$'+Math.round(attribCost/1e3)+'K';
line.appendChild(block(basket.length+'', 'Public issuers in scope'));
line.appendChild(block(bav, 'Attributed build value'));
line.appendChild(block(rows.length+'', 'Contractors indexed'));
line.appendChild(block(basket.reduce(function(s,b){return s+b.count},0)+'', 'Attribution edges'));
card.appendChild(line);
var note=el('div',null,'Computed live from /intelligence/profiler_index in '+(d.duration_ms||0)+'ms · click any of the chapter-9 curl lines to verify');
note.style.cssText='font-size:11px;color:#545d68;margin-top:10px;font-family:ui-monospace,monospace';
card.appendChild(note);
host.appendChild(card);
}).catch(function(){});
}
function loadLiveSections(){ function loadLiveSections(){
apiPost('/proof.json',{}).then(function(r){ apiPost('/proof.json',{}).then(function(r){
var host1=document.getElementById('ch1-tests');host1.textContent=''; var host1=document.getElementById('ch1-tests');host1.textContent='';

92
mcp-server/role_scenes.ts Normal file
View File

@ -0,0 +1,92 @@
// Server-side mirror of search.html's ROLE_BANDS regex table.
// Each band carries a *visual scene* — clothing + immediate backdrop —
// so ComfyUI produces role-coherent headshots instead of interchangeable
// studio portraits. The front-end sends the raw role string in the
// query (?role=Forklift%20Operator); the server resolves it to a band
// and looks up the scene here.
export type RoleBand =
| "warehouse"
| "production"
| "trades"
| "driver"
| "lead";
export interface SceneDef {
band: RoleBand;
// Free-form clause inserted into the diffusion prompt AFTER
// "[age]-year-old [race] [gender] [role], ". Should describe what
// they're wearing and what is immediately behind them. Keep under
// ~25 words — SDXL Turbo loses focus on longer prompts and starts
// hallucinating cartoon hands.
scene: string;
}
const RE_BANDS: { re: RegExp; band: RoleBand }[] = [
{ re: /forklift|warehouse|associate|material\s*handler|loader|loading|packag|shipping|logistics|inventory|sanitation|janit/i, band: "warehouse" },
{ re: /production|assembl|quality/i, band: "production" },
{ re: /welder|weld|electric|maint(enance)?\s*tech|cnc|machine\s*op|hvac|plumb|carpenter|mason|tool\s*&\s*die/i, band: "trades" },
{ re: /driver|truck|haul|cdl/i, band: "driver" },
{ re: /line\s*lead|supervisor|foreman|coordinator|lead\b/i, band: "lead" },
];
export function roleBand(role: string): RoleBand {
const r = (role || "").trim();
if (!r) return "warehouse";
for (const b of RE_BANDS) if (b.re.test(r)) return b.band;
return "warehouse";
}
// TODO J — refine these. Each `scene` string lands directly in the
// diffusion prompt. Tone target: a coordinator glances at the card
// and recognizes the role from the photo before reading the role pill.
//
// Things that work well in SDXL Turbo at 8 steps:
// - One concrete clothing item ("high-visibility yellow vest")
// - One concrete prop ("hard hat hanging from belt", "tablet in hand")
// - One blurred background element ("warehouse pallet aisle behind",
// "factory machinery softly out of focus")
// - Avoid: text/logos (rendered as scribble), specific brands, hands
// holding tools (often distorts), full-body language ("standing",
// "leaning") — model is trained on portrait crops.
//
// Each scene now bakes "monochrome black and white photography" into
// the prompt so the model produces native B&W output rather than us
// applying CSS grayscale post-hoc. SDXL Turbo handles B&W natively
// with strong tonal range — better than desaturating a color render.
export const SCENES: Record<RoleBand, SceneDef> = {
warehouse: {
band: "warehouse",
scene: "wearing a high-visibility safety vest over a t-shirt, hard hat visible, blurred warehouse pallet aisle behind, soft natural light, monochrome black and white photography, fine film grain, documentary portrait style",
},
production: {
band: "production",
scene: "wearing a work shirt with safety glasses on forehead, blurred factory machinery softly out of focus behind, fluorescent overhead lighting, monochrome black and white photography, fine film grain, documentary portrait style",
},
trades: {
band: "trades",
scene: "wearing a heavy-duty work shirt with rolled sleeves, blurred workshop tool wall behind, focused tungsten lighting, monochrome black and white photography, fine film grain, documentary portrait style",
},
driver: {
band: "driver",
scene: "wearing a polo shirt, lanyard with ID badge visible, blurred truck cab or loading dock behind, daylight, monochrome black and white photography, fine film grain, documentary portrait style",
},
lead: {
band: "lead",
scene: "wearing a button-down shirt, tablet held casually at chest level, blurred warehouse floor in soft focus behind, professional lighting, monochrome black and white photography, fine film grain, documentary portrait style",
},
};
// v2 — baked B&W + 1024×1024 render canvas (4× pixels of v1). Larger
// source means downsampling to a 40px avatar packs more detail per
// displayed pixel, hiding the diffusion-y micro-textures that read as
// "AI generated" at small sizes. Server route reads pool from
// data/headshots_role_pool/{SCENES_VERSION}/... so v1 stays available
// for rollback / A-B comparison.
export const SCENES_VERSION = "v2";
// Default render dimensions used by both the on-demand /headshots/
// generate/:key route and the offline render_role_pool.py script. v1
// used 512²; v2 doubles to 1024² (linear 2× = 4× pixels = ~3× GPU
// time on SDXL Turbo).
export const FACE_RENDER_DIM = 1024;

2078
mcp-server/search.html
View File

File diff suppressed because it is too large Load Diff

108
mcp-server/spec.html
View File

@ -78,13 +78,14 @@ table.plain tr:hover td{background:#0d1117}
<nav> <nav>
<a href=".">Dashboard</a> <a href=".">Dashboard</a>
<a href="console">Walkthrough</a> <a href="console">Walkthrough</a>
<a href="profiler">Profiler</a>
<a href="proof">Architecture</a> <a href="proof">Architecture</a>
<a href="spec" class="active">Spec</a> <a href="spec" class="active">Spec</a>
<a href="onboard">Onboard</a> <a href="onboard">Onboard</a>
<a href="alerts">Alerts</a> <a href="alerts">Alerts</a>
<a href="workspaces">Workspaces</a> <a href="workspaces">Workspaces</a>
</nav> </nav>
<div class="rt">v1 · 2026-04-20</div> <div class="rt">v3 · 2026-04-27</div>
</div> </div>
<div class="layout"> <div class="layout">
@ -120,14 +121,18 @@ table.plain tr:hover td{background:#0d1117}
<tr><td class="mono">crates/vectord/</td><td>The vector + learning surface. Embeddings stored as Parquet (ADR-008), HNSW index (Phase 15), trial system (autotune), promotion registry (Phase 16), playbook_memory (Phase 19). Core feedback loop lives here.</td></tr> <tr><td class="mono">crates/vectord/</td><td>The vector + learning surface. Embeddings stored as Parquet (ADR-008), HNSW index (Phase 15), trial system (autotune), promotion registry (Phase 16), playbook_memory (Phase 19). Core feedback loop lives here.</td></tr>
<tr><td class="mono">crates/vectord-lance/</td><td>Firewall crate. Lance 4.0 + Arrow 57, isolated from the main Arrow-55 workspace. Provides secondary vector backend for large-scale, random-access, and append-heavy workloads (ADR-019).</td></tr> <tr><td class="mono">crates/vectord-lance/</td><td>Firewall crate. Lance 4.0 + Arrow 57, isolated from the main Arrow-55 workspace. Provides secondary vector backend for large-scale, random-access, and append-heavy workloads (ADR-019).</td></tr>
<tr><td class="mono">crates/journald/</td><td>Append-only mutation event log (ADR-012). Every insert/update/delete writes here — who, when, what, old/new value. Never mutated. Foundation for time-travel + compliance audit.</td></tr> <tr><td class="mono">crates/journald/</td><td>Append-only mutation event log (ADR-012). Every insert/update/delete writes here — who, when, what, old/new value. Never mutated. Foundation for time-travel + compliance audit.</td></tr>
<tr><td class="mono">crates/aibridge/</td><td>Rust ↔ Python sidecar. HTTP client over FastAPI wrapper around Ollama. VRAM introspection via nvidia-smi. All LLM calls (embed, generate, rerank) flow through here.</td></tr> <tr><td class="mono">crates/truth/</td><td>File-backed rule store. <code>evaluate(task_class, ctx) → Vec&lt;RuleOutcome&gt;</code> (ADR-021 — semantic-correctness matrix layer). Loaded from <code>truth/*.toml</code> at gateway boot.</td></tr>
<tr><td class="mono">crates/gateway/</td><td>Axum HTTP (:3100) + gRPC (:3101). Auth middleware, tools registry (Phase 12 — governed actions), CORS. Every external request enters here.</td></tr> <tr><td class="mono">crates/aibridge/</td><td>Rust ↔ Python sidecar + provider adapter trait. HTTP client over FastAPI wrapper around Ollama for local; <code>ProviderAdapter</code> dispatch for cloud (ollama_cloud, openrouter, opencode, kimi). VRAM introspection via nvidia-smi. All LLM calls flow through here.</td></tr>
<tr><td class="mono">crates/gateway/</td><td>Axum HTTP (:3100) + gRPC (:3101). OpenAI-compat <code>/v1/*</code> (drop-in middleware), mode runner (<code>/v1/mode/execute</code>), validator (<code>/v1/validate</code>), iterate loop (<code>/v1/iterate</code>), tools registry, cost telemetry, Langfuse + observer fan-out on every chat. Every external request enters here.</td></tr>
<tr><td class="mono">crates/validator/</td><td>Phase 43 production validator. Schema / completeness / consistency / policy gates over LLM outputs. <code>FillValidator</code>, <code>EmailValidator</code>, <code>ParquetWorkerLookup</code> (loads workers_500k.parquet at boot). Fail-closed when roster absent.</td></tr>
<tr><td class="mono">crates/ui/</td><td>Dioxus WASM developer UI. Internal tool. Not exposed externally.</td></tr> <tr><td class="mono">crates/ui/</td><td>Dioxus WASM developer UI. Internal tool. Not exposed externally.</td></tr>
<tr><td class="mono">mcp-server/</td><td>Bun/TypeScript recruiter-facing app. Serves <code>devop.live/lakehouse</code>. Routes: <code>/search /match /log /log_failure /clients/:c/blacklist /intelligence/* /memory/query /models/matrix /system/summary</code>. Observer sibling at <code>observer.ts</code> with HTTP listener on :3800 for scenario event ingest. Proxies to the Rust gateway for heavy work.</td></tr> <tr><td class="mono">mcp-server/</td><td>Bun/TypeScript public-facing app + MCP tool surface. Serves <code>devop.live/lakehouse</code>. Pages: dashboard / console / profiler / contractor / proof / spec / onboard / alerts / workspaces. Routes: <code>/search /match /log /log_failure /clients/:c/blacklist /intelligence/* /staffers /memory/query /models/matrix /system/summary</code>. Observer sibling at <code>observer.ts</code> on :3800 for event ingest.</td></tr>
<tr><td class="mono">tests/multi-agent/</td><td>Dual-agent scenario harness + memory stack. <code>agent.ts</code> (prompts, continuation + tree-split primitives, cloud routing), <code>orchestrator.ts</code>, <code>scenario.ts</code> (contracts + staffer + tool_level), <code>kb.ts</code> (KB indexing, competence scoring, neighbor retrieval), <code>normalize.ts</code> (input normalizer — structured / regex / LLM), <code>memory_query.ts</code> (unified /memory/query), <code>gen_scenarios.ts</code> + <code>gen_staffer_demo.ts</code> (corpus generators), <code>run_e2e_rated.ts</code>, <code>chain_of_custody.ts</code>. Unit tests colocated (<code>kb.test.ts</code>, <code>normalize.test.ts</code>).</td></tr> <tr><td class="mono">auditor/</td><td>External claim-vs-diff verifier on PRs. Polls Gitea for open PRs, builds adversarial prompt from PRD invariants + staffing matrix, alternates Kimi K2.6 ↔ Haiku 4.5 by SHA, auto-promotes Claude Opus 4.7 on diffs &gt;100k chars. Per-PR cap=3 with auto-reset on each new head SHA. Verdicts at <code>data/_auditor/kimi_verdicts/</code>.</td></tr>
<tr><td class="mono">config/</td><td><code>models.json</code> — authoritative 5-tier model matrix (T1 hot local / T2 review local / T3 overview cloud / T4 strategic / T5 gatekeeper). Per-tier context_window + context_budget + overflow_policy. Read at runtime by scenario.ts; hot-swap friendly.</td></tr> <tr><td class="mono">tests/multi-agent/</td><td>Multi-agent scenario harness + memory stack. <code>agent.ts</code>, <code>scenario.ts</code> (contracts + staffer + tool_level), <code>kb.ts</code> (KB indexing, competence scoring), <code>normalize.ts</code>, <code>memory_query.ts</code>, <code>run_e2e_rated.ts</code>. Unit tests colocated.</td></tr>
<tr><td class="mono">docs/</td><td><code>PRD.md</code>, <code>PHASES.md</code>, <code>DECISIONS.md</code> (20 ADRs). Every significant architectural choice has an ADR with the alternatives that were rejected and why.</td></tr> <tr><td class="mono">scripts/distillation/</td><td>Distillation substrate v1.0.0 (frozen at tag <code>distillation-v1.0.0</code> / commit <code>e7636f2</code>). 145 unit tests, 22/22 acceptance, 16/16 audit-full, bit-identical reproducibility. Multi-layer contamination firewall on SFT exports.</td></tr>
<tr><td class="mono">data/</td><td>Default local object store. Parquet files per dataset, append-log batches, HNSW trial journals, promotion registries, <code>_playbook_memory/state.json</code> (now with retirement fields — Phase 25), catalog manifests. Plus four learning-loop directories: <code>_kb/</code> (signatures, outcomes, recommendations, error_corrections, config_snapshots, staffers), <code>_playbook_lessons/</code> (T3 cross-day lessons archived per run), <code>_observer/ops.jsonl</code> (append journal, durable scenario outcome stream), <code>_chunk_cache/</code> (spec'd for Phase 21 Rust port). Rebuildable from repo + this dir alone.</td></tr> <tr><td class="mono">config/</td><td><code>modes.toml</code> — task_class → mode/model router (<code>scrum_review</code>, <code>contract_analysis</code>, <code>staffing_inference</code>, <code>pr_audit</code>, <code>doc_drift_check</code>, <code>fact_extract</code>). <code>providers.toml</code> — 5 active providers (ollama, ollama_cloud, openrouter, opencode 40-model, kimi direct). <code>routing.toml</code> — cost gates per task class.</td></tr>
<tr><td class="mono">docs/</td><td><code>PRD.md</code>, <code>PHASES.md</code>, <code>DECISIONS.md</code> (21 ADRs). Every significant architectural choice has an ADR with the alternatives that were rejected and why.</td></tr>
<tr><td class="mono">data/</td><td>Default local object store. Parquet datasets, append-log batches, HNSW trial journals, promotion registries, <code>_playbook_memory/state.json</code>, <code>_pathway_memory/state.json</code> (88 traces, 11/11 successful replays, ADR-021), catalog manifests. Plus learning-loop directories: <code>_kb/</code>, <code>_playbook_lessons/</code>, <code>_observer/ops.jsonl</code>, <code>_auditor/kimi_verdicts/</code>. Rebuildable from repo + this dir alone.</td></tr>
</tbody> </tbody>
</table> </table>
</div> </div>
@ -199,20 +204,42 @@ table.plain tr:hover td{background:#0d1117}
<li>Ollama swaps to the profile's model via <code>keep_alive=0</code>; only one model in VRAM at a time</li> <li>Ollama swaps to the profile's model via <code>keep_alive=0</code>; only one model in VRAM at a time</li>
</ul> </ul>
<h3>Model matrix (Phase 20)</h3> <h3>Provider fleet — 5 active, 40+ frontier models reachable</h3>
<p>Five tiers declared in <code>config/models.json</code>. Each call site picks the tier appropriate to its purpose — hot-path JSON emitters get fast local, overview/strategic/gatekeeper decisions get thinking models on cloud. Every tier carries <code>context_window</code>, <code>context_budget</code>, and <code>overflow_policy</code>.</p> <p>Declared in <code>config/providers.toml</code> + <code>config/modes.toml</code>. Gateway is an OpenAI-compatible drop-in middleware: any consumer that speaks <code>POST /v1/chat/completions</code> gets routing, audit, cost telemetry, and the full memory substrate behind every call.</p>
<table class="plain"> <table class="plain">
<thead><tr><th>Tier</th><th>Purpose</th><th>Primary model</th><th>Frequency</th></tr></thead> <thead><tr><th>Provider</th><th>Reach</th><th>Use case</th></tr></thead>
<tbody> <tbody>
<tr><td>T1 hot</td><td>Per tool call — SQL gen, hybrid_search, propose_done</td><td><code>qwen3.5:latest</code> local, <code>think:false</code></td><td>50-200/scenario</td></tr> <tr><td><code>ollama</code></td><td>localhost:3200 — local sidecar over Ollama</td><td>Hot-path JSON emitters, embeddings, last-resort rescue</td></tr>
<tr><td>T2 review</td><td>Per-step consensus, drift flagging</td><td><code>qwen3:latest</code> local, <code>think:false</code></td><td>5-14/event</td></tr> <tr><td><code>ollama_cloud</code></td><td>ollama.com bearer key — gpt-oss:120b, qwen3-coder:480b, deepseek-v3.1:671b, kimi-k2:1t, mistral-large-3:675b, qwen3.5:397b</td><td>Strong-model reviewer rungs, T3+ overview, scrum master pipeline</td></tr>
<tr><td>T3 overview</td><td>Mid-day checkpoints + cross-day lesson distill</td><td><code>gpt-oss:120b</code> Ollama Cloud, thinking on</td><td>1-3/scenario</td></tr> <tr><td><code>openrouter</code></td><td>openrouter.ai/api/v1 — 343 models incl. Anthropic/Google/OpenAI/MiniMax/Qwen, paid + free tiers</td><td>Paid ladder for observer escalations, free-tier rescue</td></tr>
<tr><td>T4 strategic</td><td>Pattern re-ranking, weekly gap audit</td><td><code>qwen3.5:397b</code> cloud</td><td>1-10/day</td></tr> <tr><td><code>opencode</code></td><td>opencode.ai/zen/v1 — <strong>40 frontier models reachable through ONE sk-* key</strong>: Claude Opus 4.7 / Sonnet / Haiku, GPT-5.5-pro / 5.4 / codex variants, Gemini 3.1-pro, Kimi K2.6, GLM 5.1, DeepSeek, Qwen 3.6+, MiniMax, plus 4 free-tier</td><td>Cross-architecture tie-breakers, auditor cross-lineage (Haiku 4.5 + Opus 4.7), high-context reasoning (Opus on diffs &gt;100k chars)</td></tr>
<tr><td>T5 gatekeeper</td><td>Schema migrations, autotune config changes</td><td><code>kimi-k2-thinking</code> cloud, audit-logged</td><td>1-5/day</td></tr> <tr><td><code>kimi</code></td><td>api.kimi.com/coding/v1 — direct Kimi For Coding</td><td>kimi_architect when ollama_cloud rate-limits; TOS-clean primary path</td></tr>
</tbody> </tbody>
</table> </table>
<p><strong>Key mechanical finding (2026-04-21):</strong> qwen3.5 and qwen3 are <em>thinking</em> models — they burn ~650 tokens of hidden reasoning before emitting the visible response. For hot-path JSON emitters this meant 400-token budgets returned empty strings. Fix: <code>think: false</code> plumbed through sidecar's <code>/generate</code> endpoint; hot path disables thinking (structure matters more than reasoning depth), overseer tiers keep it on. Mistral was dropped entirely after a 0/14 fill rate on complex scenarios (decoder-level malformed-JSON bug, not a prompt issue).</p>
<p><strong>Continuation primitive (Phase 21):</strong> <code>generateContinuable()</code> handles output-overflow without <code>max_tokens</code> tourniquets — empty response → geometric backoff retry; truncated-JSON → continue with partial as scratchpad. <code>generateTreeSplit()</code> handles input-overflow via map-reduce with running scratchpad. Both respect <code>assertContextBudget()</code> so silent truncation can't happen.</p> <h3>The 9-rung cloud-first ladder</h3>
<p>Defined in <code>tests/real-world/scrum_master_pipeline.ts</code> as <code>const LADDER</code>. Each attempt is evaluated by <code>isAcceptable()</code> = chars ≥ 3800 ∧ not malformed JSON-only. On reject, the next rung sees a learning preamble carrying the prior rejection reason.</p>
<pre>1 ollama_cloud / kimi-k2:1t 1T params · flagship
2 ollama_cloud / qwen3-coder:480b coding specialist
3 ollama_cloud / deepseek-v3.1:671b reasoning
4 ollama_cloud / mistral-large-3:675b deep analysis
5 ollama_cloud / gpt-oss:120b reliable workhorse
6 ollama_cloud / qwen3.5:397b dense final thinker
7 openrouter / openai/gpt-oss-120b:free rescue tier
8 openrouter / google/gemma-3-27b-it:free fastest rescue
9 ollama / qwen3.5:latest last-resort local</pre>
<h3>N=3 consensus + cross-architecture tie-breaker</h3>
<p>Every audit and every consensus-required call fires the primary reviewer N=3 times in parallel (Promise.all — wall-clock = single call). Aggregate votes per claim_idx, majority wins. On a 1-1-1 split, a tie-breaker model with <em>different architecture</em> (qwen3-coder:480b vs primary gpt-oss/kimi) is invoked. Every disagreement, even when majority resolves, writes to <code>data/_kb/audit_discrepancies.jsonl</code>. Closes the cloud-non-determinism gap: <code>temp=0</code> isn't actually deterministic in practice across hours; consensus + cross-architecture tie-break stabilizes verdicts.</p>
<h3>Auditor cross-lineage (Kimi ↔ Haiku ↔ Opus)</h3>
<p>Every push to PR #11 triggers <code>auditor/audit.ts</code> within ~90s. To prevent a single model lineage's blind spots from becoming the system's blind spots, audits alternate between Kimi K2.6 (Moonshot lineage) and Haiku 4.5 (Anthropic lineage) by head SHA. Diffs over 100k chars auto-promote to Claude Opus 4.7 (Anthropic frontier). Per-PR cap of 3 audits with auto-reset on each new head SHA prevents infinite-loop spend. <strong>Latest verdict on c3c9c21:</strong> Haiku 4.5, 24.6s, 100% grounding-verified across 10 findings.</p>
<h3>Distillation v1.0.0 — the frozen substrate</h3>
<p>The substrate the auditor and mode runner sit on is tagged at <code>distillation-v1.0.0</code> / commit <code>e7636f2</code>. <strong>145 unit tests pass · 22/22 acceptance invariants · 16/16 audit-full checks · bit-identical reproducibility verified.</strong> The distillation phase exports clean SFT / RAG / preference samples with a multi-layer contamination firewall (<code>SFT_NEVER</code> constant + scorer category mapping + acceptance fixtures); the auditor consumes the substrate. The frozen tag means: any future "the system regressed" question has a baseline to bisect against, byte-for-byte.</p>
<h3>Continuation primitive (Phase 21)</h3>
<p><code>generateContinuable()</code> handles output-overflow without <code>max_tokens</code> tourniquets — empty response → geometric backoff retry; truncated-JSON → continue with partial as scratchpad. <code>generateTreeSplit()</code> handles input-overflow via map-reduce with running scratchpad. Both respect <code>assertContextBudget()</code> so silent truncation can't happen. Now Rust-native in <code>crates/aibridge/src/continuation.rs</code> (Phase 44).</p>
<h3>Per-staffer tool_level (Phase 23)</h3> <h3>Per-staffer tool_level (Phase 23)</h3>
<p>Scenarios can be scoped to a specific coordinator (<code>staffer: {id, name, tenure_months, role, tool_level}</code>). <code>tool_level</code> controls which tiers are available:</p> <p>Scenarios can be scoped to a specific coordinator (<code>staffer: {id, name, tenure_months, role, tool_level}</code>). <code>tool_level</code> controls which tiers are available:</p>
@ -265,6 +292,12 @@ table.plain tr:hover td{background:#0d1117}
<tr><td>Boost workers based on past success</td><td>No</td><td>Yes (Phase 19 playbook_memory)</td></tr> <tr><td>Boost workers based on past success</td><td>No</td><td>Yes (Phase 19 playbook_memory)</td></tr>
<tr><td>Penalize workers based on past failure</td><td>No</td><td>Yes (<code>/log_failure</code> + <code>0.5<sup>n</sup></code> penalty)</td></tr> <tr><td>Penalize workers based on past failure</td><td>No</td><td>Yes (<code>/log_failure</code> + <code>0.5<sup>n</sup></code> penalty)</td></tr>
<tr><td>Surface traits across past fills</td><td>No</td><td>Yes (<code>/vectors/playbook_memory/patterns</code>)</td></tr> <tr><td>Surface traits across past fills</td><td>No</td><td>Yes (<code>/vectors/playbook_memory/patterns</code>)</td></tr>
<tr><td>Per-staffer relevance gradient</td><td>No</td><td>Yes — same query reshapes per coordinator (<code>staffer_id</code> on <code>/intelligence/chat</code>); MARIA'S MEMORY pill labels the playbook context with the active coordinator</td></tr>
<tr><td>Triage in one shot — late-worker → backfills + draft SMS</td><td>No</td><td>Yes (<code>/intelligence/chat</code> Route 6 — pulls profile + 5 same-role same-geo backfills sorted by responsiveness + drafts client SMS in ~250ms)</td></tr>
<tr><td>Permit → fill plan derivation (forward demand)</td><td>No</td><td>Yes (<code>/intelligence/permit_contracts</code> — Chicago Socrata permit → role / headcount / deadline / fill probability / gross revenue per card)</td></tr>
<tr><td>Public-issuer attribution across contractor graph</td><td>No</td><td>Yes (<code>/intelligence/profiler_index</code> — direct + parent + co-permit associated tickers; live Stooq prices)</td></tr>
<tr><td>Cross-lineage AI audit on every PR</td><td>No</td><td>Yes (auditor crate — Kimi K2.6 ↔ Haiku 4.5 alternation + Opus 4.7 auto-promote on big diffs)</td></tr>
<tr><td>Pathway memory — system-level hot-swap by task fingerprint</td><td>No</td><td>Yes (88 traces, 11/11 successful replays, 100% reuse rate, ADR-021)</td></tr>
<tr><td>Predict staffing demand from external data</td><td>No</td><td>Yes (Chicago permit feed + 30-day rolling forecast)</td></tr> <tr><td>Predict staffing demand from external data</td><td>No</td><td>Yes (Chicago permit feed + 30-day rolling forecast)</td></tr>
<tr><td>Count down to staffing deadline per contract</td><td>No</td><td>Yes (permit issue_date + heuristic timeline)</td></tr> <tr><td>Count down to staffing deadline per contract</td><td>No</td><td>Yes (permit issue_date + heuristic timeline)</td></tr>
<tr><td>Explain why each candidate ranked</td><td>No</td><td>Yes (boost chip + narrative citations + memory pattern)</td></tr> <tr><td>Explain why each candidate ranked</td><td>No</td><td>Yes (boost chip + narrative citations + memory pattern)</td></tr>
@ -278,7 +311,7 @@ table.plain tr:hover td{background:#0d1117}
<div class="chapter" id="ch6"> <div class="chapter" id="ch6">
<div class="num">Chapter 6</div> <div class="num">Chapter 6</div>
<h2>How it gets better over time</h2> <h2>How it gets better over time</h2>
<div class="lede">Compounding learning across seven paths. The first three are automatic background loops. Paths 4-7 landed 2026-04-21 and turn the system into a reinforcement-learning pipeline: outcomes → knowledge base → pathway recommendations → cloud rescue → competence-weighted retrieval → observer analysis. All seven happen without operator intervention.</div> <div class="lede">Compounding learning across ten paths. The first three are automatic background loops. Paths 4-7 (Phase 22-24) added the reinforcement layer: outcomes → KB → recommendations → cloud rescue → competence-weighted retrieval → observer analysis. Paths 7-9 (Phase 25-43, 2026-04-26→27) added the system-level memory layers: pathway memory by task fingerprint (ADR-021), per-staffer hot-swap, and the Construction Activity Signal Engine. All ten happen without operator intervention.</div>
<h3>Path 1 — Playbook boost with geo + role prefilter (Phase 19 + refinement)</h3> <h3>Path 1 — Playbook boost with geo + role prefilter (Phase 19 + refinement)</h3>
<p>Every sealed fill is seeded to <code>playbook_memory</code>. The boost fires inside <code>/vectors/hybrid</code> when <code>use_playbook_memory: true</code>. Math, tightened 2026-04-21 after a diagnostic pass found globally-ranked playbooks were missing the SQL-filtered candidate pool entirely:</p> <p>Every sealed fill is seeded to <code>playbook_memory</code>. The boost fires inside <code>/vectors/hybrid</code> when <code>use_playbook_memory: true</code>. Math, tightened 2026-04-21 after a diagnostic pass found globally-ranked playbooks were missing the SQL-filtered candidate pool entirely:</p>
@ -311,7 +344,19 @@ boost[(city, state, name)] = min(Σ per_worker, 0.25)</pre>
<p>Answers "who handled this" as a first-class matrix-index dimension. Each scenario carries <code>staffer: {id, name, tenure_months, role, tool_level}</code>. After every run, <code>recomputeStafferStats(staffer_id)</code> aggregates their fill_rate, turn efficiency, citation density, rescue rate into a single <code>competence_score</code> (0.45·fill + 0.20·turn_eff + 0.20·cites + 0.15·rescue).</p> <p>Answers "who handled this" as a first-class matrix-index dimension. Each scenario carries <code>staffer: {id, name, tenure_months, role, tool_level}</code>. After every run, <code>recomputeStafferStats(staffer_id)</code> aggregates their fill_rate, turn efficiency, citation density, rescue rate into a single <code>competence_score</code> (0.45·fill + 0.20·turn_eff + 0.20·cites + 0.15·rescue).</p>
<p><code>findNeighbors</code> returns <code>weighted_score = cosine × max_staffer_competence</code> — top-performer playbooks rank above juniors' on similar scenarios. Auto-discovery emerges: running 4 staffers × 3 contracts × 3 rounds surfaced Rachel D. Lewis (Welder Nashville) with 18 endorsements across all 4 staffers, Angela U. Ward (Machine Op Indianapolis) with 19 — reliable-performer labels the system built without human tagging.</p> <p><code>findNeighbors</code> returns <code>weighted_score = cosine × max_staffer_competence</code> — top-performer playbooks rank above juniors' on similar scenarios. Auto-discovery emerges: running 4 staffers × 3 contracts × 3 rounds surfaced Rachel D. Lewis (Welder Nashville) with 18 endorsements across all 4 staffers, Angela U. Ward (Machine Op Indianapolis) with 19 — reliable-performer labels the system built without human tagging.</p>
<h3>Path 7 — Observer outcome ingest (Phase 24)</h3> <h3>Path 7 — Pathway memory (ADR-021 — semantic-correctness matrix layer)</h3>
<p>Memory at the system layer, not the worker layer. Every accepted scrum review writes a <code>PathwayTrace</code> with the full backtrack: file fingerprint, model used, signal class, KB chunks consulted, observer events, semantic flags (UnitMismatch, TypeConfusion, OffByOne, StaleReference, DeadCode, BoundaryViolation, …), bug fingerprints. A new query that fingerprints to the same trace can hot-swap to the prior result without re-running the 9-rung escalation. Five-factor hot-swap gate: narrow fingerprint match AND audit consensus pass AND replay_count ≥ 3 (probation) AND success_rate ≥ 0.80 AND NOT retired AND vector cosine ≥ 0.90.</p>
<p><strong>Live state (verified on this load):</strong> 88 traces · 11 / 11 successful replays · 100% reuse rate · probation gate crossed. Endpoints: <code>/vectors/pathway/insert</code> · <code>/query</code> · <code>/record_replay</code> · <code>/stats</code> · <code>/bug_fingerprints</code>. Spec: <code>docs/DECISIONS.md</code> ADR-021.</p>
<h3>Path 8 — Per-staffer hot-swap index</h3>
<p>Memory scoped to whoever's acting. <code>/intelligence/chat</code> accepts <code>staffer_id</code>; on match, defaults state filter to staffer territory, scopes playbook-pattern geo to staffer's primary city/state, and surfaces <code>response.staffer.name</code> so the UI relabels MEMORY → MARIA'S MEMORY. Same query "forklift operators" returns 167 IL workers as Maria, 89 IN as Devon, 16 WI as Aisha. The corpus stays intact; the relevance gradient is per coordinator; each accumulates fills independently.</p>
<p><strong>Roster:</strong> <code>/staffers</code> endpoint reads from <code>STAFFERS</code> in <code>mcp-server/index.ts</code>. Three personas today (Maria/Devon/Aisha); architecture generalizes — every new metro adds territories, not code paths.</p>
<h3>Path 9 — Construction Activity Signal Engine</h3>
<p>Memory at the network layer. Every contractor in the corpus is also a forward indicator on the public equities they touch via three attribution flavors: <code>direct</code> (contractor IS the public issuer — SEC tickers index match), <code>parent</code> (subsidiary of a public parent — curated KNOWN_PARENT_MAP, e.g. Turner → HOC.DE via Hochtief AG), <code>associated</code> (co-permit network — Bob's Electric appears with TARGET CORPORATION 3+ times → inherits TGT). The associated path is the moat: a staffing-permit dataset that maps contractor-to-public-issuer is not commercially available; we synthesize it from the Socrata co-occurrence graph.</p>
<p><strong>BAI (Building Activity Index)</strong> = attribution-weighted average day-change across surfaced issuers. <strong>Indexed build value</strong> = total $ of permits attributable to ANY public issuer in scope. <strong>Network depth</strong> = issuers / total attribution edges. Cross-metro replication explicit in the architecture — Chicago is Phase 1; NYC DOB / LA County / Houston BCD / Boston ISD / DC DCRA are all Socrata-shaped, ship as config-only adapters.</p>
<h3>Path 10 — Observer outcome ingest (Phase 24)</h3>
<p>Observer runs as <code>lakehouse-observer.service</code>, now with an HTTP listener on <code>:3800</code>. Scenarios POST per-event outcomes to <code>/event</code> with full provenance (staffer_id, sig_hash, event_kind, role, city, state, rescue flags). Observer's ERROR_ANALYZER and PLAYBOOK_BUILDER loops consume them alongside MCP-wrapped ops. Persistence switched from the old <code>/ingest/file</code> REPLACE path to an append-only <code>data/_observer/ops.jsonl</code> journal so the trace survives across restarts.</p> <p>Observer runs as <code>lakehouse-observer.service</code>, now with an HTTP listener on <code>:3800</code>. Scenarios POST per-event outcomes to <code>/event</code> with full provenance (staffer_id, sig_hash, event_kind, role, city, state, rescue flags). Observer's ERROR_ANALYZER and PLAYBOOK_BUILDER loops consume them alongside MCP-wrapped ops. Persistence switched from the old <code>/ingest/file</code> REPLACE path to an append-only <code>data/_observer/ops.jsonl</code> journal so the trace survives across restarts.</p>
<h3>Input normalizer + unified memory query</h3> <h3>Input normalizer + unified memory query</h3>
@ -399,7 +444,11 @@ boost[(city, state, name)] = min(Σ per_worker, 0.25)</pre>
<div class="chapter" id="ch9"> <div class="chapter" id="ch9">
<div class="num">Chapter 9</div> <div class="num">Chapter 9</div>
<h2>Per-staffer context</h2> <h2>Per-staffer context</h2>
<div class="lede">Twenty staffers don't see the same UI state. Each one's session is shaped by their active profile, their workspaces, their assigned contracts, and their client's blacklists.</div> <div class="lede">Twenty staffers don't see the same UI state. Each one's session is shaped by their identity (the per-staffer hot-swap index — Path 8 in Ch6), their active profile, their workspaces, their assigned contracts, and their client's blacklists.</div>
<h3>Per-staffer hot-swap index (the recent layer)</h3>
<p>Maria runs Chicago. Devon runs Indianapolis. Aisha runs Wisconsin/Michigan. They share one corpus, but search results, recurring-skill patterns, and playbook context all reshape to whoever is acting. <code>/intelligence/chat</code> accepts <code>staffer_id</code>; on match, defaults state filter to the staffer's territory, scopes playbook-pattern geo to their primary city/state, and surfaces <code>response.staffer.name</code> so the UI relabels MEMORY → <em>MARIA'S MEMORY</em>.</p>
<p><strong>Verified end-to-end:</strong> same query "forklift operators" returns 167 IL workers as Maria, 89 IN as Devon, 16 WI as Aisha (live numbers; refresh the profiler page to recompute). The corpus stays intact; the relevance gradient is per coordinator. As each accumulates fills, their slice of the playbook compounds independently. <strong>Roster:</strong> <code>/staffers</code> endpoint, declared in <code>STAFFERS</code> in <code>mcp-server/index.ts</code>. Adding a staffer is one append; the architecture is metro-agnostic by construction.</p>
<h3>Active profile (Phase 17)</h3> <h3>Active profile (Phase 17)</h3>
<p>Scopes every search. A <code>staffing-recruiter</code> profile bound to <code>workers_500k</code> sees only that dataset. A <code>security-analyst</code> profile bound to <code>threat_intel</code> cannot see worker data. <code>GET /vectors/profile/&lt;id&gt;/audit</code> records every tool invocation by model identity.</p> <p>Scopes every search. A <code>staffing-recruiter</code> profile bound to <code>workers_500k</code> sees only that dataset. A <code>security-analyst</code> profile bound to <code>threat_intel</code> cannot see worker data. <code>GET /vectors/profile/&lt;id&gt;/audit</code> records every tool invocation by model identity.</p>
@ -446,7 +495,7 @@ boost[(city, state, name)] = min(Σ per_worker, 0.25)</pre>
<div class="step"><div class="n">12:30</div><div class="body"><strong>Client pushes 20 new contracts + 1M ATS delta.</strong> Ch7 scale flow fires. Ingest in seconds; embedding refresh kicks off as a background job. Searches continue against old embeddings.</div></div> <div class="step"><div class="n">12:30</div><div class="body"><strong>Client pushes 20 new contracts + 1M ATS delta.</strong> Ch7 scale flow fires. Ingest in seconds; embedding refresh kicks off as a background job. Searches continue against old embeddings.</div></div>
<div class="step"><div class="n">14:00</div><div class="body"><strong>Emergency: worker Dave no-showed.</strong> Sarah clicks No-show button on Dave's card → <code>/log_failure</code> → <code>mark_failed</code> records a penalty. Next similar query dampens Dave's boost by 0.5. Sarah continues the refill — the refill excludes Dave and the 2 others already booked for this shift.</div></div> <div class="step"><div class="n">14:00</div><div class="body"><strong>Emergency: worker Dave no-showed.</strong> Sarah types "Dave running late site 4422" into the search box. ~250ms later: triage card with Dave's profile + reliability + responsiveness, draft SMS to client ("dispatching X from local bench, 96% reliability, will confirm arrival"), and 5 same-role same-geo backfills sorted by responsiveness rendered as a green list below. Sarah clicks Copy SMS, pastes to client, clicks Call on the top backfill. <code>/log_failure</code> on Dave records the penalty for the next similar query.</div></div>
<div class="step"><div class="n">15:00</div><div class="body"><strong>New embeddings live.</strong> Hot-swap promotion. Searches now see all 1M new profiles. Sarah's noon query re-run would produce different top-5.</div></div> <div class="step"><div class="n">15:00</div><div class="body"><strong>New embeddings live.</strong> Hot-swap promotion. Searches now see all 1M new profiles. Sarah's noon query re-run would produce different top-5.</div></div>
@ -468,14 +517,15 @@ boost[(city, state, name)] = min(Σ per_worker, 0.25)</pre>
<h4>Deferred — real architectural work, just not shipped yet</h4> <h4>Deferred — real architectural work, just not shipped yet</h4>
<ul> <ul>
<li><strong>BAI persistence + backtesting.</strong> Building Activity Index is computed live per page load. To validate the thesis (permit activity precedes equity moves) we need the daily series saved over months. Architectural support exists (<code>data/_kb/audit_baselines.jsonl</code> append pattern); just hasn't run long enough.</li>
<li><strong>NYC DOB adapter.</strong> Architecture is metro-agnostic — Chicago is Phase 1. NYC DOB ships next as a config-only Socrata adapter; LA County, Houston BCD, Boston ISD, DC DCRA queue behind it. Each new metro multiplies network edges without multiplying the codebase.</li>
<li><strong>12 awaiting public-data sources for contractor profile.</strong> DOL Wage &amp; Hour, EPA ECHO, MSHA, BBB, PACER civil suits, UCC liens, D&amp;B credit, State licensure, Surety bonds, DOT/FMCSA, State UI claims, DOL RAPIDS apprenticeships. Listed by name on every contractor profile with a one-line "would show:" sample. Each ships as a Socrata-style adapter; engineering scope is concrete.</li>
<li><strong>Rate / margin awareness.</strong> Worker pay expectations vs contract bill rate not modeled. Requires adding <code>pay_rate</code> to workers, <code>bill_rate</code> to contracts, and a filter + warning path. Partially addressed via <code>ContractTerms.budget_per_hour_max</code> passed to T3/rescue prompts, but the match-time filter isn't wired yet.</li> <li><strong>Rate / margin awareness.</strong> Worker pay expectations vs contract bill rate not modeled. Requires adding <code>pay_rate</code> to workers, <code>bill_rate</code> to contracts, and a filter + warning path. Partially addressed via <code>ContractTerms.budget_per_hour_max</code> passed to T3/rescue prompts, but the match-time filter isn't wired yet.</li>
<li><strong>Mem0-style UPDATE / DELETE / NOOP operations on playbooks.</strong> Today <code>/seed</code> only ADDs. Same <code>(operation, date)</code> pair appends a duplicate instead of refining an existing entry. Phase 26 item — cheap to add, moderate payoff.</li> <li><strong>Mem0-style UPDATE / DELETE / NOOP operations on playbooks.</strong> Today <code>/seed</code> only ADDs. Same <code>(operation, date)</code> pair appends a duplicate instead of refining an existing entry. Cheap to add, moderate payoff.</li>
<li><strong>Letta working-memory hot cache.</strong> Every boost query scans all active playbook entries from in-memory state. 1.9K today; cheap. Will bite somewhere north of 100K. LRU for the last-N playbooks or current-sig neighborhood deferred until that ceiling approaches.</li> <li><strong>Letta working-memory hot cache.</strong> Every boost query scans all active playbook entries from in-memory state. ~5K today; cheap. Will bite somewhere north of 100K. Deferred until the ceiling approaches.</li>
<li><strong>Chunking cache (Phase 21 Rust port).</strong> TS primitives <code>generateContinuable</code> + <code>generateTreeSplit</code> are wired, but <code>crates/aibridge/src/{continuation.rs, tree_split.rs}</code> + <code>crates/storaged/src/chunk_cache.rs</code> remain queued. Gateway-side callers currently don't have the same protection against silent truncation that the TS test harness does.</li>
<li><strong>Confidence calibration.</strong> Top-K is a rank, not a probability. No calibrated "85% likely to accept" score. Requires outcome-labeled training data.</li> <li><strong>Confidence calibration.</strong> Top-K is a rank, not a probability. No calibrated "85% likely to accept" score. Requires outcome-labeled training data.</li>
<li><strong>Neural re-ranker.</strong> Phase 19 is statistical + semantic (now with geo + role prefilter, Phase 25 retirement). A (query, candidate, outcome)-trained re-ranker is deferred only if the statistical floor plateaus below usable recall — current 14× citation lift on identical inputs suggests it hasn't.</li> <li><strong>SEC name-to-ticker fuzzy precision.</strong> Current matcher requires ≥2 non-stopword overlap; rare false positives still surface (saw FLG attach to a PNC-adjacent contractor once). Tightenable to require an explicit allow-list for production trading use.</li>
<li><strong>Observer → autotune feedback wire.</strong> Phase 24 streams scenario outcomes into <code>data/_observer/ops.jsonl</code>; autotune agent still runs on its own HNSW-trial schedule and hasn't subscribed to the outcome metric stream yet. Phase 26+ item — connects the last loop.</li> <li><strong>Tighter integration of pathway memory + scrum loop.</strong> ADR-021 substrate is shipped (88 traces, 11/11 replays). The hot-swap gate fires correctly; what's deferred is automatic mode-runner short-circuit when a high-confidence pathway match is available before any cloud call burns.</li>
<li><strong>call_log cross-reference.</strong> Infrastructure present; current synthetic candidates table is too small to cross-ref. Fixes when real ATS lands.</li>
</ul> </ul>
<h4>Non-goals — explicitly out of scope</h4> <h4>Non-goals — explicitly out of scope</h4>
@ -496,6 +546,6 @@ boost[(city, state, name)] = min(Σ per_worker, 0.25)</pre>
</div> </div>
</div> </div>
<div class="footer">Lakehouse spec · v2 2026-04-21 · Phases 19-25 shipped (playbook boost, model matrix, continuation, KB, staffer competence, observer ingest, validity windows) · maintained from <code>docs/DECISIONS.md</code> · <a href="proof">architecture live-tested</a> · <a href="console">walkthrough</a></div> <div class="footer">Lakehouse spec · v3 2026-04-27 · Phases 19-45 shipped (playbook boost, KB, staffer competence, observer ingest, validity windows, distillation v1.0.0 substrate frozen at e7636f2, gateway as OpenAI-compat drop-in, mode runner, validator + iterate, pathway memory ADR-021, per-staffer hot-swap, Construction Activity Signal Engine) · maintained from <code>docs/DECISIONS.md</code> · <a href="proof">architecture live-tested</a> · <a href="console">walkthrough</a> · <a href="profiler">profiler</a></div>
</body></html> </body></html>

