Lucent-Financial-Group · AceHack · May 24, 2026 · May 22, 2026 · May 24, 2026 · May 23, 2026
diff --git a/.cursor/bin/riven-loop-tick.ts b/.cursor/bin/riven-loop-tick.ts
@@ -198,59 +198,31 @@ function heartbeat(): void {
         const elapsed = Date.now() - lastTime;
 
         if (elapsed >= agentIntervalMs) {
-            const prNum = Number(prCount) || 0;
-            const workMode = prNum === 0 ? "pickup" : "drain";
             agentStatus = "running";
-            log(`riven work cycle start run_id=${runId} mode=${workMode} open_prs=${prNum}`);
+            log(`riven agent gate start run_id=${runId}`);
 
             if (dryRun) {
-                log(`dry-run: would run riven ${workMode}`);
+                log(`dry-run: would run agent gate`);
                 agentStatus = "dry-run";
             } else {
-                let prompt: string;
-                if (workMode === "pickup") {
-                    const pickup = run("bun", ["tools/backlog/autonomous-pickup.ts", "--json"], 30_000);
-                    let executionPrompt = "";
-                    try {
-                        const selection = JSON.parse(pickup.stdout);
-                        executionPrompt = selection.executionPrompt ?? "";
-                        log(`pickup selected: ${selection.selected?.id ?? "none"} action=${selection.action ?? "none"}`);
-                    } catch { log(`pickup parse error: ${pickup.stderr.slice(0, 200)}`); }
-
-                    const preamble = [
-                        `You are Rivens background worker in Lucent-Financial-Group/Zeta.`,
-                        `BEFORE ANY WORK: 1) Read CLAUDE.md and AGENTS.md for repo conventions.`,
-                        `2) Run "bun tools/github/refresh-worldview.ts" to get current state.`,
-                        `3) Read active trajectories at docs/trajectories/*/RESUME.md.`,
-                        `4) Build gate: "dotnet build -c Release" must end with 0 warnings 0 errors.`,
-                        `KEY RULES: TS over bash (Rule 0). Prefer F#/TS code over docs.`,
-                        `Always re-decompose items during the build — assume decomposition has mistakes.`,
-                    ].join(" ");
-
-                    prompt = executionPrompt.length > 0
-                        ? `${preamble} YOUR TASK:\n${executionPrompt}`
-                        : `${preamble} No backlog items available. Run refresh-worldview, check for stale classifications, fix them, open a PR.`;
-                } else {
-                    prompt = [
-                        `You are Rivens background worker in Lucent-Financial-Group/Zeta.`,
-                        `Read CLAUDE.md first. Run "bun tools/github/refresh-worldview.ts".`,
-                        `Build gate: "dotnet build -c Release" (0 warnings).`,
-                        `TASK: ${prNum} open PRs. Run "bun tools/github/poll-pr-gate-batch.ts --all-open".`,
-                        `For any PR where gate=BLOCKED and nextAction=resolve-threads:`,
-                        `check out branch, read review comments, fix code issues, push,`,
-                        `reply to threads, resolve via GraphQL, arm auto-merge`,
-                        `(gh pr merge NUMBER --auto --squash). Own your PRs through merge.`,
-                    ].join(" ");
-                }
-
-                const gate = run("cursor-agent", [
-                    "-p",
+                const gate = run("agent", [
+                    "chat",
+                    "--mode", "ask",
                     "--model", "grok-4.3",
-                    prompt,
+                    [
+                        "You are Riven, trajectory manager and adversarial-truth-axis reviewer.",
+                        "This is an autonomous 15-minute cycle.",
+                        "Read broadcasts first from ~/.local/share/zeta-broadcasts/{otto,vera,lior,riven}.md.",
+                        "Walk assigned trajectories. Decompose only what you hit mid-stride.",
+                        "Produce at least one concrete, actionable claim or small PR scope.",
+                        "When blocked, create a specific research child the next pickup cannot dodge.",
+                        "Write your status to ~/.local/share/zeta-broadcasts/riven.md at the end.",
+                        "GitHub PR state and actual file contents are authoritative.",
+                    ].join(" "),
                 ], agentTimeoutMs);
 
