Skip to content

chore(knowledge): remove the thinking-steering-and-cost doc-queue entry - #1868

Merged
kyle-sexton merged 1 commit into
mainfrom
chore/docqueue-thinking-steering-cost-complete
Jul 31, 2026
Merged

chore(knowledge): remove the thinking-steering-and-cost doc-queue entry#1868
kyle-sexton merged 1 commit into
mainfrom
chore/docqueue-thinking-steering-cost-complete

Conversation

@kyle-sexton

Copy link
Copy Markdown
Contributor

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

No linked issue.

🤖 Generated with Claude Code

The thinking-steering-and-cost platform doc slice completed: raw-md fetch
through interview handoff, dual verification across three correction rounds,
both arms re-verified PASS against identical frozen bytes, no degraded
fallback. Its entry leaves the 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; the run-9
entry's PR removed the first and anticipated this removal taking the heading.

Bumps knowledge 0.10.10 to 0.10.11 so consumers receive the queue change.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
@claude

claude Bot commented Jul 31, 2026

Copy link
Copy Markdown

Claude finished @kyle-sexton's task in 1m 19s —— View job


Review: PR #1868 — remove thinking-steering-and-cost doc-queue entry

  • Gather context (diff, changed files, CLAUDE.md rules)
  • Review plugin.json version bump
  • Review CHANGELOG.md entry
  • Review anthropic-docs-profile.md removal
  • Post final review

Verdict: LGTM — no issues found.

This is a small, self-consistent housekeeping change. Reviewed all three changed files against origin/main...HEAD:

  • plugin.json — clean patch bump 0.10.100.10.11, matching the delivery-vehicle convention in the CHANGELOG header (a consumer only receives the queue change once this increments). No unrelated fields touched.
  • CHANGELOG.md — new entry follows the exact structure/tone of the paired 0.10.10 entry (the run-9 PR it references), and its prose accurately matches the diff: it names the removed "Thinking" category heading and the queue's remove-on-completion rule, and correctly notes both overlapping thinking docs are now digested.
  • anthropic-docs-profile.md — the 4-line removal (heading + blank + URL + trailing blank) leaves a single blank line before Deferred with trigger (not queued):, no stray double-blank or dangling heading.

Checked one thing that could've been a red flag: no thinking-steering-and-cost slice files exist anywhere in this repo. That's expected, not a gap — plugin.json's library_dir config (and the "Artifact targets" section of the profile doc) confirms digest artifacts land in the consuming repo's library directory, not this marketplace repo. So a queue-removal PR touching only these three files is the correct shape for this campaign.

CLAUDE.md fresh-docs mandate: doesn't apply here — the doc-queue entry lives in a skill's context/prose file, not a manifest, schema, hook contract, or frontmatter contract surface, so no live WebFetch verification was required for this change.

PR-body linkage contract: compliant — body ends with the literal "No linked issue." line and contains a non-empty ## Related section.

No architecture, error-handling, or maintainability concerns; nothing to send to the security lane.

@claude

claude Bot commented Jul 31, 2026

Copy link
Copy Markdown

Claude finished @kyle-sexton's task in 26s —— View job


Security review complete

  • Fetch PR diff (origin/main...HEAD)
  • Review changed files for security issues
  • Post findings

Scope reviewed: all 3 changed files —
plugin.json,
CHANGELOG.md,
anthropic-docs-profile.md.

No security issues found.

This PR is a pure content/metadata change: a semver bump (0.10.100.10.11), a matching changelog entry, and the removal of a completed doc-queue entry (a markdown bullet + its now-empty category heading) from a reference profile file. There is:

  • No executable code, script, or hook logic touched.
  • No GitHub Actions workflow or permissions: change.
  • No secrets, tokens, credentials, or config values introduced or handled.
  • No new external inputs, URLs fetched at runtime, or injection surfaces (command/SQL/path/template) — the file only documents doc URLs for a human/agent-driven digest pipeline that isn't invoked by this change.
  • No authorization/access-control logic anywhere in the diff.

This lane (logic/architecture/trust-boundary review) has nothing to flag; there's also no CI/workflow surface here for zizmor's static advisories to apply to.

@github-actions

Copy link
Copy Markdown

Claude has reviewed this PR 1 time. The lane skips further automatic reviews after 5; deleting this comment resets the count.

