Colby McHenryandClaude Opus 5 76ab1fe130 docs(benchmarks): record the CG-24 epic resolution ...

Four shipped fixes, one open defect (CG-36), and five issues closed because
measurement contradicted them. The headline is that the reported symptom was
not an explore bug at all — it was a degraded index (CG-33), and the reported
query answers correctly on a clean rebuild with no explore change.

Records the two traps that cost real time and are now guarded in tooling: the
nonexistent .codegraph/graph.db path that sqlite3 silently creates, and
ab-new-vs-baseline.sh swapping src/ mid-run so a commit captures baseline
sources.

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

2026-08-06 14:46:11 -05:00

..

agent-eval-feedback-metrics.md

docs: the occupancy baseline says our residual is higher — write that down (CG-13)

2026-08-05 13:06:51 -05:00

answer-directly-vs-explore-agent.md

docs(benchmarks): re-derive the token figures the result.usage bug touched

2026-08-05 21:36:10 -05:00

call-sequence-analysis.md

docs(benchmarks): re-derive the token figures the result.usage bug touched

2026-08-05 21:36:10 -05:00

codegraph-ab-matrix.md

Add landing page + Starlight docs site (#375)

2026-05-24 13:21:25 -05:00

explore-allocation-ab-1500.md

docs: allocation efficiency — the metric, its guards, and the 103-run baseline (CG-9)

2026-08-05 00:44:30 -05:00

explore-allocation-efficiency.md

docs: one entry point for the three feedback metrics, and how to run them (CG-11)

2026-08-05 00:59:58 -05:00

explore-declaration-only-cg28.md

fix(explore): damp ambient declaration files on flow queries (CG-28)

2026-08-06 14:35:56 -05:00

explore-dedup-ab-cg20.md

docs: CG-20 — the dedup gate, three bars pass and the fourth cannot (CG-2)

2026-08-05 14:11:33 -05:00

explore-displacement-guard-ab-cg31.md

docs(benchmarks): record the CG-31 A/B — no regression, four repos stop truncating

2026-08-06 03:12:30 -05:00

explore-factory-closure-cg27.md

measure(explore): the factory-closure envelope premise does not hold (CG-27)

2026-08-06 14:07:22 -05:00

explore-noise-epic-cg24.md

docs(benchmarks): record the CG-24 epic resolution

2026-08-06 14:46:11 -05:00

explore-oversize-member-ab-cg30.md

docs(benchmarks): record the CG-30 A/B — deterministic win, no behavioural regression

2026-08-06 02:26:22 -05:00

explore-reservation-invariant-ab-cg26.md

docs(benchmarks): record the CG-26 A/B — the invariant holds on every path

2026-08-06 03:58:18 -05:00

explore-sufficiency.md

docs: one entry point for the three feedback metrics, and how to run them (CG-11)

2026-08-05 00:59:58 -05:00

residual-context-occupancy.md

docs(benchmarks): re-derive the token figures the result.usage bug touched

2026-08-05 21:36:10 -05:00