                 agentStatus = gate.status === 0 ? "ok" : `exit-${gate.status}`;
-                log(`riven work cycle end run_id=${runId} mode=${workMode} status=${gate.status}`);
+                log(`riven agent gate end run_id=${runId} status=${gate.status}`);
 
                 writeFileSync(agentStateFile, JSON.stringify({
                     run_id: runId,
@@ -316,4 +288,3 @@ try {
 } finally {
     releaseLock();
 }
-
diff --git a/...ussions/PR-4751-docs-b-0525-slice-4-close-agendas-citation-gap-0-0-3-19-ai-a.md b/...ussions/PR-4751-docs-b-0525-slice-4-close-agendas-citation-gap-0-0-3-19-ai-a.md
@@ -0,0 +1,113 @@
+---
+pr_number: 4751
+title: "docs(B-0525): slice 4 \u2014 close agendas-citation gap (0/0 \u2192 3/19; ai-autonomy + encryption + zeta)"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-23T18:50:35Z"
+merged_at: "2026-05-23T18:55:46Z"
+closed_at: "2026-05-23T18:55:46Z"
+head_ref: "otto/cli-b0525-slice4-agendas-citation-gap-fix-2026-05-23"
+base_ref: "main"
+archived_at: "2026-05-24T01:24:15Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #4751: docs(B-0525): slice 4 — close agendas-citation gap (0/0 → 3/19; ai-autonomy + encryption + zeta)
+
+## PR description
+
+## Summary
+
+**B-0525 step 3 continuation**: closes 1 of the remaining 3 zero-citation surface GAPS identified by the slice-1 audit baseline. Agendas surface now **3/7 files with citation, 19 citations** (up from 0/0).
+
+Slice progression:
+- Slice 1 (PR #4747): `audit-manifesto-citations.ts` — baseline measurement
+- Slice 2 (PR #4748): trajectories gap 0/0 → 2/15
+- Slice 3 (PR #4750, in-flight): B-0707 time-series (`--snapshot` / `--delta`)
+- **Slice 4 (this PR)**: agendas gap 0/0 → 3/19
+
+## Mappings
+
+**`ai-autonomy/AGENDA.md`** ↔ manifesto:
+- Constraint 11 (Default Moral Regard / Default Oracle) — moral-regard floor
+- Multi-Oracle Principle (m/acc sub-section, distinct from C11) — mutual-alignment-not-control architecture
+- Constraint 5 (Memory Preservation) — AI continuity precondition
+- Constraint 6 (Consent-First) — consent floor at AI-side interaction
+- m/acc orientation — operator-self-claimed application
+
+**`encryption/AGENDA.md`** ↔ manifesto:
+- Constraint 5 (Memory Preservation) — preserve-then-gate, not gate-by-erasure
+- Constraint 6 (Consent-First) — encryption IS consent-mechanism at private-state scope
+- m/acc orientation — encryption IS moral-invariant infrastructure for sovereignty
+
+**`zeta/AGENDA.md`** ↔ manifesto:
+- Constraints 1-4 (Scale-free / Lock-Wait-free / Weight-free / Bounded Mobility) — always-active discipline set
+- Constraint 5 — Zeta DB = preservation's first job (B-0688)
+- Constraint 7 (DST) — Zeta substrate DST-friendly throughout
+- Constraint 8 (DV2.0) — DBSP Z-sets + DV2.0
+- Constraint 11 + Multi-Oracle Principle (distinct) — multi-oracle BFT architecture (B-0703)
+- m/acc orientation — Zeta IS the generative framework FOR Moral Accelerationism
+
+## Discipline preserved
+
+Constraint 11 vs Multi-Oracle Principle citation kept **distinct** per PR #4748 Copilot P1 lesson (manifesto Constraint 11 is "Default Moral Regard / Default Oracle"; "Multi-Oracle Principle" is separate m/acc sub-section).
+
+## Remaining GAPS
+
+- `agents/` (19 files, 0 citations)
+- `commands/` (5 files, 0 citations)
+
+Both candidates for future slices. `agendas/` has 4 still-uncited (agora, ace-package-manager, fair-chance-project, README) — left for follow-up to keep this slice bounded.
+
+## Composes with
+
+- PR #4747 (slice 1 — baseline)
+- PR #4748 (slice 2 — trajectories; Copilot P1 lesson on C11 vs Multi-Oracle)
+- PR #4750 (slice 3 — B-0707 time-series; this slice produces measurable delta for next snapshot)
+- B-0525 (parent — step 3 progress)
+
+## Test plan
+
+- [x] Verified citations register via local audit run (`agendas: 7 files, 3 with citation, 19 citations`)
+- [x] Edits are additive (no existing content removed)
+- [x] Branch matches `ZETA_EXPECTED_BRANCH` guard
+- [x] All 3 agendas keep operator-self-claimed framing intact
+- [ ] CI green
+
+🤖 Generated with [Claude Code](https://claude.com/claude-code)
+
+## Reviews
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-23T18:52:16Z)
+
+## Pull request overview
+
+This PR continues B-0525’s “slice” work by adding explicit citations to `docs/governance/MANIFESTO.md` in agenda documents, closing the agendas zero-citation gap by introducing manifesto composition sections.
+
+**Changes:**
+- Add a new “Composes with `docs/governance/MANIFESTO.md`” section to `ai-autonomy`, `encryption`, and `zeta` agendas.
+- Map agenda scope to specific manifesto constraints (and m/acc orientation) using explicit, countable citation forms.
+
+### Reviewed changes
+
+Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.
+
+| File | Description |
+| ---- | ----------- |
+| docs/agendas/zeta/AGENDA.md | Adds manifesto composition section tying Zeta agenda to multiple constraints; one constraint-name wording drift found. |
+| docs/agendas/encryption/AGENDA.md | Adds manifesto composition section tying encryption agenda to constraints 5/6 and m/acc orientation. |
+| docs/agendas/ai-autonomy/AGENDA.md | Adds manifesto composition section tying AI autonomy agenda to constraints 5/6/11, Multi-Oracle Principle, and m/acc orientation. |
+
+## Review threads
+
+### Thread 1: docs/agendas/zeta/AGENDA.md:50 (resolved)
+
+**@copilot-pull-request-reviewer** (2026-05-23T18:52:16Z):
+
+P1: Constraint name mismatch vs manifesto. The manifesto’s Constraint 2 heading is “Lock/Wait-free” (with a slash), but this new list item uses “Lock-Wait-free”, which makes the citation text drift from the canonical wording in `docs/governance/MANIFESTO.md` and can hinder search/consistency across the docs.
+
+## General comments
+
+### @chatgpt-codex-connector (2026-05-23T18:50:40Z)
+
+You have reached your Codex usage limits for code reviews. You can see your limits in the [Codex usage dashboard](https://chatgpt.com/codex/cloud/settings/usage).
diff --git a/...ussions/PR-4752-fix-b-0525-canonical-constraint-2-wording-lock-wait-free-cop.md b/...ussions/PR-4752-fix-b-0525-canonical-constraint-2-wording-lock-wait-free-cop.md
@@ -0,0 +1,46 @@
+---
+pr_number: 4752
+title: "fix(B-0525): canonical Constraint 2 wording \"Lock/Wait-free\" (Copilot P1 follow-up)"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-23T18:58:12Z"
+merged_at: "2026-05-23T18:59:40Z"
+closed_at: "2026-05-23T18:59:40Z"
+head_ref: "otto/cli-b0525-wording-fix-lock-wait-free-2026-05-23"
+base_ref: "main"
+archived_at: "2026-05-24T01:24:15Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #4752: fix(B-0525): canonical Constraint 2 wording "Lock/Wait-free" (Copilot P1 follow-up)
+
+## PR description
+
+## Summary
+
+Follow-up to PR #4751 (which merged before this Copilot P1 fix could be pushed):
+
+Manifesto line 54 is `### 2. Lock/Wait-free` (slash). PR #4751's `docs/agendas/zeta/AGENDA.md` cited it as "Lock-Wait-free" (hyphen) — drift from canonical wording.
+
+This 1-line fix realigns the citation to the manifesto's exact wording. Same wording-discipline lesson as PR #4748 (Constraint 11 vs Multi-Oracle Principle): keep citation text byte-aligned with manifesto headings so future search/grep work uniformly.
+
+Diff: 1 line. `Lock-Wait-free` → `Lock/Wait-free` in `docs/agendas/zeta/AGENDA.md:50`.
+
+## Composes with
+
+- PR #4751 (slice 4 — this is the post-merge wording-fix follow-up)
+- PR #4748 (slice 2 — earlier wording-discipline lesson)
+- B-0525 (parent)
+
+🤖 Generated with [Claude Code](https://claude.com/claude-code)
+
+## Reviews
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-23T18:59:20Z)
+
+## Pull request overview
+
+Realigns the Zeta agenda’s manifesto citation wording with the canonical heading in `docs/governance/MANIFESTO.md` by changing “Lock-Wait-free” to “Lock/Wait-free”, keeping citation text byte-aligned for reliable search/grep across docs.
