Fix skill workflow regression coverage (#783)

Clarify launcher fallback and completed documentation handoffs; separate bounded protocol checkpoints from opt-in browser-backed completion diagnostics. Correct fixture containment, target syntax, and artifact assertions. AI assistance: Codex, under maintainer direction.
This commit is contained in:
Paul Bakaus
2026-09-08 08:41:54 -07:00
committed by GitHub
parent 2bc2879276
commit 6496f49a1e
23 changed files with 1305 additions and 154 deletions
+47
View File
@@ -6,6 +6,11 @@ on:
pull_request:
branches: [main]
workflow_dispatch:
inputs:
skill_workflow:
description: 'Run billed, browser-backed Claude workflow completion tests'
type: boolean
default: false
# Nightly full live-e2e matrix. The smoke groups already gate every PR; the
# full sweep is too slow for that, so it runs once a day against main.
schedule:
@@ -665,5 +670,47 @@ jobs:
- name: Install dependencies
run: bun install
- name: Prepare engine for protocol tests
run: bun run fetch:engine
- name: Run skill behavior tests
run: bun run test:skill-behavior
skill-workflow:
# Expensive, manually opted-in completion diagnostics. This does not
# replace the multi-family skill-behavior protocol suite above.
runs-on: ubuntu-latest
if: github.event_name == 'workflow_dispatch' && inputs.skill_workflow
timeout-minutes: 70
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
IMPECCABLE_SKILL_BEHAVIOR_MODELS: claude-sonnet-5
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Setup Node
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
with:
node-version: 24
- name: Setup Bun
uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2.2.0
with:
bun-version: latest
- name: Install dependencies
run: bun install --frozen-lockfile
- name: Prepare engine and browser before billing
run: |
test -n "$ANTHROPIC_API_KEY" || { echo 'ANTHROPIC_API_KEY is required'; exit 1; }
bun run fetch:engine
bunx playwright install --with-deps chromium
- name: Run completed skill workflows
env:
IMPECCABLE_SKILL_BEHAVIOR_TRACE_DIR: ${{ runner.temp }}/skill-workflow-traces
run: bun run test:skill-workflow
- name: Retain diagnostic traces
if: always()
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
with:
name: skill-workflow-traces
path: ${{ runner.temp }}/skill-workflow-traces
retention-days: 7