Conversation
…BP-25 promotion candidate Amara's 4th ferry (PR #221 absorb) Determinize-stage item: document "live-state-before-policy" as an explicit rule. The decision-proxy-evidence schema (PR #222) already has the `live_state_checks:` field that enforces it per-record; this PR adds the explicit principle section + candidates the rule for BP-25 promotion. What landed: 1. docs/decision-proxy-evidence/README.md — new section "Live-state-before-policy" covering: - Why the rule exists (Amara's HB-004 commit-sample showing same-day propose-from-symptoms → policy-stance → empirical- correction) - How the schema enforces it (live_state_checks: required for settings-change and branch-shaping task classes; examples from DP-001 worked record) - Scope (settings / branch-shaping / authority claims / roadmap assumptions) - What's excluded (pure reads, mechanical fixes) - BP-NN promotion candidacy note 2. docs/BACKLOG.md — new P2 row candidating BP-25 promotion via ADR. Aarav's call per BP-NN-promotion-cadence FACTORY-HYGIENE row. Rule text candidate provided; owner mapped to Aarav + Kenji + Rune; effort S. Not a unilateral promotion — just the candidate row. Promotion requires Aarav ADR drafting. Amara's Determinize-stage progress: 1/5 (this PR). ✓ Live-state-before-policy schema-enforcement + BP candidate Remaining: - Memory reference-existence lint (S) - Memory duplicate-title lint enforcement (partial via #220/AceHack#12) - Generated CURRENT-*.md views (L) - Memory reconciliation algorithm (L) Per Aaron Otto-72: "don't wait on me approved, mark down your decisions". This PR acts under standing authority (Otto-67 full GitHub grant); BP-25 consideration is logged as BACKLOG candidate for Aarav's promotion call. Frontier UI (future, Otto-63) will be Aaron's batch-review surface. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
deleted the
determinize/live-state-before-policy-rule-amara-determinize
branch
![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: 9468e4bba0
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
+6907
to
+6911
| Kenji integrates; Rune readability. **Source of truth:** | ||
| `docs/aurora/2026-04-23-amara-memory-drift-alignment- | ||
| claude-to-memories-drift.md` (PR #221 absorb) + | ||
| `docs/decision-proxy-evidence/README.md` (PR #222 + this | ||
| PR's addendum). |
There was a problem hiding this comment.
This new backlog entry changes planned intent, but the listed "Source of truth" does not include a docs/decision-proxy-evidence/DP-*.yaml record for this decision. docs/decision-proxy-evidence/README.md says backlog-shaping actions should be logged via an evidence record before durable action, so landing this row without that record breaks the audit trail the workflow depends on and makes authority/provenance harder to verify later.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
Pull request overview
Documents the “live-state-before-policy” principle behind live_state_checks: in the decision-proxy evidence schema, and adds a BACKLOG item to consider promoting the rule into docs/AGENT-BEST-PRACTICES.md as BP-25.
Changes:
- Adds a new section to
docs/decision-proxy-evidence/README.mdexplaining scope/why/enforcement for live-state-before-policy. - Adds a P2 BACKLOG row proposing BP-25 promotion candidacy for the rule.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
| docs/decision-proxy-evidence/README.md | Adds an explanatory section for the live-state-before-policy rule behind live_state_checks:. |
| docs/BACKLOG.md | Adds a P2 item to queue BP-25 promotion consideration and outlines next steps. |
Comment on lines
+6891
to
+6893
| field in `docs/decision-proxy-evidence/` records (documented | ||
| in the `README.md` "Live-state-before-policy" section | ||
| after PR <this>). BP-NN promotion is Aarav's call per the |
Comment on lines
+6893
to
+6895
| after PR <this>). BP-NN promotion is Aarav's call per the | ||
| BP-NN-promotion-cadence FACTORY-HYGIENE row; this row | ||
| queues the promotion consideration. Rule text candidate: |
| check change, merge policy change, or branch-rule change | ||