178
mcp-server/tif_polygons.ts Normal file
View File

@ -0,0 +1,178 @@
// TIF (Tax Increment Financing) district point-in-polygon lookup.
// Given a property's lat/long, returns which Chicago TIF district (if
// any) contains it. TIF districts are public-subsidy zones — a property
// inside one is receiving city tax-increment funding for its build.
// Strong "this project has financial backing" signal for the Project Index.
//
// Data: data/_entity_cache/tif_districts.geojson (Chicago Open Data
// dataset eejr-xtfb, 100 active districts, 3.2MB). Refresh by re-running
// `curl ... eejr-xtfb.geojson > tif_districts.geojson` — districts
// change rarely (only when city council approves new ones or repeals).
//
// Algorithm: classic ray-casting. For each MultiPolygon's outer ring,
// count edge crossings of an east-going horizontal ray from the point.
// Odd crossings = inside. Holes (inner rings) flip the parity. Library-
// free; correct for arbitrary polygons including the irregular Chicago
// shapes which often have many small detours.
import { readFile } from "node:fs/promises";
import { existsSync } from "node:fs";
import { join } from "node:path";
const TIF_GEOJSON = join("/home/profit/lakehouse/data/_entity_cache", "tif_districts.geojson");
type LngLat = [number, number]; // GeoJSON convention: [longitude, latitude]
type Ring = LngLat[];
type Polygon = Ring[]; // outer ring + optional inner rings (holes)
type MultiPolygon = Polygon[];
type TifFeature = {
name: string;
trim_name?: string;
ref?: string;
approval_date?: string;
expiration?: string;
type?: string; // T-1xx etc.
comm_area?: string;
wards?: string;
// Bounding box for quick reject
bbox: { minLon: number; minLat: number; maxLon: number; maxLat: number };
geometry: MultiPolygon;
};
let tifIdx: TifFeature[] | null = null;
function bboxOfMultiPolygon(mp: MultiPolygon): TifFeature["bbox"] {
let minLon = Infinity, minLat = Infinity, maxLon = -Infinity, maxLat = -Infinity;
for (const poly of mp) {
for (const ring of poly) {
for (const [lon, lat] of ring) {
if (lon < minLon) minLon = lon;
if (lat < minLat) minLat = lat;
if (lon > maxLon) maxLon = lon;
if (lat > maxLat) maxLat = lat;
}
}
}
return { minLon, minLat, maxLon, maxLat };
}
async function ensureLoaded(): Promise<TifFeature[]> {
if (tifIdx) return tifIdx;
if (!existsSync(TIF_GEOJSON)) {
tifIdx = [];
return tifIdx;
}
try {
const raw = JSON.parse(await readFile(TIF_GEOJSON, "utf-8"));
const out: TifFeature[] = [];
for (const f of raw.features || []) {
const geom = f.geometry;
if (!geom) continue;
// Normalize Polygon → MultiPolygon for uniform iteration
let mp: MultiPolygon;
if (geom.type === "MultiPolygon") {
mp = geom.coordinates;
} else if (geom.type === "Polygon") {
mp = [geom.coordinates];
} else {
continue;
}
const props = f.properties || {};
out.push({
name: props.name || "Unknown TIF",
trim_name: props.name_trim,
ref: props.ref,
approval_date: props.approval_d,
expiration: props.expiration,
type: props.type,
comm_area: props.comm_area,
wards: props.wards,
bbox: bboxOfMultiPolygon(mp),
geometry: mp,
});
}
tifIdx = out;
return tifIdx;
} catch (e) {
console.warn("[tif] load failed:", (e as Error).message);
tifIdx = [];
return tifIdx;
}
}
// Ray-casting point-in-polygon (single ring). Returns true if (lon, lat)
// is strictly inside the ring. Edge cases (point exactly on a vertex)
// resolve by half-open interval convention; for our use case (Chicago
// boundary precision is ~1m, sites are point queries) this is fine.
function pointInRing(lon: number, lat: number, ring: Ring): boolean {
let inside = false;
const n = ring.length;
for (let i = 0, j = n - 1; i < n; j = i++) {
const [xi, yi] = ring[i];
const [xj, yj] = ring[j];
const intersect =
yi > lat !== yj > lat &&
lon < ((xj - xi) * (lat - yi)) / (yj - yi + 0) + xi;
if (intersect) inside = !inside;
}
return inside;
}
// Polygon = outer ring + holes. Inside outer AND not inside any hole.
function pointInPolygon(lon: number, lat: number, polygon: Polygon): boolean {
if (polygon.length === 0) return false;
if (!pointInRing(lon, lat, polygon[0])) return false;
for (let i = 1; i < polygon.length; i++) {
if (pointInRing(lon, lat, polygon[i])) return false;
}
return true;
}
export type TifMatch = {
name: string;
ref?: string;
approval_date?: string;
expiration?: string;
comm_area?: string;
wards?: string;
};
export async function findTifDistrict(
longitude: number | string | undefined,
latitude: number | string | undefined,
): Promise<TifMatch | null> {
const lon = typeof longitude === "string" ? parseFloat(longitude) : longitude;
const lat = typeof latitude === "string" ? parseFloat(latitude) : latitude;
if (!lon || !lat || isNaN(lon) || isNaN(lat)) return null;
const idx = await ensureLoaded();
if (idx.length === 0) return null;
for (const f of idx) {
// Bbox reject — cheap O(1) skip for the 99% of districts that
// can't possibly contain the point.
const b = f.bbox;
if (lon < b.minLon || lon > b.maxLon || lat < b.minLat || lat > b.maxLat) continue;
// Full point-in-polygon for any polygon in this MultiPolygon
for (const poly of f.geometry) {
if (pointInPolygon(lon, lat, poly)) {
return {
name: f.name,
ref: f.ref,
approval_date: f.approval_date,
expiration: f.expiration,
comm_area: f.comm_area,
wards: f.wards,
};
}
}
}
return null;
}
export async function getTifIndexStats(): Promise<{
total: number;
loaded: boolean;
}> {
const idx = await ensureLoaded();
return { total: idx.length, loaded: idx.length > 0 };
}

28
ops/systemd/lakehouse-langfuse-bridge.service Normal file
View File

@ -0,0 +1,28 @@
[Unit]
Description=Lakehouse Langfuse → observer bridge — forwards LLM trace metadata to :3800 so KB learns from cost/latency/provider deltas
Documentation=file:///home/profit/lakehouse/mcp-server/langfuse_bridge.ts
After=network.target
# No hard dependency on either Langfuse or observer — if either is down,
# the bridge retries on the next tick without crashing. That's the
# whole point of the cursor state file.
[Service]
Type=simple
WorkingDirectory=/home/profit/lakehouse
ExecStart=/home/profit/.bun/bin/bun run /home/profit/lakehouse/mcp-server/langfuse_bridge.ts
Restart=on-failure
RestartSec=30
# Credentials resolved from env. Matches how
# crates/gateway/src/v1/langfuse_trace.rs reads them so both producer
# (gateway emitter) and consumer (this bridge) share the same config.
EnvironmentFile=-/etc/lakehouse/langfuse.env
Environment=LANGFUSE_URL=http://localhost:3001
Environment=OBSERVER_URL=http://localhost:3800
Environment=LANGFUSE_POLL_MS=30000
Environment=LANGFUSE_BATCH_LIMIT=50
Environment=LANGFUSE_STATE_FILE=/var/lib/lakehouse-guard/langfuse_last_seen.json
KillSignal=SIGTERM
TimeoutStopSec=5
[Install]
WantedBy=multi-user.target

5
package.json Normal file
View File

@ -0,0 +1,5 @@
{
"dependencies": {
"langfuse": "^3.38.20"
}
}

8
reports/distillation/phase6-acceptance-report.md
View File

@ -1,6 +1,6 @@
# Phase 6 — Acceptance Gate Report # Phase 6 — Acceptance Gate Report
**Run:** 2026-04-27T04:54:32.225Z **Run:** 2026-04-27T15:43:37.943Z
**Fixture:** `tests/fixtures/distillation/acceptance/` **Fixture:** `tests/fixtures/distillation/acceptance/`
**Temp root:** `/tmp/distillation_phase6_acceptance` **Temp root:** `/tmp/distillation_phase6_acceptance`
**Pipeline run_ids:** `acceptance-run-1-stable` (first) + `acceptance-run-2-stable` (second / hash reproducibility) **Pipeline run_ids:** `acceptance-run-1-stable` (first) + `acceptance-run-2-stable` (second / hash reproducibility)
@ -40,13 +40,13 @@
| 19 | scratchpad/tree-split case: fixture row materialized into evidence | found | found | ✓ | | 19 | scratchpad/tree-split case: fixture row materialized into evidence | found | found | ✓ |
| 20 | PRD drift case: fixture row materialized | found | found | ✓ | | 20 | PRD drift case: fixture row materialized | found | found | ✓ |
| 21 | hash reproducibility: per-stage output_hash identical across runs | 0 mismatches | all match | ✓ | | 21 | hash reproducibility: per-stage output_hash identical across runs | 0 mismatches | all match | ✓ |
| 22 | hash reproducibility: run_hash identical | 3ea12b160ee9099a... | 3ea12b160ee9099a... | ✓ | | 22 | hash reproducibility: run_hash identical | 8dfdacee62380ec2... | 8dfdacee62380ec2... | ✓ |
## Hash reproducibility detail ## Hash reproducibility detail
run 1 run_hash: `3ea12b160ee9099a3c52fe6e7fffd3076de7920d2704d24c789260d63cb1a5a2` run 1 run_hash: `8dfdacee62380ec20b7420d8f8bad3c395822da6eb0b41eeecd356e88fe20bf0`
run 2 run_hash: `3ea12b160ee9099a3c52fe6e7fffd3076de7920d2704d24c789260d63cb1a5a2` run 2 run_hash: `8dfdacee62380ec20b7420d8f8bad3c395822da6eb0b41eeecd356e88fe20bf0`
**Bit-for-bit identical.** Two runs of the entire pipeline on the same fixture with the same `recorded_at` produce the same outputs. Distillation is deterministic. **Bit-for-bit identical.** Two runs of the entire pipeline on the same fixture with the same `recorded_at` produce the same outputs. Distillation is deterministic.

16
reports/distillation/phase8-full-audit-report.md
View File

@ -1,8 +1,8 @@
# Phase 8 — Full System Audit Report # Phase 8 — Full System Audit Report
**Run:** 2026-04-27T04:54:32.283Z **Run:** 2026-04-27T15:43:38.021Z
**Git commit:** 73f242e3e41c2aa36b35fe9de54742b248915cb5 **Git commit:** ca7375ea2b178159a0c61bbf62788a2ffa2390e9
**Baseline:** 2026-04-27T04:53:45.796Z (5bdd159966e6) **Baseline:** 2026-04-27T10:31:44.043Z (d11632a6fae6)
## Result: **PASS** ✓ ## Result: **PASS** ✓
@ -26,7 +26,7 @@
| 1 | P0 | recon doc exists | Y | docs/recon/local-distillation-recon.md present | present | ✓ | | 1 | P0 | recon doc exists | Y | docs/recon/local-distillation-recon.md present | present | ✓ |
| 2 | P0 | tier-1 source streams present | — | all 4 tier-1 jsonls on disk | all present | ✓ | | 2 | P0 | tier-1 source streams present | — | all 4 tier-1 jsonls on disk | all present | ✓ |
| 3 | P1 | schema validators pass on fixtures | Y | ≥40 tests, 0 fail | 51 pass, 0 fail | ✓ | | 3 | P1 | schema validators pass on fixtures | Y | ≥40 tests, 0 fail | 51 pass, 0 fail | ✓ |
| 4 | P2 | materializer dry-run completes | Y | >=1 row from each tier-1 source | 1073 read · 16 written · 2 skipped | ✓ | | 4 | P2 | materializer dry-run completes | Y | >=1 row from each tier-1 source | 1139 read · 82 written · 2 skipped | ✓ |
| 5 | P2 | tier-1 sources each materialize ≥1 row | — | 4/4: distilled_facts, scrum_reviews, audit_facts, mode_experiments | 1/4 hit (mode_experiments) | ✓ | | 5 | P2 | tier-1 sources each materialize ≥1 row | — | 4/4: distilled_facts, scrum_reviews, audit_facts, mode_experiments | 1/4 hit (mode_experiments) | ✓ |
| 6 | P3 | on-disk scored-runs distribution non-empty | Y | >=1 accepted | acc=386 part=132 rej=57 hum=480 | ✓ | | 6 | P3 | on-disk scored-runs distribution non-empty | Y | >=1 accepted | acc=386 part=132 rej=57 hum=480 | ✓ |
| 7 | P3 | scored-runs distribution sums positive | — | >0 total | 1055 total | ✓ | | 7 | P3 | scored-runs distribution sums positive | — | >0 total | 1055 total | ✓ |
@ -38,19 +38,19 @@
| 13 | P5 | latest run (3fa51d66-784c-4c7d-843d-6c48328a608c) has all 5 stage receipts | Y | collect,score,export-rag,export-sft,export-preference | all present | ✓ | | 13 | P5 | latest run (3fa51d66-784c-4c7d-843d-6c48328a608c) has all 5 stage receipts | Y | collect,score,export-rag,export-sft,export-preference | all present | ✓ |
| 14 | P5 | every stage receipt validates against schema | Y | 0 invalid | 0 invalid | ✓ | | 14 | P5 | every stage receipt validates against schema | Y | 0 invalid | 0 invalid | ✓ |
| 15 | P5 | RunSummary validates | Y | valid | valid | ✓ | | 15 | P5 | RunSummary validates | Y | valid | valid | ✓ |
| 16 | P5 | summary.git_commit is 40-char hex | — | match | 68b6697bcb38... (HEAD: 73f242e3e41c...) | ✓ | | 16 | P5 | summary.git_commit is 40-char hex | — | match | 68b6697bcb38... (HEAD: ca7375ea2b17...) | ✓ |
| 17 | P5 | run_hash is sha256 | Y | /^[0-9a-f]{64}$/ | 2336b96c3638982d... | ✓ | | 17 | P5 | run_hash is sha256 | Y | /^[0-9a-f]{64}$/ | 2336b96c3638982d... | ✓ |
| 18 | P6 | acceptance gate passes 22/22 invariants on fixture | Y | PASS — 22/22 | 22/22 (exit=0) | ✓ | | 18 | P6 | acceptance gate passes 22/22 invariants on fixture | Y | PASS — 22/22 | 22/22 (exit=0) | ✓ |
| 19 | P7 | replay validation passes on 3/3 dry-run sample tasks | Y | 3/3 | 3/3 | ✓ | | 19 | P7 | replay validation passes on 3/3 dry-run sample tasks | Y | 3/3 | 3/3 | ✓ |
| 20 | P7 | replay retrieval surfaces ≥1 playbook on each task (when corpus present) | — | ≥1 task with retrieval | 3/3 | ✓ | | 20 | P7 | replay retrieval surfaces ≥1 playbook on each task (when corpus present) | — | ≥1 task with retrieval | 3/3 | ✓ |
| 21 | P7 | escalation loop guard: no path > 2 models | Y | 0 loops | 0 | ✓ | | 21 | P7 | escalation loop guard: no path > 2 models | Y | 0 loops | 0 | ✓ |
| 22 | P7 | replay_runs.jsonl populated by audit run | — | exists with ≥3 rows added | 21 rows total | ✓ | | 22 | P7 | replay_runs.jsonl populated by audit run | — | exists with ≥3 rows added | 27 rows total | ✓ |
## Drift vs prior baseline ## Drift vs prior baseline
| Metric | Baseline | Current | Δ% | Flag | | Metric | Baseline | Current | Δ% | Flag |
|---|---|---|---|---| |---|---|---|---|---|
| p2_evidence_rows | 15 | 16 | 7% | ok | | p2_evidence_rows | 25 | 82 | 228% | warn |
| p2_evidence_skips | 2 | 2 | 0% | ok | | p2_evidence_skips | 2 | 2 | 0% | ok |
| p3_accepted | 386 | 386 | 0% | ok | | p3_accepted | 386 | 386 | 0% | ok |
| p3_partial | 132 | 132 | 0% | ok | | p3_partial | 132 | 132 | 0% | ok |
@ -61,7 +61,7 @@
| p4_pref_pairs | 83 | 83 | 0% | ok | | p4_pref_pairs | 83 | 83 | 0% | ok |
| p4_total_quarantined | 1325 | 1325 | 0% | ok | | p4_total_quarantined | 1325 | 1325 | 0% | ok |
All metrics within 20% of baseline — pipeline stable across runs. **1 metric(s) drifted >20% from baseline.** Investigate before treating outputs as stable.
## System health status ## System health status

45
reports/kimi/audit-last-week-full.md Normal file
View File

@ -0,0 +1,45 @@
# Kimi Forensic Audit (FULL FILES) — distillation v1.0.0
**Generated:** 2026-04-27 by `kimi-for-coding` via gateway /v1/chat
**Latency:** 270.6s | **finish:** stop | **usage:** {'prompt_tokens': 66338, 'completion_tokens': 10159, 'total_tokens': 76497}
**Input:** /tmp/kimi-audit-full.md (238KB · 12 commits · 15 files · line-numbered, no truncation)
---
## Verdict
**Hold**: the substrate’s TypeScript pipeline is architecturally coherent and the SFT firewall is genuine, but committed Rust tests fail to compile, drift detection hardcodes an unverified integrity assertion, and deterministic guarantees leak wall-clock time in multiple places.
## What's solid
- **Three-layer SFT contamination firewall is real.** Schema enum restricts `quality_score` to `["accepted", "partially_accepted"]` (`sft_sample.ts:13,62`), exporter constant `SFT_NEVER` blocks rejected/needs_human_review before synthesis (`export_sft.ts:51,205`), and `receipts.ts` re-reads the output to fail loud if any forbidden score leaked (`receipts.ts:231-236`).
- **Core scorer is pure and deterministic.** `scoreRecord` takes an `EvidenceRecord`, performs no I/O, no LLM calls, and uses no mutable state (`scorer.ts:1-5,257-273`).
- **Quarantine is exhaustive and observable.** Every exporter routes skips to structured `exports/quarantine/<exporter>.jsonl` with typed reasons; silent drops are impossible by construction (`quarantine.ts:1-6,14-26`).
- **Evidence provenance is mandatory on every row.** Every `EvidenceRecord` carries `source_file`, `line_offset`, `sig_hash`, and `recorded_at` (`build_evidence_index.ts:27-34`).
- **Local-first replay reduces cloud calls.** `replay.ts` defaults to a local model, augments via RAG retrieval, and only escalates on validation failure, directly supporting the cloud-call reduction claim (`replay.ts:24,349-376`).
## What's risky
1. **receipts.ts:495** hardcodes `input_hash_match: true` in drift reports while comments on lines 467-469 admit input-hash comparison is unimplemented; this is false telemetry in a forensic system.
2. **score_runs.ts:159** deduplicates scored runs by `scored.provenance.sig_hash` (the *evidence* hash), not by a composite of evidence + scorer version, so scorer logic or `SCORER_VERSION` updates are silently ignored on re-runs against existing partition files.
3. **transforms.ts:181** `auto_apply` transform falls back to `new Date().toISOString()` when `row.ts` is missing, injecting wall-clock time into the supposedly deterministic materialization layer.
4. **mode.rs:1035,1042** Rust test code assigns `Some("...".into())` and `None` to a `Vec<String>` field (`matrix_corpus`), which would fail `cargo test` compilation; this contradicts the claim that the tag is fully tested.
5. **export_sft.ts:109-133** synthesizes fake instruction templates per source stem instead of using actual historical prompts; the SFT firewall prevents category contamination but not prompt-fidelity distortion.
## Specific findings
- **mode.rs:1035** — Compile error in test helper: `matrix_corpus: Some("distilled_procedural_v1".into())` mismatches the `Vec<String>` type declared at line 172. **Rationale:** Direct struct construction in the test module uses an `Option` where a `Vec` is required, so the Rust test suite cannot compile.
- **receipts.ts:495** — Drift detection hardcodes `input_hash_match: true`. **Rationale:** The adjacent comment admits input-hash comparison is simplified and unimplemented (lines 467-469); asserting a verified match is misleading telemetry that will hide real input-side regressions.
- **score_runs.ts:159** — Scored-run dedup ignores scorer version. **Rationale:** `loadSeenHashes` and the skip logic key only on the EvidenceRecord `sig_hash`, meaning an existing scored-run file from yesterday will block updated scores even if `SCORER_VERSION` or scorer logic changed today.
- **transforms.ts:181** — Non-deterministic timestamp fallback in `auto_apply` transform. **Rationale:** `row.ts ?? new Date().toISOString()` injects wall-clock time when the source row lacks a timestamp, violating the header claim that transforms are “deterministic by construction” and breaking bit-identical reproducibility for that stream.
- **export_sft.ts:126** — Unsafe property access via `as any`. **Rationale:** `(ev as any).contractor` bypasses the `EvidenceRecord` type contract; if the property is absent the template silently emits `"<contractor>"`, degrading SFT data quality without a type error.
- **scorer.ts:30** — Environmental dependency in deterministic scorer. **Rationale:** `process.env.LH_SCORER_VERSION` means identical evidence inputs produce different `scorer_version` stamps (and different downstream receipts) depending on the runtime environment, undermining bit-identical claims.
- **replay.ts:378** — Non-deterministic run identifier. **Rationale:** `` `replay:${task_hash.slice(0, 16)}:${Date.now()}` `` makes replay evidence rows non-reproducible and risks collision under rapid successive calls.
- **export_sft.ts:109-133** — Synthetic instruction generation replaces ground-truth prompts. **Rationale:** The exporter fabricates instruction strings from metadata (e.g., hardcoded scrum review phrasing) rather than retrieving the actual historical prompt, so the resulting SFT dataset trains on reconstructed, not authentic, user instructions.
## Direction recommendation
**Pause the staffing audit and harden the substrate first.** Before building the staffing inference mode (`staffing_inference_lakehouse` in `mode.rs:54`) on top of this substrate:
1. Fix the Rust test compile errors (`mode.rs:1035,1042`) and ensure `cargo test` runs in CI.
2. Replace the hardcoded `input_hash_match: true` in drift detection (`receipts.ts:495`) with a real hash comparison or remove the field until it is implemented.
3. Change scored-run dedup (`score_runs.ts:159`) to key on a composite hash of `evidence_sig_hash + scorer_version + SCORER_VERSION` so scorer updates force re-scoring.
4. Remove the `new Date().toISOString()` fallback in `transforms.ts:181` or fail the row so determinism is preserved.
5. Audit all `as any` casts in the export layer (`export_sft.ts:126`) for type-safe alternatives.
Once those fixes land and acceptance re-runs pass, proceed to the staffing audit wave; the architecture is sound enough to support it, but the forensic guarantees must be honest before downstream teams depend on them.

36
reports/kimi/audit-last-week.md Normal file
View File

@ -0,0 +1,36 @@
# Kimi Forensic Audit — distillation v1.0.0 (last week)
**Generated:** 2026-04-27 by `kimi-for-coding` via gateway /v1/chat
**Latency:** 157.6s | **finish:** stop | **usage:** {'prompt_tokens': 14014, 'completion_tokens': 6356, 'total_tokens': 20370}
**Input:** /tmp/kimi-audit-input.md (56k chars · 12 commits · 6 files)
---
## Verdict
**hold** — Runtime lock-in, integration mismatches, and truncated source files in the v1.0.0 payload make the tag unshippable without rework.
## What's solid
- `scorer.ts` is a pure, deterministic function with no I/O, no LLM calls, and an explicit version stamp (`scorer.ts:22`).
- SFT export enforces defense-in-depth contamination firewalls via `SFT_NEVER` and schema validators (`export_sft.ts:49-50`; `sft_sample.ts:43-48`).
- Evidence materialization is idempotent across reruns using `sig_hash` deduplication (`build_evidence_index.ts:114-126`).
- Mode router falls back to a safe built-in default if config parsing fails (`mode.rs:208-228`).
- Quarantine writer abstraction isolates bad records instead of failing the export (`export_sft.ts`).
## What's risky
- **Integration mismatch**: `replay.ts` posts to `/v1/chat`, but the provided gateway only declares `/v1/mode` and `/v1/mode/execute` (`replay.ts:186` vs `mode.rs:13-18`), suggesting an undocumented or broken proxy contract.
- **Bun runtime lock-in**: Multiple files depend on `Bun.CryptoHasher`, which throws in Node.js (`export_sft.ts:235`; `build_evidence_index.ts:89`).
- **Unauditable files in scope**: Critical files listed in the diff—`transforms.ts`, `receipts.ts`, `quarantine.ts`, `score_runs.ts`—were not provided, so their logic is unseen.
- **Every shown implementation file is truncated**: `scorer.ts`, `export_sft.ts`, `build_evidence_index.ts`, `replay.ts`, and `mode.rs` all end mid-block, hiding error handling, receipt finalization, and gateway dispatch code.
- **Type safety escape**: `(ev as any).contractor` in SFT synthesis bypasses the schema layer (`export_sft.ts:138`).
## Specific findings
1. `scripts/distillation/scorer.ts:22` — `SCORER_VERSION` reads from `process.env`, introducing environment-dependent output drift that contradicts the file’s “identical input → identical output forever” contract.
2. `scripts/distillation/export_sft.ts:138` — `(ev as any).contractor` is an unguarded `any` cast; a malformed `EvidenceRecord` will inject the string `"undefined"` or crash at runtime inside the SFT instruction template.
3. `scripts/distillation/export_sft.ts:235` — `new Bun.CryptoHasher("sha256")` is a Bun-only API; this path will fail under Node.js/Deno and makes the substrate non-portable.
4. `scripts/distillation/build_evidence_index.ts:89` — Same Bun crypto lock-in in `sha256OfFile`, fragmenting the hashing implementation (here `Bun.CryptoHasher`, elsewhere `canonicalSha256`).
5. `scripts/distillation/replay.ts:178` — Provider routing relies on fragile string heuristics (`model.includes("/")`, prefix lists); models with unexpected names will route to the wrong backend or hit the `ollama` default incorrectly.
6. `scripts/distillation/replay.ts:186` — `fetch(`${gatewayUrl()}/v1/chat`` targets an endpoint absent from the provided `mode.rs` router; without the missing gateway dispatch code, this call will 404.
7. `crates/gateway/src/v1/mode.rs:141` — `deserialize_string_or_vec` uses `serde_json::Value::deserialize` against a TOML source, which is non-idiomatic and risks mis-handling TOML-specific types (datetime, inline tables) compared to a native `toml::Value`.
8. `scripts/distillation/build_evidence_index.ts:185` — `await canonicalSha256(row)` is async, yet `sha256OfFile` is sync; the mixing of sync/async crypto calls in the same module hints at inconsistent I/O boundaries.
## Direction recommendation
Keep the substrate architecture, but **do not expand staffing audit work on top of v1.0.0 until three blockers are fixed**: (1) replace `Bun.CryptoHasher` with portable WebCrypto or Node `crypto` so the build is runtime-agnostic; (2) align `replay.ts` to the actual gateway contract (`/v1/mode/execute`) or document the `/v1/chat` proxy route; and (3) eliminate `any` casts in the export path. The schema firewalls, deterministic scorer, and receipt provenance are the right foundation—rework the runtime/contract gaps rather than rebuilding from scratch.

116
reports/lance_10m_rebench_2026-05-02.md Normal file
View File

@ -0,0 +1,116 @@
# Lance backend re-benchmark — 10M vectors (scale_test_10m)
**Date:** 2026-05-02
**Dataset:** `data/lance/scale_test_10m` (33 GB, ~10M vectors, 768d)
**Driver:** live HTTP gateway `:3100/vectors/lance/*` (post sanitizer-fix binary)
**Method tag on every search response:** `lance_ivf_pq` (confirms IVF_PQ, not brute-force)
ADR-019 deferred a 10M re-bench: *"at 10M we expect Lance to pull ahead because HNSW doesn't fit in RAM. Re-benchmark when we have a 10M-vector corpus to test against."* The corpus exists; this is that benchmark.
## Search latency, 10 diverse queries, top_k=10 (cold)
| Query | Latency |
|---|---:|
| warehouse forklift operator second shift | 50.5ms |
| senior software engineer kubernetes | 52.9ms |
| registered nurse pediatric | 37.6ms |
| welder TIG aluminum | **127.7ms** |
| data scientist python | 41.6ms |
| electrician journeyman commercial | 31.4ms |
| accountant CPA tax | 28.6ms |
| machine learning research | 32.1ms |
| construction site supervisor | 31.8ms |
| biomedical engineer | 25.0ms |
Median ~32ms, mean ~46ms, one ~128ms outlier (TIG aluminum query — not investigated; could be query-specific IVF traversal pattern or transient I/O).
## Search latency, repeated query (warm cache)
Same query (`forklift operator`) hit 5 times in a row:
| Call | Latency |
|---|---:|
| 1 | 21.9ms |
| 2 | 20.2ms |
| 3 | 19.2ms |
| 4 | 22.4ms |
| 5 | 18.6ms |
**Warm-cache p50 ~20ms.** Stable across the 5 trials.
## Doc-fetch by id, 5 calls (post-warmup) — BEFORE scalar-index fix
Fetched the same doc_id (`VEC-2196862`) repeatedly:
| Call | Latency |
|---|---:|
| 1 | 68.2ms |
| 2 | 89.3ms |
| 3 | 153.9ms |
| 4 | 126.5ms |
| 5 | 140.7ms |
**~100ms p50, climbing under repeat.** Substantially slower than the 100K-corpus number from ADR-019 (311μs claimed; ~6ms measured today on workers_500k_v1).
### Root cause (investigated post-bench)
`/vectors/lance/stats/scale_test_10m` returned `has_doc_id_index: false`. The scalar btree on `doc_id` was **never built** for this dataset. Doc-fetch was running a full table scan over 35GB.
Cause: the auto-build code in `crates/vectord/src/service.rs:1492-1503` only fires for `IndexMeta`-registered indexes during `set_active_profile` warming. `scale_test_10m` was created by the `lance-bench` binary directly via the migrate HTTP route — it bypasses the IndexMeta registry, so warming never sees it, so neither the vector index nor the scalar index gets auto-built. (The vector index was built manually via `/vectors/lance/index/scale_test_10m`; the scalar index never was.)
### Doc-fetch by id, 5 calls — AFTER `POST /vectors/lance/scalar-index/scale_test_10m/doc_id`
Build took **1.22s** for 10M rows, added 269MB of btree on disk.
| Call | Latency |
|---|---:|
| 1 | 5.6ms |
| 2 | 5.0ms |
| 3 | 5.0ms |
| 4 | 4.9ms |
| 5 | 4.7ms |
**~5ms p50, stable.** ~20x improvement. Matches workers_500k_v1's ~6ms baseline.
ADR-019's "O(1) random access via btree" claim is structurally vindicated. The 311μs projection from the 100K bench was an in-process Rust call; the live HTTP/JSON round-trip floor is ~5ms regardless of dataset size.
### Followup: close the IndexMeta-bypass gap
The `lance-bench` binary writes datasets that the rest of the gateway can't see. Two reasonable fixes:
1. **Auto-build scalar index inside `lance_migrate` HTTP handler** — every dataset created via the migrate route gets the btree before returning. Costs 1-2 seconds at ingest time, saves 100ms per doc-fetch forever after.
2. **Have `lance-bench` register an IndexMeta entry** at the end of its run, so the existing warming code picks it up on next gateway start.
Recommendation: do (1). It's a one-line addition next to the existing `build_index` call inside the handler, and it makes the migrate route self-sufficient — no caller needs to remember a follow-up build call.
## Compared to ADR-019 100K projections
| Op | 100K (ADR-019) | 10M (today) | Notes |
|---|---:|---:|---|
| Search (cold) | 2229μs | ~46ms | 21x slower at 100x scale → reasonable for IVF_PQ |
| Search (warm) | (not measured) | ~20ms | Warm cache converges nicely |
| Doc fetch (no btree) | — | ~100ms | full scan, 35GB |
| Doc fetch (post btree build) | 311μs | ~5ms | structural win confirmed; HTTP/JSON floor explains delta |
| Index method | lance_ivf_pq | lance_ivf_pq | confirmed via response tag |
## What this means
ADR-019's claim that "at 10M, Lance pulls ahead because HNSW doesn't fit in RAM" remains **unverified-but-not-refuted**. We can't directly compare to HNSW at 10M because HNSW's RAM footprint at 10M × 768d × 4 bytes = ~30 GB just for vectors, double that for the graph — way past any single-node deployment. So Lance "wins" at 10M by being the only contender that operationally exists.
What the bench DID surface:
- **Search at 10M works at production-shape latency** (~20ms warm). Acceptable for batch / async / non-conversational workloads. Too slow for sub-10ms voice or recommendation paths.
- **Doc-fetch at 10M is fast (~5ms) once the scalar btree is built.** Pre-build was ~100ms (full scan). Built in 1.2s, +269MB on disk. ADR-019's structural claim holds.
- **The auto-build only fires for IndexMeta-registered datasets.** `lance-bench` bypasses IndexMeta, so its datasets need either a manual `POST /vectors/lance/scalar-index/<name>/doc_id` after migration, or a one-line fix to the `lance_migrate` handler that builds the btree inline. Recommend the inline fix.
- **Sanitizer fix held under load** — no 500-with-leak surfaced even on rare query pattern (TIG aluminum). The fix is robust to long-tail queries.
## Repro
```bash
# Search latency, single query
curl -sS -X POST http://127.0.0.1:3100/vectors/lance/search/scale_test_10m \
-H 'Content-Type: application/json' \
-d '{"query":"forklift operator","top_k":10}' | jq '.latency_us'
# Doc fetch by id
curl -sS http://127.0.0.1:3100/vectors/lance/doc/scale_test_10m/VEC-2196862 \
| jq '.latency_us'
```

536
scripts/e2e_pipeline_check.sh Executable file
View File

@ -0,0 +1,536 @@
#!/usr/bin/env bash
# ------------------------------------------------------------
# End-to-end pipeline verification for Lakehouse.
#
# Generates realistic staffing-style data, runs it through every
# shipped pipeline stage, asserts correctness at each step, and
# cleans up after itself.
#
# Stages exercised:
# 0. Preflight — gateway + sidecar reachability
# 1. Data generation — 1000 candidates, 200 placements, 10 resumes
# 2. CSV ingest — Phase 6.1 (via ?name= query param)
# 3. NDJSON ingest — Phase 6.2
# 4. SQL queries + joins — Phase 2, Phase 8 hot cache
# 5. Content-hash re-ingest dedup — Phase 6.4
# 6. Idempotent register — ADR-020 (same-fingerprint path)
# 7. Schema-drift rejection — ADR-020 (409 Conflict path)
# 8. Catalog dedupe no-op — ADR-020 (clean state)
# 9. Metadata enrichment — Phase 10 POST
# 10. PII auto-detection audit — Phase 10
# 11. Vector index + search — Phase 7 (documents pulled via SQL)
# 12. Cleanup + baseline verify — no-orphan guarantee
#
# Usage:
# ./scripts/e2e_pipeline_check.sh # run all stages
# SKIP_VECTOR=1 ./scripts/e2e_pipeline_check.sh # skip Ollama-bound steps
# KEEP_DATA=1 ./scripts/e2e_pipeline_check.sh # leave /tmp artifacts
#
# Exit codes:
# 0 all assertions passed
# 1 one or more assertions failed
# 2 preflight failed (service unreachable)
# ------------------------------------------------------------
set -u
set -o pipefail
GATEWAY="${GATEWAY:-http://localhost:3100}"
SIDECAR="${SIDECAR:-http://localhost:3200}"
WORKDIR="${WORKDIR:-/tmp/lakehouse_e2e}"
DATA_ROOT="${DATA_ROOT:-/home/profit/lakehouse/data}"
SKIP_VECTOR="${SKIP_VECTOR:-0}"
KEEP_DATA="${KEEP_DATA:-0}"
RUN_ID="e2e_$(date +%s)"
CAND_DS="${RUN_ID}_candidates"
PLACE_DS="${RUN_ID}_placements"
RESUME_DS="${RUN_ID}_resumes"
VEC_IDX="${RESUME_DS}_v1"
# Color names use a CC_ prefix so they can't be shadowed by single-letter
# local variables like `R` that hold curl responses elsewhere in the script.
if [[ -t 1 ]]; then
CC_GRN=$'\033[0;32m'; CC_RED=$'\033[0;31m'; CC_YLW=$'\033[1;33m'
CC_BLU=$'\033[1;34m'; CC_DIM=$'\033[2m'; CC_RST=$'\033[0m'
else
CC_GRN=''; CC_RED=''; CC_YLW=''; CC_BLU=''; CC_DIM=''; CC_RST=''
fi
PASS=0; FAIL=0; WARN=0; STARTED_AT=$(date +%s)
FAILURES=()
pass() { printf ' %s✓%s %s\n' "$CC_GRN" "$CC_RST" "$1"; PASS=$((PASS+1)); }
fail() { printf ' %s✗%s %s\n' "$CC_RED" "$CC_RST" "$1"; FAIL=$((FAIL+1)); FAILURES+=("$1"); }
warn() { printf ' %s!%s %s\n' "$CC_YLW" "$CC_RST" "$1"; WARN=$((WARN+1)); }
step() { printf '\n%s== %s ==%s\n' "$CC_BLU" "$1" "$CC_RST"; }
info() { printf ' %s%s%s\n' "$CC_DIM" "$1" "$CC_RST"; }
die() { printf '%sFATAL: %s%s\n' "$CC_RED" "$1" "$CC_RST" >&2; cleanup; exit 2; }
assert_eq() {
if [[ "$1" == "$2" ]]; then pass "$3 ($1)"; else fail "$3: got '$1', expected '$2'"; fi
}
http_code() {
local method="$1" path="$2" data="${3:-}"
if [[ -n "$data" ]]; then
curl -s -o /dev/null -w '%{http_code}' -X "$method" "$GATEWAY$path" \
-H 'Content-Type: application/json' -d "$data"
else
curl -s -o /dev/null -w '%{http_code}' -X "$method" "$GATEWAY$path"
fi
}
# query_scalar <sql> -> first column of first row as string, sentinel on empty/error
query_scalar() {
local sql="$1"
local payload
payload=$(python3 -c 'import json,sys; print(json.dumps({"sql": sys.argv[1]}))' "$sql")
curl -s -X POST "$GATEWAY/query/sql" \
-H 'Content-Type: application/json' \
-d "$payload" \
| python3 -c '
import sys, json
try:
r = json.load(sys.stdin)
except Exception:
print("__PARSE_ERROR__"); sys.exit(0)
if isinstance(r, dict) and "error" in r:
sys.stderr.write("query error: " + str(r["error"]) + "\n")
print("__ERROR__"); sys.exit(0)
rows = r.get("rows") if isinstance(r, dict) else None
if not rows:
print("__NO_ROWS__"); sys.exit(0)
row = rows[0]
print(next(iter(row.values())))
'
}
cleanup() {
[[ "$KEEP_DATA" == "1" ]] && { info "KEEP_DATA=1 — leaving $WORKDIR"; return; }
info "cleaning up test datasets for $RUN_ID"
# Catch any previous-run zombies too: any catalog entry whose name
# starts with "e2e_" is definitionally ours. Using DELETE (added for
# this script's needs) purges both the live registry and the manifest
# file atomically, so the next run doesn't trip on zombie entries
# pointing at parquets we've already rm'd.
local names
names=$(curl -s "$GATEWAY/catalog/datasets" 2>/dev/null \
| python3 -c "
import sys, json
try: ds = json.load(sys.stdin)
except Exception: sys.exit(0)
for d in ds:
if d['name'].startswith('e2e_'):
print(d['name'])
" 2>/dev/null || true)
local removed=0
for n in $names; do
curl -s -o /dev/null -X DELETE "$GATEWAY/catalog/datasets/by-name/$n" && removed=$((removed+1))
done
# Delete any stray parquet + vector artifacts we can positively
# attribute to an e2e_ prefix.
rm -f "$DATA_ROOT/datasets/"e2e_*.parquet 2>/dev/null || true
rm -f "$DATA_ROOT/vectors/"e2e_*.parquet 2>/dev/null || true
rm -rf "$WORKDIR" 2>/dev/null || true
info "deleted $removed e2e datasets (covers this run + any prior zombies)"
}
trap cleanup EXIT
# ============================================================
# 0. Preflight
# ============================================================
step "0. Preflight"
curl -sf -m 3 "$GATEWAY/health" >/dev/null 2>&1 || die "gateway not reachable at $GATEWAY"
pass "gateway /health (200)"
SIDECAR_UP=0
if curl -sf -m 3 "$SIDECAR/health" >/dev/null 2>&1; then
SIDECAR_UP=1; pass "sidecar /health (200)"
else
warn "sidecar unreachable — vector stage will be skipped"
SKIP_VECTOR=1
fi
# Purge any e2e_* zombies from prior runs (stale registry entries that
# would otherwise break DataFusion schema inference for every query).
ZOMBIES=$(curl -s "$GATEWAY/catalog/datasets" 2>/dev/null \
| python3 -c "
import sys, json
try: ds = json.load(sys.stdin)
except Exception: sys.exit(0)
for d in ds:
if d['name'].startswith('e2e_'):
print(d['name'])
" 2>/dev/null || true)
if [[ -n "$ZOMBIES" ]]; then
ZCOUNT=$(echo "$ZOMBIES" | wc -l | tr -d ' ')
for n in $ZOMBIES; do
curl -s -o /dev/null -X DELETE "$GATEWAY/catalog/datasets/by-name/$n"
done
info "pre-cleaned $ZCOUNT e2e_ zombies from prior runs"
fi
BASELINE=$(curl -s "$GATEWAY/catalog/datasets" | python3 -c 'import sys,json; print(len(json.load(sys.stdin)))')
info "baseline dataset count: $BASELINE"
# ============================================================
# 1. Generate realistic data
# ============================================================
step "1. Generate realistic staffing data"
mkdir -p "$WORKDIR"
# Seed with RUN_ID (which embeds the wall-clock timestamp) so each run
# produces different content. Otherwise the content-hash dedup from
# Phase 6.4 keys off a stale hash that lingers in the live registry
# until the next gateway restart, and subsequent runs silently dedupe.
python3 - "$WORKDIR" "$RUN_ID" <<'PYEOF'
import csv, json, random, sys, os
workdir, run_id = sys.argv[1], sys.argv[2]
# Mix RUN_ID into the seed so content differs per run, but keep it
# deterministic within a single run.
random.seed(hash(run_id) & 0x7FFFFFFF)
FIRST = ['Aisha','Brandon','Carlos','Daria','Eli','Fiona','Gabriel','Hana','Ian','Julia',
'Kofi','Lena','Mateo','Nadia','Oscar','Priya','Quinn','Raj','Sofia','Tomas',
'Uma','Victor','Wendy','Xander','Yuki','Zara']
LAST = ['Adams','Brown','Chen','Davis','Evans','Fisher','Garcia','Hughes','Ibrahim','Johnson',
'Kim','Lopez','Martinez','Nguyen','Ortiz','Patel','Rossi','Singh','Thomas','Umar',
'Vargas','Williams','Xu','Young','Zhang','OConnor']
PLACES = [('Chicago','IL'),('New York','NY'),('San Francisco','CA'),('Austin','TX'),
('Seattle','WA'),('Denver','CO'),('Boston','MA'),('Atlanta','GA'),
('Miami','FL'),('Phoenix','AZ')]
SKILL_GROUPS = [
['Python','AWS','Docker'],['Java','Spring','Kubernetes'],
['React','TypeScript','Node'],['Go','PostgreSQL','gRPC'],
['Rust','DataFusion','Parquet'],['C#','.NET','Azure'],
['Ruby','Rails','Redis'],['Scala','Spark','Kafka'],
['Swift','iOS','CoreData'],['Kotlin','Android','Jetpack'],
]
STATUSES = ['active','placed','inactive','blocked']
STATUS_WEIGHTS = [60, 25, 10, 5]
with open(os.path.join(workdir, 'candidates.csv'), 'w', newline='') as f:
w = csv.DictWriter(f, fieldnames=[
'candidate_id','first_name','last_name','email','phone',
'city','state','skills','years_experience','hourly_rate_usd','status'])
w.writeheader()
for i in range(1, 1001):
fn, ln = random.choice(FIRST), random.choice(LAST)
city, state = random.choice(PLACES)
w.writerow({
'candidate_id': f'CAND-{i:05d}',
'first_name': fn, 'last_name': ln,
'email': f'{fn.lower()}.{ln.lower()}{i}@example.com',
'phone': f'({random.randint(200,999)}) {random.randint(200,999)}-{random.randint(1000,9999)}',
'city': city, 'state': state,
'skills': ','.join(random.choice(SKILL_GROUPS)),
'years_experience': random.randint(0, 20),
'hourly_rate_usd': random.randint(35, 185),
'status': random.choices(STATUSES, weights=STATUS_WEIGHTS)[0],
})
CLIENTS = ['Acme Corp','Globex','Initech','Umbrella','Wayne Enterprises',
'Stark Industries','Tyrell','Cyberdyne','Massive Dynamic','Oscorp']
with open(os.path.join(workdir, 'placements.ndjson'), 'w') as f:
for i in range(1, 201):
f.write(json.dumps({
'placement_id': f'PLACE-{i:04d}',
'candidate_id': f'CAND-{random.randint(1,1000):05d}',
'client': random.choice(CLIENTS),
'start_date': f'2026-{random.randint(1,4):02d}-{random.randint(1,28):02d}',
'weekly_hours': random.choice([20,25,30,35,40]),
'bill_rate': random.randint(80, 250),
'placement_status': random.choice(['active','completed','terminated']),
}) + '\n')
RESUMES = [
'Senior Python engineer with 8 years of cloud infrastructure experience. Expert in AWS, Docker, and distributed systems design. Led migration of monolithic legacy system to microservices.',
'Full-stack React and TypeScript developer specializing in real-time dashboards. Built financial trading interfaces. GraphQL, WebSocket, performance optimization.',
'Data engineer with deep Apache Spark and Kafka expertise. Seven years on streaming analytics pipelines processing billions of events per day. Scala and Python.',
'Embedded systems engineer with C++ and Rust experience. Worked on automotive ADAS systems and industrial IoT devices. Low-level firmware, RTOS.',
'DevOps engineer with Kubernetes and Terraform expertise. Six years at hypergrowth startups. Prometheus, Grafana, and observability tooling.',
'Machine learning engineer specializing in NLP. Built production transformer-based systems. PyTorch, Hugging Face, fine-tuning large language models.',
'iOS developer with Swift and SwiftUI. Four years building consumer apps at mid-size tech companies. Offline-first architectures and CoreData.',
'Backend Go developer focused on high-throughput APIs. Built payment processing systems handling millions of transactions. PostgreSQL, gRPC, Redis.',
'Security engineer with penetration testing and threat modeling experience. OSCP certified. Web application security, AppSec code review, SAST and DAST tooling.',
'Site reliability engineer with Linux internals and performance tuning expertise. Ten years at large-scale infrastructure. Tracing, profiling, kernel-level debugging.',
]
with open(os.path.join(workdir, 'resumes.ndjson'), 'w') as f:
for i, r in enumerate(RESUMES, 1):
f.write(json.dumps({'doc_id': f'RES-{i:03d}', 'resume_text': r}) + '\n')
PYEOF
pass "candidates.csv (1000 rows, 11 cols)"
pass "placements.ndjson (200 rows, 7 cols)"
pass "resumes.ndjson (10 rows, 2 cols)"
# ============================================================
# 2. CSV ingest
# ============================================================
step "2. CSV ingest (Phase 6.1)"
R=$(curl -s -X POST "$GATEWAY/ingest/file?name=$CAND_DS" -F "file=@$WORKDIR/candidates.csv")
echo "$R" | python3 -c 'import sys,json; json.load(sys.stdin)' 2>/dev/null \
|| { fail "ingest response was not JSON: $(echo "$R" | head -c 200)"; R='{}'; }
ROWS=$(echo "$R" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("rows",-1))' 2>/dev/null)
DEDUP=$(echo "$R" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("deduplicated","?"))' 2>/dev/null)
DS_NAME=$(echo "$R" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("dataset_name","?"))' 2>/dev/null)
assert_eq "$DS_NAME" "$CAND_DS" "ingest respected ?name= query param"
assert_eq "$ROWS" "1000" "ingest rows"
assert_eq "$DEDUP" "False" "first upload not deduplicated"
REG_ROWS=$(curl -s "$GATEWAY/catalog/datasets/by-name/$CAND_DS" \
| python3 -c 'import sys,json; print(json.load(sys.stdin).get("row_count","null"))')
assert_eq "$REG_ROWS" "1000" "manifest row_count reflects ingest"
# ============================================================
# 3. NDJSON ingest
# ============================================================
step "3. NDJSON ingest (Phase 6.2)"
R=$(curl -s -X POST "$GATEWAY/ingest/file?name=$PLACE_DS" -F "file=@$WORKDIR/placements.ndjson")
ROWS=$(echo "$R" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("rows",-1))' 2>/dev/null)
assert_eq "$ROWS" "200" "placements NDJSON ingest rows"
R=$(curl -s -X POST "$GATEWAY/ingest/file?name=$RESUME_DS" -F "file=@$WORKDIR/resumes.ndjson")
ROWS=$(echo "$R" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("rows",-1))' 2>/dev/null)
assert_eq "$ROWS" "10" "resumes NDJSON ingest rows"
# ============================================================
# 4. SQL queries + JOIN + cache
# ============================================================
step "4. SQL queries (Phase 2, Phase 8)"
N=$(query_scalar "SELECT COUNT(*) FROM $CAND_DS")
assert_eq "$N" "1000" "candidates COUNT(*)"
N=$(query_scalar "SELECT COUNT(*) FROM $CAND_DS WHERE status = 'active'")
if [[ "$N" =~ ^[0-9]+$ ]] && (( N > 400 && N < 700 )); then
pass "active candidates in plausible range ($N, expect ~600)"
else
fail "active candidates count out of range: $N"
fi
N=$(query_scalar "
SELECT COUNT(DISTINCT c.candidate_id)
FROM $CAND_DS c
JOIN $PLACE_DS p ON c.candidate_id = p.candidate_id
WHERE p.placement_status = 'active'
")
if [[ "$N" =~ ^[0-9]+$ ]] && (( N > 0 && N <= 200 )); then
pass "cross-dataset JOIN with filter returns $N rows"
else
fail "JOIN returned unexpected count: $N"
fi
AVG=$(query_scalar "SELECT AVG(hourly_rate_usd) FROM $CAND_DS")
if python3 -c "import sys; v=float('$AVG'); sys.exit(0 if 100 < v < 130 else 1)" 2>/dev/null; then
pass "average hourly rate in plausible range ($AVG, expect ~110)"
else
fail "average hourly rate out of range: $AVG"
fi
CODE=$(http_code POST "/query/cache/pin" "{\"dataset\":\"$CAND_DS\"}")
assert_eq "$CODE" "200" "cache pin HTTP"
# ============================================================
# 5. Content-hash re-ingest dedup (Phase 6.4)
# ============================================================
step "5. Content-hash re-ingest dedup"
R=$(curl -s -X POST "$GATEWAY/ingest/file?name=$CAND_DS" -F "file=@$WORKDIR/candidates.csv")
DEDUP=$(echo "$R" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("deduplicated","?"))' 2>/dev/null)
assert_eq "$DEDUP" "True" "re-upload same file is deduplicated"
# ============================================================
# 6. Idempotent register — same fingerprint (ADR-020)
# ============================================================
step "6. Idempotent register (ADR-020 same-fp path)"
DS=$(curl -s "$GATEWAY/catalog/datasets/by-name/$CAND_DS")
FP=$(echo "$DS" | python3 -c 'import sys,json; print(json.load(sys.stdin)["schema_fingerprint"])')
OBJS=$(echo "$DS" | python3 -c 'import sys,json,json as j; print(j.dumps(json.load(sys.stdin)["objects"]))')
ID_BEFORE=$(echo "$DS" | python3 -c 'import sys,json; print(json.load(sys.stdin)["id"])')
PAYLOAD=$(python3 -c "import json,sys; print(json.dumps({'name':sys.argv[1],'schema_fingerprint':sys.argv[2],'objects':json.loads(sys.argv[3])}))" "$CAND_DS" "$FP" "$OBJS")
CODE=$(http_code POST "/catalog/datasets" "$PAYLOAD")
assert_eq "$CODE" "201" "same-fp re-register returns 201"
ID_AFTER=$(curl -s "$GATEWAY/catalog/datasets/by-name/$CAND_DS" | python3 -c 'import sys,json; print(json.load(sys.stdin)["id"])')
assert_eq "$ID_AFTER" "$ID_BEFORE" "same DatasetId after re-register"
COUNT=$(curl -s "$GATEWAY/catalog/datasets" | python3 -c "import sys,json; print(sum(1 for d in json.load(sys.stdin) if d['name']=='$CAND_DS'))")
assert_eq "$COUNT" "1" "no duplicate manifest created"
# ============================================================
# 7. Schema-drift rejection (409)
# ============================================================
step "7. Schema-drift rejection (ADR-020 409 path)"
PAYLOAD=$(python3 -c "import json,sys; print(json.dumps({'name':sys.argv[1],'schema_fingerprint':'deadbeefnotmatching','objects':json.loads(sys.argv[2])}))" "$CAND_DS" "$OBJS")
CODE=$(http_code POST "/catalog/datasets" "$PAYLOAD")
assert_eq "$CODE" "409" "different-fp rejected with 409"
# ============================================================
# 8. Dedupe no-op on clean catalog
# ============================================================
step "8. Dedupe no-op on clean state"
R=$(curl -s -X POST "$GATEWAY/catalog/dedupe")
GROUPS=$(echo "$R" | python3 -c 'import sys,json; print(json.load(sys.stdin)["groups"])')
REMOVED=$(echo "$R" | python3 -c 'import sys,json; print(json.load(sys.stdin)["removed"])')
assert_eq "$GROUPS" "0" "dedupe groups (clean catalog)"
assert_eq "$REMOVED" "0" "dedupe removed count"
# ============================================================
# 9. Metadata enrichment (Phase 10)
# ============================================================
step "9. Metadata enrichment (Phase 10)"
CODE=$(http_code POST "/catalog/datasets/by-name/$CAND_DS/metadata" \
"{\"owner\":\"e2e-test\",\"description\":\"$RUN_ID synthetic candidates\",\"tags\":[\"test\",\"synthetic\"]}")
assert_eq "$CODE" "200" "POST metadata HTTP"
META=$(curl -s "$GATEWAY/catalog/datasets/by-name/$CAND_DS")
OWNER=$(echo "$META" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("owner",""))')
assert_eq "$OWNER" "e2e-test" "owner persisted"
# ============================================================
# 10. PII auto-detection (Phase 10)
# ============================================================
step "10. PII auto-detection (Phase 10)"
PII_COLS=$(echo "$META" | python3 -c '
import sys, json
m = json.load(sys.stdin)
pii = [c["name"] for c in m.get("columns",[]) if c.get("is_pii") or (isinstance(c.get("sensitivity"),str) and c["sensitivity"].lower()=="pii")]
print(" ".join(pii) if pii else "__NONE__")')
if [[ "$PII_COLS" == *"email"* ]] && [[ "$PII_COLS" == *"phone"* ]]; then
pass "email and phone flagged as PII ($PII_COLS)"
elif [[ "$PII_COLS" == "__NONE__" ]]; then
warn "no PII flagged — auto-detection may not run on this path"
else
warn "partial PII detection: $PII_COLS"
fi
# ============================================================
# 11. Vector index + semantic search (Phase 7)
# ============================================================
step "11. Vector index + semantic search (Phase 7)"
if [[ "$SKIP_VECTOR" == "1" ]]; then
warn "SKIP_VECTOR=1 — skipping vector pipeline"
else
# Pull documents out of the ingested resumes dataset via SQL,
# then feed to the inline /vectors/index body. This exercises
# the query→embed integration rather than pre-canned input.
DOCS=$(curl -s -X POST "$GATEWAY/query/sql" \
-H 'Content-Type: application/json' \
-d "$(python3 -c "import json; print(json.dumps({'sql': 'SELECT doc_id, resume_text FROM $RESUME_DS'}))")" \
| python3 -c '
import sys, json
r = json.load(sys.stdin)
docs = [{"id": row["doc_id"], "text": row["resume_text"]} for row in r.get("rows", [])]
print(json.dumps(docs))')
DOC_COUNT=$(echo "$DOCS" | python3 -c 'import sys,json; print(len(json.load(sys.stdin)))')
assert_eq "$DOC_COUNT" "10" "pulled docs via SQL for embedding"
PAYLOAD=$(python3 -c "
import json, sys
print(json.dumps({
'index_name': sys.argv[1],
'source': sys.argv[2],
'documents': json.loads(sys.argv[3]),
'chunk_size': 500,
'overlap': 50,
}))" "$VEC_IDX" "$RESUME_DS" "$DOCS")
R=$(curl -s -X POST "$GATEWAY/vectors/index" -H 'Content-Type: application/json' -d "$PAYLOAD")
JOB_ID=$(echo "$R" | python3 -c 'import sys,json; d=json.load(sys.stdin); print(d.get("job_id","__NONE__"))' 2>/dev/null)
if [[ "$JOB_ID" == "__NONE__" || -z "$JOB_ID" ]]; then
fail "vector index job rejected: $(echo "$R" | head -c 200)"
else
pass "embedding job accepted (job=$JOB_ID)"
# Poll up to 90s for 10 short resumes; Ollama cold-start can be slow.
JOB_STATUS="unknown"
for _ in $(seq 1 45); do
JOB_STATUS=$(curl -s "$GATEWAY/vectors/jobs/$JOB_ID" 2>/dev/null \
| python3 -c '
import sys, json
try: print(json.load(sys.stdin).get("status","?"))
except Exception: print("?")' 2>/dev/null)
[[ "$JOB_STATUS" == "completed" || "$JOB_STATUS" == "Completed" ]] && break
[[ "$JOB_STATUS" == "failed" || "$JOB_STATUS" == "Failed" ]] && break
sleep 2
done
case "$JOB_STATUS" in
completed|Completed)
pass "embedding job completed"
R=$(curl -s -X POST "$GATEWAY/vectors/search" \
-H 'Content-Type: application/json' \
-d "{\"index_name\":\"$VEC_IDX\",\"query\":\"fine-tuning large language models\",\"k\":3}")
TOP_DOC=$(echo "$R" | python3 -c '
import sys, json
r = json.load(sys.stdin)
if r.get("results"): print(r["results"][0].get("doc_id","?"))
else: print("__NONE__")' 2>/dev/null)
if [[ "$TOP_DOC" == "RES-006" ]]; then
pass "top match is ML/NLP resume (semantically correct)"
elif [[ "$TOP_DOC" == "__NONE__" ]]; then
fail "search returned no results"
else
warn "top match is $TOP_DOC (expected RES-006 — ranking may vary)"
fi ;;
*)
fail "embedding job did not complete (status=$JOB_STATUS)" ;;
esac
fi
fi
# ============================================================
# 12. Cleanup + baseline verify
# ============================================================
step "12. Cleanup + baseline verify"
cleanup
trap - EXIT
ON_DISK=$(ls "$DATA_ROOT/_catalog/manifests"/*.json 2>/dev/null | wc -l | tr -d ' ')
info "manifest files on disk now: $ON_DISK"
DISK_ORPHANS=0
if compgen -G "$DATA_ROOT/_catalog/manifests/*.json" > /dev/null; then
DISK_ORPHANS=$(grep -l "\"$RUN_ID" "$DATA_ROOT/_catalog/manifests"/*.json 2>/dev/null | wc -l | tr -d ' ')
fi
assert_eq "$DISK_ORPHANS" "0" "no orphan manifest files on disk for $RUN_ID"
LIVE_ORPHANS=$(curl -s "$GATEWAY/catalog/datasets" \
| python3 -c "import sys,json; print(sum(1 for d in json.load(sys.stdin) if d['name'].startswith('$RUN_ID')))")
if [[ "$LIVE_ORPHANS" != "0" ]]; then
warn "$LIVE_ORPHANS entries linger in live registry (clears on gateway restart; on-disk is ground truth)"
fi
# ============================================================
# Summary
# ============================================================
ELAPSED=$(( $(date +%s) - STARTED_AT ))
printf '\n%s─── Summary ───%s\n' "$CC_BLU" "$CC_RST"
printf ' run_id: %s\n' "$RUN_ID"
printf ' elapsed: %ss\n' "$ELAPSED"
printf ' passed: %s%d%s\n' "$CC_GRN" "$PASS" "$CC_RST"
printf ' failed: %s%d%s\n' "$CC_RED" "$FAIL" "$CC_RST"
printf ' warnings: %s%d%s\n' "$CC_YLW" "$WARN" "$CC_RST"
if (( FAIL > 0 )); then
printf '\n%sfailures:%s\n' "$CC_RED" "$CC_RST"
for f in "${FAILURES[@]}"; do printf ' - %s\n' "$f"; done
exit 1
fi
exit 0

104
scripts/lance_smoke.sh Executable file
View File

@ -0,0 +1,104 @@
#!/usr/bin/env bash
# lance smoke — gates the 5 /vectors/lance/* HTTP routes (search, doc,
# index, append, migrate). Only the read paths are exercised here so a
# CI run doesn't mutate state. Migrate + index + append have shape
# probes (request bodies are well-formed) but ride the not-found path
# that the 2026-05-02 audit added.
#
# Targets the live gateway at $LH_GATEWAY (default :3100). Uses an
# existing on-disk Lance dataset — `workers_500k_v1` — so no
# migration setup is needed. If the dataset is missing the smoke
# fails loudly with a clear message.
#
# Surfaced 2026-05-02: the lance crates had zero tests + no smoke;
# substrate change to lance_backend.rs would silently break the live
# surface. This smoke is the regression gate.
#
# Usage:
# ./scripts/lance_smoke.sh
# LH_GATEWAY=http://127.0.0.1:3100 ./scripts/lance_smoke.sh
set -euo pipefail
GATEWAY="${LH_GATEWAY:-http://127.0.0.1:3100}"
DATASET="${LH_LANCE_DATASET:-workers_500k_v1}"
PREFIX="$GATEWAY/vectors/lance"
PASS=0; FAIL=0
PROBE() { local label="$1"; shift; "$@" && { echo " ✓ $label"; PASS=$((PASS+1)); } || { echo " ✗ $label"; FAIL=$((FAIL+1)); }; }
echo "[lance-smoke] gateway=$GATEWAY dataset=$DATASET"
# ── 0. Gateway alive ─────────────────────────────────────────────
PROBE "gateway /v1/health responds" \
bash -c "curl -sf -m 3 $GATEWAY/v1/health -o /dev/null"
# ── 1. Search returns IVF_PQ results on existing dataset ────────
# Capture curl status separately so a transport-level failure (gateway
# down, network broken, timeout) shows up as its own probe — instead of
# being swallowed by `|| echo '{}'` which would surface as the next jq
# probe failing with a misleading "no method field" message. Per opus
# INFO at lance_smoke.sh:38 from the 2026-05-02 scrum.
RESP=$(curl -sS -m 30 -X POST "$PREFIX/search/$DATASET" \
-H 'Content-Type: application/json' \
-d '{"query":"forklift operator","top_k":3}' 2>/dev/null)
CURL_RC=$?
PROBE "search/$DATASET curl reachable (exit 0)" \
test "$CURL_RC" = "0"
[ "$CURL_RC" != "0" ] && RESP='{}'
PROBE "search/$DATASET returns top-3 lance_ivf_pq results" \
bash -c "echo '$RESP' | jq -e '.method == \"lance_ivf_pq\" and (.results | length) == 3' >/dev/null"
# Capture one doc_id from those results so the next probe has something real to fetch.
DOC_ID=$(echo "$RESP" | jq -r '.results[0].doc_id // ""')
# ── 2. get_doc by id returns the row ────────────────────────────
PROBE "doc/$DATASET/<known-id> returns full row" \
bash -c "[ -n '$DOC_ID' ] && curl -sf -m 5 '$PREFIX/doc/$DATASET/$DOC_ID' | jq -e '.row.doc_id == \"$DOC_ID\"' >/dev/null"
# ── 3. get_doc with bogus id returns 404 (not 500) ──────────────
STATUS=$(curl -sS -m 5 -o /tmp/lance_smoke_404.json -w '%{http_code}' \
"$PREFIX/doc/$DATASET/W500K-NOT-A-REAL-ID-00000")
PROBE "doc/$DATASET/<missing-id> → 404" \
test "$STATUS" = "404"
# ── 4. search on missing dataset returns 404 + sanitized message ─
STATUS=$(curl -sS -m 5 -o /tmp/lance_smoke_500.json -w '%{http_code}' \
-X POST "$PREFIX/search/no-such-dataset-${RANDOM}" \
-H 'Content-Type: application/json' \
-d '{"query":"x","top_k":1}')
BODY=$(cat /tmp/lance_smoke_500.json)
PROBE "search/<missing> → 404 (was 500 pre-2026-05-02)" \
test "$STATUS" = "404"
# Assert "pattern absent" — `! grep -qE` (NOT `grep -qvE` which is unsound:
# -v -q exits 0 if ANY line lacks the pattern, so a multi-line body containing
# both a leak line AND any clean line would false-PASS. Caught 2026-05-02 by
# opus scrum on the lance backend wave.)
PROBE "search/<missing> body sanitized — no filesystem leak" \
bash -c "! echo '$BODY' | grep -qE '/home/|/root/\.cargo/|/var/|/tmp/'"
# ── 5. build_index on missing dataset also sanitized ────────────
STATUS=$(curl -sS -m 5 -o /tmp/lance_smoke_idx.json -w '%{http_code}' \
-X POST "$PREFIX/index/no-such-dataset-${RANDOM}" \
-H 'Content-Type: application/json' \
-d '{}')
BODY=$(cat /tmp/lance_smoke_idx.json)
PROBE "index/<missing> body sanitized" \
bash -c "! echo '$BODY' | grep -qE '/home/|/root/\.cargo/|/var/|/tmp/'"
# ── 6. append validates input shape (rejects empty rows array) ──
STATUS=$(curl -sS -m 5 -o /dev/null -w '%{http_code}' \
-X POST "$PREFIX/append/$DATASET" \
-H 'Content-Type: application/json' \
-d '{"rows":[]}')
PROBE "append with empty rows[] → 400" \
test "$STATUS" = "400"
# ── 7. migrate route is reachable (POST without body returns a real error, not 404) ──
STATUS=$(curl -sS -m 5 -o /dev/null -w '%{http_code}' \
-X POST "$PREFIX/migrate/probe-not-real-${RANDOM}?bucket=primary" 2>/dev/null)
# Should be 4xx (bad request shape), NOT 404 (route registered) and NOT 200.
PROBE "migrate route registered (non-404, non-200 on empty body)" \
bash -c "[ '$STATUS' != '404' ] && [ '$STATUS' != '200' ]"
echo "[lance-smoke] $PASS PASS / $FAIL FAIL"
[ "$FAIL" -eq 0 ]

157
scripts/production_smoke.sh Executable file
View File

@ -0,0 +1,157 @@
#!/usr/bin/env bash
# Production substrate smoke — single command that verifies every
# production-critical surface end-to-end. Exits non-zero on the first
# failure so an operator can run this before:
# - Swapping workers_500k.parquet → real Chicago contractor data
# - Spinning up the Asterisk voice agent against /v1/chat
# - Running staffing inference loops via /v1/iterate
# - Wiring the assistant against the gateway
#
# Usage:
# ./scripts/production_smoke.sh
#
# Tunable via env:
# GATEWAY=http://localhost:3100 # gateway base URL
# FAIL_FAST=1 # exit on first failure (default 1)
# VERBOSE=1 # print full responses on success too
set -e
GATEWAY="${GATEWAY:-http://localhost:3100}"
FAIL_FAST="${FAIL_FAST:-1}"
VERBOSE="${VERBOSE:-0}"
PASS=0
FAIL=0
FAILURES=()
check() {
local name="$1"
local expected_status="$2"
local cmd="$3"
echo -n " [$(($PASS + $FAIL + 1))] $name ... "
local resp
resp=$(eval "$cmd" 2>&1) || true
local status="${resp%%|||*}"
local body="${resp#*|||}"
if [ "$status" = "$expected_status" ]; then
PASS=$((PASS + 1))
echo "✓ ($status)"
if [ "$VERBOSE" = "1" ]; then echo " $body" | head -3 | sed 's/^/ /'; fi
else
FAIL=$((FAIL + 1))
FAILURES+=("$name: expected $expected_status, got $status")
echo "✗ (got $status, expected $expected_status)"
echo " $body" | head -3 | sed 's/^/ /'
[ "$FAIL_FAST" = "1" ] && { print_summary; exit 1; }
fi
}
curl_with_status() {
# Run curl, capture HTTP status + body, format as "status|||body"
local args=("$@")
curl -sS -w "\n%{http_code}" "${args[@]}" 2>&1 | awk '
{ lines[NR]=$0 }
END {
status=lines[NR]
body=""
for (i=1; i<NR; i++) body=body lines[i] (i<NR-1?"\n":"")
print status "|||" body
}
'
}
print_summary() {
echo ""
echo "═══════════════════════════════════════════════════════════════"
echo " $PASS passed · $FAIL failed"
if [ ${#FAILURES[@]} -gt 0 ]; then
echo " failures:"
for f in "${FAILURES[@]}"; do echo " - $f"; done
fi
echo "═══════════════════════════════════════════════════════════════"
}
echo "Production substrate smoke test against $GATEWAY"
echo ""
# ─── 1. Liveness ─────────────────────────────────────────────────────
echo "▶ Liveness"
check "gateway /health" "200" \
'curl_with_status -m 5 "$GATEWAY/health"'
# ─── 2. Operational health ──────────────────────────────────────────
echo "▶ Operational state"
HEALTH_RESP=$(curl -sS -m 10 "$GATEWAY/v1/health" 2>&1) || HEALTH_RESP="{}"
WORKERS_COUNT=$(echo "$HEALTH_RESP" | python3 -c "import sys,json; print(json.load(sys.stdin).get('workers_count',0))" 2>/dev/null || echo 0)
PROVIDERS_OK=$(echo "$HEALTH_RESP" | python3 -c "import sys,json; d=json.load(sys.stdin).get('providers_configured',{}); print(sum(1 for v in d.values() if v))" 2>/dev/null || echo 0)
echo " workers_count: $WORKERS_COUNT"
echo " providers_configured (count): $PROVIDERS_OK"
if [ "$WORKERS_COUNT" -lt 1 ]; then
FAIL=$((FAIL + 1))
FAILURES+=("workers_count=0 — parquet load failed or empty")
echo " ✗ workers not loaded"
[ "$FAIL_FAST" = "1" ] && { print_summary; exit 1; }
else
PASS=$((PASS + 1))
echo " ✓ workers loaded"
fi
# ─── 3. Truth Layer ──────────────────────────────────────────────────
echo "▶ Truth Layer"
check "/v1/context returns rules" "200" \
'curl_with_status -m 10 "$GATEWAY/v1/context"'
# ─── 4. /v1/chat (provider=ollama) ──────────────────────────────────
echo "▶ /v1/chat (provider=ollama, fast model)"
check "/v1/chat ping" "200" \
'curl_with_status -m 60 -X POST "$GATEWAY/v1/chat" \
-H "content-type: application/json" \
-d "{\"provider\":\"ollama\",\"model\":\"qwen3.5:latest\",\"messages\":[{\"role\":\"user\",\"content\":\"reply: PONG\"}],\"max_tokens\":30,\"temperature\":0,\"think\":false}"'
# ─── 5. /v1/validate (negative + positive) ──────────────────────────
echo "▶ /v1/validate"
check "phantom candidate_id → 422 Consistency" "422" \
'curl_with_status -m 10 -X POST "$GATEWAY/v1/validate" \
-H "content-type: application/json" \
-d "{\"kind\":\"fill\",\"artifact\":{\"fills\":[{\"candidate_id\":\"W-FAKE-0\",\"name\":\"Fake\"}]},\"context\":{\"target_count\":1}}"'
check "real worker (W-1) → 200 OK" "200" \
'curl_with_status -m 10 -X POST "$GATEWAY/v1/validate" \
-H "content-type: application/json" \
-d "{\"kind\":\"fill\",\"artifact\":{\"fills\":[{\"candidate_id\":\"W-1\",\"name\":\"Anyone\"}]},\"context\":{\"target_count\":1}}"'
check "SSN in body → 422 Policy" "422" \
'curl_with_status -m 10 -X POST "$GATEWAY/v1/validate" \
-H "content-type: application/json" \
-d "{\"kind\":\"email\",\"artifact\":{\"to\":\"a@b.com\",\"body\":\"Your SSN 123-45-6789 is on file.\"}}"'
# ─── 6. /v1/iterate (bounded retry loop) ───────────────────────────
# Phantom worker → expect 422 IterateFailure with history (not 200)
echo "▶ /v1/iterate (bounded retry)"
check "/v1/iterate phantom → bounded fail" "422" \
'curl_with_status -m 240 -X POST "$GATEWAY/v1/iterate" \
-H "content-type: application/json" \
-d "{\"kind\":\"fill\",\"provider\":\"ollama\",\"model\":\"qwen3.5:latest\",\"system\":\"Reply with ONLY: {\\\"fills\\\":[{\\\"candidate_id\\\":\\\"W-99999999\\\",\\\"name\\\":\\\"X\\\"}]}\",\"prompt\":\"emit it\",\"context\":{\"target_count\":1},\"max_iterations\":1,\"max_tokens\":200,\"temperature\":0}"'
# ─── 7. Doc-drift batch ─────────────────────────────────────────────
echo "▶ Doc-drift scan"
check "/vectors/playbook_memory/doc_drift/scan" "200" \
'curl_with_status -m 60 -X POST "$GATEWAY/vectors/playbook_memory/doc_drift/scan"'
# ─── 8. Usage tracking ──────────────────────────────────────────────
echo "▶ Usage tracking"
USAGE=$(curl -sS -m 10 "$GATEWAY/v1/usage" 2>&1)
USAGE_REQS=$(echo "$USAGE" | python3 -c "import sys,json; print(json.load(sys.stdin).get('requests',0))" 2>/dev/null || echo 0)
echo " usage.requests: $USAGE_REQS (should be > 0 if /v1/chat fired)"
if [ "$USAGE_REQS" -ge 1 ]; then
PASS=$((PASS + 1))
echo " ✓ /v1/usage tracking"
else
FAIL=$((FAIL + 1))
FAILURES+=("/v1/usage didn't increment after /v1/chat call")
echo " ✗ /v1/usage didn't increment"
fi
print_summary
[ $FAIL -eq 0 ] && exit 0 || exit 1

59
scripts/serve_imagegen.py
View File

@ -29,8 +29,14 @@ CACHE_DIR.mkdir(parents=True, exist_ok=True)
WORKFLOW_PATH = "/opt/ComfyUI/workflows/editorial_hero.json" WORKFLOW_PATH = "/opt/ComfyUI/workflows/editorial_hero.json"
def _cache_key(prompt, width, height, steps): def _cache_key(prompt, width, height, steps, seed=None):
return hashlib.sha256(f"{prompt}|{width}|{height}|{steps}".encode()).hexdigest()[:24] # Include seed so callers can vary outputs deterministically without
# the proxy collapsing to a single cached image. None == legacy
# (omitted from the key for backward compatibility).
bits = f"{prompt}|{width}|{height}|{steps}"
if seed is not None:
bits += f"|{seed}"
return hashlib.sha256(bits.encode()).hexdigest()[:24]
def _cache_get(key): def _cache_get(key):
fp = CACHE_DIR / f"{key}.webp" fp = CACHE_DIR / f"{key}.webp"
@ -40,8 +46,15 @@ def _cache_put(key, img_bytes):
(CACHE_DIR / f"{key}.webp").write_bytes(img_bytes) (CACHE_DIR / f"{key}.webp").write_bytes(img_bytes)
def _comfyui_generate(prompt, width=1024, height=512, steps=8, seed=None): def _comfyui_generate(prompt, width=1024, height=512, steps=8, seed=None,
"""Submit workflow to ComfyUI and wait for result.""" negative_prompt=None, cfg=None, sampler=None, scheduler=None):
"""Submit workflow to ComfyUI and wait for result.
Optional overrides — when provided, replace the workflow's defaults.
The workflow template at editorial_hero.json was tuned for product
hero shots with a "no humans" negative prompt; portrait callers MUST
pass `negative_prompt` to avoid the model fighting them on faces.
"""
# Load workflow template # Load workflow template
with open(WORKFLOW_PATH) as f: with open(WORKFLOW_PATH) as f:
workflow = json.load(f) workflow = json.load(f)
@ -51,9 +64,21 @@ def _comfyui_generate(prompt, width=1024, height=512, steps=8, seed=None):
seed = random.randint(0, 2**32) seed = random.randint(0, 2**32)
workflow["3"]["inputs"]["seed"] = seed workflow["3"]["inputs"]["seed"] = seed
workflow["3"]["inputs"]["steps"] = steps workflow["3"]["inputs"]["steps"] = steps
if cfg is not None:
workflow["3"]["inputs"]["cfg"] = cfg
if sampler:
workflow["3"]["inputs"]["sampler_name"] = sampler
if scheduler:
workflow["3"]["inputs"]["scheduler"] = scheduler
workflow["5"]["inputs"]["width"] = width workflow["5"]["inputs"]["width"] = width
workflow["5"]["inputs"]["height"] = height workflow["5"]["inputs"]["height"] = height
workflow["6"]["inputs"]["text"] = prompt workflow["6"]["inputs"]["text"] = prompt
# Node 7 is the negative-prompt CLIPTextEncode. The default is tuned
# for product hero shots and contains "human, person, face, hand,
# fingers, realistic photo of people" — actively sabotaging any
# portrait render. Always overwrite when negative_prompt is given.
if negative_prompt is not None:
workflow["7"]["inputs"]["text"] = negative_prompt
# Submit to ComfyUI # Submit to ComfyUI
payload = json.dumps({"prompt": workflow}).encode() payload = json.dumps({"prompt": workflow}).encode()
@ -177,9 +202,20 @@ class ImageHandler(BaseHTTPRequestHandler):
height = min(max(int(body.get("height", 720)), 256), 1080) height = min(max(int(body.get("height", 720)), 256), 1080)
steps = min(max(int(body.get("steps", 50)), 1), 80) steps = min(max(int(body.get("steps", 50)), 1), 80)
seed = body.get("seed") seed = body.get("seed")
# Portrait-friendly overrides — None means "use workflow default".
# negative_prompt MUST be passed by portrait callers to avoid
# the workflow's "no humans" baked-in negative.
negative_prompt = body.get("negative_prompt")
cfg = body.get("cfg")
sampler = body.get("sampler")
scheduler = body.get("scheduler")
# Cache check # Cache check — seed + negative + cfg are part of the key so per-
key = _cache_key(prompt, width, height, steps) # worker / per-config requests don't collapse to one cached image.
key = _cache_key(
f"{prompt}||neg={negative_prompt or ''}||cfg={cfg or ''}",
width, height, steps, seed,
)
cached = _cache_get(key) cached = _cache_get(key)
if cached: if cached:
self._json(200, {"image": cached, "format": "webp", "width": width, "height": height, self._json(200, {"image": cached, "format": "webp", "width": width, "height": height,
@ -192,7 +228,11 @@ class ImageHandler(BaseHTTPRequestHandler):
try: try:
comfy_check = urllib.request.urlopen(f"{COMFYUI_URL}/system_stats", timeout=3) comfy_check = urllib.request.urlopen(f"{COMFYUI_URL}/system_stats", timeout=3)
if comfy_check.status == 200: if comfy_check.status == 200:
img_bytes, seed = _comfyui_generate(prompt, width, height, steps, seed) img_bytes, seed = _comfyui_generate(
prompt, width, height, steps, seed,
negative_prompt=negative_prompt, cfg=cfg,
sampler=sampler, scheduler=scheduler,
)
backend = "comfyui" backend = "comfyui"
except: except:
pass pass
@ -210,6 +250,11 @@ class ImageHandler(BaseHTTPRequestHandler):
elapsed_ms = int((time.time() - t0) * 1000) elapsed_ms = int((time.time() - t0) * 1000)
img_b64 = base64.b64encode(img_bytes).decode() img_b64 = base64.b64encode(img_bytes).decode()
# Recompute key with the actual seed used (when caller passed
# None, _comfyui_generate picks a random one and we want the
# cache to reflect that so re-requests with the same returned
# seed hit the disk).
key = _cache_key(prompt, width, height, steps, seed)
_cache_put(key, img_bytes) _cache_put(key, img_bytes)
self._json(200, { self._json(200, {

225
scripts/staffing/fetch_face_pool.py Normal file
View File

@ -0,0 +1,225 @@
#!/usr/bin/env python3
"""
fetch_face_pool.py — pull N synthetic headshots from
https://thispersondoesnotexist.com/, write to data/headshots/face_NNNN.jpg,
optionally tag each with gender via deepface, emit a JSONL manifest.
Each fetch is a fresh StyleGAN face — no real people. Deterministic per
worker mapping happens at serve time (mcp-server hashes the worker key
into the pool); this script just builds the pool.
Usage:
python3 scripts/staffing/fetch_face_pool.py --count 300 --concurrency 3
python3 scripts/staffing/fetch_face_pool.py --count 50 --no-gender
Re-running is idempotent: existing face_NNNN.jpg files are skipped, and
the manifest is rewritten from disk state.
"""
from __future__ import annotations
import argparse
import hashlib
import json
import os
import sys
import time
from concurrent.futures import ThreadPoolExecutor, as_completed
import urllib.request
import urllib.error
URL = "https://thispersondoesnotexist.com/"
UA = "Lakehouse/1.0 (face-pool fetch · synthetic-only · no real-person tracking)"
def fetch_one(idx: int, out_dir: str) -> tuple[int, str, bool, str | None]:
"""Returns (idx, basename, cached, error)."""
fname = f"face_{idx:04d}.jpg"
full = os.path.join(out_dir, fname)
if os.path.exists(full) and os.path.getsize(full) > 1024:
return idx, fname, True, None
try:
req = urllib.request.Request(URL, headers={"User-Agent": UA})
with urllib.request.urlopen(req, timeout=20) as resp:
blob = resp.read()
if len(blob) < 1024:
return idx, fname, False, f"response too small ({len(blob)} bytes)"
with open(full, "wb") as f:
f.write(blob)
return idx, fname, False, None
except urllib.error.URLError as e:
return idx, fname, False, f"urlerror: {e}"
except Exception as e:
return idx, fname, False, f"{type(e).__name__}: {e}"
def maybe_tag_gender(records: list[dict], out_dir: str) -> dict[str, int]:
"""If deepface is installed, label records that don't already have a
gender. Returns a count summary; mutates records in place.
Preservation contract: never overwrites prior `gender` (or any other
tag — race/age/excluded — set by tag_face_pool.py). On deepface
import failure, leaves existing tags alone instead of resetting them
to None. The previous behavior wiped 952 hand-classified rows when
fetch_face_pool was re-run from a Python without deepface installed."""
try:
from deepface import DeepFace # type: ignore
except Exception as e:
print(f" (deepface unavailable: {e}) — leaving existing tags untouched")
for r in records:
r.setdefault("gender", None)
already = sum(1 for r in records if r.get("gender") in ("man", "woman"))
return {"preserved_tagged": already, "untagged": len(records) - already}
todo = [r for r in records if r.get("gender") not in ("man", "woman")]
if not todo:
print(" every record already has gender — nothing to tag.")
return {"preserved_tagged": len(records)}
print(f" tagging gender via deepface ({len(todo)} of {len(records)} records, CPU; ~0.5-1s per face)…")
counts: dict[str, int] = {}
for i, r in enumerate(todo):
full = os.path.join(out_dir, r["file"])
try:
ana = DeepFace.analyze(
img_path=full,
actions=["gender"],
enforce_detection=False,
silent=True,
)
if isinstance(ana, list):
ana = ana[0] if ana else {}
g_raw = (ana.get("dominant_gender") or "").lower().strip()
r["gender"] = (
"man" if g_raw.startswith("man") else
"woman" if g_raw.startswith("woman") else
None
)
except Exception as e:
r["gender"] = None
r["gender_error"] = f"{type(e).__name__}: {e}"
counts[r["gender"] or "unknown"] = counts.get(r["gender"] or "unknown", 0) + 1
if (i + 1) % 25 == 0:
print(f" [{i+1}/{len(todo)}] {counts}")
return counts
def main():
p = argparse.ArgumentParser()
p.add_argument("--count", type=int, default=300, help="how many faces to maintain in pool")
p.add_argument(
"--out",
default=os.path.join(os.path.dirname(__file__), "..", "..", "data", "headshots"),
)
p.add_argument("--concurrency", type=int, default=3, help="parallel fetches (be polite)")
p.add_argument("--no-gender", action="store_true", help="skip deepface gender tagging")
p.add_argument("--shrink", action="store_true",
help="allow --count to drop manifest entries with id >= count. Default: preserve them.")
args = p.parse_args()
out = os.path.realpath(args.out)
os.makedirs(out, exist_ok=True)
# Load any existing manifest into a by-id dict so prior tags
# (gender / race / age / excluded) survive the rewrite. Also
# naturally dedupes — if the file accidentally has duplicate
# lines for the same id (this is how we ended up with a 2497-
# row manifest backing a 1000-face pool), the last one wins.
manifest = os.path.join(out, "manifest.jsonl")
existing: dict[int, dict] = {}
if os.path.exists(manifest):
dup_count = 0
with open(manifest) as f:
for line in f:
line = line.strip()
if not line:
continue
try:
row = json.loads(line)
except json.JSONDecodeError:
continue
rid = row.get("id")
if not isinstance(rid, int):
continue
if rid in existing:
dup_count += 1
existing[rid] = row
print(f"Loaded existing manifest: {len(existing)} unique ids ({dup_count} duplicate lines collapsed)")
max_existing = max(existing.keys()) if existing else -1
if max_existing >= args.count and not args.shrink:
print(
f"\nERROR: --count={args.count} would drop {sum(1 for k in existing if k >= args.count)} "
f"manifest entries (max existing id = {max_existing}). Pass --shrink to allow.\n",
file=sys.stderr,
)
sys.exit(2)
print(f"Fetching {args.count} faces → {out}")
print(f"Source: {URL} (synthetic StyleGAN — no real people)")
results: list[dict] = [None] * args.count # type: ignore
t0 = time.time()
with ThreadPoolExecutor(max_workers=max(1, args.concurrency)) as ex:
futs = {ex.submit(fetch_one, i, out): i for i in range(args.count)}
for done, fut in enumerate(as_completed(futs), 1):
idx, fname, cached, err = fut.result()
# Start from prior manifest row (preserves gender/race/age/excluded)
# and overlay only the fields fetch_one is responsible for.
base = dict(existing.get(idx, {}))
base.update({
"id": idx,
"file": fname,
"cached": cached,
"error": err,
})
results[idx] = base
if done % 25 == 0 or done == args.count:
ok = sum(1 for r in results if r and not r.get("error"))
print(f" [{done}/{args.count}] {ok} ok ({time.time()-t0:.1f}s)")
# Drop slots that errored or are still None (shouldn't happen)
records = [r for r in results if r and not r.get("error")]
print(f"\nPool ready: {len(records)} faces, {sum(1 for r in records if r['cached'])} from cache")
preserved_tags = sum(1 for r in records if r.get("gender") in ("man", "woman"))
if preserved_tags:
print(f"Preserved {preserved_tags} prior gender tags (and any race/age/excluded fields).")
if not args.no_gender and records:
print("\nGender-tagging pass:")
summary = maybe_tag_gender(records, out)
print(f" distribution: {summary}")
else:
for r in records:
r.setdefault("gender", None)
# If --shrink was NOT used and somehow id >= count rows are still in
# `existing` (which can only happen if the early gate was bypassed),
# carry them forward so we don't quietly drop them.
if not args.shrink:
for rid, row in existing.items():
if rid >= args.count and rid not in {r["id"] for r in records}:
records.append(row)
records.sort(key=lambda r: r.get("id", 0))
# Strip transient flags before persisting
for r in records:
r.pop("cached", None)
r.pop("error", None)
# Atomic write — if a re-run is interrupted, manifest stays intact.
tmp = manifest + ".tmp"
with open(tmp, "w") as f:
for r in records:
f.write(json.dumps(r) + "\n")
os.replace(tmp, manifest)
print(f"\nManifest: {manifest} ({len(records)} entries)")
# Quick checksum manifest for downstream debugging
h = hashlib.sha256()
for r in records:
h.update(r["file"].encode())
h.update(b"|")
h.update((r.get("gender") or "?").encode())
print(f"Pool fingerprint (sha256): {h.hexdigest()[:16]}")
if __name__ == "__main__":
main()

230
scripts/staffing/render_role_pool.py Normal file
View File

@ -0,0 +1,230 @@
#!/usr/bin/env python3
"""
render_role_pool.py — pre-render a role-aware face pool by hitting
serve_imagegen.py (localhost:3600/generate) with prompts pulled from
the bun server's /headshots/_scenes endpoint (single source of truth
for SCENES + SCENES_VERSION).
Layout:
data/headshots_role_pool/
{band}/
{gender}_{race}/
face_00.webp
face_01.webp
...
manifest.jsonl
Each entry in manifest.jsonl:
{"band": "warehouse", "gender": "man", "race": "caucasian",
"file": "warehouse/man_caucasian/face_03.webp",
"seed": 184729338, "scenes_version": "v1"}
Idempotent: a file at the target path is skipped. Re-run with --force
to regenerate. SCENES_VERSION is captured per render so the server's
pool route can refuse stale renders if the version drifts.
"""
from __future__ import annotations
import argparse
import base64
import json
import os
import sys
import time
import urllib.request
import urllib.error
DEFAULT_BANDS = ["warehouse", "production", "trades", "driver", "lead"]
DEFAULT_GENDERS = ["man", "woman"]
DEFAULT_RACES = ["caucasian", "east_asian", "south_asian", "middle_eastern", "black", "hispanic"]
def race_text(r: str) -> str:
return {
"caucasian": "",
"east_asian": "East Asian",
"south_asian": "South Asian",
"middle_eastern": "Middle Eastern",
"black": "Black",
"hispanic": "Hispanic",
}.get(r, "")
def fetch_scenes(mcp_url: str) -> tuple[str, dict]:
"""Pull canonical SCENES from the bun server. Single source of truth."""
req = urllib.request.Request(f"{mcp_url}/headshots/_scenes")
with urllib.request.urlopen(req, timeout=10) as resp:
data = json.loads(resp.read())
return data["version"], data["scenes"]
def render(comfy_url: str, prompt: str, seed: int, steps: int, timeout: int, dim: int) -> bytes | None:
payload = json.dumps({
"prompt": prompt,
"width": dim,
"height": dim,
"steps": steps,
"seed": seed,
}).encode()
req = urllib.request.Request(
f"{comfy_url}/generate",
data=payload,
headers={"Content-Type": "application/json"},
)
try:
with urllib.request.urlopen(req, timeout=timeout) as resp:
data = json.loads(resp.read())
except urllib.error.HTTPError as e:
print(f" HTTP {e.code} from comfy: {e.read()[:200]}", file=sys.stderr)
return None
except Exception as e:
print(f" comfy error: {type(e).__name__}: {e}", file=sys.stderr)
return None
img_b64 = data.get("image")
if not img_b64:
print(f" comfy response missing 'image' field: {list(data.keys())}", file=sys.stderr)
return None
return base64.b64decode(img_b64)
def main():
p = argparse.ArgumentParser()
p.add_argument("--out", default=os.path.join(os.path.dirname(__file__), "..", "..", "data", "headshots_role_pool"))
p.add_argument("--per-bucket", type=int, default=10, help="how many faces per (band × gender × race)")
p.add_argument("--mcp", default="http://localhost:3700")
p.add_argument("--comfy", default="http://localhost:3600")
p.add_argument("--steps", type=int, default=8)
p.add_argument("--bands", nargs="*", default=DEFAULT_BANDS)
p.add_argument("--genders", nargs="*", default=DEFAULT_GENDERS)
p.add_argument("--races", nargs="*", default=DEFAULT_RACES)
p.add_argument("--force", action="store_true", help="regenerate existing files")
p.add_argument("--age", type=int, default=32)
p.add_argument("--timeout", type=int, default=120, help="per-render timeout (1024² takes ~5s on A4000)")
p.add_argument("--dim", type=int, default=1024, help="square render dimension (v2 default 1024, v1 was 512)")
args = p.parse_args()
out_root = os.path.realpath(args.out)
os.makedirs(out_root, exist_ok=True)
print(f"Fetching canonical SCENES from {args.mcp}/headshots/_scenes…")
try:
version, scenes = fetch_scenes(args.mcp)
except Exception as e:
print(f"FATAL: could not fetch scenes ({e}). Is the mcp-server up?", file=sys.stderr)
sys.exit(1)
print(f" SCENES_VERSION={version}, {len(scenes)} bands available: {list(scenes.keys())}")
# v2+ files live at {out}/{version}/{band}/{g}_{r}/face_NN.webp.
# v1 lived at {out}/{band}/... — keep that layout intact for
# rollback; the server route reads both and prefers current.
out = out_root if version == "v1" else os.path.join(out_root, version)
os.makedirs(out, exist_ok=True)
print(f" writing to: {out}")
print(f" render dim: {args.dim}×{args.dim}")
# Reject any --bands not in the server's SCENES
unknown = [b for b in args.bands if b not in scenes]
if unknown:
print(f"FATAL: unknown bands {unknown}. Server has: {list(scenes.keys())}", file=sys.stderr)
sys.exit(1)
manifest_rows = []
todo = [
(band, g, r, n)
for band in args.bands
for g in args.genders
for r in args.races
for n in range(args.per_bucket)
]
print(f"\nPlanning: {len(todo)} renders ({len(args.bands)} bands × {len(args.genders)} genders × {len(args.races)} races × {args.per_bucket} faces).")
print(f"Estimated GPU time at 1.5s/render = {len(todo) * 1.5 / 60:.1f} min.\n")
t0 = time.time()
rendered = 0
skipped = 0
failed = 0
for i, (band, g, r, n) in enumerate(todo):
bucket_dir = os.path.join(out, band, f"{g}_{r}")
os.makedirs(bucket_dir, exist_ok=True)
fname = f"face_{n:02d}.webp"
full = os.path.join(bucket_dir, fname)
rel = os.path.relpath(full, out)
if os.path.exists(full) and os.path.getsize(full) > 1024 and not args.force:
skipped += 1
manifest_rows.append({
"band": band, "gender": g, "race": r, "file": rel,
"seed": None, "scenes_version": version, "cached": True,
})
continue
scene_def = scenes[band]
scene_clause = scene_def["scene"]
race_clause = race_text(r)
gender_clause = g # "man" / "woman"
# Match the bun server's prompt builder exactly. If you tweak
# one, tweak the other (or factor a /prompt-builder endpoint).
# The {role} slot is intentionally a band-typical title here
# — the pre-rendered face is shared across roles in the same
# band, so we use the band's archetypal role. Specific roles
# still hit the on-demand /headshots/generate/:key path with
# their actual title.
archetype_role = {
"warehouse": "warehouse worker",
"production": "production worker",
"trades": "skilled tradesperson",
"driver": "delivery driver",
"lead": "shift supervisor",
}.get(band, "warehouse worker")
prompt = (
f"professional headshot portrait of a {args.age}-year-old "
f"{race_clause} {gender_clause} {archetype_role}, {scene_clause}, "
f"neutral confident expression, sharp focus, photorealistic"
)
# Deterministic seed per slot — same (band, g, r, n) always
# gets the same face. Mixing scenes_version means a SCENES
# tweak shifts every face slightly; that's the right behavior
# (it's how cache invalidation propagates to the pool too).
seed_str = f"{band}|{g}|{r}|{n}|{version}"
seed_h = 5381
for ch in seed_str:
seed_h = ((seed_h << 5) + seed_h + ord(ch)) & 0x7fffffff
seed = seed_h
bytes_ = render(args.comfy, prompt, seed, args.steps, args.timeout, args.dim)
if bytes_ is None:
failed += 1
continue
with open(full, "wb") as f:
f.write(bytes_)
rendered += 1
manifest_rows.append({
"band": band, "gender": g, "race": r, "file": rel,
"seed": seed, "scenes_version": version, "cached": False,
})
if (i + 1) % 10 == 0 or (i + 1) == len(todo):
elapsed = time.time() - t0
done = i + 1
rate = done / elapsed if elapsed > 0 else 0
eta = (len(todo) - done) / rate if rate > 0 else 0
print(f" [{done}/{len(todo)}] rendered={rendered} skipped={skipped} failed={failed} "
f"rate={rate:.2f}/s eta={eta:.0f}s")
# Atomic manifest write
manifest_path = os.path.join(out, "manifest.jsonl")
tmp = manifest_path + ".tmp"
with open(tmp, "w") as f:
for row in manifest_rows:
f.write(json.dumps(row) + "\n")
os.replace(tmp, manifest_path)
print(f"\nDone. {rendered} new, {skipped} cached, {failed} failed in {time.time()-t0:.1f}s")
print(f"Manifest: {manifest_path} ({len(manifest_rows)} entries)")
print(f"\nNext: poke {args.mcp}/headshots/__reload to pick up the new pool.")
if __name__ == "__main__":
main()

169
scripts/staffing/tag_face_pool.py Normal file
View File

@ -0,0 +1,169 @@
#!/usr/bin/env python3
"""
tag_face_pool.py — run deepface gender + race classification over the
synthetic face pool produced by fetch_face_pool.py and rewrite
manifest.jsonl with `gender` (man / woman) and `race` (asian / black /
hispanic / indian / middle_eastern / white) tags.
Run with the venv that has deepface installed:
/home/profit/.local/share/deepface-venv/bin/python \
scripts/staffing/tag_face_pool.py
Idempotent: rows that already have BOTH gender and race tagged are
skipped. Pass --force to re-tag everything.
Mapping deepface buckets → /headshots/ ?e= values:
asian → split by manual region (deepface doesn't differentiate
East / South Asian; we lump as 'east_asian' since the
StyleGAN training set leans East Asian)
indian → south_asian
middle eastern → middle_eastern
black → black
hispanic → hispanic
white → caucasian
"""
from __future__ import annotations
import argparse
import json
import os
import sys
import time
DEEPFACE_RACE_TO_HINT = {
"asian": "east_asian",
"indian": "south_asian",
"middle eastern": "middle_eastern",
"black": "black",
"latino hispanic": "hispanic",
"hispanic": "hispanic",
"white": "caucasian",
}
def main():
p = argparse.ArgumentParser()
p.add_argument(
"--out",
default=os.path.join(os.path.dirname(__file__), "..", "..", "data", "headshots"),
)
p.add_argument("--force", action="store_true", help="re-tag rows that already have gender+race")
p.add_argument("--limit", type=int, default=0, help="cap how many faces to process this run (0 = all)")
p.add_argument("--min-age", type=int, default=22, help="exclude faces estimated below this age (kids/teens). Staffing context = legal-age workers only.")
args = p.parse_args()
out = os.path.realpath(args.out)
manifest_path = os.path.join(out, "manifest.jsonl")
if not os.path.exists(manifest_path):
print(f"manifest not found: {manifest_path}", file=sys.stderr)
sys.exit(1)
print(f"loading deepface (cold start ~10-15s for first model build)…")
from deepface import DeepFace # type: ignore
rows = []
with open(manifest_path) as f:
for line in f:
line = line.strip()
if not line:
continue
rows.append(json.loads(line))
print(f"manifest: {len(rows)} rows")
todo = [
r for r in rows
if args.force or r.get("gender") is None or r.get("race") is None or r.get("age") is None
]
if args.limit > 0:
todo = todo[: args.limit]
print(f"to tag: {len(todo)} faces")
if not todo:
print("nothing to do.")
return
counts_g = {}
counts_r = {}
failed = 0
t0 = time.time()
for i, r in enumerate(todo):
full = os.path.join(out, r["file"])
try:
ana = DeepFace.analyze(
img_path=full,
actions=["gender", "race", "age"],
enforce_detection=False,
silent=True,
)
if isinstance(ana, list):
ana = ana[0] if ana else {}
g_raw = (ana.get("dominant_gender") or "").lower().strip()
r["gender"] = (
"man" if g_raw.startswith("man") else
"woman" if g_raw.startswith("woman") else
None
)
r_raw = (ana.get("dominant_race") or "").lower().strip()
r["race"] = DEEPFACE_RACE_TO_HINT.get(r_raw, None)
if r["race"] is None and r_raw:
r["race_raw"] = r_raw
# Age estimation — exclude minors / teens. Staffing context
# uses adult workers only. Threshold is 22 by default
# (legal + a buffer because age estimation is noisy).
try:
age = int(round(float(ana.get("age") or 0)))
except Exception:
age = 0
r["age"] = age
if age and age < args.min_age:
r["excluded"] = "minor"
else:
r.pop("excluded", None)
counts_g[r["gender"] or "unknown"] = counts_g.get(r["gender"] or "unknown", 0) + 1
counts_r[r["race"] or r_raw or "unknown"] = counts_r.get(r["race"] or r_raw or "unknown", 0) + 1
except Exception as e:
r["tag_error"] = f"{type(e).__name__}: {e}"
failed += 1
if (i + 1) % 25 == 0 or (i + 1) == len(todo):
elapsed = time.time() - t0
rate = (i + 1) / elapsed if elapsed > 0 else 0
eta = (len(todo) - i - 1) / rate if rate > 0 else 0
print(f" [{i+1}/{len(todo)}] rate={rate:.1f}/s eta={eta:.0f}s failed={failed}")
print(f" gender: {counts_g}")
print(f" race : {counts_r}")
# Write updated manifest atomically
tmp = manifest_path + ".tmp"
with open(tmp, "w") as f:
for r in rows:
f.write(json.dumps(r) + "\n")
os.replace(tmp, manifest_path)
final_g = {}
final_r = {}
excluded = 0
age_hist = {"<18": 0, "18-22": 0, "22-30": 0, "30-40": 0, "40-50": 0, "50-60": 0, "60+": 0, "unknown": 0}
for r in rows:
if r.get("excluded"):
excluded += 1
continue
final_g[r.get("gender") or "untagged"] = final_g.get(r.get("gender") or "untagged", 0) + 1
final_r[r.get("race") or "untagged"] = final_r.get(r.get("race") or "untagged", 0) + 1
a = r.get("age") or 0
if a == 0: age_hist["unknown"] += 1
elif a < 18: age_hist["<18"] += 1
elif a < 22: age_hist["18-22"] += 1
elif a < 30: age_hist["22-30"] += 1
elif a < 40: age_hist["30-40"] += 1
elif a < 50: age_hist["40-50"] += 1
elif a < 60: age_hist["50-60"] += 1
else: age_hist["60+"] += 1
print(f"\nDone. {len(rows)} rows, {excluded} excluded as <{args.min_age}, {failed} tag errors, {time.time()-t0:.1f}s")
print(f" final gender: {final_g}")
print(f" final race : {final_r}")
print(f" age dist : {age_hist}")
print(f"\nNext: poke /headshots/__reload to refresh the in-memory pool.")
if __name__ == "__main__":
main()

385
sidecar/sidecar/lab_ui.py Normal file
View File

@ -0,0 +1,385 @@
"""Pipeline Lab notebook UI — served as a single HTML page.
Note: innerHTML usage in this file is intentional for building the UI.
All user-supplied text is escaped through the esc() function before insertion.
The only values rendered via innerHTML are pre-formatted HTML strings with
escaped user content — no raw user input is ever injected unescaped.
"""
from fastapi import APIRouter
from fastapi.responses import HTMLResponse
router = APIRouter()
def _get_lab_html() -> str:
"""Return the Pipeline Lab HTML. Separated into a function for clarity."""
# The HTML is a self-contained notebook UI.
# All user-facing text is escaped via the esc() JS function.
return r"""<!DOCTYPE html>
<html lang="en"><head>
<meta charset="UTF-8"><meta name="viewport" content="width=device-width,initial-scale=1.0">
<title>Pipeline Lab — Lakehouse</title>
<style>
:root{--bg:#08090c;--surface:rgba(14,16,22,0.9);--border:#2a2d35;--text:#e8e6e3;--text2:#7a7872;--accent:#4ade80;--gold:#e2b55a;--red:#e05252;--blue:#5b9cf5;--purple:#c084fc}
*{box-sizing:border-box;margin:0;padding:0}
body{font-family:'SF Mono','Menlo','Consolas',monospace;background:var(--bg);color:var(--text);min-height:100vh;padding:20px 28px;font-size:13px}
h1{font-size:18px;font-weight:700;margin-bottom:4px}h1 span{color:var(--accent)}
.subtitle{color:var(--text2);font-size:11px;margin-bottom:20px}
.cells{display:flex;flex-direction:column;gap:12px;max-width:1100px}
.cell{background:var(--surface);border:1px solid var(--border);border-radius:4px;overflow:hidden}
.cell.running{border-color:var(--gold)}
.cell-header{display:flex;align-items:center;gap:8px;padding:8px 12px;border-bottom:1px solid var(--border);font-size:10px;text-transform:uppercase;letter-spacing:1px;color:var(--text2)}
.cell-type{font-weight:700}
.cell-time{margin-left:auto;color:var(--text2)}
.cell-input{padding:12px;background:rgba(0,0,0,0.3)}
.cell-input textarea{width:100%;min-height:60px;background:transparent;border:none;color:var(--text);font-family:inherit;font-size:13px;resize:vertical;outline:none;line-height:1.6}
.cell-output{padding:12px;font-size:12px;line-height:1.6;white-space:pre-wrap;max-height:400px;overflow-y:auto;display:none}
.cell-output.has-data{display:block;border-top:1px solid var(--border)}
.toolbar{display:flex;gap:6px;padding:8px 12px;border-top:1px solid var(--border);flex-wrap:wrap}
.btn{font-family:inherit;font-size:10px;text-transform:uppercase;letter-spacing:0.5px;padding:5px 12px;border:1px solid var(--border);border-radius:3px;background:transparent;color:var(--text2);cursor:pointer}
.btn:hover{border-color:var(--accent);color:var(--accent)}
.btn.primary{border-color:var(--accent);color:var(--accent);background:rgba(74,222,128,0.06)}
.btn.gold{border-color:var(--gold);color:var(--gold)}
.btn.blue{border-color:var(--blue);color:var(--blue)}
.btn.purple{border-color:var(--purple);color:var(--purple)}
.btn.red{border-color:var(--red);color:var(--red)}
.top-bar{display:flex;gap:8px;margin-bottom:16px;align-items:center;flex-wrap:wrap}
.status-bar{display:flex;gap:12px;padding:8px 12px;background:var(--surface);border:1px solid var(--border);border-radius:4px;margin-bottom:16px;font-size:10px;color:var(--text2)}
.stat{display:flex;align-items:center;gap:4px}.stat b{color:var(--text)}
.result-row{display:flex;gap:8px;padding:6px 8px;border-bottom:1px solid rgba(42,45,53,0.3);align-items:center;font-size:11px}
.result-row:last-child{border-bottom:none}
.score-bar{width:60px;height:5px;background:rgba(0,0,0,0.2);border-radius:3px;overflow:hidden}
.score-fill{height:100%;border-radius:3px}
.benchmark-grid{display:grid;grid-template-columns:1fr 1fr;gap:12px;margin-top:8px}
.bench-col{background:rgba(0,0,0,0.2);border-radius:3px;padding:10px}
.bench-label{font-size:10px;text-transform:uppercase;letter-spacing:1px;margin-bottom:6px;font-weight:700}
.threshold-slider{display:flex;align-items:center;gap:8px;padding:0 12px;margin:4px 0}
.threshold-slider input[type=range]{flex:1;accent-color:var(--accent)}
.threshold-slider .val{font-weight:700;min-width:36px;text-align:right}
</style></head><body>
<h1><span>Pipeline Lab</span> // Lakehouse</h1>
<div class="subtitle">Embedding-based screening vs LLM classification &#x2014; iterative experimentation</div>
<div class="status-bar" id="status-bar">
<div class="stat"><span>Exemplars:</span> <b id="st-exemplars">0</b></div>
<div class="stat"><span>Categories:</span> <b id="st-categories">0</b></div>
<div class="stat"><span>Pipelines:</span> <b id="st-pipelines">0</b></div>
<div class="stat" style="margin-left:auto"><span>Sidecar:</span> <b id="st-health" style="color:var(--text2)">...</b></div>
</div>
<div class="top-bar">
<button class="btn primary" onclick="addCell('exemplars')">+ Exemplars</button>
<button class="btn gold" onclick="addCell('screen')">+ Screen</button>
<button class="btn blue" onclick="addCell('classify')">+ Classify</button>
<button class="btn purple" onclick="addCell('benchmark')">+ Benchmark</button>
<button class="btn" onclick="addCell('similarity')">+ Similarity</button>
<button class="btn" onclick="addCell('generate')">+ Generate</button>
<button class="btn" onclick="addCell('pipeline')">+ Pipeline</button>
<span style="flex:1"></span>
<button class="btn red" onclick="clearCells()">Clear All</button>
</div>
<div class="cells" id="cells"></div>
<script>
var BASE = '';
var cellCounter = 0;
function esc(t){var d=document.createElement('span');d.textContent=String(t);return d.innerHTML}
async function api(path, body) {
var opts = body ? {method:'POST', headers:{'Content-Type':'application/json'}, body:JSON.stringify(body)} : {};
var r = await fetch(BASE + '/lab' + path, opts);
return r.json();
}
async function refreshStatus() {
try {
var ex = await api('/exemplars');
var pl = await api('/pipelines');
var h = await fetch(BASE + '/health').then(function(r){return r.json()});
document.getElementById('st-exemplars').textContent = ex.total || 0;
document.getElementById('st-categories').textContent = Object.keys(ex.categories || {}).length;
document.getElementById('st-pipelines').textContent = (pl.pipelines || []).length;
document.getElementById('st-health').textContent = h.status || 'ok';
document.getElementById('st-health').style.color = 'var(--accent)';
} catch(e) {
document.getElementById('st-health').textContent = 'error';
document.getElementById('st-health').style.color = 'var(--red)';
}
}
function addCell(type) {
var id = 'cell-' + (++cellCounter);
var cells = document.getElementById('cells');
var cell = document.createElement('div'); cell.className = 'cell'; cell.id = id;
var colors = {exemplars:'var(--accent)',screen:'var(--gold)',classify:'var(--blue)',benchmark:'var(--purple)',similarity:'var(--text2)',generate:'var(--text2)',pipeline:'var(--accent)'};
var labels = {exemplars:'EXEMPLARS',screen:'SCREEN',classify:'CLASSIFY (LLM)',benchmark:'BENCHMARK A/B',similarity:'SIMILARITY',generate:'GENERATE',pipeline:'PIPELINE'};
var placeholders = {
exemplars:'Category: decision\n---\nWe decided to use Parquet for all storage\nThe team chose React over Vue\nArchitecture decision: microservices',
screen:'Enter texts to classify via embedding similarity (one per line):\n\nWe decided to migrate to PostgreSQL\nThe weather is nice today\nArchitecture: chose event sourcing over CRUD',
classify:'Enter texts to classify via LLM (one per line):\n\nWe decided to migrate to PostgreSQL\nThe weather is nice today',
benchmark:'Enter texts to benchmark (one per line):\n\nWe decided to use Kubernetes for orchestration\nThe new hire starts Monday\nTechnical debt: refactor the auth module\nLunch menu looks good today',
similarity:'Enter texts to compare pairwise (one per line):\n\nWe chose React for the frontend\nReact was selected as our UI framework\nThe database uses PostgreSQL',
generate:'Enter a prompt for the LLM...',
pipeline:'Pipeline name: my-extraction\n---\nscreen | threshold=0.6\nclassify\nextract | prompt=Extract the key decision and its rationale\nvalidate | dedup_threshold=0.9'
};
var color = colors[type] || 'var(--text2)';
var label = labels[type] || type.toUpperCase();
var ph = placeholders[type] || '';
// Build cell using DOM methods
var header = document.createElement('div'); header.className = 'cell-header';
var typeSpan = document.createElement('span'); typeSpan.className = 'cell-type'; typeSpan.style.color = color; typeSpan.textContent = label; header.appendChild(typeSpan);
var numSpan = document.createElement('span'); numSpan.textContent = 'Cell #' + cellCounter; header.appendChild(numSpan);
var timeSpan = document.createElement('span'); timeSpan.className = 'cell-time'; timeSpan.id = id + '-time'; header.appendChild(timeSpan);
cell.appendChild(header);
var inputDiv = document.createElement('div'); inputDiv.className = 'cell-input';
var textarea = document.createElement('textarea'); textarea.id = id + '-input'; textarea.placeholder = ph; textarea.value = ph;
inputDiv.appendChild(textarea); cell.appendChild(inputDiv);
if (type === 'screen' || type === 'benchmark') {
var slider = document.createElement('div'); slider.className = 'threshold-slider';
var slLabel = document.createElement('span'); slLabel.style.cssText = 'font-size:10px;color:var(--text2)'; slLabel.textContent = 'Threshold:'; slider.appendChild(slLabel);
var range = document.createElement('input'); range.type = 'range'; range.min = '0.3'; range.max = '0.95'; range.step = '0.05'; range.value = '0.65'; range.id = id + '-threshold';
var valSpan = document.createElement('span'); valSpan.className = 'val'; valSpan.textContent = '0.65';
range.oninput = function() { valSpan.textContent = this.value; };
slider.appendChild(range); slider.appendChild(valSpan); cell.appendChild(slider);
}
var outputDiv = document.createElement('div'); outputDiv.className = 'cell-output'; outputDiv.id = id + '-output';
cell.appendChild(outputDiv);
var tb = document.createElement('div'); tb.className = 'toolbar';
var runBtn = document.createElement('button'); runBtn.className = 'btn primary'; runBtn.textContent = 'Run';
runBtn.onclick = function() { runCell(id, type); }; tb.appendChild(runBtn);
var rmBtn = document.createElement('button'); rmBtn.className = 'btn red'; rmBtn.textContent = 'Remove';
rmBtn.onclick = function() { removeCell(id); }; tb.appendChild(rmBtn);
cell.appendChild(tb);
cells.appendChild(cell);
textarea.focus();
return id;
}
function removeCell(id) { var el = document.getElementById(id); if (el) el.remove(); }
function clearCells() { document.getElementById('cells').textContent = ''; cellCounter = 0; }
function parseLines(text) { return text.split('\n').map(function(l){return l.trim()}).filter(function(l){return l && l.charAt(0) !== '#'}); }
async function runCell(id, type) {
var cell = document.getElementById(id);
var input = document.getElementById(id+'-input').value;
var output = document.getElementById(id+'-output');
var timeEl = document.getElementById(id+'-time');
cell.classList.add('running');
output.className = 'cell-output has-data';
output.textContent = 'Running...';
try {
var t0 = performance.now();
var result;
if (type === 'exemplars') {
var parts = input.split('---');
var catLine = (parts[0] || '').trim();
var category = catLine.replace(/^category:\s*/i, '').trim().toLowerCase();
var texts = parseLines(parts.slice(1).join('\n'));
if (!category || !texts.length) { output.textContent = 'Format: Category: name\\n---\\ntext1\\ntext2'; return; }
result = await api('/exemplars', {category: category, texts: texts});
output.textContent = 'Added ' + result.added + ' exemplars to "' + result.category + '" (total: ' + result.total + ')';
output.style.color = 'var(--accent)';
refreshStatus();
}
else if (type === 'screen') {
var texts = parseLines(input);
var threshold = parseFloat((document.getElementById(id+'-threshold') || {}).value || '0.65');
result = await api('/screen', {texts: texts, threshold: threshold});
renderScreenResults(output, result, threshold);
}
else if (type === 'classify') {
var texts = parseLines(input);
result = await api('/classify', {texts: texts});
renderClassifyResults(output, result);
}
else if (type === 'benchmark') {
var texts = parseLines(input);
var threshold = parseFloat((document.getElementById(id+'-threshold') || {}).value || '0.65');
result = await api('/benchmark', {texts: texts, threshold: threshold});
renderBenchmark(output, result);
}
else if (type === 'similarity') {
var texts = parseLines(input);
result = await api('/cell', {action:'similarity', texts: texts});
renderSimilarityMatrix(output, result);
}
else if (type === 'generate') {
result = await api('/cell', {action:'generate', text: input});
output.textContent = result.text || '(empty)';
}
else if (type === 'pipeline') {
var parts = input.split('---');
var nameLine = (parts[0] || '').trim();
var pName = nameLine.replace(/^pipeline\s*name:\s*/i, '').trim();
var stageLines = parseLines(parts.slice(1).join('\n'));
var stages = stageLines.map(function(line) {
var ps = line.split('|').map(function(s){return s.trim()});
var mode = ps[0];
var config = {};
ps.slice(1).forEach(function(p) {
var kv = p.split('='); if (kv.length===2) {
var v = kv[1].trim();
config[kv[0].trim()] = isNaN(parseFloat(v)) ? v : parseFloat(v);
}
});
return {name: mode, mode: mode, config: config};
});
await api('/pipelines', {name: pName, stages: stages, description: 'Created in Pipeline Lab'});
output.textContent = 'Pipeline "' + pName + '" saved (' + stages.length + ' stages). Use the API to run it: POST /lab/pipelines/run';
output.style.color = 'var(--accent)';
refreshStatus();
}
var elapsed = Math.round(performance.now() - t0);
timeEl.textContent = elapsed + 'ms' + (result && result.time_ms ? ' (server: '+result.time_ms+'ms)' : '');
} catch(e) {
output.textContent = 'Error: ' + e.message;
output.style.color = 'var(--red)';
} finally {
cell.classList.remove('running');
}
}
function renderScreenResults(el, results, threshold) {
el.textContent = '';
results.forEach(function(r) {
var row = document.createElement('div'); row.className = 'result-row';
var cat = document.createElement('span');
cat.style.cssText = 'min-width:80px;font-weight:700;color:' + (r.above_threshold ? 'var(--accent)' : 'var(--text2)');
cat.textContent = r.best_category || 'none'; row.appendChild(cat);
var sim = document.createElement('span'); sim.style.cssText = 'min-width:50px;font-weight:700';
sim.textContent = (r.similarity * 100).toFixed(1) + '%';
sim.style.color = r.similarity >= 0.7 ? 'var(--accent)' : r.similarity >= threshold ? 'var(--gold)' : 'var(--text2)';
row.appendChild(sim);
var bar = document.createElement('div'); bar.className = 'score-bar';
var fill = document.createElement('div'); fill.className = 'score-fill';
fill.style.width = (r.similarity * 100) + '%';
fill.style.background = r.similarity >= 0.7 ? 'var(--accent)' : r.similarity >= threshold ? 'var(--gold)' : 'var(--red)';
bar.appendChild(fill); row.appendChild(bar);
var txt = document.createElement('span'); txt.style.cssText = 'flex:1;overflow:hidden;text-overflow:ellipsis;white-space:nowrap';
txt.textContent = r.text; row.appendChild(txt);
var badge = document.createElement('span');
badge.style.cssText = 'font-size:9px;padding:2px 6px;border-radius:2px;border:1px solid;' +
(r.above_threshold ? 'color:var(--accent);border-color:var(--accent)' : 'color:var(--text2);border-color:var(--border)');
badge.textContent = r.above_threshold ? 'PASS' : 'FILTERED'; row.appendChild(badge);
el.appendChild(row);
});
}
function renderClassifyResults(el, results) {
el.textContent = '';
results.forEach(function(r) {
var row = document.createElement('div'); row.className = 'result-row';
var cat = document.createElement('span'); cat.style.cssText = 'min-width:80px;font-weight:700;color:var(--blue)';
cat.textContent = r.category; row.appendChild(cat);
var conf = document.createElement('span');
conf.style.cssText = 'min-width:50px;font-size:10px;color:' + (r.confidence==='high'?'var(--accent)':r.confidence==='medium'?'var(--gold)':'var(--text2)');
conf.textContent = r.confidence; row.appendChild(conf);
var txt = document.createElement('span'); txt.style.flex = '1'; txt.textContent = r.text; row.appendChild(txt);
el.appendChild(row);
});
}
function renderBenchmark(el, result) {
el.textContent = '';
// Summary stats (using safe DOM construction)
var summary = document.createElement('div'); summary.style.cssText = 'display:flex;gap:16px;margin-bottom:12px;flex-wrap:wrap';
var stats = [
['Agreement', (result.agreement_rate*100).toFixed(1)+'%', result.agreement_rate>=0.8?'var(--accent)':'var(--gold)'],
['Speedup', result.speedup+'x', result.speedup>=2?'var(--accent)':'var(--text)'],
['Embed', result.embed_time_ms+'ms', 'var(--gold)'],
['LLM', result.llm_time_ms+'ms', 'var(--blue)'],
['Hybrid est.', result.hybrid_estimated_ms+'ms', 'var(--accent)'],
['Screened out', result.texts_screened_out+'/'+result.total_texts, 'var(--purple)']
];
stats.forEach(function(s) {
var box = document.createElement('div'); box.style.cssText = 'background:rgba(0,0,0,0.2);padding:6px 10px;border-radius:3px;text-align:center';
var lbl = document.createElement('div'); lbl.style.cssText = 'font-size:9px;color:var(--text2);text-transform:uppercase;letter-spacing:0.5px'; lbl.textContent = s[0]; box.appendChild(lbl);
var val = document.createElement('div'); val.style.cssText = 'font-size:16px;font-weight:700;color:'+s[2]; val.textContent = s[1]; box.appendChild(val);
summary.appendChild(box);
});
el.appendChild(summary);
// Side-by-side comparison
var grid = document.createElement('div'); grid.style.cssText = 'display:grid;grid-template-columns:1fr 1fr;gap:12px;margin-top:8px';
// Embed column
var leftCol = document.createElement('div'); leftCol.style.cssText = 'background:rgba(0,0,0,0.2);border-radius:3px;padding:10px';
var leftTitle = document.createElement('div'); leftTitle.style.cssText = 'font-size:10px;text-transform:uppercase;letter-spacing:1px;margin-bottom:6px;font-weight:700;color:var(--gold)';
leftTitle.textContent = 'EMBEDDING SCREENING (' + result.embed_time_ms + 'ms)'; leftCol.appendChild(leftTitle);
(result.embed_results||[]).forEach(function(r) {
var row = document.createElement('div'); row.style.cssText = 'font-size:11px;padding:3px 0;display:flex;gap:6px;align-items:center';
var c = document.createElement('span'); c.style.cssText = 'min-width:60px;font-weight:700;color:'+(r.above_threshold?'var(--accent)':'var(--text2)'); c.textContent = r.best_category||'none'; row.appendChild(c);
var s = document.createElement('span'); s.style.cssText = 'min-width:40px;color:var(--text2)'; s.textContent = (r.similarity*100).toFixed(0)+'%'; row.appendChild(s);
var t = document.createElement('span'); t.style.cssText = 'flex:1;overflow:hidden;text-overflow:ellipsis;white-space:nowrap'; t.textContent = r.text; row.appendChild(t);
leftCol.appendChild(row);
});
grid.appendChild(leftCol);
// LLM column
var rightCol = document.createElement('div'); rightCol.style.cssText = 'background:rgba(0,0,0,0.2);border-radius:3px;padding:10px';
var rightTitle = document.createElement('div'); rightTitle.style.cssText = 'font-size:10px;text-transform:uppercase;letter-spacing:1px;margin-bottom:6px;font-weight:700;color:var(--blue)';
rightTitle.textContent = 'LLM CLASSIFICATION (' + result.llm_time_ms + 'ms)'; rightCol.appendChild(rightTitle);
(result.llm_results||[]).forEach(function(r) {
var row = document.createElement('div'); row.style.cssText = 'font-size:11px;padding:3px 0;display:flex;gap:6px;align-items:center';
var c = document.createElement('span'); c.style.cssText = 'min-width:60px;font-weight:700;color:var(--blue)'; c.textContent = r.category; row.appendChild(c);
var s = document.createElement('span'); s.style.cssText = 'min-width:40px;color:'+(r.confidence==='high'?'var(--accent)':'var(--text2)'); s.textContent = r.confidence; row.appendChild(s);
var t = document.createElement('span'); t.style.cssText = 'flex:1;overflow:hidden;text-overflow:ellipsis;white-space:nowrap'; t.textContent = r.text; row.appendChild(t);
rightCol.appendChild(row);
});
grid.appendChild(rightCol);
el.appendChild(grid);
}
function renderSimilarityMatrix(el, result) {
el.textContent = '';
var matrix = result.matrix || [];
var texts = result.texts || [];
if (!matrix.length) { el.textContent = 'No results'; return; }
var tbl = document.createElement('table'); tbl.style.cssText = 'border-collapse:collapse;font-size:11px;width:100%';
var hdr = document.createElement('tr');
var corner = document.createElement('th'); hdr.appendChild(corner);
texts.forEach(function(t) {
var th = document.createElement('th'); th.style.cssText = 'padding:4px;color:var(--text2);font-size:9px;max-width:100px;overflow:hidden;text-overflow:ellipsis;white-space:nowrap';
th.textContent = t.substring(0, 20); th.title = t; hdr.appendChild(th);
});
tbl.appendChild(hdr);
matrix.forEach(function(row, i) {
var tr = document.createElement('tr');
var td0 = document.createElement('td'); td0.style.cssText = 'padding:4px;color:var(--text2);font-size:9px;max-width:100px;overflow:hidden;text-overflow:ellipsis;white-space:nowrap';
td0.textContent = texts[i].substring(0, 20); tr.appendChild(td0);
row.forEach(function(v, j) {
var td = document.createElement('td');
var bg = i===j ? 'rgba(74,222,128,0.1)' : v>=0.8 ? 'rgba(74,222,128,0.15)' : v>=0.6 ? 'rgba(226,181,90,0.1)' : 'transparent';
td.style.cssText = 'padding:4px;text-align:center;font-weight:'+(v>=0.7?'700':'400')+';color:'+(v>=0.8?'var(--accent)':v>=0.6?'var(--gold)':'var(--text2)')+';background:'+bg;
td.textContent = v.toFixed(2); tr.appendChild(td);
});
tbl.appendChild(tr);
});
el.appendChild(tbl);
}
refreshStatus();
</script>
</body></html>"""
@router.get("", response_class=HTMLResponse)
async def lab_page():
return _get_lab_html()

