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>
Run #003 surfaced rampant cross-pollination: Q2's "OSHA-30 forklift
Wisconsin" recording (w-4435) became warm top-1 for Q19 (dental
hygienist), Q20 (RN), Q21 (software engineer), and 6 other unrelated
staffing queries. Cause: InjectPlaybookMisses inherited the same
DefaultPlaybookMaxDistance (0.5) as the boost path, but inject is
structurally riskier than boost — boost only re-ranks results that
already retrieved on their own merits, while inject FORCES a result
into top-K, so a loose match cross-pollinates wrong-domain answers.
Empirical motivation from v3:
Implied playbook hit distances for cross-pollinated cases: 0.20-0.46
Implied distances for the 6/6 paraphrase recoveries: 0.23-0.30
Threshold of 0.20 should keep most paraphrases, kill the OOD bleed.
Implementation:
- New DefaultPlaybookMaxInjectDistance = 0.20 in playbook.go.
- New PlaybookMaxInjectDistance field on SearchRequest (override).
- InjectPlaybookMisses signature gains maxInjectDist param; hits whose
Distance exceeds it are skipped (boost path may still re-rank them).
- TestInjectPlaybookMisses_RespectsInjectThreshold locks the contract
with one tight + one loose hit, asserting only the tight one injects.
- Existing tests pass explicit threshold (0 = default for tight tests,
0.5 for the dedupe test which uses 0.30 hits).
Run #004 result on identical queries with the split threshold:
Verbatim discovery 8 (vs v3's 6 — judge variance, separate)
Verbatim lift 6 / 8 (75%)
Paraphrase top-1 6 / 8 (75%)
Paraphrase any-rank in K 6 / 8
OOD queries Q19/Q20/Q21 ALL show warm top-1 = cold top-1 (no
injection) — cross-pollination eliminated where it was wrong-direction.
Mean Δ top-1 distance dropped from -0.164 (v3, distorted) to -0.071
(v4, comparable to v1's -0.053).
Two paraphrases missed in v4 (Q9, Q15) were ones where qwen2.5
rephrased liberally enough to drift past 0.20 — Q9: "Inventory
specialist..." → "Individual needed for inventory management..." and
Q15: "Engaged warehouse associate..." → "Warehouse associate currently
engaged with a robust history...". The system correctly refusing to
inject when it's not confident is the right product behavior; the
boost path still re-ranks recorded answers when they appear in regular
retrieval.
The Q6 ↔ Q7 cross-pollination ("Forklift-certified loader" ↔
"Hazmat warehouse worker") is legitimate — these are genuinely similar
staffing queries and the judge ranks both directions as plausible.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Reality test section now spans v1/v2/v3 across one table — the
product story (boost-only verbatim → paraphrase gap → Shape B
closes the gap) is legible without reading the reports.
- Verbatim-lift drop v1→v3 (7→2) explicitly framed as
cross-pollination, NOT regression — and filed as v4 re-judge metric
in OPEN.
- "DO NOT RELITIGATE" gains: Shape B is the stance now (don't revert
to boost-only); local_judge stays on qwen2.5 (don't bump to qwen3.5
for cleanliness — vision-SSM cost geometry).
- OPEN list: removed the now-closed paraphrase v2 row + the boost-math
Q15 row (Shape B may have addressed it; flagged for verify after v4).
Added v4 re-judge metric and Shape B injection cap/decay design call.
- RECENT VERIFIED WAVE adds the four new commits past 6c02c90
(2c71d1c, 9ce067b, e9822f0, 154a72e).
- Matrix indexer §5/5 component description now references
InjectPlaybookMisses + the run #002→#003 evidence chain.
- [models] tier registry comment locks the local_judge=qwen2.5 choice
with the rationale inline.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The v0 boost-only stance documented in internal/matrix/playbook.go:22-27
("the boost only re-ranks results that ALREADY surfaced from the regular
retrieval") couldn't promote recorded answers that dropped out of a
paraphrase's top-K. playbook_lift_002 surfaced exactly that gap: 0/2
paraphrase recoveries because the recorded answers weren't in regular
retrieval at all (rank=-1).
Shape B: when warm-pass retrieval doesn't surface a playbook hit's
answer, inject a synthetic Result for it directly. Distance =
playbook_hit_distance × BoostFactor — same formula as the boost path so
injections land in comparable distance space. Caller re-sorts +
truncates after both boost and inject have run.
Result on playbook_lift_003 (Shape B + paraphrase pass):
Verbatim discovery 6
Verbatim lift 2 / 6
**Paraphrase top-1** **6 / 6**
Paraphrase any-rank in K 6 / 6
Mean Δ top-1 distance -0.1637 (warm closer than cold)
Every paraphrase the judge generated landed the v1-recorded answer at
top-1 of the new query's results. The learning property holds — cosine
on embed(paraphrase) finds the recorded query's vector within
DefaultPlaybookMaxDistance (0.5), and Shape B injects the answer.
Verbatim lift dropped from v1's 7/8 because Shape B cross-pollinates
recorded answers across queries. w-4435 (Q2's recording) appears as
warm top-1 for several other queries because their embeddings are
within the playbook hit threshold of "OSHA-30 forklift Wisconsin." This
is a feature, not a bug — the matrix layer's purpose is to share
knowledge across queries — but the lift metric only counts "warm top-1
== cold judge best," so cross-pollinated lifts don't register. A v3
metric would re-judge warm pass to measure true judge improvement.
Tests:
- TestInjectPlaybookMisses_AddsMissingAnswers — primary claim
- TestInjectPlaybookMisses_SkipsAnswersAlreadyPresent — no double-inject
- TestInjectPlaybookMisses_DedupesPerAnswer — multi-hit same answer
- TestInjectPlaybookMisses_EmptyHits — fast-path no-op
Driver fix: ParaphraseRecordedRank int → *int. The `omitempty` int
silently dropped rank=0 (top-1, the WANTED value) from JSON, making the
v003 report show "null" instead of "0" for every successful recovery.
Pointer keeps nil/rank-0 distinguishable.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds an opt-in Pass 3 to the lift driver: for each query whose Pass 1
recorded a playbook, ask the judge to rephrase the query, then re-query
with playbook=true and check whether the recorded answer surfaces in
top-K. This is the test the v1 report's caveat #3 explicitly flagged
as the actual learning-property gate (not the cheap verbatim case).
Implementation:
- New flag --with-paraphrase on the driver (default off).
- New WITH_PARAPHRASE env in the harness (default 1, on for prod runs).
- New paraphrase_* fields on queryRun + summary, // 0 fallback in jq so
re-rendering verbatim-only evidence stays clean.
- generateParaphrase() calls the same judge model with format=json and
a tight schema; temperature=0.5 for variance without domain drift.
- Markdown report adds a paraphrase per-query table (only when the
pass ran) and an honesty caveat about judge-also-rephrases coupling.
Run #002 result (reports/reality-tests/playbook_lift_002.{json,md}):
Verbatim lift 2/2 (100% — Q7 + Q13, both stable from v1)
Paraphrase top-1 0/2
Paraphrase any-rank in K 0/2
Both paraphrases dropped the recorded answer OUT of top-K entirely
(rank=-1). This isn't a paraphrase-quality problem — qwen2.5's outputs
preserved intent ("Hazmat-certified warehouse worker comfortable with
cold storage" → "Warehouse worker with Hazmat certification and
experience in cold storage"). It's the v0 boost-only stance documented
in internal/matrix/playbook.go:22-27: the boost only re-ranks results
that ALREADY surfaced from regular retrieval. If paraphrase's cosine
retrieval doesn't include the recorded answer in top-K, no boost can
promote it.
The "Shape B" upgrade mentioned in the playbook.go comment — inject
playbook hits directly even when they weren't in the top-K — is what
would close this gap. The reality test surfaced exactly the gap the
docs warned about. Worth filing as the next product gate.
Run-to-run variance also visible: v1 had 8 discoveries, v2 had 2.
HNSW insertion order + judge variance both contribute. Stability of
Q7 and Q13 across both runs (lifted in v1 AND v2) is the most reliable
signal in the dataset.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
TestWorkflowRun_AllProvenanceRecordedPostRun proves that
handleWorkflowRun records ObservedOps only AFTER runner.Run returns,
not interleaved with node execution.
The test pauses inside a node via a controlled channel, samples
observer.Store mid-run (must be 0), unblocks, then samples again
(must be N). If a future commit adds per-node streaming (e.g.
runner.NodeHook firing as each node finishes), n1's record would
appear before the unblock and the first assertion fires.
This is intentional test-as-spec lock. Closing the streaming gap is
deferred per the ADR ("acceptable for short workflows; streaming
callback is the right shape when workflows get longer") — but if
someone later adds the streaming callback without updating the ADR,
this test catches it in `go test` instead of leaving the doc and
code drifted.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes the OPEN item from STATE_OF_PLAY. Required because observerd is
now on the prod-realistic data path via the lift harness boot (b2e45f7),
so the next consumer (scrum runner / distillation rebuild / production
workflow) needs the fail-safe rationale locked, not implicit.
The Rust "verdict:accept on crash" anti-pattern doesn't translate
one-to-one to the Go observer (witness, not gate). But four adjacent
fail-safe decisions are real and live:
5.1 Persist failure is logged-not-fatal; ring is in-flight source of
truth. Persist-required mode deferred to a future opt-in ADR.
5.2 Mode failure → Success=false, no panic-swallow path. The runner
catches mode errors and surfaces them via node.Error; downstream
consumers see failures explicitly rather than as fake successes
(the Rust anti-pattern surface).
5.3 One row per node, recorded post-run. A workflow with N nodes
produces N audit rows, never a per-workflow catch-all that
survives partial crashes. Known gap: recording happens after
runner.Run returns (acceptable for short workflows; streaming
callback is the right shape when workflows get longer).
5.4 /observer/event accepts on full ring (oldest evicted). Refusing
to write would translate every burst into client errors — wrong
direction for an audit witness.
Mostly ratifies existing behavior; cross-checked claims against
actual code (caught one error in Decision 5.3 draft — recording is
post-run-batched, not per-node-as-it-completes — and the ADR now
states reality).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Cross-lineage scrum on b2e45f7 produced 1 convergent + 3 single-reviewer
findings worth fixing. All apply.
1. (Opus WARN + Qwen INFO convergent) scripts/playbook_lift.sh: replace
sleep 2.5 in SQL probe with active polling up to 5s. refresh_every=1s
is a lower bound; under load the manifest may not be visible in a
fixed sleep, which would 4xx the probe and abort the reality run.
2. (Opus INFO) scripts/playbook_lift.sh: report template glued
"env JUDGE_MODEL" + value as "env JUDGE_MODELqwen2.5:latest" with no
separator. Replaced two :+/:- substitution chains with a single
JUDGE_SOURCE variable computed once at the top of the harness.
3. (Opus INFO) scripts/staffing_workers/main.go: -id-prefix "" silently
allowed, defeating the flag's purpose (cross-corpus collision prevent).
Now log.Fatal at startup with explicit hint.
4. (Opus WARN) cmd/{pathwayd,observerd}/main_test.go: newTestRouter
returned http.Handler then re-cast to chi.Router for chi.Walk.
Returning chi.Router directly satisfies http.Handler AND avoids an
assertion that would panic if future middleware wraps the router.
Dismissed (with rationale):
- Kimi INFO hardcoded MinIO endpoint: harness is local-by-design.
- Kimi WARN matrixd accepts 502/500: documented; real retriever needs
real upstreams the test doesn't spin up.
- Qwen INFO queryd string.Contains: brittle but very low risk; restating
through typed-error path would couple without adding signal.
go test ./cmd/{matrixd,queryd,pathwayd,observerd} all green.
Verdicts at reports/scrum/_evidence/2026-04-30/verdicts/lift_001_*.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The 5-loop substrate's load-bearing gate is verified — playbook +
matrix indexer give the results we're looking for. Per the report's
rubric, lift ≥ 50% of discoveries means matrix is doing real work;
7/8 = 87.5% blew through that.
Harness was structurally hiding bugs behind a 5-daemon stripped boot.
Expanding to the full 10-daemon prod stack surfaced 7 fixes in cascade:
1. driver→matrixd: {"query": ...} → {"query_text": ...} field name
2. harness temp toml missing [s3] → wrong default bucket → catalogd
rehydrate 500 on first call
3. harness→queryd SQL probe: {"q": ...} → {"sql": ...} field name
4. expand boot from 5 → 10 daemons in dep-ordered launch
5. add SQL surface probe (3-row CSV ingest → COUNT(*)=3 assertion)
6. candidates corpus was synthetic SWE-tech (Swift/iOS, Scala/Spark) —
wrong domain for staffing queries; replaced with ethereal_workers
(10K rows, real staffing schema, "e-" id prefix to avoid collision
with workers' "w-"). staffing_workers driver gains -index-name +
-id-prefix flags so the same binary serves both corpora
7. local_judge qwen3.5:latest is a vision-SSM 256K-ctx build running
~30s per judge call against the lift loop; reverted to
qwen2.5:latest (~1s/call, 30× faster, held lift theory)
Each contract drift (1, 3) is now locked into a cmd/<bin>/main_test.go
so future drift fires in `go test`, not in a reality run. R-005 closed:
- cmd/matrixd/main_test.go (new) — playbook record drift detector +
score bounds + 6 routes mounted
- cmd/queryd/main_test.go — wrong-field-name drift detector
- cmd/pathwayd/main_test.go (new) — 9 routes + add round-trip + retire
- cmd/observerd/main_test.go (new) — 4 routes + invalid-op + unknown-mode
`go test ./cmd/{matrixd,queryd,pathwayd,observerd}` all green.
Reality test results (reports/reality-tests/playbook_lift_001.{json,md}):
Queries 21 (staffing-domain, 7 categories)
Discoveries 8 (judge ≠ cosine top-1)
Lifts 7/8 (87.5%)
Boosts triggered 9
Mean Δ distance -0.053 (warm closer than cold)
OOD honesty dental/RN/SWE rated 1, no fake matches
Cross-corpus boosts confirmed (e- ↔ w- swaps in lifts)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Phase 4-bundle review (128KB diff) hit "Argument list too long" when
curl --data was passed the body as a literal arg. Pipe via stdin
with --data-binary @- instead. Lifts the practical bundle size from
~30KB to whatever fits in process memory.
Caught while running the harness scrum on golangLAKEHOUSE today —
the bigger Phase A+B harness diff (4566 lines) tripped it.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- SPEC §1 component table: add chatd row marked DONE; replaces
Rust gateway's v1::ollama_cloud / openrouter / opencode adapters
+ the aibridge crate.
- SPEC §3.9 — chatd shipped: 5-provider routing (ollama, ollama_cloud,
openrouter, opencode, kimi) by model-name prefix or :cloud suffix.
Captures the Anthropic 4.7 temperature-deprecation quirk + the
local-Ollama think=false default that the playbook_lift judge
needed. Mentions scrum_review.sh as the reusable cross-lineage
vehicle eating chatd's own /v1/chat.
- SPEC §3.10 — local-review-harness sibling tool: separate repo at
git.agentview.dev/profit/local-review-harness, MVP shipped today.
Documents the cross-pollination plan for when both substrates
stabilize (chatd as the harness's LLM backend; harness findings
as Lakehouse pathway-memory drift signal; .memory/known-risks
as a matrix corpus). Explicit "don't re-port" so future Claudes
don't try to absorb the harness into Lakehouse.
- STATE_OF_PLAY.md: SIBLING TOOLS section with 1-line summary
+ pointer to SPEC §3.10.
No code changes. just verify still PASS — touched only docs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Bash driver wrapping /v1/chat for Opus + Kimi + Qwen3-coder review
runs. Used today to scrum the 4-phase wave (1,624 LoC of chatd +
config-refactor + Rust cleanup) and caught 2 BLOCKs + 2 WARNs.
Usage:
./scripts/scrum_review.sh <bundle.diff> <bundle_label>
Output: reports/scrum/_evidence/<DATE>/verdicts/<bundle>_<reviewer>.md
verbatim, per the evidence-only convention. Per-reviewer latency +
token counts captured in the report header.
System prompt enforces the BLOCK/WARN/INFO + WHERE/WHAT/WHY shape
per feedback_cross_lineage_review.md — leads with verdict, no
preamble (Kimi tends to spend tokens thinking otherwise).
Reviewer fleet matches project_golang_lakehouse.md "Scrum routing":
- opencode/claude-opus-4-7
- openrouter/moonshotai/kimi-k2-0905
- openrouter/qwen/qwen3-coder
This is the first dogfood of chatd as the scrum vehicle — eats its
own /v1/chat dispatcher.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3-lineage scrum (Opus 4.7 / Kimi K2.6 / Qwen3-coder) on today's wave
landed 4 real findings (2 BLOCK + 2 WARN) and 2 INFO touch-ups.
Verbatim verdicts + disposition table at:
reports/scrum/_evidence/2026-04-30/
B-1 (BLOCK Opus + INFO Kimi convergent) — ResolveKey API:
collapse from 3-arg (envVar, envFileName, envFilePath) to 2-arg
(envVar, envFilePath). Pre-fix every chatd caller passed the env
var name twice; if operator renamed *_key_env in lakehouse.toml
while keeping the canonical KEY= line in the .env file, fallback
silently missed.
