Version bumped in all four places that carry it: package.json,
.claude-plugin/plugin.json, and the fleetVersion in both the .claude/ and
assets/ skills manifests (the assets mirror drifts easily and is shipped).
Adds the v3.13.1 changelog entry and release notes covering the four fixed
issues (#565, #567, #568, #569) plus the Codex QE skills and lifecycle hooks
from a parallel session (763ea385), and draft issue-closing comments to post
once the release is published.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Closes the two security questions raised by the adversarial review that the
prosecutors never returned a ruling on, so I settled them with evidence.
1. Coverage measurement executes the analyzed repository.
Collecting real coverage means running the project's own tests: the JS/TS path
runs `npx vitest|jest|nyc` (pre-existing), and the Rust path added in this
release runs `cargo llvm-cov`, which compiles and runs test binaries, executes
`build.rs`, and honors any `runner`/linker directive in that repo's
`.cargo/config.toml`. For a trusted project that is exactly what the caller
wants; it is surprising for an operation that reads like a static query, and an
agent can be pointed at an untrusted checkout.
Execution stays the default — requiring opt-in would make measured coverage the
exceptional case and estimation the norm, inverting ADR-126's whole point — but
is now opt-out via `AQE_COVERAGE_NO_EXEC=1`, which disables ALL build-tool
execution. Existing coverage reports are still parsed; everything else degrades
to clearly-labelled static estimation with guidance explaining why.
Verified end-to-end through the real MCP server with a fake `cargo` shim on
PATH: switch off -> cargo invoked; switch on -> not invoked. The unit test
includes the same control, so it cannot pass vacuously.
2. Credential stripping in agentOverrides was already complete, but under-reported.
`sanitizeAgentOverrides` builds its result as an ALLOW-LIST, so any field that
is not provider/model/temperature/maxTokens/priority never survives — apiKey,
token, password and friends were all dropped already. Only the *warning* was
apiKey-specific, so a user who pasted a token got no feedback. The warning now
covers all credential-shaped keys, and a test asserts no warning ever echoes a
secret value.
ADR-126 gains a section recording the execution decision and what was rejected
(opt-in-by-default, sandboxing), plus the requirement that future language
delegations honor the same switch.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Four independent user-reported issues, each verified end-to-end through the real
MCP protocol server and adversarially reviewed via qe-court.
#565 — HIGH CVE reachable by consumers
`@huggingface/transformers` was an *optional* peerDependency, but npm >=7
auto-installs optional peers — `optional` only suppresses the error when the peer
cannot be resolved. Every `npm install agentic-qe` therefore pulled
onnxruntime-node -> adm-zip@0.5.x (GHSA-xcpc-8h2w-3j85), and no resolvable
version of that chain is unaffected. Dropped the peer (it stays a devDependency
and an opt-in for local in-process embeddings; both load sites already degrade
with an actionable message). Consumer audit: 4 HIGH -> 0.
#567 — test_generate_enhanced never invoked the LLM
The DI factory behind the task-executor path was registered as `(memory) => ...`,
so `llmRouter` never reached TestGeneratorService and the ADR-051 branch was
unreachable regardless of provider configuration. Threaded the router through the
registry -> resolveTestGeneratorService -> getTestGenerator (now async), honored
the documented `aiEnhancement` opt-out, and surfaced `llmEnhanced` /
`generationMode` / `note` so a silent fallback is diagnosable. `llmEnhanced` now
reflects what the LLM actually produced — a broken provider (401/timeout/empty)
no longer reports AI-enhanced output it did not produce. The CLI was unaffected
(it goes through the domain plugin, which was already wired).
#568 — per-agent provider routing had no on-disk surface
Added `agentOverrides` to `.agentic-qe/llm-config.json` with keyed-object merge,
validation that drops bad entries individually and strips leaked API keys, and
resolution ahead of the category defaults. Materialized the overrides into
routing rules the router actually evaluates, and threaded `agentType` through all
nine router-calling domain services — without it a parsed override built a rule
that never fired. Also added the missing `codex` entry to ALL_PROVIDER_TYPES,
which had made that provider unselectable through the router.
#569 — coverage_analyze_sublinear reported fabricated data for Rust
Coverage now carries provenance (`estimated` / `measured` / `coverageMethod`),
uncollected branch and function metrics report `null` instead of 0 or 100, gaps
derived from an estimate carry low confidence and an `estimated` flag, and Rust
crates are measured with `cargo llvm-cov` where available. Test code (`tests/`,
`benches/`, brace-matched `#[cfg(test)]` blocks) is excluded from production
coverage, and line numbers can no longer exceed the file length. Security scans
now state their analysis depth so "zero findings" is not read as "verified clean".
