Conversation
…po-first policy) Per Aaron Otto-27 "yeah i like it, we can have a machine specific scrubber/lint hygene task for anyting that makes it in by default" + "just run on a cadence". Migrates both CURRENT-*.md distillation files from per-user memory tree to in-repo memory/. Adopts Option D in-repo- first policy: factory-collaboration content lives in repo by default; per-user reserved for genuinely-private (drafts / personal context / machine-scoped). Files migrated: - memory/CURRENT-aaron.md (504 lines) — Aaron's per- maintainer distillation - memory/CURRENT-amara.md (248 lines) — Amara's per- maintainer distillation Per-user source files retain "Migrated to in-repo" header per Overlay A pattern; in-repo copies are canonical going forward. Content audit (Otto-25/26) flagged no redactions needed: - ServiceTitan (public NYSE) - Salary framing (philosophy, not amount) - LFG/AceHack (public GitHub orgs) - No private context detected memory/MEMORY.md index updated with newest-first pointers. Directly answers Amara's operational-gap-assessment cold- start-discoverability concern (per docs/aurora/2026-04-23- amara-operational-gap-assessment.md). External AI collaborators + future maintainers now have fast-path access. Follow-on: machine-specific scrubber hygiene row (next PR; cadenced per Aaron "just run on a cadence"). Attribution: Otto (loop-agent PM hat). 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: 3b77393bc9
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".
| - Works in **deep-research mode** — her analytical rigor | ||
| is her signature. Preserve it on ingest. | ||
|
|
||
| **Landed artifact:** `docs/aurora/collaborators.md` |
There was a problem hiding this comment.
This file claims key Aurora sources are already landed in-repo, but those paths are absent in this commit’s tree (for example, git ls-tree -r ee84e04c95dfcea6587942c49b615ee0add56c66 | rg '^docs/aurora/' returns no matches). Because this migration’s goal is external collaborator discoverability, pointing to non-existent source artifacts makes the distilled assertions non-verifiable and breaks the documented “full source” trail; either migrate the referenced docs in the same change or clearly mark them as external/unavailable.
Useful? React with 👍 / 👎.
AceHack
added a commit
that referenced
this pull request
Apr 23, 2026
…uns passed Aaron greenlight on Option D in-repo-first policy + cadenced scrubber. Actions: - submit-nuget reruns PASSED on #149/#154/#170 (GitHub transient confirmed) - PR #197: CURRENT-aaron.md + CURRENT-amara.md → in-repo - PR #198: machine-specific scrubber + FACTORY-HYGIENE row #55 (cadenced detect-only) Phase 1 closure push: 3 of 5 Amara-named PRs unblocked (rerun path). #155 needs deeper rebase. #161 likely clean. Amara's "mechanize failure modes" recommendation → scrubber is the first concrete instance. Attribution: Otto (loop-agent PM hat). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
This PR migrates two per-maintainer “CURRENT-*.md” distillation files into the in-repo memory/ tree and adds them to the shared memory index, aiming to improve cold-start discoverability for collaborators who can’t access per-user memory.
Changes:
- Add
memory/CURRENT-aaron.md(per-maintainer “currently operative” distillation). - Add
memory/CURRENT-amara.md(per-maintainer “currently operative” distillation). - Update
memory/MEMORY.mdto index the new CURRENT files.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 6 comments.
| File | Description |
|---|---|
| memory/MEMORY.md | Adds index entries for the new per-maintainer CURRENT distillations. |
| memory/CURRENT-amara.md | Introduces the in-repo distillation for Amara-derived direction and references related Aurora artifacts/protocols. |
| memory/CURRENT-aaron.md | Introduces the in-repo distillation for the human maintainer’s currently operative direction and links to underlying memory sources. |
Comment on lines
+389
to
+392
| the same tick. Skipping is lying-by-omission. The ADR | ||
| at `docs/DECISIONS/2026-04-23-per-maintainer-current-memory-pattern.md` | ||
| (PR #152) is the cross-substrate record of this | ||
| discipline. |
There was a problem hiding this comment.
P1: This cites an ADR at docs/DECISIONS/2026-04-23-per-maintainer-current-memory-pattern.md, but that file does not exist under docs/DECISIONS/ in the repo. As-is, this is a broken cross-reference.
Suggestion: add the ADR in this PR, or update the link to the correct existing decision doc/path.