B-2 (WARN Opus + WARN Kimi convergent) — handleProviders probe:
drop the synthesize-then-Resolve probe; look up by name directly
via Registry.Available(name). Prior probe synthesized "<name>/probe"
model strings and routed through Resolve, fragile to any future
routing rule (e.g. cloud-suffix special case).
B-3 (BLOCK Opus single — verified by trace + end-to-end probe) —
OllamaCloud.Chat StripPrefix used "cloud" but registry routes
"ollama_cloud/<m>". Result: upstream got the prefixed model name
and 400'd. Smoke missed it because chatd_smoke runs without
ollama_cloud registered. Now strips the right prefix; new
TestOllamaCloud_StripsCorrectPrefix locks both prefix + suffix
cases. Verified live: ollama_cloud/deepseek-v3.2 round-trips
cleanly through the real ollama.com endpoint.
B-4 (WARN Opus single) — Ollama finishReason: read done_reason
field instead of inferring from done bool alone. Newer Ollama
reports done=true with done_reason="length" on truncation; the
prior code mapped that to "stop" and lost the truncation signal
the playbook_lift judge needs to retry. New
TestFinishReasonFromOllama_PrefersDoneReason covers the fallback
ladder.
INFOs:
- B-5: replace hand-rolled insertion sort in Registry.Names with
sort.Strings (Opus called the "avoid sort import" comment a
false economy — correct).
- A-1: clarify the playbook_lift.sh comment around -judge "" arg
passing (Opus noted the comment said "env priority" but didn't
reflect that the empty arg also passes through the Go driver's
resolution chain).
False positives dismissed (3, documented in disposition.md):
- Kimi: TestMaybeDowngrade_WithConfigList wrong assertion (test IS
correct per design — model excluded from weak list = strong = downgrade)
- Qwen: nil-deref claim (defensive code already handles nil)
- Opus: qwen3.5:latest doesn't exist on Ollama hub (true on the
public hub but local install has it)
just verify: PASS. chatd_smoke 6/6 PASS. New regression tests:
3 (B-2, B-3, B-4 each get a focused test).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
new cmd/chatd on :3220 routes /v1/chat to the right provider based
on model-name prefix or :cloud suffix. closes the architectural gap
named in lakehouse.toml [models]: tiers map to model IDs, but until
phase 4 there was no service that could actually CALL those models
from go.
routing rules (registry.Resolve):
ollama/<m> → local Ollama (prefix stripped)
ollama_cloud/<m> → Ollama Cloud
<m>:cloud → Ollama Cloud (suffix variant — kimi-k2.6:cloud)
openrouter/<v>/<m> → OpenRouter (prefix stripped, OpenAI-compat)
opencode/<m> → OpenCode unified Zen+Go
kimi/<m> → Kimi For Coding (api.kimi.com/coding/v1)
bare names → local Ollama (default)
provider implementations:
- internal/chat/types.go Provider interface, Request/Response, errors
- internal/chat/registry.go prefix + :cloud suffix dispatch
- internal/chat/ollama.go local Ollama via /api/chat (think=false default)
- internal/chat/ollama_cloud.go Ollama Cloud via /api/generate (Bearer auth)
- internal/chat/openai_compat.go shared OpenAI Chat Completions for the
OpenRouter/OpenCode/Kimi family
- internal/chat/builder.go BuildRegistry from BuilderInput;
ResolveKey reads env then .env file fallback
config:
- ChatdConfig in internal/shared/config.go with bind, ollama_url,
per-provider key env names + .env fallback paths, timeout
- Gateway gains chatd_url + /v1/chat + /v1/chat/* routes
- lakehouse.toml [chatd] block with /etc/lakehouse/<provider>.env defaults
tests (19 in internal/chat):
- registry: prefix + :cloud + errors + telemetry + provider listing
- ollama: happy path + prefix strip + format=json + 500 mapping +
flatten_messages
- openai_compat: happy path + format=json + 429 mapping + zero-choices
think=false default in ollama + ollama_cloud — local hot path skips
reasoning, low-budget callers (the playbook_lift judge at max_tokens=10)
get direct answers instead of empty content + done_reason=length.
proven via chatd_smoke acceptance.
acceptance gate: scripts/chatd_smoke.sh — 6/6 PASS:
1. /v1/chat/providers lists exactly registered providers (1 in dev mode)
2. bare model → ollama default with content + token counts + latency
3. explicit ollama/<m> → prefix stripped at upstream
4. <m>:cloud without ollama_cloud registered → 404 (no silent fall-through)
5. unknown/<m> → falls through to default → upstream 502 (no prefix rewrite)
6. missing model field → 400
just verify: PASS (vet + 30 packages × short tests + 9 smokes).
chatd_smoke is a domain smoke (not in just verify, mirrors matrix /
observer / pathway pattern).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
migrate the reality-test harness's judge-model default from a
hardcoded "qwen3.5:latest" string to cfg.Models.LocalJudge.
resolution priority: explicit -judge flag > $JUDGE_MODEL env >
cfg.Models.LocalJudge from lakehouse.toml > hardcoded fallback.
bumping the judge for run #N+1 now means editing one line in
lakehouse.toml [models].local_judge — no Go file or shell script
edits required.
changes:
- scripts/playbook_lift/main.go: -config flag added, judge default
flips to "" so resolution chain runs. Imports internal/shared for
config loader.
- scripts/playbook_lift.sh: JUDGE_MODEL no longer defaulted in bash;
EFFECTIVE_JUDGE resolved by mirror-of-the-Go-chain (env > config
grep > qwen3.5:latest fallback). Used for the Ollama presence
check + report header. Pre-flight grep avoids requiring jq just
to read the toml.
- reports/reality-tests/README.md: documents the 4-step priority
chain.
verified all 4 paths produce the expected judge:
- config (no env): qwen3.5:latest (from lakehouse.toml)
- env override: env wins
- flag override: flag wins over env
- missing config: DefaultConfig fallback still gives qwen3.5:latest
just verify PASS.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
migrate the strong-model auto-downgrade gate from a hardcoded weak
list to cfg.Models.WeakModels. backward compatible: existing API
preserved, callers that don't migrate keep using DefaultWeakModels.
changes:
- internal/matrix/downgrade.go: split IsWeakModel into rule-based
base (`:free` suffix/infix) + literal-list lookup. New
IsWeakModelInList(model, list) takes the config-supplied list.
DowngradeInput grows a WeakModels field; nil falls back to
DefaultWeakModels (preserves pre-phase-2 behavior).
- internal/workflow/modes.go: add MatrixDowngradeWithWeakList(list)
factory mirroring MatrixSearch's pattern. Plain MatrixDowngrade
kept for backward compat.
- cmd/matrixd/main.go: handlers struct holds weakModels populated
from cfg.Models.WeakModels at startup; handleDowngrade threads it
into every DowngradeInput.
- cmd/observerd/main.go: registerBuiltinModes accepts weakModels
and uses the factory variant. observerd reads cfg.Models.WeakModels
in main().
end-to-end verified: downgrade + matrix + observer + workflow smokes
all pass. Existing TestMaybeDowngrade_TruthTable + TestIsWeakModel
unchanged (backward compat). Two new tests cover the config path:
- TestIsWeakModelInList — covers rule + literal + empty + nil
- TestMaybeDowngrade_WithConfigList — verifies cfg list overrides
default
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Codifies the small-model-pipeline tiering (per project_small_model_pipeline_vision.md)
in lakehouse.toml [models] section. Tier names map to actual model
IDs; bumping a model means editing one line, not hunting through code.
Tier philosophy:
- local_* : on-box Ollama. Inner-loop hot path. Repeated calls.
- cloud_* : Ollama Cloud (Pro plan). Larger context, fail-up tier.
- frontier_* : OpenRouter / OpenCode. Rate-limited, billed per call.
weak_models is the codified "local-hot-path eligible" list — phase 2
will migrate matrix.downgrade to read it instead of hardcoding.
Defaults reflect 2026-04-29 architecture: qwen3.5:latest as local
(stronger than qwen2.5, same JSON-clean property), kimi-k2.6 as cloud
judge (kimi-k2:1t still upstream-broken), opus-4-7 + kimi-k2-0905 as
frontier review/arch via OpenRouter, opencode/claude-opus-4-7 as
frontier_free leveraging the OpenCode subscription.
