docs: CLAUDE.md version record for v1.108.144

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

Author: jgravelle

CLAUDE.md

@@ -1,7 +1,8 @@
 # jcodemunch-mcp — Project Brief
 
 ## Current State
-- **Version:** 1.108.143 — **UNDER_THE_HOOD.md technical manual (docs only).** New root doc, 6 chapters (verdicts/confidence/freshness; ranking internals incl. exact seeding + regret loop; declared/measured provenance contract w/ the candid duck 0.65-declared-vs-0.5-measured story; meter errs-downward design; tool tiers + schema budget; import-scip/import-trace evidence rule) + spine mapping ARCHITECTURE/SPEC/CONFIGURATION/CONTEXT_PROVIDERS/TOKEN_SAVINGS/schemas + forthcoming-chapter list (_meta reference, CLI reference, storage internals, harnesses, hooks/watch). README doc-table link. Purpose: surface the under-the-hood machinery (jjg directive); each chapter doubles as a spokesperson-drafted public piece — ch1+ch3 derivatives DRAFTED (dev.to/X/LinkedIn), awaiting jjg publish.
+- **Version:** 1.108.144 — **Deep-doc currency sweep (docs only).** ARCHITECTURE/SPEC/USER_GUIDE/CONFIGURATION/CONTEXT_PROVIDERS/TOKEN_SAVINGS caught up via targeted additive sections (honesty signals, exact seeding, fusion, find_implementations channels + evidence rule, tiers/schema-budget/annotations, provenance on proof surface; _meta fields as protocol; 6 undocumented config keys incl. allow_paid_summaries; provider table 1→9 rows from docstrings; meter conservatism + receipt). GOTCHA: `tests/test_docs_config_parity.py` parses CONFIGURATION.md's Default column and requires LITERAL equality with config.py defaults — prose defaults fail CI; put nuance in Description. TROUBLESHOOTING/AGENT_HOOKS/HEADLESS deliberately untouched (stale-by-omission only). NO behavior change.
+- **Prior (1.108.143):** **UNDER_THE_HOOD.md technical manual (docs only).** New root doc, 6 chapters (verdicts/confidence/freshness; ranking internals incl. exact seeding + regret loop; declared/measured provenance contract w/ the candid duck 0.65-declared-vs-0.5-measured story; meter errs-downward design; tool tiers + schema budget; import-scip/import-trace evidence rule) + spine mapping ARCHITECTURE/SPEC/CONFIGURATION/CONTEXT_PROVIDERS/TOKEN_SAVINGS/schemas + forthcoming-chapter list (_meta reference, CLI reference, storage internals, harnesses, hooks/watch). README doc-table link. Purpose: surface the under-the-hood machinery (jjg directive); each chapter doubles as a spokesperson-drafted public piece — ch1+ch3 derivatives DRAFTED (dev.to/X/LinkedIn), awaiting jjg publish.
 - **Prior (1.108.142):** **Docs-only: tool descriptions catch up with the contracts.** `find_implementations` description gains the SCIP channel (missing since v1.108.96) and states the scores are declared priors with `_meta.confidence_provenance` carrying basis + measured P/R; `get_ranked_context` description + README document exact-name pinning (v1.108.137) incl. `_meta.query_shape`. Schema-budget guard forced two tightening rounds (4014→4001→<4000 compact core tier) — trim descriptions, never regenerate the baseline. Also committed the previously-untracked Odysseus works-with retrieval-layer benchmark (`benchmarks/harness/run_odysseus_compare.py` + results). NO behavior/INDEX_VERSION change.
 - **Prior (1.108.141):** **Gold corpus v2: TS + Go join the channel-accuracy measurement.** Corpus `authored-scenarios-v2` (31 files): TS = extends-based Notifier subclasses + UI-toast homonym trap (AST), PushGateway.send conformer vs ConveyorBelt/ElevatorBank physical-dispatch traps (duck), @On("invoice_paid") handlers vs @Get/@Task substring traps (decorator; TS decorators only exist on class members — probed empirically before authoring, decorator capture confirmed). Go = duck-ONLY by design (implicit interfaces = no declared inheritance to walk; no decorators; Go method ids are unparented `file.go::Push#method`): RingBuffer/PriorityList Push conformers vs Lawnmower (physical) / Recruiter (advocacy) traps. **Round 2 aggregate: ast P=.818/R=1.0 (tp9 fp2), duck P=.5/R=1.0 (tp6 fp6), decorator P=.556/R=1.0 (tp5 fp4); artifact gains `per_language`.** Duck prior 0.65 now clearly optimistic vs 0.5 measured — the visibility the measured_ref exists for; constants STILL declared pending deliberate replay-gated recalibration. measure.py: sha covers .py/.ts/.go, per-language rollups. Registry/measured_refs updated to v2; tests auto-guard (40 green). NO INDEX_VERSION / tool-count / schema change. **Next corpus growth: larger n per channel (esp. duck), maybe Rust/Java; recalibration release stays gated on corpus maturity.**
 - **Version:** 1.108.140 — **Phase C of the self-attesting contract: first gold corpus + measured channel accuracy.** New `benchmarks/goldset/`: authored Python corpus (14 files: payments protocol + subclasses, duck conformers incl. test-double/adapter, event-bus decorator handlers) with DELIBERATE traps (module-homonym `PaymentProvider` base → AST FP; electrical/legal `charge` → duck FPs; `/user_created_report` route + `cleanup_user_created_exports` task substring-matches → decorator FPs); `gold.json` labels every pair with rationale + expected channel. `measure.py`: snapshot-to-tmp (dodges the git-identity contains-path trap — NEVER index a subtree of the host repo in place), index, run find_implementations per target, join to labels; UNLABELED surfaced pair = harness error (corpus must stay complete). **Measured round 1: ast P=0.833/R=1.0 (tp5 fp1), duck P=0.6/R=1.0 (tp3 fp2), decorator P=0.6/R=1.0 (tp3 fp2)** → `benchmarks/provenance/channel_accuracy.json` (carries corpus_sha256 + scope note). `tests/test_channel_accuracy.py` (7) RE-RUNS the measurement live in CI + hash-pins the corpus + chains registry↔artifact. provenance.py: `measured_ref` per heuristic channel beside the DECLARED operating constant (deliberately NOT recalibrated — small-n would jitter ranking for false precision; declared priors held up: 0.85/0.833, 0.65/0.6, 0.45 more conservative than 0.6); `MEASURED["implementation_channel_accuracy"]`; `channel_provenance()` surfaces measured_ref (schema already permits it — additionalProperties). LSP/SCIP stay declared, no measured_ref (they're the ground-truth side). README provenance section extended. NO INDEX_VERSION / tool-count / schema change. **Corpus growth path: add languages (TS/Go), grow n per channel, then a DELIBERATE recalibration release flips constants to measured values gated by replay. jMRI normative section still LAST.**