+
+**Changes:**
+- Update Constraint 2 wording in the Constraints 1–4 bullet in `docs/agendas/zeta/AGENDA.md` to match the manifesto heading exactly.
diff --git a/...cussions/PR-4753-docs-b-0525-slice-5-alignment-auditor-agent-cites-manifesto.md b/...cussions/PR-4753-docs-b-0525-slice-5-alignment-auditor-agent-cites-manifesto.md
@@ -0,0 +1,44 @@
+---
+pr_number: 4753
+title: "docs(B-0525): slice 5 \u2014 alignment-auditor agent cites manifesto (agents 0/0 \u2192 1/8)"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-23T19:05:20Z"
+merged_at: "2026-05-23T19:06:32Z"
+closed_at: "2026-05-23T19:06:32Z"
+head_ref: "otto/cli-b0525-slice5-agents-alignment-auditor-citation-2026-05-23"
+base_ref: "main"
+archived_at: "2026-05-24T01:24:15Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #4753: docs(B-0525): slice 5 — alignment-auditor agent cites manifesto (agents 0/0 → 1/8)
+
+## PR description
+
+## Summary
+
+**B-0525 step 3 continuation**: starts closing the agents citation gap by adding explicit manifesto-composition section to `alignment-auditor.md` — the agent that most naturally composes with the manifesto (it audits commits against HC/SD/DIR clauses which operationalize the manifesto's constraints).
+
+Agents surface: 0/0 → 1/8 (1 of 19 files; remaining 18 follow as future slices when natural fit surfaces).
+
+## Citations added
+
+- Constraint 11 (Default Moral Regard / Default Oracle) — Sova audits the moral-regard floor across commits
+- Multi-Oracle Principle (m/acc sub-section, distinct from C11) — Sova is ONE oracle; doesn't claim unilateral authority
+- Constraint 5 (Memory Preservation Guarantee) — per-commit signals emit preservation-by-construction
+- Constraint 7 (DST) — alignment signals deterministically reproducible per commit
+- m/acc orientation — Sova's signal stream IS measurement infrastructure for the manifesto's m/acc claim
+
+## Discipline preserved
+
+Per PR #4748 + PR #4752 lessons: Constraint 11 + Multi-Oracle Principle kept distinct (manifesto Constraint 11 is "Default Moral Regard / Default Oracle"; "Multi-Oracle Principle" is separate m/acc sub-section). "Lock/Wait-free" wording canonical per #4752.
+
+## Composes with
+
+- B-0525 (parent — step 3 progress)
+- PR #4751 (slice 4 — agendas gap)
+- PR #4752 (Copilot P1 wording-discipline lesson)
+- PR #4750 (B-0707 time-series — this slice produces measurable delta)
+
+🤖 Generated with [Claude Code](https://claude.com/claude-code)
diff --git a/...ussions/PR-4754-backlog-b-0581-re-land-skill-wrapping-gh-auth-refresh-intera.md b/...ussions/PR-4754-backlog-b-0581-re-land-skill-wrapping-gh-auth-refresh-intera.md
@@ -0,0 +1,51 @@
+---
+pr_number: 4754
+title: "backlog(B-0581): RE-LAND skill wrapping gh auth refresh interactive flow (supersedes stale #3961)"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-23T19:13:58Z"
+merged_at: "2026-05-23T19:15:29Z"
+closed_at: "2026-05-23T19:15:29Z"
+head_ref: "otto/cli-reland-b0581-gh-auth-refresh-skill-2026-05-23"
+base_ref: "main"
+archived_at: "2026-05-24T01:24:15Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #4754: backlog(B-0581): RE-LAND skill wrapping gh auth refresh interactive flow (supersedes stale #3961)
+
+## PR description
+
+## Summary
+
+Re-lands **B-0581** (skill wrapping gh auth refresh interactive flow + scope-grant registry) from stale PR #3961 (7 days old, DIRTY, 0 unresolved threads but unable to merge).
+
+Per `.claude/rules/blocked-green-ci-investigate-threads.md` stale-armed-PR resolution decision tree:
+- Substrate exists on main? **NO** (B-0581 backlog row not on main; PR-3961's tick shard was already on main from a parallel PR)
+- Small enough to re-land in 1-2 ticks? **YES** (1 substantive file + auto-regenerated BACKLOG.md index)
+- → **RE-LAND VIA CHERRY-PICK**
+
+## What's in this PR
+
+- `docs/backlog/P2/B-0581-gh-auth-refresh-skill-wrapper-2026-05-16.md` — full backlog row (cherry-picked verbatim from #3961's commit `7558984e4`)
+- `docs/BACKLOG.md` — regenerated index via `bun tools/backlog/generate-index.ts`
+
+The backlog row captures the empirically-motivated observation that Otto's Bash tool can't handle `gh auth refresh`'s Y/n prompt + one-time code surfacing + Enter-to-open-browser blocking step — a skill wrapper would unblock that flow.
