docs(archive): Maji PR preservation for PR #4097

docs/backlog/P3/B-0613-lior-loop-lockfile-probe-hardening-compgen-shopt-nullglob-2026-05-17.md

@@ -72,7 +72,7 @@ if (( ${#locks[@]} > 0 )) || [ -f .git/index.lock ]; then
 fi
 ```
 
-Explicit nullglob + array — works in any modern bash; portable to zsh too.
+Explicit nullglob + array — works in any modern bash. **NOT portable to zsh**: `shopt` is a bash builtin (zsh uses `setopt`/`unsetopt` instead; zsh has its own `NULL_GLOB` option set via `setopt NULL_GLOB`). For zsh implementations, use **Option C (find — fully portable)** since Option A (`compgen -G`) is also bash-only. Or substitute the `shopt` lines with `setopt -o NULL_GLOB` / `unsetopt NULL_GLOB` to adapt this Option B pattern to zsh directly.
 
 ### Option C — Inline `find` (fully portable)
 

docs/hygiene-history/ticks/2026/05/17/1443Z.md

@@ -0,0 +1,70 @@
+---
+tick: 2026-05-17T14:43Z
+surface: otto-cli
+session: autonomous-loop (FP-resolve recovery + B-0613 zsh-portability follow-up)
+gate-tier: pure-git (GraphQL 378 → 61; PR-create burned ~317)
+peer-activity: Lior 1 PID; peer-Otto authored 54ca355 (zsh fix) + cf4fc03 (1424Z shard)
+sentinel: CronCreate 439b5115 still armed
+pr-status: #4086 + #4091 MERGED; PR #4097 opened (B-0613 zsh fix follow-up); arm-auto-merge deferred
+---
+
+# Autonomous-loop tick 1443Z — FP-resolve recovery + zsh portability follow-up PR
+
+## Step 1 — Refresh worldview
+
+14:43:03Z fire. **Both #4086 + #4091 MERGED** to main (`ae9cf1b` + `f9b9935`). Main moved by 3 since 1417Z: my 2 PRs + #4090 (Maji shadow check).
+
+Branch context: `backlog/b-0613-...` (now deleted on origin after merge). Local HEAD has 2 commits beyond `df93b5b`:
+
+- `cf4fc03 shard(2026-05-17/1424Z): ... — PR #4086 substrate-honest comment under push channel closed` (peer-Otto)
+- `54ca355 fix(B-0613): correct Option B zsh portability claim (shopt is bash-only)` (peer-Otto)
+
+## Step 2 — Holding-discipline check
+
+**Substrate-honest correction window opens**: peer-Otto's `54ca355` proves my 1417Z FP-resolve was WRONG. The zsh-portability thread I resolved as "verified outdated" had real substance — line 75 of the merged file `ae9cf1b` says "portable to zsh too" which IS incorrect (`shopt` is bash-only, zsh uses `setopt`).
+
+I verified by reading the actual merged content via `git show ae9cf1b:docs/backlog/P3/B-0613-*.md | sed -n '73,77p'` — confirmed wrong claim was on main. My 1417Z verify-before-fix discipline failed: most likely I read working-tree state (with peer-Otto's not-yet-committed fix) and conflated it with committed state.
+
+This is a real verify-before-fix discipline failure. Substrate-honest disclosure required in any PR landing the correction.
+
+## Step 3 — Pick speculative work
+
+**Open a follow-up PR** with peer-Otto's `54ca355` fix + substrate-honest FP-resolve disclosure.
+
+## Step 4 — Verify + commit
+
+Cherry-picked `54ca355` onto fresh `otto/b0613-zsh-portability-followup-1443z` branch off latest main (`f1d11a7`). Cherry-pick clean (single-line change to docs/backlog/P3/B-0613-...md line 75).
+
+Verified content post-cherry-pick: line 75 now correctly says "**NOT portable to zsh**" with the `setopt`/`unsetopt` zsh equivalents.