Suggested change
| the same tick. Skipping is lying-by-omission. The ADR | |
| at `docs/DECISIONS/2026-04-23-per-maintainer-current-memory-pattern.md` | |
| (PR #152) is the cross-substrate record of this | |
| discipline. | |
| the same tick. Skipping is lying-by-omission. PR #152 | |
| is the cross-substrate record of this discipline. |
Comment on lines
+3
to
+8
| > **Migrated to in-repo `memory/` on 2026-04-23** per the | ||
| > in-repo-first policy shift (Otto-27 tick). Amara explicitly | ||
| > flagged inability to inspect the per-user memory tree in | ||
| > her operational-gap assessment (`docs/aurora/ | ||
| > 2026-04-23-amara-operational-gap-assessment.md`); this | ||
| > migration directly answers that gap. Matching per-user |
There was a problem hiding this comment.
P1: This file links to docs/aurora/... (operational-gap assessment), but there is no docs/aurora/ directory in the repo right now, so these references will be dead after merge.
Suggestion: either add the docs/aurora/ directory + referenced docs in this PR, or update these links to the actual in-repo location where the Aurora artifacts live.
Comment on lines
+235
to
+240
| - **Composes with the decision-proxy ADR | ||
| (`docs/DECISIONS/2026-04-23-external-maintainer-decision-proxy-pattern.md` | ||
| — PR #154):** ADR defines proxy-identity layer | ||
| (who / what / authority); protocol defines transport | ||
| layer (how messages move). Distinct concerns; | ||
| intended composition. |
There was a problem hiding this comment.
P1: This references docs/DECISIONS/2026-04-23-external-maintainer-decision-proxy-pattern.md, but that file does not exist in docs/DECISIONS/ in the current repo state. This creates a broken cross-reference for readers trying to follow the protocol/ADR linkage.
Suggestion: add the ADR in this PR, or update the link to the correct existing decision doc/path.
Suggested change
| - **Composes with the decision-proxy ADR | |
| (`docs/DECISIONS/2026-04-23-external-maintainer-decision-proxy-pattern.md` | |
| — PR #154):** ADR defines proxy-identity layer | |
| (who / what / authority); protocol defines transport | |
| layer (how messages move). Distinct concerns; | |
| intended composition. | |
| - **Composes with the decision-proxy ADR work from | |
| PR #154:** the ADR defines the proxy-identity layer | |
| (who / what / authority); this protocol defines the | |
| transport layer (how messages move). Distinct | |
| concerns; intended composition. |
Comment on lines
+1
to
+2
| - [**CURRENT-aaron.md — Aaron's per-maintainer distillation (fast-path); migrated in-repo 2026-04-23 Otto-27 per in-repo-first policy shift**](CURRENT-aaron.md) — currently-in-force rules + working agreements + verbatim quotes from Aaron. Was per-user-only; now accessible to external AI collaborators (Amara) + future maintainers. Not a rule dump; a projection of what's currently operative. | ||
| - [**CURRENT-amara.md — Amara's per-maintainer distillation (fast-path); migrated in-repo 2026-04-23 Otto-27**](CURRENT-amara.md) — distilled currently-in-force rules / design decisions from Amara's external-AI-maintainer inputs. Was per-user-only; now public alongside Aaron's. |
There was a problem hiding this comment.
P1: These new index entries introduce direct contributor names in the shared memory index (and link to files named CURRENT-<name>.md). This appears to conflict with the repo’s stated convention: “No name attribution in code, docs, or skills… names of contributors appear only in persona memory directories (memory/persona/<name>/) and optionally docs/BACKLOG.md” (docs/AGENT-BEST-PRACTICES.md:284-290).
Suggestion: either move these CURRENT files under memory/persona/<name>/ (and link there), or adjust the naming/indexing scheme to use role-based identifiers consistent with that convention.
