feat(autopilot): Staleness Sentinel — automated PR aging & escalation pipeline by Copilot · Pull Request #177 · labgadget015-dotcom/autonomous-github-agent

Copilot · 2026-07-01T08:19:18Z

The daily autopilot summary surfaces stale PRs (108d, 97d open in ai-automation-engine) but takes no action on them. This adds a StalenessEngine that classifies open PRs by age, tracks tier transitions in a local state file, and posts escalation comments when a PR moves to a higher-severity tier.

Core: `autopilot/staleness_engine.py`

Four-tier classification: T0 fresh (0–6d) → T1 aging (7–29d) → T2 stale (30–89d) → T3 critical (90+d)
Dry-run ON by default — no GitHub writes unless ENABLE_LIVE_MODE=true in env
init_state_from_prs() — first-run seeding of staleness_state.json without posting any comments; prevents spam on already-stale PRs at deployment time
process_prs() — escalates only on tier increases; stable or downgrading PRs are skipped
Claude-generated comments via core/llm_provider.py with a hard cap (MAX_CLAUDE_CALLS_PER_RUN, default 20, overridable via env); falls back to static templates when cap is hit or llm_config is absent
Cost logging delegated to LLMClient.get_session_cost()
Standalone CLI: python -m autopilot.staleness_engine [--init-only]

# Recommended first-run sequence (safe — seeds state, posts nothing)
python -m autopilot.staleness_engine --init-only

# Subsequent runs in dry-run (default)
python -m autopilot.staleness_engine
# [dry-run] Would escalate acme/repo/30 to T3 (critical, 108d): fix: resolve import errors…

# Go live
ENABLE_LIVE_MODE=true python -m autopilot.staleness_engine

Integration & config

autopilot/config.yaml — new staleness: block with enabled, max_claude_calls_per_run, tier day-thresholds, and state_file path
autopilot/autopilot.py — _run_staleness_check() invoked at the end of each daily run() when staleness.enabled: true; auto-seeds on first run (state file absent)

Safety

autopilot/staleness_state.json added to .gitignore (runtime state, not source)
40 new unit tests covering tier boundaries, dry-run enforcement, call-cap behaviour, state persistence, init/process logic, and GitHub API posting

Copilot

Copilot wasn't able to review any files in this pull request.

Copilot

Copilot wasn't able to review any files in this pull request.

labgadget015-dotcom · 2026-07-01T08:21:14Z

🤖 DRC Agent Analysis

Recommendation: 🟠 P1 IMPORTANT

Summary: Staleness Sentinel: Tiered PR Escalation Pipeline (Realist #1 recommendation) vs BugHunterAgent-First (Dreamer #2 top pick)

Next steps:

Step 1: Audit all 7 repo names and ownership to confirm GITHUB_TOKEN scope covers cross-repo API reads — block implementation if any repo requires separate auth
Step 2: Implement staleness_engine.py with StalenessEngine class, tiered classification logic, and dry-run guard (ENABLE_LIVE_MODE=false default) — target 6 hours
Step 3: Create .github/workflows/staleness-sentinel.yml with nightly cron, artifact download/upload for state persistence, and environment variable injection for GITHUB_TOKEN and ANTHROPIC_API_KEY
Step 4: Pre-populate staleness_state.json with PR ⚠️ Test Coverage Below Threshold - 2025-12-01 #30 (108d, ZOMBIE, notified=true) and PR ⚠️ Test Coverage Below Threshold - 2025-12-01 #31 (97d, ZOMBIE, notified=true) to prevent spam on first live run
Step 5: Run 48-hour dry-run, review logs for correct tier assignments and Claude comment quality — do not enable live mode until output is manually verified

Strategic fit: Consulting: high · Product: high · Tech debt: reduces

Analysed by GadgetLab DRC Agent (Dreamer → Realist → Critic) · Run run_1782893961096

labgadget015-dotcom · 2026-07-01T08:24:09Z

🤖 DRC Agent Analysis

Recommendation: 🟠 P1 IMPORTANT

Summary: State-Aware StalenessEngine with Action History (Dreamer ID 2, Realist Recommended)

Next steps:

Step 1: Create data/ directory in repo root and add to docker-compose.yml as a named volume mount at container path /app/data — do this before any code to unblock state persistence
Step 2: Implement autopilot/staleness_engine.py following Realist implementation path Steps 1-4, with StateStore inner class, atomic write, tier logic, and Claude call cap
Step 3: Add staleness config block to autopilot/config.yaml with dry_run: true, max_claude_calls_per_run: 10, tiers at 14/30/60 days, cooldown_days: 7 for warn and nudge
Step 4: Add startup assertion validating state_path parent is writable; add cost projection warning if daily run rate would exceed $5/month
Step 5: Integrate into autopilot/autopilot.py with config-gated optional block (Steps 6 of Realist path)

Strategic fit: Consulting: high · Product: high · Tech debt: reduces

Analysed by GadgetLab DRC Agent (Dreamer → Realist → Critic) · Run run_1782894133980

…tion pipeline

labgadget015-dotcom · 2026-07-01T08:29:23Z

🤖 DRC Agent Analysis

Recommendation: 🟠 P1 IMPORTANT

Summary: Autonomous BugHunterAgent with Claude-Powered Triage Pipeline (Dreamer ID 3, Realist recommended)

Next steps:

Step 1: Before any new code, complete the import error audit using py_compile and pylint --errors-only across all autopilot modules and commit fixes as a standalone PR to unblock CI — this is a hard prerequisite
Step 2: Add bandit, ruff, anthropic>=0.25.0 to requirements.txt and verify clean install in Docker environment; pin versions explicitly
Step 3: Implement BugHunterAgent class with BugFinding dataclass and scan() method (Bandit + Ruff JSON normalization, 50-finding cap) — no Claude calls yet; validate false-positive rate with dry run against repo
Step 4: Implement ClaudeTriage helper mirroring StalenessEngine pattern with max_claude_calls=10 default, cost logging to bug_hunter_state.json, and BudgetExhaustedError; reduce unit test target to 25 focused tests covering cap enforcement, cost accumulation, and graceful degradation
Step 5: Add bug_hunter config section to config.yaml with enabled=false, dry_run=true defaults; integrate into autopilot.py with full try/except isolation so BugHunterAgent failure never blocks StalenessEngine

Strategic fit: Consulting: high · Product: high · Tech debt: neutral

Analysed by GadgetLab DRC Agent (Dreamer → Realist → Critic) · Run run_1782894462613

labgadget015-dotcom · 2026-07-01T08:29:52Z

🤖 DRC Agent Analysis

Recommendation: 🟠 P1 IMPORTANT

Summary: Sentinel-as-Designed: Faithful StalenessEngine Implementation (Solution 1)

Next steps:

Step 1: Create autopilot/staleness_engine.py with TierState dataclass, StalenessConfig dataclass, classify_tier(), load_state(), save_state(), init_state_from_prs(), process_prs(), execute_escalation_actions(), and CLI entrypoint with --init-only and --dry-run flags
Step 2: Add generate_escalation_comment() wired to core/llm_provider.py with max_claude_calls_per_run counter enforcement and static Jinja2-style fallback template
Step 3: Add staleness: config block to autopilot/config.yaml with enabled: false, dry_run: true, tier_thresholds_days: [7, 30, 90], max_claude_calls_per_run: 5, state_file: autopilot/staleness_state.json
Step 4: Add _run_staleness_check() to autopilot/autopilot.py wrapped in try/except with structured error logging, called at end of run() guarded by config.staleness.enabled
Step 5: Add staleness_state.json to .gitignore and document state recovery procedure in README to mitigate state-loss risk

Strategic fit: Consulting: high · Product: high · Tech debt: reduces

Analysed by GadgetLab DRC Agent (Dreamer → Realist → Critic) · Run run_1782894492264

github-actions · 2026-07-01T10:26:35Z

📊 Code Complexity Analysis

Summary:

Total Functions Analyzed: 788
Average Complexity: 3.48
High Complexity Functions: 25
Low Maintainability Files: 57

⚠️ High Complexity Functions

These functions exceed the complexity threshold and should be refactored:

File	Function	Complexity	Line
`core/risk_scorer.py`	`score_pull_request`	35	141
`autopilot/autopilot.py`	`generate_summary`	24	195
`autopilot/ai_optimization/performance_monitor.py`	`get_benchmark_stats`	15	184
`.github/scripts/weekly_digest.py`	`build_blocks`	15	38
`.github/scripts/metrics_collector.py`	`parse_workflow_metrics`	14	148
`.github/scripts/setup_branch_protection.py`	`main`	14	240
`.github/scripts/self_healing_system.py`	`analyze_failure_patterns`	14	256
`.github/scripts/ai_code_suggestor.py`	`_check_import_organization`	14	113
`.github/scripts/prometheus_exporter.py`	`collect_metrics`	14	99
`.github/scripts/workflow_monitor.py`	`get_workflow_statistics`	14	216

... and 15 more

Recommendations:

Break down large functions into smaller, focused units
Extract complex conditional logic into separate functions
Use early returns to reduce nesting

🔧 Low Maintainability Files

These files have low maintainability scores and may need refactoring:

File	Score	Status
`.github/scripts/health_dashboard_generator.py`	28.14	🔴
`.github/scripts/workflow_monitor.py`	33.73	🔴
`.github/scripts/ai_code_suggestor.py`	33.76	🔴
`.github/scripts/ai_workflow_optimizer.py`	35.51	🔴
`.github/scripts/performance_benchmark.py`	39.46	🔴
`autopilot/autopilot.py`	40.18	🔴
`.github/scripts/self_healing_system.py`	40.27	🔴
`.github/scripts/threshold_monitor.py`	41.13	🔴
`.github/scripts/parallel_code_analyzer_optimized.py`	41.16	🔴
`autopilot/ai_optimization/anomaly_detector.py`	42.56	🔴
`agents/triage_agent.py`	42.79	🔴
`.github/scripts/refactoring_assistant.py`	43.03	🔴
`autopilot/ai_optimization/intelligent_cache.py`	43.28	🔴
`autopilot/ai_optimization/commit_summarizer.py`	44.05	🔴
`.github/scripts/async_parallel_analyzer.py`	44.47	🔴
`autopilot/ai_optimization/performance_monitor.py`	44.69	🔴
`.github/scripts/badge_generator.py`	45.28	🔴
`.github/scripts/copilot_integration.py`	45.37	🔴
`.github/scripts/distributed_monitoring.py`	45.53	🔴
`.github/scripts/elite_copilot.py`	45.69	🔴
`agents/dependency_agent.py`	45.76	🔴
`.github/scripts/cost_calculator.py`	46.4	🔴
`.github/scripts/inline_pr_commenter.py`	46.63	🔴
`.github/scripts/complexity_reporter.py`	46.78	🔴
`.github/scripts/pr_triage.py`	47.13	🔴
`autopilot/staleness_engine.py`	47.39	🔴
`core/risk_scorer.py`	48.15	🔴
`autopilot/ai_optimization/nlp_relevance_filter.py`	48.43	🔴
`.github/scripts/pr_inline_commenter.py`	48.47	🔴
`.github/scripts/metrics_collector.py`	48.91	🔴
`.github/scripts/dependency_updater.py`	48.91	🔴
`autopilot/ai_optimization/ml_priority_scorer.py`	49.53	🔴
`.github/scripts/changelog_generator.py`	49.75	🔴
`.github/scripts/parallel_code_analyzer.py`	49.96	🔴
`autopilot/ai_optimization/api_optimizer.py`	50.46	🟡
`.github/scripts/issue_auto_creator.py`	50.89	🟡
`agents/security_scan_agent.py`	51.04	🟡
`.github/scripts/workflow_optimizer.py`	51.67	🟡
`.github/scripts/cot_selector.py`	51.73	🟡
`.github/scripts/release_manager.py`	51.92	🟡
`.github/scripts/llm_router.py`	52.55	🟡
`.github/scripts/auto_pr.py`	52.72	🟡
`.github/scripts/notification_manager.py`	53.58	🟡
`.github/scripts/prometheus_exporter.py`	54.96	🟡
`.github/scripts/weekly_digest.py`	55.02	🟡
`core/audit_logger.py`	55.6	🟡
`.github/scripts/gather_context.py`	56.0	🟡
`core/llm_provider.py`	56.32	🟡
`.github/scripts/streaming_results.py`	56.64	🟡
`.github/scripts/setup_branch_protection.py`	57.0	🟡
`.github/scripts/optimized_github_client.py`	58.27	🟡
`agents/orchestrator_agent.py`	59.02	🟡
`agents/code_review_agent.py`	60.45	🟡
`core/github_client.py`	61.96	🟡
`core/message_queue.py`	63.22	🟡
`core/agent_config.py`	63.86	🟡
`core/idempotency.py`	64.45	🟡

Maintainability Index Guide:

🟢 85-100: Excellent maintainability
🟡 65-84: Good maintainability
🟠 50-64: Moderate maintainability (consider refactoring)
🔴 0-49: Poor maintainability (needs refactoring)

github-actions · 2026-07-01T10:26:41Z

🟢 Risk Assessment: LOW (2.1/10)

Analysed 5 files, 1059+ / 0− lines. Test coverage unchanged or improved.

Scoring breakdown

Factor	Score
Change volume — 1059 lines changed	+1.1
Risky extensions — 1 config/script files	+0.5
Draft PR — marked as draft	+0.5

✅ Eligible for auto-merge (subject to CI passing).

github-actions · 2026-07-01T10:26:52Z

🤖 Elite AI Copilot Analysis

Elite AI Copilot Analysis Report

Generated: 2026-07-01 10:26:50
Session ID: copilot_1782901610
Repository: .

🎯 Health Score: 100.0/100

🚀 Top Recommendations

✅ Repository is in excellent shape - continue current practices

📊 Detailed Insights

Code Quality Baseline Established

Category: code_quality
Severity: info
Description: Repository code quality metrics captured
Suggested Action: Continue monitoring for regressions
Confidence: 90%

Security Scan Initiated

Category: security
Severity: info
Description: No critical vulnerabilities detected in initial scan
Suggested Action: Enable continuous security monitoring
Confidence: 85%

Repository Structure Analyzed

Category: architecture
Severity: info
Description: Well-organized modular structure detected
Suggested Action: Maintain separation of concerns
Confidence: 80%

Performance Baseline Captured

Category: performance
Severity: info
Description: Repository performance metrics recorded
Suggested Action: Monitor for performance regressions
Confidence: 75%

Documentation Structure Good

Category: documentation
Severity: info
Description: Comprehensive documentation files present
Suggested Action: Keep documentation in sync with code changes
Confidence: 90%

Powered by Elite AI Copilot v1.0

github-actions · 2026-07-01T10:26:58Z

Code Quality Analysis ❌ FAILED

Duration: 0.01s
Total Issues: 10

Tool Results

pylint: ❌
flake8: ❌
bandit: ❌
radon_cc: ❌
radon_mi: ❌

View detailed results

{
  "timestamp": "2026-07-01 10:26:56",
  "elapsed_seconds": 0.01,
  "summary": {
    "total_issues": 10,
    "critical": 0,
    "high": 0,
    "medium": 0,
    "low": 0
  },
  "tools": {
    "pylint": {
      "status": "failed",
      "output": "",
      "errors": "Pylint error: [Errno 2] No such file or directory: 'pylint'"
    },
    "flake8": {
      "status": "failed",
      "output": "",
      "errors": "Flake8 error: [Errno 2] No such file or directory: 'flake8'"
    },
    "bandit": {
      "status": "failed",
      "output": "",
      "errors": "Bandit error: [Errno 2] No such file or directory: 'bandit'"
    },
    "radon_cc": {
      "status": "failed",
      "output": "",
      "errors": "Radon error: [Errno 2] No such file or directory: 'radon'"
    },
    "radon_mi": {
      "status": "failed",
      "output": "",
      "errors": "Radon MI error: [Errno 2] No such file or directory: 'radon'"
    }
  },
  "passed": false
}

github-actions · 2026-07-01T10:27:18Z

🔒 Security Scan Results

🛡️ Bandit Security Scan

🔴 HIGH: 0
🟡 MEDIUM: 9
🟢 LOW: 77

📦 Dependency Vulnerabilities

Total vulnerable dependencies: 61

Vulnerable Dependencies:

pygithub 2.9.1
aiohttp 3.14.1
multidict 6.7.1
yarl 1.24.2
pyyaml 6.0.3
... and 56 more

Security scans run automatically on every PR. View detailed reports in the Actions tab.

github-actions · 2026-07-01T10:27:24Z

🔍 Pre-commit Checks

⚠️ Pre-commit checks found issues that could not be auto-fixed.

Please run the following locally to fix them:

pre-commit run --all-files

Or install pre-commit hooks to automatically check on commit:

pre-commit install

Pre-commit hooks help maintain code quality and consistency.

