Conversation
…ness fix (Aaron 2026-04-29) Aaron's correction post-#855-merge: > we want atest for all those from searches to not historical truth > like the porject or your training data so search Two distinct sources of "historical truth" called out: 1. Training data (Jan 2026 cutoff) — Otto's parameters 2. Project state — what's in the repo today, may itself be stale, copy-cargo-culted, or never-current-to-begin-with Both are historical. Neither substitutes for current authoritative upstream sources. The test for any load-bearing claim is a fresh web search. This generalises Otto-247 (version-currency rule, narrowly scoped to version numbers) to ALL authoritative claims — tools, standards, APIs, runtimes, libraries, CI services, security policies, conventions. Carved blade: Training data is historical. Project state is historical. Current upstream docs are the test. Search first. Cite second. Assert third. ## Demonstrated by application Per Otto-363 (substrate-or-it-didn't-happen), this rule must itself land as substrate. Per Otto-364 itself, it must be demonstrated, not just asserted. Did both. Four web searches against current authoritative sources verified Amara's CI-classifier-design claims. Each search produced a sharper finding than training-data recall: 1. Bun ci/lockfile semantics Sources: bun.sh/docs/pm/lockfile, bun.sh/blog/bun-lock-text-lockfile Sharper: bun.lock (text) is v1.2.0+ default; legacy bun.lockb binary form is being phased out. Zeta has neither committed yet — first-implementation decision point. 2. GitHub Actions paths-ignore + required checks Sources: docs.github.com/en/pull-requests/.../troubleshooting- required-status-checks, github.com/orgs/community/discussions/54877, github.com/orgs/community/discussions/44490 Sharper: Required checks remain Pending (not Skipped) when paths-ignore matches. Three GitHub-blessed workarounds ranked: (1) conditional with success-on-skip — the classifier pattern, (2) dummy workflow same name + inverse path, (3) external dorny/paths-filter. 3. GitHub Actions cross-job outputs Sources: docs.github.com/en/actions/how-tos/write-workflows/ choose-what-workflows-do/pass-job-outputs, docs.github.com/actions/using-workflows/workflow-syntax- for-github-actions Sharper: 1 MB per-job output cap, 50 MB total per workflow. Load-bearing for classifier-output JSON design. 4. mise project config Sources: mise.jdx.dev/configuration.html, mise.jdx.dev/walkthrough.html Sharper: Both `mise.toml` and `.mise.toml` are valid; Zeta's dotfile form is fine. Verbatim packet + four search verifications preserved at: docs/research/2026-04-29-aaron-search-first-authority-not-training- data-not-project-memory.md ## Also fixed in this PR Codex P2 PRRT_kwDOSF9kNM5-i1UH (filed on closed #855 just before merge, caught real surviving disjointness violation): CLAUDE.md and AGENTS.md bootstrap pointers still listed "GitHub Issue" as *parked*, contradicting the mutually-exclusive 5-tier taxonomy the Otto-363 memory file established. The doctrine memory was correct; the cold-start entry points were not. Fixed: vocabulary lines in both CLAUDE.md and AGENTS.md now read: *captured* (TaskUpdate — ephemeral) ≠ *parked* (pushed WIP branch like wip/<topic>-<date>, optionally with draft PR — git-ref-backed; GitHub Issues are NOT parking surfaces, they live in the host-durable-not-git-canonical class) ≠ *preserved* (git-native repo, committed + reachable-from-long-lived- ref + indexed) ≠ *canonical* (accepted spec) ≠ *operational* (enforced by tooling) Now consistent with the canonical taxonomy. The 5-tier classifier the recovery process / future lints depend on no longer self-contradicts across CLAUDE.md, AGENTS.md, and the doctrine memory file. ## Files + docs/research/2026-04-29-aaron-search-first-authority-not-training- data-not-project-memory.md (verbatim packet + four search verifications) + memory/feedback_otto_364_search_first_authority_not_training_data_ not_project_memory_aaron_2026_04_29.md (distilled rule + composes-with map) ~ memory/MEMORY.md (paired index entry, newest-first) ~ CLAUDE.md (Version-currency bullet generalised to Otto-364 search-first-authority; vocabulary line fixed for taxonomy disjointness) ~ AGENTS.md (vocabulary line fixed for taxonomy disjointness) ## Composes with - Otto-247 (version-currency, narrower predecessor — NOT superseded; remains the version-specific instance) - Otto-363 (substrate-or-it-didn't-happen — search results in chat are weather; cited in research doc are substrate; same family) - Otto-362 (intra-file supersession — Otto-364 is upstream-vs-recall version of the stale-claims-must-be-refreshed family) - feedback_best_practices_evidence_lineage_survival_substrate_* (best-practice-evidence-lineage rule; Otto-364 is its search step) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: dec2647c36
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
There was a problem hiding this comment.
Pull request overview
Introduces the Otto-364 doctrine: “search-first authority” for any load-bearing upstream/tooling/API/policy claim (generalizing the earlier version-currency rule), and fixes a taxonomy/vocabulary disjointness regression in the CLAUDE.md + AGENTS.md bootstrap pointers.
Changes:
- Adds Otto-364 as a new doctrine memory entry plus a research-grade source packet demonstrating the rule via four upstream verifications.
- Indexes Otto-364 in
memory/MEMORY.md(newest-first). - Updates CLAUDE.md and AGENTS.md bootstrap bullets to reflect the broader search-first-authority rule and to correct the “GitHub Issues” durability-class placement.