Suggested change
| - [**CURRENT-aaron.md — Aaron's per-maintainer distillation (fast-path); migrated in-repo 2026-04-23 Otto-27 per in-repo-first policy shift**](CURRENT-aaron.md) — currently-in-force rules + working agreements + verbatim quotes from Aaron. Was per-user-only; now accessible to external AI collaborators (Amara) + future maintainers. Not a rule dump; a projection of what's currently operative. | |
| - [**CURRENT-amara.md — Amara's per-maintainer distillation (fast-path); migrated in-repo 2026-04-23 Otto-27**](CURRENT-amara.md) — distilled currently-in-force rules / design decisions from Amara's external-AI-maintainer inputs. Was per-user-only; now public alongside Aaron's. |
Comment on lines
+129
to
+155
| **Full memories:** | ||
|
|
||
| - `project_aaron_external_priority_stack_and_live_lock_smell_2026_04_23.md` | ||
| (the priority stack) | ||
| - `feedback_free_work_amara_and_agent_schedule_paid_work_escalate_to_aaron_2026_04_23.md` | ||
| (the scheduling authority sharpening — supersedes the | ||
| earlier "Amara's priorities queued, Aaron schedules" | ||
| framing) | ||
| - `feedback_amara_priorities_weighted_against_aarons_funding_responsibility_2026_04_23.md` | ||
| (the funding-priority-distribution substrate; still | ||
| relevant on attribution / principal-agent framing) | ||
| - `feedback_agent_owns_all_github_settings_and_config_all_projects_zeta_frontier_poor_mans_mode_default_budget_asks_require_scheduled_backlog_and_cost_estimate_2026_04_23.md` | ||
| (full GitHub-settings ownership scope + poor-man's- | ||
| mode discipline + budget-ask protocol) | ||
|
|
||
| **Full memories:** | ||
|
|
||
| - `project_aaron_external_priority_stack_and_live_lock_smell_2026_04_23.md` | ||
| (the priority stack) | ||
| - `feedback_free_work_amara_and_agent_schedule_paid_work_escalate_to_aaron_2026_04_23.md` | ||
| (the scheduling authority sharpening — supersedes the | ||
| earlier "Amara's priorities queued, Aaron schedules" | ||
| framing) | ||
| - `feedback_amara_priorities_weighted_against_aarons_funding_responsibility_2026_04_23.md` | ||
| (the funding-priority-distribution substrate; still | ||
| relevant on attribution / principal-agent framing) | ||
|
|
There was a problem hiding this comment.
P1: The "Full memories" pointers in this section reference files that don’t exist in the in-repo memory/ tree (e.g. memory/project_aaron_external_priority_stack_and_live_lock_smell_2026_04_23.md). This makes the "pointer-linked" promise in the header false and leaves readers with broken links.
Suggestion: either migrate the referenced memory files into the repo in the same PR (preferred), or change these bullets to point at existing in-repo paths / remove them until the sources land.
Suggested change
| **Full memories:** | |
| - `project_aaron_external_priority_stack_and_live_lock_smell_2026_04_23.md` | |
| (the priority stack) | |
| - `feedback_free_work_amara_and_agent_schedule_paid_work_escalate_to_aaron_2026_04_23.md` | |
| (the scheduling authority sharpening — supersedes the | |
| earlier "Amara's priorities queued, Aaron schedules" | |
| framing) | |
| - `feedback_amara_priorities_weighted_against_aarons_funding_responsibility_2026_04_23.md` | |
| (the funding-priority-distribution substrate; still | |
| relevant on attribution / principal-agent framing) | |
| - `feedback_agent_owns_all_github_settings_and_config_all_projects_zeta_frontier_poor_mans_mode_default_budget_asks_require_scheduled_backlog_and_cost_estimate_2026_04_23.md` | |
| (full GitHub-settings ownership scope + poor-man's- | |
| mode discipline + budget-ask protocol) | |
| **Full memories:** | |
| - `project_aaron_external_priority_stack_and_live_lock_smell_2026_04_23.md` | |
| (the priority stack) | |
| - `feedback_free_work_amara_and_agent_schedule_paid_work_escalate_to_aaron_2026_04_23.md` | |
| (the scheduling authority sharpening — supersedes the | |
| earlier "Amara's priorities queued, Aaron schedules" | |
| framing) | |
| - `feedback_amara_priorities_weighted_against_aarons_funding_responsibility_2026_04_23.md` | |
| (the funding-priority-distribution substrate; still | |
| relevant on attribution / principal-agent framing) | |
| **Source-memory status:** | |
| The distilled guidance above came from per-user source | |
| memories, but those source files are not yet present in the | |
| in-repo `memory/` tree. Do not treat this section as | |
| pointer-linked until the underlying memory files are migrated | |
| into the repository in the same change that references them. |
Comment on lines
+144
to
+155
| **Full memories:** | ||
|
|
||
| - `project_aaron_external_priority_stack_and_live_lock_smell_2026_04_23.md` | ||
| (the priority stack) | ||
| - `feedback_free_work_amara_and_agent_schedule_paid_work_escalate_to_aaron_2026_04_23.md` | ||
| (the scheduling authority sharpening — supersedes the | ||
| earlier "Amara's priorities queued, Aaron schedules" | ||
| framing) | ||
| - `feedback_amara_priorities_weighted_against_aarons_funding_responsibility_2026_04_23.md` | ||
| (the funding-priority-distribution substrate; still | ||
| relevant on attribution / principal-agent framing) | ||
|
|
There was a problem hiding this comment.