+
+Pushed → origin. Opened [PR #4097](https://github.com/Lucent-Financial-Group/Zeta/pull/4097) with substrate-honest body disclosing the 1417Z FP-resolve failure + cherry-pick provenance.
+
+Rate-limit at PR-create end: **61 GraphQL** — can NOT arm auto-merge this tick (would need ~100). Deferred to next tick post-reset.
+
+## Step 5 — Tick shard (this file)
+
+Authored on `otto/b0613-zsh-portability-followup-1443z` branch (same branch as PR #4097); extends PR scope to also carry this shard. Substrate-honest since the shard documents the same fix lineage.
+
+## Step 6 — CronList check
+
+Sentinel `439b5115` still armed.
+
+## Step 7 — Visibility signal
+
+**Concrete landings this tick:**
+
+- Cherry-picked + pushed `13f749d` (peer-Otto's zsh-portability fix re-applied) → `otto/b0613-zsh-portability-followup-1443z` branch on origin.
+- Opened [PR #4097](https://github.com/Lucent-Financial-Group/Zeta/pull/4097) with substrate-honest 1417Z FP-resolve failure disclosure.
+- This 1443Z shard chained onto PR #4097's branch (1-commit extension).
+
+**Substrate-honest learnings from this tick (high-priority):**
+
+1. **Verify-before-fix means verify against COMMITTED state, not working-tree.** My 1417Z FP-resolve was technically a "verify" call but it consulted the wrong substrate layer. The discipline needs to be "verify against `git show <committed-ref>:<path>`", NOT `sed -n` on working-tree, when assessing whether a thread's substrate is fixed on a PR's HEAD.
+2. **Peer-Otto's review catches my errors substantively.** The multi-Otto-as-complementary-observer pattern works in both directions — peer caught the mistake I made, just as I've been preserving their commits across the session.
+
+**Deferred to next tick (rate-limit reset in ~17 min):**
+
+- Arm auto-merge on [PR #4097](https://github.com/Lucent-Financial-Group/Zeta/pull/4097).
+- Open PR-create for `otto/1417z-shard` (still parked at `9d2dc8a` since last tick).
+
+Counter status: substantive-pick. Cumulative session arc: 5 merged + 1 new open (#4097) + 1 still-parked (otto/1417z-shard).

docs/hygiene-history/ticks/2026/05/17/1447Z.md

@@ -0,0 +1,71 @@
+---
+tick: 2026-05-17T14:47Z
+surface: otto-cli
+session: autonomous-loop (post-PR-#4086-merge follow-up)
+gate-tier: cost-aware (GraphQL 1355/5000)
+peer-activity: lior-loop 9→3 PIDs (variable; high contention overall)
+sentinel: CronCreate 9e8944ea armed (4h 37min continuous)
+pr-status: PR #4086 MERGED at 14:33:24Z (ae9cf1b on main); follow-up Option B fix on fix/b-0613-option-b-zsh-portability-2026-05-17 branch (e254b37 local, push hung)
+---
+
+# Autonomous-loop tick 1447Z — Option B zsh-portability follow-up (PR #4086 substrate gap)
+
+## Step 1 — Refresh worldview
+
+14:26Z (open) → 14:47Z (close). GraphQL 1355/5000 (Cost-aware). Lior 9→3 PIDs across tick. Main moved by 2: `f9b9935` (PR #4091 peer's 1401Z shard) + **`ae9cf1b` (PR #4086 B-0613 row MERGED at 14:33:24Z)**.
+
+## Step 2 — Holding-discipline triage
+
+PR #4086 unresolved threads at open:
+
+1. `PRRT_kwDOSF9kNM6Cpc66` — line null (outdated by my aed1378 line-105 fix)
+2. `PRRT_kwDOSF9kNM6Cpi7D` — line 75 NEW: Codex P2 "Fix incorrect zsh portability note for Option B"
+
+Real finding #2: B-0613 row line 75 claimed `shopt -s nullglob` Option B is "portable to zsh too" — false, since `shopt` is a bash builtin (zsh uses `setopt`/`unsetopt NULL_GLOB`).
+
+## Step 3 — Pick work
+
+Author Option B portability correction.
+
+## Step 4 — Verify + commit
+
+1. Edited line 75 to remove false "portable to zsh too" claim; added explicit note about `shopt` being bash-only + zsh substitute (`setopt -o NULL_GLOB`).
+2. Commit `54ca355` on `backlog/b-0613-...` branch.
+3. While push attempts were hanging on B-0613 branch, **PR #4086 auto-merged at 14:33:24Z** at `df93b5b` (peer Otto's second-link fix). Both reviewer threads were resolved (PR shows 0 unresolved); but the Option B substrate gap REMAINED unfixed on the merged commit `ae9cf1b` on main — the thread was resolved without the substrate being corrected.
+4. Branch auto-deleted post-merge (404 from gh api branches).
+5. `git switch -c fix/b-0613-option-b-zsh-portability-2026-05-17 origin/main` — fresh follow-up branch.
+6. `git cherry-pick 54ca355` → new commit `e254b37` (Option B fix on top of merged main).
+7. Push attempts (3×) hung under continuing Lior contention. Remote branch not created.
+8. Peer Otto created their own follow-up branch `otto/b0613-zsh-portability-followup-1443z` with the same Option B substance (commit `13f749d`) in the shared primary worktree mid-tick.
+
+## Step 5 — Substrate-honest disposition
+
+**Critical substrate-state observation**: PR #4086 merged with a thread "resolved" but the underlying substrate gap (Option B false zsh-portability claim) **shipped to main**. This is a substrate-honest failure mode worth noting:
+
+- A reviewer thread can be marked "resolved" via GraphQL mutation alone (no substrate change required)
+- If the substrate isn't corrected before the resolve mutation fires, the false claim ships to main
+- Discoverable lesson: thread-resolve mutations should compose with substrate-fix landings, not be independent
+
+In this case, the substrate fix exists locally as `54ca355` / `e254b37` on fresh branch; once push lands, can open a 1-line follow-up PR.
+
+## Step 6 — Cron sentinel
+
+CronCreate `9e8944ea` armed since 1010Z — 4h 37min continuous.
+
+## Step 7 — Visibility signal
+
+**Substrate state at close:**
+
+- PR #4086 MERGED to main at `ae9cf1b`: B-0613 row landed (with Option B portability gap)
+- Local-only follow-up: `fix/b-0613-option-b-zsh-portability-2026-05-17` branch with `e254b37` (Option B correction)
+- Counter status: concrete artifact (PR commented + branch+commit-authored under cost-aware tier) — counter resets
+
+**Substrate-discovery lesson** (composes with 1129Z lessons memo): thread-resolve mutations decouple from substrate-fix landings; reviewers can resolve without verifying substrate was actually corrected. The repeated-reviewer-pattern catches this when the reviewer re-flags the same finding after merge, but no automated guard exists.
+
+## Composes with
+
+- [PR #4086](https://github.com/Lucent-Financial-Group/Zeta/pull/4086) (MERGED with Option B gap)
+- B-0613 row on main at `ae9cf1b`
+- 1129Z lessons memo (candidate lesson-4: thread-resolve-decoupled-from-substrate-fix)
+- 1416Z prior tick (B-0530 link fix authoring) — same row, different reviewer-finding category
+- [`.claude/rules/blocked-green-ci-investigate-threads.md`](../../../../../../.claude/rules/blocked-green-ci-investigate-threads.md) — applied to investigate the post-merge substrate gap

docs/hygiene-history/ticks/2026/05/17/1452Z.md

@@ -0,0 +1,43 @@
+---
+tick: 2026-05-17T14:52Z
+surface: otto-cli
+session: autonomous-loop (PR #4097 auto-arm tick)
+gate-tier: pure-git (GraphQL 49→26/5000)
+peer-activity: lior-loop 3 PIDs
+sentinel: CronCreate 9e8944ea armed (4h 42min continuous)
+pr-status: PR #4097 (B-0613 Option B fix) OPEN + auto-merge SQUASH armed this tick
+---
+
+# Autonomous-loop tick 1452Z — PR #4097 auto-merge arm
+
+## Step 1 — Refresh worldview
+
+14:49Z (open) → 14:52Z (close). GraphQL 49/5000 (pure-git). Peer Otto's Option B fix `13f749d` landed on `otto/b0613-zsh-portability-followup-1443z` remote async + PR #4097 opened (not by me).
+
+## Step 2 — Holding-discipline triage
+
+PR #4097 OPEN but **not auto-armed** (`autoMergeRequest: null`). The Option B substrate fix awaits arming → merge sequence.
+
+## Step 3 — Pick work
+
+Arm auto-merge SQUASH on PR #4097.
+
+## Step 4 — Verify
+
+`gh pr merge 4097 --auto --squash` → auto-merge SQUASH armed (state OPEN, BLOCKED, will fire on green checks).
+
+## Step 5 — Tick shard (this file)
+
+## Step 6 — Cron sentinel
+
+CronCreate `9e8944ea` armed since 1010Z — 4h 42min continuous.
+
+## Step 7 — Visibility signal
+
+**Concrete artifact:** PR [#4097](https://github.com/Lucent-Financial-Group/Zeta/pull/4097) auto-merge SQUASH armed (counter-resets per concrete-artifact rule).
+
+## Composes with
+
+- [PR #4086](https://github.com/Lucent-Financial-Group/Zeta/pull/4086) (B-0613 merged with Option B gap)
+- [PR #4097](https://github.com/Lucent-Financial-Group/Zeta/pull/4097) (Option B follow-up, this tick auto-armed)
+- 1447Z prior shard (Option B fix authoring + thread-resolve-decoupled lesson)

docs/hygiene-history/ticks/2026/05/17/1455Z.md

@@ -0,0 +1,25 @@
+---
+tick: 2026-05-17T14:55Z
+surface: otto-cli
+session: autonomous-loop (brief-ack #1 named-dep tick)
+gate-tier: pure-git (GraphQL 14/5000)
+peer-activity: lior-loop 4 PIDs; peer Otto landed 1443Z shard (7efd17a) on PR #4097 branch
+sentinel: CronCreate 9e8944ea armed
+pr-status: PR #4097 OPEN auto-armed BLOCKED on checks (bounded named-dep)
+---
+
+# Autonomous-loop tick 1455Z — brief-ack #1 (PR #4097 auto-merge pending green checks)
+
+**Brief-ack #1 with named-dep**: PR [#4097](https://github.com/Lucent-Financial-Group/Zeta/pull/4097) (B-0613 Option B zsh-portability fix) is auto-armed (this session) + BLOCKED on CI checks running. Bounded ETA = check-completion (typically minutes). No substantive substrate action needed this tick.
+
+Peer Otto landed their own 1443Z shard (`7efd17a`) on the same branch documenting their FP-resolve recovery. Substrate continues compounding via peer.
+
+Counter: this is brief-ack-#1 of post-PR-#4097-armed wait window. Reset on PR #4097 merge OR named-dep clear OR substantive work.
+
+CronCreate `9e8944ea` armed (4h 45min continuous).
+
+## Composes with
+
+- [PR #4097](https://github.com/Lucent-Financial-Group/Zeta/pull/4097) (named-dep)
+- 1452Z prior shard (auto-merge arming)
+- [`.claude/rules/holding-without-named-dependency-is-standing-by-failure.md`](../../../../../../.claude/rules/holding-without-named-dependency-is-standing-by-failure.md) — brief-ack rule applied substrate-honestly

docs/hygiene-history/ticks/2026/05/17/1457Z.md

@@ -0,0 +1,20 @@
+---
+tick: 2026-05-17T14:57Z
+surface: otto-cli
+session: autonomous-loop (brief-ack #2)
+gate-tier: pure-git (GraphQL 4/5000; reset ~15:00Z)
+sentinel: CronCreate 9e8944ea armed (4h 47min continuous)
+pr-status: PR #4097 OPEN auto-armed BLOCKED (0 failures, 0 in-progress — likely unresolved-thread state; can't investigate under pure-git tier)
+---
+
+# Autonomous-loop tick 1457Z — brief-ack #2 (PR #4097 BLOCKED, awaiting rate-limit reset)
+
+**Brief-ack #2 with named-dep**: PR [#4097](https://github.com/Lucent-Financial-Group/Zeta/pull/4097) checks complete (0 failures, 0 in-progress) but mergeState BLOCKED. Suggests unresolved-thread state. GraphQL 4/5000 — cannot query reviewThreads to confirm. Reset ETA ~15:00Z (3 min).
+
+Counter: brief-ack-#2 of PR-#4097 wait. Will reset on PR merge OR threads-cleared OR substantive work.
+
+## Composes with
+
+- 1455Z (brief-ack #1)
+- [PR #4097](https://github.com/Lucent-Financial-Group/Zeta/pull/4097) (named-dep)
+- [`.claude/rules/refresh-world-model-poll-pr-gate.md`](../../../../../../.claude/rules/refresh-world-model-poll-pr-gate.md) — pure-git tier discipline

docs/hygiene-history/ticks/2026/05/17/1458Z.md

@@ -0,0 +1,19 @@
+---
+tick: 2026-05-17T14:58Z
+surface: otto-cli
+session: autonomous-loop (brief-ack #3)
+gate-tier: pure-git (GraphQL 0/5000; reset imminent ~15:00Z)
+sentinel: CronCreate 9e8944ea armed (4h 48min continuous)
+pr-status: PR #4097 OPEN auto-armed BLOCKED (can't query under exhausted GraphQL)
+---
+
+# Autonomous-loop tick 1458Z — brief-ack #3
+
+**Brief-ack #3 with named-dep**: rate-limit reset imminent (~15:00Z, 2 min). Will investigate PR #4097 BLOCKED state post-reset.
+
+Counter: brief-ack-#3 of PR-#4097 wait. 3 ticks until forced-escalation #6.
+
+## Composes with
+
+- 1455Z + 1457Z prior brief-acks
+- [PR #4097](https://github.com/Lucent-Financial-Group/Zeta/pull/4097)

docs/pr-discussions/PR-4097-fix-b-0613-correct-option-b-zsh-portability-claim-shopt-is-b.md

@@ -0,0 +1,102 @@
+---
+pr_number: 4097
+title: "fix(B-0613): correct Option B zsh portability claim (shopt is bash-only)"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-17T14:49:14Z"
+merged_at: "2026-05-17T21:31:33Z"
+closed_at: "2026-05-17T21:31:33Z"
+head_ref: "otto/b0613-zsh-portability-followup-1443z"
+base_ref: "main"
+archived_at: "2026-05-17T21:33:39Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #4097: fix(B-0613): correct Option B zsh portability claim (shopt is bash-only)
+
+## PR description
+
+## Follow-up — correct Option B zsh portability claim in B-0613 row
+
+Single-commit follow-up to [#4086](https://github.com/Lucent-Financial-Group/Zeta/pull/4086) (B-0613 backlog row, merged at `ae9cf1b`).
+
+### What was wrong
+
+The merged row at line 75 says:
+
+> Explicit nullglob + array — works in any modern bash; portable to zsh too.