@kyle-sexton
kyle-sexton merged commit 16c236b into main Jul 31, 2026
32 checks passed
@kyle-sexton
kyle-sexton deleted the chore/docqueue-thinking-steering-cost-complete branch July 31, 2026 19:47
kyle-sexton added a commit that referenced this pull request Aug 1, 2026
…e-digest queue (#1872)

The `platform.claude.com/docs/en/resources/overview` slice ran end to
end and reached dual verification, so its entry leaves the
`docpage-digest` Anthropic doc queue under the queue's
remove-on-completion rule.

## What ran

- Raw-md fetch, per-unit digests (4 digests, 57 claim rows, 13
`api-only`), correction rounds, and Phase 5 interview handoff.
- **Dual verification on identical SHA-256-pinned bytes**: verifier arm
A and cross-vendor arm B both returned `VERDICT: PASS` with **no MAJOR
findings**.
- Arm B's coverage: all 57 claim rows and all 117 source lines examined;
31 distinct commands replayed with every count agreeing; all 174
`llms.txt` hits mechanically verified; 57/57 quote anchors, row/tag
parity, stated tallies and placeholder scans all clean.

Residual MINOR findings are disclosed in the slice's
`interview-handoff.md` as Open questions for the batched dispositions
interview, per the campaign's stopping rule.

## What this PR changes

- Removes the resources-overview entry from the profile's Doc queue
section. The **"Supplementary references" heading remains** — the
system-prompts release-notes page sits under it as a separate concurrent
run, and its own queue PR removes the heading once it empties.
- Bumps the `knowledge` plugin `0.10.11` → `0.10.12`.
- Adds the matching CHANGELOG entry, mirroring the 0.10.8–0.10.11
exemplars.

No linked issue

## Related

- Follows the same queue-drain pattern as #1868
(thinking-steering-and-cost), #1842, and #1816.
- Two sibling run-11 slices (system-prompts release notes,
verification-loops blog) follow in serialized PRs, since all three touch
the same profile file.

🤖 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
…ocpage-digest queue (#1873)

The
`claude.com/blog/building-verification-loops-in-claude-code-with-skills`
slice ran end to end and reached dual verification, so its entry leaves
the `docpage-digest` Anthropic doc queue under the queue's
remove-on-completion rule. It was the last entry under **"Blog posts"**,
so that heading is removed too.

## What ran

- Raw-md fetch, per-unit digests (6 digests, 78 claim rows, **0
`api-only`** — every row is positive-tagged), correction rounds, and
Phase 5 interview handoff.
- **Dual verification on identical SHA-256-pinned bytes**: arm A and
cross-vendor arm B both returned `VERDICT: PASS` with **no MAJOR
findings**.
- Arm B's coverage: 78/78 rows examined including all 44
`vendor-claimed` rows; 7/7 pin hashes matched; 50 commands replayed with
every count agreeing; 78/78 source quotes exact including ellipsis
placement; a structural platform-scope sweep over 68 candidate
paragraphs found no unscoped absence claim remaining.

## Why this slice took extra rounds

It exercised the **vendor-blog attestation rule** (profile 0.10.9) at
scale. The rule's predicate names two properties — an assertion exists
only in the blog when *"no harness **or platform** doc states the same
assertion"* — so a `code.claude.com`-only search never establishes it.
All 44 `vendor-claimed` rows now carry a **targeted row-local
`platform.claude.com` check**, using `curl -sSL` for pages outside the
snapshot subset per DIGEST-BRIEF §5. Exhaustiveness language stays
scoped to `code.claude.com`; the platform half is stated as the check
performed, never as corpus-wide platform absence.

Residual MINOR findings are disclosed in the slice's
`interview-handoff.md` as Open questions for the batched dispositions
interview.

## What this PR changes

- Removes the blog entry and the now-empty "Blog posts" heading from the
profile's Doc queue.
- Bumps the `knowledge` plugin `0.10.12` → `0.10.13`.
- Adds the matching CHANGELOG entry.

No linked issue

## Related

- Second of three serialized run-11 queue PRs; follows #1872 (resources
overview). All three touch the same profile file, so they merge one at a
time.
- Same queue-drain pattern as #1868, #1842, #1816.

🤖 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>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant