fix(agents): make the optimizer recursion guard actually correlate runs by stranske · Pull Request #2993 · stranske/Workflows

stranske · 2026-08-08T23:14:59Z

Source: Issue #464

Closes #464

Automated Status Summary

Scope

Address unmet acceptance criteria from PR #463.

Original scope:

After merging PR chore(codex): bootstrap PR for issue #101 #103 (multi-agent routing infrastructure), we need to:
1. Validate the CLI agent pipeline works end-to-end with the new task-focused prompts
1. Add GITHUB_STEP_SUMMARY output so iteration results are visible in the Actions UI
1. Streamline the Automated Status Summary to reduce clutter when using CLI agents
1. Clean up comment patterns to avoid a mix of old UI-agent and new CLI-agent comments

Context for Agent

Related Issues/PRs

Tasks

Acceptance criteria

CLI agent receives explicit tasks in prompt and works on them
CLI agent PRs have ≤3 bot comments total (summary, one per iteration update) instead of 10+
Requires PR chore(codex): bootstrap PR for issue #101 #103 to be merged first

Head SHA: c49feee
Latest Runs: ✅ success — Gate
Required: gate: ✅ success

Workflow / Job	Result	Logs
Gate	✅ success	View run
Health 40 Sweep	✅ success	View run
Health 44 Gate Branch Protection	❔ action required	View run
Health 45 Agents Guard	✅ success	View run
Health 50 Security Scan	✅ success	View run
Health 51 Actions SAST (zizmor)	✅ success	View run
Health 52 Semgrep Scan	✅ success	View run
Health 69 Consumer Sync Shadow Evidence	✅ success	View run
Health 73 Template Completeness	✅ success	View run
Health 74 Template Drift	✅ success	View run
Maint 52 Validate Workflows	✅ success	View run
PR 11 - Minimal invariant CI	✅ success	View run
PR 46 Dependency Repair Contract	⏭️ skipped	View run
Selftest CI	✅ success	View run
Validate Sync Manifest	✅ success	View run

The guard counts prior optimizer runs for an issue by matching the issue number against `displayTitle`. workflow_dispatch runs display the bare workflow name ("Agents Issue Optimizer"), so the filter matched nothing. Observed on Fine-Art-Archive#464, which the optimizer re-ran roughly once a minute for ~20 hours while its own guard logged: Optimizer runs for issue #464 in last hour: 0 Set `run-name` so both trigger types carry `#<issue>`, raise the `gh run list` window past its 20-run default (a tight loop exhausts that inside the hour), and match with `endswith` rather than `contains` so the new suffix form cannot count #4640 against #464. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

cursor · 2026-08-08T23:15:02Z

Bugbot is not enabled for your account, so this pull request was not reviewed.

Enable Bugbot in the Cursor dashboard to get automatic reviews on future PRs.

coderabbitai · 2026-08-08T23:15:09Z

Warning

Review limit reached

You’ve reached a temporary PR review limit under our Fair Usage Limits Policy.

Your recent review volume is higher than typical usage, so adaptive limits are currently applied.

Next review available in: 19 minutes

Your organization has reached its usage spending cap. Adjust your spending cap in the billing tab.

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro

Run ID: 046f8ff8-5632-494a-a84c-6b50b4707560

📥 Commits

Reviewing files that changed from the base of the PR and between c251301 and c49feee.

📒 Files selected for processing (3)

.github/workflows/agents-issue-optimizer.yml
config/template-drift-allowlist.txt
templates/consumer-repo/.github/workflows/agents-issue-optimizer.yml

_{Comment @coderabbitai help to get the list of available commands.}

agents-workflows-bot · 2026-08-08T23:16:48Z

Automated Status Summary

Head SHA: 839396e
Latest Runs: ⏳ pending — Gate
Required contexts: summary
Required: core tests (3.12): ⏳ pending, core tests (3.13): ⏳ pending, docker smoke: ⏳ pending, gate: ⏳ pending

Workflow / Job	Result	Logs
(no jobs reported)	⏳ pending	—

Coverage Overview

Coverage history entries: 0

Updated automatically; will refresh on subsequent CI/Docker completions.

Keepalive checklist

Scope

Address unmet acceptance criteria from PR #463.

Original scope:

After merging PR chore(codex): bootstrap PR for issue #101 #103 (multi-agent routing infrastructure), we need to:
1. Validate the CLI agent pipeline works end-to-end with the new task-focused prompts
1. Add GITHUB_STEP_SUMMARY output so iteration results are visible in the Actions UI
1. Streamline the Automated Status Summary to reduce clutter when using CLI agents
1. Clean up comment patterns to avoid a mix of old UI-agent and new CLI-agent comments

Context for Agent

Related Issues/PRs

Tasks

Acceptance criteria

CLI agent receives explicit tasks in prompt and works on them
CLI agent PRs have ≤3 bot comments total (summary, one per iteration update) instead of 10+
Requires PR chore(codex): bootstrap PR for issue #101 #103 to be merged first

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 24b65c3c64

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. 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".

chatgpt-codex-connector · 2026-08-08T23:17:25Z

+run-name: >-
+  Agents Issue Optimizer #${{
+  github.event.issue.number || inputs.issue_number }}


Apply the recursion guard fix to the consumer template

This changes only the Workflows-local copy, but the manifest compiler's workflow ownership policy selects templates/consumer-repo/.github/workflows/agents-issue-optimizer.yml for consumer sync; that template still lacks run-name, uses the 20-run default, and filters with contains. Consequently, the sync workflow will continue distributing the ineffective recursion guard to Fine-Art-Archive and the other consumers, leaving the runaway loop this commit targets unfixed there. Mirror these changes into the consumer template before syncing.

AGENTS.md reference: AGENTS.md:L60-L66

Useful? React with 👍 / 👎.

Copilot

Pull request overview

This PR aims to make the issue-optimizer recursion guard actually count prior runs for a given issue by ensuring workflow runs are correlatable via displayTitle and by tightening the match logic to avoid false positives.

Changes:

Adds run-name to include #<issue> so workflow_dispatch runs can be correlated via displayTitle.
Updates the recursion-guard run correlation from contains($issue) to endswith($issue) to avoid counting #4640 as #464.
Increases gh run list history to --limit 100 so tight-loop scenarios aren’t truncated by the 20-run default.

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

+run-name: >-
+  Agents Issue Optimizer #${{
+  github.event.issue.number || inputs.issue_number }}


+          # window; ask for enough history to actually see the recursion.
          # shellcheck disable=SC2016
          count=$(gh run list \
            --workflow=agents-issue-optimizer.yml \
+            --limit 100 \


…r template Check Template Drift flagged agents-issue-optimizer.yml as unallowlisted: the root copy carried the fix and the consumer template did not. The template is the copy the fleet's 13 consumer repos actually run, so it needs the same run-name, endswith match, and --limit 100. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

Both surfaces changed in this branch, so the stored pair.11 fingerprints no longer match and the drift check reported unallowlisted content. Refresh both hashes and record this round's shared contract in the reason, per the file's existing re-baseline convention. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

stranske · 2026-08-09T08:24:07Z

Closer audit: this PR's only closing reference is long-closed #464 (closed 2026-01-03); its unresolved acceptance checklist is unrelated to this optimizer-recursion-guard diff. No durable verifier label is being applied against that stale source. Owner decision needed: identify the correct source issue, or authorize this as a no-source maintenance disposition; then the closer can route/verify it safely.

Copilot AI lite review requested due to automatic review settings August 8, 2026 23:15

stranske temporarily deployed to agent-high-privilege August 8, 2026 23:15 — with GitHub Actions Inactive

Copilot started reviewing on behalf of stranske August 8, 2026 23:15 View session

chatgpt-codex-connector Bot reviewed Aug 8, 2026

View reviewed changes

Copilot AI reviewed Aug 8, 2026

View reviewed changes

stranske temporarily deployed to agent-high-privilege August 8, 2026 23:26 — with GitHub Actions Inactive

stranske temporarily deployed to agent-high-privilege August 8, 2026 23:28 — with GitHub Actions Inactive

stranske merged commit 54d8b9e into main Aug 8, 2026
230 of 235 checks passed

stranske deleted the fix/optimizer-recursion-guard-match branch August 8, 2026 23:35

agents-workflows-bot Bot mentioned this pull request Aug 8, 2026

chore(main): release 1.20.16 #2996

Merged

stranske mentioned this pull request Aug 9, 2026

fix(agents): cap issue-format optimizer retries #2998

Merged

9 tasks

Navigation Menu

fix(agents): make the optimizer recursion guard actually correlate runs - #2993

fix(agents): make the optimizer recursion guard actually correlate runs#2993
stranske merged 3 commits into
mainfrom
fix/optimizer-recursion-guard-match

stranske commented Aug 8, 2026 •

edited by stranske-keepalive Bot

Loading

Uh oh!

cursor Bot commented Aug 8, 2026

Uh oh!

coderabbitai Bot commented Aug 8, 2026 •

edited

Loading

Review limit reached

Uh oh!

agents-workflows-bot Bot commented Aug 8, 2026 •

edited

Loading

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot Aug 8, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

stranske commented Aug 9, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

stranske commented Aug 8, 2026 • edited by stranske-keepalive Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Automated Status Summary

Scope

Context for Agent

Related Issues/PRs

Tasks

Acceptance criteria

Uh oh!

cursor Bot commented Aug 8, 2026

Uh oh!

coderabbitai Bot commented Aug 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Review limit reached

Uh oh!

agents-workflows-bot Bot commented Aug 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Automated Status Summary

Coverage Overview

Keepalive checklist

Scope

Context for Agent

Related Issues/PRs

Tasks

Acceptance criteria

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot Aug 8, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

stranske commented Aug 9, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

stranske commented Aug 8, 2026 •

edited by stranske-keepalive Bot

Loading

coderabbitai Bot commented Aug 8, 2026 •

edited

Loading

agents-workflows-bot Bot commented Aug 8, 2026 •

edited

Loading