Adversarial review (qe-court, cross-vendor) found and this commit fixes: an
anchoring bug that dropped `latest_parser.rs` as a test file; brace matching that
counted braces inside string literals and comments; `#[cfg(test)]` on a
non-module item swallowing the following production function; crate detection
that skipped instrumentation for subdirectory targets, over-claimed nonexistent
targets, and hijacked polyglot subtrees; and a Cobertura fallback that rounded a
measured 47% to 0%.
ADR-125 (on-disk agent routing overrides) and ADR-126 (measurement provenance)
document the decisions; ADR-115 gains an amendment on optional peers.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The user-facing intro's "Selected QE skills available" table omitted qe-court and
still read 75. Adds /qe-court to the Review category and updates the count to 76.
AQE-QE-scoped only (excludes ruflo/platform/dev skills); the on-disk "115 skill
definitions" line is already correct (qe-court made it 114→115).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Source-verified in /workspaces/ruflo: the flywheel already refuses to promote a
candidate whose paired candidate-vs-baseline delta isn't significant —
`significant = bootstrapDeltaCILow(paired holdout deltas) > 0`, rule accept/v1+sig,
one-sided 95% paired bootstrap, n>=20 (evolve-proof.ts:174-183). That is STRONGER
than the unpaired ANOVA we were going to contribute (2-group ANOVA F = t², and it
drops the pairing). Our premise ("maybe ruflo promotes noise") was wrong.
Outcome: NO contribution PR (would be redundant and weaker). Corrects the strategy
report's open-Q #3 (ruflo's flywheel IS rigorously DoE-validated) and retires the
M3.1 action. The draft is kept, marked superseded, documenting the one genuinely-
additive idea (an ANOVA candidate-SELECTION veto) and why it's a bigger, replay-
verifier-touching change — deferred, not pursued.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
M3.1: a ready-to-post, collegial issue draft offering AQE's DoE/ANOVA screen
(ADR-122) to validate ruflo's ADR-176 flywheel promotions — the "2 compounding
promotions / flat human anchor" shape matches AQE's own "beads" null. HELD from
posting to ruvnet/ruflo pending the user (a ruflo collaborator).
M3.2: assessment — ruflo v3.25.2's torn-full-image-flush fix does not apply to
AQE (better-sqlite3 WAL = atomic commits, not sql.js full-image flushes); AQE's
actual corruption class (virtiofs WAL/shm) is already mitigated in safe-db.ts.
Transferable lesson filed: auto-restore-on-malformed-open (AQE restores manually
today) — a scoped follow-up, not built here (memory.db recovery is data-sensitive).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
(A) npm "@ruvector Lattice WASM" = vaporware (E404; claude-flow's own source admits
the default package doesn't exist; inert opt-in slot) — the ruvllm mock-mode pattern.
(B) github.com/ohdearquant/lattice = a REAL pure-Rust inference engine (runs on
arm64 here, pushed 2026-07-18). But the shipped binary is chat-only — serve exposes
/v1/chat/completions,/v1/models,/health, NO /v1/embeddings (source
crates/inference/src/serve/mod.rs:248). Embeddings are a separate lattice-embed
crate, source-build-only, CLI not HTTP. Models incl. BGE-small 384 (default) …
Qwen3-Embedding 1024.
Verdict: GO-with-caveats, NOT a drop-in and not the cheapest path — the near-term
win (BGE-small @384, MTEB-stronger than MiniLM, same dim) is reachable via AQE's
existing transformers.js path (Xenova/bge-small-en-v1.5), no Rust/shim. Keep lattice
for a bigger move (Qwen3-1024, SIMD perf, Cognitum-side embedding serving).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds the single AQE-side verifier that reconciles AQE flywheel receipts with
Cognitum qe-harness witness bundles, so QE evidence signed by the shared platform
identity (fingerprint f1ac28607da49ec1) is verifiable on either side.
Investigation (read-only, cognitum-one/qe-harness) established the bridge is
HALF-wired already: both sides use Ed25519, the same QE_WITNESS_SIGNING_KEY (JSON
PEM), and the IDENTICAL fingerprint scheme sha256(pem.trim())[:16] — both sign as
f1ac28607da49ec1. What was NOT aligned: the signed artifacts (AQE = fixed-order
JSON body, hex; qe-harness = stableStringify sha256: digest, base64, nested
witness{}) are not natively cross-verifiable.
- src/learning/qe-flywheel/witness-verify.ts: allowlist-driven verifier for BOTH
formats + stableStringify/canonicalDigest (qe-harness parity), tamper-detecting,
fail-closed allowlist. node:crypto only; reuses receipt.ts for the AQE path.