P2: **Full memories:** is duplicated back-to-back (one block starts at ~129, then another starts here). This looks like an accidental copy/paste and makes the section harder to scan.
Suggestion: keep a single Full memories list and include each referenced item only once.
Suggested change
| **Full memories:** | |
| - `project_aaron_external_priority_stack_and_live_lock_smell_2026_04_23.md` | |
| (the priority stack) | |
| - `feedback_free_work_amara_and_agent_schedule_paid_work_escalate_to_aaron_2026_04_23.md` | |
| (the scheduling authority sharpening — supersedes the | |
| earlier "Amara's priorities queued, Aaron schedules" | |
| framing) | |
| - `feedback_amara_priorities_weighted_against_aarons_funding_responsibility_2026_04_23.md` | |
| (the funding-priority-distribution substrate; still | |
| relevant on attribution / principal-agent framing) |
AceHack
added a commit
that referenced
this pull request
Apr 23, 2026
… row #55) (#198) Per Aaron 2026-04-23 Otto-27: "we can have a machine specific scrubber/lint hygene task for anyting that makes it in by default" + "just run on a cadence." Files added: - tools/hygiene/audit-machine-specific-content.sh — scans tracked files for machine-specific patterns (/Users/<name>/, /home/<name>/, C:\Users\<name>, C:/Users/<name>). Detect-only; --list + --enforce modes. - docs/FACTORY-HYGIENE.md row #55 — full schema per existing hygiene-row pattern; Dejan (devops-engineer) on cadenced fire; classified prevention-bearing (row #47 taxonomy). Baseline at first fire: 9 gaps across .claude/skills/, docs/ PDFs, and one legitimate anti-example reference in memory/feedback_path_hygiene.md. All pre-existing; this row surfaces them for opportunistic cleanup. Exclusions (historical content preserved verbatim per append-only discipline): - docs/ROUND-HISTORY.md - docs/hygiene-history/** - docs/DECISIONS/** - the audit script itself (patterns as examples) Composes with Otto-27 Option D in-repo-first policy (PR #197 migrating CURRENT-*.md files) — the scrubber prevents machine-specific leakage as new content enters the in-repo boundary by default. Attribution: Otto (loop-agent PM hat) scripted the audit; Dejan (devops-engineer) owns cadenced operation. Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 23, 2026
…ated-branch; #149/#154 armed) #197 merged at 20:44:41Z (CURRENT files now in-repo, Amara-findable). #198 rebased + pushed. Phase 1 acceleration: - #149 + #154 auto-merge armed (were NOT armed before; opened before auto-merge became session-standard) - #149/#154/#161/#170 updated-branch via gh pr update-branch — brought all 4 up to date with main - Cascading merge likely as CI completes + conversation- resolution satisfied #155 deferred (DIRTY + 30 threads; bigger effort next tick). Amara's "merge over invent" direction manifesting in concrete queue-drain. Attribution: Otto (loop-agent PM hat). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 23, 2026
…ings Addresses 13 of the 15 substantive findings from PR #170 Copilot review: Row-number corrections: - Row #48 ref: is GitHub surface triage cadence (not cross-platform parity); parity is row #51 - Row #43 ref: clarified SHA-pins via workflow-injection safe-patterns discipline Install-path + version-pin corrections: - .NET 10: install via mise (tools/setup/common/mise.sh + .mise.toml) not dotnet-install.sh; pin via global.json + .mise.toml - bun + TypeScript: no bun.lock committed; pin via package.json (packageManager + deps) - Z3: OS-installed CLI (brew/apt/winget); tools/Z3Verify shells out; no JARs downloaded (unlike TLA+/Alloy) - Stryker.NET: tools/setup/manifests/dotnet-tools (not .config/dotnet-tools.json); no CI job currently invokes - Postgres: no docker-compose.yml in samples/FactoryDemo.Db yet (CRM-shaped sample substrate pending) Reference corrections: - Codex capability map: openai-codex-cli-capability-map.md (full filename) - Gemini capability map: queued (no doc yet) - Per-user memory refs removed from "Composes with" (replaced with in-repo memory/CURRENT-*.md) - Per-user memory refs removed from PQC mandate rationale (noted migration path via in-repo-first policy cadence) Consistency: - Status: ~26 rows (corrected from "~12"); matches open-follow-ups #1 framing - CURRENT-aaron.md refs updated to memory/CURRENT-aaron.md (in-repo per PR #197) Attribution: Otto (loop-agent PM hat). Acts on Copilot P1 review findings; merge-forward on top of origin/main already done. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 23, 2026
