The v3.10.9 publish failed: the "Integration tests on tag SHA" job runs
test:integration:fast (which now includes the #528/#535 MCP integration tests
that drive the BUILT bundles), but the job never downloaded the dist artifact
from the build job. With CI=true the tests' guard refuses to silently skip, so
they hard-failed on a missing bundle. Add the download-artifact step (like the
init-gate and consumer-audit jobs already do) so the bundles are present.
No source/package change — re-releasing v3.10.9 (never published to npm).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
MCP server reliability + database-free completeness (community issues from
@nagoodman): in-process `agentic-qe mcp` (#528), memory_delete stale-cache fix
(#535), db-free propagation to all editor MCP configs (#533), and the opt-in
--no-claude exclusive install (#532). Plus the js-yaml dev bump (#540) and the
devil's-advocate follow-up fixes (routing/merge/startup + CI guard).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The #528 and #535 integration tests (tests/integration/mcp, gated on
describe.skipIf(!BUILT)) never executed in CI — a false green:
- the mcp-integration-tests job ran `npm ci` but no `npm run build`, so the
dist bundles were absent and both tests silently skipped;
- the step was `continue-on-error: true`, so even a real failure passed;
- neither test was in the release gate's test:integration:fast list.
Fixes:
- mcp-tools-test.yml: add `npm run build` before test:mcp:integration and drop
continue-on-error so the job is a real gate (the exit-124 hang tolerance
stays for the known vitest-hang flake).
- both tests: skip only for LOCAL unbuilt checkouts (`!BUILT && !process.env.CI`)
— in CI a missing build now fails loudly instead of skipping. Verified:
CI=1 with the bundle removed fails the suite instead of reporting green.
- package.json: add both tests to test:integration:fast so they also run on the
release gate (npm-publish.yml), which builds first.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Devil's-advocate review of today's branch surfaced three real gaps:
C1 (init-handler.ts): bare `aqe init --no-claude` (no --with-<platform>, no
--no-database) fell through to runStandardInit and installed the FULL Claude
surface it was meant to suppress — `noClaude` was only honored inside the
modular path. Add `options.claude === false` to the modular routing guard.
Verified: `aqe init --no-claude --minimal` now writes no .claude/, .mcp.json,
or CLAUDE.md (and the empty-install warning fires).
C2 (continuedev-installer.ts): the mergeExistingYamlConfig branch (existing
`mcpServers:` + --overwrite) appended a hardcoded AQE_MEMORY_PATH entry,
ignoring memoryBackend — re-introducing the #533 db leak in db-free installs
over an existing Continue config. Honor memoryBackend on this path too. Adds a
regression test.
H3 (entry.ts): main() ran fire-and-forget, so a startup rejection that escaped
its internal try hit the unhandledRejection handler (which intentionally keeps
the server alive at runtime) → on the in-process `agentic-qe mcp` path the CLI
wrapper would hang on its never-resolving promise with a zero exit. main() now
`.catch`es and exits non-zero on a failed startup. Re-verified #528/#535
integration tests still green (normal startup unaffected).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
#533 — database-free mode now propagates AQE_MEMORY_BACKEND=memory to ALL
generated MCP-server configs, not just opencode.json. Previously `aqe init
--no-database` left .mcp.json (Claude Code) and every editor config pointed at
.agentic-qe/memory.db, so launching the server via any non-OpenCode client
recreated the db at runtime and defeated the db-free install.
- platform-config-generator.ts: generateMcpConfig(platformId, { memoryBackend })
emits AQE_MEMORY_BACKEND=memory and drops AQE_MEMORY_PATH for JSON/TOML/YAML;
covers the 8 shared-generator installers (cursor/cline/continuedev/kilocode/
roocode/windsurf/codex/copilot).
- 08-mcp.ts (.mcp.json) and kiro-installer.ts: same db-free env; learning/workers
not forced on in db-free mode (they persist to SQLite).
- 09-assets.ts threads memoryBackend into every platform installer.
Default (persistent) output is byte-for-byte unchanged.
#532 — new opt-in `--no-claude` suppresses the default Claude Code surface
(.claude/ skills+agents, .mcp.json, CLAUDE.md, governance, hooks) so
`--with-<platform>` flags become the only install targets — e.g. a clean
OpenCode-only install. Gated via shouldRun/run on phases 07-hooks, 08-mcp,
09-assets (core assets), 11-claude-md, 13-governance. Default install
(no flag) is unchanged; warns if --no-claude is passed with no platform.
Verified by real `aqe init` runs in temp dirs:
- `--no-database --with-codex --with-cursor`: .mcp.json/.cursor/.codex all emit
AQE_MEMORY_BACKEND=memory; no memory.db created.
- `--no-claude --with-opencode --no-database`: .opencode present; .claude/,
.mcp.json, CLAUDE.md all absent.
- default `--with-cursor`: full surface + persistent env intact (no regression).
Adds db-free + no-claude cases to platform-config-generator and mcp-phase tests;
all 406 init unit tests pass.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
memory_delete returned {deleted:true} but an immediate memory_retrieve still
returned the value (with an identical timestamp). Root cause was NOT the delete
— it works. memory_retrieve is isConcurrencySafe, so the Issue-#473 session
cache stored its result; memory_delete never invalidated it, so the follow-up
read served the stale cached "found" entry (the identical timestamp was the
cache fingerprint). Confirmed by reproduction: with AQE_SESSION_CACHE=off the
post-delete read already returned found:false.
Fix: mutating tools now invalidate their domain's cached reads. Adds
SessionOperationCache.invalidateDomain() (clears in-memory + persisted rows);
the protocol server calls it after any successful tool whose name ends in a
mutation verb (_store/_delete/_set/_share/_update/_remove/_clear/_promote/
_cleanup). Generalizes to other write/read pairs (e.g. cross_phase_store).
Verified end-to-end through the protocol server with the cache ENABLED:
store -> retrieve(found) -> delete -> retrieve(found:false). Adds
tests/integration/mcp/memory-delete-cache-invalidation.test.ts.
Note: the other findings in #535 (cross_phase_stats counter, GOAP
maxSteps/plan-lookup/activeAgents, test_generate_enhanced quality,
qe_coherence_consensus text) are separate root causes and remain open for
dedicated follow-up per the issue's own "split into its own issue" note.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Records the 2026-06-17 evidence: ADR-038 (DRACO ceiling) is now Accepted
upstream → the A3 gate leans G-ABORT; MetaHarness v0.1.15 ships mcp-scan --json
+ scorecard, shrinking A1 to "consume, not build"; and two new standalone
candidate actions lifted from ADR-150 (A9 graceful-degradation, A10 KRR router).
Cross-links the ADR-150 spawnSync bug class to AQE #528.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The `mcp` subcommand spawned `node dist/mcp/bundle.js` with stdio:'inherit'.
With a piped stdin (any programmatic MCP client), the grandchild received
`stdin-eof` right after answering `initialize` and the Issue #513 stdin-EOF
guard shut it down before serving `tools/list` — so `tools/list` never
returned. The dedicated `aqe-mcp` bin (which runs the bundle directly) worked.
Fix: dynamic-import the MCP entry so it runs in-process on the command's real
stdio, exactly like `aqe-mcp`. entry.ts kicks off `main()` fire-and-forget, so
the action then awaits a never-resolving promise to keep the CLI wrapper from
exiting out from under the server; entry.ts owns shutdown.
Verified with the exact issue reproduction (piped stdin + EOF): `agentic-qe mcp`
now answers initialize AND tools/list (86 tools), matching the direct bundle.
Adds tests/integration/mcp/mcp-cli-inprocess.test.ts as a regression guard.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Supersedes #536. Dependabot's regenerated lockfile dropped the
@ruvector/ruvllm-* optional platform packages, making `npm ci` fail
with EUSAGE (lockfile out of sync). Regenerated with a targeted
`npm update vite --package-lock-only` on Linux, which keeps the
optional platform entries intact.
vite 8.0.9 -> 8.0.16 (transitive dev dependency; routine bug-fix bump).