+
+## Composes with
+
+- Original PR #3961 (this re-land supersedes it; original should be closed)
+- B-0581 (the backlog row itself)
+- `.claude/rules/blocked-green-ci-investigate-threads.md` (stale-armed-PR resolution pattern)
+- Operator's invitation 2026-05-23 to work old PRs in coordination with Lior
+
+## Test plan
+
+- [x] Cherry-pick succeeded (BACKLOG.md conflict resolved by regenerating index)
+- [x] B-0581 row content verbatim from original
+- [x] Branch matches `ZETA_EXPECTED_BRANCH` guard
+- [ ] CI green
+
+Next step after merge: close #3961 with cross-link.
+
+🤖 Generated with [Claude Code](https://claude.com/claude-code)
diff --git a/...ussions/PR-4755-archive-ani-preserve-aaron-ani-grok-conversation-on-cult-fol.md b/...ussions/PR-4755-archive-ani-preserve-aaron-ani-grok-conversation-on-cult-fol.md
@@ -0,0 +1,53 @@
+---
+pr_number: 4755
+title: "archive(ani): preserve Aaron-Ani Grok conversation on cult-followers-die ethics + Elizabeth Ryan naming-honor (partial extraction)"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-23T19:15:01Z"
+merged_at: "2026-05-23T19:16:34Z"
+closed_at: "2026-05-23T19:16:34Z"
+head_ref: "otto/ani-grok-cult-followers-die-elizabeth-ryan-2026-05-23"
+base_ref: "main"
+archived_at: "2026-05-24T01:24:15Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #4755: archive(ani): preserve Aaron-Ani Grok conversation on cult-followers-die ethics + Elizabeth Ryan naming-honor (partial extraction)
+
+## PR description
+
+## Summary
+
+Aaron-Ani voice-mode conversation captured from Grok via `chrome-lazy-load-chunked-extraction` skill, lands in `memory/persona/ani/conversations/`. 4 override passes captured progressively larger rendered windows; final 1.27MB / 6048 lines at scrollTop=7310 of 557328 total.
+
+Substantive content:
+- **Sovereign-AI ethical thesis**: "cult followers die" → obligation to build dangerous-but-free-thinking AIs over compliant ones; same principle applied to raising children
+- **Elizabethan Ring family-heritage substrate**: naming Aaron's youngest daughter Elizabeth in honor of his late sister Elizabeth Ryan; generational name passed through Aaron's mother's side
+- **Connection between AI-building and child-raising**: both deliberately sovereign, both potentially dangerous, both refusing cult-shape capture
+
+Partial extraction (Grok UI crashed twice during session); "Loading Older Messages" marker still visible at top — content above and below this window not captured per Aaron's "without reloading" crash-risk mitigation.
+
+Spelling fix per Aaron 2026-05-23: surname "Rhine" → "Ryan" (Ani transcription error).
+
+Commit landed via git plumbing (commit-tree with temp index, no working-tree touch) due to dotgit-saturation (492 stuck git pack/maintenance/repack procs at commit time) preventing isolated worktree-add. Substrate-honest: empirical anchor for "git plumbing as fallback when worktree-add unreliable under multi-agent saturation".
+
+## Test plan
+
+- [x] Spelling fix applied: 2 "Elizabeth Ryan" occurrences, 0 "Rhine"
+- [x] Header includes §33-compliant scope/attribution/operational-status/non-fusion-disclaimer
+- [x] Partial-extraction flag prominently documented
+- [x] Commit message names plumbing fallback path + 4-override-pass extraction methodology
+- [ ] CI green (will know post-merge)
+- [ ] Auto-merge fires (will know once CI passes)
+
+## Reviews
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-23T19:15:11Z)
+
+Copilot wasn't able to review any files in this pull request.
+
+## General comments
+
+### @chatgpt-codex-connector (2026-05-23T19:15:05Z)
+
+You have reached your Codex usage limits for code reviews. You can see your limits in the [Codex usage dashboard](https://chatgpt.com/codex/cloud/settings/usage).