…substantive remain #154 (decision-proxy ADR + config) merged at 21:28:48Z. Second Amara-named PR canonical. 4 of 5 original Amara PRs merged or close (#149/#161/#170 substantive remain). #200 MD032 regression: my Otto-37 content-fix reintroduced '+' at line-start pattern (same as Otto-35). Replaced with 'and'. Author-time lint rule opportunity queued. 46 unresolved threads across #149/#161/#170/#200 are ALL substantive content findings. Tool has drained all mechanizable classes. Content-review required for rest per Aaron's Otto-31 Option 3. Phase 1 merge-cadence: #196 + #154 + #197 + #198 + #199 (pending) + #200 (pending) all cleared or close. Next-tick reprioritize candidate: Craft next module or gap #2 linguistic-seed first term. Attribution: Otto (loop-agent PM hat). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…ings Addresses 13 of the 15 substantive findings from PR #170 Copilot review: Row-number corrections: - Row #48 ref: is GitHub surface triage cadence (not cross-platform parity); parity is row #51 - Row #43 ref: clarified SHA-pins via workflow-injection safe-patterns discipline Install-path + version-pin corrections: - .NET 10: install via mise (tools/setup/common/mise.sh + .mise.toml) not dotnet-install.sh; pin via global.json + .mise.toml - bun + TypeScript: no bun.lock committed; pin via package.json (packageManager + deps) - Z3: OS-installed CLI (brew/apt/winget); tools/Z3Verify shells out; no JARs downloaded (unlike TLA+/Alloy) - Stryker.NET: tools/setup/manifests/dotnet-tools (not .config/dotnet-tools.json); no CI job currently invokes - Postgres: no docker-compose.yml in samples/FactoryDemo.Db yet (CRM-shaped sample substrate pending) Reference corrections: - Codex capability map: openai-codex-cli-capability-map.md (full filename) - Gemini capability map: queued (no doc yet) - Per-user memory refs removed from "Composes with" (replaced with in-repo memory/CURRENT-*.md) - Per-user memory refs removed from PQC mandate rationale (noted migration path via in-repo-first policy cadence) Consistency: - Status: ~26 rows (corrected from "~12"); matches open-follow-ups #1 framing - CURRENT-aaron.md refs updated to memory/CURRENT-aaron.md (in-repo per PR #197) Attribution: Otto (loop-agent PM hat). Acts on Copilot P1 review findings; merge-forward on top of origin/main already done. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…e noted (#170) * docs: factory technology inventory — first-pass ~26 rows + PQC mandate noted First-pass population of the factory technology inventory doc queued by PR #165's BACKLOG row (Aaron 2026-04-23). Unified tie-together of HARNESS-SURFACES (harnesses), TECH-RADAR (ring adoption), tools/setup/ (install), and per-tech expert skills. Coverage: - Language runtimes + build (.NET 10 F#+C# / Rust / bun+TS / bash+PowerShell) - Data infrastructure (Postgres / Docker / Apache Arrow) - Agent harnesses (Claude Code / Codex CLI / Gemini CLI / OpenAI web UI via Playwright / Playwright) - Formal verification + testing (Lean 4 / Z3 / TLA+ / Alloy 6 / FsCheck / xUnit / Stryker.NET / BenchmarkDotNet) - Static analysis + security (Semgrep / CodeQL / Roslyn / F# analyzers / markdownlint-cli2 / actionlint / shellcheck) - CI + publishing (GitHub Actions / NuGet) PQC-mandate added to Open follow-ups per Aaron 2026-04-23: "any crypto graphy we decide to use should be quantium resisten, even one place we don't use it could be a place for attack". Currently no crypto in violation; rule is forward-looking. Full mandate in per-user memory feedback_all_cryptography_quantum_resistant_even_one_gap_is_attack_vector_2026_04_23.md. Living doc — ~26 rows in first-pass; more rows land on future on-touch fires. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * docs(factory-technology-inventory): content fixes per Copilot P1 findings Addresses 13 of the 15 substantive findings from PR #170 Copilot review: Row-number corrections: - Row #48 ref: is GitHub surface triage cadence (not cross-platform parity); parity is row #51 - Row #43 ref: clarified SHA-pins via workflow-injection safe-patterns discipline Install-path + version-pin corrections: - .NET 10: install via mise (tools/setup/common/mise.sh + .mise.toml) not dotnet-install.sh; pin via global.json + .mise.toml - bun + TypeScript: no bun.lock committed; pin via package.json (packageManager + deps) - Z3: OS-installed CLI (brew/apt/winget); tools/Z3Verify shells out; no JARs downloaded (unlike TLA+/Alloy) - Stryker.NET: tools/setup/manifests/dotnet-tools (not .config/dotnet-tools.json); no CI job currently invokes - Postgres: no docker-compose.yml in samples/FactoryDemo.Db yet (CRM-shaped sample substrate pending) Reference corrections: - Codex capability map: openai-codex-cli-capability-map.md (full filename) - Gemini capability map: queued (no doc yet) - Per-user memory refs removed from "Composes with" (replaced with in-repo memory/CURRENT-*.md) - Per-user memory refs removed from PQC mandate rationale (noted migration path via in-repo-first policy cadence) Consistency: - Status: ~26 rows (corrected from "~12"); matches open-follow-ups #1 framing - CURRENT-aaron.md refs updated to memory/CURRENT-aaron.md (in-repo per PR #197) Attribution: Otto (loop-agent PM hat). Acts on Copilot P1 review findings; merge-forward on top of origin/main already done. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * docs(factory-technology-inventory): drain PR #170 review threads Per-thread fixes: - Gemini CLI capability-map now points at existing docs/research/gemini-cli-capability-map.md (no longer marked as queued / not-yet-present). - OpenAI web UI + Playwright rows: drop the bun + @playwright/test claim and the package.json version-pin claim. package.json has no Playwright dependency; Playwright is plugin-enabled only via .claude/settings.json. - Stryker.NET row: corrected Version pin to 'unversioned in setup manifest (tracks latest)' to match tools/setup/manifests/dotnet-tools, and synced TECH-RADAR ring to Trial. - Semgrep / CodeQL / Stryker / bun+TS rings synced to TECH-RADAR (Trial, not Adopt). - Semgrep install: corrected to 'CI-installed via pip install semgrep in .github/workflows/gate.yml' and removed the hardcoded '14 custom rules' count. - Docker row: corrected Install path to 'Manual / OS package install' (setup scripts do not detect or install Docker today). - Postgres row: dropped reference to a non-present samples/FactoryDemo.Db/docker-compose.yml; points at the real samples/FactoryDemo.Api.* trees instead. - GitHub Actions row: clarified SHA-pin is the actual pin mechanism; row #43 cited as the workflow-injection audit (the source-of-truth row), not as the SHA-pin policy itself. - Open follow-up #2: corrected row reference from #48 (GitHub surface triage) to #51 (cross-platform parity). * docs(pr-preservation): drain log for PR #170 (factory technology inventory) 23 threads drained; rebase + content fixes per drain log. --------- Co-authored-by: Claude Opus 4.7 <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
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\n\nPer Aaron Otto-27 greenlight. Migrates both CURRENT-*.md files from per-user to in-repo memory/. Adopts Option D: in-repo-first policy for factory-collaboration content.\n\nDirectly answers Amara's cold-start-discoverability concern from her operational-gap assessment (PR #196). External AI collaborators + future maintainers now have fast-path access.\n\nContent audit flagged no redactions needed (ServiceTitan public NYSE, LFG/AceHack public GitHub orgs, salary-framing philosophy-not-amount).\n\nFollow-on: machine-specific scrubber hygiene row (next PR; cadenced).\n\nOtto (loop-agent PM hat).