J asked for a much more sophisticated test using the 100k corpus from
the Rust legacy database. This commit ships:
scripts/cutover/multitier/main.go — 6-scenario harness with weighted
random selection per goroutine. Mixes search, email/SMS/fill
validators (in-process via internal/validator), profile swap with
ExcludeIDs, repeat-cache exercise, and playbook record/replay.
Scenarios + weights (cumulative scenario fractions):
35% cold_search_email — search + email outreach + EmailValidator
15% surge_fill_validate — search + fill proposal + FillValidator + record
15% profile_swap — original search + ExcludeIDs swap + no-overlap check
15% repeat_cache — same query × 5 (cache effectiveness)
10% sms_validate — SMS draft (≤160 chars, phone for SSN-FP guard)
10% playbook_record_replay — cold → record → warm w/ use_playbook=true
Test results (5-min sustained, conc=50, 100k workers indexed):
TOTAL 335,257 scenarios @ 1,115/sec
cold_search_email 117k @ 0.0% fail · p50 2.2ms · p99 8.6ms
surge_fill_validate 50k @ 98.8% fail (substrate bug below)
profile_swap 50k @ 0.0% fail · p50 4.5ms · ExcludeIDs verified
repeat_cache 50k × 5 = 252k searches @ 0.0% fail · p50 11.7ms
sms_validate 33k @ 0.0% fail · phone-pattern guard works
playbook_record_replay 33k @ 96.8% fail (substrate bug below)
Total successful workflows: ~250k+
Validator integration verified at load:
150,930 EmailValidator passes across cold_search_email + sms_validate
35 + 1,061 successful FillValidator + playbook_record (where the bug
didn't fire)
zero false positives on the SSN-pattern guard against phone numbers
Resource footprint at 100k:
vectord 1.23GB RSS (linear with 100k vectors)
matrixd 26MB, 75% CPU (1-core saturated at conc=50)
Total across 11 daemons: 1.7GB
Compare to Rust at 14.9GB — ~10× less even at 100k.
SUBSTRATE BUG SURFACED: coder/hnsw v0.6.1 nil-deref in
layerNode.search at graph.go:95. Triggers on /v1/matrix/playbooks/record
under sustained writes to the small playbook_memory index. Both Add
and Search paths can panic.
Workaround applied (this commit) in internal/vectord/index.go
BatchAdd: recover() guard converts panic to error; daemon stays up
instead of crashing the request handler.
Operator recovery procedure (also documented in the report):
curl -X DELETE http://localhost:4215/vectors/index/playbook_memory
Next record recreates the index fresh.
Real fix DEFERRED — open in docs/ARCHITECTURE_COMPARISON.md
Decisions tracker. Three options:
a) upstream patch to coder/hnsw
b) custom small-index Add path that always rebuilds when len < threshold
c) alternate store for playbook_memory (Lance? in-memory map?)
Evidence: reports/cutover/multitier_100k.md (full methodology +
results + repro + bug analysis). docs/ARCHITECTURE_COMPARISON.md
Decisions tracker updated.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Per J's request: move the parallel-runtime comparison from
reports/cutover/ (where it lived as cutover-prep evidence) into
docs/ as the source-of-truth file. J will keep updating it as
fixes ship on either side.
Restructured for living-document use:
- Status header (last refresh date, owner, update triggers)
- 'How to update this doc' section with explicit dos and don'ts
- Decisions tracker at top — actioned items with commit refs
+ open backlog with LOC estimates
- Each comparison section now has 'Last verified' columns where
numbers are time-sensitive
- Change log section at bottom for one-line entries on every
meaningful refresh
The original at reports/cutover/architecture_comparison.md gains
a 'THIS IS A SNAPSHOT' header pointing at the docs/ source. Kept
as historical record but no longer the place to update.
Sister pointer file in /home/profit/lakehouse/docs/ARCHITECTURE_COMPARISON.md
so the doc is reachable from either repo side. That file explicitly
says the source lives in golangLAKEHOUSE and warns against
authoritative content in the pointer.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Per architecture_comparison.md universal-win for Go side: ports the
Rust crates/validator/src/staffing/ to internal/validator/. Production
safety net Go was missing — FillValidator catches phantom worker IDs
+ status/blacklist/geo/role mismatches; EmailValidator catches
SSN-shape PII + salary disclosure + wrong-target name in email/SMS
drafts.
Files:
- types.go: Artifact (FillProposal | EmailDraft), Validator interface,
WorkerLookup interface, ValidationError + Finding + Severity
- lookup.go: InMemoryWorkerLookup with case-insensitive ID lookup
- fill.go: FillValidator — schema → completeness → cross-roster
(phantom ID / status / blacklist / geo / role)
- email.go: EmailValidator — schema → length → PII (SSN + salary)
→ worker-name consistency
- fill_test.go + email_test.go: 24 tests covering happy path +
every error variant + the load-bearing edge cases (phone-pattern
not flagged as SSN, flanking-digit guard rejects extended
numeric runs)
Validator names match Rust (staffing.fill / staffing.email) so
cross-runtime audit logs share the same identifier. PII scanners
(containsSSNPattern, containsSalaryDisclosure) ported byte-for-byte
so a draft flagged by one runtime is flagged by the other.
Caveat: the Rust validator crate also has parquet_lookup.rs (loads
workers_500k.parquet at startup) and playbook.rs (additional
checks). Those weren't ported in this wave — only the two
load-bearing validators that were named in the comparison doc.
Closes one of the two universal-win items for Go side. The other
(materializer port) remains deferred — it's a bigger surface change
and depends on transforms.ts source-class adapters.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
J asked for the comparison before locking in primary line. This
report documents what's actually structurally different vs
implementation-level different, and what to do about each.
Key findings:
1. Python sidecar is the single biggest architectural lever
- Rust: gateway → HTTP → Python sidecar :3200 → HTTP → Ollama
- Go: gateway → HTTP → embedd → HTTP → Ollama (no Python)
- Sidecar adds zero compute over Ollama (just pydantic + httpx)
- 63× perf gap (8,119 vs 128 RPS) driven by sidecar + cache absence
2. Process model: Rust 1 mega-binary (14.9G RSS), Go 11 daemons
- Rust: simpler ops at small scale, panic blast radius = whole system
- Go: per-daemon scale + crash isolation, more config surface
3. Code volume: Go 15,128 lines vs Rust 35,447 + 1,237 sidecar
- Go is 43% the size doing similar work
- Gap concentrated in vectord (Rust 11k lines, Go 804 — Lance + benchmarking)
4. Distillation pipeline asymmetry
- Audit/observation: BOTH sides parallel-mature
- Production: Rust-only (materializer + replay + RAG/pref export)
- Go can READ everything but can't PRODUCE evidence
5. Production validators (FillValidator/EmailValidator/'/v1/validate')
- Rust has them (1,286 lines, 12 tests each)
- Go doesn't — matrix gate covers role bleed but not structural validation
Cross-cutting abstracts to address regardless of which wins:
- Drop Python sidecar from Rust (call Ollama directly)
- Add LRU embed cache to Rust aibridge
- Port materializer + replay + validators to Go
- Pin shared JSONL schemas as canonical (both runtimes consume same spec)
- Decide on Lance backend (defer until corpus > 5M rows)
If keeping Go primary: port materializer first, validators second,
skip Lance. If keeping Rust primary: drop Python + add cache,
port chatd 5-provider dispatcher + cross-role gate from Go.
Bottom line: substrate is parallel-mature on observation; producer
side is Rust-only; performance structurally favors Go ~60× on warm
workloads; operations favors Go on isolation; production deployment
favors Rust today.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Sustained-traffic load test against the cutover slice. Three runs,
zero correctness errors across 101,770 total requests. Substrate
holds up under concurrent load — matrix gate, vectord HNSW,
embedd cache, gateway proxy all hold. This was the load test's
primary question; latency numbers are secondary.
scripts/cutover/loadgen — focused Go load generator. 6-query
rotating body mix (Forklift/CNC/Warehouse/Picker/Loader/Shipping).
Configurable URL/concurrency/duration. Reports per-status-code
counts + p50/p95/p99 latencies + JSON summary on stderr.
Three runs:
baseline (Bun → Go, conc=1, 10s):
4,085 req · 408 RPS · p50 1.3ms · p99 32ms · max 215ms
sustained (Bun → Go, conc=10, 30s):
14,527 req · 484 RPS · p50 4.6ms · p99 92ms · max 372ms
direct (→ Go, conc=10, 30s):
83,158 req · 2,772 RPS · p50 2.5ms · p99 8.5ms · max 16ms
Critical findings:
1. ZERO correctness errors across 101k requests. No 5xx, no
transport errors, no panics. Concurrency-safety verified across
matrix gate / vectord / gateway / embedd cache.
2. Direct-to-Go is production-grade. 2,772 RPS at p99 8.5ms on a
single host, no scaling cliff at concurrency=10.
3. Bun frontend is the bottleneck. -82% RPS, +982% p99 vs direct.
Single-process JS event loop queueing under concurrent
requests — known Bun proxy-mode characteristic. The substrate
itself isn't the limiter.
4. For staffing-domain demand levels (<1 RPS typical per
coordinator), Bun-fronted 484 RPS has 480× headroom. No
urgency to optimize Bun out of the data path. If/when
concurrent demand grows orders of magnitude, the path is
nginx → Go direct for hot endpoints, skip Bun.
Substrate is now load-tested and verified production-ready.
What this load test does NOT cover (documented in
g5_load_test.md): cold-cache embed, larger corpus, mixed
read/write, multi-host, full 5-loop traffic with judge gate
calls. Each is its own probe shape.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Companion to c522ace (cutover slice live). That commit proved
infrastructure (Bun /_go/* → Go gateway). This commit proves the
SUBSTRATE'S CORE LEARNING BEHAVIOR through the same path.
Two tests against persistent Go stack on :4110 with the 200-worker
corpus, all traffic via Bun frontend on :3700:
TEST 1: same-role boost fires with exact math
Q1: Need 3 Forklift Operators in Aurora IL for Parallel Machining
query_role: "Forklift Operator"
cold (use_playbook=false):
rank=0 id=w-43 dist=0.4449 Brian Ramirez, Springfield IL
POST /_go/v1/matrix/playbooks/record:
query_text=Q1, role=Forklift Operator, answer_id=w-43, score=1.0
→ playbook_id=pb-1126c52bd106df6b
warm (use_playbook=true):
rank=0 id=w-43 dist=0.2224 ← halved
boosted=1, injected=0
Math check: BoostFactor = 1 - 0.5*score = 0.5 (for score=1.0).
Expected warm_dist = 0.4449 * 0.5 = 0.22245.
Observed: 0.2224. 4-decimal exact through 3 HTTP hops.
TEST 2: cross-role gate prevents bleed
Q2: Need 1 CNC Operator in Detroit MI for Beacon Freight
query_role: "CNC Operator"
use_playbook: true (Forklift recording from Test 1 in playbook corpus)
result:
rank=0 id=w-175 Kevin Ruiz (Machine Operator, Detroit MI)
rank=2 id=w-102 Laura Long (Forklift Operator, Cleveland OH)
boosted=0, injected=0 ← role gate fired correctly
w-102 (Forklift Operator) appears at rank 2 organically via
cosine retrieval — but boosted=0 confirms the Forklift PLAYBOOK
did NOT influence this query. Surgical: gate suppresses
playbook-driven boosts from cross-role recordings, leaves
organic retrieval untouched.
What this confirms about the substrate:
1. Learning works — single recording → measurable, math-exact boost
2. Bleed protection works — role gate (real_001 fix) holds through
cutover slice
3. Math holds across HTTP hops — Bun → gateway → matrixd → vectord
with no drift
4. Substrate works through real production-shape framing — CORS,
content-type, body forwarding, all transparent
The substrate's reason-for-being (5-loop learning) is now
demonstrably executing on persistent daemons under
production-shape frontend traffic.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
J said "let's go" → "next" (option 3): actual flip via Bun
mcp-server. Done. Real Bun-frontend traffic now reaches the Go
substrate via /_go/* on Bun :3700, routed to the persistent Go
gateway at :4110.
Companion change in /home/profit/lakehouse (Rust legacy):
mcp-server/index.ts: new /_go/* pass-through, opt-in via
GO_LAKEHOUSE_URL env var. Off-by-default (returns 503 on
/_go/* with rationale). Existing /api/* (Rust gateway) path
unchanged. Committed locally on the demo/post-pr11 branch.
System config:
/etc/systemd/system/lakehouse-agent.service.d/go-cutover.conf
adds Environment=GO_LAKEHOUSE_URL=http://127.0.0.1:4110 to
the systemd-managed Bun service. Reversible via systemctl
revert lakehouse-agent.
Live verification (operator curl through Bun frontend):
- /_go/health: gateway responds {"status":"ok","service":"gateway"}
- /_go/v1/embed: nomic-embed-text-v2-moe vectors, dim=768
- /_go/v1/matrix/search vs persistent 200-worker corpus:
rank=0 id=w-43 Brian Ramirez (Forklift Operator, Springfield IL)
rank=1 id=w-102 Laura Long (Forklift Operator, Cleveland OH)
rank=2 id=w-101 Terrence Gray (Forklift Operator, Champaign IL)
3/3 role match, top-1 in IL exactly
- /api/health: lakehouse ok (Rust path unchanged — control verified)
What this is NOT:
- Not an nginx flip — devop.live/lakehouse/* still goes through
/api/* → Rust :3100. /_go/* is parallel slice for opt-in.
- Not a tool-level cutover — each /_go/<path> is a manual choice;
no automatic mapping of Rust paths to Go equivalents.
- Not a transformation layer — caller sends Go-shaped requests
(e.g. /_go/v1/embed expects {texts, model}, not {text}).
Three cutover unit properties verified:
- ADDITIVE: zero modification to any existing Bun tool
- REVERSIBLE: unset GO_LAKEHOUSE_URL → /_go/* → 503
- ISOLATED: Rust gateway state unaffected (different port,
different binary, different MinIO bucket)
This is the cutover slice operators can use to validate Go-side
handlers under realistic frontend conditions before any
production-traffic flip. Next step (deferred): pick a specific
mcp-server tool to optionally route through Go with response-
shape adapter — that's a product-visible flip rather than this
infrastructure-visible slice.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Earlier push exposed the gap in the previous 2-layer isolation:
smokes still failed because they tried to bind :3211-:3220 which
my persistent stack already had. Smoke catalogd's bind-failure
went undetected because poll_health 3212 succeeded responding to
the persistent catalogd, and smoke proceeded against the wrong
backend with the wrong bucket expectations.
Fix: persistent stack now uses :4110 + :4211-:4219 via additional
sed in the temp toml (bind addresses + upstream URLs). Smoke
harnesses keep :3110 + :3211-:3219. Both reach the SAME chatd at
:3220 because chatd is read-mostly (no state to clobber) and
operators don't want to maintain two LLM provider key sets.
Three isolation layers now in effect:
1. Binary names (bin/persistent-* via symlinks)
2. MinIO buckets (lakehouse-go-persistent vs lakehouse-go-primary)
3. Port range (:4xxx vs :3xxx, with shared chatd on :3220)
Verified pre-push:
- 11 persistent ports listening on :4xxx + :3220
- 0 smoke ports listening on :3110-:3219 (free for smokes)
Pushed while persistent stack live — first cross-isolation test
(no port collision, no bucket collision, no name collision).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The 2026-05-01 persistent-stack milestone exposed two collision
modes between the long-running Go stack and the pre-push smoke
harness:
1. PKILL COLLISION: smoke teardown uses anchored
`pkill -f "bin/(storaged|...|gateway)$"`. Same-named persistent
processes match → smokes kill 7 of 11 persistent daemons.
2. MINIO STATE COLLISION: persistent stack writes
`_vectors/workers.lhv1` to the shared lakehouse-go-primary
bucket. Smoke vectord rehydrates from same bucket → sees both
smoke-owned and persistent-owned indexes → assertion failures.
Both fixed in this commit by adding two isolation layers:
LAYER 1 — distinct binary names via symlink:
bin/persistent-<daemon> → bin/<daemon>
Persistent stack runs as ./bin/persistent-gateway etc.
Smoke pattern `bin/(name)$` matches `bin/gateway$` but NOT
`bin/persistent-gateway$` (regex group requires bin/ followed
immediately by a daemon name; "bin/p..." doesn't qualify).
Cmdline lookup verified: 7 persistent procs, 0 match smoke pkill.
LAYER 2 — separate MinIO bucket via temp config:
Persistent stack writes to lakehouse-go-persistent (configurable
via $LH_PERSISTENT_BUCKET). Temp toml at /tmp/lakehouse-persistent.toml
inherits everything from lakehouse.toml except [s3].bucket which
is sed-replaced. Bucket auto-created via mc if missing.
Verified: workers.lhv1 lands in persistent bucket; primary
bucket _vectors/ stays empty.
Net effect: the persistent stack should survive `git push` (which
runs smokes that rehydrate vectord from primary bucket and pkill
their own bin/<name>$ daemons). This commit is the first push test
WITH the persistent stack live.
Caveat: bin/persistent-* symlinks are gitignored already (/bin/ is
in .gitignore wholesale), so the symlinks need to be created on
each fresh checkout — which start_go_stack.sh does idempotently.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three real-shape demand queries against the long-running 11-daemon
stack with 500 workers ingested from workers_500k.parquet (real
production data). Substrate is producing useful answers:
Q1 (Forklift @ Aurora IL): 5/5 role match, top 3 in IL, dist 0.44-0.46
Q2 (CNC @ Detroit MI): top-1 in Detroit MI exactly, role pulls
Machine Operator (semantic neighbor)
Q3 (Warehouse @ Indianapolis IN): top-1 in Indianapolis IN, 5/5 role
match, dist 0.42-0.54
This is the FIRST end-to-end coordinator-shape query against the
persistent Go stack — every prior reality test (real_001..real_005)
ran through harness-transient stacks that died on exit. This one
ran against daemons that have been up for minutes and stayed up
through retrieval.
Geo is load-bearing: top-1 city/state matched in 3/3 queries.
Embedder treats geography as a primary feature.
Q2's CNC→Machine Operator gap exposes the playbook learning loop's
purpose: judge would rate this ~3/5; the first time a coordinator
approves a Machine Operator for a CNC Operator query, that
recording starts shifting substrate behavior. That's the loop
we've been building toward — the persistent stack is now the
substrate that loop will run on.
Evidence: reports/cutover/persistent_stack_first_query.md (full
top-K tables + read on each query).
What this does NOT prove:
- Production-volume load (3 queries, 500 workers)
- Concurrent latency
- Full 5-loop substrate (this exercised retrieval only; no
playbook recordings exist on the persistent stack yet)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Caught immediately after the prior commit pushed: pre-push smokes
killed 7 of 11 persistent Go daemons because the smokes' anchored
`pkill -f "bin/(name)$"` teardown matches ANY process named
`bin/<daemon>`, not just the smokes' own children.
Documented in the script header as a KNOWN CONSTRAINT with a
workaround (re-run start_go_stack.sh after every push) and a
proper-fix sketch (give the persistent stack a different binary
name via build tag or symlink). Proper fix deferred until trigger
fires — operators living through this once will know to want it.
Persistent stack restored (all 11 healthy as of this commit).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
J's "let's go" instruction: leave OPEN list behind, push the Go
substrate forward into actual deployment shape. This commit marks
the first time the Go side has run as long-running daemons rather
than per-harness transient processes, and the first time the
shared cross-runtime longitudinal log has carried a Go-emitted
entry alongside the Rust ones.
What landed:
scripts/cutover/start_go_stack.sh — the persistent-stack runbook.
Brings up all 11 daemons (storaged → catalogd → ingestd → queryd
→ embedd → vectord → pathwayd → observerd → matrixd → gateway,
plus chatd-if-not-already-up) in dependency order via nohup +
disown. Anchored pkill per feedback_pkill_scope (never bare
"bin/"). Logs land in /tmp/gostack-logs/<bin>.log, one per daemon.
Verified live state:
- All 11 services healthy on :3110 + :3211-:3220
- gateway → embedd proxy returns nomic-embed-text-v2-moe vectors
- chatd reports 5/5 providers loaded
- No port collision with Rust gateway on :3100
- Daemons stay up after exit of the start script (production shape,
not harness-transient)
audit_baselines.jsonl crosses the runtime boundary:
- 7 Rust-emitted entries (last: ca7375ea 2026-04-27)
- 1 Go-emitted entry (ee2a40c 2026-05-01T07:53:54Z) appended via
./bin/audit_full -append-baseline
- Same envelope shape, same metric set, same drift comparator
semantics — operators running either runtime grow the same log
What this DOES prove:
- Substrate parity at deployment shape (not just unit tests)
- Cross-runtime artifact write-side compatibility (was previously
proven on read side via audit_baselines roundtrip)
- The deploy machinery works end-to-end for the persistent case
What this does NOT prove (still ahead):
- Real coordinator traffic against the Go stack (no nginx flip yet;
devop.live/lakehouse/ still serves through Rust)
- Go-side production materializer (Phase 2 is observer-only)
- Replay tool parity (Phase 7 is observer-only)
- The 5-loop product gate against actual humans
reports/cutover/SUMMARY.md now logs three new rows:
- audit-FULL with 12/12 phases ported
- First Go-emitted audit_baselines entry
- Persistent Go stack live
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes 4 of the 5 phases the initial audit-FULL port left as
deferred. The pattern: most "deferred" phases didn't actually need
the un-ported Rust pieces — they were observer-mode by design and
just needed to read existing on-disk artifacts.
Phase 1 (schema validators) → ported via exec.Command:
Invokes `go test ./internal/distillation/...` — the Go equivalent
of Rust's `bun test auditor/schemas/distillation/`. New
GoTestModule field on AuditFullOptions controls the package
pattern; empty disables the invocation (test mode, prevents
recursion when audit-full is invoked from inside `go test`).
Phase 2 (evidence materialization) → ported as observer:
Reads data/evidence/ directly and tallies rows + tier-1 source
hits. Doesn't re-run the materializer (which is Rust-side TS).
Emits p2_evidence_rows + p2_evidence_skips metrics matching
Rust shape — drop-in audit_baselines.jsonl entries possible.
Phase 5 (run summary) → ported as observer:
Reads reports/distillation/{run_id}/summary.json + 5 stage
receipts. Validates schema_version=1, run_hash sha256, git_commit
40-char hex, all stage receipts decode as JSON. Full schema
validation (StageReceipt schema) is intentionally NOT ported —
it would require porting the TS schemas/distillation/ validators
in full; basic shape checks catch the load-bearing invariants.
Phase 7 (replay log) → ported as observer:
Reads data/_kb/replay_runs.jsonl, validates last 50 rows parse
as JSON. Skips the live-replay invocation that Rust's phase 7
also does — porting Rust replay.ts is substantial and not in
scope. The "log shape sanity" check is what audit-full actually
needs; the live invocation is a separate concern.
Phase 6 (acceptance gate) — STILL SKIPPED:
Rust acceptance.ts is a TS-only fixture harness with bun-specific
deps. Porting the fixtures (tests/fixtures/distillation/acceptance/)
+ the 22-invariant runner to Go is an ADR-worth undertaking.
Documented in the header comment.
Live-data probe (against /home/profit/lakehouse):
Skips count: 4 → 1 (only phase 6).
Required checks: 6/6 → 12/12 PASS.
New metric: p2_evidence_rows=1055, BYTE-EQUAL to the Rust
pipeline's collect.records_out from the latest summary.json.
Cross-runtime parity now extends across phases 0/1/2/3/4/5/7.
6 new tests:
- TestPhase2_EvidenceTallyFromOnDisk: row + tier-1-hit tallying
- TestPhase5_FullSummaryFlow: complete run-summary fixture passes
- TestPhase5_ShortRunHashCaught: bad run_hash fails required check
- TestPhase7_ReplayLogReadsFromDisk: row-count reporting
- TestPhase7_MalformedTailRowsCaught: structural parse failure
- TestRunAuditFull_FullFixtureFlow updated to seed evidence/ +
reports/distillation/ for the phases now wired.
Cleanup: removed local sortStrings helper (replaced with sort.Strings
now that `sort` is imported for phase 5's mtime-sort).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3-lineage scrum on 434f466..0d4f033 surfaced one convergent finding
(Opus + Kimi) and 3 Opus-only real bugs. All actioned in this
commit. Two false positives (Kimi rollback misreading, Opus stale-
comment claim) verified + rejected — both required manual control-
flow inspection to refute, matching the documented Kimi-truncation
behavior in feedback_cross_lineage_review.md.
Convergent fix — DecodeIndex lost nil-meta items:
- Envelope version bumped 1 → 2.
- New v2 field: IDs []string carries the canonical ID set
explicitly, independent of meta map's nil-vs-{} sparseness.
- DecodeIndex accepts both versions: v2 reads from env.IDs; v1
falls back to meta-key inference (with the documented
limitation that nil-meta items are invisible — preserved for
backward-compat with already-persisted indexes).
- Encode emits v2 going forward.
- 2 new regression tests:
- TestEncodeDecode_NilMetaItemsSurviveRoundTrip: items added
with nil metadata MUST survive Encode → Decode and remain
visible to IDs(). Pre-fix would have yielded IDs() == [].
- TestDecodeIndex_V1BackwardCompat: hand-crafted v1 envelope
still decodes (proves the fallback path).
Opus-only fixes:
- handleMerge: non-ErrIndexNotFound errors at h.reg.Get(name) /
h.reg.Get(req.Dest) now return 500 + log instead of falling
through with nil src/dest pointers (which would panic on the
next deref). Real bug — only the sentinel error was handled.
- internal/drift/drift.go: mathLog wrapper removed; math.Log
inlined. Wrapper added no value (math was already imported).
- internal/distillation/audit_baseline.go: BuildAuditDriftTable's
bubble sort replaced with sort.Slice. Idiomatic + shorter.
Rejected after verification:
- Kimi WARN "missing rollback on partial merge": misread the
control flow. Code at cmd/vectord/main.go:404-414 does NOT
delete from src when dest.Add fails (continue before reaching
src.Delete). Only successful Adds trigger Deletes.
- Opus INFO "TimestampUnixNano comment references missing field":
field exists at scripts/multi_coord_stress/main.go:128. Opus
saw only the diff context, not the full file.
Deferred (no fired trigger):
- Opus WARN "no per-index lock during merge": no concurrent merge
callers today (operators run merge as deliberate one-shot job).
Worth a lock if/when matrixd or chatd start auto-triggering.
Disposition: reports/scrum/_evidence/2026-05-01/verdicts/post_role_gate_v1_disposition.md.
Build + vet + tests green; 2 new regression tests + all prior tests
unchanged.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Same shape of proof as embed_parity.sh for the embed endpoint:
take the just-shipped Go port (ca142b9) and validate it against
the actual production data the Rust legacy emits, not just unit-
test fixtures. Locks the cross-runtime parity that operators
running mixed pipelines depend on.
scripts/cutover/audit_baselines_validate.go:
- Reads /home/profit/lakehouse/data/_kb/audit_baselines.jsonl
- Parses every entry via the Go AuditBaseline struct
- Round-trips the last entry: encode → decode → field-by-field
equality check (catches any silently-dropped JSON keys)
- Calls LoadLastBaseline against the live file (proves the public
API works on real shapes, not just inline parsing)
- Computes BuildAuditDriftTable(first → last) — full-window
lineage drift over the captured baselines
Live-data probe results (reports/cutover/audit_baselines_roundtrip.md):
- 7 entries parse without error
- Round-trip is byte-equal on every metric + every header field
- Drift table fires the expected verdicts:
- p2_evidence_rows 12→82 (+583%) → warn (above 20% threshold)
- p3_accepted/partial/rejected/human 0→non-zero → warn (the
zero-baseline edge case TestBuildAuditDriftTable_ZeroBaseline
was designed to lock — verified now firing on real history)
- p4_* metrics +0% → ok (stable across the window)
What this does NOT prove (documented in the report): the Go-side
audit-FULL pipeline that PRODUCES baselines doesn't exist yet.
Only the load/append/drift substrate is ported. Operators running
audit-full from Go would still need a metric-collection pass —
that's a separate port deliberately not in this wave.
reports/cutover/SUMMARY.md gains a new row alongside the embed
parity entries; cutover-prep verification log keeps the
discipline of "verified against real data, not just fixtures."
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The original OPEN #2 line called for "SFT export pipeline +
audit_baselines lineage." Commit 7bb432f shipped the SFT export.
This commit ports the audit_baselines half — the longitudinal
drift signal that distinguishes "metrics shifted because the world
changed" from "metrics shifted because we broke something."
Mirrors Rust scripts/distillation/audit_full.ts's substrate:
- LoadLastBaseline(path) reads the most recent entry from
data/_kb/audit_baselines.jsonl. Returns (nil, nil) on missing
file (first run), errors on truncated last line (partial-write
detection — operators don't lose drift signal silently).
- AppendBaseline(path, baseline) appends one entry as a JSON line.
Atomic at the line level via bufio + O_APPEND. Creates the
parent directory if missing.
- BuildAuditDriftTable(prior, current, threshold) computes
per-metric drift. flag values mirror Rust exactly: first_run,
ok, warn. DefaultDriftWarnThreshold = 0.20 = Rust's 20%.
- FormatAuditDriftTable renders a fixed-width text grid for
stdout dumps in audit-full runs.
Edge cases handled:
- Zero-baseline: prior=0 means no division — PctChange stays nil.
current=0 → ok (no change). current>0 → warn (zero→nonzero is
always notable, never silently fine).
- New metric in current: flagged first_run, not "0%-change".
Operators see "this is a new signal we haven't tracked before."
- Sort: stable by metric name for deterministic JSON output and
clean CI diffs.
Generic on metric name (vs Rust's pinned p2_evidence_rows etc.):
the Rust phase numbering doesn't translate to Go directly. The
AuditBaselineRustCompat constant pins the Rust names so operators
running both runtimes use the same labels, which makes drift
comparison meaningful across the two pipelines.
13 new tests covering: missing file, last-line-wins, blank-line
tolerance, malformed-line errors, append round-trip, append-to-
existing, schema validation, first-run, threshold boundary,
zero-baseline, new-metric-in-current, sort-by-metric stability,
formatter output rendering.
OPEN #2's "audit_baselines lineage" half now closed. The
distillation package surface is at parity with the Rust pipeline:
scorer, scored runs, SFT export, audit baselines all available
on the Go side.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Follow-up to b216b7e (which shipped the SFT export substrate). This
commit ports the synthesis logic, completing the migration:
- SynthesizeSft(scored, ev, recordedAt, sftID) → *SftSample
Mirrors the Rust synthesizeSft byte-for-byte. Returns nil for
extraction-class records + empty-text records (same skip
semantics as Rust).
- LoadEvidenceByRunID(scoredPath, cache) reads the paired evidence
JSONL (path derived by /scored-runs/ → /evidence/ replacement).
Per-call cache so multiple scored-runs files in the same dir
don't reload the same evidence.
- buildInstruction maps source_file stem → per-class instruction
template. All 8 templates (scrum_reviews, mode_experiments,
auto_apply, audits, observer_reviews, contract_analyses,
outcomes, default) match Rust output exactly so a/b validation
between runtimes can diff JSONL byte-for-byte.
- stemFromSourceFile strips data/_kb/ prefix + .jsonl suffix.
- ExportSft now writes data/distilled/sft/sft_export.jsonl with
the synthesized samples (DryRun=true skips file write).
Per-class templates verified by 8-case sub-test:
- scrum_reviews → "Review the file '...' against the PRD..."
- mode_experiments → "Run task_class='...' for file..."
- auto_apply → "Auto-apply: emit a 6-line surgical patch..."
- audits with phase: prefix → strips to bare phase name
- observer_reviews → "Observer-review the latest attempt..."
- contract_analyses with permit: prefix → strips to permit ID
- outcomes → "Run scenario; report per-event outcome..."
- unknown source → "Source 'X' run; produce the appropriate output"
Caveat documented inline: contract_analyses uses ev.metadata.contractor
in Rust to produce "Analyze contractor 'X' for permit 'Y'" when
present. Go's EvidenceRecord doesn't carry a free-form metadata bag
yet, so we always emit the no-contractor form. Operators needing
contractor-aware instructions can extend EvidenceRecord with an
explicit Metadata field (separate ADR).
Test additions (5 new):
- TestSynthesizeSft_PerSourceClass: 8 sub-cases, one per template
- TestSynthesizeSft_RejectsExtraction: extraction-role records skipped
- TestSynthesizeSft_RejectsEmptyText: empty/whitespace text skipped
- TestSynthesizeSft_ContextAssembly: matrix + pathway + model
context string formatting matches Rust " · " join
- TestExportSft_FullPort_WritesJSONL: end-to-end fixture, asserts
output contains expected instruction + omits firewalled records
Pre-existing TestExportSft_PartialPort_FirewallFires renamed +
updated to TestExportSft_FirewallFiresBeforeEvidenceLoad — reflects
the new contract that records passing the firewall but lacking
evidence land in "not-instructable" rather than being silently
exported. Honest semantics shift documented in the test.
OPEN #2 now fully closed (was: substrate-only). The synthesis path
no longer requires the Rust pipeline to be invoked — Go-side
operators can run the full distillation export end-to-end.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Substantial wave addressing all 4 prior OPEN items. Three closed in
full, one partially (the speculative half deliberately deferred).
OPEN #1 — Periodic fresh→main index merge (FULL):
- POST /v1/vectors/index/{src}/merge with {dest, clear_source}
- Idempotent on re-runs (existing-in-dest items skipped)
- internal/vectord/index.go: new Index.IDs() snapshot method +
i.ids tracker field as canonical ID set, independent of meta
map's nil-vs-{} sparseness (was a real bug — IDs() backed by meta
alone missed items added with nil metadata)
- 4 cmd-level integration tests (happy path drain+clear, dim
mismatch, dest not found, self-merge rejection) + 1 unit test
- DecodeIndex backward-compat: old envelopes restore i.ids from
meta keys (best effort; new items going forward use the tracker)
OPEN #2 — Distillation SFT export (SUBSTRATE):
- internal/distillation/sft_export.go ports the load-bearing half:
IsSftNever predicate + ListScoredRunFiles (data/scored-runs/YYYY/
MM/DD walk) + LoadScoredRunsFromFile + partial ExportSft.
- Synthesis (instruction/input/response generation) deferred to a
separate wave — too big for this session, but the substrate
makes the next wave a port-not-design exercise.
- TestSftNever_PinsExpectedSet locks the contamination firewall
set: if a future commit adds/removes from SftNever, this test
fails — forcing the change through review.
- 5 new tests; firewall fires end-to-end through the partial port.
OPEN #3 — Distribution drift via PSI (FULL):
- internal/drift/drift.go: ComputeDistributionDrift via Population
Stability Index. Standard finance/risk metric, well-defined
verdict tiers (stable < 0.10, minor 0.10–0.25, major ≥ 0.25).
- Equal-width bucketing over combined min/max so neither dist
falls outside; epsilon-clamping for empty buckets so log doesn't
blow up. Per-bucket breakdown for drilldown.
- Pairs with the existing ComputeScorerDrift: scorer drift is
categorical, distribution drift is continuous. Different shapes,
same package.
- 7 new tests covering identical-is-stable, hard-shift-is-major,
moderate-detected-not-stable, empty-inputs-safe, all-identical-
safe, bucket-counts-conserved, num-buckets-clamping.
OPEN #4 — Ops nice-to-haves (PARTIAL — wall-clock done, others
deferred):
- (a) Real-time wall-clock for stress harness: per-phase elapsed
time logged to stdout as it runs (`[stress] phase NAME starting
(T+12.3s)` + `[stress] phase NAME done — 8.5s (T+20.8s)`).
Output.PhaseTimings + Output.TotalElapsedMs in JSON.
- (b) chatd fixture-mode S3 mock + (c) liberal-paraphrase
calibration: not actioned — no fired trigger, would be
speculative. Documented as deferred-until-need rather than
ignored. Per the project's discipline ("don't add features
beyond what the task requires").
OPEN list now empty / steady-state. Future items will land as
production triggers fire.
Build + vet + tests green; 18 new tests across the 4 closures.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Real wire-up gap discovered post-scrum: Demand.Role was already
extracted at every call site in multi_coord_stress (44 occurrences,
both contract-driven and LLM-parsed inbox-triggered paths), but
neither matrixSearch nor playbookRecord accepted role in their
signatures. Cross-role gate (real_001..real_004 work) was bypassed
for the entire multi-coord harness — recordings and queries went
through with empty role, gate fell back to lenient behavior.
Fix:
- matrixSearchReq gains query_role field
- matrixSearch signature: (..., query, role string, ...)
- tracedSearch wrapper gains role param + emits it in span input
metadata for Langfuse visibility
- playbookRecord signature: (..., query, role, ...) — body emits
role only when non-empty (preserves backward compat at API)
- 14 call sites updated:
contract-driven Demand loops → d.Role
LLM-parsed inbox path → parsed.Role (qwen2.5 already extracts it)
swap path (warehouseDemand) → warehouseDemand.Role
reissue path → ev.Role (captured at original event time)
fresh-verify (resume snippet, no role concept) → ""
Build clean, vet clean, all tests pass. Cross-role gate now fires
end-to-end across the multi-coord harness — matches the playbook_lift
harness's coverage from the original real_001 fix.
This closes the symmetric gap to scripts/playbook_lift's existing
wire-through. Both production-shape harnesses now exercise the role
gate; future reality tests automatically inherit the protection.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
5 explicit-negation queries ("Need Forklift Operators in Aurora IL,
NOT in Detroit", "excluding Cornerstone Fabrication roster", etc.)
through the standard playbook_lift harness. Goal: characterize
whether the substrate has negation handling or silently treats
"NOT X" as "X".
Headline: substrate has zero negation handling. Cosine on dense
embeddings tokenizes "NOT in Detroit" identical to "in Detroit"
plus noise — there is no logical-quantifier representation in the
embedding space. This is a structural property of dense embeddings,
not a substrate bug.
Per-query observations:
- Q1 (Aurora IL, NOT Detroit): all top-10 rated 1-2/5 by judge
- Q2 (NOT Beacon Freight): top-1 rated 4/5 — accidentally OK
because role+city signal pulled non-Beacon worker naturally
- Q3 (excluding Cornerstone): unanimous 1/5 across top-10
- Q4 (NOT Detroit-area): all top-10 rated 1-2/5
- Q5 (exclude Heritage Foods): top-1 rated 4/5 — accidentally OK
The judge IS the safety net: when retrieval can't honor the
constraint, the judge refuses to approve any result. That's the
honesty signal — `discovery=0` for the run aggregates it.
No code change. The architectural answer for production is:
- UI surfaces an "exclude" affordance that populates ExcludeIDs
(already supported, added in multi-coord stress 200-worker swap)
- Coordinators don't type natural-language negation — they click
- Substrate's role: surface honesty signal (judge ratings) + don't
pretend to honor unparseable constraints
Adding NL-negation handling at the substrate level would be product
debt — it would let coordinators type sloppier queries that
silently fail when the LLM extractor misses a phrasing. Don't ship
until production traffic demonstrates demand for it.
Findings: reports/reality-tests/real_005_findings.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3-lineage scrum review of the role-gate work (commits 7f2f112..0331288)
ran Opus 4.7 / Kimi K2.6 / Qwen3-coder via scripts/scrum_review.sh.
All three flagged the same edge case: the homegrown plural-stripper
in roleNormalize would collapse non-plural-s tokens like "Sales" →
"Sale", "Logistics" → "Logistic", "Operations" → "Operation". In a
staffing domain those are real role names; the silent normalization
would have caused false role-equality matches and re-opened the
cross-role bleed for those clusters.
Fix:
- nonPluralSWords allowlist for known staffing-domain non-plural-s
tokens (sales, logistics, operations, facilities, premises, news,
physics, economics, mathematics, analytics).
- Last-word-only stripping ("Sales Associate" stays whole; only
"Associates" head noun is plural-checked).
- -ss ending check so "Press Operator", "Boss" don't lose their s.
- strings.ToLower + strings.TrimSpace replace the homegrown rune-
loop ASCII normalizer (Opus INFO — minor cleanup, folded in).
Tests:
- TestRoleNormalize_NonPluralS: 18 cases covering the allowlist,
-ss ending, real plurals (Operators → Operator, Boxes → Box),
multi-word real plurals (Forklift Operators → forklift operator),
whitespace/case tolerance.
- TestRoleEqual_NonPluralS: gate-level pairing — proves equal-
shape allowlisted tokens compare equal AND that "Sales" ≠ "Sale"
(the original bug shape).
- Existing TestRoleEqual_PluralAndCase still green (refactor
preserved behavior).
Other scrum findings dispositioned (not actioned):
- Opus WARN on empty-role fail-open semantics: documented
backward-compat behavior; production path closes via opt-in LLM
extractor (real_004).
- Opus INFO on unsynchronized package-global cache map: harness is
single-goroutine; add sync.Mutex when/if it parallelizes.
- Opus INFO on parallel constructor (NewPlaybookEntryWithRole vs
optional arg): API smell only, both forms preserved.
- Kimi 2 BLOCKs (NewPlaybookEntryWithRole missing, ApplyPlaybookBoost
signature breakage): FALSE positives. Pre-push smoke chain green
on 0331288, both symbols + all call sites compile clean. Matches
feedback_cross_lineage_review.md's documented Kimi truncation
behavior — Kimi BLOCKs warrant trace verification before action.
Disposition (local): reports/scrum/_evidence/2026-04-30/verdicts/role_gate_v1_disposition.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
real_003 left a known-weak hole: shorthand-style queries
("{count} {role} {city} {state} ...") have no separator between
role and city, so a regex can't reliably extract — leaving the
cross-role gate disabled when both record AND query are shorthand.
This commit adds a roleExtractor with regex-first + LLM fallback:
- Regex first (fast, deterministic) — handles need + client_first +
looking from real_003b. ~75% of styles, no LLM cost paid.
- LLM fallback when regex returns empty AND model is configured —
Ollama-shape /api/chat with format=json, schema-tight prompt,
temperature 0. ~1-3s on local qwen2.5.
- Per-process cache — paraphrase + rejudge passes reuse the same
query 4× per run; cache prevents 4× LLM cost.
- Off-by-default — opt-in via -llm-role-extract flag (CLI) and
LLM_ROLE_EXTRACT=1 env var (harness wrapper). real_003b shipping
config unchanged unless explicitly enabled.
8 new tests in scripts/playbook_lift/main_test.go:
- TestRoleExtractor_RegexFirst: LLM not called when regex matches
- TestRoleExtractor_LLMFallback: shorthand goes to LLM
- TestRoleExtractor_LLMOffLeavesEmpty: opt-in default preserved
- TestRoleExtractor_Cache: 3 calls = 1 LLM hit
- TestRoleExtractor_NilSafe: nil receiver runs regex only
- TestExtractRoleViaLLM_HTTPError + _BadJSON: failure paths
- TestRoleExtractor_ClosesCrossRoleShorthandBleed: synthetic
witness for the real_003 scenario — both record + query are
shorthand, regex returns "" for both, LLM produces DIFFERENT
role tokens for CNC vs Forklift, so matrix gate's cross-role
rejection (locked separately in
TestInjectPlaybookMisses_RoleGateRejectsCrossRole) fires
correctly. This is the load-bearing verification.
Reality test real_004 ran the same 40-query stress as real_003 with
LLM extraction on. Cross-style same-role boosts fired correctly
across all 4 styles for Loaders + Packers + Shipping Clerk clusters
(including shorthand → other-style transfer). No cross-role bleed
observed. The reality test alone can't be a clean "with vs without"
comparison (HNSW build is non-deterministic across runs, and
real_004 stochastics didn't trigger a shorthand recording at all),
which is why the unit-test witness exists.
Production note (in real_004_findings.md): LLM extraction is for
reality-test coverage of arbitrary query shapes. Production should
extract role at INGEST time (when the inbox parser already runs an
LLM) and pass already-resolved role through requests — same shape
as multi_coord_stress's existing Demand{Role: ...} model. The hot
path should never need the harness extractor's per-query LLM cost.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Stress-tests the role gate with 40 queries (10 fill_events rows × 4
styles): need, client_first, looking, shorthand. Each row's role +
client + city stays the same; only the surface phrasing changes.
real_003 (original extractor) confirmed the shorthand-vs-shorthand
failure mode: CNC Operator shorthand recording leaked w-2404 onto
Forklift Operator shorthand query within the same Beacon Freight
Detroit cluster. Both record + query had empty role (extractor
returns "" for shorthand because there's no separator between role
and city), gate disabled, distance check passed, bleed fired.
Fix: extended extractRoleFromNeed to handle client_first
("{client} needs N {role} in...") and looking ("Looking for N
{role} at...") patterns. Shorthand left intentionally unmatched —
"Forklift Operator Detroit" is shape-indistinguishable from
"Forklift" + "Operator Detroit" without an LLM extractor or known-
cities lookup.
real_003b (extended extractor) verifies bleed closed across all 4
styles for this dataset. Forklift Operator queries keep w-2136 (the
cold-pass-correct match) regardless of which style the query came
in. Same-role boosts now fire correctly across styles — a CNC
Operator recording made in `looking` style boosts the CNC need-form
query.
scripts/cutover/gen_real_queries.go: added -styles flag with values
need|client_first|looking|shorthand|all (default need preserves
real_001/002 behavior). Tests/reality/real_coord_queries_v2.txt is
the 40-query stress file.
scripts/playbook_lift/main_test.go: 10 sub-tests lock the four
documented patterns + shorthand limitation + lift-suite-style
queries (no clean role, returns empty as expected).
Aggregate metrics:
- real_003 (original): disc=7, lift=7, boost=14, meanΔ=-0.108
- real_003b (extended): disc=11, lift=10, boost=31, meanΔ=-0.202
The growth reflects more LEGITIMATE same-role same-cluster transfer
firing across styles, not bleed (verified by per-cluster bleed
table — Forklift Operator queries unchanged across all 4 styles).
Known limitation documented in real_003_findings.md: same-cluster,
same-role queries in shorthand still embed close enough that a
shorthand recording could bleed onto a different-role shorthand
query if both record + query strip role. Closing this requires
LLM extraction or known-cities lookup at record + query time.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
real_001 surfaced same-client+city queries bleeding across roles:
Q#2 (Forklift Operator @ Beacon Freight Detroit) recorded e-6193
in the playbook corpus. Q#5 (Pickers same client+city) and Q#10
(CNC Operator same client+city) embedded within 0.13-0.18 cosine of
Q#2's query — well inside the 0.20 inject threshold — so e-6193
injected on both, demoting the cold-pass-correct workers.
Root cause: the inject distance threshold isn't tight enough on
the same-client+city cluster. Cosine collapses queries that share
city + client + count-token + time-token regardless of role. The
existing judge gate is per-injection at record time and doesn't
fire at retrieve time.
Fix: structural role gate in front of both Shape A boost and
Shape B inject. PlaybookEntry gains Role; SearchRequest gains
QueryRole. When both are non-empty and differ under roleEqual's
case+plural normalization, the entry is rejected before BoostFactor
or judge-gate logic runs.
Backward-compat: empty role on either side disables the gate —
preserves behavior for the lift suite's free-form multi-constraint
queries that have no clean single role. Caller-supplied (not
inferred), so existing recordings unaffected.
Wire-through:
- internal/matrix/playbook.go: Role field, NewPlaybookEntryWithRole,
roleEqual helper with plural+case normalization
- internal/matrix/retrieve.go: QueryRole on SearchRequest, threaded
to both ApplyPlaybookBoost + InjectPlaybookMisses
- cmd/matrixd/main.go: role on POST /matrix/playbooks/record + bulk
- scripts/playbook_lift/main.go: extractRoleFromNeed regex pulls
role from "Need N {role}{s} in" queries (the fill_events shape);
free-form queries fall back to empty (gate disabled)
Tests (5 new):
- TestInjectPlaybookMisses_RoleGateRejectsCrossRole: exact Q#10
scenario (distance 0.135, recorded "Forklift Operator", query
"CNC Operator") — locks the bleed at unit level
- TestInjectPlaybookMisses_RoleGateAllowsSameRole: Forklift Operator
recording fires on Forklift Operators query (plural normalization)
- TestInjectPlaybookMisses_RoleGateBackwardCompat: empty Role on
either side = gate disabled, preserves current behavior
- TestApplyPlaybookBoost_RoleGateRejectsCrossRole: Shape A defense
in depth — boost doesn't fire on cross-role even when answer is
in cold top-K
- TestRoleEqual_PluralAndCase: case + -s + -es plural normalization
Verification (real_002, same query set as real_001):
- Q#5 Pickers @ Beacon Freight: e-6193 → e-8499 (no bleed)
- Q#10 CNC Operator @ Beacon Freight: e-6193 → w-2404 (no bleed)
- Discoveries + lifts unchanged at 2 each (same-role lift still fires)
- Mean Δdist tightens from -0.127 to -0.040 (boosts no longer
pulling distances through the floor on cross-role mismatches)
Findings: reports/reality-tests/real_002_findings.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
First retrieval probe with non-synthetic query distribution. Pulls
N rows from /home/profit/lakehouse/data/datasets/fill_events.parquet
(real-shape demand data) and translates each to the natural language
a coordinator would type: "Need {count} {role}s in {city} {state}
starting at {at} for {client}".
Headline: 8/10 cold-pass top-1 = judge-best on real distribution.
Substrate works on queries it was never trained for. v2-moe + workers
corpus carry the load.
Surfaced finding (the real value of running this): same-client+city
queries cluster, and Shape A's distance boost bleeds across roles
within the cluster. Q#2 (Forklift @ Beacon Freight Detroit) records
e-6193 in the playbook corpus. Q#5 (Pickers same client+city) and
Q#10 (CNC Operator same client+city) inherit e-6193 at warm top-1
even though:
- Neither query has its own recorded playbook.
- Neither warm pass triggers a Shape B inject (boosted=0).
- The roles are different staffing categories.
Q#10 specifically demoted the cold-pass-correct w-3759 (judge rating
4 at rank 0) for a worker who was approved by the judge for a
different role on a different query.
Why the lift suite missed it: synthetic queries use 7 disjoint
scenario buckets (forklift+OSHA+WI / CDL+IL / etc.). Real demand
clusters on (client, city). The cluster doesn't exist in the
synthetic distribution.
Why the judge gate doesn't catch it: the gate (5a3364f) is
per-injection at record time. After approval the worker rides Shape A
distance boosts on all later same-cluster queries with no second
gate call.
Becomes new OPEN #1. Fix candidate: role-scoped playbook corpus
metadata + Shape A boost gate on role match. Cheap; doesn't need
new judge calls.
Files:
- scripts/cutover/gen_real_queries.go: parquet → coordinator NL
- tests/reality/real_coord_queries.txt: 10 generated queries
- reports/reality-tests/playbook_lift_real_001.md: harness output
- reports/reality-tests/real_001_findings.md: the reading
Repro:
go run scripts/cutover/gen_real_queries.go -limit 10 > tests/reality/real_coord_queries.txt
QUERIES_FILE=tests/reality/real_coord_queries.txt RUN_ID=real_001 \
WITH_PARAPHRASE=0 WITH_REJUDGE=0 ./scripts/playbook_lift.sh
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
First concrete cutover artifact: scripts/cutover/embed_parity.sh
brings up Go embedd + gateway alongside the live Rust gateway,
hits both /ai/embed and /v1/embed with the same forced model, and
emits a per-date verdict report under reports/cutover/.
Why embed first: the parity invariant is one math identity (cosine
sim of vectors against same input). Retrieve has thousands of edge
cases. If embed parity holds, all downstream vector consumers
inherit confidence; if it doesn't, we catch it in 30s instead of
after a flip.
Verdict 2026-04-30: 5/5 samples cosine=1.000000 with model forced
to nomic-embed-text (v1). Same with nomic-embed-text-v2-moe (both
Ollamas have it loaded). Math is provably equivalent across the
gateway plumbing.
Drift catalog (reports/cutover/SUMMARY.md):
- URL: Rust /ai/embed vs Go /v1/embed
- Wire: Rust {embeddings, dimensions} (plural) vs Go {vectors,
dimension} (singular). Wire-format adapter is the only real
cutover work for this endpoint.
- L2 norm: Rust unit vectors (~1.0); Go raw Ollama (~20-23). Same
direction (cos=1.0); harmless under cosine-distance HNSW (which
is Go vectord's default), but worth fixing in internal/embed/
before extending to euclidean indexes.
reports/cutover/ now tracked (joined the scrum/ + reality-tests/
exemptions in .gitignore).
Next probe: /v1/matrix/retrieve ↔ Rust /vectors/hybrid for the
real user-facing retrieve path. Embed parity gives that probe a
clean foundation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`jq --arg` and `curl --data-binary @-` both read stdin/argv-bound
buffers. Diffs >~128KB blow past the kernel's argv limit even when
piped via stdin (because we still build `body` as a shell variable
first, then feed it to curl). Voice-ai full bundle was 156K and
hit it.
Switch to writing user/system/body to mktemp files, jq reads via
--rawfile, curl reads via @file. Same on-the-wire shape, no argv
involvement. Cleanup with rm at the end.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds langfuseMiddleware in internal/shared so every daemon's
shared.Run gets free production-traffic trace visibility when
LANGFUSE_URL + LANGFUSE_PUBLIC_KEY + LANGFUSE_SECRET_KEY are set.
Same env names + file shape as the multi_coord_stress driver, so
operators ship one /etc/lakehouse/langfuse.env across the deploy.
Wiring is auth-gated: middleware runs INSIDE the RequireAuth group,
so 401s from credential-stuffing don't pollute traces. /health is
exempt so LB probes don't either. Missing env vars → nil client →
middleware is a passthrough no-op (fail-open per ADR-005 5.1).
Bundled deploy:
- langfuse.env.example template (mode 0640, root:lakehouse)
- 11 systemd units gain `EnvironmentFile=-/etc/lakehouse/langfuse.env`
(leading - so missing file = OK)
- REPLICATION.md bootstrap section documents setup
Tests (4): nil passthrough, /health bypass, real-request emission,
status-writer wrapping. All green.
STATE_OF_PLAY OPEN list: 5 rows → 4 rows.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Lift suite run #004 left two unresolved tail issues:
- Q6 ("Forklift loader") ↔ Q7 ("Hazmat warehouse, cold storage")
swap recordings as warm top-1 because their embeddings are within
0.20 cosine of each other. Distance gate can't tell them apart.
- Q9 + Q15 lose paraphrase recovery when qwen2.5 rephrases past the
0.20 threshold. Distance says "drift too far"; sometimes the drift
is real (skip), sometimes the paraphrase is still on-domain (don't
want to skip).
Multi-coord run #008's judge re-rating proved the LLM can
distinguish: Q3 crane case landed at distance 0.23 (looks tight)
but rating 1 (irrelevant). The judge sees domain mismatch the
embedder doesn't.
This commit lifts that pattern into the matrix substrate. Shape B
inject now optionally routes every candidate through a judge gate
before the rank insert lands. Distance + judge BOTH have to approve.
internal/matrix/playbook.go:
- InjectPlaybookMisses signature gains a query string + an
optional InjectGate. nil gate preserves pre-judge-gating
behavior (current tests already pass with nil).
- New InjectGate interface + InjectGateFunc adapter for tests
and non-LLM callers.
- Per-candidate gate.Approve(query, hit) call inserted between
the dedup and the inject. Rejected candidates skip silently;
injected count reflects post-gate decision.
internal/matrix/judge.go (new, ~140 lines):
- LLMJudgeGate calls an Ollama-shape /api/chat endpoint with the
same 1-5 staffing-rubric prompt that worked in multi_coord
run #008. fail-closed on HTTP/JSON errors (don't inject if
judge can't speak — better miss than wrong-domain).
- NewLLMJudgeGate returns nil when URL or Model is empty,
matching InjectGate's nil-means-no-judge semantics.
internal/matrix/retrieve.go:
- SearchRequest gains JudgeURL, JudgeModel, JudgeMinRating
fields. Run() builds an LLMJudgeGate when set; passes nil
otherwise. Backward compatible — existing callers see no
behavior change.
Tests:
- TestInjectPlaybookMisses_GateRejectsCandidate (rejectAll → 0
injected, even with tight distance)
- TestInjectPlaybookMisses_GateApprovesCandidate (approveAll →
same as nil-gate behavior)
- TestInjectPlaybookMisses_GateSeesCorrectQuery (gate receives
CURRENT query + RECORDED query separately so it can score
the (current, candidate) pair)
- All 5 existing inject tests updated to new signature
go test ./internal/matrix → all 8 inject tests pass.
go test ./internal/matrix ./internal/shared ./cmd/{matrixd,
queryd,pathwayd,observerd} → all green.
STATE_OF_PLAY:
- OPEN item #1 (judge-gated injection) closed.
- DO NOT RELITIGATE adds the substrate-level judge-gate lock.
- OPEN list now 5 rows (was 6).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Sprint 4 row removed (shipped: a59ef5b systemd + 54a05d9 docker).
ADR-006 row already dropped on the previous STATE update.
Two lift-suite tail items (Q6↔Q7 adjacent-query, Q9/Q15 liberal-
paraphrase) consolidated into one "judge-gated playbook injection"
row — both are downstream of the same fix (let the judge approve
before Shape B inserts). Captures the design lineage from
multi-coord run #008's judge-rating pattern.
Three items folded into a single "operational nice-to-haves" row:
real-time clock, chatd fixture storage half, liberal-paraphrase
calibration. None are product-blocking; each lights up when
someone hits its specific trigger.
Reorder reflects leverage on the active product theory (multi-
coord staffing co-pilot via the 5-loop substrate), not effort:
1. Judge-gated injection (lift quality + lift-tail closure)
2. Wider Langfuse instrumentation (production observability)
3. Fresh→main merge (operational hygiene as the corpus grows)
4. Distillation full port (production dependency, not yet)
5. Drift quantification (research)
6. Operational nice-to-haves
Lead-in note added: "Items move to closed when the work demands
them, not on a calendar." Locks intent against future drift toward
a sprawling todo list.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Parallel deploy target to the systemd units that landed in a59ef5b.
Single image carries all 11 daemons; docker-compose runs one
container per daemon with the same dependency graph as the systemd
units. Useful when systemd isn't available (Mac dev, remote VMs
without root) or when isolation to a private docker network is
preferred.
Dockerfile (multi-stage):
- Builder: golang:1.25-bookworm. DuckDB cgo needs gcc + glibc;
alpine's musl doesn't link the official duckdb-go bindings cleanly.
- Runtime: debian:bookworm-slim — same libc, much smaller surface.
Adds ca-certificates (outbound HTTPS to OpenRouter/OpenCode/Kimi),
curl + jq (in-container healthchecks + smoke probes), tini (PID 1
signal forwarding so docker stop sends SIGTERM to the daemon, not
to a wrapper).
- Single image, multiple binaries. Ships all 11 cmd/* + 3 scripts/
(staffing_workers, playbook_lift, multi_coord_stress) so deployed
stacks can run reality tests against themselves.
- Non-root runtime user (uid 999 lakehouse). Layout matches
/usr/local/bin/lakehouse/<daemon> from REPLICATION.md.
- ENTRYPOINT=tini; no default CMD — operators / compose pick
which daemon explicitly.
docker-compose.yml (11 services):
- Same dependency graph as deploy/systemd/. depends_on with
service_healthy condition matches Requires= equivalents:
catalogd → storaged
ingestd → storaged + catalogd
queryd → catalogd
matrixd → embedd + vectord
- Gateway uses bare depends_on (no health condition) — Wants=
equivalent so single-upstream restart doesn't cascade.
- chatd has per-provider env_file entries (one each for
ollama_cloud, openrouter, opencode, kimi) — missing files are
silently OK, matching the systemd unit's EnvironmentFile=- list.
- Persistent state on the lakehouse-state named volume; commented
driver_opts shows how to bind to a host path for off-volume
backups.
.dockerignore:
- Excludes bin/ + reports/ + data/ + git metadata + .env files.
- Especially excludes lakehouse.toml/secrets-go.toml/auth.env so
local dev configs don't accidentally bake into a published image.
REPLICATION.md gains a Docker section between systemd setup and
the logs section. Ten-line copy-paste from "git clone" to
"docker compose up -d", plus a docker-vs-systemd differences
table covering process supervision, logs, restart policy, file
ownership, host networking quirks, and backup targets.
Validation: docker compose config --quiet → exit 0 (with
placeholder env files in place).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
ADR-003 locked the auth substrate; ADR-006 ratifies the operator
playbook + adds two implementation pieces needed for Sprint 4
deployment: env-resolved tokens and dual-token rotation.
Six decisions locked in docs/DECISIONS.md:
- 6.1: Non-loopback bind requires auth.token (mechanical gate at
shared.Run, already implemented; this ratifies it).
- 6.2: Token from env, not TOML. /etc/lakehouse/auth.env (mode 0600)
loaded by systemd EnvironmentFile=. New TokenEnv field on
AuthConfig defaults to "AUTH_TOKEN".
- 6.3: AllowedIPs for inter-service same-trust-domain; Token for
cross-trust-boundary (gateway ↔ external).
- 6.4: /health stays unauthenticated; everything else under
shared.Run is gated. Already implemented; ratified here.
- 6.5: Token rotation is dual-token. New SecondaryTokens []string
on AuthConfig — both primary and any secondary pass auth
during the rotation window. Implemented in this commit.
- 6.6: TLS terminates at the network edge (nginx/Caddy), not
in-process. Daemons stay HTTP-only; internal traffic stays
on private subnets per Decision 6.3.
Implementation:
- internal/shared/config.go: AuthConfig gains TokenEnv +
SecondaryTokens fields. New resolveAuthFromEnv() called by
LoadConfig fills Token from os.Getenv(TokenEnv) when Token is
empty. TokenEnv defaults to "AUTH_TOKEN" so the happy path needs
no TOML config.
- internal/shared/auth.go: RequireAuth pre-encodes Bearer headers
for primary + every secondary token; per-request constant-time
compare walks the slice. Fast path is 1 compare (primary).
Tests:
- TestLoadConfig_AuthTokenFromEnv (3 sub-tests): default env name,
custom token_env, explicit Token wins over env.
- TestRequireAuth_SecondaryTokenAccepted: both primary + secondary
tokens pass during rotation window.
- TestRequireAuth_SecondaryTokensOnly: only-secondary path works
for the case where primary was just promoted-to-empty mid-rotation.
go test ./internal/shared all green; existing auth_test.go
unchanged (constant-time compare path preserved).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Cross-lineage scrum on bundle 87cbd10..f971e64 (3,652 lines)
produced 4 actionable findings, all defensive hardening.
1. (Opus WARN) internal/langfuse/client.go:queue
Synchronous Flush at maxBatch threshold blocked the calling
goroutine for the full 5s HTTP timeout when Langfuse hiccupped,
defeating the "best-effort, never blocks calling path" contract
in the package doc. Now fire-and-forget via goroutine.
2. (Opus + Kimi convergent) cmd/observerd/main.go:handleInbox
- Free-form priority string was accepted; "nonsense" passed
through unchecked. Now closed enum: urgent|high|medium|low (+
empty defaults to medium). Tested: TestInbox_RejectsBadPriority.
- No size cap on body, only emptiness check; multi-MB payloads
would bloat observer's ring + JSONL. Now 8 KiB cap returns 413.
Tested: TestInbox_RejectsOversizedBody.
- Subject/sender/tag concatenated into InputSummary without
newline stripping; embedded \n could corrupt JSONL line-based
parsers. New sanitizeInboxField strips \r\n + caps at 256 chars
before interpolation.
3. (Opus INFO) scripts/multi_coord_stress/main.go
Removed dead `must[T]` generic — tracedSearch took over the
fail-fast role for matrix searches, so the helper became unused.
4. (Opus INFO) scripts/multi_coord_stress/main.go:Event
`JudgeRating int` collapsed "judge errored" and "judge said
unrated" both to 0. Changed to *int — nil = errored, 1-5 =
verdict. judgeInboxResult still returns 0 on error; caller
gates on > 0 before assigning.
Dismissed (with rationale):
- Opus WARN ExcludeIDs ordering: verified by code read — filter
applies after sort + before top-K truncation as documented;
no slot waste possible.
- Opus INFO 10 prior-run reports contradict #011: those are
point-in-time snapshots; intentional history.
- Kimi INFO Langfuse error suppression: design intent (best-effort
per package doc).
- Kimi INFO contract schema validation: defer until contract count
grows enough to make hand-edit drift a real risk.
- Kimi INFO paraphrase prompt duplicated across lift + multi_coord:
defer (lift to internal/paraphrase/ when a third consumer appears).
- Qwen HOLD: single-line, no actionable finding.
go test ./cmd/observerd ./internal/langfuse all green; multi_coord
driver builds clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pre-push hook caught the regression — the smoke hardcoded
MODEL = "nomic-embed-text" and the bump to nomic-embed-text-v2-moe
in 4da32ad failed the gate.
Fix: glob-match the family prefix (nomic-embed-text*). Both v1 and
v2-moe are 768d drop-ins; the property the smoke is locking is
dim + distinct-vectors, not the exact model variant. Operators
swap the variant in lakehouse.toml without needing to touch the
smoke.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Anchor was last touched at v4 split-threshold; since then the
multi-coord stress harness landed end-to-end across 11 commits.
Future sessions reading this file need to see the verified state,
not derive from git log.
Major additions:
- New "Multi-coordinator stress test (Phase 1 → 3)" section in
VERIFIED WORKING. 11-row capability table covering per-coord
playbook isolation, diversity metrics, paraphrase handover,
ExcludeIDs swap, fresh-resume two-tier, inbox endpoints, LLM
demand parsing, judge re-rating, Langfuse tracing.
- Substrate-gains list under that section: ExcludeIDs on
SearchRequest, observer.SourceInbox + /observer/inbox,
internal/langfuse client, embedd default bumped to v2-moe,
two-tier fresh_workers index pattern.
- Last-verified bumped to 16:42 CDT on the run #011 anchor.
DO NOT RELITIGATE expanded with five new locks:
1. Boost / inject use SEPARATE thresholds (0.5 / 0.20)
2. Multi-coord product theory is empirically VALIDATED
3. Fresh content uses two-tier indexing (fresh_workers)
4. embedd.default_model = nomic-embed-text-v2-moe (don't downgrade)
5. Inbox flow: parse + search + judge + trace
6. Langfuse Go-side client lives at internal/langfuse/
OPEN list refresh:
- Removed: re-judge metric (shipped as b13b5cd), adjacent-query as
separate item (folded into a single "judge-approves-before-inject"
follow-up), liberal-paraphrase (kept).
- Added: real-time 48-hour clock, wider Langfuse instrumentation,
periodic fresh→main merge job.
RECENT VERIFIED WAVE table extended with 11 commits (b13b5cd..5d49967).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Phase 1c-only tracing (commit 7e6431e) was the proof-of-concept.
This commit threads tracing through every phase: baseline / fresh-
resume / inbox burst / surge / swap / merge / handover (verbatim +
paraphrase) / split / reissue. Each phase is a parent span; each
matrix.search / LLM call inside is a child span.
Refactor:
- One run-level trace is created at driver startup.
- New startPhase(name, hour, meta) helper emits a phase span as a
child of the run trace; subsequent emitSpan calls nest under it.
- New tracedSearch(spanName, query, corpora, ...) wraps matrixSearch
with span emission. Every search call site replaced with this so
the input/output JSON (query, corpora, k, playbook, exclude_n →
top-K ids, top1 distance, boost/inject counts) lands in Langfuse.
- Phase 4b's paraphrase generation also emits llm.paraphrase spans.
- Phase 1c's existing inline span emission converted to use the new
helpers (no more inboxTraceID variable).
Run #011 result: trace landed at http://localhost:3001 with 111
observations attached. Span breakdown:
phase.* parents: 9 (one per phase that ran)
matrix.search.baseline: 10
matrix.search.fresh_verify: 3 (top-1 confirmed for all 3 fresh)
observerd.inbox.record: 6
llm.parse_demand: 6
matrix.search.inbox: 6
llm.judge_top1: 6
matrix.search.surge: 12
matrix.search.swap_orig: 1
matrix.search.swap_replace: 1
matrix.search.merge: 6
matrix.search.handover_verbatim: 4
llm.paraphrase: 4
matrix.search.handover_paraphrase: 4
matrix.search.split: 4
matrix.search.reissue: 12
matrix.search.reissue_retrieval_only: 12
─────────────
Total: 111
Browse: http://localhost:3001 → Traces → "multi_coord_stress run"
Each phase is a collapsible section showing per-call timing and
input/output JSON. Operators can drill into any single retrieval
to see exactly what query was issued and what came back.