- 15 tests: fingerprint parity (keyFingerprint === signer.keyId), both formats
round-trip, tamper → bad-signature/digest-mismatch, allowlist enforcement.
Two external dependencies remain (need the qe-harness owner — documented in the
GOAP plan, NOT done unilaterally): provision the f1ac28607da49ec1 PUBLIC key via
QE_WITNESS_PUBLIC_KEYS_JSON; confirm byte-parity vs a real qe-harness sample;
decide canonicalization convergence (AQE's hand-listed body silently drops new
fields — recommend adopting stableStringify).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The hosted qe-court: POST a delivery (diff/patch/files), get a signed,
overturn-tested verdict. Grounded in the M1 live probe — a NEW route on the
existing api.cognitum.one inference service (X-API-Key, x_cognitum receipts),
NOT the ADR-308 funnel (which 404s on that host); /v1/qe/* confirmed free.
Verdict semantics reference the OSS referee (src/skills/qe-court/referee.ts) so
client and server agree: 3-valued verdict, the overturn mechanic (overturnDepth),
writer≠juror + vendor-diversity (422 PANEL_INVARIANT_VIOLATION), DoE-gated score,
Ed25519-signed record (ADR-118), provenance-tiered charges (ADR-121). Sync + async
job models; budget/cap semantics mirror /v1/chat/completions.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
M1 resolved: api.cognitum.one's inference API and the ADR-308 funnel/proxy API
are NOT the same backend. /v1/proxy/*, /v1/credits, /v1/events, /v1/funnel-policy
all 404 ROUTE_NOT_FOUND on the inference host; the funnel layer is a separate
service (confirms ADR-308's addendum). /v1/qe/* namespace is free (404) — build
ADR-124 Phase 2 as a new route on the existing inference Express app. Hard cap
confirmed: hardCapUsd $20, headroom $19.34. Tiers route to a model marketplace
(cognitum-low -> z-ai/glm-5.2).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Six Thinking Hats strategy report and the precondition-ordered GOAP execution
plan for the AQE <-> ruflo <-> Cognitum integration work. Captures: what's new
in ruflo (Cognitum funnel ADR-301..319), AQE's current integration state, the
gap analysis / top-10 opportunities, the QE-Court addendum (= ADR-124 /
/v1/qe/verdict from the user-facing end), and the tiered plan with per-item
approval gates (incl. Codex-as-prosecutor and Codex-as-provider M3.5).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
QE-Court convenes independent, cross-vendor AI reviewers against a delivery
(diff / PR / test-suite), makes them file charges from their own probe sets,
then forces any SHIP verdict to SURVIVE an escalating deeper review before it
stands (loop-until-dry overturn). Verdict is 3-valued — SHIP / REMAND / BLOCK —
with a human as final judge. It is the reference implementation of ADR-124; the
hosted sibling is the planned Cognitum /v1/qe/verdict endpoint.
The skill is an orchestration layer that COMPOSES existing assets — it does not
reimplement critics:
- Prosecutors: qe-devils-advocate, brutal-honesty-review, sherlock-review,
qe-security-scanner, qe-mutation-tester, and `codex exec review` (cross-vendor
GPT lens — the strongest form of writer≠juror).
- Kill round: src/verification/adversarial-verify. Jury: two-gate judge (ADR-119).
- Evidence: provenance tiers (ADR-121), signed receipt (ADR-118).
Configurable per-role model routing (config.json `routing`) across Claude /
Cognitum tiers / OpenRouter / Codex / local, all through the ADR-123 provider
layer (budget caps + receipts). Invariants: >=2 distinct vendors, jury vendor
!= writer, DoE-gated scoring (no un-validated "91/100").
Self-learning (ADR-124 M0.B/C): signed court records feed the flywheel; reproduced
charges become oracle-tier qe_patterns; an overturned SHIP is persisted as a
discriminator training pair for the frozen anchor + two-gate judge.
Ships via `aqe init` (added to V3_DOMAIN_SKILLS; auto-installed, not excluded)
and the assets/ npm mirror. Includes a runnable acceptance eval + a seeded-mutant
fixture (a boundary off-by-one a shallow reviewer rates SHIP; the overturn round
must flip it, and MUST regress to SHIP at overturnDepth=0). trust_tier 1 until the
eval runs green (>=5 oracle cases) → then tier 3.
Skill count: 75 -> 76 user-facing (totalQESkills 81 -> 82). Parity clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Closes the structural gap from issue #557: AQE could only bill the paid
Anthropic API even for Pro/Max subscribers, and its budget caps were never
enforced.