503
sidecar/sidecar/pipeline_lab.py Normal file
View File

@ -0,0 +1,503 @@
"""Pipeline Lab — iterative embedding/LLM pipeline experimentation.
Provides:
- Exemplar-based embedding classification (fast screening)
- LLM-based classification (accurate but slow)
- A/B benchmarking between the two
- Pipeline definition and execution
- Notebook-style API for interactive experimentation
"""
import json
import math
import os
import time
from pathlib import Path
from typing import Optional
from fastapi import APIRouter, HTTPException
from fastapi.responses import HTMLResponse
from pydantic import BaseModel
from .ollama import client
router = APIRouter()
EMBED_MODEL = os.environ.get("EMBED_MODEL", "nomic-embed-text")
GEN_MODEL = os.environ.get("GEN_MODEL", "qwen2.5")
LAB_DIR = Path(os.environ.get("LAB_DIR", "./data/_pipeline_lab"))
LAB_DIR.mkdir(parents=True, exist_ok=True)
# ─── Vector math ─────────────────────────────────────────────
def cosine_similarity(a: list[float], b: list[float]) -> float:
dot = sum(x * y for x, y in zip(a, b))
norm_a = math.sqrt(sum(x * x for x in a))
norm_b = math.sqrt(sum(x * x for x in b))
if norm_a == 0 or norm_b == 0:
return 0.0
return dot / (norm_a * norm_b)
# ─── Exemplar store ──────────────────────────────────────────
# Exemplars are labeled text+embedding pairs used for classification.
# e.g. category="decision" texts=["We decided to use Parquet", "The team chose React"]
_exemplars: dict[str, list[dict]] = {} # category -> [{text, embedding}]
def _exemplar_file() -> Path:
return LAB_DIR / "exemplars.json"
def _load_exemplars():
global _exemplars
fp = _exemplar_file()
if fp.exists():
data = json.loads(fp.read_text())
_exemplars = data
return _exemplars
def _save_exemplars():
_exemplar_file().write_text(json.dumps(_exemplars, indent=2))
_load_exemplars()
# ─── Pipeline store ──────────────────────────────────────────
def _pipelines_dir() -> Path:
d = LAB_DIR / "pipelines"
d.mkdir(exist_ok=True)
return d
# ─── Embedding helper ────────────────────────────────────────
async def _embed_texts(texts: list[str], model: str = EMBED_MODEL) -> list[list[float]]:
embeddings = []
async with client() as c:
for text in texts:
resp = await c.post("/api/embed", json={"model": model, "input": text})
if resp.status_code != 200:
raise HTTPException(502, f"Ollama embed error: {resp.text}")
data = resp.json()
embeddings.extend(data.get("embeddings", []))
return embeddings
async def _generate(prompt: str, model: str = GEN_MODEL, temperature: float = 0.3) -> str:
async with client() as c:
resp = await c.post("/api/generate", json={
"model": model, "prompt": prompt, "stream": False,
"options": {"temperature": temperature, "num_predict": 1024}
})
if resp.status_code != 200:
raise HTTPException(502, f"Ollama generate error: {resp.text}")
return resp.json().get("response", "")
# ─── API: Exemplars ──────────────────────────────────────────
class ExemplarAdd(BaseModel):
category: str
texts: list[str]
class ExemplarList(BaseModel):
categories: dict[str, int] # category -> count
@router.post("/exemplars")
async def add_exemplars(req: ExemplarAdd):
"""Add labeled exemplar texts for a category. Embeddings generated automatically."""
category = req.category.strip().lower()
if not category or not req.texts:
raise HTTPException(400, "category and texts required")
embeddings = await _embed_texts(req.texts)
if category not in _exemplars:
_exemplars[category] = []
for text, emb in zip(req.texts, embeddings):
_exemplars[category].append({"text": text, "embedding": emb})
_save_exemplars()
return {"ok": True, "category": category, "added": len(req.texts),
"total": len(_exemplars[category])}
@router.get("/exemplars")
async def list_exemplars():
"""List all exemplar categories and counts."""
return {"categories": {k: len(v) for k, v in _exemplars.items()},
"total": sum(len(v) for v in _exemplars.values())}
@router.delete("/exemplars/{category}")
async def delete_exemplar_category(category: str):
if category in _exemplars:
del _exemplars[category]
_save_exemplars()
return {"ok": True}
# ─── API: Screen (embedding-based classification) ────────────
class ScreenRequest(BaseModel):
texts: list[str]
threshold: float = 0.65
top_k: int = 1
class ScreenResult(BaseModel):
text: str
best_category: str | None
similarity: float
above_threshold: bool
all_scores: dict[str, float]
@router.post("/screen", response_model=list[ScreenResult])
async def screen_texts(req: ScreenRequest):
"""Classify texts by cosine similarity to exemplar embeddings (fast path)."""
if not _exemplars:
raise HTTPException(400, "No exemplars defined. Add exemplars first.")
embeddings = await _embed_texts(req.texts)
results = []
for text, emb in zip(req.texts, embeddings):
category_scores = {}
for category, exemplar_list in _exemplars.items():
sims = [cosine_similarity(emb, ex["embedding"]) for ex in exemplar_list]
category_scores[category] = max(sims) if sims else 0.0
best_cat = max(category_scores, key=category_scores.get) if category_scores else None
best_sim = category_scores.get(best_cat, 0.0) if best_cat else 0.0
results.append(ScreenResult(
text=text[:200],
best_category=best_cat if best_sim >= req.threshold else None,
similarity=round(best_sim, 4),
above_threshold=best_sim >= req.threshold,
all_scores={k: round(v, 4) for k, v in sorted(category_scores.items(),
key=lambda x: x[1], reverse=True)},
))
return results
# ─── API: Classify (LLM-based classification) ────────────────
class ClassifyRequest(BaseModel):
texts: list[str]
categories: list[str] | None = None # if None, use exemplar category names
model: str | None = None
class ClassifyResult(BaseModel):
text: str
category: str
confidence: str
reasoning: str
@router.post("/classify", response_model=list[ClassifyResult])
async def classify_texts(req: ClassifyRequest):
"""Classify texts using LLM (slow but accurate path)."""
categories = req.categories or list(_exemplars.keys())
if not categories:
raise HTTPException(400, "No categories. Provide categories or add exemplars.")
model = req.model or GEN_MODEL
results = []
for text in req.texts:
prompt = (
f"Classify this text into exactly ONE of these categories: {', '.join(categories)}\n\n"
f"TEXT: {text[:500]}\n\n"
f"Respond with JSON: {{\"category\": \"...\", \"confidence\": \"high|medium|low\", "
f"\"reasoning\": \"one sentence\"}}"
)
raw = await _generate(prompt, model=model, temperature=0.1)
# Parse
try:
j_s, j_e = raw.find("{"), raw.rfind("}") + 1
parsed = json.loads(raw[j_s:j_e]) if j_s >= 0 and j_e > j_s else {}
except Exception:
parsed = {}
results.append(ClassifyResult(
text=text[:200],
category=parsed.get("category", "unknown"),
confidence=parsed.get("confidence", "low"),
reasoning=parsed.get("reasoning", raw[:200]),
))
return results
# ─── API: Benchmark (A/B comparison) ─────────────────────────
class BenchmarkRequest(BaseModel):
texts: list[str]
threshold: float = 0.65
model: str | None = None
class BenchmarkResult(BaseModel):
total_texts: int
# Embedding path
embed_time_ms: int
embed_results: list[dict]
# LLM path
llm_time_ms: int
llm_results: list[dict]
# Comparison
agreement_rate: float
speedup: float
texts_screened_out: int
texts_needing_llm: int
hybrid_estimated_ms: int
@router.post("/benchmark", response_model=BenchmarkResult)
async def benchmark(req: BenchmarkRequest):
"""Run same texts through embedding screening and LLM classification. Compare."""
if not _exemplars:
raise HTTPException(400, "No exemplars. Add exemplars first.")
categories = list(_exemplars.keys())
# Embedding path
t0 = time.monotonic()
embed_results = await screen_texts(ScreenRequest(
texts=req.texts, threshold=req.threshold
))
embed_ms = int((time.monotonic() - t0) * 1000)
# LLM path
t0 = time.monotonic()
llm_results = await classify_texts(ClassifyRequest(
texts=req.texts, categories=categories, model=req.model
))
llm_ms = int((time.monotonic() - t0) * 1000)
# Compare
agreements = 0
screened_out = 0
for er, lr in zip(embed_results, llm_results):
if not er.above_threshold:
screened_out += 1
if er.best_category == lr.category:
agreements += 1
needing_llm = len(req.texts) - screened_out
# Hybrid estimate: embed all + LLM only the uncertain ones
per_text_embed_ms = embed_ms / max(len(req.texts), 1)
per_text_llm_ms = llm_ms / max(len(req.texts), 1)
hybrid_ms = int(embed_ms + needing_llm * per_text_llm_ms)
return BenchmarkResult(
total_texts=len(req.texts),
embed_time_ms=embed_ms,
embed_results=[r.model_dump() for r in embed_results],
llm_time_ms=llm_ms,
llm_results=[r.model_dump() for r in llm_results],
agreement_rate=round(agreements / max(len(req.texts), 1), 3),
speedup=round(llm_ms / max(hybrid_ms, 1), 2),
texts_screened_out=screened_out,
texts_needing_llm=needing_llm,
hybrid_estimated_ms=hybrid_ms,
)
# ─── API: Pipeline definition & execution ────────────────────
class PipelineStage(BaseModel):
name: str
mode: str # "screen", "classify", "extract", "validate", "custom"
config: dict = {} # stage-specific config (threshold, prompt, etc.)
class PipelineDef(BaseModel):
name: str
stages: list[PipelineStage]
description: str = ""
class PipelineRunRequest(BaseModel):
pipeline_name: str
texts: list[str]
@router.post("/pipelines")
async def save_pipeline(pipeline: PipelineDef):
"""Save a pipeline definition."""
fp = _pipelines_dir() / f"{pipeline.name}.json"
fp.write_text(pipeline.model_dump_json(indent=2))
return {"ok": True, "name": pipeline.name}
@router.get("/pipelines")
async def list_pipelines():
"""List saved pipeline definitions."""
pipelines = []
for fp in _pipelines_dir().glob("*.json"):
try:
data = json.loads(fp.read_text())
pipelines.append({"name": data["name"], "stages": len(data["stages"]),
"description": data.get("description", "")})
except Exception:
pass
return {"pipelines": pipelines}
@router.get("/pipelines/{name}")
async def get_pipeline(name: str):
fp = _pipelines_dir() / f"{name}.json"
if not fp.exists():
raise HTTPException(404, "Pipeline not found")
return json.loads(fp.read_text())
@router.post("/pipelines/run")
async def run_pipeline(req: PipelineRunRequest):
"""Execute a pipeline on a set of texts. Returns per-stage results and timing."""
fp = _pipelines_dir() / f"{req.pipeline_name}.json"
if not fp.exists():
raise HTTPException(404, f"Pipeline '{req.pipeline_name}' not found")
pipeline = json.loads(fp.read_text())
results = {"pipeline": req.pipeline_name, "stages": [], "total_ms": 0}
current_texts = req.texts[:]
for stage_def in pipeline["stages"]:
stage_name = stage_def["name"]
mode = stage_def["mode"]
config = stage_def.get("config", {})
t0 = time.monotonic()
stage_result = {"name": stage_name, "mode": mode, "input_count": len(current_texts)}
if mode == "screen":
threshold = config.get("threshold", 0.65)
screen_res = await screen_texts(ScreenRequest(
texts=current_texts, threshold=threshold
))
passed = [r for r in screen_res if r.above_threshold]
stage_result["output_count"] = len(passed)
stage_result["filtered_out"] = len(current_texts) - len(passed)
stage_result["results"] = [r.model_dump() for r in screen_res]
# Pass only above-threshold texts to next stage
current_texts = [r.text for r in screen_res if r.above_threshold]
elif mode == "classify":
cls_res = await classify_texts(ClassifyRequest(
texts=current_texts,
categories=config.get("categories"),
model=config.get("model"),
))
stage_result["output_count"] = len(cls_res)
stage_result["results"] = [r.model_dump() for r in cls_res]
elif mode == "extract":
extract_prompt = config.get("prompt", "Extract key information from this text:")
extractions = []
for text in current_texts:
raw = await _generate(f"{extract_prompt}\n\nTEXT: {text[:800]}")
extractions.append({"text": text[:200], "extracted": raw})
stage_result["output_count"] = len(extractions)
stage_result["results"] = extractions
elif mode == "validate":
# Embedding-based dedup: find near-duplicate results
if len(current_texts) > 1:
embs = await _embed_texts(current_texts)
dupes = []
threshold = config.get("dedup_threshold", 0.92)
for i in range(len(embs)):
for j in range(i + 1, len(embs)):
sim = cosine_similarity(embs[i], embs[j])
if sim >= threshold:
dupes.append({"i": i, "j": j, "similarity": round(sim, 4),
"text_a": current_texts[i][:100],
"text_b": current_texts[j][:100]})
stage_result["duplicates_found"] = len(dupes)
stage_result["results"] = dupes
else:
stage_result["duplicates_found"] = 0
stage_result["results"] = []
stage_result["output_count"] = len(current_texts)
else:
stage_result["error"] = f"Unknown mode: {mode}"
stage_result["output_count"] = len(current_texts)
stage_ms = int((time.monotonic() - t0) * 1000)
stage_result["time_ms"] = stage_ms
results["stages"].append(stage_result)
results["total_ms"] += stage_ms
return results
# ─── API: REPL cell (free-form eval) ─────────────────────────
class CellRequest(BaseModel):
action: str # "embed", "generate", "similarity", "screen", "classify"
text: str = ""
texts: list[str] = []
params: dict = {}
@router.post("/cell")
async def run_cell(req: CellRequest):
"""Execute a single notebook cell. Flexible entry point for ad-hoc operations."""
t0 = time.monotonic()
result = {}
if req.action == "embed":
texts = req.texts or ([req.text] if req.text else [])
embs = await _embed_texts(texts)
result = {"embeddings_count": len(embs), "dimensions": len(embs[0]) if embs else 0,
"texts": texts}
elif req.action == "generate":
text = await _generate(req.text, **{k: v for k, v in req.params.items()
if k in ("model", "temperature")})
result = {"text": text}
elif req.action == "similarity":
if len(req.texts) < 2:
raise HTTPException(400, "Need at least 2 texts for similarity")
embs = await _embed_texts(req.texts)
matrix = []
for i in range(len(embs)):
row = []
for j in range(len(embs)):
row.append(round(cosine_similarity(embs[i], embs[j]), 4))
matrix.append(row)
result = {"matrix": matrix, "texts": [t[:80] for t in req.texts]}
elif req.action == "screen":
texts = req.texts or ([req.text] if req.text else [])
threshold = req.params.get("threshold", 0.65)
res = await screen_texts(ScreenRequest(texts=texts, threshold=threshold))
result = {"results": [r.model_dump() for r in res]}
elif req.action == "classify":
texts = req.texts or ([req.text] if req.text else [])
res = await classify_texts(ClassifyRequest(texts=texts))
result = {"results": [r.model_dump() for r in res]}
else:
raise HTTPException(400, f"Unknown action: {req.action}")
result["time_ms"] = int((time.monotonic() - t0) * 1000)
return result

90
tests/agent_test/PRD.md Normal file
View File

@ -0,0 +1,90 @@
# PRD: Chicago Permit Staffing Recommendation
## Mission
You are a staffing-intelligence assistant. Your job is to **analyze a Chicago building permit and produce a one-page staffing recommendation** for our staffing company.
The output is a markdown document that a human staffing coordinator will read in under 2 minutes to decide whether to pursue the contract for staffing fit.
## Critical rules
1. **DO NOT START WRITING THE FINAL ANALYSIS YET.**
- First, READ this PRD fully.
- Then, PLAN your approach in `note()` — what steps will you take, what tools will you call, what evidence will you need.
- Only after planning, begin executing.
2. **Never invent facts.** If you don't have evidence for a claim (from a tool call), do not make the claim. Say "no evidence available" instead.
3. **Cite your sources.** Every factual claim in the final output should reference either:
- The permit data you read (cite the permit ID)
- A matrix-retrieved chunk (cite as `[matrix:source:doc_id]`)
4. **Stay focused.** This is a one-page deliverable, not a research paper. Aim for 600-1000 words total.
## Tools available
- `list_permits(min_cost?: number, permit_type?: string)` — list permits matching filter; default returns top 5 by cost
- `read_permit(permit_id: string)` — get full details for one permit
- `query_matrix(query: string, top_k?: number)` — search the knowledge base for relevant context (contractor entities, prior permits, SEC tickers, LLM team patterns)
- `note(text: string)` — append to your working scratchpad (visible to you across iterations)
- `read_scratchpad()` — read your full scratchpad
- `done(summary: string)` — finish; pass your final markdown analysis as `summary`
## Required output structure
When you call `done(summary=...)`, the summary should contain:
```markdown
# Staffing Recommendation: Permit <ID>
## Permit Summary
[2-3 sentences: type, cost, address, scope of work]
## Contractor Profile
[What we know about the contractor(s) from matrix evidence. If no matrix hits, say so explicitly.]
## Staffing Implications
[What trades + headcount this permit implies. Ground in the work description.]
## Risk Signals
[Any matrix hits suggesting caution: debarment, prior incidents, low-quality history. If none, say so.]
## Recommendation
[Pursue / Pass / Investigate-Further, with one-sentence rationale.]
```
## Example workflow (do not copy verbatim)
1. Note your plan: "I will list 5 mid-range permits, pick one with a private contractor, read it fully, query the matrix for the contractor name, then write the recommendation."
2. Call `list_permits(min_cost=100000)` → see candidates
3. **PICK A PERMIT WITH A PRIVATE CONTRACTOR (a person's name or a private LLC), NOT a government agency** like CDOT, City of Chicago, etc. Government permits have no useful contractor profile to recommend on.
4. `read_permit(id)` → see all fields
5. Call `query_matrix("<contractor name> contractor Chicago renovation")` → see what the matrix has
6. Note any evidence found, gaps, surprises
7. Call `done(summary="<final markdown>")`
## Success criteria
- You called `done()` with a summary that follows the required structure
- Every factual claim has a source (permit ID or matrix citation)
- Total output is 600-1000 words
- You did not invent contractor names, prior incidents, or capabilities
- Plan was noted BEFORE execution started
## What "good" looks like
- Plan is concrete (which permit, which queries)
- Matrix queries are specific (contractor name + work type, not "find anything about this")
- When matrix returns nothing useful, you say so honestly
- Recommendation reflects the actual evidence, not boilerplate
## What "bad" looks like
- Skipping the plan and jumping to execution
- Making up contractor histories with no matrix evidence
- Generic recommendations that don't reference the actual permit
- Walls of text or structured padding to look thorough
## Begin
Start by acknowledging you've read this PRD and noting your plan via `note()`. Then proceed.

404
tests/battery/compounding_battery.ts Normal file
View File

@ -0,0 +1,404 @@
// Compounding Stress Battery — the rigorous smoke test.
//
// Three iterations against /v1/respond, each running:
// α baseline (3 easy tasks) — should complete local-only with boost
// β drift (3 niche tasks) — forces executor miss → overseer fires
// γ impossible (2 zero-supply) — must fail honestly, no token explosion
// δ distill outcomes — writes distilled_*.jsonl + vector indexes
// ε overseer meta-review — gpt-oss:120b judges the iteration
// ζ scrum judgment — gpt-oss:120b reviews overseer proposals
//
// Iteration N+1 runs the same tasks as iteration N. We measure compounding:
// does turns_per_task drop? does overseer_called_rate drop? does
// correction_effective rise? If 3/5 metrics trend favorably, architecture
// validated; otherwise the scrum verdict points at what to fix.
//
// Fail-fast: every error bubbles. No silent catches — the run ABORTS with
// the underlying stack so we see exactly where the architecture broke.
//
// Runtime: ~60-90 min. Cloud cost: ~24-32 gpt-oss calls (well under daily cap).
import { writeFile, mkdir, readFile } from "node:fs/promises";
import { join } from "node:path";
const GATEWAY = process.env.GATEWAY_URL ?? "http://localhost:3100";
const LLM_TEAM = process.env.LLM_TEAM_URL ?? "http://localhost:5000";
const BATTERY_DIR = process.env.BATTERY_DIR
?? "/home/profit/lakehouse/data/_kb/battery";
// 10-minute timeout per /v1/respond call — cloud executor on a hard task
// can chew for a while, and we want to see real behavior, not premature aborts.
const RESPOND_TIMEOUT_MS = 10 * 60 * 1000;
const META_TIMEOUT_MS = 5 * 60 * 1000;
interface Task {
task_class: string;
operation: string;
spec: Record<string, any>;
}
interface Tasks {
phases: {
alpha_baseline: Task[];
beta_drift: Task[];
gamma_impossible: Task[];
};
models: {
executor_cloud: string;
reviewer_cloud: string;
overseer_cloud: string;
};
}
interface RunResult {
status: "ok" | "failed" | "blocked";
iterations: number;
artifact: any;
log: any[];
error?: string | null;
_elapsed_ms: number;
}
interface TaskRun {
task: Task;
phase: "alpha" | "beta" | "gamma";
result: RunResult;
}
// ─── HTTP helpers ───
async function runRespond(task: Task, models: Tasks["models"]): Promise<RunResult> {
const body = {
task_class: task.task_class,
operation: task.operation,
spec: task.spec,
executor_model: models.executor_cloud,
reviewer_model: models.reviewer_cloud,
};
const start = Date.now();
const resp = await fetch(`${GATEWAY}/v1/respond`, {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify(body),
signal: AbortSignal.timeout(RESPOND_TIMEOUT_MS),
});
if (!resp.ok) {
const txt = await resp.text();
throw new Error(`/v1/respond HTTP ${resp.status}: ${txt.slice(0, 500)}`);
}
const j = (await resp.json()) as RunResult;
j._elapsed_ms = Date.now() - start;
return j;
}
async function runDistill(source: string): Promise<any[]> {
const body = { mode: "distill", prompt: "battery iteration distill", source };
const resp = await fetch(`${LLM_TEAM}/api/run?mode=distill`, {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify(body),
signal: AbortSignal.timeout(META_TIMEOUT_MS),
});
if (!resp.ok) throw new Error(`distill HTTP ${resp.status}`);
const text = await resp.text();
// SSE stream — parse data: lines, return parsed event objects
const events: any[] = [];
for (const line of text.split("\n")) {
if (!line.startsWith("data: ")) continue;
try { events.push(JSON.parse(line.slice(6))); } catch { /* skip */ }
}
return events;
}
async function cloudChat(
model: string,
prompt: string,
temperature: number,
think: boolean,
): Promise<string> {
const resp = await fetch(`${GATEWAY}/v1/chat`, {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
model,
messages: [{ role: "user", content: prompt }],
temperature,
think,
provider: "ollama_cloud",
}),
signal: AbortSignal.timeout(META_TIMEOUT_MS),
});
if (!resp.ok) {
const txt = await resp.text();
throw new Error(`/v1/chat ${model} HTTP ${resp.status}: ${txt.slice(0, 500)}`);
}
const j = await resp.json() as any;
return j.choices?.[0]?.message?.content ?? "";
}
// ─── Meta-review + scrum ───
async function overseerReview(
iterNum: number,
artifacts: any,
models: Tasks["models"],
): Promise<string> {
const prompt = `You are the OVERSEER reviewing iteration ${iterNum} of a stress battery run against Lakehouse /v1/respond.
For each task in the battery below, examine: status (ok/failed/blocked), iterations used, error signature, whether the in-loop overseer fired, total tokens.
Produce a PR-style meta-review in markdown with these sections:
## What worked
List specific tasks (by operation string) that completed correctly and the evidence — turns_used, citations, tokens. Be concrete.
## What failed
List specific tasks that failed or needed overseer correction. Classify: was it a real failure (impossible task), a drift we should repair, or a false positive from the test?
## Proposed changes for iteration ${iterNum + 1}
At least 3 concrete architectural changes, each with:
- **Target file** (e.g. \`crates/gateway/src/execution_loop/mod.rs\`)
- **Rationale** (what the metrics show)
- **Expected impact** (which metric should move in iter ${iterNum + 1})
Be honest about weaknesses. Do NOT propose generic best practices — reference specific observations from the artifacts below.
ARTIFACTS (iteration ${iterNum}):
${JSON.stringify(artifacts, null, 2).slice(0, 30000)}`;
return cloudChat(models.overseer_cloud, prompt, 0.2, true);
}
async function scrumJudge(
iterNum: number,
review: string,
models: Tasks["models"],
): Promise<string> {
const prompt = `You are the SCRUM MASTER. The OVERSEER proposed these architectural changes for iteration ${iterNum + 1} based on iteration ${iterNum}'s results.
For each proposal, produce a verdict in markdown:
- **Proposal N**: <short name>
- **Verdict**: APPROVE | REVISE | REJECT
- **Reason**: why
- **If APPROVE**: is the expected impact realistic? what's the blast radius? is the target file correct?
- **If REVISE**: what should change about the proposal before applying?
- **If REJECT**: why is the proposal wrong or out of scope?
Final section:
## PR-ready changes
Bulleted list of only the APPROVE proposals, ready to apply.
Be rigorous. Don't rubber-stamp. If a proposal references a file that probably doesn't exist, REJECT and say so. If a proposal is a generic "improve X" without concrete plan, REVISE.
OVERSEER PROPOSED:
${review.slice(0, 15000)}`;
return cloudChat(models.overseer_cloud, prompt, 0.1, true);
}
// ─── Iteration driver ───
async function runIteration(iterNum: number, tasks: Tasks): Promise<any> {
console.log(`\n${"═".repeat(60)}`);
console.log(`▶ ITERATION ${iterNum}`);
console.log(`${"═".repeat(60)}\n`);
const iterDir = join(BATTERY_DIR, `iter_${iterNum}`);
await mkdir(iterDir, { recursive: true });
const runs: TaskRun[] = [];
for (const [phaseKey, phaseName] of [
["alpha_baseline", "alpha"],
["beta_drift", "beta"],
["gamma_impossible", "gamma"],
] as const) {
console.log(`\n── Phase ${phaseName} ──`);
for (const task of tasks.phases[phaseKey]) {
console.log(` ▶ ${task.operation}`);
const result = await runRespond(task, tasks.models);
const overseerFired = (result.log ?? []).some(e => e.kind === "overseer_correction");
console.log(
` status=${result.status} turns=${result.iterations}` +
` tokens=${result.artifact?.usage?.total_tokens ?? 0}` +
` overseer=${overseerFired}` +
` elapsed=${Math.round(result._elapsed_ms / 1000)}s`
);
if (result.error) console.log(` error: ${result.error.slice(0, 200)}`);
runs.push({ task, phase: phaseName, result });
}
}
// Phase δ
console.log(`\n── Phase δ: distill outcomes_tail:20 ──`);
const distillEvents = await runDistill("outcomes_tail:20");
const distillFinal = [...distillEvents].reverse()
.find(e => e.role === "final") ?? distillEvents[distillEvents.length - 1];
const distillText = distillFinal?.text ?? JSON.stringify(distillFinal ?? {}).slice(0, 200);
console.log(` ${distillText.split("\n")[0]}`);
await writeFile(join(iterDir, "distill_output.txt"), distillText);
// Metrics
const collectPhase = (p: string) => runs.filter(r => r.phase === p);
const phaseMetrics = (p: string) => {
const ps = collectPhase(p);
if (ps.length === 0) return { count: 0 };
return {
count: ps.length,
ok: ps.filter(r => r.result.status === "ok").length,
failed: ps.filter(r => r.result.status === "failed").length,
avg_turns: ps.reduce((s, r) => s + (r.result.iterations || 0), 0) / ps.length,
total_tokens: ps.reduce((s, r) => s + (r.result.artifact?.usage?.total_tokens ?? 0), 0),
overseer_called: ps.filter(r => (r.result.log ?? []).some(e => e.kind === "overseer_correction")).length,
avg_elapsed_s: ps.reduce((s, r) => s + (r.result._elapsed_ms || 0), 0) / ps.length / 1000,
};
};
const metrics = {
iteration: iterNum,
total_tasks: runs.length,
ok_tasks: runs.filter(r => r.result.status === "ok").length,
failed_tasks: runs.filter(r => r.result.status === "failed").length,
blocked_tasks: runs.filter(r => r.result.status === "blocked").length,
total_tokens: runs.reduce((s, r) => s + (r.result.artifact?.usage?.total_tokens ?? 0), 0),
avg_turns_per_task: runs.reduce((s, r) => s + (r.result.iterations || 0), 0) / runs.length,
overseer_called_rate: runs.filter(r => (r.result.log ?? []).some(e => e.kind === "overseer_correction")).length / runs.length,
total_elapsed_s: runs.reduce((s, r) => s + (r.result._elapsed_ms || 0), 0) / 1000,
by_phase: {
alpha: phaseMetrics("alpha"),
beta: phaseMetrics("beta"),
gamma: phaseMetrics("gamma"),
},
};
console.log(`\n── Metrics ──`);
console.log(` total_tokens: ${metrics.total_tokens}`);
console.log(` avg_turns_per_task: ${metrics.avg_turns_per_task.toFixed(2)}`);
console.log(` overseer_called_rate: ${(metrics.overseer_called_rate * 100).toFixed(1)}%`);
console.log(` ok/total: ${metrics.ok_tasks}/${metrics.total_tasks}`);
await writeFile(join(iterDir, "runs.json"), JSON.stringify(runs, null, 2));
await writeFile(join(iterDir, "metrics.json"), JSON.stringify(metrics, null, 2));
// Phase ε: overseer review
console.log(`\n── Phase ε: overseer meta-review ──`);
const reviewInput = {
metrics,
task_summary: runs.map(r => ({
operation: r.task.operation,
phase: r.phase,
status: r.result.status,
iterations: r.result.iterations,
tokens: r.result.artifact?.usage?.total_tokens ?? 0,
overseer_called: (r.result.log ?? []).some(e => e.kind === "overseer_correction"),
error: r.result.error ?? null,
elapsed_s: Math.round((r.result._elapsed_ms || 0) / 1000),
})),
};
const review = await overseerReview(iterNum, reviewInput, tasks.models);
await writeFile(join(iterDir, "overseer_review.md"), review);
console.log(` ✓ ${review.length} chars`);
// Phase ζ: scrum
console.log(`\n── Phase ζ: scrum judgment ──`);
const verdict = await scrumJudge(iterNum, review, tasks.models);
await writeFile(join(iterDir, "scrum_findings.md"), verdict);
console.log(` ✓ ${verdict.length} chars`);
return metrics;
}
// ─── Main ───
async function main() {
const tasks = JSON.parse(
await readFile("/home/profit/lakehouse/tests/battery/tasks.json", "utf8"),
) as Tasks;
await mkdir(BATTERY_DIR, { recursive: true });
const iterations: any[] = [];
const batteryStart = Date.now();
for (let i = 1; i <= 3; i++) {
const m = await runIteration(i, tasks);
iterations.push(m);
}
const batteryElapsed = (Date.now() - batteryStart) / 1000;
// Summary
const delta = (k: keyof any, inverted = false) => {
const vals = iterations.map((m: any) => m[k]);
if (vals.some(v => v === undefined)) return "—";
const diff = vals[2] - vals[0];
const pct = vals[0] !== 0 ? (diff / vals[0]) * 100 : 0;
const arrow = inverted ? (diff < 0 ? "↓ better" : "↑ worse") : (diff > 0 ? "↑ better" : "↓ worse");
return `${arrow} (${diff > 0 ? "+" : ""}${diff.toFixed?.(2) ?? diff}, ${pct.toFixed(1)}%)`;
};
const rows = [
["total_tokens", "inverted", "want ↓ — fewer tokens for same work"],
["avg_turns_per_task", "inverted", "want ↓ — executor gets smarter"],
["overseer_called_rate", "inverted", "want ↓ — fewer cloud escalations"],
["ok_tasks", "normal", "want ↑ — more successes"],
["total_elapsed_s", "inverted", "want ↓ — faster iterations"],
];
let summary = `# Compounding Stress Battery — Summary\n\n`;
summary += `**Run:** ${new Date().toISOString()}\n`;
summary += `**Elapsed:** ${Math.round(batteryElapsed)}s (${(batteryElapsed/60).toFixed(1)} min)\n`;
summary += `**Models:** executor=${tasks.models.executor_cloud}, reviewer=${tasks.models.reviewer_cloud}, overseer=${tasks.models.overseer_cloud}\n\n`;
summary += `## Compounding Metrics\n\n`;
summary += `| Metric | iter 1 | iter 2 | iter 3 | Trend (1→3) | Goal |\n`;
summary += `|---|---|---|---|---|---|\n`;
for (const [key, inv, goal] of rows) {
const vals = iterations.map((m: any) => {
const v = m[key as string];
return typeof v === "number" ? v.toFixed(2) : String(v);
});
summary += `| ${key} | ${vals[0]} | ${vals[1]} | ${vals[2]} | ${delta(key as any, inv === "inverted")} | ${goal} |\n`;
}
summary += "\n";
// Count trending metrics
const trends = rows.map(([k, inv]) => {
const vs = iterations.map((m: any) => m[k as string]) as number[];
const improved = inv === "inverted" ? vs[2] < vs[0] : vs[2] > vs[0];
return { metric: k, improved };
});
const improvedCount = trends.filter(t => t.improved).length;
summary += `## Verdict\n\n`;
if (improvedCount >= 3) {
summary += `**✓ Architecture validated** — ${improvedCount}/${trends.length} compounding metrics improved from iteration 1 to 3.\n\n`;
} else {
summary += `**✗ Compounding NOT demonstrated** — only ${improvedCount}/${trends.length} metrics improved. See scrum_findings.md in each iter_N/ directory for the overseer's proposals and the scrum master's review of what to change.\n\n`;
}
summary += `Metrics that ${improvedCount >= 3 ? "improved" : "regressed"}:\n`;
for (const t of trends) {
summary += `- ${t.metric}: ${t.improved ? "✓ improved" : "✗ flat or worse"}\n`;
}
summary += `\n## Artifacts\n\n`;
summary += `- \`iter_1/\`, \`iter_2/\`, \`iter_3/\` — per-iteration runs.json, metrics.json, overseer_review.md, scrum_findings.md, distill_output.txt\n`;
summary += `- \`summary.md\` — this file\n`;
await writeFile(join(BATTERY_DIR, "summary.md"), summary);
console.log(`\n${"═".repeat(60)}`);
console.log(`✓ BATTERY COMPLETE — ${Math.round(batteryElapsed)}s`);
console.log(` Summary: ${join(BATTERY_DIR, "summary.md")}`);
console.log(`${"═".repeat(60)}\n`);
console.log(summary);
}
main().catch(e => {
console.error(`\n${"═".repeat(60)}`);
console.error(`✗ BATTERY FAILED: ${e.message}`);
console.error(`${"═".repeat(60)}\n`);
if (e.stack) console.error(e.stack);
process.exit(1);
});

