[aw] Failure Investigator (6h)

Durable reports produced by .github/workflows/aw-failure-investigator.md in github/gh-aw.

standalone

.github/workflows/aw-failure-investigator.md

View authored workflow

Reports

0 Open 2 Resolved

Daily Rendering Scripts Verifier completed with no action

Daily Rendering Scripts Verifier Daily Rendering Scripts Verifier: no action needed. Most recent run overall (Avenger, run 33064033499) failed at sandbox/CLI startup before producing any real agent transcript, so it could not be used to test the parser. Fell back to the next most recent run with real output: [aw] Failure Investigator (6h) (run 33060910129, Claude engine, https://github.com/github/gh-aw/actions/runs/33060910129). Verification: parseclaudelog.cjs ran against the real agent-stdio.log via a temporary vitest spec (npm run test:js) with no exceptions and a well-formed 1315-byte markdown summary (4 turns, 237170 tokens, cost 0.2116 USD). rendertemplate.cjs existing test suite: 3...

complete live noop

[agentic-token-optimizer] Optimize [aw] Failure Investigator (6h): unused MCP toolset + sub-agent consolidation

Target Workflow [aw] Failure Investigator (6h) (.github/workflows/aw-failure-investigator.lock.yml, source aw-failure-investigator.md) Selected because it is the single highest-AIC workflow in the last 7 days (top-workflows.json), has not been optimized in the last 14 days (last touched: none found in optimization-log.json), and its name does not contain "Token". Analysis Period + Runs Analyzed 7-day window snapshot: 1 run, AIC 254.60, 89,361 raw tokens (top-workflows.json). Historical daily snapshots: 2026-07-07 (AIC 105.21), 2026-07-08 (AIC 145.90) — AIC has grown 2.4x since early July for a functionally unchanged prompt. API-confirmed run history (last 15 scheduled runs): 14 success, 1...

closed review issue