- claude-code provider: run QE via `claude -p` on the user's subscription;
child env strips API-billing keys so it can't revert to API billing
- Enforced cross-process spend caps (--max-budget-usd / AQE_MAX_BUDGET_USD),
persisted to memory.db (llm_spend); enforced on the ProviderManager AND
HybridRouter paths; over-budget aborts with COST_LIMIT_EXCEEDED
- cognitum provider: OpenAI/Anthropic-compatible gateway with per-request
cost receipts, embeddings, and a server-side hard cap
- Billing-mode taxonomy + startup notice + `aqe health` LLM Billing section
- config-store: honor explicit `enabled: false` over env key presence;
AQE_LLM_PROVIDER selector
- Fix: `aqe eval run` no longer scores fabricated mock responses — real
provider by default, hard-error when none configured, `--mock` opt-in
- Consensus verification path prints a billing warning (deferred full port)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Non-destructive `aqe init` for `.claude/settings.json`: merge instead of
overwrite, preserve user-owned config (custom statusLine, explicit
includeCoAuthoredBy, AQE_* env overrides, other tools' hooks such as ruflo /
Claude Flow), deep-merge v3 sections, and back up the pristine original before
writing (mirroring CLAUDE.md.backup).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Completes and supersedes the 2026-07-09 directional DoE (which was 25/27 cells, had
no F-test, and — the reproducibility gap found this session — never persisted its raw
data). Re-run full under the CRIT-2 design (N=5 stochastic replicates of fixed item
A1-inRange, real within-cell error term), qwen local $0 + anthropic/claude-haiku-4.5
+ anthropic/claude-opus-4.8 via OpenRouter. $1.538 total, well under the $11 budget.
Results (real main-effects ANOVA, 135 observations, first real data the aggregator
has ever consumed — previously stub-only):
- scaffold: none 1.000 >> plan-and-solve 0.311 >> reflexion 0.067
F(2,108)=218.9, p=1.0e-38, 71.9% of variance — DOMINANT and strongly NEGATIVE.
Both scaffolds DROP. retort's "more harness lowers reliability", now overwhelming.
- model: qwen3-coder:30b 0.644 > haiku-4.5 0.400 > opus-4.8 0.333
F(2,108)=25.1, p=1.1e-9 — local qwen best & free; opus 5x+ cost = negative value.
(Complete 27/27 reverses the prior unequal-n haiku>opus>qwen ordering, significantly.)
- retrieval: off 0.480 > on 0.433 F(1,108)=1.5, p=0.22 NOT significant, slightly
negative — the ADR-118 flywheel feature-on-trial formally fails as `beads`.
EXPLAINED by the 2026-07-10 coupling finding: A1-inRange is a no-headroom item
the models know cold, so a retrieved exemplar has nothing to add.
- prompt: TDD 0.533 > ATDD 0.467 > neutral 0.378 F(2,108)=5.7, p=4.5e-3.
Changes:
- scripts/doe-run.ts: cloud path rewired from raw Anthropic fetch to OpenRouter
(vendor/model ids, opus-4.8 not opus-4-7, exact per-call cost from usage.cost).
- docs/implementation/doe-run-2026-07-10.jsonl: raw per-cell data persisted IN-REPO
(fixes the gap that lost the 2026-07-09 run's data).
- DOE-HARNESS-SCREEN-DESIGN.md §Results (DEFINITIVE) + ADR-122 status/history updated;
prior directional run retained, marked SUPERSEDED.
Verified: tsc 0 errors; $0 --stub and --smoke pipelines green before the metered run.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Runs the CRIT-1 coupling experiment live on qwen3-coder:30b (Ollama, $0) and
characterizes EXACTLY when the ADR-118 flywheel's retrieval helps generated tests.
Result (N=5/condition, mutation-oracle graded, end-to-end "runs∧kills" response):
- POSITIVE CONTROL (POS-reserved — an arbitrary system-specific rule the model
cannot know a priori, a proxy for project-specific corpus knowledge):
NONE 0.00 / IRRELEVANT 0.00 / RELEVANT 1.00 → gain +1.00 COUPLING VALIDATED.
Without the exemplar qwen can't even write a passing test; with it, a perfect one.
- TEXTBOOK (B4-isLeapYear — the century/400 rule):
NONE 1.00 / RELEVANT 1.00 → NO HEADROOM (the model knows the trap cold).
Conclusion: the coupling mechanism is REAL (the harness demonstrably detects it, so
its nulls are live measurements) but HEADROOM-GATED — retrieval improves tests iff
the corpus supplies knowledge the base model lacks. Generic QE edge cases are
already known to code models (30b AND 7b), which is WHY the ADR-122 DoE rated
retrieval `beads`. This explains the prior honest nulls rather than contradicting them.