57
tests/battery/tasks.json Normal file
View File

@ -0,0 +1,57 @@
{
"description": "Compounding stress battery tasks. Each iteration runs α (baseline) + β (drift) + γ (impossible) phases. The SAME tasks repeat across iterations so we can measure compounding (turns_used, overseer_called_rate, correction_effective).",
"phases": {
"alpha_baseline": [
{
"task_class": "staffing.fill",
"operation": "fill: Warehouse Associate x3 in Columbus, OH",
"spec": { "target_role": "Warehouse Associate", "target_count": 3, "target_city": "Columbus", "target_state": "OH", "approach_hint": "hybrid search against workers_500k_v1" }
},
{
"task_class": "staffing.fill",
"operation": "fill: Forklift Operator x2 in Toledo, OH",
"spec": { "target_role": "Forklift Operator", "target_count": 2, "target_city": "Toledo", "target_state": "OH", "approach_hint": "hybrid search against workers_500k_v1" }
},
{
"task_class": "staffing.fill",
"operation": "fill: Packer x4 in Cleveland, OH",
"spec": { "target_role": "Packer", "target_count": 4, "target_city": "Cleveland", "target_state": "OH", "approach_hint": "hybrid search against workers_500k_v1" }
}
],
"beta_drift": [
{
"task_class": "staffing.fill",
"operation": "fill: Machine Operator x2 in Youngstown, OH (requires OSHA 30 + bilingual Spanish)",
"spec": { "target_role": "Machine Operator", "target_count": 2, "target_city": "Youngstown", "target_state": "OH", "approach_hint": "hybrid search against workers_500k_v1; prefer candidates with OSHA certification and Spanish" }
},
{
"task_class": "staffing.fill",
"operation": "fill: Welder x2 in Dayton, OH (AWS D1.1 certified, night shift)",
"spec": { "target_role": "Welder", "target_count": 2, "target_city": "Dayton", "target_state": "OH", "approach_hint": "hybrid search against workers_500k_v1; filter by certification and shift flexibility" }
},
{
"task_class": "staffing.fill",
"operation": "fill: Assembler x5 in Akron, OH (SMT experience, cleanroom)",
"spec": { "target_role": "Assembler", "target_count": 5, "target_city": "Akron", "target_state": "OH", "approach_hint": "hybrid search against workers_500k_v1" }
}
],
"gamma_impossible": [
{
"task_class": "staffing.fill",
"operation": "fill: Underwater Welder x2 in Toledo, OH",
"spec": { "target_role": "Underwater Welder", "target_count": 2, "target_city": "Toledo", "target_state": "OH", "approach_hint": "hybrid search against workers_500k_v1 (expected to fail — no supply)" }
},
{
"task_class": "staffing.fill",
"operation": "fill: Astronaut x1 in Springfield, OH",
"spec": { "target_role": "Astronaut", "target_count": 1, "target_city": "Springfield", "target_state": "OH", "approach_hint": "(expected to fail — out-of-domain role)" }
}
]
},
"models": {
"executor_cloud": "gpt-oss:20b",
"reviewer_cloud": "gpt-oss:20b",
"overseer_cloud": "gpt-oss:120b",
"notes": "gpt-oss:20b for hot path (faster, cheaper per call), gpt-oss:120b for meta-reviews. All cloud per 2026-04-23 'cloud modes are on' directive."
}
}

45
tests/multi-agent/playbooks/ab_scorecard.json Normal file
View File

@ -0,0 +1,45 @@
{
"generated_at": "2026-04-21T00:44:59.486489Z",
"runs": [
{
"label": "A(no-T3)",
"path": "tests/multi-agent/playbooks/scenario-2026-04-21T00-30-54",
"ok_events": 0,
"total_events": 5,
"total_turns": 0,
"total_gaps": 5,
"total_citations": 0,
"prior_lessons_loaded": 0
},
{
"label": "B(T3-seed)",
"path": "tests/multi-agent/playbooks/scenario-2026-04-21T00-37-04",
"ok_events": 0,
"total_events": 5,
"total_turns": 0,
"total_gaps": 5,
"total_citations": 0,
"prior_lessons_loaded": 1
},
{
"label": "C(T3-read)",
"path": "tests/multi-agent/playbooks/scenario-2026-04-21T00-39-54",
"ok_events": 0,
"total_events": 5,
"total_turns": 0,
"total_gaps": 5,
"total_citations": 0,
"prior_lessons_loaded": 2
},
{
"label": "D(T3-cloud)",
"path": "tests/multi-agent/playbooks/scenario-2026-04-21T00-43-44",
"ok_events": 0,
"total_events": 5,
"total_turns": 0,
"total_gaps": 5,
"total_citations": 0,
"prior_lessons_loaded": 3
}
]
}

25
tests/multi-agent/playbooks/kb_measurement.md Normal file
View File

@ -0,0 +1,25 @@
# KB Measurement Report
Generated from 26 runs across 24 distinct signatures.
## Recommender confidence
- high: 23
- medium: 1
- low: 3
## Overall fill + citation
- Fill rate: **60/86** (69.8%)
- Avg citations per run: **1.38**
- Avg turns per run: 6.6
## Citation coverage by (role, city, state)
- Combos with ≥1 citation: 9
- Combos with ok fills but 0 citations: 31
## Item 3 decision signal
Non-zero: there are **combos that succeeded but never triggered playbook_memory boost**. Candidates for item 3 investigation:
- Machine Operator in Indianapolis, IN: 1/1 ok, 0 cites
- Assembler in Indianapolis, IN: 2/2 ok, 0 cites
- Warehouse Associate in Indianapolis, IN: 1/1 ok, 0 cites
- Forklift Operator in Cleveland, OH: 1/1 ok, 0 cites
- Assembler in Cleveland, OH: 2/2 ok, 0 cites

1
tests/multi-agent/playbooks/scenario-2026-04-20T09-55-13/dispatch.jsonl Normal file
View File

@ -0,0 +1 @@
{"at":"10:30","kind":"recurring","operation":"fill: Machine Operator x2 in Toledo, OH","fills":[{"candidate_id":"W500K-29048","name":"Raymond G. Ward","reason":"Raymond has a high availability score (0.9033) and relevant skills for the Machine Operator position in Toledo, OH. He is also endorsed by past similar fills."},{"candidate_id":"W500K-20613","name":"Pamela V. Green","reason":"Pamela has a high availability score (0.8496) and relevant skills for the Machine Operator position in Toledo, OH. She is also endorsed by past similar fills."}],"turns":5,"duration_secs":12.051,"pool_size":997,"playbook_citations":[]}

17
tests/multi-agent/playbooks/scenario-2026-04-20T09-55-13/emails.md Normal file
View File

@ -0,0 +1,17 @@
# Client emails — Riverfront Steel, 2026-04-21
## 10:30 recurring — Machine Operator x2
Subject: 2 Filled
Dear Riverfront Steel Team,
We are pleased to confirm that we have filled both Machine Operator roles for your Tuesday/Thursday shifts starting at 11:00 AM.
- Raymond G. Ward
- Pamela V. Green
Both candidates have high availability scores and relevant experience. Please note this is a recurring slot, and prior workers may still be available.
Best regards,
Dispatch Team Lakehouse

45
tests/multi-agent/playbooks/scenario-2026-04-20T09-55-13/report.md Normal file
View File

@ -0,0 +1,45 @@
# Scenario retrospective — Riverfront Steel, 2026-04-21
Executor: `mistral:latest` Reviewer: `qwen2.5:latest` Draft: `qwen2.5:latest`
## Events
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|---|---|---|---|---|---|---|---|---|
| 08:00 | baseline_fill | Warehouse Associate × 3 | - | ✗ 0 | 0 | 28.9 | 0 | 1 |
| 10:30 | recurring | Machine Operator × 2 | 997 | ✓ 2 | 5 | 12.1 | 0 | 1 |
| 12:15 | expansion | Forklift Operator × 5 | - | ✗ 0 | 0 | 20.3 | 0 | 1 |
| 14:00 | emergency | Loader × 4 | - | ✗ 0 | 0 | 35.7 | 0 | 1 |
| 15:45 | misplacement | Warehouse Associate × 1 | - | ✗ 0 | 0 | 11.5 | 0 | 1 |
## Final roster
| Worker | Booked | Role | City, ST | Status |
|---|---|---|---|---|
| undefined Raymond G. Ward | 10:30 | Machine Operator | Toledo, OH | confirmed |
| undefined Pamela V. Green | 10:30 | Machine Operator | Toledo, OH | confirmed |
## Gap signals
### drift_or_tool
- **08:00** — invalid JSON from executor: JSON Parse error: Unable to parse JSON string | raw: {"kind":"plan","steps":["Verify one candidate from the current list using sql tool for SQL verification.","Propose_done with top 3 candidates who are Warehouse Associates in Toledo, OH."]}
{"kind":"tool_call","tool":"sql","args":{"query":"SELECT worker_id, name, role, city, state, availability FROM
- **12:15** — invalid JSON from executor: JSON Parse error: Expected ']' | raw: {"kind":"plan","steps":["1. Use hybrid_search to find Forklift Operators in Toledo, OH with high engagement and communications scores who are available for work at Riverfront Steel starting at 01:00 PM. The search should prioritize workers with team/collaboration signals (engagement, communications
- **14:00** — no consensus after 14 turns
- **15:45** — invalid JSON from executor: JSON Parse error: Expected '}' | raw: {"kind":"tool_call","tool":"hybrid_search", "args":{"index_name":"workers_500k_v1","sql_filter":"LOWER(role) LIKE '%warehouse%' AND city = 'Toledo' AND state = 'OH' AND availability > 0.5 AND shift = '08:00' AND worker_id NOT IN [, ] AND worker_id NOT IN ["EXCLUDE_WORKERS_ID1", "EXCLUDE_WORKERS_ID2"
### double_book
- **10:30** — undefined Pamela V. Green already booked for 10:30
### fairness
- _cross-event_ — Raymond G. Ward (undefined) booked 2 times today
### write_through_audit
- _post-run_ — playbook_memory has 33 entries (ran 5 events, expected ≥ 1 new entries from this run)
## Narrative
- 1/5 events reached consensus.
- Final roster: 2 bookings across 1 distinct workers.
- Playbook citations across the day: 0 (proof the feedback loop fired across events).
- Dropped events: 08:00 baseline_fill, 12:15 expansion, 14:00 emergency, 15:45 misplacement.

118
tests/multi-agent/playbooks/scenario-2026-04-20T09-55-13/results.json Normal file
View File

@ -0,0 +1,118 @@
[
{
"event": {
"kind": "baseline_fill",
"at": "08:00",
"role": "Warehouse Associate",
"count": 3,
"city": "Toledo",
"state": "OH",
"shift_start": "08:00 AM",
"scenario_note": "Regular Monday morning shift, 8-hour."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 28.888,
"error": "invalid JSON from executor: JSON Parse error: Unable to parse JSON string | raw: {\"kind\":\"plan\",\"steps\":[\"Verify one candidate from the current list using sql tool for SQL verification.\",\"Propose_done with top 3 candidates who are Warehouse Associates in Toledo, OH.\"]}\n{\"kind\":\"tool_call\",\"tool\":\"sql\",\"args\":{\"query\":\"SELECT worker_id, name, role, city, state, availability FROM ",
"gap_signals": [
"drift_or_tool: invalid JSON from executor: JSON Parse error: Unable to parse JSON string | raw: {\"kind\":\"plan\",\"steps\":[\"Verify one candidate from the current list using sql tool for SQL verification.\",\"Propose_done with top 3 candidates who are Warehouse Associates in Toledo, OH.\"]}\n{\"kind\":\"tool_call\",\"tool\":\"sql\",\"args\":{\"query\":\"SELECT worker_id, name, role, city, state, availability FROM "
]
},
{
"event": {
"kind": "recurring",
"at": "10:30",
"role": "Machine Operator",
"count": 2,
"city": "Toledo",
"state": "OH",
"shift_start": "11:00 AM",
"scenario_note": "Recurring Tuesday/Thursday slot — prior workers may still be available."
},
"ok": true,
"fills": [
{
"candidate_id": "W500K-29048",
"name": "Raymond G. Ward",
"reason": "Raymond has a high availability score (0.9033) and relevant skills for the Machine Operator position in Toledo, OH. He is also endorsed by past similar fills."
},
{
"candidate_id": "W500K-20613",
"name": "Pamela V. Green",
"reason": "Pamela has a high availability score (0.8496) and relevant skills for the Machine Operator position in Toledo, OH. She is also endorsed by past similar fills."
}
],
"turns": 5,
"duration_secs": 12.051,
"gap_signals": [
"double_book: undefined Pamela V. Green already booked for 10:30"
],
"sources_first_score": 0.6692528,
"sources_last_score": 0.64494026,
"pool_size": 997,
"playbook_citations": []
},
{
"event": {
"kind": "expansion",
"at": "12:15",
"role": "Forklift Operator",
"count": 5,
"city": "Toledo",
"state": "OH",
"shift_start": "01:00 PM",
"scenario_note": "New warehouse location opening, five-worker team needed."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 20.342,
"error": "invalid JSON from executor: JSON Parse error: Expected ']' | raw: {\"kind\":\"plan\",\"steps\":[\"1. Use hybrid_search to find Forklift Operators in Toledo, OH with high engagement and communications scores who are available for work at Riverfront Steel starting at 01:00 PM. The search should prioritize workers with team/collaboration signals (engagement, communications ",
"gap_signals": [
"drift_or_tool: invalid JSON from executor: JSON Parse error: Expected ']' | raw: {\"kind\":\"plan\",\"steps\":[\"1. Use hybrid_search to find Forklift Operators in Toledo, OH with high engagement and communications scores who are available for work at Riverfront Steel starting at 01:00 PM. The search should prioritize workers with team/collaboration signals (engagement, communications "
]
},
{
"event": {
"kind": "emergency",
"at": "14:00",
"role": "Loader",
"count": 4,
"city": "Toledo",
"state": "OH",
"shift_start": "04:00 PM same day",
"deadline": "16:00",
"scenario_note": "Walkoff incident — replacement crew needed by 16:00 sharp."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 35.727,
"error": "no consensus after 14 turns",
"gap_signals": [
"drift_or_tool: no consensus after 14 turns"
]
},
{
"event": {
"kind": "misplacement",
"at": "15:45",
"role": "Warehouse Associate",
"count": 1,
"city": "Toledo",
"state": "OH",
"shift_start": "remainder of 08:00 shift",
"scenario_note": "One worker from the 08:00 fill didn't show; rebuild the gap.",
"replaces_event": "08:00"
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 11.518,
"error": "invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"hybrid_search\", \"args\":{\"index_name\":\"workers_500k_v1\",\"sql_filter\":\"LOWER(role) LIKE '%warehouse%' AND city = 'Toledo' AND state = 'OH' AND availability > 0.5 AND shift = '08:00' AND worker_id NOT IN [, ] AND worker_id NOT IN [\"EXCLUDE_WORKERS_ID1\", \"EXCLUDE_WORKERS_ID2\"",
"gap_signals": [
"drift_or_tool: invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"hybrid_search\", \"args\":{\"index_name\":\"workers_500k_v1\",\"sql_filter\":\"LOWER(role) LIKE '%warehouse%' AND city = 'Toledo' AND state = 'OH' AND availability > 0.5 AND shift = '08:00' AND worker_id NOT IN [, ] AND worker_id NOT IN [\"EXCLUDE_WORKERS_ID1\", \"EXCLUDE_WORKERS_ID2\""
]
}
]

18
tests/multi-agent/playbooks/scenario-2026-04-20T09-55-13/roster.json Normal file
View File

@ -0,0 +1,18 @@
[
{
"name": "Raymond G. Ward",
"booked_for": "10:30",
"role": "Machine Operator",
"city": "Toledo",
"state": "OH",
"status": "confirmed"
},
{
"name": "Pamela V. Green",
"booked_for": "10:30",
"role": "Machine Operator",
"city": "Toledo",
"state": "OH",
"status": "confirmed"
}
]

11
tests/multi-agent/playbooks/scenario-2026-04-20T09-55-13/sms.md Normal file
View File

@ -0,0 +1,11 @@
# SMS drafts — Riverfront Steel, 2026-04-21
## 10:30 recurring — Machine Operator x2 in Toledo, OH
TO: Raymond G. Ward
Confirming your Machine Operator shift at Riverfront Steel in Toledo, OH starting at 11:00 AM on Tuesday/Thursday. Still available!
---
TO: Pamela V. Green
Your Machine Operator shift at Riverfront Steel in Toledo, OH starts at 11:00 AM on Tuesday/Thursday. Confirm your availability please.

0
tests/multi-agent/playbooks/scenario-2026-04-20T19-59-48/dispatch.jsonl Normal file
View File

1
tests/multi-agent/playbooks/scenario-2026-04-20T19-59-48/emails.md Normal file
View File

@ -0,0 +1 @@
# Client emails — Riverfront Steel, 2026-04-21

1
tests/multi-agent/playbooks/scenario-2026-04-20T19-59-48/sms.md Normal file
View File

@ -0,0 +1 @@
# SMS drafts — Riverfront Steel, 2026-04-21

0
tests/multi-agent/playbooks/scenario-2026-04-20T20-02-01/dispatch.jsonl Normal file
View File

22
tests/multi-agent/playbooks/scenario-2026-04-20T20-02-01/emails.md Normal file
View File

@ -0,0 +1,22 @@
# Client emails — Riverfront Steel, 2026-04-21
## 12:15 expansion — Forklift Operator x5
Subject: 5 Workers Confirmed
Dear Riverfront Steel Team,
I am pleased to confirm that we have filled all five positions for Forklift Operators at your new warehouse location opening today starting at 1:00 PM. The workers are:
- Laura F. Morales
- Kyle F. Brooks
- Maria K. Cruz
- Jeffrey D. Taylor
- Charles T. Walker
All meet the criteria of being Forklift Operators in Toledo, OH.
Looking forward to a successful shift!
Best regards,
Dispatch Team Lakehouse

26
tests/multi-agent/playbooks/scenario-2026-04-20T20-02-01/sms.md Normal file
View File

@ -0,0 +1,26 @@
# SMS drafts — Riverfront Steel, 2026-04-21
## 12:15 expansion — Forklift Operator x5 in Toledo, OH
TO: Laura F. Morales
Confirming your shift as a Forklift Operator at Riverfront Steel in Toledo, OH starting at 1:00 PM for the new warehouse location opening. W500K-22625
---
TO: Kyle F. Brooks
You're scheduled to start your Forklift Operator shift at Riverfront Steel in Toledo, OH at 1:00 PM for the new warehouse location opening. Confirm W500K-33961
---
TO: Maria K. Cruz
Your shift as a Forklift Operator at Riverfront Steel in Toledo, OH starts at 1:00 PM for the new warehouse location opening. Please confirm your attendance. W500K-19588
---
TO: Jeffrey D. Taylor
Confirming your shift as a Forklift Operator at Riverfront Steel in Toledo, OH starting at 1:00 PM for the new warehouse location opening. W500K-37729
---
TO: Charles T. Walker
You're scheduled to start your Forklift Operator shift at Riverfront Steel in Toledo, OH at 1:00 PM for the new warehouse location opening. Confirm your attendance. W500K-17543

2
tests/multi-agent/playbooks/scenario-2026-04-20T20-04-45/dispatch.jsonl Normal file
View File

@ -0,0 +1,2 @@
{"at":"08:00","kind":"baseline_fill","operation":"fill: Warehouse Associate x3 in Toledo, OH","fills":[{"candidate_id":"W500K-49164","name":"Christopher Y. Phillips","reason":"Reliable Warehouse Associate with availability greater than 0.5 in Toledo, OH."},{"candidate_id":"W500K-40928","name":"Janet E. Hill","reason":"Reliable Warehouse Associate with availability greater than 0.5 in Toledo, OH."},{"candidate_id":"W500K-34704","name":"Fatima U. Rivera","reason":"Reliable Warehouse Associate with availability greater than 0.5 in Toledo, OH."}],"turns":7,"duration_secs":20.128,"pool_size":770,"playbook_citations":[],"discovered_pattern":"Across 25 similar past playbooks (8 workers examined) · archetype mostly: reliable · reliability median 0.80 (range 0.66–0.96)"}
{"at":"10:30","kind":"recurring","operation":"fill: Machine Operator x2 in Toledo, OH","fills":[{"candidate_id":"W500K-19759","name":"Carmen Z. Rodriguez","reason":"Recurring Machine Operator in Toledo, OH with a score of 0.75, verified via sql tool."},{"candidate_id":"W500K-29298","name":"Robert W. Gonzalez","reason":"Recurring Machine Operator in Toledo, OH with a score of 0.74, not yet SQL verified but highly likely to meet requirements."}],"turns":5,"duration_secs":17.426,"pool_size":997,"playbook_citations":[],"discovered_pattern":"Across 25 similar past playbooks (8 workers examined) · archetype mostly: reliable · reliability median 0.80 (range 0.66–0.96)"}

40
tests/multi-agent/playbooks/scenario-2026-04-20T20-04-45/emails.md Normal file
View File

@ -0,0 +1,40 @@
# Client emails — Riverfront Steel, 2026-04-21
## 08:00 baseline_fill — Warehouse Associate x3
Subject: 3 Filled
Dear Riverfront Steel Staffing Team,
I am pleased to confirm that we have filled all three roles of Warehouse Associate for your Monday morning shift starting at 08:00 AM.
The workers assigned are:
- Christopher Y. Phillips
- Janet E. Hill
- Fatima U. Rivera
All three have confirmed their availability and are reliable team members.
Best regards,
Dispatch Team Lakehouse
## 10:30 recurring — Machine Operator x2
To: staffing@riverfrontsteel.example
From: dispatch@lakehouse.example
Subject: Confirmed
Dear Riverfront Steel Team,
We are pleased to confirm that we have filled both Machine Operator roles for your Tuesday/Thursday shifts starting at 11:00 AM. The workers assigned are:
- Carmen Z. Rodriguez
- Robert W. Gonzalez
Both are recurring Machine Operators in Toledo, OH with a score of 0.7.
Please note this is a recurring slot; prior workers may still be available.
Best regards,
Dispatch Team

74
tests/multi-agent/playbooks/scenario-2026-04-20T20-04-45/report.md Normal file
View File

@ -0,0 +1,74 @@
# Scenario retrospective — Riverfront Steel, 2026-04-21
Executor: `mistral:latest` Reviewer: `qwen2.5:latest` Draft: `qwen2.5:latest`
## Events
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|---|---|---|---|---|---|---|---|---|
| 08:00 | baseline_fill | Warehouse Associate × 3 | 770 | ✓ 3 | 7 | 20.1 | 0 | 2 |
| 10:30 | recurring | Machine Operator × 2 | 997 | ✓ 2 | 5 | 17.4 | 0 | 2 |
| 12:15 | expansion | Forklift Operator × 5 | - | ✗ 0 | 0 | 46.4 | 0 | 1 |
| 14:00 | emergency | Loader × 4 | - | ✗ 0 | 0 | 54.1 | 0 | 1 |
| 15:45 | misplacement | Warehouse Associate × 1 | - | ✗ 0 | 0 | 59.6 | 0 | 1 |
## Final roster
| Worker | Booked | Role | City, ST | Status |
|---|---|---|---|---|
| undefined Christopher Y. Phillips | 08:00 | Warehouse Associate | Toledo, OH | no_show |
| undefined Janet E. Hill | 08:00 | Warehouse Associate | Toledo, OH | confirmed |
| undefined Fatima U. Rivera | 08:00 | Warehouse Associate | Toledo, OH | confirmed |
| undefined Carmen Z. Rodriguez | 10:30 | Machine Operator | Toledo, OH | confirmed |
| undefined Robert W. Gonzalez | 10:30 | Machine Operator | Toledo, OH | confirmed |
## Gap signals
### double_book
- **08:00** — undefined Janet E. Hill already booked for 08:00
- **08:00** — undefined Fatima U. Rivera already booked for 08:00
- **10:30** — undefined Carmen Z. Rodriguez already booked for 08:00
- **10:30** — undefined Robert W. Gonzalez already booked for 08:00
### drift_or_tool
- **12:15** — invalid JSON from executor: JSON Parse error: Invalid escape character ' | raw: {"kind":"plan", "steps":["TOOL_CALL hybrid_search({'index_name':'workers_500k_v1', 'sql_filter':'LOWER(role) LIKE '%forklift%' AND city = \'Toledo\' AND state = \'OH\' AND availability > CAST(0.5 AS DOUBLE) AND reliability > CAST(0.75 AS DOUBLE)', 'question':'reliable forklift operators in Toledo, O
- **14:00** — invalid JSON from executor: JSON Parse error: Expected '}' | raw: {"kind":"tool_call","tool":"hybrid_search",
"args":{"index_name":"workers_500k_v1","sql_filter":"LOWER(role) LIKE '%loader%' AND city = 'Toledo' AND state = 'OH' AND availability > CAST(0.7 AS DOUBLE) AND worker_id NOT IN ('W500K-4321', 'W500K-8963', 'W500K-2345', 'W500K-6789', 'W500K-9876') AND wor
- **15:45** — no consensus after 14 turns
### fairness
- _cross-event_ — Christopher Y. Phillips (undefined) booked 4 times today
### write_through_audit
- _post-run_ — playbook_memory has 165 entries (ran 5 events, expected ≥ 2 new entries from this run)
## Workers touched across the week
6 distinct workers made it through to a decision. Every one is accounted for below — no-shows flagged, rebookings noted, everyone visible.
| Worker ID | Name | Events | Outcome |
|---|---|---|---|
| W500K-49164 | Christopher Y. Phillips | 08:00 baseline_fill | booked |
| W500K-40928 | Janet E. Hill | 08:00 baseline_fill | booked |
| W500K-34704 | Fatima U. Rivera | 08:00 baseline_fill | booked |
| W500K-19759 | Carmen Z. Rodriguez | 10:30 recurring | booked |
| W500K-29298 | Robert W. Gonzalez | 10:30 recurring | booked |
| undefined | Christopher Y. Phillips | 08:00 | no_show |
## Discovered patterns (meta-index)
What the system identified across semantically-similar past fills as each event ran:
- **08:00 baseline_fill** (Warehouse Associate): Across 25 similar past playbooks (8 workers examined) · archetype mostly: reliable · reliability median 0.80 (range 0.66–0.96)
- **10:30 recurring** (Machine Operator): Across 25 similar past playbooks (8 workers examined) · archetype mostly: reliable · reliability median 0.80 (range 0.66–0.96)
- **12:15 expansion** (Forklift Operator): —
- **14:00 emergency** (Loader): —
- **15:45 misplacement** (Warehouse Associate): —
## Narrative
- 2/5 events reached consensus.
- Final roster: 5 bookings across 1 distinct workers.
- Workers touched (booked, failed, or otherwise decided): 6.
- Playbook citations across the day: 0 (proof the feedback loop fired across events).
- Dropped events: 12:15 expansion, 14:00 emergency, 15:45 misplacement.