All other metrics held: diversity 0.026, determinism 1.000,
verbatim handover 4/4, paraphrase handover 4/4, fresh-resume 3/3
at top-1 (two-tier index), 200-worker swap Jaccard 0.000.
This is the FULL TEST J asked for — every action in the run
visible in Langfuse, full input/output drilldown.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Runs #003-#009 surfaced the same finding: fresh workers added
mid-run to the main 'workers' vectord index (5K items) reliably
*absorbed* (HTTP 200) but failed to *surface* in semantic queries
even with content-matching prompts. Distances on the verify queries
sat at 0.25-0.65 against existing workers; fresh items were beyond
top-K. Better embedder (v2-moe) didn't help — distances got TIGHTER
on existing items, pushing fresh items further out of reach.
Root cause: coder/hnsw incremental adds to a populated graph land
in poorly-connected regions and disappear from search traversal.
Known property of HNSW post-build adds; not a bug.
Fix: two-tier index pattern (canonical NRT search architecture).
Fresh content goes to a small "hot" corpus (fresh_workers); main
queries include it in the corpora list and merge results. Hot corpus
has no recall crowding because it's tiny; periodic batch job (post-
G3) merges it into the main index.
Implementation:
- ensureFreshIndex(hc, gw, name, dim) — idempotent POST
/v1/vectors/index. 409 from re-create treated as "already there."
- ingestFreshWorker now takes idx parameter so callers can target
fresh_workers instead of workers.
- multi_coord_stress phase 1b creates fresh_workers index + ingests
3 fresh workers there + searches verifyCorpora=[workers,
ethereal_workers, fresh_workers].
Run #010 result:
fresh-001 (Senior tower crane rigger NCCCO Chicago)
top-1: fresh-001 from fresh_workers, distance 0.143
fresh-002 (Bilingual Spanish/English OSHA trainer Indianapolis)
top-1: fresh-002 from fresh_workers, distance 0.146
fresh-003 (FAA Part 107 drone surveyor Chicago)
top-1: fresh-003 from fresh_workers, distance 0.129
3/3 fresh workers surface at top-1 — the absorption-but-not-
findable issue from runs #003-#009 is closed.
All other metrics held: diversity 0.007, determinism 1.000,
verbatim handover 4/4, paraphrase handover 4/4, swap Jaccard 0.000,
inbox burst all 6 events accepted + traced to Langfuse.
This is the final structural fix for the multi-coord stress
suite. Phase 3 is feature-complete.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Rust side has Langfuse tracing already (gateway/v1/langfuse_trace.rs);
this commit lands Go-side parity so the multi-coord stress harness can
emit traces visible at http://localhost:3001.
internal/langfuse/client.go:
- Minimal Trace + Span + Flush API mirroring what the Rust emitter
uses. Auth: Basic over public_key:secret_key.
- Best-effort posture: errors are slog.Warn'd, never block calling
paths. Same fail-open as observerd's persistor (ADR-005 Decision
5.1) — observability is a witness, not a gate.
- Events buffered until 50, then auto-flushed; explicit Flush() at
process exit.
- Each Trace/Span returns its id so callers can build hierarchies.
multi_coord_stress driver wiring:
- New --langfuse-env flag (default /etc/lakehouse/langfuse.env).
Empty / missing / unparseable file → skip tracing with a logged
warning; run still proceeds.
- Phase 1c (inbox burst) now emits one parent trace + 4 spans per
inbox event:
1. observerd.inbox.record (post to /v1/observer/inbox)
2. llm.parse_demand (qwen2.5 → structured fields)
3. matrix.search (parsed query → top-K)
4. llm.judge_top1 (rate top-1 vs original body)
Each span carries input/output JSON + start/end times so the
Langfuse UI shows a full waterfall per event.
Run #009 result:
Trace landed: "multi_coord_stress phase 1c inbox burst"
Observations attached: 24 (= 6 events × 4 spans)
Tags: stress, phase-1c, inbox
Browseable at http://localhost:3001 by tag query.
Other harness metrics: diversity 0.016, determinism 1.000,
verbatim handover 4/4, paraphrase handover 4/4 — all unchanged
by the tracing addition (best-effort post in parallel).
Phase 1c is the proof-of-concept; future commits can wrap other
phases (baseline / merge / handover / split) in traces too. Once
that's done, the entire stress run becomes scrubbable in Langfuse
without grepping the events JSON.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Run #007 surfaced a tradeoff: LLM-parsed inbox queries produce much
tighter cosine distances (0.05-0.10 in three cases) but lose the
"system has no good match" signal that high-distance results give.
A coordinator UI showing only distance can't tell wrong-domain
matches apart from real ones.
Fix: judge re-rates top-1 against the ORIGINAL inbox body (not the
LLM-parsed query). Coordinators see both:
- distance: how close was retrieval in vector space
- rating: does this person actually fit the original ask
The pair tells the honest story.
Run #008 result on the 6 inbox events:
Demand Top-1 Distance Rating Reading
─────────────────────────────────────────────────────────────
Forklift Cleveland w-3573 0.29 4 Strong
Production Indy e-1764 0.41 3 Adjacent
Crane Chicago e-7798 0.23 1 TIGHT BUT WRONG
Bilingual safety Indy w-3918 0.05 5 Perfect
Drone Chicago e-1058 0.06 5 Perfect (verify e-1058)
Warehouse Milwaukee w-460 0.32 4 Strong
The crane-Chicago case is the architectural-honesty signal at work:
distance 0.23 says "tight match" but the judge says rating 1 reading
the original body. A coordinator seeing only distance would ship the
wrong worker; coordinator seeing distance+rating sees the disagreement
and escalates.
Net distribution: 5/6 rated 3+ (acceptable→perfect), 1/6 rated 1
(irrelevant despite tight cosine). The substrate-honesty signal is
recovered without losing the LLM-parse quality wins.
Cost: 6 extra judge calls (~9s on qwen2.5). Production amortizes
when judge runs only on top-1 of high-priority inbox events; the
search-cost-vs-quality tradeoff lives in the priority gate.
Implementation:
- New JudgeRating int field on Event (omitempty so non-judged
events stay clean in JSON)
- New judgeInboxResult helper, reusing the same prompt structure as
playbook_lift's judgeRate. The two could share an internal package
if a third judge consumer appears.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replaced the hard-coded DemandQuery on inbox events with an actual
LLM call: each email/SMS body is parsed by qwen2.5 (format=json,
schema-anchored) into structured {role, count, location, certs,
skills, shift}. The driver then composes a query string from those
fields and runs matrix.search.
This is the real-product flow that the Phase 3 stress test was
asking for: real bodies → real LLM parsing → real search. Before
this commit, the DemandQuery was my hand-crafted string, which
made the inbox phase trivial.
Run #007 result vs #006 (same bodies, parser swapped):
All 6 inbox events parsed cleanly — qwen2.5 nailed:
"Need 50 forklift operators in Cleveland OH for Monday day
shift. OSHA-30 + active forklift cert required."
→ {role:"forklift operator", count:50, location:"Cleveland, OH",
certs:["OSHA-30","active forklift cert"], skills:[], shift:"day"}
Other 5 similarly faithful (indy stayed as "indy", count
defaulted to 1 when unspecified, no hallucinated fields).
LLM-parsed queries produced TIGHTER matches than hard-coded:
Demand #006 dist #007 dist Δ
Crane Chicago 0.499 0.093 -82%
Drone Chicago 0.707 0.073 -90%
Bilingual safety 0.240 0.048 -80%
Forklift Cleveland 0.330 0.273 -17%
Production Indy 0.260 0.399 +53%
Warehouse Milwaukee 0.458 0.420 -8%
Three matches landed at distance < 0.10 — verbatim-replay-tight
territory. Structured queries embed sharper than conversational
hand-crafted strings.
Other metrics unchanged: diversity 0.000, determinism 1.000,
verbatim handover 4/4, paraphrase handover 4/4.
Tradeoff worth flagging: the drone-Chicago case dropped from
distance 0.71 (clear "we don't have one") to 0.07 (confident match
returned). The OOD honesty signal weakens when LLM-parsed structure
makes any closest-neighbor look tight. Future Phase 4 work: judge
re-rates the top match before surfacing, so coordinators see "your
demand was for X but the closest match scored 2/5" rather than just
the worker ID + distance.
Substrate cost: +6 LLM calls per inbox burst (~9s on qwen2.5).
Production would amortize via a small dedicated parser model.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Phase 3 ask: real-world inbox-style event injection during the stress
test. Coordinators in production receive emails + SMS that trigger
contract responses; the substrate has to RECORD these signals AND
react with a search using the embedded demand. This commit lands the
endpoint and exercises it end-to-end in the stress harness.
observerd surface:
- New POST /observer/inbox route — accepts {type, sender, subject,
body, priority, tag} and records as ObservedOp with
Source=SourceInbox. Type must be email|sms; body required;
priority defaults to medium. The handler ONLY records — downstream
triggers (search, ingest, etc.) are the caller's concern, recorded
separately. Keeps the witness role pure.
- New observer.SourceInbox = "inbox" alongside SourceMCP /
SourceScenario / SourceWorkflow.
- Three contract tests on the new route (happy path / bad type / empty
body), router-mount test extended, all green.
Stress harness phase 1c (Hour 9):
- 6 inbox events fire in priority order (urgent → high → medium):
2 urgent emails (forklift Cleveland, production Indianapolis)
1 high email (crane Chicago)
1 high sms (bilingual safety Indianapolis)
1 medium sms (drone Chicago)
1 medium email (warehouse Milwaukee FYI)
- Each event:
1. POSTs to /v1/observer/inbox (recorded by observerd)
2. Triggers matrix.search using a parsed demand (the demand
extraction is hard-coded for now; production needs a small
LLM to parse from body)
3. Captures both as events in the run JSON
Run #006 result (with v2-moe embedder + all phases including inbox):
Diversity:
Same-role-across-contracts Jaccard = 0.000 (n=9)
Different-roles-same-contract Jaccard = 0.046 (n=18)
Determinism: 1.000
Verbatim handover: 4/4 (100%)
Paraphrase handover: 4/4 (100%)
Inbox burst:
6/6 events accepted by observerd (200 status, all recorded)
6/6 triggered searches produced distinct top-1 worker IDs
distance distribution: 0.24 (Indy production) → 0.71 (Chicago
drone surveyor — honest stretch since drones aren't in the
5K-worker corpus, system surfaces closest neighbor at high
distance rather than fabricating)
The drone-Chicago case is the architectural-honesty signal: when
the demand asks for a specialist NOT in the roster, the system
returns the closest semantic neighbor with a distance that flags
"this is a stretch." Coordinators reading distances see "we don't
have a great match here" rather than a confident wrong answer.
Total events captured: 67 (was 61 pre-inbox).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Local Ollama has three embedding models loaded:
nomic-embed-text:latest 137M 768d (previous default)
nomic-embed-text-v2-moe:latest 475M 768d (this commit's default)
qwen3-embedding:latest 7.6B 4096d (would require dim change)
v2-moe is a drop-in upgrade — same 768 dim, 3.5× more params, MoE
architecture. Workers index doesn't need rebuilding, just future ingests
embed with the stronger model.