3 new tests in internal/shared/config_test.go:
- TestDefaultConfig_ModelsTier — locks tier defaults
- TestModelsConfig_IsWeak — weak-bypass list
- TestLoadConfig_ModelsTOMLRoundTrip — override semantics
just verify PASS (g2 had one flake on first run — Ollama transfer
truncation; clean on retry, unrelated to this change).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
First reality test driver. Two-pass design:
- Pass 1 (cold): matrix.search use_playbook=false → small-model judge
rates top-K → record playbook entry pointing at the highest-rated
result (which may NOT be top-1 by distance — that's the discovery).
- Pass 2 (warm): same queries with use_playbook=true → measure
ranking shift. Lift = real if recorded answer becomes top-1.
Files:
- scripts/playbook_lift/main.go driver (391 LoC)
- scripts/playbook_lift.sh stack-bring-up + report gen
- tests/reality/playbook_lift_queries.txt query corpus (5 placeholders;
J writes real 20+)
- reports/reality-tests/README.md framework + interpretation
- .gitignore track reports/reality-tests/
but ignore per-run JSON evidence
This answers the gate from project_small_model_pipeline_vision.md:
"the playbook + matrix indexer must give the results we're looking
for." Without ground-truth labels, the LLM judge is the proxy — the
same small-model thesis applied to evaluation. Honest about that
limitation in the generated reports.
Driver compiles clean; full run requires Ollama + workers/candidates
ingest. Skips cleanly if Ollama absent.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
5 small fixes from the §3.8 scrum2 review wave:
- workflow.stringifyValue now JSON-marshals maps/slices instead of
fmt.Sprint %v (Opus+Kimi convergent: LLM modes were getting Go's
map[k:v] syntax, which is unparseable as JSON context).
- workflow.detectCycle removed — duplicate of topoSort that discarded
the useful node ID. Validate() now calls topoSort directly and
returns its wrapped ErrCycle.
- observer.SourceWorkflow named constant — was an implicit string
cast (observer.Source("workflow")) at the cmd/observerd handler.
- Unused context imports + dead silencer comments removed across
workflow/modes.go and observerd/main.go.
- Unused store parameter dropped from registerBuiltinModes (reserved
comment removed; can be re-added when a mode actually needs it).
just verify still PASS — these are pure cleanup, no behavior change.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Audited stash-clean c7e3124 (30 commits past rerun-1 4840c10).
3 HIGH risks closed (R-002 internal/shared, R-003 internal/storeclient,
R-008 queryd/db.go). 3 advanced to partial (R-001 via fail-loud-bind +
opt-in auth, R-006 via g2_smoke_fixtures, R-007 via ADR-003 auth.go).
Biggest move: Agent Memory Correctness 4 → 9 — pathway Mem0 ops
(ADD/UPDATE/REVISE/RETIRE/HISTORY) all tested, including cycle-detection
and retired-trace-exclusion. Sprint 2 acceptance criteria are now
verified code, not design-bar work.
Two new findings:
- F1 (MED): cmd/{matrixd,observerd,pathwayd}/main_test.go absent —
reopens R-005 against new daemons.
- F2 (LOW): scripts/staffing_*/main.go flag-defaults reach
/home/profit/lakehouse/data/...
Evidence under reports/scrum/_evidence/rerun2/ (local; per
.gitkeep convention).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
distillation.score, drift.scorer)
Lands the workflow.Mode adapters for the §3.4 components + the
distillation scorer + drift quantifier. Workflows can now compose
real measurement capabilities; the substrate's parallel
capabilities become composable Lego bricks (per the prior commit's
closing insight).
Modes registered (in observerd's registerBuiltinModes):
Pure-function wrappers (no I/O):
- matrix.relevance → matrix.FilterChunks
- matrix.downgrade → matrix.MaybeDowngrade
- distillation.score → distillation.ScoreRecord
- drift.scorer → drift.ComputeScorerDrift
HTTP-backed:
- matrix.search → POST matrixd /matrix/search
(registered only when matrixd_url is set)
Fixture (kept from §3.8 first slice):
- fixture.echo, fixture.upper
internal/workflow/modes.go:
Each mode follows the same glue pattern: marshal generic input
through a typed struct (free schema validation + clear error
messages), call the underlying capability, return a generic
output map. Roundtrip-via-JSON gives us schema validation
without writing custom field-by-field coercion.
internal/workflow/modes_test.go (10 tests, all PASS):
- matrix.relevance filters adjacency pollution (Connector kept,
catalogd::Registry dropped — same headline as the relevance
smoke, run through the workflow mode)
- matrix.downgrade flips lakehouse→isolation on strong model;
keeps lakehouse on weak (qwen3.5:latest); errors on missing
fields
- distillation.score rates scrum_review attempt_1 as accepted;
rejects empty record
- drift.scorer reports zero drift on matched inputs; errors on
empty inputs slice
- matrix.search HTTP flow round-trips through httptest fake
matrixd; non-OK status surfaces a clear error
scripts/workflow_smoke.sh (5 assertions PASS, was 4):
New assertion #5: real-mode chain
matrix.downgrade (lakehouse + grok-4.1-fast → isolation)
→ distillation.score (scrum_review attempt_1 → accepted)
Proves §3.4 components compose through the workflow runner with
no fixture intermediation. Both nodes ran successfully, runner
recorded provenance, status=succeeded.
Mode listing assertion now expects 7 modes (5 real + 2 fixture)
instead of just the fixtures.
17-smoke regression all green. SPEC §3.8 acceptance gate G3.8.D
("Mode catalog dispatches matrix.search invocation to the matrixd
backend without going through HTTP") still pending — current path
goes through HTTP for matrix.search, which is the cleaner service-
mesh shape but slower than direct in-process. In-process dispatch
when matrixd is co-resident is a future optimization.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Per the 2026-04-29 scope-discipline pause: the wave shipped four
pieces beyond SPEC §3.4 component scope, and one architectural
pattern surfaced (Archon-style multi-pass workflow runner) that's
the observer's natural growth path. Document them as port targets
so the next scrum review has authoritative SPEC components.
§3.5 — Drift quantification (loop 5 of the PRD)
Names the SCORER drift work shipped in be65f85 + the deferred
shapes (PLAYBOOK drift, EMBEDDING drift, AUDIT BASELINE drift).
Acceptance gates G3.5.A–B.
§3.6 — Staffing-side structured filter
Names the metadata-filter MVP shipped in b199093 + the deferred
pre-retrieval SQL gate via queryd. Acceptance gates G3.6.A–C.
§3.7 — Operational rating wiring
Names the bulk playbook-record endpoint shipped in 6392772 + the
deferred UI shim, negative-feedback path, and time-decay.
Acceptance gates G3.7.A–B.
§3.8 — Observer-KB workflow runner (Archon-style multi-pass) —
PORT TARGET, not yet started
Documents the architecture J was working on across the Rust
observer-kb branch (10 commits ahead of main, never merged) and
the local Archon mod (committed 2026-04-29 as 3f2afc8 in
/home/profit/external/Archon, not pushed to coleam00/Archon).
The pattern: multi-pass mode chain (extract → validator →
hallucination → consensus → redteam → pipeline → render) where
each pass is a deterministic measurement. The observer is the
natural home — workflows ARE observation patterns whose every
step is recorded. Five components in dependency order: workflow
definition (YAML), node executor (DAG runner), provenance
recording (ObservedOps), mode catalog (matrix.search,
distillation.score, drift.scorer, llm.chat), HTTP surface
(/v1/observer/workflow/run).
Reference materials on the system (preserved, not lost):
- /home/profit/lakehouse/.archon/workflows/lakehouse-architect-review.yaml
(Rust main, 69919d9) — 3-node Archon-via-Lakehouse proof
- /home/profit/external/Archon dev branch — upstream engine
with local pi/provider.ts mod (3f2afc8) for Lakehouse routing
- Rust observer-kb branch — apps/observer-kb/docs/PRD.md +
Python prototypes proven on real ChatGPT/Claude PDF data
Acceptance gates G3.8.A–D. Estimated effort: L.
PRD updated with "Observer as system resource (clarified
2026-04-29)" section pointing at §3.8 as the architectural growth
path. The bare-bones observerd in bc9ab93 is the substrate; the
workflow runner is what makes it the "objective measurement engine"
the small-model pipeline needs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
POST /v1/matrix/playbooks/bulk accepts an array of playbook entries
and records each independently — failures per-entry don't abort the
batch. Designed for two operational use cases:
1. Backfilling historical placement data into the playbook
substrate (the Rust system has 4,701 fill operations recorded
with embeddings; that data deserves to feed the Go learning
loop without a 4,701-call procedural script).
2. Batched click-tracking from a session's worth of coordinator
interactions, posted once at idle rather than per-click.
Per-entry response shape: {index, playbook_id} on success or
{index, error} on failure. Caller can inspect failures without
diffing.