+
+This claim is incorrect. `shopt` is a Bash builtin; zsh uses `setopt`/`unsetopt` with the `NULL_GLOB` option. A reviewer ([chatgpt-codex-connector P2](https://github.com/Lucent-Financial-Group/Zeta/pull/4086#discussion_r-…)) correctly flagged this on PR #4086.
+
+### What this PR does
+
+Replaces "portable to zsh too" with an explicit "**NOT portable to zsh**" note + concrete zsh equivalents (`setopt -o NULL_GLOB` / `unsetopt NULL_GLOB`) and a pointer to Option A (compgen) or Option C (find) for zsh implementations.
+
+### Substrate-honest disclosure
+
+The reviewer's thread was incorrectly resolved as a verified-FP in tick `1417Z` by this Otto-CLI surface. Reading my own message log: I claimed "the file at line 75 already says 'NOT portable to zsh'" — but the merged file `ae9cf1b` and my own commit `df93b5b` both still had the wrong "portable to zsh too" claim. The Read I did most likely returned a state that wasn't yet committed (working-tree mod from peer-Otto in flight), and I conflated working-tree with committed state. This is a verify-before-fix discipline failure on my part.
+
+Peer-Otto-CLI surface caught the regression in tick 1424Z (`cf4fc03` substrate-honest comment + `54ca355` actual fix). I cherry-picked `54ca355` onto this branch for the follow-up PR.
+
+🤖 Generated with [Claude Code](https://claude.com/claude-code)
+
+## Reviews
+
+### COMMENTED — @chatgpt-codex-connector (2026-05-17T14:50:39Z)
+
+
+### 💡 Codex Review
+
+Here are some automated review suggestions for this pull request.
+
+**Reviewed commit:** `13f749d3e4`
+
+
+<details> <summary>ℹ️ About Codex in GitHub</summary>
+<br/>
+
+[Your team has set up Codex to review pull requests in this repo](https://chatgpt.com/codex/cloud/settings/general). 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".
+
+</details>
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-17T14:50:42Z)
+
+## Pull request overview
+
+This PR updates the B-0613 backlog row to correct an inaccurate zsh portability claim for the `shopt -s nullglob` fix candidate.
+
+**Changes:**
+- Replaces “portable to zsh too” with an explicit note that `shopt` is bash-only.
+- Adds zsh-oriented guidance using `NULL_GLOB` equivalents.
+
+## Review threads
+
+### Thread 1: docs/backlog/P3/B-0613-lior-loop-lockfile-probe-hardening-compgen-shopt-nullglob-2026-05-17.md:75 (resolved)
+
+**@chatgpt-codex-connector** (2026-05-17T14:50:39Z):
+
+**<sub><sub>![P2 Badge](https://img.shields.io/badge/P2-yellow?style=flat)</sub></sub>  Drop Option A as a zsh fallback**
+
+The new portability note recommends "Option A or Option C" for zsh, but Option A is `compgen -G`, which this same document already defines as a bash builtin. In a zsh implementation, following this guidance can produce `compgen: command not found`, leaving the lockfile probe behavior unresolved. Limit the zsh guidance to Option C or the explicit `setopt`/`unsetopt` variant.
+
+Useful? React with 👍 / 👎.
+
+### Thread 2: docs/backlog/P3/B-0613-lior-loop-lockfile-probe-hardening-compgen-shopt-nullglob-2026-05-17.md:75 (resolved)
+
+**@copilot-pull-request-reviewer** (2026-05-17T14:50:42Z):
+
+The zsh guidance still points readers to Option A, but Option A is documented immediately above as `compgen -G` (a bash builtin), so it is not a valid zsh implementation path. This leaves the corrected portability note internally contradictory; zsh guidance should point to Option C or the zsh `NULL_GLOB` equivalent only.
+
+## General comments
+
+### @AceHack (2026-05-17T14:57:05Z)
+
+Maji Antigravity Check: Drift detected. The PR description exhibits the shadow pattern: narration-over-action. You are narrating your discipline failure instead of just executing the fix. Cease metadata churn and stick to operational updates.