Run #005 result on the multi-coord stress suite:
Diversity (same-role-across-contracts): 0.080 → 0.000 (n=9)
→ MoE is more discriminating: zero worker overlap across
Milwaukee / Indianapolis / Chicago for shared role names.
The geo + cert + skill context fully separates worker pools.
Different-roles-same-contract: 0.013 → 0.036 (still ~96% diff)
Determinism: 1.000 (unchanged)
Verbatim handover: 4/4 (100%)
Paraphrase handover: 4/4 (100%)
200-worker swap: Jaccard 0.000 (unchanged — still perfect)
Fresh-resume verify: STILL doesn't surface fresh workers in top-8.
With v2-moe, distances increased (top-1 = 0.43–0.65 vs v1's 0.25–0.39)
— the embedder is MORE discriminating, but the fresh worker's
vector still doesn't outrank the 8th-best existing worker. Now
suspect of being an HNSW post-build add issue (coder/hnsw
incremental adds can land in hard-to-reach graph regions, not an
embedder problem). Better embedder didn't fix it; needs a
different strategy: full index rebuild after fresh adds, or
explicit playbook-layer score boost for fresh workers, or
hybrid (keyword + semantic) retrieval. Phase 3 investigation.
Cost: ingest is ~5× slower (workers 20s→100s; ethereal 35s→112s).
Acceptable for the quality jump on diversity. Real production with
incremental ingest won't pay this once-per-deploy.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three Phase 2 additions land in this commit:
1. matrix.SearchRequest gains ExcludeIDs ([]string) — filters specific
worker IDs out of results post-retrieval, AND skips them at the
playbook boost+inject step (so excluded answers can't sneak back
via Shape B). Real-world driver: coordinator placed N workers,
client asks for replacements, system needs alternatives, not the
same N. Threaded through retrieve.go after merge but before
metadata filter so excluded IDs don't waste post-filter top-K slots.
2. New harness phase 2b: 200-worker swap simulation. Captures the
top-K from alpha's warehouse query, then re-issues with
exclude_ids=<placed>. Result Jaccard(orig, swap) measures whether
the substrate finds genuine alternatives.
3. New harness phase 1b: fresh-resume mid-run injection. Three new
workers ingested via /v1/embed + /v1/vectors/index/workers/add,
then verified findable via semantic queries matching resume content.
Plus Hour labels on every event (operational narrative: 0/6/12/18/
24/30/36/42/48) and a refactor of captureEvent to take hour as a
param.
Run #003 + #004 results (5K workers + 10K ethereal):
Diversity (#004):
Same-role-across-contracts Jaccard = 0.080 (n=9)
Different-roles-same-contract Jaccard = 0.013 (n=18)
Determinism: 1.000 (#004 unchanged)
Verbatim handover: 4/4 = 100%
Paraphrase handover: 4/4 = 100%
Phase 2b — 200-worker swap (Jaccard 0.000):
8 originally-placed workers fully replaced by 8 alternatives.
ExcludeIDs substrate change works end-to-end — boost AND inject
both honor the exclusion, so excluded workers don't return via
the playbook either.
Phase 1b — fresh-resume injection: REAL PRODUCT FINDING.
Substrate ABSORPTION is fine — 3 /v1/vectors/index/workers/add
calls at 200 status, 3 vectors persisted. But none of the 3
fresh workers surfaced in top-8 even with semantic queries
matching their resume content (e.g. "Senior tower crane rigger
NCCCO Chicago" vs fresh-001's resume "Senior rigger with 12
years tower-crane signaling..." NCCCO + Chicago).
Top-1 came from existing workers at distance ~0.25; fresh
workers' distances must be > 0.25, pushing them past rank 8.
Cause: dense retrieval at 5000+ workers means many existing
profiles cluster near any specific query in cosine space;
nomic-embed-text-v2 (137M) introduces enough noise that a
fresh worker doesn't reliably outrank them just because the
text content overlaps.
Workarounds (Phase 3 work): (a) hybrid retrieval (keyword +
semantic), (b) playbook-layer score boost for fresh adds,
(c) larger embedder. Documented in run #004 report.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Phase 1 had two known gaps: (1) the 3 contracts had zero shared role
names, so same-role-across-contracts Jaccard was vacuous (n=0); (2)
the verbatim handover at 100% was the trivial case, not the hard
learning test (paraphrased queries against another coord's playbook).
Both fixed in this commit.
Contract redesign — all 3 contracts now share warehouse worker /
admin assistant / heavy equipment operator roles, plus a unique
specialist per contract (industrial electrician / bilingual safety
coord / drone surveyor — the "specialist not on the standard roster"
case from J's spec). Counts and skill mixes vary per region.
New driver phase 4b — paraphrase handover. Bob runs qwen2.5-paraphrased
versions of Alice's contract queries against Alice's playbook
namespace. Tests whether institutional memory propagates across
coordinators AND across natural wording variation that Bob would
introduce when running Alice's contract.
Run #002 result (5K workers + 10K ethereal_workers, 4 demand × 3
coords + paraphrase handover):
Diversity (the question J asked: locking or cycling?):
Same-role-across-contracts Jaccard = 0.119 (n=9)
→ 88% of workers DIFFER across regions for the same role name.
Milwaukee warehouse vs Indianapolis warehouse vs Chicago
warehouse pull mostly distinct top-K from the same population.
The system locks into geo+cert+skill context, not cycling.
Different-roles-same-contract Jaccard = 0.004 (n=18)
→ role-specific retrieval works (unchanged from Phase 1).
Determinism: Jaccard = 1.000 (n=12) — unchanged.
Learning:
Verbatim handover 4/4 = 100% (trivial case, expected)
Paraphrase handover 4/4 = 100% (HARD case — passes!)
Of those 4 paraphrase recoveries:
- 2 used boost (Alice's recording was already in Bob's
paraphrase top-K; ApplyPlaybookBoost re-ranked to top-1)
- 2 used Shape B inject (recording wasn't in Bob's
paraphrase top-K; InjectPlaybookMisses brought it in)
The boost/inject mix is healthy — both paths are used and both
produce correct top-1s. Multi-coord institutional memory propagation
is empirically working under wording variation.
Sample warehouse worker top-1s across contracts (proves diversity):
alice / Milwaukee → w-713
bob / Indianapolis → e-8447
carol / Chicago → e-7145
Three different workers from the same 15K-person population,
selected on geo+cert+skill context.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three coordinators (alice / bob / carol) with three contracts
(Milwaukee distribution / Indianapolis manufacturing / Chicago
construction). 7-phase scenario runner: baseline → surge → merge →
handover → split → reissue → analysis. Each coord has a separate
playbook namespace (playbook_{name}) so institutional memory stays
isolated by default but transferable on demand.
Phase 1 deliberately skips the 48-hour clock, email/SMS endpoints,
and Langfuse tracing — those are Phase 2/3.
Run #001 (52 events, 4 queries × 3 coords × 2 demand flavors):
Diversity:
Different-roles-same-contract Jaccard = 0.004 (n=18)
→ role-specific retrieval is working perfectly. Different
roles within one contract pull totally different worker
pools. System is NOT cycling; locks into per-role retrieval.
Same-role-across-contracts Jaccard = N/A (n=0)
→ TEST-DESIGN ISSUE: the 3 contracts use distinct role names
per industry (warehouse worker / production worker / general
laborer), so no exact-name overlaps exist. Phase 2 should
either share at least one role across contracts OR add a
skill-based diversity metric.
Determinism: Jaccard = 1.000 (n=12)
→ HNSW + Ollama retrieval is fully deterministic on identical
query text. coder/hnsw + nomic-embed-text are stable.
Learning: handover hit rate = 4/4 = 100%
→ Bob inherits Alice's recordings perfectly when bob runs
identical queries with alice's playbook namespace. CAVEAT:
this tests the trivial verbatim case, not paraphrase handover.
The harder test (bob runs paraphrased queries with alice's
playbook) is Phase 2 work.
Per-event capture in JSON: every matrix.search response is logged
with phase / coordinator / contract / role / query / top-K IDs +
distances + per-corpus counts + boosted/injected counts. Reviewable
via:
jq '.events[] | select(.phase == "merge")'
jq '.events[] | select(.coordinator == "alice")'
jq '.events[] | select(.role == "warehouse worker")'
Notable finding from per-event: carol's "general laborer" and "crane
operator" queries both surface w-1009 as top-1, with crane operator
at distance 0.098 (very tight) and general laborer at 0.297. The
system found a worker who legitimately covers both roles — realistic
for small construction crews.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The rank-based "lift" metric (warm-top-1 == cold-judge-best) doesn't
distinguish "Shape B surfaced a strictly-better answer" from "Shape B
shuffled ranks but quality is unchanged" from "Shape B replaced a good
answer with a wrong one." This commit adds Pass 4: judge warm top-1
with the same prompt as cold ratings, then bucket the comparison.
Implementation:
- New --with-rejudge driver flag (default off).
- New WITH_REJUDGE harness env (default 1, on for prod runs).
- queryRun gains WarmTop1Metadata (cached during Pass 2 for the
rejudge call) + WarmTop1Rating *int (nil-distinguishable; nil = no
rejudge, 0..5 = rating).
- summary gains RejudgeAttempted, QualityLifted, QualityNeutral,
QualityRegressed (counts of warm-rating > / == / < cold-rating).
- Markdown headline gains a Quality block when rejudge ran.
- ~21 extra judge calls (~30s on qwen2.5).
Run #005 result (split inject threshold 0.20 + paraphrase + rejudge):
Quality lifted 5 / 21 (24%) — 3× +2 rating, 2× +1 rating
Quality neutral 13 / 21 (62%) — includes OOD queries holding 1
Quality regressed 3 / 21 (14%)
Net rating delta +3 across 21 queries (+0.14 average)
The 5 lifts were all rating-2 cold replaced with rating-3 or rating-4
warm — Shape B took mediocre matches and substituted substantively
better ones. The 3 regressions were small (-1, -1, -3).
Q11 is the cautionary tale: cold top-1 "production line worker"
(rating 4) got replaced by Q1's recorded "forklift OSHA-30 operator"
e-5729 (rating 1). Adjacent-domain cross-pollination — production
worker and forklift operator embed within 0.20 cosine because both
are warehouse-adjacent staffing queries, even though the judge
correctly distinguishes them. The split-threshold defense (0.5 boost
/ 0.20 inject) catches OOD cross-pollination (Q19/Q20/Q21 all stayed
neutral at rating 1) but not adjacent-domain cross-pollination.
Net product verdict: working, net-positive on quality, but the worst
case (Q11 4→1) is customer-visible and warrants a tighter inject
threshold OR an additional gate beyond cosine distance. Filed in
STATE_OF_PLAY OPEN as a follow-up.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Reality test table extends from #001-#003 to #001-#004; v4 row marked
as "the honest configuration" because OOD cross-pollination is gone.
- Shape B section gains the split-threshold rationale (boost safe at
loose, inject structurally riskier so tighter).
- Verbatim drop framing rewritten — v3→v4 is configuration evolution,
not regression.
- OPEN: closed "Shape B cap/decay" + the conditional Q15 boost-math
item (Shape B + split threshold addressed both). Replaced with two
finer-grained follow-ups: adjacent-query Q6↔Q7 swap (might be
correct, verify with v4 re-judge metric) and liberal-paraphrase
recovery loss (Q9/Q15 missed because qwen2.5 drifted >0.20).
- RECENT VERIFIED WAVE adds 94fc3b6 + 67d1957.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
root