| unless the current live state has been queried in the same | ||
| work unit."* **Scope:** draft ADR under | ||
| `docs/DECISIONS/YYYY-MM-DD-bp-25-live-state-before-policy.md` |
Comment on lines
+6908
to
+6909
| `docs/aurora/2026-04-23-amara-memory-drift-alignment- | ||
| claude-to-memories-drift.md` (PR #221 absorb) + |
Merged
3 tasks
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…59 (Amara Determinize action) (#225) Amara's 4th ferry (PR #221 absorb) Determinize-stage item: prevent the retrieval-drift class where prose cites paths that don't resolve. Her commit samples show repeated cleanup passes for memory paths that didn't exist; this is the third leg of memory-index hygiene. Three-leg memory-index hygiene now complete: 1. row #58 (PR #220 merged) — every memory/*.md change updates MEMORY.md in same commit/PR 2. AceHack PR #12 (pending Aaron merge) — MEMORY.md has no duplicate link targets 3. row #59 (this PR) — every MEMORY.md link target resolves to an actual file under memory/ New artifacts: - tools/hygiene/audit-memory-references.sh Parses `](foo.md)` link targets, resolves each against base dir (default memory/), fails (exit 2 under --enforce) on any broken reference. Supports --file PATH + --base DIR for custom use. - .github/workflows/memory-reference-existence-lint.yml Safe-pattern compliant per FACTORY-HYGIENE row #43 (SHA-pinned checkout, minimum permissions, concurrency group, runs-on pinned, no user-authored context). Triggers on PRs/pushes touching memory/** or the audit tool / workflow itself. - FACTORY-HYGIENE row #59 documenting cadence / owner / scope / classification (prevention-bearing — blocks merge before broken refs land). First-run baseline captured in commit: - In-repo memory/MEMORY.md: 44 refs all resolve (clean) - Per-user MEMORY.md: 391 refs all resolve (clean) Both clean confirms that PR #220's memory-index-integrity CI has been keeping the substrate in good shape. This lint closes the third-leg gap before drift regresses. Amara Determinize-stage progress: 2/5 (with this PR). ✓ Live-state-before-policy (PR #224) ✓ Memory reference-existence lint (this PR) Remaining: - Memory duplicate-title lint (partial via AceHack PR #12) - Generated CURRENT-*.md views (L) - Memory reconciliation algorithm (L) Per Aaron Otto-72 standing directive: acting under Otto-67 full-GitHub authority, decisions logged in PR body + memory, Frontier UI is the future batch-review surface. Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…rows (Amara Govern-stage 1/2) Amara's 4th ferry (PR #221 absorb) named populating docs/CONTRIBUTOR-CONFLICTS.md as the Govern-stage action: the schema has existed since PR #166 but the Resolved table was empty despite multiple session-observed contributor-level disagreements that closed with evidence. Backfills three genuine contributor-level conflicts observed this session (narrow scope — not maintainer-directives, which are out-of-scope per the schema's contributor-level disagreement definition): - CC-001: Copilot (PR reviewer) vs Aaron on no-name-attribution rule scope (history-file exemption). Resolved in Aaron's favor via Otto-52 clarification; policy BACKLOG row filed in PR #210. - CC-002: Amara (4th ferry) vs Otto (pre-Otto-67 pattern) on Stabilize-vs-keep-opening-new-frames. Resolved in Amara's favor; Otto pivoted at Otto-68 to execute her roadmap; 3/3 Stabilize + 3/5 Determinize landed via PRs #222/#223/#224/#225/#226. - CC-003: Codex (PR reviewer) vs Otto (initial framing) on citing-absent-artifacts. Resolved in Codex's favor via fix commits 29872af/1c7f97d on PRs #207/#208; pattern now discipline (distinguish merged-on-main from proposed-in-PR-open). All three rows follow the schema's 8-column layout and include the full Resolution-so-far / Scope / Source cells the schema requires. No retroactive Aaron→human-maintainer sweep of prior rows; schema's rule 1 (resolutions are additive) honored. This is 1/2 of Amara's Govern-stage work. 2/2 is the authority-envelope + escalation-path ADR (deferred, M-effort). Part of Amara's 4-stage remediation roadmap (Stabilize → Determinize → Govern → Assure). Otto-75 tick.
