chore(knowledge): retire sonnet-5 guide doc-queue entry after slice completion - #1761
Conversation
…ompletion Removes the prompting-claude-sonnet-5 entry (and its now-empty "Per-model guides:" heading) from the docpage-digest Anthropic profile's doc queue - the slice completed end-to-end (raw-md fetch through interview handoff, dual verification with three correction rounds ending REVERIFY3: PASS from both verifiers). Adds two applicability-filter clarifications from that verification (row-local evidence; unverified-inference is an additional marker, never a substitute tag) and bumps the knowledge plugin 0.10.3 -> 0.10.4 with a matching CHANGELOG entry. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
Claude finished @kyle-sexton's task in 1m 34s —— View job Review
Verdict: APPROVE — no blocking issues. Clean documentation/configuration PR with precise, well-scoped changes.
|
|
Claude finished @kyle-sexton's task in 46s —— View job Security Review — PR #1761
No security issues found. This PR is a documentation-only change touching three files:
No GitHub Actions workflows were modified. Supply-chain, trigger-pattern, and permission-widening risks (zizmor's lane) are out of scope for this diff. |
…ompletion (#1765) ## Summary - Removes the code.claude.com best-practices entry from the `docpage-digest` Anthropic profile's doc queue — its slice completed end-to-end (fetch through interview handoff) per the queue's remove-on-completion rule. It was the sole "Applies across all of the above" entry, so the emptied category heading goes with it. - Channel: raw-md (`.md` appended to the page URL; HTTP 200, 610 lines / 39,668 bytes — channel re-verified for this page, no degradation); provenance recorded in the slice checklist. - Slice verification: Verifier A (same-vendor, fresh context) CORRECTION-NEEDED (1+3); Verifier B (cross-vendor Codex CLI 0.146.0 via the issue #1740 elevated recipe, no degraded fallback) CORRECTION-NEEDED (8+1). One correction round (session-default agents — cross-model harness doc, no model pin per the profile's model-matching table); re-verified REVERIFY: PASS by both verifiers, 12/12 findings resolved, zero new findings. Records under `.work/code-claude-com-docs-en-best-pr-9686dc16/verification/`. - Profile applicability-filter clarification codified from that verification: a digested page that is itself a live code.claude.com harness doc serves as its own row-local basis for intrinsic harness-guidance claims; the boundary rule still routes API-surface-naming claims to `mixed`, with third-party APIs (e.g. the GitHub API) counting as API surfaces. - Knowledge plugin `0.10.4` → `0.10.5` with matching CHANGELOG entry. ## Verification - `markdownlint-cli2` on changed markdown: 0 errors - `check-skill.sh docpage-digest` (`CHECK_SKILL_SKILLS_ROOT=plugins/knowledge/skills`, base `origin/main`): PASS (1 pre-existing soft warning, SKILL.md length) - `check-changelog-parity.sh --check-bump origin/main`: PASS - Independent fresh-context reviewer on the diff: APPROVE (traced the changelog claims to the slice checklist and verification records; its one info-level attribution observation was applied before commit) - Base freshness: fetched origin/main immediately before commit; zero commits behind No linked issue — this PR closes no GitHub issue; the doc queue is tracked in the profile file itself. ## Related - #1761 (previous doc-queue completion in this series — sonnet-5 prompting-guide slice) - #1740 (Verifier B elevated recipe used for cross-vendor verification) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
…ry (#1868) ## Summary The thinking-steering-and-cost platform doc slice completed, so its entry leaves the `docpage-digest` Anthropic profile's doc queue per the queue's remove-on-completion rule. The now-empty "Thinking" category heading goes with it — that category held two overlapping docs digested one page per run under its own contract, and the run-9 entry's PR (#1842) removed the first while anticipating this removal taking the heading. Knowledge bumps 0.10.10 → 0.10.11 so consumers receive the queue change. ## Verification Dual verification reached PASS on both arms against **identical frozen bytes** — a SHA-256 pin of all nine slice files, with the tree quiesced before either arm audited, per the frozen-tree rule this campaign adopted after a concurrent-correction race produced a spurious MAJOR. - **Arm B (cross-vendor, Codex)** — `VERDICT: PASS`, `FINDINGS: none`, six checks PASS, three round-1 findings RESOLVED. - **Arm A (same-vendor, fresh context, rationale withheld)** — `REVERIFY2: PASS`, six checks PASS, five prior findings RESOLVED, three MINORs, all record-keeping and none touching fidelity. Fidelity was swept mechanically: all 108 quoted spans across the six digests are exact substrings of the single source line each cites, 0 misses. Tag census 41 `cc-applicable` / 28 `mixed` / 12 `api-only` = 81 rows, exactly one vocabulary tag per row. The three MINORs were remediated after the verdicts without altering any claim row: two stale self-check footer records got dated "historical as of" annotations, and the missing round-2/3 applied record was written. The slice's `interview-handoff.md` was independently re-validated against the corrected digest bytes by a separate agent and its five stale items corrected. No degraded fallback was used at any point. Three findings from this run carry to the batched dispositions interview rather than this PR: the absence of any cross-digest citation-consistency check in the verification contract, the absence of a required applied-record artifact per correction round, and a genuine unharmonized cross-source tension about where a resolved effort value physically lives. ## Related - Follows #1842 (run 9, the paired thinking doc), which removed the first entry of this category. - Same campaign as #1816, #1788, #1779, #1775, #1765, #1761, #1756, #1752. No linked issue. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
…ge-digest queue (#1874) The `platform.claude.com/docs/en/release-notes/system-prompts` slice completed. It is the **last entry in the doc queue** — after this merges, the queue section holds only the deferred task-budgets trigger entry, which was never queued. ## What ran The largest slice this pipeline has processed: **18 digests over a 2,548-line source, 659 claim rows, 561 `api-only`.** - Seven correction rounds and five dual-verification rounds, each on SHA-256-pinned bytes with the frozen-tree rule enforced — both arms re-hash before *and* after auditing, and no correction runs while a verifier holds the tree. - Final state: both arms `VERDICT: PASS`, with a confirming round after the last corrections. - Final gates: **1,895 recorded command/count pairs replay with 0 mismatches**, 0 `<corpus>` placeholders, 659/659 rows parse with `N. Quote (line` count equal to `- Tag:` count in all 18 digests, every stated tally equal to its anchored `grep -c`, `check-quotes.py` clean. ## What the run found worth carrying forward - **Narrow-slug false absences** remained the dominant defect — a basis testing one literal while the corpus documents the same concept in other words. Rows now disclose near-misses by name and line, each produced by a command recorded in that row. - **Prose is unparsed by every gate.** Summary paragraphs, Implications bullets and Open questions carried stale counts and false statements across several rounds; two sweeps (one whitespace-normalized with an offset map back to physical lines) closed the class. - **A contested tag-ordering question is escalated, not decided** — whether selecting a positive tag requires first establishing harness applicability. It is written up as a candidate profile amendment with both readings, the evidence, and a recommendation, for the dispositions interview. Residual MINOR findings are disclosed in the slice's `interview-handoff.md` as Open questions, per the run's stopping rule. ## What this PR changes - Removes the system-prompts entry and the now-empty "Supplementary references" heading from the profile's Doc queue. - Bumps the `knowledge` plugin `0.10.13` → `0.10.14`. - Adds the matching CHANGELOG entry. No linked issue ## Related - Third and final of the serialized run-11 queue PRs, after #1872 (resources overview) and #1873 (verification-loops blog). All three touch the same profile file, so they merged one at a time. - Completes the queue drain begun in #1752 and continued through #1756, #1761, #1765, #1775, #1779, #1788, #1816, #1842 and #1868. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
1 participant
Summary
docpage-digestAnthropic profile's doc queue — its slice completed end-to-end (fetch through interview handoff) per the queue's remove-on-completion rule. It was the last remaining per-model guide, so the emptied category heading goes with it..mdappended to the page URL; HTTP 200, 15,864 bytes — channel re-verified for this page, no degradation); provenance recorded in the slice checklist..work/platform-claude-com-docs-en-bui-1b530928/verification/.unverified-inferenceis an additional uncertainty marker, never a substitute for thecc-applicable/api-only/mixedtag; the sibling positive-claims bullet now says "additionally recorded" to close the substitute-tag misreading at its origin.0.10.3→0.10.4with matching CHANGELOG entry.Verification
markdownlint-cli2on changed markdown: 0 errorscheck-skill.sh docpage-digest(CHECK_SKILL_SKILLS_ROOT=plugins/knowledge/skills, baseorigin/main): PASS (1 pre-existing soft warning, SKILL.md length)check-changelog-parity.sh --check-bump origin/main: PASSNo linked issue — this PR closes no GitHub issue; the doc queue is tracked in the profile file itself.
Related
🤖 Generated with Claude Code