Initial plan

e7a2cdf

Copilot AI assigned Copilot and labgadget015-dotcom Jul 1, 2026

Copilot started work on behalf of labgadget015-dotcom July 1, 2026 08:19 View session

Copilot AI linked an issue Jul 1, 2026 that may be closed by this pull request

📅 Daily Repository Summary - 2026-06-30 #175

Closed

labgadget015-dotcom requested a review from Copilot July 1, 2026 08:20

Copilot AI reviewed Jul 1, 2026

View reviewed changes

labgadget015-dotcom requested review from Copilot and labgadget015-dotcom July 1, 2026 08:20

Copilot AI reviewed Jul 1, 2026

View reviewed changes

labgadget015-dotcom approved these changes Jul 1, 2026

View reviewed changes

feat(autopilot): add Staleness Sentinel — automated PR aging & escala…

a4a9f2d

…tion pipeline

Copilot AI changed the title ~~[WIP] Fix import errors and implement BugHunterAgent~~ feat(autopilot): Staleness Sentinel — automated PR aging & escalation pipeline Jul 1, 2026

Copilot AI requested a review from labgadget015-dotcom July 1, 2026 08:28

Copilot finished work on behalf of labgadget015-dotcom July 1, 2026 08:28

labgadget015-dotcom approved these changes Jul 1, 2026

View reviewed changes

github-actions Bot added testing autopilot Changes to autopilot/ labels Jul 1, 2026

This was referenced Jul 3, 2026

📅 Daily Repository Summary - 2026-07-03 #182

Closed

📅 Daily Repository Summary - 2026-07-04 #183

Open

Copilot AI mentioned this pull request Jul 4, 2026

feat(autopilot): PR Dependency Graph Resolver with tier labelling #185

Draft

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(autopilot): Staleness Sentinel — automated PR aging & escalation pipeline#177

feat(autopilot): Staleness Sentinel — automated PR aging & escalation pipeline#177
labgadget015-dotcom with Copilot wants to merge 2 commits into
mainfrom
copilot/fix-import-errors-bughunteragent

Copilot AI commented Jul 1, 2026 •

edited

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI left a comment

Uh oh!

labgadget015-dotcom commented Jul 1, 2026

Uh oh!

labgadget015-dotcom commented Jul 1, 2026

Uh oh!

labgadget015-dotcom commented Jul 1, 2026

Uh oh!

labgadget015-dotcom commented Jul 1, 2026

Uh oh!

github-actions Bot commented Jul 1, 2026

Uh oh!

github-actions Bot commented Jul 1, 2026

Uh oh!

github-actions Bot commented Jul 1, 2026

Uh oh!

github-actions Bot commented Jul 1, 2026

Uh oh!

github-actions Bot commented Jul 1, 2026

Uh oh!

github-actions Bot commented Jul 1, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

Copilot AI commented Jul 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Core: autopilot/staleness_engine.py

Integration & config

Safety

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Uh oh!

labgadget015-dotcom commented Jul 1, 2026

🤖 DRC Agent Analysis

Uh oh!

labgadget015-dotcom commented Jul 1, 2026

🤖 DRC Agent Analysis

Uh oh!

labgadget015-dotcom commented Jul 1, 2026

🤖 DRC Agent Analysis

Uh oh!

labgadget015-dotcom commented Jul 1, 2026

🤖 DRC Agent Analysis

Uh oh!

github-actions Bot commented Jul 1, 2026

📊 Code Complexity Analysis

⚠️ High Complexity Functions

🔧 Low Maintainability Files

Uh oh!

github-actions Bot commented Jul 1, 2026

🟢 Risk Assessment: LOW (2.1/10)

Scoring breakdown

Uh oh!

github-actions Bot commented Jul 1, 2026

🤖 Elite AI Copilot Analysis

Elite AI Copilot Analysis Report

🎯 Health Score: 100.0/100

🚀 Top Recommendations

📊 Detailed Insights

Code Quality Baseline Established

Security Scan Initiated

Repository Structure Analyzed

Performance Baseline Captured

Documentation Structure Good

Uh oh!

github-actions Bot commented Jul 1, 2026

Code Quality Analysis ❌ FAILED

Tool Results

Uh oh!

github-actions Bot commented Jul 1, 2026

🔒 Security Scan Results

🛡️ Bandit Security Scan

📦 Dependency Vulnerabilities

Vulnerable Dependencies:

Uh oh!

github-actions Bot commented Jul 1, 2026

🔍 Pre-commit Checks

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Copilot AI commented Jul 1, 2026 •

edited

Loading

Core: `autopilot/staleness_engine.py`