chore(knowledge): retire increase-consistency doc-queue entry after slice completion - #1779
Merged
Merged
Conversation
…lice completion Removes the increase-consistency guardrail entry (and its now-empty "Guardrail 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 one correction round, re-verified REVERIFY: PASS by both verifiers). Bumps the knowledge plugin 0.10.6 -> 0.10.7 with a matching CHANGELOG entry. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Contributor
|
Claude finished @kyle-sexton's task in 1m 8s —— View job PR Review
SummaryClean, well-scoped maintenance PR. All three changes are internally consistent, follow established patterns, and the PR body carries exceptional verification provenance. No correctness, security, or alignment issues found. File-by-file findings
Checklist
Verdict: LGTM. No blocking findings. |
Contributor
|
Claude finished @kyle-sexton's task in 42s —— View job Security Review
No security issues found. The three changed files are:
No logic flaws, injection vectors, authorization gaps, credential exposure, or supply-chain risk introduced by this diff. |
kyle-sexton
added a commit
that referenced
this pull request
Jul 30, 2026
…t-half completion (#1788) ## Summary - Removes the choosing-a-model entry from the `docpage-digest` Anthropic profile's doc queue — its digest slice completed end-to-end (fetch through interview handoff) per the queue's remove-on-completion rule, closing the entry's second half. The routing-vet half was already executed 2026-07-29 (#1697, PR #1725) and was NOT redone; the slice checklist records that scope explicitly. The emptied "Model selection" special-handling category goes with the entry. - The paired models-explained blog entry's annotation now points at the completed slice's interview handoff (its OQ-10 is a clearly-marked pairing package for that run) and carries the fully-qualified vet reference. - Channel: raw-md (`.md` appended; HTTP 200, 112 lines / 7,568 bytes — channel re-verified for this page, no degradation). - Slice verification: Verifier A (same-vendor, fresh context) CORRECTION-NEEDED (1+1); Verifier B (cross-vendor Codex CLI 0.146.0 via the issue #1740 elevated recipe, no degraded fallback) CORRECTION-NEEDED (3+2; B-1 shared A-1's root — a dropped launch-page cross-link sentence). Two correction rounds (session-default agents — cross-model doc, no model pin); round 2 resolved a shorthand residual plus two round-1-reverify findings, one a genuine verifier split (external-doc price-shorthand relay) resolved by applying the stricter cross-vendor ruling in-slice and escalating the standard to the interview. Final: REVERIFY2: PASS from both verifiers, zero new findings. Records under `.work/platform-claude-com-docs-en-abo-38ebff0f/verification/`. - No profile-learning bullet this run: the ruling candidates (product/feature-name tag boundary, Mythos api-only basis, the price-shorthand standard) are all escalated for interview ratification in the handoff's OQ-2 — codifying now would front-run them (#1775/#1779 precedent). - Knowledge plugin `0.10.7` → `0.10.8` 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 every changelog claim to the slice records; its three advisories — a machine-local path ghost-ref in the blog annotation, a de-qualified issue reference, and a missing ratification home for the verifier-split ruling — were all 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 - #1779 (previous doc-queue completion in this series — increase-consistency slice) - #1697 (the routing-vet half of this queue entry, executed 2026-07-29; PR #1725) - #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>
kyle-sexton
added a commit
that referenced
this pull request
Jul 30, 2026
…slice completion (#1816) ## Summary The claude-models-explained blog slice completed the full docpage-digest pipeline: rendered-channel fetch (raw-md confirmed absent per the profile's blog-post channel note) with firecrawl extraction, 7-unit digest fan-out executing the run-7 pairing cross-link contract (a)–(g), dual verification (Verifier A fable-5 + cross-vendor Codex per the #1740 recipe, two correction rounds, final REVERIFY2: PASS from both, no degraded fallback), and interview handoff (pairing results + 8 CAs + 8 OQs, all 32 digest questions mapped). Profile changes: - Models-explained blog queue entry removed per the remove-on-completion rule, taking its inlined seven-item pairing contract with it (executed; results recorded in the slice's handoff). - Vendor-blog attestation rule codified: assertion-specific `vendor-claimed (blog, <fetch date> fetch)` markers, illustrative assertion-class list — the rule the context-engineering slice's handoff recommended (its OQ-3), enforced end-to-end by both verifiers on this slice. Knowledge plugin 0.10.8 → 0.10.9 with changelog. No linked issue ## Related - #1788 — run 7 (choosing-a-model digest), whose OQ-10 pairing contract this slice executed - #1775 / #1779 — the guardrail-lane queue PRs preceding this run - #1740 — the elevated Codex Verifier B recipe used for cross-vendor verification Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
kyle-sexton
added a commit
that referenced
this pull request
Jul 31, 2026
…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>
kyle-sexton
added a commit
that referenced
this pull request
Aug 1, 2026
…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>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
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 guardrail guide, so the emptied category heading goes with it..mdappended to the page URL; HTTP 200, 93 lines / 29,682 bytes — channel re-verified for this page, no degradation); provenance recorded in the slice checklist.claude -p --json-schemaCLI structured-output surface, since corrected against live headless/cli-reference checks). One correction round (session-default agents — guardrail guide, no model pin per the profile's model-matching table); re-verified REVERIFY: PASS by both verifiers, 10/10 findings resolved, zero new findings, both re-verifiers independently re-fetched the cited live docs. Records under.work/platform-claude-com-docs-en-tes-44ba86b3/verification/.0.10.6→0.10.7with 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: PASS (0.10.7 ordering conforms to the changelog-order gate)No linked issue — this PR closes no GitHub issue; the doc queue is tracked in the profile file itself.
Related
🤖 Generated with Claude Code