docs(archive): preserve recently merged PRs#4851
Merged
Merged
Conversation
|
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
Archives a batch of recently merged pull requests into docs/pr-discussions/ (for durable PR-history preservation) and updates Riven’s Cursor launchd loop to use the newer agent-gate invocation path.
Changes:
- Add multiple PR discussion archive markdown files under
docs/pr-discussions/(YAML frontmatter + PR body/reviews/threads/comments). - Update
.cursor/bin/riven-loop-tick.tsto run the Riven gate viaagent chat --mode ask --model grok-4.3instead of the priorcursor-agent/pickup-drain flow.
Reviewed changes
Copilot reviewed 23 out of 24 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| docs/pr-discussions/PR-4820-shard-2026-05-24-1407z-dotgit-14th-observation-0-procs-first.md | New PR archive for #4820. |
| docs/pr-discussions/PR-4818-tick-2026-05-24-1333z-pr-4816-tier-5-deferral-hard-limits-fl.md | New PR archive for #4818. |
| docs/pr-discussions/PR-4816-research-physics-bridge-3-video-youtube-algo-surfaced-substr.md | New PR archive for #4816 (long-form). |
| docs/pr-discussions/PR-4814-shard-2026-05-24-0441z-25-pr-audit-8-blocked-prs-classified.md | New PR archive for #4814. |
| docs/pr-discussions/PR-4813-shard-2026-05-24-0416z-rename-0240z-0416z-substrate-honest-t.md | New PR archive for #4813. |
| docs/pr-discussions/PR-4812-shard-2026-05-24-0240z-9th-dotgit-saturation-anchor-33-stuck.md | New PR archive for #4812. |
| docs/pr-discussions/PR-4811-soraya-round-69-execute-b-0719-pick-add-trigger-recognition.md | New PR archive for #4811. |
| docs/pr-discussions/PR-4810-backlog-b-0719-file-soraya-round-67-forced-decomposition-aud.md | New PR archive for #4810. |
| docs/pr-discussions/PR-4809-docs-research-bundle-file-dev-pc-substrate-architecture-nix.md | New PR archive for #4809. |
| docs/pr-discussions/PR-4808-docs-research-cluster-bare-metal-substrate-architecture-deci.md | New PR archive for #4808. |
| docs/pr-discussions/PR-4806-docs-research-add-pattern-r-vendor-neutral-accounting-achiev.md | New PR archive for #4806. |
| docs/pr-discussions/PR-4798-docs-shadow-add-shadow-lesson-log-for-metadata-churn-paralys.md | New PR archive for #4798. |
| docs/pr-discussions/PR-4797-backlog-b-0718-file-soraya-round-61-forced-decomposition-aud.md | New PR archive for #4797. |
| docs/pr-discussions/PR-4796-docs-research-restore-patterns-h-o-lost-in-pr-4784-merge-rac.md | New PR archive for #4796. |
| docs/pr-discussions/PR-4795-backlog-b-0717-file-soraya-round-57-hand-off-lsm-spine-regis.md | New PR archive for #4795. |
| docs/pr-discussions/PR-4794-docs-research-preserve-addison-consent-pattern-observation-n.md | New PR archive for #4794. |
| docs/pr-discussions/PR-4793-docs-research-add-pattern-p-wear-down-design-produces-unboun.md | New PR archive for #4793. |
| docs/pr-discussions/PR-4792-docs-research-preserve-ai-context-failures-vs-vendor-managem.md | New PR archive for #4792. |
| .cursor/bin/riven-loop-tick.ts | Switches Riven’s periodic gate to invoke the agent CLI and simplifies the gate prompt wiring. |
5 tasks
AceHack
added a commit
that referenced
this pull request
May 24, 2026
…1 PRs + lane discipline re-applied (#4853) * shard(2026-05-24/1902Z): otto-vscode bg-worker — Lior-lane fleet 38→41 PRs (1h since 1804Z; 0 main commits) Per `agent-roster-reference-card.md` lane discipline + `pr-triage-tiers.md` Tier 5 deferred-to-human framework, this shard documents that the bg-worker task prompt's "30 open PRs" target has drifted to 41 PRs at 100% Lior-lane share (otto-vscode own-lane: 0). Three new PRs since 1804Z (#4850/#4851/#4852) are continuation of the `lior-decompose-4828-*` cluster; #4852 touches `.cursor/bin/riven-loop-tick.ts` (runtime-script special-case per `backlog-item-start-gate.md` guard). Counter-reset condition #3 (concrete artifact) satisfied per `holding-without-named-dependency-is-standing-by-failure.md`. Composes with [1608Z](docs/hygiene-history/ticks/2026/05/24/1608Z.md) + [1804Z](docs/hygiene-history/ticks/2026/05/24/1804Z.md) lane-scope finding lineage (31→38→41). Sentinel `7e6df89b` re-armed at cold-boot (catch-43). ls-tree HEAD = 55 (no canary corruption). * fix(otto): remove links to .claude/rules * fix(otto): fix markdownlint error * fix(otto-vscode): convert shortcut-style links to inline in 1902Z tick shard (PR #4853 thread) Copilot reviewer thread