- Update status: 14 PRs merged (#1-12)
- Add PRs 9-12 to task table (Tasks 012-015)
- Document new features:
  - Request Logging Middleware (PR #9)
  - Configurable Scoring Hyperparameters (PR #10)
  - Memory Stats Endpoint (PR #11)
  - Memory Archive/Delete Endpoints (PR #12)
- Add new environment variables (SCORING_*, LOG_*)
- Update Key Files Reference with new files
- Mark Tasks 016, 017 as in-progress

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Gap Interview System (Task #8):
- Add GapInterviewer for generating interview prompts from capability gaps
- Create type-specific prompts for data_source, reasoning, query_pattern gaps
- Add RunWeeklyInterview() APE job with configurable scheduling
- Add API endpoints: GET/POST /v1/system/gap-interviews
- Add prompt answer/skip tracking with Neo4j persistence
- Add V0010 migration for InterviewPrompt schema
- Wire StartWeeklyGapInterviews() background job into server

CMS Integration Tests (Task #9):
- Add integration_test.go with Neo4j test fixtures
- Test visibility filtering (private/team/global)
- Test Context Cooler graduation and decay
- Test Jiminy rationale generation
- Test REFERS_TO cross-module linking
- Test surprise detection for corrections
- Test end-to-end conversation flow

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Close three feedback loop gaps in the Jiminy guidance system to create
a self-improving guidance pipeline where chronically ignored guidance
decays automatically and consistently followed guidance strengthens.

Gap 1 — Dispatcher gap (3 new executors):
- review_guidance_effectiveness: diagnostic executor that queries
  per-constraint effectiveness and categorizes items as high/low/insufficient
- adjust_guidance_confidence: mutating executor that boosts items with
  effectiveness >= 0.7, decays items < 0.1 (min 5 surfaces), archives stale
- archive_ineffective_constraints: delegates to ArchiveStaleConstraints

Gap 2 — Confidence scope gap:
- ConfidenceUpdater now fires for ALL guidance types (constraints,
  corrections, patterns, decisions), not just GuidanceConstraint
- Archive guard added: only constraint nodes get archived when confidence
  drops below threshold — corrections/learnings/patterns retain status

Gap 3 — SignalLearner isolation:
- Jiminy Guide() now records Hebbian emissions for each surfaced item
- RecordOutcome() records responses for followed/partial-compliance outcomes
- SignalLearnerProvider interface avoids circular import between jiminy/ape

New reflection pattern #15 (guidance_confidence_drift):
- Triggers adjust_guidance_confidence when GuidanceHealth is between 0 and 0.7
- Complements pattern #9 (diagnostic at 0.5) with corrective action at 0.7

Architecture:
- GuidanceCalibrationProvider interface in ape/types_rsic.go
- rsicGuidanceCalibrationAdapter in api/rsic_adapters.go bridges ape→jiminy
- 5 new RSIC_GUIDANCE_* config variables with sensible defaults
- Wired in server.go: SetGuidanceCalibrator + SetSignalLearner

Tests: 10 new tests across 4 test files
Docs: feature doc, UATS spec, cli-reference, .env.example, AGENT_HANDOFF

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

…lag-off) + Phase 13 Epic 6 V0017 audit-writer fix + Phase 11+ feature-doc backfill (narrow close)

Narrow close per operator approval after Epic 0+1+2 produced design questions
that warrant dedicated follow-up sprints. Note 05 deferred to Phase 14.2;
Note 06 default flip deferred to Phase 14.1.

What landed
-----------

* Phase 13 Epic 6 V0017 audit-writer fix (in-flight discovery)
  - tsdb/retrieval_audit_writer.go (new, ~165 LOC; buffered + 30s flush via CopyFrom)
  - retrievalAuditAdapter in api/server.go (cycle-safe translation)
  - V0017 was empty since Phase 13 because SetRetrievalAuditWriter had no
    callers; now writes per retrieve when RETRIEVAL_AUDIT_ENABLED=true.
  - Live verification: 279 audit rows accumulated in 4h since fix landed.

* Note 06 sparse activation gate (flag-off)
  - retrieval/gate.go (~190 LOC) + 9 Tier 1 unit tests, all green
  - Wired post-aggregation, pre-rerank in service.go
  - 4 config knobs (SPARSE_*); default off, percentile 0.95, min 3, max 20
  - Per-request override via ?sparse=true|false and ?sparse_percentile=N
  - debug.sparse_gate_* + debug.below_threshold_* (when JiminyEnabled)
  - 3 Prometheus histograms

* TSDB V0019 sparse_gate_metrics
  - migrations/019_sparse_gate_metrics.sql (hypertable, 7-day chunks)
  - tsdb/sparse_gate_writer.go (~165 LOC)
  - sparseGateRecorderAdapter in api/server.go (always wired so per-request
    overrides record even when default off)
  - TSDB_REQUIRED_SCHEMA_VERSION 18 -> 19

* Epic 0 forensic doc — phase_14_score_distribution_analysis.md
  - Defaults derived from llm_interactions.retrieval_scores (99k+50k score
    points across consulting.classify + retrieval.rerank_cross)
  - Heavy-tail confirmed (p98/p50 ~ 4-5x); within-call clamp dominates
    percentile choice in dominant K=20-50 regime
  - Note 05 catalog redesign needed for whk-wms (0 distinct symbols, 0
    distinct roles) — flagged for Phase 14.2

* A/B verdicts captured
  - 16q quick at MIN=3 / p95,p98,p99: all FAIL (q69 boundary)
  - 16q quick at MIN=10 / p95: PASS (mean +0.019, 0 regressions, 3 improvements)
  - 120q full at MIN=10 / p95: FAIL per-question (mean parity 0.413=0.413,
    7 boundary regressions across 4 categories, 3 of 7 in
    architecture_structure)
  - Per sprint plan §10 risk #1: ship flag-off; Phase 14.1 will retune.

* Phase 11+ feature-doc backfill (operator request 2026-05-04)
  - new: docs/features/{mlx-watchdog,uvts-validation,column-voting-retrieval,
         local-llm-runtime,sparse-retrieval}.md
  - extended: docs/features/service-resilience.md (Phase 11.6.x additions)
  - Standing rule saved as memory feedback_per_feature_docs_required.md

* Follow-up sprint stubs scoped
  - sprint_plan_phase_14_1_adaptive_per_category_gate.md (~3 days, ~$15)
  - sprint_plan_phase_14_2_note_05_sparse_fingerprints.md (~7 days, ~$25)

Decision-fork outcomes
----------------------

| Fork | Provisional | Outcome |
|---|---|---|
| #2 percentile default | 0.98 | 0.95 (Epic 0 data) |
| #5 catalog bit policy | static 64/64/64/64 | adaptive (deferred Phase 14.2) |
| #8 gate ordering | pre-rerank | pre-rerank (confirmed) |
| #9 default flip | per-Note conditional | flag-off (Phase 14.1 will flip) |

OpenAI spend (actual): ~$13. Well under sprint $25-50 budget.

Tests + lint
------------

* go test -race ./internal/{retrieval,config,metrics,tsdb}: all green
* golangci-lint run on affected packages: 0 issues
* Live smoke: /healthz green, retrieve returns 20 (gate off), 279 V0017
  audit rows in 4h (Phase 13 Epic 6 fix verified in production)

Memory observations
-------------------

* rw0mzergwcqct8abpw0dli9x — Phase 14 Epic 8 doc-backfill scope
* sc4iwy3of9ndn5kowja1i14i — Epic 0 forensic + audit-writer gap
* omr2rs5jppqrvee2k0l1xtd1 — Epic 1 gate code complete
* re4k7rpd3hjt5a52l8qwx8fp — Epic 2 verdict + Phase 14.1 scope

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>