Dragan Spiridonov 8663df13b7 feat(learning): PatternNullStore + null capture on failed pattern-guided tasks per ADR-110 (issue #522) ...

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>

2026-06-11 10:56:35 +00:00

..

dream

feat(learning,bridge): dream_insights retention + bridge cursor guard (#488 Phase 3)

2026-05-15 14:39:41 +00:00

_aqe-engine-test-helpers.ts

test(learning): split aqe-learning-engine.test.ts into three forks (issue #448 step 2)

2026-05-19 12:02:12 +00:00

agent-routing-domain-dedilution.test.ts

fix(test)+docs: address qe-devils-advocate audit of #510 loop

2026-06-02 10:54:19 +00:00

agent-routing-exploration.test.ts

fix(routing): collapse Q-state to 3-dim (drop complexityBucket) (#499)

2026-05-19 13:53:53 +00:00

agent-routing-language.test.ts

…

agent-routing-state-encoding.test.ts

test(routing): regression guard for ruflo router bugs #2229/#2239 (audit, #510 item 3)

2026-06-02 08:18:26 +00:00

aqe-learning-engine-factory.test.ts

test(learning): split aqe-learning-engine.test.ts into three forks (issue #448 step 2)

2026-05-19 12:02:12 +00:00

aqe-learning-engine-patterns.test.ts

test(learning): split aqe-learning-engine.test.ts into three forks (issue #448 step 2)

2026-05-19 12:02:12 +00:00

aqe-learning-engine-regression.test.ts

…

aqe-learning-engine.test.ts

test(learning): split aqe-learning-engine.test.ts into three forks (issue #448 step 2)

2026-05-19 12:02:12 +00:00

asymmetric-learning.test.ts

…

causal-verifier.test.ts

…

daily-log.test.ts

…

dream-scheduler.test.ts

fix(dream): kernel DreamScheduler reconciles dream-scheduler:hook-state per cycle (#509)

2026-06-02 11:34:40 +00:00

embedder-endpoint-client.test.ts

fix(embeddings): harden ADR-097 endpoint client against devil's-advocate audit

2026-05-20 07:52:23 +00:00

experience-capture-middleware.test.ts

…

experience-capture-regression.test.ts

…

experience-capture.test.ts

…

experience-consolidation-contradiction.test.ts

feat(learning): contradiction detection in consolidation (#510 item 7)

2026-06-02 09:22:51 +00:00

experience-consolidation-safety-valve.test.ts

fix(learning): non-destructive safety valve + CLI table bootstrap

2026-05-09 13:04:58 +00:00

init-abort-signal.test.ts

chore(release): bump version to v3.9.27

2026-05-14 09:10:11 +00:00

loop-health.test.ts

feat(observability): daemon pidfile fix + learning loop-health (#488 Phase 1)

2026-05-15 13:11:32 +00:00

memory-auditor.test.ts

…

meta-learning-cycle.test.ts

…

metrics-tracker.test.ts

…

opd-remediation.test.ts

…

pattern-lifecycle-ewc.test.ts

fix(learning): surface consecutive_failures so the 'failures' deprecation branch fires (#510 side-finding)

2026-06-02 11:04:57 +00:00

pattern-null-capture.test.ts

feat(learning): PatternNullStore + null capture on failed pattern-guided tasks per ADR-110 (issue #522)

2026-06-11 10:56:35 +00:00

pattern-store-regression.test.ts

…

pattern-store.test.ts

…

pattern-usage-recorder.test.ts

refactor(learning): single writer for pattern usage — qe_pattern_usage + qe_patterns columns (#486 Gap B)

2026-05-15 12:41:37 +00:00

qe-guidance.test.ts

…

qe-hooks.test.ts

test(qe-hooks): update QEAgentCompletion outcome test for #447 behavior

2026-05-11 15:07:43 +00:00

qe-reasoning-bank-feedback-loop.test.ts

test(learning): release module singletons between tests (issue #448 step 3)

2026-05-19 10:07:41 +00:00

qe-reasoning-bank-init-reentrancy.test.ts

fix(learning): stop QEReasoningBank.initialize() recursing → MCP domain tools hung on fresh install

2026-06-03 12:04:37 +00:00

qe-reasoning-bank-rvf-backfill.test.ts

chore(release): bump version to v3.9.34

2026-05-18 17:42:55 +00:00

qe-reasoning-bank-utilities.test.ts

test(learning): split qe-reasoning-bank.test.ts into three forks (issue #448 step 2)

2026-05-19 09:45:16 +00:00

qe-reasoning-bank.test.ts

test(learning): release module singletons between tests (issue #448 step 3)

2026-05-19 10:07:41 +00:00

real-embeddings-endpoint.test.ts

feat(embeddings): optional external embedder endpoint (ADR-097, #503)

2026-05-19 20:03:14 +00:00

real-qe-reasoning-bank.benchmark.test.ts

…

regret-tracker.test.ts

…

routing-mincut-safety-gate.test.ts

fix(routing,kernel,cli): audit follow-ups — CRITICAL #1 + HIGH #1/#2 + smoke

2026-05-15 16:25:47 +00:00

rvf-pattern-store-orphan-purge.test.ts

fix(learning): purge orphan RVF vectors on init (#462)

2026-05-13 11:29:19 +00:00

rvf-pattern-store.test.ts

fix(rvf): resolve project root via static import, not require() (#516 follow-up)

2026-06-08 16:10:16 +00:00

skill-validation-learner.test.ts

fix(adr-093): post-audit sweep — CI workflow, consensus provider, MCP sampling, 12 skill evals, 9 test files

2026-04-17 14:26:23 +00:00

sqlite-aggregate-stats.test.ts

fix(learning): getStats falls back to DB aggregation when counters are zero (#454)

2026-05-13 10:02:10 +00:00

sqlite-persistence-recent-embeddings.test.ts

chore(release): bump version to v3.9.34

2026-05-18 17:42:55 +00:00

token-tracker.test.ts

…