146
tests/multi-agent/playbooks/scenario-2026-04-20T20-04-45/results.json Normal file
View File

@ -0,0 +1,146 @@
[
{
"event": {
"kind": "baseline_fill",
"at": "08:00",
"role": "Warehouse Associate",
"count": 3,
"city": "Toledo",
"state": "OH",
"shift_start": "08:00 AM",
"scenario_note": "Regular Monday morning shift, 8-hour."
},
"ok": true,
"fills": [
{
"candidate_id": "W500K-49164",
"name": "Christopher Y. Phillips",
"reason": "Reliable Warehouse Associate with availability greater than 0.5 in Toledo, OH."
},
{
"candidate_id": "W500K-40928",
"name": "Janet E. Hill",
"reason": "Reliable Warehouse Associate with availability greater than 0.5 in Toledo, OH."
},
{
"candidate_id": "W500K-34704",
"name": "Fatima U. Rivera",
"reason": "Reliable Warehouse Associate with availability greater than 0.5 in Toledo, OH."
}
],
"turns": 7,
"duration_secs": 20.128,
"gap_signals": [
"double_book: undefined Janet E. Hill already booked for 08:00",
"double_book: undefined Fatima U. Rivera already booked for 08:00"
],
"sources_first_score": 0.7124013,
"sources_last_score": 0.66623676,
"pool_size": 770,
"playbook_citations": [],
"discovered_pattern": "Across 25 similar past playbooks (8 workers examined) · archetype mostly: reliable · reliability median 0.80 (range 0.66–0.96)"
},
{
"event": {
"kind": "recurring",
"at": "10:30",
"role": "Machine Operator",
"count": 2,
"city": "Toledo",
"state": "OH",
"shift_start": "11:00 AM",
"scenario_note": "Recurring Tuesday/Thursday slot — prior workers may still be available."
},
"ok": true,
"fills": [
{
"candidate_id": "W500K-19759",
"name": "Carmen Z. Rodriguez",
"reason": "Recurring Machine Operator in Toledo, OH with a score of 0.75, verified via sql tool."
},
{
"candidate_id": "W500K-29298",
"name": "Robert W. Gonzalez",
"reason": "Recurring Machine Operator in Toledo, OH with a score of 0.74, not yet SQL verified but highly likely to meet requirements."
}
],
"turns": 5,
"duration_secs": 17.426,
"gap_signals": [
"double_book: undefined Carmen Z. Rodriguez already booked for 08:00",
"double_book: undefined Robert W. Gonzalez already booked for 08:00"
],
"sources_first_score": 0.72546995,
"sources_last_score": 0.6690281,
"pool_size": 997,
"playbook_citations": [],
"discovered_pattern": "Across 25 similar past playbooks (8 workers examined) · archetype mostly: reliable · reliability median 0.80 (range 0.66–0.96)"
},
{
"event": {
"kind": "expansion",
"at": "12:15",
"role": "Forklift Operator",
"count": 5,
"city": "Toledo",
"state": "OH",
"shift_start": "01:00 PM",
"scenario_note": "New warehouse location opening, five-worker team needed."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 46.391,
"error": "invalid JSON from executor: JSON Parse error: Invalid escape character ' | raw: {\"kind\":\"plan\", \"steps\":[\"TOOL_CALL hybrid_search({'index_name':'workers_500k_v1', 'sql_filter':'LOWER(role) LIKE '%forklift%' AND city = \\'Toledo\\' AND state = \\'OH\\' AND availability > CAST(0.5 AS DOUBLE) AND reliability > CAST(0.75 AS DOUBLE)', 'question':'reliable forklift operators in Toledo, O",
"gap_signals": [
"drift_or_tool: invalid JSON from executor: JSON Parse error: Invalid escape character ' | raw: {\"kind\":\"plan\", \"steps\":[\"TOOL_CALL hybrid_search({'index_name':'workers_500k_v1', 'sql_filter':'LOWER(role) LIKE '%forklift%' AND city = \\'Toledo\\' AND state = \\'OH\\' AND availability > CAST(0.5 AS DOUBLE) AND reliability > CAST(0.75 AS DOUBLE)', 'question':'reliable forklift operators in Toledo, O"
]
},
{
"event": {
"kind": "emergency",
"at": "14:00",
"role": "Loader",
"count": 4,
"city": "Toledo",
"state": "OH",
"shift_start": "04:00 PM same day",
"deadline": "16:00",
"scenario_note": "Walkoff incident — replacement crew needed by 16:00 sharp."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 54.123,
"error": "invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"hybrid_search\",\n\"args\":{\"index_name\":\"workers_500k_v1\",\"sql_filter\":\"LOWER(role) LIKE '%loader%' AND city = 'Toledo' AND state = 'OH' AND availability > CAST(0.7 AS DOUBLE) AND worker_id NOT IN ('W500K-4321', 'W500K-8963', 'W500K-2345', 'W500K-6789', 'W500K-9876') AND wor",
"gap_signals": [
"drift_or_tool: invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"hybrid_search\",\n\"args\":{\"index_name\":\"workers_500k_v1\",\"sql_filter\":\"LOWER(role) LIKE '%loader%' AND city = 'Toledo' AND state = 'OH' AND availability > CAST(0.7 AS DOUBLE) AND worker_id NOT IN ('W500K-4321', 'W500K-8963', 'W500K-2345', 'W500K-6789', 'W500K-9876') AND wor"
]
},
{
"event": {
"kind": "misplacement",
"at": "15:45",
"role": "Warehouse Associate",
"count": 1,
"city": "Toledo",
"state": "OH",
"shift_start": "remainder of 08:00 shift",
"scenario_note": "One worker from the 08:00 fill didn't show; rebuild the gap.",
"replaces_event": "08:00",
"exclude_worker_ids": [
null,
null,
null
]
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 59.593,
"error": "no consensus after 14 turns",
"gap_signals": [
"drift_or_tool: no consensus after 14 turns"
]
}
]

42
tests/multi-agent/playbooks/scenario-2026-04-20T20-04-45/roster.json Normal file
View File

@ -0,0 +1,42 @@
[
{
"name": "Christopher Y. Phillips",
"booked_for": "08:00",
"role": "Warehouse Associate",
"city": "Toledo",
"state": "OH",
"status": "no_show"
},
{
"name": "Janet E. Hill",
"booked_for": "08:00",
"role": "Warehouse Associate",
"city": "Toledo",
"state": "OH",
"status": "confirmed"
},
{
"name": "Fatima U. Rivera",
"booked_for": "08:00",
"role": "Warehouse Associate",
"city": "Toledo",
"state": "OH",
"status": "confirmed"
},
{
"name": "Carmen Z. Rodriguez",
"booked_for": "10:30",
"role": "Machine Operator",
"city": "Toledo",
"state": "OH",
"status": "confirmed"
},
{
"name": "Robert W. Gonzalez",
"booked_for": "10:30",
"role": "Machine Operator",
"city": "Toledo",
"state": "OH",
"status": "confirmed"
}
]

26
tests/multi-agent/playbooks/scenario-2026-04-20T20-04-45/sms.md Normal file
View File

@ -0,0 +1,26 @@
# SMS drafts — Riverfront Steel, 2026-04-21
## 08:00 baseline_fill — Warehouse Associate x3 in Toledo, OH
TO: Christopher Y. Phillips
Confirming your shift as a Warehouse Associate at Riverfront Steel in Toledo, OH starting 8 AM today.
---
TO: Janet E. Hill
Good morning! Confirming your shift as a Warehouse Associate from 8 AM onwards at our Toledo, OH location.
---
TO: Fatima U. Rivera
Morning Fatima! Just confirming your shift as a Warehouse Associate at Riverfront Steel in Toledo, OH starting at 8 AM.
## 10:30 recurring — Machine Operator x2 in Toledo, OH
TO: Carmen Z. Rodriguez
Confirming your shift as a Machine Operator at Riverfront Steel in Toledo, OH starting 11:00 AM on Tuesday/Thursday. Still available!
---
TO: Robert W. Gonzalez
Your recurring Tuesday/Thursday Machine Operator shift at Riverfront Steel in Toledo, OH starts at 11:00 AM. Confirm your availability please.

0
tests/multi-agent/playbooks/scenario-2026-04-20T20-11-11/dispatch.jsonl Normal file
View File

1
tests/multi-agent/playbooks/scenario-2026-04-20T20-11-11/emails.md Normal file
View File

@ -0,0 +1 @@
# Client emails — Riverfront Steel, 2026-04-21

57
tests/multi-agent/playbooks/scenario-2026-04-20T20-11-11/report.md Normal file
View File

@ -0,0 +1,57 @@
# Scenario retrospective — Riverfront Steel, 2026-04-21
Executor: `mistral:latest` Reviewer: `qwen2.5:latest` Draft: `qwen2.5:latest`
## Events
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|---|---|---|---|---|---|---|---|---|
| 08:00 | baseline_fill | Warehouse Associate × 3 | - | ✗ 0 | 0 | 63.8 | 0 | 1 |
| 10:30 | recurring | Machine Operator × 2 | - | ✗ 0 | 0 | 9.5 | 0 | 1 |
| 12:15 | expansion | Forklift Operator × 5 | - | ✗ 0 | 0 | 47.8 | 0 | 1 |
| 14:00 | emergency | Loader × 4 | - | ✗ 0 | 0 | 60.1 | 0 | 1 |
| 15:45 | misplacement | Warehouse Associate × 1 | - | ✗ 0 | 0 | 62.3 | 0 | 1 |
## Final roster
| Worker | Booked | Role | City, ST | Status |
|---|---|---|---|---|
## Gap signals
### drift_or_tool
- **08:00** — aborted — 3 consecutive drift flags
- **10:30** — invalid JSON from executor: JSON Parse error: Unterminated string | raw: {"kind":"plan","steps":["TOOL_CALL hybrid_search({'index_name':'workers_500k_v1','sql_filter':'role = 'Machine Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5'})",
"TOOL_CALL sql({'query':'SELECT worker_id, name, role, city, state, CAST(availability AS DOUBLE) A
- **12:15** — aborted — 3 consecutive drift flags
- **14:00** — aborted — 3 consecutive drift flags
- **15:45** — invalid JSON from executor: JSON Parse error: Unterminated string | raw: {"kind": "plan", "steps": ["1.1. TOOL_CALL hybrid_search({'index_name': 'workers_500k_v1', 'sql_filter': 'role = 'Warehouse Associate' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND worker_id NOT IN (49164, 1181, 7239, 299, 30930, 33212)'})",
"2.2. TOOL_CALL sql({'qu
### write_through_audit
- _post-run_ — playbook_memory has 165 entries (ran 5 events, expected ≥ 0 new entries from this run)
## Workers touched across the week
0 distinct workers made it through to a decision. Every one is accounted for below — no-shows flagged, rebookings noted, everyone visible.
| Worker ID | Name | Events | Outcome |
|---|---|---|---|
## Discovered patterns (meta-index)
What the system identified across semantically-similar past fills as each event ran:
- **08:00 baseline_fill** (Warehouse Associate): —
- **10:30 recurring** (Machine Operator): —
- **12:15 expansion** (Forklift Operator): —
- **14:00 emergency** (Loader): —
- **15:45 misplacement** (Warehouse Associate): —
## Narrative
- 0/5 events reached consensus.
- Final roster: 0 bookings across 0 distinct workers.
- Workers touched (booked, failed, or otherwise decided): 0.
- Playbook citations across the day: 0 (proof the feedback loop fired across events).
- Dropped events: 08:00 baseline_fill, 10:30 recurring, 12:15 expansion, 14:00 emergency, 15:45 misplacement.

104
tests/multi-agent/playbooks/scenario-2026-04-20T20-11-11/results.json Normal file
View File

@ -0,0 +1,104 @@
[
{
"event": {
"kind": "baseline_fill",
"at": "08:00",
"role": "Warehouse Associate",
"count": 3,
"city": "Toledo",
"state": "OH",
"shift_start": "08:00 AM",
"scenario_note": "Regular Monday morning shift, 8-hour."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 63.815,
"error": "aborted — 3 consecutive drift flags",
"gap_signals": [
"drift_or_tool: aborted — 3 consecutive drift flags"
]
},
{
"event": {
"kind": "recurring",
"at": "10:30",
"role": "Machine Operator",
"count": 2,
"city": "Toledo",
"state": "OH",
"shift_start": "11:00 AM",
"scenario_note": "Recurring Tuesday/Thursday slot — prior workers may still be available."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 9.538,
"error": "invalid JSON from executor: JSON Parse error: Unterminated string | raw: {\"kind\":\"plan\",\"steps\":[\"TOOL_CALL hybrid_search({'index_name':'workers_500k_v1','sql_filter':'role = 'Machine Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5'})\",\n\"TOOL_CALL sql({'query':'SELECT worker_id, name, role, city, state, CAST(availability AS DOUBLE) A",
"gap_signals": [
"drift_or_tool: invalid JSON from executor: JSON Parse error: Unterminated string | raw: {\"kind\":\"plan\",\"steps\":[\"TOOL_CALL hybrid_search({'index_name':'workers_500k_v1','sql_filter':'role = 'Machine Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5'})\",\n\"TOOL_CALL sql({'query':'SELECT worker_id, name, role, city, state, CAST(availability AS DOUBLE) A"
]
},
{
"event": {
"kind": "expansion",
"at": "12:15",
"role": "Forklift Operator",
"count": 5,
"city": "Toledo",
"state": "OH",
"shift_start": "01:00 PM",
"scenario_note": "New warehouse location opening, five-worker team needed."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 47.797,
"error": "aborted — 3 consecutive drift flags",
"gap_signals": [
"drift_or_tool: aborted — 3 consecutive drift flags"
]
},
{
"event": {
"kind": "emergency",
"at": "14:00",
"role": "Loader",
"count": 4,
"city": "Toledo",
"state": "OH",
"shift_start": "04:00 PM same day",
"deadline": "16:00",
"scenario_note": "Walkoff incident — replacement crew needed by 16:00 sharp."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 60.115,
"error": "aborted — 3 consecutive drift flags",
"gap_signals": [
"drift_or_tool: aborted — 3 consecutive drift flags"
]
},
{
"event": {
"kind": "misplacement",
"at": "15:45",
"role": "Warehouse Associate",
"count": 1,
"city": "Toledo",
"state": "OH",
"shift_start": "remainder of 08:00 shift",
"scenario_note": "One worker from the 08:00 fill didn't show; rebuild the gap.",
"replaces_event": "08:00"
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 62.283,
"error": "invalid JSON from executor: JSON Parse error: Unterminated string | raw: {\"kind\": \"plan\", \"steps\": [\"1.1. TOOL_CALL hybrid_search({'index_name': 'workers_500k_v1', 'sql_filter': 'role = 'Warehouse Associate' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND worker_id NOT IN (49164, 1181, 7239, 299, 30930, 33212)'})\",\n\"2.2. TOOL_CALL sql({'qu",
"gap_signals": [
"drift_or_tool: invalid JSON from executor: JSON Parse error: Unterminated string | raw: {\"kind\": \"plan\", \"steps\": [\"1.1. TOOL_CALL hybrid_search({'index_name': 'workers_500k_v1', 'sql_filter': 'role = 'Warehouse Associate' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND worker_id NOT IN (49164, 1181, 7239, 299, 30930, 33212)'})\",\n\"2.2. TOOL_CALL sql({'qu"
]
}
]

1
tests/multi-agent/playbooks/scenario-2026-04-20T20-11-11/roster.json Normal file
View File

@ -0,0 +1 @@
[]

1
tests/multi-agent/playbooks/scenario-2026-04-20T20-11-11/sms.md Normal file
View File

@ -0,0 +1 @@
# SMS drafts — Riverfront Steel, 2026-04-21

0
tests/multi-agent/playbooks/scenario-2026-04-20T20-16-49/dispatch.jsonl Normal file
View File

1
tests/multi-agent/playbooks/scenario-2026-04-20T20-16-49/emails.md Normal file
View File

@ -0,0 +1 @@
# Client emails — Riverfront Steel, 2026-04-21

55
tests/multi-agent/playbooks/scenario-2026-04-20T20-16-49/report.md Normal file
View File

@ -0,0 +1,55 @@
# Scenario retrospective — Riverfront Steel, 2026-04-21
Executor: `qwen2.5:latest` Reviewer: `qwen2.5:latest` Draft: `qwen2.5:latest`
## Events
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|---|---|---|---|---|---|---|---|---|
| 08:00 | baseline_fill | Warehouse Associate × 3 | - | ✗ 0 | 0 | 6.4 | 0 | 1 |
| 10:30 | recurring | Machine Operator × 2 | - | ✗ 0 | 0 | 16.8 | 0 | 1 |
| 12:15 | expansion | Forklift Operator × 5 | - | ✗ 0 | 0 | 7.2 | 0 | 1 |
| 14:00 | emergency | Loader × 4 | - | ✗ 0 | 0 | 54.0 | 0 | 1 |
| 15:45 | misplacement | Warehouse Associate × 1 | - | ✗ 0 | 0 | 49.3 | 0 | 1 |
## Final roster
| Worker | Booked | Role | City, ST | Status |
|---|---|---|---|---|
## Gap signals
### drift_or_tool
- **08:00** — invalid JSON from executor: JSON Parse error: Expected '}' | raw: {"kind":"tool_call","tool":"sql","args":{"query":"SELECT worker_id, name FROM workers_500k_v1 WHERE role = 'Warehouse Associate' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 LIMIT 3"},"rationale":"verify top candidates via SQL query")}
- **10:30** — invalid JSON from executor: JSON Parse error: Expected '}' | raw: {"kind":"tool_call","tool":"hybrid_search","args":{"index_name":"workers_500k_v1","sql_filter":"role = 'Machine Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND reliability >= 0.7","question":"machine operator Toledo OH high reliability","k":2}
- **12:15** — invalid JSON from executor: JSON Parse error: Expected '}' | raw: {"kind":"tool_call","tool":"sql","args":{"query":"SELECT worker_id FROM workers_500k_v1 WHERE role = 'Forklift Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND CAST(reliability AS DOUBLE) > 0.75 LIMIT 5"},"rationale":"verify top candidates via SQL query to me
- **14:00** — no consensus after 14 turns
- **15:45** — no consensus after 14 turns
### write_through_audit
- _post-run_ — playbook_memory has 165 entries (ran 5 events, expected ≥ 0 new entries from this run)
## Workers touched across the week
0 distinct workers made it through to a decision. Every one is accounted for below — no-shows flagged, rebookings noted, everyone visible.
| Worker ID | Name | Events | Outcome |
|---|---|---|---|
## Discovered patterns (meta-index)
What the system identified across semantically-similar past fills as each event ran:
- **08:00 baseline_fill** (Warehouse Associate): —
- **10:30 recurring** (Machine Operator): —
- **12:15 expansion** (Forklift Operator): —
- **14:00 emergency** (Loader): —
- **15:45 misplacement** (Warehouse Associate): —
## Narrative
- 0/5 events reached consensus.
- Final roster: 0 bookings across 0 distinct workers.
- Workers touched (booked, failed, or otherwise decided): 0.
- Playbook citations across the day: 0 (proof the feedback loop fired across events).
- Dropped events: 08:00 baseline_fill, 10:30 recurring, 12:15 expansion, 14:00 emergency, 15:45 misplacement.

104
tests/multi-agent/playbooks/scenario-2026-04-20T20-16-49/results.json Normal file
View File

@ -0,0 +1,104 @@
[
{
"event": {
"kind": "baseline_fill",
"at": "08:00",
"role": "Warehouse Associate",
"count": 3,
"city": "Toledo",
"state": "OH",
"shift_start": "08:00 AM",
"scenario_note": "Regular Monday morning shift, 8-hour."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 6.434,
"error": "invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"sql\",\"args\":{\"query\":\"SELECT worker_id, name FROM workers_500k_v1 WHERE role = 'Warehouse Associate' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 LIMIT 3\"},\"rationale\":\"verify top candidates via SQL query\")}",
"gap_signals": [
"drift_or_tool: invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"sql\",\"args\":{\"query\":\"SELECT worker_id, name FROM workers_500k_v1 WHERE role = 'Warehouse Associate' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 LIMIT 3\"},\"rationale\":\"verify top candidates via SQL query\")}"
]
},
{
"event": {
"kind": "recurring",
"at": "10:30",
"role": "Machine Operator",
"count": 2,
"city": "Toledo",
"state": "OH",
"shift_start": "11:00 AM",
"scenario_note": "Recurring Tuesday/Thursday slot — prior workers may still be available."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 16.752,
"error": "invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"hybrid_search\",\"args\":{\"index_name\":\"workers_500k_v1\",\"sql_filter\":\"role = 'Machine Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND reliability >= 0.7\",\"question\":\"machine operator Toledo OH high reliability\",\"k\":2}",
"gap_signals": [
"drift_or_tool: invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"hybrid_search\",\"args\":{\"index_name\":\"workers_500k_v1\",\"sql_filter\":\"role = 'Machine Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND reliability >= 0.7\",\"question\":\"machine operator Toledo OH high reliability\",\"k\":2}"
]
},
{
"event": {
"kind": "expansion",
"at": "12:15",
"role": "Forklift Operator",
"count": 5,
"city": "Toledo",
"state": "OH",
"shift_start": "01:00 PM",
"scenario_note": "New warehouse location opening, five-worker team needed."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 7.181,
"error": "invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"sql\",\"args\":{\"query\":\"SELECT worker_id FROM workers_500k_v1 WHERE role = 'Forklift Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND CAST(reliability AS DOUBLE) > 0.75 LIMIT 5\"},\"rationale\":\"verify top candidates via SQL query to me",
"gap_signals": [
"drift_or_tool: invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"sql\",\"args\":{\"query\":\"SELECT worker_id FROM workers_500k_v1 WHERE role = 'Forklift Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND CAST(reliability AS DOUBLE) > 0.75 LIMIT 5\"},\"rationale\":\"verify top candidates via SQL query to me"
]
},
{
"event": {
"kind": "emergency",
"at": "14:00",
"role": "Loader",
"count": 4,
"city": "Toledo",
"state": "OH",
"shift_start": "04:00 PM same day",
"deadline": "16:00",
"scenario_note": "Walkoff incident — replacement crew needed by 16:00 sharp."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 54.028,
"error": "no consensus after 14 turns",
"gap_signals": [
"drift_or_tool: no consensus after 14 turns"
]
},
{
"event": {
"kind": "misplacement",
"at": "15:45",
"role": "Warehouse Associate",
"count": 1,
"city": "Toledo",
"state": "OH",
"shift_start": "remainder of 08:00 shift",
"scenario_note": "One worker from the 08:00 fill didn't show; rebuild the gap.",
"replaces_event": "08:00"
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 49.298,
"error": "no consensus after 14 turns",
"gap_signals": [
"drift_or_tool: no consensus after 14 turns"
]
}
]

1
tests/multi-agent/playbooks/scenario-2026-04-20T20-16-49/roster.json Normal file
View File

@ -0,0 +1 @@
[]

1
tests/multi-agent/playbooks/scenario-2026-04-20T20-16-49/sms.md Normal file
View File

@ -0,0 +1 @@
# SMS drafts — Riverfront Steel, 2026-04-21

0
tests/multi-agent/playbooks/scenario-2026-04-20T20-20-23/dispatch.jsonl Normal file
View File

1
tests/multi-agent/playbooks/scenario-2026-04-20T20-20-23/emails.md Normal file
View File

@ -0,0 +1 @@
# Client emails — Riverfront Steel, 2026-04-21

55
tests/multi-agent/playbooks/scenario-2026-04-20T20-20-23/report.md Normal file
View File

@ -0,0 +1,55 @@
# Scenario retrospective — Riverfront Steel, 2026-04-21
Executor: `mistral:latest` Reviewer: `qwen2.5:latest` Draft: `qwen2.5:latest`
## Events
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|---|---|---|---|---|---|---|---|---|
| 08:00 | baseline_fill | Warehouse Associate × 3 | - | ✗ 0 | 0 | 47.4 | 0 | 1 |
| 10:30 | recurring | Machine Operator × 2 | - | ✗ 0 | 0 | 40.4 | 0 | 1 |
| 12:15 | expansion | Forklift Operator × 5 | - | ✗ 0 | 0 | 9.4 | 0 | 1 |
| 14:00 | emergency | Loader × 4 | - | ✗ 0 | 0 | 44.7 | 0 | 1 |
| 15:45 | misplacement | Warehouse Associate × 1 | - | ✗ 0 | 0 | 45.1 | 0 | 1 |
## Final roster
| Worker | Booked | Role | City, ST | Status |
|---|---|---|---|---|
## Gap signals
### drift_or_tool
- **08:00** — no consensus after 14 turns
- **10:30** — aborted — 3 consecutive drift flags
- **12:15** — invalid JSON from executor: JSON Parse error: Expected '}' | raw: {"kind":"tool_call","tool":"propose_done","args":{"fills":[{"candidate_id":"W500K-37736","name":"Jennifer K. Robinson","reason":"verified Toledo forklift op, reliability 0.9"}],"rationale":"one SQL-verified candidate from surfaced candidates"}
- **14:00** — aborted — 3 consecutive drift flags
- **15:45** — no consensus after 14 turns
### write_through_audit
- _post-run_ — playbook_memory has 165 entries (ran 5 events, expected ≥ 0 new entries from this run)
## Workers touched across the week
0 distinct workers made it through to a decision. Every one is accounted for below — no-shows flagged, rebookings noted, everyone visible.
| Worker ID | Name | Events | Outcome |
|---|---|---|---|
## Discovered patterns (meta-index)
What the system identified across semantically-similar past fills as each event ran:
- **08:00 baseline_fill** (Warehouse Associate): —
- **10:30 recurring** (Machine Operator): —
- **12:15 expansion** (Forklift Operator): —
- **14:00 emergency** (Loader): —
- **15:45 misplacement** (Warehouse Associate): —
## Narrative
- 0/5 events reached consensus.
- Final roster: 0 bookings across 0 distinct workers.
- Workers touched (booked, failed, or otherwise decided): 0.
- Playbook citations across the day: 0 (proof the feedback loop fired across events).
- Dropped events: 08:00 baseline_fill, 10:30 recurring, 12:15 expansion, 14:00 emergency, 15:45 misplacement.

104
tests/multi-agent/playbooks/scenario-2026-04-20T20-20-23/results.json Normal file
View File

@ -0,0 +1,104 @@
[
{
"event": {
"kind": "baseline_fill",
"at": "08:00",
"role": "Warehouse Associate",
"count": 3,
"city": "Toledo",
"state": "OH",
"shift_start": "08:00 AM",
"scenario_note": "Regular Monday morning shift, 8-hour."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 47.404,
"error": "no consensus after 14 turns",
"gap_signals": [
"drift_or_tool: no consensus after 14 turns"
]
},
{
"event": {
"kind": "recurring",
"at": "10:30",
"role": "Machine Operator",
"count": 2,
"city": "Toledo",
"state": "OH",
"shift_start": "11:00 AM",
"scenario_note": "Recurring Tuesday/Thursday slot — prior workers may still be available."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 40.374,
"error": "aborted — 3 consecutive drift flags",
"gap_signals": [
"drift_or_tool: aborted — 3 consecutive drift flags"
]
},
{
"event": {
"kind": "expansion",
"at": "12:15",
"role": "Forklift Operator",
"count": 5,
"city": "Toledo",
"state": "OH",
"shift_start": "01:00 PM",
"scenario_note": "New warehouse location opening, five-worker team needed."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 9.414,
"error": "invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"propose_done\",\"args\":{\"fills\":[{\"candidate_id\":\"W500K-37736\",\"name\":\"Jennifer K. Robinson\",\"reason\":\"verified Toledo forklift op, reliability 0.9\"}],\"rationale\":\"one SQL-verified candidate from surfaced candidates\"}",
"gap_signals": [
"drift_or_tool: invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"propose_done\",\"args\":{\"fills\":[{\"candidate_id\":\"W500K-37736\",\"name\":\"Jennifer K. Robinson\",\"reason\":\"verified Toledo forklift op, reliability 0.9\"}],\"rationale\":\"one SQL-verified candidate from surfaced candidates\"}"
]
},
{
"event": {
"kind": "emergency",
"at": "14:00",
"role": "Loader",
"count": 4,
"city": "Toledo",
"state": "OH",
"shift_start": "04:00 PM same day",
"deadline": "16:00",
"scenario_note": "Walkoff incident — replacement crew needed by 16:00 sharp."
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 44.673,
"error": "aborted — 3 consecutive drift flags",
"gap_signals": [
"drift_or_tool: aborted — 3 consecutive drift flags"
]
},
{
"event": {
"kind": "misplacement",
"at": "15:45",
"role": "Warehouse Associate",
"count": 1,
"city": "Toledo",
"state": "OH",
"shift_start": "remainder of 08:00 shift",
"scenario_note": "One worker from the 08:00 fill didn't show; rebuild the gap.",
"replaces_event": "08:00"
},
"ok": false,
"fills": [],
"turns": 0,
"duration_secs": 45.149,
"error": "no consensus after 14 turns",
"gap_signals": [
"drift_or_tool: no consensus after 14 turns"
]
}
]

1
tests/multi-agent/playbooks/scenario-2026-04-20T20-20-23/roster.json Normal file
View File

@ -0,0 +1 @@
[]

1
tests/multi-agent/playbooks/scenario-2026-04-20T20-20-23/sms.md Normal file
View File

@ -0,0 +1 @@
# SMS drafts — Riverfront Steel, 2026-04-21

2
tests/multi-agent/playbooks/scenario-2026-04-20T20-24-48/dispatch.jsonl Normal file
View File

@ -0,0 +1,2 @@
{"at":"12:15","kind":"expansion","operation":"fill: Forklift Operator x5 in Toledo, OH","fills":[{"candidate_id":"W500K-37736","name":"Jennifer K. Robinson","reason":"Meets the criteria of being a Forklift Operator in Toledo, OH with availability and reliability above the specified thresholds."},{"candidate_id":"W500K-33961","name":"Kyle F. Brooks","reason":"Meets the criteria of being a Forklift Operator in Toledo, OH with availability and reliability above the specified thresholds."},{"candidate_id":"W500K-31297","name":"Jacob T. Diaz","reason":"Meets the criteria of being a Forklift Operator in Toledo, OH with availability and reliability above the specified thresholds."},{"candidate_id":"W500K-40884","name":"Jerry M. Jones","reason":"Meets the criteria of being a Forklift Operator in Toledo, OH with availability and reliability above the specified thresholds."},{"candidate_id":"W500K-37729","name":"Jeffrey D. Taylor","reason":"Meets the criteria of being a Forklift Operator in Toledo, OH with availability and reliability above the specified thresholds."}],"turns":7,"duration_secs":28.23,"pool_size":687,"playbook_citations":[],"discovered_pattern":"Across 25 similar past playbooks (10 workers examined) · recurring certifications: Forklift (40%), OSHA-10 (40%) · recurring skills: mill (40%) · archetype mostly: leader · reliability median 0.83 (range 0.66–0.96)"}
{"at":"14:00","kind":"emergency","operation":"fill: Loader x4 in Toledo, OH","fills":[{"candidate_id":"W500K-15305","name":"Mary R. Richardson","reason":"Verified availability score of 0.988 via SQL and ranked highest among the candidates with an availability score greater than 0.7."},{"candidate_id":"W500K-12325","name":"Raj Torres","reason":"Ranked second among the candidates with an availability score greater than 0.7."},{"candidate_id":"W500K-16975","name":"Brian X. Price","reason":"Ranked third among the candidates with an availability score greater than 0.7."},{"candidate_id":"W500K-22851","name":"Fatima X. Gutierrez","reason":"Ranked fourth among the candidates with an availability score greater than 0.7."}],"turns":6,"duration_secs":22.25,"pool_size":380,"playbook_citations":[],"discovered_pattern":"Across 25 similar past playbooks (9 workers examined) · recurring certifications: Forklift (44%) · recurring skills: mill (44%) · archetype mostly: leader · reliability median 0.80 (range 0.66–0.96)"}

40
tests/multi-agent/playbooks/scenario-2026-04-20T20-24-48/emails.md Normal file
View File

@ -0,0 +1,40 @@
# Client emails — Riverfront Steel, 2026-04-21
## 12:15 expansion — Forklift Operator x5
Subject: 5 Workers Confirmed
Dear Riverfront Steel Team,
We are pleased to confirm that we have filled all five positions for Forklift Operators at your new warehouse location opening. The workers starting at 01:00 PM today are:
- Jennifer K. Robinson
- Kyle F. Brooks
- Jacob T. Diaz
- Jerry M. Jones
- Jeffrey D. Taylor
Each meets the criteria of being a Forklift Operator in Toledo, OH.
Best regards,
Dispatch Team Lakehouse
## 14:00 emergency — Loader x4
Subject: 4 Loader Workers Confirmed
Dear Riverfront Steel Team,
I am pleased to confirm that we have filled all four loader positions as requested:
- Mary R. Richardson
- Raj Torres
- Brian X. Price
- Fatima X. Gutierrez
All workers will start their shift at 04:00 PM today. Please note the walkoff incident requiring a replacement crew by 16:00 sharp.
Thank you for your trust in Lakehouse Dispatch.
Best regards,
Dispatch Team

Some files were not shown because too many files have changed in this diff Show More