Conversation
…rections Dedicated absorb of Amara's 19th courier ferry per CC-002 close-on-existing discipline. Scheduled Otto-164 → executed Otto-165, following 7-ferry precedent (PRs #196 / #211 / #219 / #221 / #235 / #245 / #259 / #330 / #337). Two-part ferry: Part 1 deep-research DST audit (12 sections: rulebook, 12-row entropy scan, dependency audit, 7-row simulation-surface coverage, retry audit, CI determinism, seed discipline, Cartel-Lab DST readiness, KSK/Aurora DST readiness, state-of-the-art comparison, 10-row PR roadmap, what-not-to-claim caveats; Mermaid CI diagram + Gantt timeline). Part 2 Amara's own 5.5-Thinking correction pass (7 required corrections, per-area grade table with B- overall, revised 6-PR roadmap with titles locked, DST-held + FoundationDB-grade acceptance criteria, copy-paste Kenji summary). Key findings: - DST grade: B- (strong architecture, partial impl) - Blockers: DiskBackingStore bypasses simulation (D-grade filesystem simulation), no ISimulationDriver, Task.Run ambient ThreadPool risk, no seed artifacts / no swarm harness - 4 of 12 Part-1 sections already align with shipped substrate: - §6 test classification → PR #339 - §7 artifact layout → PR #342 design - §8 Cartel-Lab stage discipline → PRs #330/#337/#342 - §9 KSK advisory-only → PR #336 + Otto-140..145 memory 6-PR revised roadmap queued as graduation candidates: 1. DST scanner + accepted-boundary registry (new tool + policy docs + workflow) 2. Seed protocol + CI artifacts 3. Sharder reproduction (NOT widen) — reinforces 18th #10 4. ISimulationDriver + VTS promotion to core 5. Simulated filesystem (DiskBackingStore rewrite) 6. Cartel-Lab DST calibration (aligns with #342 design) Plus: push-with-retry.sh retry-audit finding; DST-held + FDB-grade criteria lock. GOVERNANCE §33 four-field header (Scope / Attribution / Operational status / Non-fusion disclaimer). Amara verdict preserved: "strong draft / not canonical yet." Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
There was a problem hiding this comment.
Pull request overview
Adds a new Aurora research/absorb document capturing Amara’s 19th-ferry DST audit (Part 1) plus her 5.5 correction pass (Part 2), with Otto’s operationalization notes and cross-references for follow-on work.
Changes:
- Introduces a new
docs/aurora/ferry absorb covering DST audit findings and a revised remediation roadmap. - Documents queued “graduation” items (scanner/artifacts/scheduler/fs simulation) and reiterates non-authorization boundaries.
Comment on lines
+102
to
+105
| than paraphrase (GOVERNANCE §33); corrections are tracked | ||
| in Part 2 below. Where the text cites sources (e.g. | ||
| "【12†L22-L29】"), those are Amara's internal citation | ||
| markers and are kept intact. |
There was a problem hiding this comment.
References to “GOVERNANCE §33” appear to be incorrect: GOVERNANCE.md currently has no §33, and other docs note the 4-field archive-header convention is not yet codified as a numbered governance section. Update this doc to cite the current source of the convention (or explicitly say it’s an uncodified convention) so readers aren’t sent to a nonexistent governance rule.
Suggested change
| than paraphrase (GOVERNANCE §33); corrections are tracked | |
| in Part 2 below. Where the text cites sources (e.g. | |
| "【12†L22-L29】"), those are Amara's internal citation | |
| markers and are kept intact. | |
| than paraphrase; this is a current factory convention and | |
| is not yet codified as a numbered section in | |
| `GOVERNANCE.md`. Corrections are tracked in Part 2 below. | |
| Where the text cites sources (e.g. "【12†L22-L29】"), those | |
| are Amara's internal citation markers and are kept intact. |
Comment on lines
+26
to
+46
| - **Aaron** — origination of the DST directive as a | ||
| factory-wide discipline (rulebook in `.claude/skills`, | ||
| Otto-56 break→do-no-permanent-harm framing, | ||
| Otto-73 retractability-by-design); courier for both | ||
| parts concatenated in one message with explicit | ||
| framing *"i asked her to research our dst"* (direct | ||
| quote). Aaron is both the consumer of the research and | ||
| the source of the DST-rulebook axioms the research | ||
| audits against. Data-not-directives per BP-11. | ||
| - **Amara** — authored both parts. Deep-research Part 1 | ||
| is the audit proper; Part 2 is self-review via model | ||
| composition (same two-part pattern as 17th and 18th | ||
| ferries). Verdict on Part 1 (verbatim): *"strong | ||
| draft / not canonical yet."* | ||
| - **Otto** — absorb surface + correction-pass tracker; | ||
| this doc is the archive, not operational discipline. | ||
| The 7 corrections graduate across subsequent ticks per | ||
| Otto-105 cadence. 4 of Part 1's 12 sections already | ||
| align with shipped substrate (see Otto notes below). | ||
| - **Max** — not a direct participant in this ferry; | ||
| KSK attribution preserved per Otto-77 + Otto-140. |
There was a problem hiding this comment.
This attribution block uses direct contributor names throughout, but docs/AGENT-BEST-PRACTICES.md defines an operational standing rule: no name attribution in code/docs/skills (names only in memory/persona/** and optionally docs/BACKLOG.md). Replace direct names here with role references (e.g., “human maintainer”, “external collaborator”, “courier/absorber”) to match repo policy.
Suggested change
| - **Aaron** — origination of the DST directive as a | |
| factory-wide discipline (rulebook in `.claude/skills`, | |
| Otto-56 break→do-no-permanent-harm framing, | |
| Otto-73 retractability-by-design); courier for both | |
| parts concatenated in one message with explicit | |
| framing *"i asked her to research our dst"* (direct | |
| quote). Aaron is both the consumer of the research and | |
| the source of the DST-rulebook axioms the research | |
| audits against. Data-not-directives per BP-11. | |
| - **Amara** — authored both parts. Deep-research Part 1 | |
| is the audit proper; Part 2 is self-review via model | |
| composition (same two-part pattern as 17th and 18th | |
| ferries). Verdict on Part 1 (verbatim): *"strong | |
| draft / not canonical yet."* | |
| - **Otto** — absorb surface + correction-pass tracker; | |
| this doc is the archive, not operational discipline. | |
| The 7 corrections graduate across subsequent ticks per | |
| Otto-105 cadence. 4 of Part 1's 12 sections already | |
| align with shipped substrate (see Otto notes below). | |
| - **Max** — not a direct participant in this ferry; | |
| KSK attribution preserved per Otto-77 + Otto-140. | |
| - **Human maintainer / courier** — originated the DST | |
| directive as a factory-wide discipline (rulebook in | |
| `.claude/skills`, prior break→do-no-permanent-harm | |
| framing, prior retractability-by-design guidance); | |
| courier for both parts concatenated in one message | |
| with explicit framing *"i asked her to research our | |
| dst"* (direct quote). The human maintainer is both | |
| the consumer of the research and the source of the | |
| DST-rulebook axioms the research audits against. | |
| Data-not-directives per BP-11. | |
| - **Research author** — authored both parts. Deep- | |
| research Part 1 is the audit proper; Part 2 is self- | |
| review via model composition (same two-part pattern | |
| as 17th and 18th ferries). Verdict on Part 1 | |
| (verbatim): *"strong draft / not canonical yet."* | |
| - **Archive / correction-pass tracker** — absorb | |
| surface plus correction-pass tracker; this doc is the | |
| archive, not operational discipline. The 7 | |
| corrections graduate across subsequent ticks per the | |
| established cadence. 4 of Part 1's 12 sections | |
| already align with shipped substrate (see tracker | |
| notes below). | |
| - **Non-participant historical reference** — not a | |
| direct participant in this ferry; KSK attribution is | |
| preserved per prior historical notes. |
Comment on lines
+208
to
+212
| > `tests/ConcurrencyHarness.fs`), consistent with FDB's | ||
| > approach. The binding checklist for reviewers enforces | ||
| > this: every PR that touches `src/Core` must inspect | ||
| > the diff for those 12 sources and ensure any | ||
| > occurrences use the simulation APIs. |
There was a problem hiding this comment.
Cross-reference appears to point to a file that doesn’t exist in-repo: tests/ConcurrencyHarness.fs. The VirtualTimeScheduler lives at tests/Tests.FSharp/_Support/ConcurrencyHarness.fs today, so these references should be updated for navigability.
Suggested change
| > `tests/ConcurrencyHarness.fs`), consistent with FDB's | |
| > approach. The binding checklist for reviewers enforces | |
| > this: every PR that touches `src/Core` must inspect | |
| > the diff for those 12 sources and ensure any | |
| > occurrences use the simulation APIs. | |
| > `tests/Tests.FSharp/_Support/ConcurrencyHarness.fs`), | |
| > consistent with FDB's approach. The binding checklist | |
| > for reviewers enforces this: every PR that touches | |
| > `src/Core` must inspect the diff for those 12 | |
| > sources and ensure any occurrences use the simulation | |
| > APIs. |
| > | `RandomNumberGenerator` (crypto) | *Not used in core* | Real crypto RNG | MEDIUM | Avoid; prefer `env.Rng` | Determinism of crypto ops | | ||
| > | `Task.Run` / `Task.Factory.StartNew` | *Used only in tests/tools if at all* | Bypasses VT scheduler | HIGH (core) | `env.RunAsync` or scheduler; boundary-accepted | New tasks schedule deterministically | | ||
| > | `Task.Delay` / `Thread.Sleep` | *Not in core logic; possibly integration tests* | Real-time wait | HIGH (core) | `env.Delay` or `VirtualTimeScheduler.Sleep` | Replay of delay-based workflows | | ||
| > | `File.*`, `FileStream` | **`DiskBackingStore` (spine/disk)**, e.g. `src/Core/DiskBackingStore.fs` | Bypasses simulation | **BLOCKER (core)** | Route through `ISimulatedFs` | E2E: random disk faults + rollback | |
There was a problem hiding this comment.
The doc references src/Core/DiskBackingStore.fs, but DiskBackingStore is currently defined in src/Core/DiskSpine.fs (and referenced by src/Core/Durability.fs). Update the file path(s) so readers land on the right implementation.
Suggested change
| > | `File.*`, `FileStream` | **`DiskBackingStore` (spine/disk)**, e.g. `src/Core/DiskBackingStore.fs` | Bypasses simulation | **BLOCKER (core)** | Route through `ISimulatedFs` | E2E: random disk faults + rollback | | |
| > | `File.*`, `FileStream` | **`DiskBackingStore` (spine/disk)**, e.g. `src/Core/DiskSpine.fs` | Bypasses simulation | **BLOCKER (core)** | Route through `ISimulatedFs` | E2E: random disk faults + rollback | |
| > threshold guessing. | ||
| > | ||
| > ```text | ||
| > tests/Tests.FSharp/Formal/SharderInfoTheoreticTests.fs |
There was a problem hiding this comment.
The roadmap references tests/Tests.FSharp/Formal/SharderInfoTheoreticTests.fs, but the current test file is tests/Tests.FSharp/Formal/Sharder.InfoTheoretic.Tests.fs (module Zeta.Tests.Formal.SharderInfoTheoreticTests). Adjust the filename/path in the doc so the cross-reference is accurate.
Suggested change
| > tests/Tests.FSharp/Formal/SharderInfoTheoreticTests.fs | |
| > tests/Tests.FSharp/Formal/Sharder.InfoTheoretic.Tests.fs |
Comment on lines
+1081
to
+1084
| - **`memory/feedback_ksk_naming_unblocked_aaron_ | ||
| directed_rewrite_authority_max_initial_starting | ||
| _point_2026_04_24.md`** (Otto-140..145) — KSK | ||
| canonical expansion (Kinetic Safeguard Kernel). |
There was a problem hiding this comment.
This cross-reference points to a memory/feedback_ksk_naming_unblocked_... file that does not exist under memory/ in the repo. Either fix the filename/path to the actual memory entry or remove the reference to avoid a broken link.
Suggested change
| - **`memory/feedback_ksk_naming_unblocked_aaron_ | |
| directed_rewrite_authority_max_initial_starting | |
| _point_2026_04_24.md`** (Otto-140..145) — KSK | |
| canonical expansion (Kinetic Safeguard Kernel). | |
| - **Otto-140..145** — KSK canonical expansion | |
| (Kinetic Safeguard Kernel). |
Comment on lines
+1097
to
+1098
| - **`tests/ConcurrencyHarness.fs`** — VirtualTimeScheduler | ||
| test-side; Part 1 §4 status "P1 — promote." |
There was a problem hiding this comment.
Cross-reference appears to point to a non-existent path: tests/ConcurrencyHarness.fs. The correct location is tests/Tests.FSharp/_Support/ConcurrencyHarness.fs (where VirtualTimeScheduler is defined). Update this entry so it resolves.
Suggested change
| - **`tests/ConcurrencyHarness.fs`** — VirtualTimeScheduler | |
| test-side; Part 1 §4 status "P1 — promote." | |
| - **`tests/Tests.FSharp/_Support/ConcurrencyHarness.fs`** — | |
| VirtualTimeScheduler test-side; Part 1 §4 status | |
| "P1 — promote." |
| implementation; Part 1 §4 status "P0 — exists." | ||
| - **`tests/ConcurrencyHarness.fs`** — VirtualTimeScheduler | ||
| test-side; Part 1 §4 status "P1 — promote." | ||
| - **`src/Core/DiskBackingStore.fs`** — Part 1 §2's |
There was a problem hiding this comment.
Cross-reference appears to point to a non-existent file: src/Core/DiskBackingStore.fs. The DiskBackingStore implementation currently lives in src/Core/DiskSpine.fs; update this link so it resolves.
Suggested change
| - **`src/Core/DiskBackingStore.fs`** — Part 1 §2's | |
| - **`src/Core/DiskSpine.fs`** — Part 1 §2's |
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…mara 19th-ferry correction #6) (#346) Research-grade criteria doc locking two acceptance bars: 1. DST-held — minimum: 6 items (seeds committed, failing tests emit seed+params, bit-for-bit local-vs-CI reproducibility, broad sweeps nightly-not-gating, zero unreviewed entropy hits in main-path, boundaries either simulated or explicitly accepted). 2. FoundationDB-grade DST candidate — aspirational: 8 surfaces (simulated FS, simulated network, deterministic task scheduler, fault injection/buggify, swarm runner, replay artifact storage, failure minimization/shrinking, end-to-end scenario from one seed). Maps 19th-ferry revised-roadmap PRs to which criteria items each addresses. Captures Amara's per-area grade table (overall B-) as "Amara's assessment, not factory- certified." Explicit promotion path: doc stays research-grade until PR 1 of the 19th-ferry revised roadmap lands an ADR promoting the DST-held bar to factory discipline; at that point criteria migrate to docs/DST-COMPLIANCE.md top-level. No graduation claims DST-held today; graduations reference this doc as target without self-certification. Composes with test-classification.md (PR #339; supports items 1+2+4), calibration-harness-stage2-design.md (PR #342; artifact schema supports item 2), Amara 19th ferry (PR #344 absorb; source of criteria). Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
4 tasks
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…sification (Amara 19th #3) Amara 19th-ferry correction #3 asked for push-with-retry.sh to either (a) document as external-boundary exception with rationale, or (b) convert to investigation-wrapper. Audit finding: the script already implements (a) with high discipline — root-cause investigation block in the header, targeted-5xx-only retries (not blind), exponential backoff, max-attempts cap, per-attempt logging to stderr, full error-text preservation via tee, distinct exit codes for transient-retry-exhausted vs non-transient vs env-error. Amara's concern was based on the doc-level visibility gap, not an implementation gap. This PR closes the gap by: 1. Creating docs/research/dst-accepted-boundaries.md — the accepted-boundaries registry Amara's correction #2 + the DST-compliance-criteria doc (PR #346) both require. Schema for entries locked. First entry: push-with-retry.sh with full rationale, investigation summary, retry- discipline breakdown, and revisit triggers. 2. Adding a classification pointer in the script's header comment block: cites the registry + "First classified 2026-04-23, formally registered Otto-168 2026-04-24." Registry research-grade today; promotes to docs/DST-ACCEPTED- BOUNDARIES.md top-level when PR 1 of the 19th-ferry revised roadmap lands (entropy-scanner + ADR). Next migration candidates named: DiskBackingStore stays BLOCKER until PR 5 simulates it (not accepted-boundary — simulation is correct answer there). Future multi-node network I/O stays BLOCKER until PR 8. Composes with PR #346 dst-compliance-criteria doc, PR #344 19th-ferry absorb, .claude/skills DST guide, existing push-with-retry.sh implementation. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…ation (Amara 19th #3) (#347) * docs: DST accepted-boundaries registry stub + push-with-retry.sh classification (Amara 19th #3) Amara 19th-ferry correction #3 asked for push-with-retry.sh to either (a) document as external-boundary exception with rationale, or (b) convert to investigation-wrapper. Audit finding: the script already implements (a) with high discipline — root-cause investigation block in the header, targeted-5xx-only retries (not blind), exponential backoff, max-attempts cap, per-attempt logging to stderr, full error-text preservation via tee, distinct exit codes for transient-retry-exhausted vs non-transient vs env-error. Amara's concern was based on the doc-level visibility gap, not an implementation gap. This PR closes the gap by: 1. Creating docs/research/dst-accepted-boundaries.md — the accepted-boundaries registry Amara's correction #2 + the DST-compliance-criteria doc (PR #346) both require. Schema for entries locked. First entry: push-with-retry.sh with full rationale, investigation summary, retry- discipline breakdown, and revisit triggers. 2. Adding a classification pointer in the script's header comment block: cites the registry + "First classified 2026-04-23, formally registered Otto-168 2026-04-24." Registry research-grade today; promotes to docs/DST-ACCEPTED- BOUNDARIES.md top-level when PR 1 of the 19th-ferry revised roadmap lands (entropy-scanner + ADR). Next migration candidates named: DiskBackingStore stays BLOCKER until PR 5 simulates it (not accepted-boundary — simulation is correct answer there). Future multi-node network I/O stays BLOCKER until PR 8. Composes with PR #346 dst-compliance-criteria doc, PR #344 19th-ferry absorb, .claude/skills DST guide, existing push-with-retry.sh implementation. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix(#347): 4 review threads — schema clarify + planned-file xref softening - thread PRRT_kwDOSF9kNM59Wql1 (line 12, P1): self-resolving; docs/research/dst-compliance-criteria.md now exists on main via a later merge; cross-reference is valid, no edit needed. - thread PRRT_kwDOSF9kNM59Wqmv (line 42, P2): schema relaxed from "one of the 12 DST entropy classes" to "one or more of the 12 DST entropy classes, comma- or `+`-separated when a site genuinely crosses multiple (e.g. a network boundary whose only retry policy is itself a distinct entropy source)". Keeps the first entry's combined "external network I/O + retry-on-failure" value accurate — retry-on-failure is a policy IN the network-I/O boundary, not a separate class. - thread PRRT_kwDOSF9kNM59Wqm8 (line 172, P1): same self-resolve as thread 1; docs/research/dst-compliance-criteria.md exists. - thread PRRT_kwDOSF9kNM59WqnP (line 125, P1): DiskBackingStore.fs and ISimulationFs are not in src/; rephrased as forward-looking with explicit "(planned, not yet landed)" parentheticals plus a sentence clarifying this row is a placeholder the scan can compare against once PR 5 of the 19th-ferry roadmap arrives. --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…ll (10 PRs) Otto-207: maintainer "are we saving these yet gitnative and have we backfilled them yet?" Honest answer was NO — the PR-preservation BACKLOG row (Otto-150..154, PR #335 in queue) specifies the discipline but never shipped the capture tooling. This PR ships the minimal viable implementation + backfills 10 PRs from this session. New tool: - tools/pr-preservation/archive-pr.sh — one-shot bash script that fetches a PR's review threads, reviews, and comments via `gh api graphql` and writes them to docs/pr-discussions/PR-<N>-<slug>.md with YAML frontmatter (pr_number / title / author / state / dates / refs / archived_at / archive_tool). - tools/pr-preservation/README.md — scope (Phase 0 minimal vs Phase 1-4 longer plan), usage, output schema, backfill status, dependencies (bash + python3 + gh; no external packages), cross-references to Otto-171 / Otto-204 / Otto-204c / PR #335. Backfill (10 PRs archived this tick): - PR #354 backlog-split Phase 1a - PR #352 Server Meshing + SpacetimeDB research - PR #336 KSK naming definition doc - PR #342 calibration-harness Stage-2 design (merged) - PR #344 Amara 19th ferry absorb (merged) - PR #346 DST compliance criteria (merged) - PR #350 Frontier rename pass-2 (merged) - PR #353 BACKLOG split Phase 0 design (merged) - PR #355 Codex first peer-agent deep-review absorb (merged) - PR #356 PR-resolve-loop skill row (merged) Total: 72 review threads + 40 reviews + 6 general comments captured across ~97KB of archive markdown. Long-term plan deliberately kept in BACKLOG row (Otto-150 ..154 / PR #335 queue elevation) rather than expanded in this commit's docs. Phase 0 shipping now; Phase 1 GHA workflow + Phase 2 historical backfill + Phase 3 reconciliation + Phase 4 redaction layer remain queued tickets. Per maintainer directive "make sure you backlog then to a proper long term solution" — the phased plan is already in PR #335 and covers the remaining work. Discipline applied: active-management on the preservation gap itself. Previous tick's "ship and pray" pattern is the exact failure mode this tool begins to close (operator- initiated archive instead of silent reliance on GitHub- side conversation storage). Composes with Otto-204c livelock-diagnosis memory + Otto-204 PR-resolve-loop skill (this script is step 4 of that cycle's conversation-preservation hook). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…ll (10 PRs) Otto-207: maintainer "are we saving these yet gitnative and have we backfilled them yet?" Honest answer was NO — the PR-preservation BACKLOG row (Otto-150..154, PR #335 in queue) specifies the discipline but never shipped the capture tooling. This PR ships the minimal viable implementation + backfills 10 PRs from this session. New tool: - tools/pr-preservation/archive-pr.sh — one-shot bash script that fetches a PR's review threads, reviews, and comments via `gh api graphql` and writes them to docs/pr-discussions/PR-<N>-<slug>.md with YAML frontmatter (pr_number / title / author / state / dates / refs / archived_at / archive_tool). - tools/pr-preservation/README.md — scope (Phase 0 minimal vs Phase 1-4 longer plan), usage, output schema, backfill status, dependencies (bash + python3 + gh; no external packages), cross-references to Otto-171 / Otto-204 / Otto-204c / PR #335. Backfill (10 PRs archived this tick): - PR #354 backlog-split Phase 1a - PR #352 Server Meshing + SpacetimeDB research - PR #336 KSK naming definition doc - PR #342 calibration-harness Stage-2 design (merged) - PR #344 Amara 19th ferry absorb (merged) - PR #346 DST compliance criteria (merged) - PR #350 Frontier rename pass-2 (merged) - PR #353 BACKLOG split Phase 0 design (merged) - PR #355 Codex first peer-agent deep-review absorb (merged) - PR #356 PR-resolve-loop skill row (merged) Total: 72 review threads + 40 reviews + 6 general comments captured across ~97KB of archive markdown. Long-term plan deliberately kept in BACKLOG row (Otto-150 ..154 / PR #335 queue elevation) rather than expanded in this commit's docs. Phase 0 shipping now; Phase 1 GHA workflow + Phase 2 historical backfill + Phase 3 reconciliation + Phase 4 redaction layer remain queued tickets. Per maintainer directive "make sure you backlog then to a proper long term solution" — the phased plan is already in PR #335 and covers the remaining work. Discipline applied: active-management on the preservation gap itself. Previous tick's "ship and pray" pattern is the exact failure mode this tool begins to close (operator- initiated archive instead of silent reliance on GitHub- side conversation storage). Composes with Otto-204c livelock-diagnosis memory + Otto-204 PR-resolve-loop skill (this script is step 4 of that cycle's conversation-preservation hook). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…ll (10 PRs) Otto-207: maintainer "are we saving these yet gitnative and have we backfilled them yet?" Honest answer was NO — the PR-preservation BACKLOG row (Otto-150..154, PR #335 in queue) specifies the discipline but never shipped the capture tooling. This PR ships the minimal viable implementation + backfills 10 PRs from this session. New tool: - tools/pr-preservation/archive-pr.sh — one-shot bash script that fetches a PR's review threads, reviews, and comments via `gh api graphql` and writes them to docs/pr-discussions/PR-<N>-<slug>.md with YAML frontmatter (pr_number / title / author / state / dates / refs / archived_at / archive_tool). - tools/pr-preservation/README.md — scope (Phase 0 minimal vs Phase 1-4 longer plan), usage, output schema, backfill status, dependencies (bash + python3 + gh; no external packages), cross-references to Otto-171 / Otto-204 / Otto-204c / PR #335. Backfill (10 PRs archived this tick): - PR #354 backlog-split Phase 1a - PR #352 Server Meshing + SpacetimeDB research - PR #336 KSK naming definition doc - PR #342 calibration-harness Stage-2 design (merged) - PR #344 Amara 19th ferry absorb (merged) - PR #346 DST compliance criteria (merged) - PR #350 Frontier rename pass-2 (merged) - PR #353 BACKLOG split Phase 0 design (merged) - PR #355 Codex first peer-agent deep-review absorb (merged) - PR #356 PR-resolve-loop skill row (merged) Total: 72 review threads + 40 reviews + 6 general comments captured across ~97KB of archive markdown. Long-term plan deliberately kept in BACKLOG row (Otto-150 ..154 / PR #335 queue elevation) rather than expanded in this commit's docs. Phase 0 shipping now; Phase 1 GHA workflow + Phase 2 historical backfill + Phase 3 reconciliation + Phase 4 redaction layer remain queued tickets. Per maintainer directive "make sure you backlog then to a proper long term solution" — the phased plan is already in PR #335 and covers the remaining work. Discipline applied: active-management on the preservation gap itself. Previous tick's "ship and pray" pattern is the exact failure mode this tool begins to close (operator- initiated archive instead of silent reliance on GitHub- side conversation storage). Composes with Otto-204c livelock-diagnosis memory + Otto-204 PR-resolve-loop skill (this script is step 4 of that cycle's conversation-preservation hook). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…ll (10 PRs) Otto-207: maintainer "are we saving these yet gitnative and have we backfilled them yet?" Honest answer was NO — the PR-preservation BACKLOG row (Otto-150..154, PR #335 in queue) specifies the discipline but never shipped the capture tooling. This PR ships the minimal viable implementation + backfills 10 PRs from this session. New tool: - tools/pr-preservation/archive-pr.sh — one-shot bash script that fetches a PR's review threads, reviews, and comments via `gh api graphql` and writes them to docs/pr-discussions/PR-<N>-<slug>.md with YAML frontmatter (pr_number / title / author / state / dates / refs / archived_at / archive_tool). - tools/pr-preservation/README.md — scope (Phase 0 minimal vs Phase 1-4 longer plan), usage, output schema, backfill status, dependencies (bash + python3 + gh; no external packages), cross-references to Otto-171 / Otto-204 / Otto-204c / PR #335. Backfill (10 PRs archived this tick): - PR #354 backlog-split Phase 1a - PR #352 Server Meshing + SpacetimeDB research - PR #336 KSK naming definition doc - PR #342 calibration-harness Stage-2 design (merged) - PR #344 Amara 19th ferry absorb (merged) - PR #346 DST compliance criteria (merged) - PR #350 Frontier rename pass-2 (merged) - PR #353 BACKLOG split Phase 0 design (merged) - PR #355 Codex first peer-agent deep-review absorb (merged) - PR #356 PR-resolve-loop skill row (merged) Total: 72 review threads + 40 reviews + 6 general comments captured across ~97KB of archive markdown. Long-term plan deliberately kept in BACKLOG row (Otto-150 ..154 / PR #335 queue elevation) rather than expanded in this commit's docs. Phase 0 shipping now; Phase 1 GHA workflow + Phase 2 historical backfill + Phase 3 reconciliation + Phase 4 redaction layer remain queued tickets. Per maintainer directive "make sure you backlog then to a proper long term solution" — the phased plan is already in PR #335 and covers the remaining work. Discipline applied: active-management on the preservation gap itself. Previous tick's "ship and pray" pattern is the exact failure mode this tool begins to close (operator- initiated archive instead of silent reliance on GitHub- side conversation storage). Composes with Otto-204c livelock-diagnosis memory + Otto-204 PR-resolve-loop skill (this script is step 4 of that cycle's conversation-preservation hook). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…ll (10 PRs) Otto-207: maintainer "are we saving these yet gitnative and have we backfilled them yet?" Honest answer was NO — the PR-preservation BACKLOG row (Otto-150..154, PR #335 in queue) specifies the discipline but never shipped the capture tooling. This PR ships the minimal viable implementation + backfills 10 PRs from this session. New tool: - tools/pr-preservation/archive-pr.sh — one-shot bash script that fetches a PR's review threads, reviews, and comments via `gh api graphql` and writes them to docs/pr-discussions/PR-<N>-<slug>.md with YAML frontmatter (pr_number / title / author / state / dates / refs / archived_at / archive_tool). - tools/pr-preservation/README.md — scope (Phase 0 minimal vs Phase 1-4 longer plan), usage, output schema, backfill status, dependencies (bash + python3 + gh; no external packages), cross-references to Otto-171 / Otto-204 / Otto-204c / PR #335. Backfill (10 PRs archived this tick): - PR #354 backlog-split Phase 1a - PR #352 Server Meshing + SpacetimeDB research - PR #336 KSK naming