Getting here required fixing three measure-the-measurement traps that had produced a
FALSE "no coupling" verdict on the first run:
- baseline floored by 500-token truncation (→ 1400) and empty-input over-reach;
- spec leaked the trap (anchor inputUnderTest spells out the edge) → no headroom →
switched to UNDER-SPECIFIED specs graded against the frozen trap-encoding reference;
- metric conditioned on baseline, hiding retrieval's strongest effect (rescuing a
test that otherwise can't be written) → switched to end-to-end usable-quality.
Also:
- OpenRouter wired as the cloud path (vendor/model ids; anthropic/claude-haiku-4.5
et al. confirmed reachable), replacing the rate-limited Anthropic-direct fetch.
- coupled-anchor.test.ts: adds an honest AQE_LIVE_COUPLING-gated end-to-end test that
fails loudly (never fabricates a pass) rather than asserting the mechanism the
scripted unit test only assumes.
- ADR-118 status → "INFRASTRUCTURE WITH A CHARACTERIZED SIGNAL": the flywheel's
retrieval-tuning pays off iff qe_patterns holds knowledge the base model lacks.
Verified: tsc 0 errors; coupled-anchor 1 passed + 1 skipped.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Addresses the CRITICAL/HIGH/MED findings from the brutal-honesty review of the
learning-integrity cluster. The theme: the machinery was real but several claims
outran the evidence. This makes the claims honest and the evidence falsifiable.
CRIT-1 / HIGH-3 (flywheel gated vapor / toy anchor can't move):
- verification/anchors/qe-anchor-v2.json — 5 oracle-verified DISCRIMINATING items
(13 mutants), each with a trap edge a happy-path test misses, so the anchor CAN
actually move. v1's items were too easy to discriminate a retrieval effect.
- scripts/coupling-experiment.ts — falsifiable NONE/IRRELEVANT/RELEVANT controlled
test (N reps, temp>0, $0 mutation-oracle grading). Live run remains blocked on
model availability; the harness refuses to fabricate a verdict.
CRIT-2 (DoE "stats" were a range proxy):
- scripts/doe-run.ts — N real replicates of a FIXED item at temp=0.6 (was 5
different items x1 at temp=0), per-replicate seed, plus a deterministic $0 --stub.
- scripts/doe-aggregate.mjs — real main-effects factorial ANOVA: within-cell error
term, F-test via dependency-free regularized incomplete beta; beads verdict now
gates on p<0.05, not an eyeballed mean delta.
- tests/unit/scripts/doe-aggregate.test.ts — F-CDF + incomplete-beta vs closed
forms/R, planted-effect recovery (p<0.001), null factor (p>0.5), unbalanced cells.
HIGH-4 / MED-6 (over-claimed gate guarantees):
- ADR-120 gains a "Threat model and limits (honest)" section: gateReExecutes
catches a lying log, not a buggy gate (same-process seal+rule).
- ADR-118 status reframed to "infrastructure awaiting a validated signal."
- tests/unit/validation/rule-consistency.test.ts — property test scoping what the
gate actually guarantees (determinism, stable fingerprints, flipped-verdict).
- DOE-HARNESS-SCREEN-DESIGN.md — unequal-n note.
HIGH-5 / MED-7 (self-fulfilling test / brittle scripts):
- tests/unit/learning/mmr-scaling.test.ts — FALSIFIABLE regression for the real
O(n^4) scoreHeldOut hang the MMR_POOL_SIZE cap fixed (96s->420ms at n=300).
- coupled-anchor.test.ts de-faked: relabeled as a MECHANISM/wiring test, documents
that the scripted generator hardcodes the outcome and the real model was an
honest null — no longer readable as evidence that coupling helps.
- tests/unit/validation/sealed-hash-roundtrip.test.ts — regression for the
canonicalJson undefined-key seal bug.
Verification: tsc 0 errors; 33/33 new remediation tests + 290/290 full
validation+flywheel cluster green. No live model run (Ollama offline + Anthropic
account at usage limit) — coupling live-validation surfaced as the one honest
open item, not faked.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adopts the receipt-gated self-improvement discipline from the 2026-07 cross-repo
analysis of ruflo (flywheel), MetaHarness (gateReExecutes), and retort (two-gate
spec conformance + DoE). All DI'd and unit-tested (178 tests); run end-to-end on
real qe_patterns; every limitation honestly scoped.
- ADR-117 frozen oracle anchor: hash-pinned, constant-denominator eval set that
no promotion may regress; loader throws on drift (verification/anchors/qe-anchor-v1.json).
- ADR-118 receipt-gated QE-policy flywheel: generational loop over qe_patterns,
conjunctive frozen accept(), Ed25519-signed receipts + compounding lineage,
durable persistence (flywheel_receipts), corpus + semantic-retriever coupling.