Smoke (scripts/playbook_smoke.sh, new assertion #4):
Bulk POST 3 entries: 2 valid (alpha→widget-a, bravo→widget-b) +
1 invalid (empty query_text). Verifies recorded=2, failed=1,
the 2 valid ones get playbook_ids back, and the invalid one
surfaces its validation error in-line.
Single-record /matrix/playbooks/record from 06e7152 still works
unchanged; bulk is additive. The corpus field can be set per-
entry or once at the batch level (entry-level wins on collision).
Per the small-model autonomous pipeline framing: this is the
"the playbook gets denser with each iteration" mechanism. Click
tracking → bulk POST → playbook entries → future similar queries
get those answers boosted via the existing /matrix/search
use_playbook path. The learning loop now has both inflows wired
(single + bulk) — what remains is the demo UI shim that calls
/feedback on result interaction (deferred — no Go demo UI yet).
15-smoke regression all green.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Addresses the reality-test gap surfaced by the candidates and
multi-corpus e2e runs (0d1553c, a97881d): semantic-only retrieval
can't gate by status / state / availability. SearchRequest now
takes an optional MetadataFilter map; results whose metadata
doesn't match every key are dropped before top-K truncation.
Filter value semantics:
string|number|bool → exact equality (JSON-canonical, so 1 ≡ 1.0)
[]any → OR within key (any element matching wins)
AND across keys: every filter key must match.
Missing key in metadata = drop. Malformed metadata = drop. Filter
absent or empty = pass through (zero overhead).
The response now reports MetadataFilterDropped so callers can see
how aggressive the filter was without re-querying.
Caveat (also captured in code comment): this is POST-retrieval, not
PRE-filtering via SQL. Aggressive filters can shrink the result set
below K; caller should bump PerCorpusK to compensate. A queryd-
backed pre-filter is a future commit; this lands the user-visible
fix today.
Tests:
- 7 unit tests (internal/matrix/filter_test.go) covering: nil/
empty filter pass-through, missing-metadata always-fails,
single-value exact match (incl. numeric 5 ≡ 5.0), AND across
keys, OR within list, bool match, malformed JSON metadata
- matrix_smoke.sh: new assertion #7 — filter
label∈{"a near","b near"} drops the 4 mid/far entries from the
6-entry pool, keeping exactly 2 (one per corpus, both with the
matching label). Dropped count surfaces in the response.
15-smoke regression all green. vet clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
PRD's 5-loop substrate names "drift" as loop 5: quantify when
historical decisions stop matching current reality. Distinct from
the rating+distillation loop because drift is MEASUREMENT, not
LEARNING. The learning loop says "this match worked, remember it";
the drift loop says "this 4-month-old playbook entry — does it
still match what the substrate would surface today?"
First-shipped drift shape: SCORER drift. When the deterministic
scorer's ScorerVersion bumps, historical ScoredRuns may no longer
match what the current scorer produces on the same EvidenceRecord.
internal/drift/drift.go:
- ScorerDriftInput — (EvidenceRecord, persisted_category) pair
- ScorerDriftEntry — one mismatch with current reasons attached
- CategoryShift — (from, to, count) cell in the shift matrix
- ScorerDriftReport — summary + sorted shift matrix + optional entries
- ComputeScorerDrift(inputs, includeEntries) — pure function;
re-runs ScoreRecord over each input and reports mismatches
Why this matters: without a drift quantifier, a scorer-rule change
silently invalidates the historical training data feeding the
learning loop. With drift quantification, a rule change surfaces
a concrete number ("847 of 4701 historical ScoredRuns now
disagree") that triggers a re-score-and-retrain cycle rather than
letting the substrate quietly rot.
Tests (6/6 PASS):
- No-drift: all 3 inputs match → 100% matched
- Shift detected: 5 inputs, 3 drift cases, drift_rate=0.6,
shift matrix shows accepted→partially_accepted x3
- Multiple shifts sorted by count desc
- includeEntries=false skips the per-mismatch list
- Empty input → all-zero report (no division-by-zero)
- ScorerVersion stamped on every report
Future drift shapes (deferred to follow-ups, named in package doc):
- PLAYBOOK drift: re-run playbook queries through current
matrix-search; recorded answer not in top-K = drift
- EMBEDDING drift: KS-test on vector distribution at T1 vs T2
- AUDIT BASELINE drift: matches Rust audit_baselines.jsonl
longitudinal signal
Pure compute. Materialization layer (read scored-runs jsonl + their
matching evidence jsonl + feed into ComputeScorerDrift) lands with
the distillation materialization commit.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
First slice of the Rust v1.0.0 distillation substrate (e7636f2)
ported to Go per ADR-001 #4 (port LOGIC, not bit-identical
reproducibility). This commit lands the LOAD-BEARING pieces named
in project_distillation_substrate.md memory:
- The deterministic Success Scorer (8 sub-scorers + dispatch)
- The contamination firewall on SFT samples (the "non-negotiable"
spec property: rejected/needs_human_review NEVER ship to SFT)
- All on-wire types + validators for ScoredRun, SftSample,
EvidenceRecord with Provenance
Files:
internal/distillation/types.go — types + ScorerVersion + SftNever
+ ValidateScoredRun + ValidateSftSample
internal/distillation/scorer.go — ScoreRecord + 8 class scorers +
BuildScoredRun (deterministic)
internal/distillation/scorer_test.go — ~40 test cases:
- source-class dispatch (verdict / telemetry / extraction)
- scrum_review (4 attempt cases)
- observer_review (5 verdict cases)
- audit (legacy + severity, 9 cases)
- auto_apply (4 cases)
- outcomes / mode_experiment / extraction
- CONTAMINATION FIREWALL: ErrSftContamination sentinel fires
on rejected/needs_human_review, distinct from typo errors
- empty-pair guard (instruction/response trim != "")
- reasons-required ScoredRun validation
- deterministic sig_hash on identical input
- purity check (input not mutated, repeatable output)
Per the 2026-04-29 cross-lineage scrum's discipline: false-positive
findings would be dismissed inline (none in this commit). Real
findings would be addressed before merge — but this is greenfield
port code reviewed against its Rust source line-by-line, which the
test suite encodes as truth tables.
Explicitly DEFERRED to follow-up commits:
- Materialization layer (jsonl read/write, date-partitioned
storage in data/scored-runs/YYYY/MM/DD/, evidence index)
- SFT exporter (file iteration + filtering — the SCORING firewall
is here; the EXPORT firewall is the next layer)
- export_preference, export_rag (other export shapes)
- Acceptance harness (16/16 acceptance gate that locks v1.0.0)
- replay, receipts, build_evidence_index, transforms
The scorer + firewall validator are pure functions — operational
tooling layers on top without changing the deterministic logic the
downstream learning loop depends on. The Go ScorerVersion stays at
v1.0.0 to match the Rust e7636f2 baseline; bumping in the Go
materialization commit is reserved for the next scoring-rule
change, NOT the port itself.
15-smoke regression all green. vet clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Workers driver embed text reverted to V0 after testing 3 variants
on the "Forklift operator with OSHA-30 certification, warehouse
experience" reality-test query against 5000 workers (which contains
569 actual Forklift Operators per the 31b4088 probe).
V0 (current, restored): "Worker role: <role>. Skills: ...
Certifications: ... <resume_text>"
→ 6 workers in top-8, 0 Forklift Ops,
top distance 0.327, top role
"Production Worker"
V4a (role-doubled): "<role>. <role> with <skills>. ..."
drop archetype + resume_text
→ 6 workers in top-8, 0 Forklift Ops,
top distance 0.254, top role
"Production Worker"
V4b (resume-only): just the resume_text natural-language
sentence, no structured prefix
→ 4 workers in top-8 (WORSE mix —
software-engineer candidates filled
the displaced slots), 0 Forklift Ops,
top distance 0.379
Conclusion: all three variants surface Production Workers / Machine
Operators / Line Leads ABOVE Forklift Operators for this query.
The 569 actual Forklift Operators in the 5000-row sample don't
appear in any top-8. Embed-text design isn't the bottleneck —
nomic-embed-text 137M's geometry doesn't separate "Forklift
Operator" from "Production Worker" / "Machine Operator" / "Line
Lead" in this query's neighborhood.
Real fixes belong elsewhere:
- Hybrid SQL+semantic (B): pre-filter by role/certs via queryd
before semantic ranking. Addresses the gap directly.
- Different embedding model: mxbai-embed-large or a staffing-
fine-tuned model. Costs an Ollama model swap + re-embedding.
- Playbook boost (component 5, already shipped): record
successful Forklift placements; future queries surface those
workers via similarity. Compounds with use.
V0 restored because it has the best worker/candidate mix in top-8
(6 vs 4 in V4b), preserving the multi-corpus reality-test signal
quality even if the role match is imperfect. Comments updated to
record the experiment so future sessions don't relitigate.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Cross-lineage scrum review on the 12 commits of this session
(afbb506..06e7152) via Rust gateway :3100 with Opus + Kimi +
Qwen3-coder. Results:
Real findings landed:
1. Opus BLOCK — vectord BatchAdd intra-batch duplicates panic
coder/hnsw's "node not added" length-invariant. Fixed with
last-write-wins dedup inside BatchAdd before the pre-pass.
Regression test TestBatchAdd_IntraBatchDedup added.
2. Opus + Kimi convergent WARN — strings.Contains(err.Error(),
"status 404") was brittle string-matching to detect cold-
start playbook state. Fixed: ErrCorpusNotFound sentinel
returned by searchCorpus on HTTP 404; fetchPlaybookHits
uses errors.Is.
3. Opus WARN — corpusingest.Run returned nil on total batch
failure, masking broken pipelines as "empty corpora." Fixed:
Stats.FailedBatches counter, ErrPartialFailure sentinel
returned when nonzero. New regression test
TestRun_NonzeroFailedBatchesReturnsError.
4. Opus WARN — dead var _ = io.EOF in staffing_500k/main.go
was justified by a fictional comment. Removed.
Drivers (staffing_500k, staffing_candidates, staffing_workers)
updated to handle ErrPartialFailure gracefully — print warn, keep
running queries — rather than fatal'ing on transient hiccups
while still surfacing the failure clearly in the output.
Documented (no code change):
- Opus WARN: matrixd /matrix/downgrade reads
LH_FORCE_FULL_ENRICHMENT from process env when body omits
it. Comment now explains the opinionated default and points
callers wanting deterministic behavior to pass the field
explicitly.
False positives dismissed (caught and verified, NOT acted on):
A. Kimi BLOCK on errors.Is + wrapped error in cmd/matrixd:223.
Verified false: Search wraps with %w (fmt.Errorf("%w: %v",
ErrEmbed, err)), so errors.Is matches the chain correctly.
B. Kimi INFO "BatchAdd has no unit tests." Verified false:
batch_bench_test.go has BenchmarkBatchAdd; the new dedup
test TestBatchAdd_IntraBatchDedup adds another.
C. Opus BLOCK on missing finite/zero-norm pre-validation in
cmd/vectord:280-291. Verified false: line 272 already calls
vectord.ValidateVector before BatchAdd, so finite + zero-
norm IS checked. Pre-validation is exhaustive.
D. Opus WARN on relevance.go tokenRe (Opus self-corrected
mid-finding when realizing leading char counts toward token
length).
Qwen3-coder returned NO FINDINGS — known issue with very long
diffs through the OpenRouter free tier; lineage rotation worked
as designed (Opus + Kimi between them caught everything Qwen
would have).
15-smoke regression sweep all green (D1-D6, G1, G1P, G2,
storaged_cap, pathway, matrix, relevance, downgrade, playbook).
Unit tests all green (corpusingest +1, vectord +1).
Per feedback_cross_lineage_review.md: convergent finding #2 (404
detection) is the highest-signal one — both Opus and Kimi
flagged it independently. The other Opus findings stand on
single-reviewer signal but each one verified against the actual
code.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes SPEC §3.4. The matrix indexer is now a learning meta-index per
feedback_meta_index_vision.md — every successful (query → answer)
pair recorded via /matrix/playbooks/record boosts that answer for
future similar queries.
This is the architectural piece that lifts vectord from "static
hybrid search" to the meta-index J originally framed in Phase 19 of
the Rust system.
What's new:
- internal/matrix/playbook.go — PlaybookEntry, PlaybookHit,
ApplyPlaybookBoost. Pure-function boost math:
distance' = distance * (1 - 0.5 * score)
Score 0 = no boost (factor 1.0); score 1 = halve distance
(factor 0.5). Capped at 0.5 deliberately so a single high-
confidence playbook can't dominate the base ranking forever
(runaway-feedback-loop guard).
- Retriever.Record(entry, corpus) — embeds query_text, ensures
playbook corpus exists (idempotent), upserts via deterministic
sha256-derived ID (last score wins on re-record of same triple).
- Retriever.Search extended with UsePlaybook + PlaybookCorpus +
PlaybookTopK + PlaybookMaxDistance. Reuses the query vector —
no extra embed call. Missing-corpus 404 = no-op (cold-start
state before any Record call), not an error.
- POST /v1/matrix/playbooks/record (matrixd) — caller submits
{query_text, answer_id, answer_corpus, score, tags?}; gets
{playbook_id} back.
Storage: a vectord index named "playbook_memory" (configurable per
request) with embed(query_text) as the vector and the
PlaybookEntry JSON as metadata. Just another corpus — observable
from /vectors/index, persistable through G1P, etc.
Match key for boost: (AnswerID, AnswerCorpus). Cross-corpus ID
collisions don't false-match — verified by
TestApplyPlaybookBoost_CorpusAttributionRespected.
End-to-end smoke (scripts/playbook_smoke.sh, all assertions PASS):
- Baseline search: widget-c at distance 0.6566 (rank 3)
- Record playbook: query → widget-c, score=1.0
- Re-search with use_playbook=true:
widget-c distance: 0.3283 (rank 2)
ratio: 0.5 EXACTLY (matches boost math precisely)
playbook_boosted: 1
- widget-c jumped from #3 to #2 — learning loop visible
Tests:
- 8 unit tests in internal/matrix/playbook_test.go covering
Validate, BoostFactor (5 cases), the no-boost identity, the
boost-moves-result-up scenario, highest-score wins on duplicate
matches, cross-corpus attribution, JSON round-trip, and
rejection of empty metadata
- scripts/playbook_smoke.sh integration test (3 assertions PASS)
15-smoke regression sweep all green (D1-D6, G1, G1P, G2,
storaged_cap, pathway, matrix, relevance, downgrade, playbook).
SPEC §3.4 NOW COMPLETE: 5 of 5 components shipped. The matrix
indexer's port is done as a substrate; remaining work is operational
(rating signal sources, telemetry, eventual structured filtering for
staffing data — none in §3.4).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds WORKERS_LIMIT env override (default 5000) so the e2e can be
re-run at different sample sizes. Tiny change; the interesting part
is the FINDING that motivated the run.
Investigation: a97881d's reality test put zero Forklift Operators in
the top-6 for "Forklift operator with OSHA-30 certification,
warehouse experience" — instead returned Production Worker / Machine
Operator / Assembler.
Hypothesis tested: maybe the 5000-row sample didn't contain
forklift operators in retrievable density.
Result: hypothesis falsified. Direct probe of workers_500k.parquet:
All 500K rows → 55,349 Forklift Operators (11.07%)
→ 150,328 with "forklift" in certs
→ 74,852 with OSHA-30 specifically
First 5K rows → 569 Forklift Operators (11.38%)
→ distribution matches global, no ordering bias
So 569 forklift operators were IN the corpus the matrix indexer
searched and STILL didn't surface in top-6. That means the bottleneck
isn't sample size — it's nomic-embed-text + our embed-text template
ranking "Production Worker" / "Machine Operator" / "Assembler" as
semantically nearer to the query than literal "Forklift Operator".
The reality test exposed this faithfully. Three real follow-ups, none
in scope of this commit:
1. Embed text design — front-loading role + certs (currently
"Worker role: <role>" then skills then certs) might dominate
retrieval better. Worth A/B-testing.
2. Hybrid SQL+semantic — pre-filter by role/certs via queryd
before semantic ranking. Not in SPEC §3.4 today; would address
the "available" / "Chicago" gap from the candidates reality
test (0d1553c) too.
3. Playbook-memory boost — SPEC §3.4 component 5. When a query
"Forklift OSHA-30" was answered with worker w-X in the past,
boost w-X's score for similar future queries. The retrieval
gap CAN be bridged by the learning loop without changing the
base embedder.
Commits the env knob; the finding lives in the commit body so future
sessions don't re-run the sample-size hypothesis.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Lands the second real-data corpus (workers_500k) and the first
multi-corpus reality test through /v1/matrix/search composing both
corpora live.
What's new:
- scripts/staffing_workers/main.go — parquet driver over
workers_500k.parquet, multi-chunk arrow handling (workers
parquet has multiple row groups vs candidates' one). Embed text:
role + skills + certifications + city + state + archetype +
resume_text. IDs prefixed "w-".
- scripts/multi_corpus_e2e.sh — first end-to-end test composing
both corpora through the matrix indexer.
Real-data multi-corpus result (this commit):
Query: "Forklift operator with OSHA-30 certification, warehouse
experience"
Corpora: workers (5000 rows) + candidates (1000 rows)
Merged top-8: workers=6, candidates=2
Top hits:
w d=0.327 w-4573 Production Worker
w d=0.353 w-1726 Machine Operator
w d=0.362 w-3806 Production Worker
w d=0.366 w-1000 Machine Operator
w d=0.374 w-1436 Assembler
w d=0.395 w-162 Machine Operator
c d=0.440 c-CAND-00727 C#,.NET,Azure
c d=0.446 c-CAND-00031 React,TypeScript,Node
The matrix indexer correctly chose the right domain — manufacturing/
warehouse roles in workers (correct semantic match for the staffing
query) rank ABOVE software-engineer candidates from the candidates
corpus. 0.11 gap between the worst worker (0.395) and the best
candidate (0.440) — clean distance separation.
Compared to the candidates-only e2e run from 0d1553c:
candidates-only top: c-CAND-00727 at d=0.4404
multi-corpus top: w-4573 at d=0.3265 (a Production Worker)
That's the matrix indexer's whole point made visible: composing
domain-distinct corpora surfaces better matches than single-corpus
search. Without workers in the search space, the staffing query
returned software engineers (wrong domain). With workers, it
returns roles in the right ballpark.
What's still imperfect (signal for component 5 + future work):
- No top-6 worker actually has "Forklift" or "OSHA-30" visible in
metadata; "Production Worker" is semantically nearest in this
sample. Likely needs a larger workers ingest (5000 from 500K)
or skill-keyword boost.
- Status/availability still not gated. The staffing-side
structured filtering gap from 0d1553c persists; relevance filter
(CODE-aware) doesn't address it.
Pipeline timings:
workers ingest: 5000 rows / 19.2s = 260/sec end-to-end
candidates ingest: 1000 rows / 3.1s = 322/sec
multi-corpus query (text → embed → 2 parallel vectord → merge): 14ms
14-smoke regression sweep all green (D1-D6, G1, G1P, G2,
storaged_cap, pathway, matrix, relevance, downgrade).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Faithful port of mcp-server/relevance.ts (Rust observer's adjacency-
pollution filter). Same 5-signal scoring, same default threshold 0.3.
Adds POST /v1/matrix/relevance endpoint via matrixd.
Scoring signals (additive, can sign-flip):
path_match +1.0 chunk source/doc_id encodes focus.path
filename_match +0.6 chunk text mentions focus's filename
defined_match +0.6 chunk text mentions focus.defined_symbols
token_overlap +0.4 jaccard of non-stopword tokens
prefix_match +0.3 chunk source shares first-2-segment prefix
import_penalty -0.5 mentions ONLY imported symbols, no defined ones
What this does and doesn't do:
- DOES filter code-aware corpora (eventually lakehouse_arch_v1,
lakehouse_symbols_v1, scrum_findings_v1) — drops chunks about
code the focus file IMPORTS rather than DEFINES, the
"adjacency pollution" pattern that makes a reviewer LLM
hallucinate imported-crate internals as belonging to the focus
- DOES NOT meaningfully filter staffing data — the candidates
reality test 2026-04-29 had "exact skill match buried at #3"
which is a different problem (semantic-only ranking dominated
by secondary text). Staffing needs structured filtering
(status gates, location gates) that lives outside this
package — future work, not in SPEC §3.4 yet
Headline smoke assertion: focus = crates/queryd/src/db.go which
defines Connector and imports catalogd::Registry. The filter
scores:
Connector chunk: +0.68 (defined_match fires, kept)
Registry chunk: -0.46 (import_only penalty fires, dropped)
unrelated junk: 0.00 (no signals, dropped)
That's a 1.14-point gap between what we ARE and what we IMPORT —
the entire purpose of the filter.
Tests:
- 9 unit tests in internal/matrix/relevance_test.go covering
Tokenize, Jaccard, ExtractDefinedSymbols (Rust + TS),
ExtractImportedSymbols, FilePrefix, ScoreRelevance per-signal,
FilterChunks threshold splitting, and the headline
AdjacencyPollutionScenario
- scripts/relevance_smoke.sh integration smoke (3 assertions PASS):
adjacency-pollution scenario, empty-chunks 400, threshold honored
13-smoke regression sweep all green (D1-D6, G1, G1P, G2,
storaged_cap, pathway, matrix, relevance).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Lands the second staffing corpus and the first end-to-end reality test
through the full Go pipeline: parquet → corpusingest → embedd →
vectord → matrixd → gateway.
What's new:
- scripts/staffing_candidates/main.go — parquet Source over
candidates.parquet (1000 rows, 11 cols), single-chunk arrow-go
pqarrow read. Embed text: "Candidate skills: <s>. Based in
<city>, <state>. <years> years experience. Status: <status>.
<first> <last>." IDs prefixed "c-" so multi-corpus merges
against workers ("w-") stay unambiguous.
- scripts/candidates_e2e.sh — first integration smoke that runs
the full stack (storaged + embedd + vectord + matrixd + gateway),
ingests via corpusingest, runs a real query through
/v1/matrix/search, prints results. Ephemeral mode (vectord
persistence disabled via custom toml) so re-runs don't pollute
MinIO _vectors/ and break g1p_smoke's "only-one-persisted-index"
assertion.
Real bug caught + fixed in corpusingest:
When LogProgress > 0, the progress goroutine's only exit was
ctx.Done(). With context.Background() in the production driver,
Run hung forever after the pipeline finished. Added a stopProgress
channel that close()s after wg.Wait(). Regression test
TestRun_ProgressLoggerExits bounds Run's wall to 2s with
LogProgress=50ms.
This is the bug the unit tests didn't catch because every prior test
set LogProgress: 0. Reality test surfaced it on first real-data
run — exactly the hyperfocus-and-find-architectural-weakness
property J framed as the reason for the Go pass.
End-to-end output (1000 candidates, query "Python AWS Docker
engineer in Chicago available now"):
populate: scanned=1000 embedded=1000 added=1000 wall=3.5s
matrix returned 5 hits in 26ms
The result quality is the interesting signal: top-5 had ZERO
Chicago candidates, ZERO active-status candidates, and the exact-
skill-match (Python,AWS,Docker) ranked #3 not #1. Pipeline works;
retrieval quality has real architectural limits (no structured
filtering, no relevance gate, semantic-only ranking dominated by
secondary signals like "1 year experience" and "engineer"). This
motivates SPEC §3.4 components 3 (relevance filter) and
eventually structured filtering — exactly the kind of finding the
deep field reality tests are supposed to surface before Enterprise
cutover.
12-smoke regression sweep all green. 9 corpusingest unit tests
including the new regression. vet clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Generalizes the staffing_500k driver's embed-and-push loop into
internal/corpusingest. Per docs/SPEC.md §3.4 component 1 (corpus
builders): adding a new staffing/code/playbook corpus is now one
Source impl + one main.go calling Run, not 200 lines of pipeline
copy-paste.
API:
type Source interface { Next() (Row, error) }
func Run(ctx, Config, Source) (Stats, error)
Library owns:
- Index lifecycle (create, optional drop-existing, idempotent
reuse on 409)
- Parallel embed dispatcher (configurable workers + batch size)
- Vectord push batching
- Progress logging + Stats reporting
- Partial-failure semantics (log + continue per-batch errors;
operator decides on re-run via Stats.Embedded vs Scanned delta)
Per-corpus driver owns: source parsing + column→Row mapping +
post-ingest validation queries.
Refactor scripts/staffing_500k/main.go to use it. Driver is now
~190 lines (was 339), with the embed/add plumbing replaced by one
Run call. -drop flag added so callers can opt out of the destructive
DELETE-first behavior (default still true to keep the 500K test
clean-recall semantics).
Unit tests (internal/corpusingest/ingest_test.go, 8/8 PASS):
- Pipeline shape: 50 rows / 16 batch → 4 embed + 4 add calls,
every ID added exactly once, vectors at correct dimension
- DropExisting fires DELETE
- 409 on create → reuse existing index
- Limit stops early
- Empty Text rows skipped (counted as scanned, not added)
- Required IndexName + Dimension validation
- Context cancel stops mid-pipeline
Real bug caught and fixed by the test suite: if embedd ever returns
fewer vectors than texts in the request (degraded backend), the
addBatch loop would panic with index-out-of-range. Worker now
length-checks the response and logs+skips on mismatch.
12-smoke regression sweep all green (D1-D6, G1, G1P, G2,
storaged_cap, pathway, matrix). vet clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Lands the matrix indexer's first piece per docs/SPEC.md §3.4:
multi-corpus retrieve+merge with corpus attribution per result.
Future components (relevance filter, downgrade gate, learning-loop
integration) layer on top of this surface.
