Skip to content

Add CI failure triage runx skill#153

Open
liomilet4-png wants to merge 98 commits into
runxhq:mainfrom
liomilet4-png:codex/frantic-ci-failure-triage
Open

Add CI failure triage runx skill#153
liomilet4-png wants to merge 98 commits into
runxhq:mainfrom
liomilet4-png:codex/frantic-ci-failure-triage

Conversation

@liomilet4-png

@liomilet4-png liomilet4-png commented Jun 26, 2026

Copy link
Copy Markdown

Summary

Adds ci-failure-triage, a read-only runx skill for classifying CI failures and emitting an evidence-backed runx.ci.triage.v1 routing packet.

  • classifies failures as flake, infra, real-break, dep, or needs_agent
  • includes sealed harness cases for a deterministic real break and a truncated ambiguous failure
  • keeps the skill read-only: no reruns, issue creation, paging, repository mutation, or root-cause claims without evidence

Frantic #61 Evidence

Validation

  • runx skill inspect ./skills/ci-failure-triage --json passed locally with runx-cli 0.6.13
  • Hosted registry harness passed: 2 checks passed, 0 failed
  • runx add liomilet4-png/ci-failure-triage@sha-92622cb44366 --registry https://api.runx.ai --json succeeded
  • runx skill liomilet4-png/ci-failure-triage@sha-92622cb44366 --registry https://api.runx.ai --json produced a governed dogfood run
  • runx resume run_agent_task-ci-failure-triage-classify-output dogfood-answers.json --json sealed the dogfood run
  • runx verify --receipt skills/ci-failure-triage/harness-evidence/dogfood-receipt.json --json returned valid=true

Scope

This PR only adds the skills/ci-failure-triage/ package, public harness evidence, and dedicated evidence workflows for the new skill.

auscaster and others added 30 commits June 19, 2026 19:55
default to the /internal/thread-outbox pending cursor (drops the fragile client cursor-cache that re-walked history on a fresh runner) and listen for a board-sync repository_dispatch so the venue can trigger the drain low-latency.
a no-ua, no-browser-headers, http1.1 client is an obvious bot signature. the fetch tool now presents a current chrome ua + the browser header set and negotiates http2 with gzip/brotli, applied as overridable defaults. configurable via RUNX_HTTP_USER_AGENT and RUNX_HTTP_BROWSER=0; the anthropic and registry transports stay plain; all transport guards unchanged. tls (ja3/ja4) and http2 fingerprint matching are out of scope.
Conventional follow-up for the pushed lockfile refresh.
Adds the dependency-cve-audit runx skill and registers it in the official catalog.

Verified:
- CI green on PR runxhq#82
- node --check skills/dependency-cve-audit/run.mjs
- runx doctor skills/dependency-cve-audit --json
- runx harness skills/dependency-cve-audit --receipt-dir <tmp> --json
- packages/cli/src/skill-refs.test.ts
Adds the structured-extraction runx skill and completes the paid follow-up integration work.

Maintainer cleanup added:
- deterministic tool fixture for structured.extract
- SKILL.md frontmatter for official catalog generation
- official skill lock/Rust table/catalog allowlist entries

Verified:
- CI green on PR runxhq#80
- local merge simulation after runxhq#82
- node --check skills/structured-extraction/tools/structured/extract/run.mjs
- runx doctor skills/structured-extraction --json
- runx harness skills/structured-extraction --receipt-dir <tmp> --json
- runx dev tools/structured/extract --json with RUNX_PROJECT_DIR set to the skill root
- packages/cli/src/skill-refs.test.ts
auscaster and others added 27 commits June 24, 2026 03:12
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants