jonah-fleet 1.17.0 → 1.19.0

package/CHANGELOG.md

@@ -5,6 +5,20 @@ 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).
 
+## [1.19.0](https://github.com/juliendurandeu/jonah-fleet/compare/v1.18.0...v1.19.0) (2026-09-20)
+
+
+### Features
+
+* **autowork:** add opportunistic operational log sweep (idle GC) to Step 9 ([#285](https://github.com/juliendurandeu/jonah-fleet/issues/285)) ([8e4cf12](https://github.com/juliendurandeu/jonah-fleet/commit/8e4cf122cb949bdc23bdc3eaa1f80e4a7739dde6))
+
+## [1.18.0](https://github.com/juliendurandeu/jonah-fleet/compare/v1.17.0...v1.18.0) (2026-09-20)
+
+
+### Features
+
+* **guard:** update routine GitHub Actions workflows to execute via run-with-loop-guard wrapper ([#227](https://github.com/juliendurandeu/jonah-fleet/issues/227)) ([#277](https://github.com/juliendurandeu/jonah-fleet/issues/277)) ([496ce8c](https://github.com/juliendurandeu/jonah-fleet/commit/496ce8c0c56ddcfd8ac09e530fb4bdaee9c934c9))
+
 ## [1.17.0](https://github.com/juliendurandeu/jonah-fleet/compare/v1.16.0...v1.17.0) (2026-09-19)
 
 
@@ -16,12 +30,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Features
 
+* **guard:** execute routine GitHub Actions workflows via run-with-loop-guard wrapper script ([#227](https://github.com/juliendurandeu/jonah-fleet/issues/227))
 * **orchestration:** adopt 4-part human escalation card in peer-review routine on round-5 escalation ([#235](https://github.com/juliendurandeu/jonah-fleet/issues/235))
 * **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.
+* **autowork:** add opportunistic operational log sweep (idle GC) to Step 9 in `autowork.md`, cleaning up stale untargeted failures when the issue backlog is clear.
 
 ## [1.16.0](https://github.com/juliendurandeu/jonah-fleet/compare/v1.15.1...v1.16.0) (2026-09-19)
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jonah-fleet",
-  "version": "1.17.0",
+  "version": "1.19.0",
   "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

@@ -168,7 +168,9 @@ Single source of truth for handling routine run failures, context extraction, an
    ```
    (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.
+4. **Garbage Collection for Untargeted / Stale Crashes (Housekeeping & Idle Autowork)**: 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 and closed once older than 48 hours by:
+   - `issues-housekeeping.md` during scheduled backlog maintenance sweeps.
+   - `autowork.md` Step 9 as an opportunistic idle sweep when no eligible unclaimed work exists, ensuring repositories running minimal presets without dedicated housekeeping crons stay pristine.
 
 ---
 

package/templates/prompts/autowork.md

@@ -165,8 +165,19 @@ _Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/ru
    - **Dual Execution Priority Routing**:
      - If running in **Cloud Actions** (`$GITHUB_ACTIONS` / `$CI`): Scan mode selects `priority/P0` or `priority/P1` issues first. Lower-priority `priority/P2` or `priority/P3` issues are eligible in cloud Scan mode ONLY if the issue has remained unclaimed for more than 48 hours (`created_at` older than 48h, acting as a cloud catchup sweep).
      - If running in **Local Agent** (`$LOCAL_AGENT`): Scan mode selects across all priorities (P0 → P1 → P2 → P3) without time gating, prioritizing active local backlog consumption.
-   - Skip assigned issues (unless stale claim per `ORCHESTRATION.md`), issues with open PRs, issues with unclosed blocking dependencies (`Blocked by #N` / `Depends on #N`), issues labeled `needs-human`, `needs-design`, or `needs-info`, and issues under cross-run cooldown.
-9. If no eligible candidate exists, STOP — run is SUCCESS with "No unclaimed work available".
+9. If no eligible candidate exists:
+   - **Opportunistic Operational Log Sweep (Idle GC)**: Before concluding an idle run, perform a lightweight sweep of open `routine-log` issues to prevent operational clutter from accumulating across repositories (especially those running minimal presets without dedicated housekeeping crons):
+     ```bash
+     STALE_FAILURES=$(gh issue list --label routine-log,status:failure --state open --limit 20 --json number,title,body,createdAt || true)
+     ```
+     For each stale failure issue:
+     - Check if it is untargeted (no `(Issue #N)` or `(PR #M)` in title/body) and older than 48 hours, OR if its referenced target issue or PR is already closed or merged.
+     - If eligible, close it with a resolution note:
+       ```bash
+       gh issue comment "$stale_num" --body "Closed by autowork idle sweep: routine failure superseded or untargeted crash older than 48 hours.\n\n_Generated by [Antigravity](${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID:-})_" || true
+       gh issue close "$stale_num" --reason completed || true
+       ```
+   - STOP — run is SUCCESS with "No unclaimed work available; swept stale operational logs".
 10. If the candidate should be closed already (work done, merged PR found in git history or via `gh pr list --state merged --search "<ISSUE_NUMBER>"`), close it immediately (`gh issue close <ISSUE_NUMBER> --comment "Closed: work already merged in PR #<PR_NUMBER>.\n\n_Generated by [Antigravity](${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:**