AceHack
added a commit
that referenced
this pull request
Apr 24, 2026
…rows (Amara Govern 1/2) (#227) * govern: CONTRIBUTOR-CONFLICTS backfill — 3 resolved session-observed rows (Amara Govern-stage 1/2) Amara's 4th ferry (PR #221 absorb) named populating docs/CONTRIBUTOR-CONFLICTS.md as the Govern-stage action: the schema has existed since PR #166 but the Resolved table was empty despite multiple session-observed contributor-level disagreements that closed with evidence. Backfills three genuine contributor-level conflicts observed this session (narrow scope — not maintainer-directives, which are out-of-scope per the schema's contributor-level disagreement definition): - CC-001: Copilot (PR reviewer) vs Aaron on no-name-attribution rule scope (history-file exemption). Resolved in Aaron's favor via Otto-52 clarification; policy BACKLOG row filed in PR #210. - CC-002: Amara (4th ferry) vs Otto (pre-Otto-67 pattern) on Stabilize-vs-keep-opening-new-frames. Resolved in Amara's favor; Otto pivoted at Otto-68 to execute her roadmap; 3/3 Stabilize + 3/5 Determinize landed via PRs #222/#223/#224/#225/#226. - CC-003: Codex (PR reviewer) vs Otto (initial framing) on citing-absent-artifacts. Resolved in Codex's favor via fix commits 29872af/1c7f97d on PRs #207/#208; pattern now discipline (distinguish merged-on-main from proposed-in-PR-open). All three rows follow the schema's 8-column layout and include the full Resolution-so-far / Scope / Source cells the schema requires. No retroactive Aaron→human-maintainer sweep of prior rows; schema's rule 1 (resolutions are additive) honored. This is 1/2 of Amara's Govern-stage work. 2/2 is the authority-envelope + escalation-path ADR (deferred, M-effort). Part of Amara's 4-stage remediation roadmap (Stabilize → Determinize → Govern → Assure). Otto-75 tick. * govern: annotate CC-002/CC-003 Source cells — PR #221/#219 open, not yet on main Applies CC-003's own discipline (cite-as-open-not-landed) to CC-002 and CC-003 themselves. Both rows cited `docs/aurora/2026-04-23-amara-memory-drift-*` and `docs/aurora/2026-04-23-amara-decision-proxy-*` without the "not yet on main" marker — the files are added by PRs #221 / #219 which are still open. Drain for PR #227 review threads PRRT_kwDOSF9kNM59RFIx and PRRT_kwDOSF9kNM59RFJE (dangling file refs at lines 132, 133). * fix: markdownlint auto-fixes on governance doc Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 25, 2026
…ize L-effort item) Amara's 4th ferry (PR #221 absorb) centerpiece proposal: replace hand-maintained CURRENT-*.md distillations with generated views over typed memory facts. Her sketch was ~40 lines of Python; this is the design that downstream implementation follows. ~380 lines covering: - MemoryFact record schema (id / subject / predicate / object / source_kind / source_path / source_anchor / timestamp_utc / supersedes / priority / status / confidence / tags) - 6 schema invariants (at-most-one-active-per-canonical-key + monotone-timestamps-on-chain + retraction-leaves-trail + ...) - Canonical-key normalization rules (7 apply; 3 deliberately NOT applied to preserve distinctions) - Reconciliation pseudocode (group by canonical key, detect conflicts, follow supersession chains) - Conflict output format → CONTRIBUTOR-CONFLICTS.md rows - Rendering rules for CURRENT-<maintainer>.md + MEMORY.md - 5-phase incremental migration (schema adoption → generator prototype → mechanical backfill → cutover → LLM extraction) - CI integration hooks composing with rows #58, #59, #12 - Worked examples (MF-2026-04-23-001 "Aaron endorses deterministic reconciliation"; MF-2026-04-23-004 "Aaron grants full GitHub access") - 5 open questions for Phase 1 PR design decisions Composes with: - Otto-73 retractability-by-design foundation — MemoryFact status (active / superseded / retracted) is the retraction- native primitive at the memory substrate - PR #222 decision-proxy-evidence — consulted_memory_ids can now reference MemoryFact.id directly - PR #225 memory-reference-existence CI (row #59) — generated output preserves the invariant by construction - Zeta's ZSet algebra — MemoryFact records ARE Z-set entries at the memory layer; same primitive, different surface Addresses MEMORY.md cap-drift (Otto-70 snapshot-tool surfaced 58842 bytes vs. 24976-byte cap): a generated index can be bounded by construction (top-N most-recent, archive the rest). Not implementation. Research doc only. Downstream arc: schema adoption (S) → generator prototype off-CI (S-M) → mechanical backfill (M) → cutover with retractability (M) → LLM-assisted extraction (L research). Amara Determinize-stage: 3/5 (with this PR). ✓ Live-state-before-policy (PR #224) ✓ Memory reference-existence lint (PR #225) ✓ Memory reconciliation algorithm design (this PR) Remaining: - Generated CURRENT-*.md views (L; this doc's Phase 2) - Memory duplicate-title lint enforcement (partial via AceHack PR #12; graduates via batch-sync) Per Aaron Otto-73 retractability foundation: the design itself embodies the thesis — supersession + status + retraction make the memory layer's reconciliation deterministic, same primitive as Zeta's data layer. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 25, 2026
