BigSimmo · BigSimmo · Aug 21, 2026 · Aug 21, 2026 · chatgpt-codex-connector · Aug 21, 2026
@@ -0,0 +1 @@
+| 2026-08-21 | claude/issues-reconcile-post-2206 | 02d1bcaab01f933b8af3eefa3a7f085e95aac661 | docs(issues): reconcile the queued inbox batch into the canonical ledger (#2218) | Backfilled record — PR #2218 merged 2026-08-21 (squash 02d1bcaab01f933b8af3eefa3a7f085e95aac661) with no review record captured at the time. Diff inspected post hoc: 29 immutable inbox requests applied verbatim into docs/outstanding-issues.md plus 2 closures (#VZN8G3 dup of #BSBE9B, #Q5JHBJ archived) verified against the ledger by the PR author; docs-only, classifyPullRequestFiles clinicalRisk:false, no RAG/src/worker/supabase paths touched. Approved by content. | PR-reported: reconciler applied 29/29 requests cleanly; pre-push guard ran check:ledger-write-discipline on pushed commit 42dc0e0f4 with no rejection; Prettier clean on changed markdown; CI static-pr required checks green (merged). Not independently re-run in this session — docs-truth backfill only. |
@@ -0,0 +1 @@
+| 2026-08-21 | claude/shadow-runbook-operator-answers | 1fe3c60c94822f61a60e5b61858114274fb8b340 | docs(worker): answer two of the four B4 operator unknowns from measured evidence (#2228) | Backfilled record — PR #2228 merged 2026-08-21 (squash 1fe3c60c94822f61a60e5b61858114274fb8b340) with no review record captured at the time. Diff inspected post hoc: docs/worker-deploy-runbook.md updated with measured Railway variable-change and memory-headroom evidence (read-only lookups only, no mutation), plus a one-line worker/main.ts startup log-message correction (rollback now states set-then-deploy, no behaviour change) and one queued issues:update inbox request. classifyPullRequestFiles clinicalRisk:false; shadow extraction remains default-off everywhere. Approved by content. | PR-reported: npm run docs:check-links passed (2063 references resolve); Prettier clean on both changed files; CI static-pr required checks green (merged). verify:pr-local full and provider-backed gates explicitly not run per PR body (docs/log-message scope). Not independently re-run in this session — docs-truth backfill only. |
@@ -99,7 +99,7 @@ generation-quality verdict on fallback`), merged 2026-08-13 — structured
 | S6 | B3: Docling lab benchmark | `claude/packet-s6-docling-lab-d6foa6` | #2057 | Merged 2026-08-17 (merge `5a6418636`) | Offline only: `check:docling-lab` 36 fixtures / 10 hostile / 6 canaries + Gate B template valid; `verify:pr-local` heavy plan failed:(none); contract test 20/20; legacy smoke 46 docs, 10/10 hostile contained, canary-clean report. Verdict is a separate owner dispatch of `docling-lab.yml` |
 | S6b | Gate B run: docling-lab dispatch, verdict, decision record | `claude/docling-gate-b-eval-5czgln` | (this PR) | Gate B **PASS** 2026-08-18 (evidence run 32176604314 at `8a92378`); four latent harness defects found+fixed en route (setuptools pin, libGL, torch.compile/no-toolchain, HTML-entity scoring) | All five gates pass at pre-agreed 0 pp margins: parse 36/36 both engines, exactness 162/162 both, table F1 parity at ceiling (agreed 0 pp target; fixtures.v2 hardness follow-up queued), hostile 10/10 contained / 0 crash / 0 canary echo, resources max 12.6 s P95 / 1.40 GiB vs 120 s / 6 GiB caps; record: `docs/rag-improvement/gate-b-decision-record-2026-08-18.{md,json}`, validated `--final` |
 | S7 | B4: Docling worker shadow mode | `claude/docling-worker-shadow-mode-b6fa17` | #2170 | Merged 2026-08-19 (squash `5437c309f`), landed by content; default legacy — shadow is an operator flag (Railway); ledger #9DGA6R closed | Offline only: `WORKER_DOCUMENT_EXTRACTOR_MODE=legacy\ | shadow`(default legacy) +`WORKER_SHADOW_EXTRACTION_COHORT_PERCENT`(1–5, default 2) +`WORKER_DOCLING_PYTHON_BIN`; shadow runs after `commitDocumentIndexGeneration`, aggregate record in `documents.metadata.shadow_extraction` via the existing final metadata merge, no chunk/embedding/index/table-fact/`document_index_quality`writes; bounded 120 s / 40 pages / 1 process; vitest`tests/worker-shadow-extraction.test.ts`19/19 + Python unittest 7/7; caveats: table-heavy leg passed at parity-on-ceiling (fixtures.v2 first), eager-mode latency budgeted by the three bounds; rollback`WORKER_DOCUMENT_EXTRACTOR_MODE=legacy` |
-| Gate E | Blinded before/after read tooling (capture `--extra-cases` + gate-outcome dump fields; `blind-answer-pairs.ts` build/unblind) | `claude/gate-e-blinded-eval-b6076d` | (this PR) | Tooling merged, offline-only; paid v18 (4ea310e48) vs v19 capture and the owner's blinded read still pending (`#E0N0QC`; procedure in §2a) | Offline only: blind-answer-pairs + eval-answer-quality focused suites 36/36 (blinding swap-proof, key round-trip, byte-stable builds); eval:rag:offline + eval:rag:adversarial:offline unchanged; no canary — no runtime behaviour change |