package/templates/workflows/analytics-review-cron.yml

@@ -161,6 +161,7 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           ANTIGRAVITY_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           GH_TOKEN: ${{ secrets.GH_PAT || github.token }}
+          ROUTINE: analytics-review
           ROUTINE_ISSUE_NUMBER: ${{ steps.run-issue.outputs.issue_number }}
           VERCEL_TOKEN: ${{ secrets.VERCEL_TOKEN }}
           POSTHOG_API_KEY: ${{ secrets.POSTHOG_API_KEY }}
@@ -174,7 +175,8 @@ jobs:
           PROMPT="You are the Analytics Review routine for this repository. Read and follow the instructions in .github/prompts/analytics-review.md exactly. ${SKILLS_PROMPT}"
 
           set +e
-          agy -p "$PROMPT" \
+          node .github/scripts/run-with-loop-guard.js \
+            -p "$PROMPT" \
             --model "$MODEL" \
             --output-format text \
             --print-timeout "$PRINT_TIMEOUT" \

package/templates/workflows/autowork-cron.yml

@@ -183,6 +183,7 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           ANTIGRAVITY_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           GH_TOKEN: ${{ secrets.GH_PAT || github.token }}
+          ROUTINE: autowork
           TARGET_ISSUE: ${{ inputs.target_issue || inputs.issue_number }}
           ROUTINE_ISSUE_NUMBER: ${{ steps.run-issue.outputs.issue_number }}
           SKILLS_PROMPT: ${{ steps.skills.outputs.skills_prompt }}
@@ -199,7 +200,8 @@ jobs:
           fi
 
           set +e
-          agy -p "$PROMPT" \
+          node .github/scripts/run-with-loop-guard.js \
+            -p "$PROMPT" \
             --model "$MODEL" \
             --output-format text \
             --print-timeout "$PRINT_TIMEOUT" \

package/templates/workflows/dependency-check-cron.yml

@@ -139,6 +139,7 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           ANTIGRAVITY_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           GH_TOKEN: ${{ secrets.GH_PAT || github.token }}
+          ROUTINE: dependency-update-security-check
           ROUTINE_ISSUE_NUMBER: ${{ steps.run-issue.outputs.issue_number }}
           MODEL: ${{ steps.routine-config.outputs.model || 'gemini-3.8-flash-medium' }}
           PRINT_TIMEOUT: ${{ steps.routine-config.outputs.print_timeout || '25m' }}
@@ -149,7 +150,8 @@ jobs:
           PROMPT="You are the Dependency Update & Security Check routine. Read and follow .github/prompts/dependency-update-security-check.md exactly. Check dependencies for updates and vulnerabilities, and create or update tracking issues."
 
           set +e
-          agy -p "$PROMPT" \
+          node .github/scripts/run-with-loop-guard.js \
+            -p "$PROMPT" \
             --model "$MODEL" \
             --output-format text \
             --print-timeout "$PRINT_TIMEOUT" \

package/templates/workflows/design-review-cron.yml

@@ -126,6 +126,7 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           ANTIGRAVITY_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           GH_TOKEN: ${{ secrets.GH_PAT || github.token }}
+          ROUTINE: design-review
           ROUTINE_ISSUE_NUMBER: ${{ steps.run-issue.outputs.issue_number }}
           VERCEL_TOKEN: ${{ secrets.VERCEL_TOKEN }}
           POSTHOG_API_KEY: ${{ secrets.POSTHOG_API_KEY }}
@@ -138,7 +139,8 @@ jobs:
           PROMPT="You are the Design Review routine for this repository. Read and follow the instructions in .github/prompts/design-review.md exactly. ${SKILLS_PROMPT}"
 
           set +e
-          agy -p "$PROMPT" \
+          node .github/scripts/run-with-loop-guard.js \
+            -p "$PROMPT" \
             --model gemini-3.8-flash-high \
             --output-format text \
             --print-timeout 50m \

package/templates/workflows/issues-housekeeping-cron.yml

@@ -139,6 +139,7 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           ANTIGRAVITY_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           GH_TOKEN: ${{ secrets.GH_PAT || github.token }}
+          ROUTINE: issues-housekeeping
           ROUTINE_ISSUE_NUMBER: ${{ steps.run-issue.outputs.issue_number }}
           MODEL: ${{ steps.routine-config.outputs.model || 'gemini-3.8-flash-medium' }}
           PRINT_TIMEOUT: ${{ steps.routine-config.outputs.print_timeout || '40m' }}
@@ -149,7 +150,8 @@ jobs:
           PROMPT="You are the Issues Housekeeping routine for this repository. Read and follow .github/prompts/issues-housekeeping.md exactly. Sweep open issues for staleness, duplicates, priority accuracy, and orphaned claims."
 
           set +e
-          agy -p "$PROMPT" \
+          node .github/scripts/run-with-loop-guard.js \
+            -p "$PROMPT" \
             --model "$MODEL" \
             --output-format text \
             --print-timeout "$PRINT_TIMEOUT" \

package/templates/workflows/prompt-optimizer-cron.yml

@@ -139,6 +139,7 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           ANTIGRAVITY_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           GH_TOKEN: ${{ secrets.GH_PAT || github.token }}
+          ROUTINE: optimizer
           ROUTINE_ISSUE_NUMBER: ${{ steps.run-issue.outputs.issue_number }}
           MODEL: ${{ steps.routine-config.outputs.model || 'gemini-3.8-flash-high' }}
           PRINT_TIMEOUT: ${{ steps.routine-config.outputs.print_timeout || '35m' }}
@@ -149,7 +150,8 @@ jobs:
           PROMPT="You are the Prompt Optimizer routine for this repository. Read and follow .github/prompts/optimizer.md exactly. Diagnose failures, token anomalies, and review loops, and propose preventative prompt and test fixes."
 
           set +e
-          agy -p "$PROMPT" \
+          node .github/scripts/run-with-loop-guard.js \
+            -p "$PROMPT" \
             --model "$MODEL" \
             --output-format text \
             --print-timeout "$PRINT_TIMEOUT" \

package/templates/workflows/trigger-autowork-manual.yml

@@ -188,6 +188,7 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           ANTIGRAVITY_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           GH_TOKEN: ${{ secrets.GH_PAT || github.token }}
+          ROUTINE: autowork
           TARGET_ISSUE: ${{ inputs.issue_number }}
           ROUTINE_ISSUE_NUMBER: ${{ steps.run-issue.outputs.issue_number }}
           MODE: ${{ inputs.mode || 'targeted' }}
@@ -210,7 +211,8 @@ jobs:
           fi
 
           set +e
-          agy -p "$PROMPT" \
+          node .github/scripts/run-with-loop-guard.js \
+            -p "$PROMPT" \
             --model "$MODEL" \
             --output-format text \
             --print-timeout "$PRINT_TIMEOUT" \

package/templates/workflows/trigger-autowork-on-bug.yml

@@ -155,6 +155,7 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           ANTIGRAVITY_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           GH_TOKEN: ${{ secrets.GH_PAT || github.token }}
+          ROUTINE: autowork
           TARGET_ISSUE: ${{ github.event.issue.number }}
           ROUTINE_ISSUE_NUMBER: ${{ steps.run-issue.outputs.issue_number }}
           SKILLS_PROMPT: ${{ steps.skills.outputs.skills_prompt }}
@@ -167,7 +168,8 @@ jobs:
           PROMPT="You are the Autowork routine for this repository. A high-priority bug was filed. Read and follow .github/prompts/autowork.md. ${SKILLS_PROMPT} Your target is issue #${TARGET_ISSUE}. You are in Targeted mode: work issue #${TARGET_ISSUE} directly."
 
           set +e
-          agy -p "$PROMPT" \
+          node .github/scripts/run-with-loop-guard.js \
+            -p "$PROMPT" \
             --model "$MODEL" \
             --output-format text \
             --print-timeout "$PRINT_TIMEOUT" \

package/templates/workflows/trigger-autowork-on-merge.yml

@@ -186,6 +186,7 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           ANTIGRAVITY_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           GH_TOKEN: ${{ secrets.GH_PAT || github.token }}
+          ROUTINE: autowork
           ROUTINE_ISSUE_NUMBER: ${{ steps.run-issue.outputs.issue_number }}
           SKILLS_PROMPT: ${{ steps.skills.outputs.skills_prompt }}
           MODEL: ${{ steps.routine-config.outputs.model || 'gemini-3.8-flash-high' }}
@@ -197,7 +198,8 @@ jobs:
           PROMPT="You are the Autowork routine for this repository. A PR was recently merged. Read and follow .github/prompts/autowork.md. ${SKILLS_PROMPT} You are in Scan mode: converge on open PRs, close merged issues, and pick the next unblocked priority issue."
 
           set +e
-          agy -p "$PROMPT" \
+          node .github/scripts/run-with-loop-guard.js \
+            -p "$PROMPT" \
             --model "$MODEL" \
             --output-format text \
             --print-timeout "$PRINT_TIMEOUT" \

package/templates/workflows/trigger-review-routine.yml

@@ -252,6 +252,7 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           ANTIGRAVITY_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           GH_TOKEN: ${{ secrets.GH_PAT || github.token }}
+          ROUTINE: peer-review
           PR_NUMBER: ${{ github.event.pull_request.number || github.event.issue.number || inputs.pr_number }}
           PR_URL: ${{ github.event.pull_request.html_url || github.event.issue.html_url }}
           ROUTINE_ISSUE_NUMBER: ${{ steps.run-issue.outputs.issue_number }}
@@ -275,7 +276,8 @@ jobs:
           fi
 
           set +e
-          agy -p "$PROMPT" \
+          node .github/scripts/run-with-loop-guard.js \
+            -p "$PROMPT" \
             --model "$MODEL" \
             --output-format text \
             --print-timeout "$PRINT_TIMEOUT" \