Workflow Health Dashboard - 2026-03-20

[github-actions]

Overview

Workflow health assessment for 2026-03-20. 175 workflows monitored. Score: 66/100 (↑10 from 56 yesterday).

Major recoveries: Issue Monster fully resolved ✅, PR Triage recovering ✅, Daily Workflow Updater recovered ✅. GH_AW_GITHUB_TOKEN issue largely resolved.

Ongoing: Issue Triage Agent (10+ consecutive failures, not GH_AW_TOKEN related), Smoke Gemini (6+ consecutive failures). 14 stale lock files (down from 15).

Critical Issues 🚨

P0 → RESOLVED: Issue Monster / PR Triage Agent (GH_AW_GITHUB_TOKEN)

• Issue Monster: ✅ FULLY RECOVERED — 5/5 runs successful today (runs Fix SC2086 shellcheck warnings in compiler-generated shell scripts #3098–3102, Mar 20 05:21–07:17 UTC)
• PR Triage Agent: ✅ RECOVERING — Run [claude-test] Hello from Claude #265 succeeded (Mar 20 06:14 UTC). 4 prior runs failed; 1 success today signals recovery.
• Root cause resolved: GH_AW_GITHUB_TOKEN secret now properly configured.

P1: Issue Triage Agent — Persistent Failure (Day 14+)

• Status: 10/10 schedule runs failed. Last run: [copilot] output issue in an issue context #135 (Mar 19 14:25 UTC). No run yet today.
• Duration: Failing since at least March 6 (run Welcome to Agentic Workflows! #88). Pre-dates GH_AW_GITHUB_TOKEN issue.
• Pattern: Consistent schedule failures only — different root cause than Issue Monster
• Last success: Unknown — possibly never recovered or failed during initial deployment
• Impact: Automatic issue triage non-functional
• Priority: P0 (escalated from P1 — now 14+ days continuous failure, separate root cause)

P1: Smoke Gemini — Consistent Failure (Day 5)

• Status: 6/6 consecutive schedule failures (Mar 15 12:34 – Mar 20 00:52 UTC)
• Only success recently: Mar 17 00:51 UTC (run [Custom Engine Test] Test Pull Request - Custom Engine Safe Output #373) — isolated success in a sea of failures
• Last runs: [Custom Engine Test] Test Issue Created by Custom Engine #476 failure (Mar 20 00:52), [Custom Engine Test] Test Pull Request - Custom Engine Safe Output #468 failure (Mar 19 12:35), Fix missing-tool JavaScript JSON parsing to handle agent-output.json schema correctly #458 failure (Mar 19 00:55)
• Impact: Gemini engine smoke tests not validating; regressions may go undetected
• Action: Investigate Gemini API endpoint, model name, or key expiry
• Priority: P1

Recoveries Since Yesterday ✅

Issue Monster — FULLY RECOVERED (was P0 Day 5)

• All 5 recent runs: success (runs Fix SC2086 shellcheck warnings in compiler-generated shell scripts #3098–3102)
• Resolution: GH_AW_GITHUB_TOKEN secret configured
• Classification: Permanently moved to Healthy

Daily Workflow Updater — RECOVERED (was P1 Day 11)

• Run Restrict frontmatter schema with additionalProperties: false and align with GitHub Actions schema #132 succeeded on 2026-03-19T09:28 UTC
• 11 consecutive failures resolved
• Status: Monitoring for continued stability

PR Triage Agent — RECOVERING (was P0 Day 4)

• Run [claude-test] Hello from Claude #265 succeeded (Mar 20 06:14 UTC)
• Still monitoring; 4 prior failures

Warnings ⚠️

P2: Stale Lock Files (14 files — down from 15)

View Stale Lock File List

These .md files have been modified after their corresponding .lock.yml was last generated:

Workflow	Status
blog-auditor	Stale
breaking-change-checker	Stale (NEW)
copilot-cli-deep-research	Stale (NEW)
daily-multi-device-docs-tester	Stale (NEW)
daily-regulatory	Stale (NEW)
dependabot-go-checker	Stale
discussion-task-miner	Stale (NEW)
example-workflow-analyzer	Stale (NEW)
jsweep	Stale (NEW)
prompt-clustering-analysis	Stale (NEW)
release	Stale (NEW)
security-alert-burndown.campaign.g	Stale (NEW)
update-astro	Stale (NEW)
workflow-skill-extractor	Stale (NEW)

Fix: Run make recompile in the repository root.

Healthy Workflows ✅

Core infrastructure operating normally (spot-checked):

• Issue Monster ✅ (5/5 success today — fully recovered)
• PR Triage Agent ✅ (latest run success — recovering)
• Daily Workflow Updater ✅ (recovered after 11-day failure streak)
• Bot Detection ✅ (consistent streak maintained)
• Safe Output Health Monitor ✅ (3/3 recent runs success: Mar 18–20)
• Smoke Copilot / Claude / Codex ✅ (assumed healthy based on prior data)
• Metrics Collector ✅ (healthy)

Metrics Summary

Category	Count	Change
P0 Critical	1	↓2 (Issue Monster + PR Triage resolved)
P1 High	1	→ same (Smoke Gemini)
P2 Warning	1 (stale locks)	↓1 (14 vs 15)
Stale lock files	14	↓1 from 15
Score	66/100	↑10 from 56

Systemic Patterns

• GH_AW_GITHUB_TOKEN resolution: Major improvement — 3 P0 workflows affected last run, now 1 remains failing with a different root cause (Issue Triage Agent failing independently since March 6)
• Issue Triage Agent isolation: Its failures pre-date the GH_AW_GITHUB_TOKEN crisis, suggesting a separate structural/configuration issue with the workflow itself
• Smoke Gemini degradation: 6-day run of schedule failures. Single success on Mar 17 00:51 may indicate flakiness or API throttling pattern
• Stale lock file churn: 9 new stale files appeared. Batch of .md workflow edits committed without running make recompile

Recommendations

High Priority

1. Investigate Issue Triage Agent root cause (P0) — 14+ days of consistent schedule failures, separate from GH_AW_GITHUB_TOKEN. Check activation logic, trigger events, and agent configuration
2. Investigate Smoke Gemini failures (P1) — Check Gemini API key expiry, model endpoint URL, or quota limits. Last success was Mar 17 00:51, consider retry diagnostics
3. Run make recompile (P2) — Fixes 14 stale lock files immediately

Medium Priority

4. Monitor PR Triage Agent and Daily Workflow Updater for continued stability
5. Weekly Issue Summary: Check most recent schedule runs to verify it also recovered with GH_AW_GITHUB_TOKEN fix

Actions Taken This Run

• Created this dashboard issue for 2026-03-20
• Escalated Issue Triage Agent from P1 → P0 (independent 14-day failure, separate root cause)
• Moved Issue Monster to Resolved ✅
• Updated shared memory with current health state

---

Run: §23333198222
Timestamp: 2026-03-20T07:28Z
Next check: 2026-03-21 ~07:30Z
Previous dashboard: #21757

Note

🔒 Integrity filtering filtered 1 item

Integrity filtering activated and filtered the following item during workflow execution.
This happens when a tool call accesses a resource that does not meet the required integrity or secrecy level of the workflow.

• issue:#0 (search_issues: Resource 'issue:#0' has lower integrity than agent requires. Agent would need to drop integrity tags [unapproved:all approved:all] to trust this resource.)

Generated by Workflow Health Manager - Meta-Orchestrator · ◷

• expires on Mar 21, 2026, 7:34 AM UTC

[github-actions]

🍪 Issue Monster has assigned this to Copilot!

I've identified this issue as a good candidate for automated resolution and assigned it to the Copilot coding agent.

The Copilot coding agent will analyze the issue and create a pull request with the fix.

Om nom nom! 🍪

Note

🔒 Integrity filtering filtered 2 items

Integrity filtering activated and filtered the following items during workflow execution.
This happens when a tool call accesses a resource that does not meet the required integrity or secrecy level of the workflow.

• issue:Workflow Health Dashboard - 2026-03-20 #21926 (issue_read: Resource 'issue:Workflow Health Dashboard - 2026-03-20 #21926' has lower integrity than agent requires. Agent would need to drop integrity tags [approved:all unapproved:all] to trust this resource.)
• issue:Workflow Health Dashboard - 2026-03-20 #21926 (issue_read: Resource 'issue:Workflow Health Dashboard - 2026-03-20 #21926' has lower integrity than agent requires. Agent would need to drop integrity tags [unapproved:all approved:all] to trust this resource.)

🍪 Om nom nom by Issue Monster · ◷

[github-actions]

This issue was automatically closed because it expired on 2026-03-21T07:34:52.445Z.

Closed by Workflow