+| Gate E | Blinded before/after read tooling (capture `--extra-cases` + gate-outcome dump fields; `blind-answer-pairs.ts` build/unblind) | `claude/gate-e-blinded-eval-b6076d` | #2208 | Merged 2026-08-21 (squash `588191c06`), offline-only; paid v18 (4ea310e48) vs v19 capture and the owner's blinded read still pending (`#E0N0QC`; procedure in §2a) | Offline only: blind-answer-pairs + eval-answer-quality focused suites 36/36 (blinding swap-proof, key round-trip, byte-stable builds); eval:rag:offline + eval:rag:adversarial:offline unchanged; no canary — no runtime behaviour change |
 | S8+ | B5 Ragas / B6 reranker / B7 DSPy | — | — | Still gated — owner decision | — |
 | #212 T1–T3 | Runtime row contracts (rag.ts, rag-candidate-sources.ts, src/app/api) — sibling stream sharing `src/lib/rag/**` | — | #1946 / #1981 / #2023 | Merged (T3 squash `440a34f71` 2026-08-17) | see the #212 ledger row; RAG surface complete for the cast class |
 | #212 T4 | Runtime row contracts: `worker/main.ts` (11 casts) — sibling stream | `claude/ledger-212-tranche-4-worker-q3y6i4` | #2037 | Merged 2026-08-17 (squash `1726537b7`); #212 closed by reconcile PR #2045 | Governance Preflight complete; audit: 1 inbound cast (claim rows, per-row fail-soft) + 2 read-back param casts contracted, 9 outbound/interop left; closes #212 (inbox `done` queued in the PR) |
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		\| 2026-08-21 \| claude/issues-reconcile-post-2206 \| 02d1bcaab01f933b8af3eefa3a7f085e95aac661 \| docs(issues): reconcile the queued inbox batch into the canonical ledger (#2218) \| Backfilled record — PR #2218 merged 2026-08-21 (squash 02d1bcaab01f933b8af3eefa3a7f085e95aac661) with no review record captured at the time. Diff inspected post hoc: 29 immutable inbox requests applied verbatim into docs/outstanding-issues.md plus 2 closures (#VZN8G3 dup of #BSBE9B, #Q5JHBJ archived) verified against the ledger by the PR author; docs-only, classifyPullRequestFiles clinicalRisk:false, no RAG/src/worker/supabase paths touched. Approved by content. \| PR-reported: reconciler applied 29/29 requests cleanly; pre-push guard ran check:ledger-write-discipline on pushed commit 42dc0e0f4 with no rejection; Prettier clean on changed markdown; CI static-pr required checks green (merged). Not independently re-run in this session — docs-truth backfill only. \|
chatgpt-codex-connectorBotAug 21, 2026 Copy link Copy Markdown Choose a reason for hiding this comment The reason will be displayed to describe this comment to others. Learn more. Record the PR head instead of the squash commit When `ledger:lookup` is run for either feature branch, it resolves the branch's pre-merge PR head and requires both the ref and HEAD to match; these two backfills instead pair the branch refs with merge squash SHAs (`02d1bca…` and `1fe3c60…`). Reproducing the documented lookup therefore returns `NOT REVIEWED` and reports the record only as belonging to a different HEAD, defeating review throttling. Append superseding records using each PR's actual reviewed head SHA rather than its squash commit. AGENTS.md reference: AGENTS.md:L147-L147 Useful? React with 👍 / 👎.
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		\| 2026-08-21 \| claude/shadow-runbook-operator-answers \| 1fe3c60c94822f61a60e5b61858114274fb8b340 \| docs(worker): answer two of the four B4 operator unknowns from measured evidence (#2228) \| Backfilled record — PR #2228 merged 2026-08-21 (squash 1fe3c60c94822f61a60e5b61858114274fb8b340) with no review record captured at the time. Diff inspected post hoc: docs/worker-deploy-runbook.md updated with measured Railway variable-change and memory-headroom evidence (read-only lookups only, no mutation), plus a one-line worker/main.ts startup log-message correction (rollback now states set-then-deploy, no behaviour change) and one queued issues:update inbox request. classifyPullRequestFiles clinicalRisk:false; shadow extraction remains default-off everywhere. Approved by content. \| PR-reported: npm run docs:check-links passed (2063 references resolve); Prettier clean on both changed files; CI static-pr required checks green (merged). verify:pr-local full and provider-backed gates explicitly not run per PR body (docs/log-message scope). Not independently re-run in this session — docs-truth backfill only. \|