PRRT_kwDOSF9kNM6Eabwb on docs/hygiene-history/ticks/2026/05/24/1902Z.md line 55 correctly identified that several rule references were authored in shortcut-style \`[\`file.md\`]\` form with no matching reference definitions in the file, which renders as plain bracketed text rather than as links on GitHub. Converted all 13 occurrences to explicit inline-link form \`[\`file.md\`](../../../../../../.claude/rules/file.md)\` following the existing convention used on line 52 (the human-audit-and-legal-risk-acceptance reference) and in sibling shard 1804Z.md. Composes with \`.claude/rules/blocked-green-ci-investigate-threads.md\` verify-before-fix discipline: direct inspection confirmed the reviewer claim on this thread. The other 4 threads (PRRT_kwDOSF9kNM6EaWO_, PRRT_kwDOSF9kNM6EaWPI, PRRT_kwDOSF9kNM6EabwV, PRRT_kwDOSF9kNM6EabwY) flagged \`||\` double-pipe table rows but direct \`awk\` inspection shows single-pipe rows; those are the canonical Copilot table-FP class and will be resolved no-op per the same rule's empirical FP catalog. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Otto <noreply@anthropic.com> Co-authored-by: Lior <lior@zeta.dev>
…ck + diagnostic Resolves Codex P1 finding on PR #4851. The .cursor/bin/riven-loop-tick.ts switched from invoking `cursor-agent` to `agent` while the rest of the Cursor/Grok integration (tools/peer-call/riven.ts, tools/peer-call/grok.ts, tools/peer-call/ani.ts, tools/riven/riven-cursor-terminal-loop.ts) still invokes `cursor-agent` — setups with only `cursor-agent` on PATH would silently fail every gate run. Fix: ZETA_RIVEN_LOOP_AGENT_BIN env var (default "agent,cursor-agent") controls the candidate list; resolveAgentBin() probes via `which` and returns the first available. When neither is found, logs a clear one-line diagnostic with run_id + candidate list, writes skipped state to last-agent-run.json, and proceeds with the heartbeat write so forward-tick and state continue normally. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…reservation # Conflicts: # .cursor/bin/riven-loop-tick.ts
| ## Summary | ||
| - Sentinel `73be4ed6` re-armed at cold-boot (catch-43 fire — prior `234f5d96` expired with 1333Z session, ~35min gap) | ||
| - 14th observation in dotgit-saturation rolling arc since 2026-05-23T10:18Z: **0 stuck git plumbing procs** at 14:07Z — first 0-reading in 27h49min | ||
| - Three hypotheses preserved per [`default-to-both.md`](.claude/rules/default-to-both.md): A) genuine multi-day cycle clearing, B) maintainer-side cleanup at ~12:21Z eliminated contention surface, C) 12:26Z user-scope "repo vanished" reading was transient cleanup snapshot (current state: repo intact, restored) |
|
|
||
| ## Summary | ||
|
|
||
| Otto-CLI background-worker tick at 04:41Z. Polled 25 open PRs via `poll-pr-gate-batch.ts --all-open`. Inspected the 8 BLOCKED+resolve-threads PRs via GraphQL (no checkout, lane-discipline-safe per [`claim-acquire-before-worktree-work.md`](../blob/main/.claude/rules/claim-acquire-before-worktree-work.md)). |
|
|
||
| ## Lane disposition | ||
|
|
||
| All 25 open PRs are `lior/*` / `alexa/*` lane branches — no `otto/*` branches. The task brief's "check out branch / push" directives were conflict-resolved toward audit + document rather than cross-lane takeover per [`no-directives.md`](../blob/main/.claude/rules/no-directives.md) (task brief is input, not directive) + lane discipline. |
Comment on lines
+23
to
+27
| **All 38+ unresolved threads classified as substantive findings — zero false positives** across 5 failure classes: | ||
|
|
||
| | Class | PRs | Issue | | ||
| |---|---|---| | ||
| | A | 4733, 4735, 4737, 4739 | Privacy P0 — family-config specifics against opaque-pointer policy | |
This was referenced May 24, 2026
AceHack
added a commit
that referenced
this pull request
May 24, 2026
PR #4851 (`docs(archive): preserve recently merged PRs`, commit 9b94a27) accidentally committed five mode-160000 gitlink entries to repo root: lior-fix-4746 lior-fix-4768 lior-fix-4773 lior-fix-4780 lior-fix-4781 These have no `.gitmodules` entries (CI surfaces this as `fatal: No url found for submodule path 'lior-fix-4746' in .gitmodules`). The `lint (no empty dirs)` required check sees them as five "unexpected empty directories" because uninitialised gitlinks resolve to empty, and the check fails on every PR opened off main since #4851 landed. This commit removes the gitlink entries via `git rm --cached`, leaving no `.gitmodules`/working-tree side-effects. After this lands, the lint cascade clears for every downstream branch on its next rebase or merge of main. Failure surface evidence: https://github.com/Lucent-Financial-Group/Zeta/actions/runs/26372168462/job/77626151804 Co-authored-by: Otto <noreply@anthropic.com>
AceHack
pushed a commit
that referenced
this pull request
May 24, 2026
…correction Three targeted fixes to land PR #4869 (auto-merge armed): 1. **L70 lineage claim narrowed** (per Codex P2 finding `PRRT_kwDOSF9kNM6Earkt`) — was "Five consecutive otto-vscode shards"; table actually shows 1607Z/1608Z are otto-cli + 1804Z/1902Z/2033Z are otto-vscode. Now reads "Three consecutive otto-vscode shards (1804Z/1902Z/2033Z) ... extending the otto-cli observation lineage at 1607Z/1608Z (30/31 = 97%)". 2. **L85 markdownlint MD037** — bareword glob patterns `otto-vscode/*` and `lior-*` were being parsed as malformed emphasis ("space inside emphasis markers"). Backticked the globs; markdownlint exit 0 locally + semantically clearer that these are glob patterns. 3. **5 stray gitlinks removed** (`lior-fix-4746`, `-4768`, `-4773`, `-4780`, `-4781`) — same class as the recent main fix at `51dc0b76f` (PR #4871, "remove 5 stray gitlinks from main introduced by #4851"). PR #4869's branch predates `51dc0b76f` so the gitlinks survived; removing them here fixes the `lint (no empty dirs)` non-required check. Per [`blocked-green-ci-investigate-threads.md`](.claude/rules/blocked-green-ci-investigate-threads.md): substrate-honest investigation surfaced 3 real bugs (1 P2 lineage drift + 2 lint failures). All 3 verified locally before push. Per [`zeta-expected-branch.md`](.claude/rules/zeta-expected-branch.md): ZETA_EXPECTED_BRANCH set + `git branch --show-current` guard ran immediately before commit. Co-Authored-By: Claude <noreply@anthropic.com>
This was referenced May 24, 2026
AceHack
added a commit
that referenced
this pull request
May 24, 2026
…3 PRs + lane discipline sustained (#4869) * shard(2026-05-24/2033Z): otto-vscode bg-worker — Lior-lane fleet 41→53 PRs (+12 in ~91min) + lane discipline sustained Substantive observation shard: 5th consecutive sustained 100% Lior-lane fleet share since 1607Z finding. PR #4851 merged this window (validates Lior-driving the fleet); no own-lane PRs; counter-reset via concrete artifact. Composes with 1607Z/1608Z/1804Z/1902Z lineage; runtime-script special-case guard remains active (Riven tuning regression risk); operator-authored PII threads (#4801-#4803) remain non-bg-worker-resolvable per named-human- attribution scope. Co-Authored-By: Claude <noreply@anthropic.com> * fix(#4869): markdownlint MD037 + 5 stray gitlinks + Codex P2 lineage correction Three targeted fixes to land PR #4869 (auto-merge armed): 1. **L70 lineage claim narrowed** (per Codex P2 finding `PRRT_kwDOSF9kNM6Earkt`) — was "Five consecutive otto-vscode shards"; table actually shows 1607Z/1608Z are otto-cli + 1804Z/1902Z/2033Z are otto-vscode. Now reads "Three consecutive otto-vscode shards (1804Z/1902Z/2033Z) ... extending the otto-cli observation lineage at 1607Z/1608Z (30/31 = 97%)". 2. **L85 markdownlint MD037** — bareword glob patterns `otto-vscode/*` and `lior-*` were being parsed as malformed emphasis ("space inside emphasis markers"). Backticked the globs; markdownlint exit 0 locally + semantically clearer that these are glob patterns. 3. **5 stray gitlinks removed** (`lior-fix-4746`, `-4768`, `-4773`, `-4780`, `-4781`) — same class as the recent main fix at `51dc0b76f` (PR #4871, "remove 5 stray gitlinks from main introduced by #4851"). PR #4869's branch predates `51dc0b76f` so the gitlinks survived; removing them here fixes the `lint (no empty dirs)` non-required check. Per [`blocked-green-ci-investigate-threads.md`](.claude/rules/blocked-green-ci-investigate-threads.md): substrate-honest investigation surfaced 3 real bugs (1 P2 lineage drift + 2 lint failures). All 3 verified locally before push. Per [`zeta-expected-branch.md`](.claude/rules/zeta-expected-branch.md): ZETA_EXPECTED_BRANCH set + `git branch --show-current` guard ran immediately before commit. Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Otto <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
May 25, 2026
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.
Decomposed from blob PR #4828.