definition doc - PR #342 calibration-harness Stage-2 design (merged) - PR #344 Amara 19th ferry absorb (merged) - PR #346 DST compliance criteria (merged) - PR #350 Frontier rename pass-2 (merged) - PR #353 BACKLOG split Phase 0 design (merged) - PR #355 Codex first peer-agent deep-review absorb (merged) - PR #356 PR-resolve-loop skill row (merged) Total: 72 review threads + 40 reviews + 6 general comments captured across ~97KB of archive markdown. Long-term plan deliberately kept in BACKLOG row (Otto-150 ..154 / PR #335 queue elevation) rather than expanded in this commit's docs. Phase 0 shipping now; Phase 1 GHA workflow + Phase 2 historical backfill + Phase 3 reconciliation + Phase 4 redaction layer remain queued tickets. Per maintainer directive "make sure you backlog then to a proper long term solution" — the phased plan is already in PR #335 and covers the remaining work. Discipline applied: active-management on the preservation gap itself. Previous tick's "ship and pray" pattern is the exact failure mode this tool begins to close (operator- initiated archive instead of silent reliance on GitHub- side conversation storage). Composes with Otto-204c livelock-diagnosis memory + Otto-204 PR-resolve-loop skill (this script is step 4 of that cycle's conversation-preservation hook). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…ll (10 PRs) Otto-207: maintainer "are we saving these yet gitnative and have we backfilled them yet?" Honest answer was NO — the PR-preservation BACKLOG row (Otto-150..154, PR #335 in queue) specifies the discipline but never shipped the capture tooling. This PR ships the minimal viable implementation + backfills 10 PRs from this session. New tool: - tools/pr-preservation/archive-pr.sh — one-shot bash script that fetches a PR's review threads, reviews, and comments via `gh api graphql` and writes them to docs/pr-discussions/PR-<N>-<slug>.md with YAML frontmatter (pr_number / title / author / state / dates / refs / archived_at / archive_tool). - tools/pr-preservation/README.md — scope (Phase 0 minimal vs Phase 1-4 longer plan), usage, output schema, backfill status, dependencies (bash + python3 + gh; no external packages), cross-references to Otto-171 / Otto-204 / Otto-204c / PR #335. Backfill (10 PRs archived this tick): - PR #354 backlog-split Phase 1a - PR #352 Server Meshing + SpacetimeDB research - PR #336 KSK naming definition doc - PR #342 calibration-harness Stage-2 design (merged) - PR #344 Amara 19th ferry absorb (merged) - PR #346 DST compliance criteria (merged) - PR #350 Frontier rename pass-2 (merged) - PR #353 BACKLOG split Phase 0 design (merged) - PR #355 Codex first peer-agent deep-review absorb (merged) - PR #356 PR-resolve-loop skill row (merged) Total: 72 review threads + 40 reviews + 6 general comments captured across ~97KB of archive markdown. Long-term plan deliberately kept in BACKLOG row (Otto-150 ..154 / PR #335 queue elevation) rather than expanded in this commit's docs. Phase 0 shipping now; Phase 1 GHA workflow + Phase 2 historical backfill + Phase 3 reconciliation + Phase 4 redaction layer remain queued tickets. Per maintainer directive "make sure you backlog then to a proper long term solution" — the phased plan is already in PR #335 and covers the remaining work. Discipline applied: active-management on the preservation gap itself. Previous tick's "ship and pray" pattern is the exact failure mode this tool begins to close (operator- initiated archive instead of silent reliance on GitHub- side conversation storage). Composes with Otto-204c livelock-diagnosis memory + Otto-204 PR-resolve-loop skill (this script is step 4 of that cycle's conversation-preservation hook). 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
Dedicated absorb of Amara's 19th courier ferry per CC-002 close-on-existing discipline. 12 sections of deep-research DST audit + 7-correction pass.
4 of 12 sections already align with shipped substrate
7 queued corrections / 6 revised-roadmap PRs
ISimulationDriver+ VTS promotion to corePlus:
tools/git/push-with-retry.shretry-audit finding; DST-held + FDB-grade criteria lock.DST grade (Amara's assessment, not factory-certified)
B- — strong architectural intent, partial implementation. DST philosophy A-, filesystem simulation D (blocker), task scheduling C-, network D/NA (future).
Amara verdict: "strong draft / not canonical yet."
Test plan
🤖 Generated with Claude Code