…ize L-effort item) Amara's 4th ferry (PR #221 absorb) centerpiece proposal: replace hand-maintained CURRENT-*.md distillations with generated views over typed memory facts. Her sketch was ~40 lines of Python; this is the design that downstream implementation follows. ~380 lines covering: - MemoryFact record schema (id / subject / predicate / object / source_kind / source_path / source_anchor / timestamp_utc / supersedes / priority / status / confidence / tags) - 6 schema invariants (at-most-one-active-per-canonical-key + monotone-timestamps-on-chain + retraction-leaves-trail + ...) - Canonical-key normalization rules (7 apply; 3 deliberately NOT applied to preserve distinctions) - Reconciliation pseudocode (group by canonical key, detect conflicts, follow supersession chains) - Conflict output format → CONTRIBUTOR-CONFLICTS.md rows - Rendering rules for CURRENT-<maintainer>.md + MEMORY.md - 5-phase incremental migration (schema adoption → generator prototype → mechanical backfill → cutover → LLM extraction) - CI integration hooks composing with rows #58, #59, #12 - Worked examples (MF-2026-04-23-001 "Aaron endorses deterministic reconciliation"; MF-2026-04-23-004 "Aaron grants full GitHub access") - 5 open questions for Phase 1 PR design decisions Composes with: - Otto-73 retractability-by-design foundation — MemoryFact status (active / superseded / retracted) is the retraction- native primitive at the memory substrate - PR #222 decision-proxy-evidence — consulted_memory_ids can now reference MemoryFact.id directly - PR #225 memory-reference-existence CI (row #59) — generated output preserves the invariant by construction - Zeta's ZSet algebra — MemoryFact records ARE Z-set entries at the memory layer; same primitive, different surface Addresses MEMORY.md cap-drift (Otto-70 snapshot-tool surfaced 58842 bytes vs. 24976-byte cap): a generated index can be bounded by construction (top-N most-recent, archive the rest). Not implementation. Research doc only. Downstream arc: schema adoption (S) → generator prototype off-CI (S-M) → mechanical backfill (M) → cutover with retractability (M) → LLM-assisted extraction (L research). Amara Determinize-stage: 3/5 (with this PR). ✓ Live-state-before-policy (PR #224) ✓ Memory reference-existence lint (PR #225) ✓ Memory reconciliation algorithm design (this PR) Remaining: - Generated CURRENT-*.md views (L; this doc's Phase 2) - Memory duplicate-title lint enforcement (partial via AceHack PR #12; graduates via batch-sync) Per Aaron Otto-73 retractability foundation: the design itself embodies the thesis — supersession + status + retraction make the memory layer's reconciliation deterministic, same primitive as Zeta's data layer. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
Apr 25, 2026
…e 3/5, L-effort design) (#226) * research: memory reconciliation algorithm — v0 design (Amara Determinize L-effort item) Amara's 4th ferry (PR #221 absorb) centerpiece proposal: replace hand-maintained CURRENT-*.md distillations with generated views over typed memory facts. Her sketch was ~40 lines of Python; this is the design that downstream implementation follows. ~380 lines covering: - MemoryFact record schema (id / subject / predicate / object / source_kind / source_path / source_anchor / timestamp_utc / supersedes / priority / status / confidence / tags) - 6 schema invariants (at-most-one-active-per-canonical-key + monotone-timestamps-on-chain + retraction-leaves-trail + ...) - Canonical-key normalization rules (7 apply; 3 deliberately NOT applied to preserve distinctions) - Reconciliation pseudocode (group by canonical key, detect conflicts, follow supersession chains) - Conflict output format → CONTRIBUTOR-CONFLICTS.md rows - Rendering rules for CURRENT-<maintainer>.md + MEMORY.md - 5-phase incremental migration (schema adoption → generator prototype → mechanical backfill → cutover → LLM extraction) - CI integration hooks composing with rows #58, #59, #12 - Worked examples (MF-2026-04-23-001 "Aaron endorses deterministic reconciliation"; MF-2026-04-23-004 "Aaron grants full GitHub access") - 5 open questions for Phase 1 PR design decisions Composes with: - Otto-73 retractability-by-design foundation — MemoryFact status (active / superseded / retracted) is the retraction- native primitive at the memory substrate - PR #222 decision-proxy-evidence — consulted_memory_ids can now reference MemoryFact.id directly - PR #225 memory-reference-existence CI (row #59) — generated output preserves the invariant by construction - Zeta's ZSet algebra — MemoryFact records ARE Z-set entries at the memory layer; same primitive, different surface Addresses MEMORY.md cap-drift (Otto-70 snapshot-tool surfaced 58842 bytes vs. 24976-byte cap): a generated index can be bounded by construction (top-N most-recent, archive the rest). Not implementation. Research doc only. Downstream arc: schema adoption (S) → generator prototype off-CI (S-M) → mechanical backfill (M) → cutover with retractability (M) → LLM-assisted extraction (L research). Amara Determinize-stage: 3/5 (with this PR). ✓ Live-state-before-policy (PR #224) ✓ Memory reference-existence lint (PR #225) ✓ Memory reconciliation algorithm design (this PR) Remaining: - Generated CURRENT-*.md views (L; this doc's Phase 2) - Memory duplicate-title lint enforcement (partial via AceHack PR #12; graduates via batch-sync) Per Aaron Otto-73 retractability foundation: the design itself embodies the thesis — supersession + status + retraction make the memory layer's reconciliation deterministic, same primitive as Zeta's data layer. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * drain(#226 P0+P1×2+P2×3 Codex): retraction semantics + cap consistency + smart-quote + pseudocode init + present-with-schema Six substantive Codex findings on memory-reconciliation algorithm doc: P0 (line 202) — retraction semantics inconsistency: reconcile() filtered by status == 'active' which masked the intent. Added explicit retraction-semantics docstring: - Facts transition via explicit FactRetracted / FactSuperseded events; never deleted, only marked. - reconcile() ignores retracted/superseded for liveness but STILL considers them when checking version-chain integrity. - Updated chain check to operate over ALL facts in the group (including retracted/superseded), not just active ones — chain integrity needs the full history. P1 (line 187) — stable fact identity vs grouping key: Distinguished fact ID (stable identity, unique) from (subject, predicate, canonical_key) grouping tuple (which multiple facts can share under invariant-2's collision case). Comment makes the distinction explicit. P1 (line 270) — MEMORY.md cap inconsistency: Default 30KB exceeded FACTORY-HYGIENE row #11 cap (24,976 bytes). Updated to 24,000 bytes — strictly under the hard cap with ~1KB headroom for header/annotation overhead. P2 (line 130) — smart-quote example ambiguous: Both sides showed plain ASCII ('"' / "'"). Replaced with explicit Unicode codepoint references (U+201C/D for double, U+2018/9 for single) so the rule is unambiguous in plain-ASCII source. P2 (line 186) — pseudocode by_key[k] used before init: Switched to defaultdict(list); added a comment noting the equivalence to 'if k not in by_key: by_key[k] = []' for non-Python implementers. P2 (line 216) — CONTRIBUTOR-CONFLICTS.md 'empty' wording: File is present and contains a schema; just unpopulated. Updated text to 'present-with-schema-but-unpopulated; this design starts populating it via the generator'. * drain(#226 P1+P2 Codex): chain-head liveness + chain-integrity for retired groups P1 (line 210) — chain-HEAD liveness, not 'any active in group': The reconcile filter marked a key live whenever any record in the group had status==active. That's wrong — a key with active(t=1) → retracted(t=2) has an earlier active record but the HEAD of the supersession chain is retracted, so the key is not live. Fix: `follow_supersession_to_head(group)` walks supersedes-pointers to find the most-recent record; liveness keyed on its status == active. P2 (line 224) — chain integrity for fully retired groups: The chain-integrity check looped over `accepted.items()`, which only included keys with at least one active record. Retired groups (all members retracted/superseded) could have broken chains and we'd silently miss them. Fix: loop over `by_key.items()` (all groups, including fully retired ones). Chain integrity is independent of liveness. --------- 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
Amara's 4th ferry (PR #221) Determinize-stage item landed: documents the "live-state-before-policy" rule explicitly in
docs/decision-proxy-evidence/README.md+ files BP-25 promotion candidacy as BACKLOG row for Aarav.What landed
docs/decision-proxy-evidence/README.md— new section between "Review block" and "Relationship to the hard rule", covering why / how / scope / exclusions / BP candidacydocs/BACKLOG.md— new P2 row "BP-25 promotion candidate — live-state-before-policy" for Aarav's considerationWhy
Per Amara:
The schema's
live_state_checks:field (PR #222) already enforces it per-record; this PR surfaces the principle explicitly so future authors see the rule, not just the field.Amara Determinize-stage progress
Acting under Otto-72 directive
Per Aaron Otto-72 ("don't wait on me approved, mark down your decisions"), this PR lands under the Otto-67 standing full-GitHub authority. BP-25 promotion decision is not made unilaterally — it's queued as BACKLOG for Aarav's ADR-driven promotion call.
Test plan
🤖 Generated with Claude Code