Architecture:
- internal/matrix/retrieve.go — Retriever takes (query, corpora,
k, per_corpus_k), parallel-fans across vectord indexes, merges
by distance ascending, preserves corpus origin per hit
- cmd/matrixd — HTTP service on :3217, fronts /v1/matrix/*
- gateway proxy + [matrixd] config + lakehouse.toml entry
- Either query_text (matrix calls embedd) or query_vector
(caller pre-embedded) — vector takes precedence if both set
Error policy: fail-loud on any corpus error. Silent partial returns
would lie about coverage, defeating the matrix's whole purpose.
Bubbles vectord errors as 502 (upstream), validation as 400.
Smoke (scripts/matrix_smoke.sh, 6 assertions PASS first try):
- /matrix/corpora lists indexes
- Multi-corpus search returns hits from BOTH corpora
- Top hit is the globally-closest across all corpora
(b-near beats a-near at distance 0.05 vs 0.1 — proves merge)
- Metadata round-trips through the merge
- Distances ascending in result list
- Negative paths: empty corpora → 400, missing corpus → 502,
no query → 400
12-smoke regression sweep all green (D1-D6, G1, G1P, G2,
storaged_cap, pathway, matrix).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a "Product vision" section before the Direction-pivot section.
Captures the framing J flagged 2026-04-29: the Go refactor is not the
goal. The goal is a small-model-driven autonomous pipeline that gets
better with each run, with frontier models in audit/oversight, not
the hot path.
Five loops named explicitly:
1. Knowledge pathway (pathway memory + matrix indexer)
2. Execution (small models on focused context)
3. Observer (refines configs that got the model to a good pathway)
4. Rating + distillation (outcomes fold back into the playbook)
5. Drift (measure when the playbook stops matching reality)
Triage / human-in-loop named as the system's job, not an escape
hatch. The gate: "playbook + matrix indexer must give the results
we're looking for" — single load-bearing acceptance criterion.
Why Go after Rust: second-language pass surfaces architectural
weaknesses Rust hid; the pipeline must work AS A PIPELINE, not as
crates that interact. Maps existing Rust components (✓ pathway, ✓
matrix, ✓ observer, ✓ distillation, ✓ auditor; partial: drift,
rating gate, triage).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds matrix indexer as its own row in the §1 component table and a
new §3.4 with port plan. Distinct from vectord (substrate); lives at
internal/matrix/ + gateway /v1/matrix/*.
Five components in dependency order: corpus builders → multi-corpus
retrieve+merge → relevance filter → strong-model downgrade gate →
learning-loop integration.
Locks in the framing J flagged 2026-04-29: in Rust the matrix indexer
was emergent across mode.rs + build_*_corpus.ts + observer /relevance,
and earlier port-planning reduced it to "we have vectord." The SPEC
now names it explicitly so the port preserves the multi-corpus
retrieval shape AND the learning loop, not just the HNSW substrate.
Sharding-by-id was investigated as a throughput fix and rejected —
corpus-as-shard at the matrix layer is the existing retrieval shape
and parallelizes Adds for free.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replaces the per-item Add loop in the HTTP handler with one call to
Index.BatchAdd, which acquires the write-lock once and pushes the
whole batch through coder/hnsw's variadic Graph.Add. Pre-validation
stays in the handler so per-item error messages keep their item-index
precision.
Microbench (internal/vectord/batch_bench_test.go) at d=768 cosine:
N=16 SingleAdd 283µs/op → BatchAdd 170µs/op 1.66×
N=128 SingleAdd 7.9ms/op → BatchAdd 7.5ms/op 1.05×
N=1024 SingleAdd 87.5ms/op → BatchAdd 83.4ms/op 1.05×
Win is biggest at staffing-driver batch sizes (N=16) where
per-call lock + validation overhead is a meaningful fraction. At
larger N the inner HNSW neighborhood search per insert dominates,
which is the load-bearing finding for Option B (sharded indexes):
the throughput ceiling lives inside the library, not at the lock,
so sharding to N parallel Graphs is the only path to true
concurrent-Add throughput.
g1, g1p, g2 smokes all PASS post-change.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Network-callable Mem0-style trace memory at :3217, fronted by gateway
/v1/pathway/*. Closes the ADR-004 wire-up: store substrate landed in
2a6234f, this lands the HTTP surface + [pathwayd] config + acceptance
gate.
Smoke proves the architecturally distinctive properties: Revise →
History walks the predecessor chain backward (audit trail), Retire
excludes from Search default but stays Get-able, AddIdempotent bumps
replay_count without replacing — and all survive kill+restart via
JSONL log replay.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes Sprint 2 design-bar work (audit reports/scrum/sprint-backlog.md):
S2.1 — ADR-004 documents the pathway-memory data model
S2.2 — pathway port lands with deterministic fixture corpus
and full test coverage on day one
S2.3 — retired traces are excluded from retrieval (test
passes; would fail without the filter)
Mem0-style operations: Add / AddIdempotent / Update / Revise /
Retire / Get / History / Search. Each operation is a method on
Store; persistence is JSONL append-only with corruption recovery
on Replay.
internal/pathway/types.go Trace + event + SearchFilter + sentinel errors
internal/pathway/store.go in-memory state + RWMutex + ops
internal/pathway/persistor.go JSONL append-only log with replay
internal/pathway/store_test.go 20 test funcs covering all 7
Sprint 2 claim rows + concurrency
internal/pathway/persistor_test.go 6 test funcs covering missing-
file, corruption recovery, long-line
handling, parent-dir auto-create,
apply-error skip behavior
Sprint 2 claim coverage row-by-row:
ADD TestAdd_AssignsUIDAndTimestamps + TestAdd_RejectsInvalidJSON
UPDATE TestUpdate_ReplacesContentSameUID + Update_MissingUID_Errors
REVISE TestRevise_LinksToPredecessorViaHistory +
TestRevise_PredecessorMissing_Errors +
TestRevise_ChainOfThree_BackwardWalk
RETIRE TestRetire_ExcludedFromSearch +
TestRetire_StillAccessibleViaGet +
TestRetire_StillAccessibleViaHistory
HISTORY/cycle TestHistory_CycleDetected (injected via internal map),
TestHistory_PredecessorMissing_TruncatesChain,
TestHistory_UnknownUID_ErrorsClean
REPLAY/dup TestAddIdempotent_IncrementsReplayCount (locks the
"replay preserves original content" rule per ADR-004)
CORRUPTION TestPersistor_CorruptedLines_Skipped +
TestPersistor_ApplyError_Skipped
ROUND-TRIP TestPersistor_RoundTrip locks the full Save → fresh
Store → Load → Stats-match contract
Two real bugs caught during testing:
- Add returned the same *Trace stored in the map, so callers
holding a reference saw later mutations. Fixed: clone before
return (matches Get's contract). Same fix in AddIdempotent
+ Revise.
- Test typo: {"v":different} isn't valid JSON; AddIdempotent's
json.Valid rejected it as ErrInvalidContent. Test fixed to
use {"v":"different"}; the validation behavior is correct.
Skipped this commit (next):
- cmd/pathwayd HTTP binary
- gateway routing for /v1/pathway/*
- end-to-end smoke
These add the wire surface; the substrate ships first so the
wire layer can be a pure proxy in the next commit.
Verified:
go test -count=1 ./internal/pathway/ — 26 tests green
just verify — vet + test + 9 smokes 34s
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes the "needs heavy integration smoke" follow-up from the
ADR-002 commit (423a381). Until now the per-prefix PUT cap was
verified only by unit tests + commits' theory; this smoke runs
the actual cap path with real bytes.
Three assertions, ~2s wall:
1. PUT 300 MiB to _vectors/<key> → 200 (cap raised to 4 GiB
for the vectord persistence prefix).
2. PUT same 300 MiB to datasets/<key> → 413 (default 256 MiB
cap still protects routine traffic).
3. GET _vectors/<key> → sha256 round-trips (no truncation
between cap-raise and S3 multipart streaming).
scripts/storaged_cap_smoke.sh
Builds storaged + gateway, boots them, generates 300 MiB
deterministic /dev/zero payload (sha stable across runs),
runs the 3 assertions, cleans up the keys + processes via trap.
/dev/zero generation chosen over yes/head pipe — pipefail
catches the SIGPIPE from yes when head closes early.
just smoke-storaged-cap
Wrapper recipe. Outside the main `just verify` chain because
300 MiB payload generation + transfer is MB-heavy. Run after
meaningful storaged or vectord-persistence changes.
Verified:
bash scripts/storaged_cap_smoke.sh — 3/3 PASS · 2s wall
just verify — vet + test + 9 smokes still 33s
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
root