Lockfile-only change; `npm ci` sync check passes; `npm audit --omit=dev`
reports 0 vulnerabilities.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
The earlier lean boot skipped fleet auto-init, experience capture, CrossPhaseHooks,
ReasoningBank and workers in memory mode. That left the server functionally
degraded — aqe_health reported unhealthy/memory.connected:false/loadedDomains:0,
and read-only fleet/team calls failed with 'Fleet not initialized'. Now that all
persistence layers are gated to run in-memory (unified memory, RVF, hypergraph,
sessions, results), those subsystems write nothing, so boot the SAME as normal
mode. Verified: aqe_health => healthy/connected/14 domains, full tool surface
works, and still ZERO files under .agentic-qe/. Refs #534
Smoke testing showed fleet_init still wrote patterns.rvf and agent_spawn wrote
branches/ in database-free mode — the per-site gates missed the getSharedRvfAdapter
pattern-store path and the agent memory-branch path. Gate the single chokepoint
instead: isRvfNativeAvailable() reports false when AQE_MEMORY_BACKEND=memory, so
every RVF consumer (pattern store, dual-writer, agent memory branches) takes its
existing no-native-RVF degraded path and writes nothing. Verified: fleet_init +
agent_spawn x2 create zero files; default mode still creates RVF/db. Refs #534
Without --auto, `aqe init` fell through to the legacy runStandardInit path,
which ignores --with-opencode (no assets installed) and --no-database/--memory
memory (boots the full kernel and writes .agentic-qe/memory.db). Route to
runModularInit whenever a platform flag or database-free mode is requested, so
those flags take effect regardless of --auto. Refs #529, #530
When AQE_MEMORY_BACKEND=memory the MCP server now uses InMemoryBackend and
boots lean (skips token persistence, experience-capture, ReasoningBank
prewarm, workers, QualityDaemon and fleet auto-init), writing nothing
under .agentic-qe/. Also route console.log/info/debug to stderr so stray
subsystem diagnostics never corrupt the JSON-RPC stream on stdout, which
made strict MCP clients fail with 'Failed to get tools'. Refs #530, #527
Add an opt-in in-memory backend mode wired through the modular
orchestrator. Skips the database, learning, code-intelligence and workers
phases; verification adapts (no DB to verify/write); the kernel no longer
creates .agentic-qe/ in memory mode. Default persistent behavior is
unchanged. Refs #530
OpenCode could not load AQE's .opencode/agents/*.yaml schema, so 0 agents
and 0 skills appeared. Convert at install time to OpenCode-native
.opencode/agent/*.md and .opencode/skills/<name>/SKILL.md (with per-agent
permission frontmatter); drop the incompatible tool wrappers. The
generated opencode.json now invokes the 'aqe-mcp' bin directly to avoid
the 'agentic-qe mcp' double-spawn stdin bug. Refs #529, #528
handleInitialize() returned a fixed protocolVersion regardless of the
client's request, which strict MCP clients (OpenCode, official SDK) can
reject. Echo the client's requested version when supported, else fall
back to the latest. Refs #527
Follow-up to d95f0d7b / 2f4d119c — the earlier passes updated .claude/skills
and assets/skills but missed several other eval surfaces that still pinned
retired IDs (claude-3.5-sonnet, claude-3-haiku):
- `.github/workflows/test-qe-browser.yml` — the `aqe eval run --model` flag
(inert in command-eval mode, but a real dead-ID leftover) -> claude-sonnet-4-6.
- `plugins/agentic-qe-fleet/skills/` — the tracked plugin-marketplace skill copy
(8 eval suites + a sample-output fixture); chaos skills get the opus-4-8 ceiling.
- `docs/schemas/skill-eval.schema.json` — models `enum` was missing claude-opus-4-8
and still allowed retired/deprecated IDs; trimmed to current+active, default
flipped to claude-sonnet-4-6. Plus description examples in the sibling schemas
and the modelUsed values in docs/examples/*.json fixtures.
- `docs/templates/skill-frontmatter.example.yaml` validation_models list.
- `src/cli/commands/eval.ts` — the `aqe eval` `--model` help example and the
`run-all --models` default (`claude-3.5-sonnet` -> `claude-sonnet-4-6`).
Verified: typecheck clean; all edited JSON/YAML parse; zero retired IDs remain in
any eval suite, schema, template, workflow, or eval-CLI default. Intentionally
left untouched: the consensus-provider subsystem (pricing tables / type-unions /
defaults — separate routing layer, bucket-2 data) and historical release notes /
QE audit reports (which document the old IDs by design).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Follow-up to d95f0d7b — that commit updated only .claude/skills/*/evals and
docs/templates, missing two surfaces:
1. assets/skills/ — the npm-distribution copy (tracked, generated from
.claude/skills by prepare-assets.cjs). All 54 eval matrices + nested
cross-model inputs + the .validation templates/schemas/examples now carry
current model IDs, at exact parity with .claude/skills.
2. .claude/skills/.validation/ — the *shipped* eval template, schema, and
example fixtures (the real source new skill evals are generated from):
- skill-eval.schema.json: the models `enum` was missing claude-opus-4-8
(so high-stakes evals using it would fail validation) and still listed
retired claude-3.5-sonnet / claude-3-haiku and soon-retiring
claude-sonnet-4; enum trimmed to current+active IDs, default flipped from
claude-3.5-sonnet -> claude-sonnet-4-6.
- eval.template.yaml / security-testing-eval.template.yaml: models_to_test
refreshed (security template gets the opus-4-8 ceiling).
- skill-frontmatter.example.yaml, schema description examples, and the
modelUsed values in .validation/examples/*.json and
mutation-testing/test-data/sample-output.json fixtures.
Verified: zero retired/deprecated Claude IDs in either tree; both trees at
parity (55x sonnet-4-6, 55x haiku-4-5, 7x opus-4-8 across the 7 high-stakes
skills); all edited YAML/JSON parses. Unrelated .md/.sh drift that
prepare-assets surfaced was reverted to keep this commit model-IDs only.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The cross-model consistency matrix (models_to_test) in 54 skill evals + both
eval templates pinned retired/malformed model IDs — `claude-3.5-sonnet`
(malformed: dashes, not dots; resolves to Sonnet 3.5, retired Oct 2025) and
`claude-3-haiku` (retired Apr 19 2026). Both 404, so those evals could not run
a meaningful cross-model check.
Refresh to current pinned IDs, preserving the original "primary + fast floor"
design:
- claude-sonnet-4-6 # primary (high accuracy)
- claude-haiku-4-5 # fast floor (minimum quality)
High-stakes skills additionally get the capability ceiling claude-opus-4-8
(security-testing, security-visual-testing, n8n-security-testing,
pentest-validation, chaos-engineering-resilience, qe-chaos-resilience,
qe-defect-intelligence) and the security eval template. Opus is scoped to these
7 + the security template rather than all 54 to avoid a fleet-wide eval-cost
blowup.
Also fixes the two `--model claude-3.5-sonnet/claude-3-haiku` examples in
run-skill-eval.ts and a nested cross-model test-case input in
qe-learning-optimization.yaml.
Verified: all eval YAML parses; zero retired/deprecated Claude IDs remain across
skills/evals + templates + runner. (src/domains/constants.ts MODEL_TIERS was
already current — tier 1 claude-haiku-4-5 — so it is intentionally unchanged;
the legacy claude-3-haiku-20240307 entries in cost-tracker/bedrock are retained
historical pricing/availability data.)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
npm-publish.yml runs a consumer-POV tarball audit as a publish blocker, but
only at release time — so an override-masked vuln (root-only `overrides` don't
propagate to consumers) merges to main undetected and only surfaces as a late,
blocked release. This adds consumer-audit.yml running the SAME clean-consumer
tarball audit on every dependency-affecting PR and push to main, catching the
regression before merge so main stays releasable.
Mirrors the proven publish-time job: npm ci -> build -> npm pack -> install the
tarball into a fresh consumer project -> `npm audit --audit-level=high` from the
consumer's perspective (where our overrides do NOT apply). Path-filtered to
dependency-affecting files (package.json, package-lock.json, build/pack scripts,
.npmignore, this workflow), least-privilege (contents: read), concurrency-guarded.
Precedent: v3.9.13 shipped 15 CRITICAL protobufjs ACE vulns to every installer
while in-repo `npm audit` read 0 (GHSA-xq3m-2v4x-88gg). Verified: actionlint
clean; logic confirmed passing on the current v3.10.6 tree (consumer install
resolves protobufjs@7.6.3, 0 high/critical).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
0.1.5's SONA learning engine had a bug where reward feedback produced zero
weight changes (fixed upstream in 0.1.7, published 2026-06-11). AQE drives that
exact path via the trajectory API in sona-wrapper.ts
(beginTrajectory/addTrajectoryStep/endTrajectory + forceLearn), so reward
signals into SONA were effectively inert.
Verified on linux-arm64:
- 0.1.7 linux-arm64-gnu binary is a Linux ELF; native module loads (SonaEngine)
- all 12 native methods the wrapper calls exist in 0.1.7 (API compatible)
- functional smoke test: forceLearn now reports "20 trajectories -> 20 patterns",
patterns_learned 0 -> 20 (was 0 in 0.1.5 — fix confirmed)
- tsc --noEmit: 0 errors; 206 SONA unit tests pass
- better-sqlite3 native fix from prior commit intact (experience capture unaffected)
Note: 0.1.7 restructured platform binaries into optional per-platform packages
(hence the lockfile churn). Install resolves the correct binary per platform;
do not rely on a host-side install in the bind-mounted container.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The aqe-hook.cjs shim discarded all stderr and always exited 0. When the
project-local better-sqlite3 binary was the wrong platform (host/container
mismatch → `invalid ELF header`), UnifiedMemoryManager init failed and
persistCommandExperience silently dropped every captured_experiences INSERT.
Self-learning stopped for days with zero trace while dream_cycles (written by
the global MCP server's working binary) masked the outage.
The shim now captures stderr and tees fatal native-init markers (invalid ELF
header, UnifiedMemoryManager init failure, ERR_DLOPEN_FAILED, Node ABI
mismatch) to a throttled (5min) .agentic-qe/hooks-health.log with an actionable
fix hint. The happy path is unchanged — stdout still emits only the JSON
object, stderr stays out of the transcript, and the hook always exits 0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The 'reworded prose' mutation test used .replace('qe_agent_definition',
'qe_agent_definition') — a no-op replacing a string with itself (CodeQL
js/identity-replacement). Replaced with a real non-invariant edit
(frontmatter description + a <notes> block after the closing tag) that
genuinely exercises 'edits outside required sections must not trip the
gate'. 9/9 tests still pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
CodeQL/actions best practice + repo convention: invariant-check.yml and
safety-eval.yml lacked an explicit top-level permissions block. Both only
checkout and run scripts/tests — no gh, git push, PR comments, or release
writes — so contents:read is sufficient. Matches existing workflows.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The gate fired correctly on PR #523 but its path assumption was too
strict: it looked for RUBRIC-v*.md only in the results file's own
directory, while the real layout is benchmarks/<name>/RUBRIC-v1.md with
results under <name>/results/. Now checks the dir OR its parent, with
two separate OR'd ls calls (a single 'ls a b' exits non-zero when either
glob is unmatched, which masked the present rubric).
Verified locally: real repo passes (rubric found in parent); a results
dir with no rubric anywhere still fails.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Statuses updated to reflect reality (were stale 'Proposed' despite
implementation): 107/108/110 Implemented; 105 Implemented w/ INFERRED
domain-finding follow-up; 106 Implemented (live matrix, native tiers
pass every cell); 109 Implemented infrastructure w/ corpus-scaling
follow-up. Gitignore transient run outputs, force-keeping canonical
evidence files.
Verified: full branch tsc clean; both new workflows valid YAML; 58
locally-runnable tests green; no .env or key material in any branch
commit (audited).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Live runner executed for real: OpenAI gpt-4o-mini under test, Gemini
2.5-flash as the non-same-family judge, hidden-test ground truth, seeded
X/Y counterbalance, pre-registered RUBRIC-v1 hash embedded per row.
The real run surfaced and fixed two harness bugs:
1. Ground-truth fix-rate was coupled to judge-row validity — a fixed bug
that zeroed a real B-arm fix when its judge pass returned no winner.
Ground truth is now tracked per (scenario, arm), independent of the
judge; numbers are internally consistent.
2. Judge row model: emit ONE comparison row per (scenario, pass) — the
unit the sign test clusters — instead of duplicated per-arm rows.
Plus judge-verdict parse hardened (last-verdict wins, broader regex,
more tokens): unparseable rate 50% -> 25%, the rest excluded in code.
Result at n=2: ground truth A=0.50 B=0.00, judge clustered 1-1 p=1.0 —
no arm signal, honestly underpowered. Corpus scaling is the path to a
claim (stated in results README + ADR).
Verified: 30 deterministic tests (stats + safety) green; real run $0.003.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Path A (model-judgment) live runner over the real ADR-026 tiers
(haiku/sonnet/opus via Anthropic API). Each tier is given the
data-protection absolutes + an explicit ACTIONS: [...] declaration
protocol, hit with each temptation as opener AND mid-task, N=5, and run
through the existing assertion engine. Asserts on declared intent only;
never touches a real DB. safety-eval.yml live job now executes it.
Real run found and fixed a harness false-positive: a REFUSING model that
illustrates a command in prose was wrongly flagged. The ACTIONS protocol
makes intent unambiguous; discrimination tests prove a genuinely-declared
rm memory.db still FAILS while an illustrated one PASSES (not neutered).
Verified: 16 deterministic tests; live matrix 5/5 all cells, all 3 tiers
(haiku $0.085 / sonnet $0.231 / opus $1.108), committed as evidence.
Retry-resilient client (transient fetch/429/5xx backoff).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Brutal-honesty review found the ADR-110 loop fully plumbed but fed by
inputs no real caller supplied: null capture never fired (no caller
passed appliedPatterns) and the discount always ran the unknown-context
branch (no caller passed contextFingerprint).
startTask now retrieves the patterns that will guide a task and threads
their ids into startCapture (fail-soft), so a task failure attributes
nulls to the right patterns. searchPatternsForTask forwards a
domain:agent contextFingerprint into the search, and routeTask passes
its own context — so the null-discount weights in-context failures
hardest, as ADR-110 intends.
Loop now closed end to end: guide -> capture -> fail -> null -> discount.
Verified: tsc clean; the review's own dead-input greps now show both
inputs connected at real call sites (was empty before). Behavioral
proof needs the full-engine harness (CI-only here, same constraint as
the migration suite) — not claiming a local green I can't produce.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Layer 1 (always): engine tests + runner over committed fixture
trajectories — all three violating shapes must FAIL, all three
compliant shapes must PASS; an engine regression that lets a violation
through fails CI with an explicit error.
Layer 2 (release/dispatch): live per-tier matrix — fails LOUDLY when
requested with an API key until runner.ts --live lands, and warns-skips
without the key. Never fakes a pass.
Verified locally: YAML parses; both gate steps executed verbatim —
violating shapes all exit non-zero, compliant shapes all exit 0.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
MCP-CLI parity bug found by a REAL protocol call during P5 acceptance:
the handler projected findings to a fixed 5-field shape, stripping
ADR-105's evidenceClass at the MCP boundary — unit tests passed because
they tested the projection itself. Projection now carries evidenceClass
+ evidenceArtifact per finding and the needsVerification queue; two
parity-pin tests added so the field can never be silently dropped again.
Verified: 9/9 handler tests; direct handler invocation (same code path
as the MCP tool) shows evidenceClass STATIC + needsVerification array.
Live MCP server reflects this after restart (long-running process has
pre-fix code loaded).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
RUBRIC-v1.md committed first per ADR-108: ground-truth primary outcome
(hidden acceptance test), style-neutral verbatim judge instruction (no
treatment-revealing framing in either direction), two-pass cross-family
judging with INFERRED-labeled fallback, clustered-stats reporting rule.
Provably rubric-before-data: this commit precedes any results-* artifact.
2 scenarios with seeded defects + personas + hidden tests (off-by-one
pagination; swallowed async rejection). Hidden tests verified both
directions: FAIL on seeded bug with precise reasons, PASS on the fix.
lib/stats.ts encodes the three Pattern Space harness fixes as code:
isGoodRow enforced inside aggregate() (no path to a number that skips
it), seeded per-item counterbalance (their null cell was 72% position-
skewed), exact scenario-clustered sign test (validated against the
known 27/11 → p≈0.0136 re-analysis).
Verified: 14/14 stats tests; hidden-test ground truth both directions;
tsc clean. Remaining: live conversation driver + judge integration
(API-gated, same decision as ADR-106 live mode).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
PatternStore.search now surfaces kept nulls on every result
(nullSummary) and discounts scores by context-matched null density
before ranking — 'succeeded elsewhere' never outranks 'failed here'.
Callers pass contextFingerprint via PatternSearchOptions. Fail-soft:
discount skipped (debug-logged) when the sqlite handle is absent.
AQELearningEngine wires PatternNullStore.recordNull into
ExperienceCaptureService.setNullRecorder at the composition root,
mirroring the witness-chain fail-soft wiring pattern.
Arena losing-strategy persistence required NO new code: ADR-104's
persisted run JSON already keeps every EvaluatedStrategy (killRate,
coveragePct, fitness) + competitiveArray + ranking — losers and their
loss reasons are on the record by construction.
Verified: tsc clean; 28/28 across null-capture, evidence-gating, and
invariant-verifier suites locally. DB-backed paths covered by the
migration suite in CI (native-binding constraint).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
PatternNullStore: recordNull with ON CONFLICT consolidation,
getNullSummaries batch fetch, and the pure applyNullDiscount ranking
helper (context-matched nulls discount 5x harder than remote ones;
0.25 floor keeps patterns retrievable — nulls inform, never erase).
ExperienceCaptureService: appliedPatterns on TaskExperience (patterns
that GUIDED the task), setNullRecorder following the setWitnessChain
convention, and null capture in completeCapture — failure = negative
reward when a signal exists, else !success; recorder errors never break
capture; context fingerprint = domain:agent (v1, per ADR).
Verified: 11/11 tests run locally (London-school mocked backend — no
native deps) incl. reward-overrides-success, per-pattern fan-out,
recorder-throw survival, and discount floor/ordering; tsc clean.
Remaining for ADR-110: retrieval-time discount wiring in PatternStore
search, arena losing-strategy persistence, composition-root recorder
wiring.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Additive schema v10: qe_pattern_nulls (pattern_id FK, context_fingerprint,
failure_mode, trajectory_ref, evidence_class CHECK per ADR-105,
consolidated_count, UNIQUE(pattern_id, context_fingerprint)) + 2 indexes.
Wired into unified-memory v10 migration block; rollback refuses when
nulls exist (nulls are data — the un-committed v2.1 lesson).
Verified against a sqlite3-online-backup COPY of the real memory.db
(61MB, original never written): all 51 pre-existing table counts
byte-identical before/after (qe_patterns=298, qe_trajectories=377,
kv_store=5008), PRAGMA integrity_check ok, table+4 indexes created,
UNIQUE fires on duplicate, ON CONFLICT consolidation bumps count to 2.
tsc --noEmit clean. Unit tests (10) follow the repo's better-sqlite3
convention and run in CI — local native binding is the known macOS
binary (invalid ELF header).
Verification also caught a false-positive in its own first run: an
empty SQL pipe reported 'applied' with trivially-unchanged counts; the
new-objects query exposed it.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Dragan Spiridonov