Reviewed changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
memory/feedback_otto_364_search_first_authority_not_training_data_not_project_memory_aaron_2026_04_29.md |
New Otto-364 doctrine memory: rule, triggers, skip cases, citation hygiene, and composition links. |
memory/MEMORY.md |
Adds newest-first index entry for Otto-364. |
docs/research/2026-04-29-aaron-search-first-authority-not-training-data-not-project-memory.md |
Preserves the source packet and demonstrates Otto-364 via four cited upstream searches. |
CLAUDE.md |
Generalizes the version-currency bootstrap rule to search-first-authority and adjusts vocabulary wording to reflect the disjointness fix. |
AGENTS.md |
Aligns bootstrap vocabulary wording with the corrected durability taxonomy (Issues are host-durable-not-git-canonical, not “parked”). |
…ntradiction Three thread fixes from PR #856 review: 1. CLAUDE.md L320-338 (Codex P2 + Copilot P1): the same Otto-363 bullet contained two contradictory claims — "PRs and issues are host-durable parking surfaces" then "GitHub Issues are NOT parking surfaces". Resolution: promote host-durable-not-git-canonical to its own enumerated class (5 → 6), and reword the earlier line to "host-durable-not-git- canonical surfaces" so both lines tell the same story. 2. AGENTS.md L279-288 (Copilot P1): same 5-vs-6 inconsistency. The underlying 5-tier channel taxonomy at L270-277 already had host-durable-not-git-canonical as a distinct tier; the vocabulary layer was under-counting. Now matches. 3. docs/research/2026-04-29-aaron-search-first-authority-...md L5 (Copilot P1): "Status: Verbatim" was inaccurate because the document contains translation/analysis/demonstration sections beyond the verbatim Aaron quote. Reworded to clarify scope: "The quoted Aaron message is verbatim; the surrounding material is translation, analysis, and demonstration." No new doctrine added. Smallest sufficient substrate (Otto-362 + Otto-365 discipline). Operating-invariant maintenance, not a new lane. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: fa3beab895
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Comment on lines
+325
to
+326
| and GitHub Issues are host-durable-not-git-canonical | ||
| surfaces, NOT substrate; for doctrine-changing |
There was a problem hiding this comment.
This line assigns all PRs to host-durable-not-git-canonical, but the same bullet later defines parked as including a pushed WIP branch “optionally with draft PR.” Those two labels are declared mutually exclusive, so this reintroduces a taxonomy contradiction for the common draft-PR parking flow and can cause agents to apply the wrong preservation workflow for parked work.
Useful? React with 👍 / 👎.
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
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
Lands Otto-364 — generalises Otto-247 (version-currency, narrowly version-numbers) to all authoritative claims: tools, standards, APIs, runtimes, libraries, CI services, security policies, conventions.
Plus fixes a post-merge Codex P2 catch on closed #855 (vocabulary disjointness violation in CLAUDE.md + AGENTS.md bootstrap pointers).
Carved blade (Aaron verbatim)
What's in this PR
docs/research/2026-04-29-aaron-search-first-authority-not-training-data-not-project-memory.mdmemory/feedback_otto_364_search_first_authority_not_training_data_not_project_memory_aaron_2026_04_29.mdmemory/MEMORY.mdCLAUDE.mdAGENTS.mdCLAUDE.md(also)Demonstrated by application
Per Otto-363 (substrate-or-it-didn't-happen) AND Otto-364 itself, the rule must be demonstrated, not just asserted. Did both.
Four web searches against current authoritative sources verified Amara's CI-classifier claims. Each search produced a sharper finding than training-data recall:
Bun ci/lockfile — verified at bun.sh/docs/pm/lockfile + bun.sh/blog/bun-lock-text-lockfile. Sharper: text-based
bun.lockis v1.2.0+ default; binarybun.lockbis legacy. Zeta has neither — first-implementation decision point.GitHub Actions
paths-ignore+ required checks — verified at docs.github.com troubleshooting required status checks + Discussion #54877 + Discussion #44490. Sharper: required checks remain Pending (not Skipped); three GitHub-blessed workarounds ranked, with classifier-pattern matching option (1) (conditional with success-on-skip).GitHub Actions cross-job outputs — verified at docs.github.com pass-job-outputs. Sharper: 1 MB per-job cap, 50 MB total — load-bearing for classifier-output JSON design.
mise project config — verified at mise.jdx.dev/configuration.html + mise.jdx.dev/walkthrough.html. Sharper: both
mise.tomland.mise.tomlare valid; Zeta's dotfile form is fine.Disjointness fix (Codex P2 from #855)
Codex P2 PRRT_kwDOSF9kNM5-i1UH caught a real surviving violation: CLAUDE.md and AGENTS.md bootstrap pointers still listed "GitHub Issue" as parked, contradicting the mutually-exclusive 5-tier taxonomy the Otto-363 memory file established. The doctrine memory was correct; the cold-start entry points were not.
Fixed: vocabulary lines in both CLAUDE.md and AGENTS.md now read consistently with the doctrine memory — GitHub Issues live in host-durable-not-git-canonical, NOT in parked. The 5 classes are now mutually exclusive across all three surfaces.
Composes with
memory/feedback_version_currency_*) — narrower predecessor (version numbers only). NOT superseded; remains the version-specific instance.Test plan
🤖 Generated with Claude Code