jonah-fleet 1.15.0 → 1.16.0

package/CHANGELOG.md

@@ -5,6 +5,30 @@ All notable changes to `jonah-fleet` will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.16.0](https://github.com/juliendurandeu/jonah-fleet/compare/v1.15.1...v1.16.0) (2026-09-19)
+
+
+### Features
+
+* **orchestration:** routine run failure ingestion, dynamic target binding, and auto-closure ([#232](https://github.com/juliendurandeu/jonah-fleet/issues/232)) ([b76b3fc](https://github.com/juliendurandeu/jonah-fleet/commit/b76b3fccd767e5cc9517d977fd08c8979baf64b6))
+
+## [Unreleased] - 2026-09-19
+
+### Features
+
+* **orchestration:** add Routine Run Failure Ingestion & Auto-Closure Protocol to `ORCHESTRATION.md`, unifying prior failure memory and resolution lifecycle across `autowork` and `peer-review`.
+* **prompts:** add Dynamic Target Binding in Scan mode to `autowork.md` and `peer-review.md`, dynamically updating `$ROUTINE_ISSUE_NUMBER` titles with `(Issue #N)` or `(PR #M)` upon claiming so crashed runs are never anonymous.
+* **prompts:** add Prior Failure Ingestion Protocol to `autowork.md` and `peer-review.md`, inspecting past open failed routine issues to extract error logs and crash milestones before implementation or review.
+* **prompts:** add resolution-triggered auto-closure to `autowork.md` and `peer-review.md`, automatically commenting on and closing past failed routine issues for a target once work is marked ready or merged.
+* **housekeeping:** expand `issues-housekeeping.md` to sweep and close stale untargeted `status:failure` routine issues older than 48 hours or whose targets are resolved, eliminating backlog clutter.
+
+## [1.15.1](https://github.com/juliendurandeu/jonah-fleet/compare/v1.15.0...v1.15.1) (2026-09-19)
+
+
+### Bug Fixes
+
+* **radar:** robust options resolution in evaluateActivity when orbital data is empty object ([#248](https://github.com/juliendurandeu/jonah-fleet/issues/248)) ([02e9999](https://github.com/juliendurandeu/jonah-fleet/commit/02e9999609ac4d2ea052e3a52c4c146c393e2957)), closes [#215](https://github.com/juliendurandeu/jonah-fleet/issues/215)
+
 ## [1.15.0](https://github.com/juliendurandeu/jonah-fleet/compare/v1.14.0...v1.15.0) (2026-09-19)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jonah-fleet",
-  "version": "1.15.0",
+  "version": "1.16.0",
   "description": "Standalone autonomous agent fleet with Symphony orchestration, claim protocols, and continuous improvement loops",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

package/templates/prompts/ORCHESTRATION.md

@@ -153,6 +153,23 @@ How live execution progress is reported during autonomous routine runs:
 6. **Harness Interruption Card**: If a routine run fails, times out, or crashes abruptly before Milestone 4, the workflow harness or local runner post-step automatically appends an Interruption Card (`### ❌ Milestone: Run Interrupted / Failed`) before marking `status:failure`.
 7. **Final State Reconciliation**: The final comment is Milestone 4 (Compact completion card). The workflow harness replaces the top-level issue body with the comprehensive telemetry & audit report (`.jonah-fleet/run-report.md`) and closes the issue on success.
 
+### Routine Run Failure Ingestion & Auto-Closure Protocol
+
+Single source of truth for handling routine run failures, context extraction, and issue tracker clutter across the fleet:
+
+1. **Dynamic Target Binding (Scan Mode)**: When `autowork` or `peer-review` starts in Scan mode, the routine tracking issue is initialized with a generic timestamp title (`[routine-name] run {timestamp}`). As soon as the runner claims an Issue or PR, it immediately updates the routine tracking issue title:
+   ```bash
+   gh issue edit "$ROUTINE_ISSUE_NUMBER" --title "[autowork] run ${TIMESTAMP} (Issue #<TARGET_ISSUE>)"
+   ```
+   (or `(PR #<PR_NUMBER>)` for PR convergence and peer review). This guarantees that even if a run is abruptly terminated, times out, or crashes midway, the resulting failure issue is explicitly tied to its target in GitHub issue lists.
+2. **Prior Failure Ingestion (Active Memory)**: Before writing code or conducting review, routines query open routine run issues for the target:
+   ```bash
+   gh issue list --label routine-log --search "Issue #<TARGET_ISSUE>" --state open --json number,title,body
+   ```
+   (or `PR #<PR_NUMBER>`). If prior failed runs exist, the runner extracts error messages, failing test names, or crash milestones from the Interruption Card and incorporates this context into Milestone 1 and its reproduction strategy, preventing repeated identical failures.
+3. **Resolution-Triggered Auto-Closure**: When a target issue or PR reaches terminal completion (a ready PR opened, review decision executed, or PR merged), the routine iterates through any open past failed routine issues for that target, posts a resolution comment referencing the successful run (including the Antigravity run footer), and closes them via `gh issue close <ISSUE> --reason completed`.
+4. **Housekeeping Garbage Collection for Untargeted Crashes**: Routine runs that fail before claiming a target (e.g. runner VM startup errors, GitHub CLI auth failures) or whose target has already been resolved are audited by `issues-housekeeping.md` and closed once older than 48 hours, keeping consumer issue lists clean and noise-free.
+
 ---
 
 ## Token Anomaly Triage & Remediation

package/templates/prompts/autowork.md

@@ -87,7 +87,17 @@ a. **Read the target issue and check eligibility.** Eligible = open, unassigned
    - **Claim atomically**: assign yourself to the PR (`gh pr edit <PR> --add-assignee <login>`) AND post a claim comment on the PR:
      - In **Cloud Actions**: `🔒 Addressing review findings by autowork run {run_url} {timestamp}`
      - In **Local Agent**: `🔒 Addressing review findings by local autowork session (host: {hostname}) {timestamp}`
-   - **Confirm sole ownership**: fetch comments on the PR. Earliest `created_at` among competing claim comments in this round wins. If you lost the race, unassign yourself (`gh pr edit <PR> --remove-assignee <login>`), annotate your comment, and evaluate the next PR (or proceed to Phase 2 if none left).
+    - **Confirm sole ownership**: fetch comments on the PR. Earliest `created_at` among competing claim comments in this round wins. If you lost the race, unassign yourself (`gh pr edit <PR> --remove-assignee <login>`), annotate your comment, and evaluate the next PR (or proceed to Phase 2 if none left).
+    - **Dynamic Target Binding (Scan Mode)**: If `$ROUTINE_ISSUE_NUMBER` is set and its title does not mention `PR #<PR_NUMBER>`, update the routine issue title to bind the target PR:
+      ```bash
+      TIMESTAMP=$(date -u +"%Y-%m-%dT%H-%M-%SZ")
+      gh issue edit "$ROUTINE_ISSUE_NUMBER" --title "[autowork] run ${TIMESTAMP} (PR #<PR_NUMBER>)" || true
+      ```
+    - **Prior Failure Ingestion**: Query open routine run issues for `PR #<PR_NUMBER>`:
+      ```bash
+      gh issue list --label routine-log --search "PR #<PR_NUMBER>" --state open --json number,title,body
+      ```
+      If prior failed routine runs exist (carrying label `status:failure` or an Interruption Card), read the Interruption Card or comments to understand why the previous autowork pass on this PR failed, crashed, or timed out, and take that into account before making fixes.
 2. For the claimed PR, fetch ALL review threads and PR-level comments. Filter for actionable findings matching trust & noise rules (author login matching `get_me`, non-noise). Address every single one in this run — push fixes for actionable findings, reply to clarifying questions, and comment on deferred items.
 3. For PRs where you have addressed all findings:
    3a. **Pre-ready self-audit** (run before marking ready):
@@ -97,18 +107,29 @@ a. **Read the target issue and check eligibility.** Eligible = open, unassigned
    - **Documentation accuracy**: update relevant docs (`ARCHITECTURE.md`, `CODEMAP.md`, `API.md`, `CHANGELOG.md` if maintained by repo).
    - **Build & type-check verification**: run the repository's test, type-check, and lint commands from `AGENTS.md` (e.g. `npm test`, `npm run type-check`, `npm run lint`, `pytest`, `cargo test`). Confirm zero errors and zero test failures.
    - **Active Origin Sync & Clean-Merge Gate**: Run `git fetch origin main && git merge origin/main --no-edit` to absorb any newly merged pull requests and resolve any conflicts locally. Verify `git merge-tree origin/main HEAD` reports no conflicts before marking ready.
-   - **Release claim on ready**: mark the PR ready (`gh pr ready <PR>`) and unassign yourself (`gh pr edit <PR> --remove-assignee <login>`) so Peer Review can evaluate without holding stale agent reservation locks.
-      Only mark the PR ready after passing every check above.
-      3b. **Ping-pong cap**: If this same PR has bounced between draft and ready 3 or more times over the same substantive finding, stop re-marking it ready. Post the mandatory 4-part escalation card summarizing the disagreement for human resolution and leave the PR in draft:
-        ```markdown
-        ## 🛑 Escalation: Human Decision Required
-        - **Decision Needed**: [1 focused question or choice]
-        - **Evidence ("Why I believe this")**: [Specific files, lines, test outputs, or conflicting docs]
-        - **Evaluated Options & Trade-offs**:
-          - *Option A*: [Pros / Cons]
-          - *Option B*: [Pros / Cons]
-        - **Recommended Path**: [Agent recommendation]
-        ```
+   - **Release claim on ready & resolve past failures**: mark the PR ready (`gh pr ready <PR>`), unassign yourself (`gh pr edit <PR> --remove-assignee <login>`) so Peer Review can evaluate without holding stale agent reservation locks, and resolve any open past failed routine issues for `PR #<PR_NUMBER>`:
+     ```bash
+     PAST_FAILURES=$(gh issue list --label routine-log --search "PR #<PR_NUMBER>" --state open --json number --jq '.[].number' || true)
+     for past_num in $PAST_FAILURES; do
+       if [ -n "$past_num" ] && [ "$past_num" != "$ROUTINE_ISSUE_NUMBER" ]; then
+         gh issue comment "$past_num" --body "Resolved by autowork run ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-} (PR #<PR_NUMBER> findings addressed and marked ready).
+
+_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-})_" || true
+         gh issue close "$past_num" --reason completed || true
+       fi
+     done
+     ```
+     Only mark the PR ready after passing every check above.
+     3b. **Ping-pong cap**: If this same PR has bounced between draft and ready 3 or more times over the same substantive finding, stop re-marking it ready. Post the mandatory 4-part escalation card summarizing the disagreement for human resolution and leave the PR in draft:
+       ```markdown
+       ## 🛑 Escalation: Human Decision Required
+       - **Decision Needed**: [1 focused question or choice]
+       - **Evidence ("Why I believe this")**: [Specific files, lines, test outputs, or conflicting docs]
+       - **Evaluated Options & Trade-offs**:
+         - *Option A*: [Pros / Cons]
+         - *Option B*: [Pros / Cons]
+         - **Recommended Path**: [Agent recommendation]
+       ```
      3c. **Orphaned Ready PR Recovery**: If an open PR authored by this routine is `ready_for_review`, has passing CI, no unaddressed review comments, and has received no review activity for over 2 hours (e.g. because peer review crashed or encountered quota limits), kickstart the review routine by posting `/review` comment or toggling draft and ready (`gh pr ready <PR> --undo && gh pr ready <PR>`).
    - **Passing CI Verification Gate**: Verify via `gh pr view <PR> --json statusCheckRollup,mergeStateStatus` that all required and existing checks have completed with `conclusion: "SUCCESS"` and `mergeStateStatus` is `CLEAN` (neither `UNSTABLE`, `BLOCKED`, nor `DIRTY`).
    - **Unapproved/Pending Workflow Invariant**: NEVER post `/review` or toggle draft state if checks are in-progress, failing, or awaiting approval (`conclusion: "ACTION_REQUIRED"`). Doing so creates an infinite comment storm while workflows remain paused awaiting human permissions.
@@ -116,7 +137,19 @@ a. **Read the target issue and check eligibility.** Eligible = open, unassigned
    - For open issues, check if recent git history or merged PRs reference the issue (e.g. `git log -n 50 --grep="#<ISSUE_NUMBER>"` or `gh pr list --state merged --search "<ISSUE_NUMBER>" --limit 5`).
    - If a merged PR or commit on `main` resolved the issue, close it immediately:
      ```bash
-     gh issue close <ISSUE_NUMBER> --comment "Closed via merged PR #<PR_NUMBER> (found in git history)."
+     gh issue close <ISSUE_NUMBER> --comment "Closed via merged PR #<PR_NUMBER> (found in git history).
+
+_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-})_"
+     # Reconcile lingering past failed routine run issues for this resolved issue
+     PAST_FAILURES=$(gh issue list --label routine-log --search "Issue #<ISSUE_NUMBER>" --state open --json number --jq '.[].number' || true)
+     for past_num in $PAST_FAILURES; do
+       if [ -n "$past_num" ] && [ "$past_num" != "$ROUTINE_ISSUE_NUMBER" ]; then
+         gh issue comment "$past_num" --body "Resolved via merged PR #<PR_NUMBER>.
+
+_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-})_" || true
+         gh issue close "$past_num" --reason completed || true
+       fi
+     done
      ```
 
 5. If any PR was updated in this phase, STOP — run is SUCCESS.
@@ -134,17 +167,30 @@ a. **Read the target issue and check eligibility.** Eligible = open, unassigned
      - If running in **Local Agent** (`$LOCAL_AGENT`): Scan mode selects across all priorities (P0 → P1 → P2 → P3) without time gating, prioritizing active local backlog consumption.
    - Skip assigned issues (unless stale claim per `ORCHESTRATION.md`), issues with open PRs, issues with unclosed blocking dependencies (`Blocked by #N` / `Depends on #N`), issues labeled `needs-human`, `needs-design`, or `needs-info`, and issues under cross-run cooldown.
 9. If no eligible candidate exists, STOP — run is SUCCESS with "No unclaimed work available".
-10. If the candidate should be closed already (work done, merged PR found in git history or via `gh pr list --state merged --search "<ISSUE_NUMBER>"`), close it immediately (`gh issue close <ISSUE_NUMBER> --comment "Closed: work already merged in PR #<PR_NUMBER>."`) and return to step 8.
+10. If the candidate should be closed already (work done, merged PR found in git history or via `gh pr list --state merged --search "<ISSUE_NUMBER>"`), close it immediately (`gh issue close <ISSUE_NUMBER> --comment "Closed: work already merged in PR #<PR_NUMBER>.\n\n_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-})_"`), close any lingering past failed routine run issues (`PAST_FAILURES=$(gh issue list --label routine-log --search "Issue #<ISSUE_NUMBER>" --state open --json number --jq '.[].number' || true); for p in $PAST_FAILURES; do if [ -n "$p" ] && [ "$p" != "$ROUTINE_ISSUE_NUMBER" ]; then gh issue comment "$p" --body "Resolved: work already merged in PR #<PR_NUMBER>.\n\n_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-})_" || true; gh issue close "$p" --reason completed || true; fi; done`), and return to step 8.
     10a. **Stale-claim reclamation:** If candidate is a stale claim per `ORCHESTRATION.md`, re-read immediately before writing, unassign the dead owner, post reclamation comment, and proceed to claim.
 11. **Claim protocol:**
     a. Re-read candidate issue immediately before claiming (`issue_read`). If assigned, abort and pick next candidate.
     b. Claim atomically: assign yourself (`login` from step 7) AND post claim comment:
     - In **Cloud Actions**: `🔒 Claimed by autowork run {run_url} {timestamp}`
     - In **Local Agent**: `🔒 Claimed by local autowork session (host: {hostname}) {timestamp}`
-      c. Confirm sole ownership by counting `🔒 Claimed by autowork run` / `🔒 Claimed by local autowork session` comments. Earliest `created_at` wins. If you lost the race, leave assignee as is, annotate your comment, and pick next candidate.
+    c. Confirm sole ownership by counting `🔒 Claimed by autowork run` / `🔒 Claimed by local autowork session` comments. Earliest `created_at` wins. If you lost the race, leave assignee as is, annotate your comment, and pick next candidate.
+    d. **Dynamic Target Binding (Scan Mode)**: If `$ROUTINE_ISSUE_NUMBER` is set and its title does not mention `Issue #<TARGET_ISSUE>`, update the routine issue title to bind the target issue:
+       ```bash
+       TIMESTAMP=$(date -u +"%Y-%m-%dT%H-%M-%SZ")
+       gh issue edit "$ROUTINE_ISSUE_NUMBER" --title "[autowork] run ${TIMESTAMP} (Issue #<TARGET_ISSUE>)" || true
+       ```
 12. Evaluate whether the claimed issue can be completed autonomously:
     - Confirm your `🔒` claim comment is present on the issue.
     - Read the issue description, linked code, and comment thread.
+    - **Prior Failure Ingestion Protocol**: Query open routine run issues for `<TARGET_ISSUE>`:
+      ```bash
+      gh issue list --label routine-log --search "Issue #<TARGET_ISSUE>" --state open --json number,title,body
+      ```
+      If prior failed routine issues are found (carrying label `status:failure` or an Interruption Card):
+      - Read the Interruption Card or latest milestone card to identify previous failure causes (e.g. failing test suite, build failure, timeout, or infeasible dependency).
+      - Incorporate findings into the reproduction plan and note in Milestone 1:
+        `- **Prior Failure Context**: <summary of past error/crash and strategy to avoid repeating it>`
     - If bug: use `/diagnosing-bugs` to establish reproduction test before fixing.
     - If large/complex: use `/domain-modeling` and `/codebase-design`.
     - **Pre-Flight Memory Scan**: If `LESSONS.md` exists, grep matching subsystem tags (`grep -E "^### \[(subsystem)\]" LESSONS.md -A 4`) to incorporate known landmines into implementation plans before writing code.
@@ -174,6 +220,7 @@ a. **Read the target issue and check eligibility.** Eligible = open, unassigned
 - **Phase**: \`Phase 1 · Target Selection & Planning\`
 - **Status**: ⏳ In Progress
 - **Target / Context**: \`#<TARGET_ISSUE> (<Title>)\`
+- **Prior Failure Context**: <summary of past error/crash and strategy to avoid repeating it>
 - **Key Decision / Finding**: <Summary of plan, root cause, or reproduction strategy>
 - **Next**: Implementation & Test Verification" || true
       ```
@@ -199,6 +246,18 @@ a. **Read the target issue and check eligibility.** Eligible = open, unassigned
     - **Issue Cross-Reference Comment Guardrail**: Post an explicit comment on the tracking issue referencing the newly created PR (`gh issue comment <ISSUE_NUMBER> --body "Work in progress in PR #<PR_NUMBER>."`). This guarantees an unambiguous, permanent link on the issue timeline even when GitHub's native UI link is suppressed for bot draft PRs.
     - **Warm Context Assignment**: Assign yourself to the newly opened PR (`gh pr edit <PR> --add-assignee <login>`) to hold the reservation across Step 15's in-session review wait so parallel Scan routines recognise the PR as actively held by a live session.
     - Mark PR ready (`gh pr ready <PR>`).
+    - **Auto-Closure on Success**: Once the PR is marked ready (`gh pr ready <PR>`), resolve and close any open past failed routine issues for `#<TARGET_ISSUE>`:
+      ```bash
+      PAST_FAILURES=$(gh issue list --label routine-log --search "Issue #<TARGET_ISSUE>" --state open --json number --jq '.[].number' || true)
+      for past_num in $PAST_FAILURES; do
+        if [ -n "$past_num" ] && [ "$past_num" != "$ROUTINE_ISSUE_NUMBER" ]; then
+          gh issue comment "$past_num" --body "Resolved by autowork run ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-} (PR #<PR_NUMBER> created and ready).
+
+_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-})_" || true
+          gh issue close "$past_num" --reason completed || true
+        fi
+      done
+      ```
     - **Milestone 3 (Autonomous Handoff)**: Once PR is marked ready, emit milestone card if `$ROUTINE_ISSUE_NUMBER` is set:
       ```bash
       gh issue comment "$ROUTINE_ISSUE_NUMBER" --body "### 🚀 Milestone: Autonomous Handoff
@@ -211,7 +270,18 @@ a. **Read the target issue and check eligibility.** Eligible = open, unassigned
 14. If run aborts before opening PR, release claim (unassign).
 15. **In-Session Peer Review Wait & Immediate Convergence (Warm Context):**
     - Poll PR status for up to 10–12 minutes.
-    - If merged: unassign yourself, record terminal SUCCESS and exit cleanly.
+    - If merged: unassign yourself, resolve and close any open past failed routine run issues for `#<TARGET_ISSUE>`, record terminal SUCCESS and exit cleanly:
+      ```bash
+      PAST_FAILURES=$(gh issue list --label routine-log --search "Issue #<TARGET_ISSUE>" --state open --json number --jq '.[].number' || true)
+      for past_num in $PAST_FAILURES; do
+        if [ -n "$past_num" ] && [ "$past_num" != "$ROUTINE_ISSUE_NUMBER" ]; then
+          gh issue comment "$past_num" --body "Resolved by autowork run ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-} (PR #<PR_NUMBER> merged).
+
+_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-})_" || true
+          gh issue close "$past_num" --reason completed || true
+        fi
+      done
+      ```
     - If bounced to draft with findings: fetch review comments, apply fixes in active worktree, run tests, push fix commit, re-mark ready (`gh pr ready <PR>`), and complete run.
     - If timeout (>12m): unassign yourself from the PR (`gh pr edit <PR> --remove-assignee <login>`) and exit cleanly; scheduled cron will handle subsequent rounds.
 

package/templates/prompts/issues-housekeeping.md

@@ -23,7 +23,7 @@ The run is SUCCESS only if ALL of these are true:
 - [ ] Label audit completed: every open issue has consistent type, size, and priority labels
 - [ ] Dependency check completed: issues with `## Dependencies` verified against blocker status
 - [ ] Orphaned-claim sweep completed: stale autowork claims (per `ORCHESTRATION.md`) released back to the unclaimed pool
-- [ ] Stalled routine run audit completed: routine log issues in `status:running` older than 6 hours marked as `status:failure` (timed_out)
+- [ ] Stalled routine run audit and stale failure sweep completed: routine log issues in `status:running` older than 6 hours marked as `status:failure`; untargeted or already-resolved `status:failure` routine log issues older than 48 hours closed with resolution summary
 - [ ] Summary posted listing all changes made
 
 If any criterion cannot be met, stop immediately and log FAILURE with the reason.
@@ -39,7 +39,9 @@ If any criterion cannot be met, stop immediately and log FAILURE with the reason
 
 ### Phase 1: Quick Recovery & Clearing
 
-1. **Stalled routine run sweep**: Check open issues with labels `routine-log` and `status:running`. If an issue has been in `status:running` for > 6 hours without updates, add label `status:failure`, remove `status:running`, add label `needs-attention`, and comment noting the runner timeout or crash.
+1. **Stalled routine run and stale failure sweep**:
+   - **Stalled runs**: Check open issues with labels `routine-log` and `status:running`. If an issue has been in `status:running` for > 6 hours without updates, add label `status:failure`, remove `status:running`, add label `needs-attention`, and comment noting the runner timeout or crash.
+   - **Stale / untargeted failures**: Check open issues with labels `routine-log` and `status:failure`. If an issue is older than 48 hours and either: (i) has no target issue or PR in its title or body (an untargeted infrastructure crash), or (ii) references a target issue or PR that has already been closed or merged, close the routine-log issue with comment "Closed: routine failure superseded or resolved.\n\n_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-})_" and reason completed.
 2. **Orphaned-claim sweep**: Sweep assigned issues. If an issue meets the 3 stale-claim conditions in `ORCHESTRATION.md` (autowork claim comment, no open PR, comment > 6 hours old), re-read immediately before writing, unassign the dead owner, and post a release comment.
 
 ### Phase 2: Backlog Hygiene
@@ -68,7 +70,7 @@ If any criterion cannot be met, stop immediately and log FAILURE with the reason
 
 After completing (SUCCESS or FAILURE), record run execution details to `.jonah-fleet/run-report.md`. Include:
 - Prompt SHA
-- Tally of issues audited, claims released, stalled runs reconciled
+- Tally of issues audited, claims released, stalled runs reconciled, and stale failure runs closed
 - List of closed or modified issues
 
 **Issue Logging Protocol**:

package/templates/prompts/peer-review.md

@@ -90,8 +90,18 @@ Check if `$PR_NUMBER` is set:
    - **Category A (re-review)**: PRs with prior review comments where author has pushed new fix commits.
    - **Category B (first review / unreviewed)**: Brand new PRs ready for review, or ready PRs whose previous review session failed or timed out.
 
-### Step 3: Round tracking & Starting Review marker
+### Step 3: Round tracking, Target Binding, Failure Ingestion & Starting Review marker
 
+- **Dynamic Target Binding (Scan Mode)**: If `$ROUTINE_ISSUE_NUMBER` is set and its title does not mention `(PR #<PR_NUMBER>)`:
+  ```bash
+  TIMESTAMP=$(date -u +"%Y-%m-%dT%H-%M-%SZ")
+  gh issue edit "$ROUTINE_ISSUE_NUMBER" --title "[peer-review] run ${TIMESTAMP} (PR #<PR_NUMBER>)" || true
+  ```
+- **Prior Review Failure Ingestion**: Query open routine run issues for `PR #<PR_NUMBER>`:
+  ```bash
+  gh issue list --label routine-log --search "PR #<PR_NUMBER>" --state open --json number,title,body
+  ```
+  If prior failed routine issues exist (carrying `status:failure` or an Interruption Card), read the Interruption Card or comments to understand what caused the previous review session to fail, crash, or timeout.
 - Post a "Starting review (round N)" comment on the target PR to claim the review window:
   - If `$ROUTINE_ISSUE_NUMBER` is set in the environment or routine prompt, include a link to the tracking log issue:
     `Starting review (round N) · [Run Log #$ROUTINE_ISSUE_NUMBER](${GITHUB_SERVER_URL:-https://github.com}/${GITHUB_REPOSITORY}/issues/${ROUTINE_ISSUE_NUMBER})`
@@ -104,6 +114,7 @@ Check if `$PR_NUMBER` is set:
 - **Phase**: \`Phase 1 · Review Target & Scope\`
 - **Status**: ⏳ In Progress
 - **Target / Context**: \`PR #<PR_NUMBER> (Round N)\`
+- **Prior Failure Context**: <summary of past review failure/crash and verification focus, or None>
 - **Key Decision / Finding**: Claimed review window; starting multi-angle evaluation passes.
 - **Next**: Multi-Angle Code Review Pass" || true
   ```
@@ -144,7 +155,7 @@ If the PR is clean and approved for merge, but lacks a `Closes #N` tracking link
    gh pr edit <PR_NUMBER> --body "<PR Description>\n\nCloses #$ISSUE_NUMBER"
    ```
 
-### Step 6: Execute Final Action
+### Step 6: Execute Final Action & Reconcile Past Failures
 
 - **If Blocking findings exist**:
   - If `N < 5`: Post inline comments, submit review as `COMMENT`, and convert PR to draft (`gh pr ready <N> --undo`).
@@ -156,12 +167,26 @@ If the PR is clean and approved for merge, but lacks a `Closes #N` tracking link
   - Squash-merge the PR: `gh pr merge <N> --squash --delete-branch`.
   - **Explicit Tracking Issue Closure Guardrail**: If a tracking issue was referenced (`$ISSUE_NUMBER`), explicitly close it immediately after merge rather than relying solely on GitHub's native keyword parser (which often fails to trigger on bot-merged squash commits or draft PRs):
     ```bash
-    gh issue close "$ISSUE_NUMBER" --comment "Closed via PR #<N> (merged into main)."
+    gh issue close "$ISSUE_NUMBER" --comment "Closed via PR #<N> (merged into main).
+
+_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-})_"
     ```
   - Submit held review comments.
   - In any review summary, decision comment, or escalation comment posted to the PR, include the run log reference if `$ROUTINE_ISSUE_NUMBER` is set (e.g. `- **Run Log**: [#$ROUTINE_ISSUE_NUMBER](${GITHUB_SERVER_URL:-https://github.com}/${GITHUB_REPOSITORY}/issues/${ROUTINE_ISSUE_NUMBER})`).
   - File follow-up issues for material non-blocking findings.
   - If mechanical doc fixes are needed, commit directly to `main`.
+- **Resolve Past Failed Review Runs**: After the terminal action (merge or bounce to draft) completes successfully, resolve and close any open past failed routine issues for `PR #<PR_NUMBER>`:
+  ```bash
+  PAST_FAILURES=$(gh issue list --label routine-log --search "PR #<PR_NUMBER>" --state open --json number --jq '.[].number' || true)
+  for past_num in $PAST_FAILURES; do
+    if [ -n "$past_num" ] && [ "$past_num" != "$ROUTINE_ISSUE_NUMBER" ]; then
+      gh issue comment "$past_num" --body "Resolved by peer-review run ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-} (PR #<PR_NUMBER> review cycle completed).
+
+_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-})_" || true
+      gh issue close "$past_num" --reason completed || true
+    fi
+  done
+  ```
 
 ## Logging