- ADR-119 two-gate quality verdicts: mechanical gate + frontier judge, three-valued
(pass/fail/inconclusive) with preflight; new `aqe quality-gate` CLI + `qe/quality/gate` MCP tool.
- ADR-120 gateReExecutes: re-execute a versioned frozen rule on sealed inputs;
catches the A8-EXT forged-promote class; retrofit onto pattern-promote + dream-apply.
- ADR-121 provenance tiers: only oracle:test-exec evidence changes fleet behavior;
additive, conservative-backfill migration.
- ADR-122 DoE screen: model x prompt x retrieval x scaffold, run on real data
(25/27 cells, $1.25) — scaffolding (esp. reflexion) and retrieval degrade
reliability (the retort `beads` signature); simplest+cheapest stack wins.
- safe-db: AQE_DISABLE_WAL / AQE_JOURNAL_MODE env-gate (macOS virtiofs bind-mount
WAL corruption mitigation; default behavior unchanged).
Honest nulls documented: the flywheel lift is on a self-supervised proxy with the
anchor held flat; making the coupled anchor move needs harder items + a relevant
corpus (an ADR-117 re-freeze), not a retriever change.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Bumps package.json + package-lock + skills-manifest fleetVersion to
3.11.5. Also fixes .claude-plugin/plugin.json and
assets/skills/skills-manifest.json fleetVersion, which had drifted
stale at 3.11.0 across the last 4 releases (found via full-repo
version-string audit).
- Backup-verified cleanup of .agentic-qe/memory.db: 200/200 degenerate
mincut_snapshots rows, 501/501 degenerate mincut_history rows, 530/530
test-fixture execution_results rows, 705/705 test-fixture executed_steps
rows (all confirmed 100% junk before deleting); corrected 72
dream_insights.applied rows corrupted by the now-fixed counter bug back
to the correct boolean value. Full backup + before/after row counts +
integrity check per data-protection policy.
- Fixed 4 unused-vars lint errors in goap-planner.ts/goap-execute.ts
(2 pre-existing + 1 that surfaced after removing the first + 1 in
goap-execute.ts). Left two genuinely unimplemented stub params
(updateActionStats duration tracking, findSimilarPlan fuzzy matching)
honestly marked rather than scope-expanded.
- Filed proffesor-for-testing/agentic-qe#554 to track everything from the
system-integrity remediation that's deliberately deferred, so it isn't
silently dropped.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Full remediation of docs/analysis/SYSTEM-INTEGRITY-AUDIT-2026-07-04.md's
P0-P2 findings, tracked in docs/plans/SYSTEM-INTEGRITY-REMEDIATION-GOAP-PLAN-2026-07-04.md.
Highlights:
- Dream engine: real pattern creation on insight apply, error/outcome
concept nodes from real ADR-110 data, and a follow-up fix ensuring the
concept refresh actually runs on the real automatic path (not just via
test wrappers); persistTaskOutcome now genuinely promotes pending
insights instead of blindly incrementing an applied counter
- Witness chain: Ed25519 signing wired via persistent key directory,
archival/append-after-archival bug fixed, CI verification gate added
- Mincut: real event-bus wiring (was a no-op stub) and scaffold-vertex
detection fixes
- GOAP: real domain-API dispatch executor replacing the always-mock one
- SONA: EWC++ cold-start deadlock fixed via independent request-count
persistence
- ADR-110 pattern-nulls wired into the real production capture path
- Daemon/snapshot visibility, TTL unit bugs, and 8 ADRs re-statused with
additive verification notes
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
3.11.4 = the local-model-improvements branch (LLM/Ollama plumbing, free-tier
local test-gen, proof-gate ADR-116) + the already-merged dependency-security
system (ADR-115). Merged origin/main in first so the release carries the
grpc-js HIGH fix and moderate-CVE reductions rather than regressing them.
Bumps package.json + package-lock + skills-manifest fleetVersion to 3.11.4.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The proof-gate work cited only upstream RuVector 'ADR-194' — which is not an
AQE in-repo ADR. Adds ADR-116 (the AQE-side integration decision: port the
hash-chain to TS, opt-in/fail-soft/single-store wiring, and why NOT to depend
on the @ruvector npm packages — backed by the verified ruvllm mock-mode/demo
findings) and cross-references it from the four source/test files that cite
ADR-194, so the in-repo decision is discoverable from the code.
Comment/docs only — no behavior change.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
#2: single resolveOllamaBaseUrl() knob (AQE_OLLAMA_URL > OLLAMA_URL >
each call-site default) wired into all local clients — chat provider,
consensus provider, local judge, embeddings, free-tier. Unset = identical
behavior; one var now repoints every client at a remote/host Ollama.
#3: size each Ollama request timeout from num_predict and the model's
observed tok/s (EMA) instead of a fixed 120s, so slow dense/thinking
models (~15 tok/s measured) no longer silently time out mid-generation.
Explicit/configured timeouts still win.
Adds scripts/oracle-model-bench-local.ts (local mutation-oracle bench).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Close the biggest remaining drift gap (ADR-114 follow-up).
- skill-parity now gates plugins/agentic-qe-fleet/skills as a strict body-mirror alongside
assets/skills; reconcileBody + `check-skill-parity --sync` resync drifted mirrors while
preserving each tree's frontmatter (used to fix the plugins qe-quality-assessment drift)
- .kiro/skills is an intentionally divergent 86-skill variant (qe- prefixed, some large
.kiro-only bodies) — gated by PRESENCE via the conservation guard's kiro-skills surface,
not body-equality (which would destroy the divergence)
- both guards (verify:skill-parity blocking, verify:conservation non-blocking) wired into
invariant-check.yml with plugins/.kiro paths; policy doc updated
- tests: reconcileBody/splitFrontmatter covered; 16 validation tests pass
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Consolidate C4 diagram generation onto a single engine and expose it to
users via CLI and MCP, with a deterministic confidence gate and real
Knowledge-Graph-derived relationships.
- Consolidation (C1/C6): C4ModelService is the single render/analyze/store
engine; the bridge delegates and FAILS LOUD on a render error instead of
silently degrading. Duplicate inline generators removed.
- C2: real component relationships from the Knowledge Graph (AST import/call
edges) replace the naming heuristic; project-scoped via a new KG basePath
so repos outside cwd don't trip the path-traversal guard.
- C3: deterministic confidence gate (high/medium/low + reasons) on every
diagram — surfaces the detector's known limits instead of hiding them.
- C4/C5: `aqe code c4` CLI + `qe/code/c4` MCP tool (generate/search),
verified at MCP-CLI parity and through the protocol-server bridge.
- Search: generate persists embeddings (opt-in `enableC4Embeddings`, on for
MCP) so `qe/code/c4 search` returns hits in the standard flow.
- Fixed pre-existing lint in touched files (require->import, unused catches).
Docs: ADR-112 + docs/guides/c4-architecture-diagrams.md. tsc + lint clean;
C4 surface fully green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
ADR-150 graceful-degradation core. AQE's native/optional deps (@ruvector/*,
hnswlib-node, rvlite) must degrade — not crash — when a platform binary or a
Dependabot-pruned lockfile is missing.
- src/shared/optional-module.ts: loadOptionalModule(name, req?) → {available}|
{degraded}. Fixes the #528 anti-pattern in the existing ad-hoc
try{require}catch{} (6+ ruvector wrappers): degrades ONLY on genuine absence
(MODULE_NOT_FOUND) and RE-THROWS real load failures (ABI mismatch / corrupt
.node) instead of masking them. 8 tests incl. the rethrow property.
- .github/workflows/degraded-mode.yml: the absent drill — npm ci --omit=optional
--ignore-scripts, then run the degraded-path tests. Pairs with the regular
install job (proves both paths, #528).
Follow-up (held, CI-verified): migrate the ad-hoc sites + the static import in
sona-wrapper.ts onto loadOptionalModule (changes a production native-load path).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Investigated A8 (pin @metaharness/darwin + retire the type-mirror):
- VERIFIED: AQE's DarwinScoreCard mirror is byte-identical to upstream ScoreCard
from @metaharness/darwin@0.2.1 THROUGH the published 0.7.0 (no drift, 5 minors).
- HELD the dep-swap deliberately: upstream is fast-moving pre-1.0 with napi/wasm
transitive deps; adding it changes every user's install + lockfile and can't be
verified locally (host-shared-node_modules breaks native rebuilds) — negative-EV
vs 74 stable, zero-coupling mirror lines.
- SHIPPED the version-contract half: pinned provenance (0.2.1–0.7.0) + a drift-
guard test (darwin-version-contract.test.ts) that fails CI on any field-set
divergence. 17 darwin tests green; tsc clean.
Swap only after upstream stabilizes (≥1.0) + a CI-verified install impact; needs OK.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The opt-in "verify before you emit" primitive a vertical/harness embeds: route
findings through the blind refuters, drop the refuted, surface every verdict for
witness, report overhead. Built in @ruvector/adversarial-verify (vendor-ready,
zero deps) so MetaHarness can embed it.
- gate.ts: verifyGate(findings, {judge, enabled, dropUncertain}) →
{emitted, blocked, all, latencyMs, judgeCalls}. Disabled ⇒ no-op, ZERO judge
calls (cost-neutral). Default-off-able per cheap-vertical posture.
- gate.test.ts (6): (a) false claim killed (b) true survives (c) no-op cost-
neutral when disabled (d) overhead measured. 31 green across the module; tsc clean.
MetaHarness-side embedding (template var + generated-harness wiring) is spec'd in
plan 05 — cross-repo (agent-harness-generator) + needs the package vendored/
published, both pending explicit OK.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Factor AQE's blind-refuter primitive out of qcsd-development-review.js into a
host-agnostic, ZERO-AQE-dependency module (publishable as @ruvector/* later;
not published per no-publish-without-OK). Closes G2.
- src/verification/adversarial-verify/: types (Finding/FindingVerdict/Judge),
blind refuterPrompt + lenses (ADR-074), pure k-of-n majority-kill synthesis,
adversarialVerify orchestrator (injected Judge — no agent()/Claude dep),
calibrate() (false-kill/false-keep vs ground truth, any Judge).
- 25 tests: synthesis math, blind orchestration, calibration (majority-of-3 ≤
single-refuter error), and PARITY — byte-identical to the workflow's inline
synthesis. The Workflow harness sandboxes .claude/workflows (no imports), so
the workflow inline-mirrors the package; annotated canonical + parity-guarded.
- Verification (plan A2): (a) synthesis tests ✓ (b) calibration mechanism ✓
(c) regression parity ✓ (d) zero AQE import (grep) ✓. strict-tsc clean.
Remaining (optional): empirical real-LLM false-kill on a labeled corpus (inject
a real local/OpenRouter Judge into calibrate()). Unblocks A5.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A12 measured cross-model best-of-N at +6 composite over single-model (diverse
models cover each other's validity failures; the win is captured by first-pass
selection, no judge needed). Wire it as an opt-in capability:
- executor: candidateProviders?: FreeTierProviderConfig[] — when set, round-0
best-of-k at the START free tier draws each candidate from a DIFFERENT provider
(e.g. local qwen + an OpenRouter model) instead of one model's variants;
selection stays the objective verifier (first-pass = validity rescue). Per-
candidate attempt.model telemetry. Off (single-model) unless set.
- coordinator-support: FreeTierCoordinatorConfig.freeTierCandidateProviders
passthrough so coordinators can opt in.
- tests: cross-model rescue (falls through to the valid model, no escalation) +
single-model-unchanged. 87 green across the lane; strict-tsc clean.
No judge wired — A12 showed it does not beat first-valid on the cross-model pool.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Measured n=20 (qwen3:30b local + glm-5.2 OpenRouter, judge deepseek-v3.2):
- Cross-model best 84.8 vs qwen-alone 63.5 / glm-alone 71.2; the two models cover
each other's validity failures (qwen 0-valid on 4 instances, glm on 3, both on 11).
- Selector delivery (14 judged): judge 82.8 vs first-valid 82.2 (Δ0.6, noise) vs
qwen-alone 76.1 → cross-model gives +6 over single-model and barely needs the judge.
- A11 judge's same-model 88.9% did NOT transfer cross-model (33% best-pick).
- Production lever = cross-model GENERATION + cheap selection, NOT a judge.
Fixed a tautological metric: "union lift vs max(single models)" was always 0
(== cross-model best); now reports lift vs EACH model alone + validity rescue.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Code check of FreeTierEscalatingExecutor: each escalated tier's round-0 prompt is
built from req.messages (cold), not the prior tier's failed output (executor.ts:248-251).
The only warm context is within-tier repairMessages — correctly scoped. So the
plan's "executor escalates warm" claim was wrong; ADR-182 cold-start is already
satisfied. A12 reduces to the cross-model best-of-N lever (d3-xmodel.mjs, running).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A11 validated the judge (deepseek-v3.2 = 88.9%) but its aggregate gain was ~0
because a single model's candidates cluster. A12 generates candidates ACROSS
families to widen the spread so the judge can pay off.
- d3-xmodel.mjs: generators = local qwen3:30b-a3b + OpenRouter z-ai/glm-5.2
(cross-family); judge = deepseek-v3.2 (a third family — clean writer≠evaluator).
No Anthropic, per preference. Routes local↔OpenRouter by slug; scores every
candidate by REAL mutation-kill+coverage (ground truth, judge blind).
- Measures: union lift (cross-model best vs best-single-model), per-model win
share, and the judge's regret-vs-first-valid on the wider pool.
- Smoke (1 instance): GLM 82.5 > qwen 75.0; judge picked GLM → Δ +7.5 vs
first-valid (vs A11's clustered ~0.5). Full n=20 run pending.
Model note: Qwable-3.6-27b (local, Qwen3.5 dense) is diverse but too slow
(9.3 tok/s) for the loop — OpenRouter cross-family generator used instead.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Dragan Spiridonov