• Home
  • Features
  • Pricing
  • Docs
  • Announcements
  • Sign In

zwave-js / zwave-js-ui / 30525098149
12%

Build:
DEFAULT BRANCH: master
Ran 30 Jul 2026 08:03AM UTC
Jobs 1
Files 50
Run time 1min
Badge
Embed ▾
README BADGES
x

If you need to use a raster PNG badge, change the '.svg' to '.png' in the link

Markdown

Textile

RDoc

HTML

Rst

30 Jul 2026 08:02AM UTC coverage: 12.408% (-0.1%) from 12.503%
30525098149

push

github

web-flow
feat(bot): judge docs answers with an agentic workflow (#4765)

## Description

Last of three PRs migrating off GitHub Models (based on #4764, porting
zwave-js/zwave-js#8987). The docs answer bot's gpt-4o judge moves to a
gh-aw workflow on the Copilot engine, split so only the judgment is
agentic:

- **Pre-activation** keeps all deterministic gates (excluded users,
categories, existing answers, suppression list) plus the index
restore/health machinery (`restore-bot-index`, `report-index-status`),
retrieves the doc excerpts, posts related-posts-only comments directly,
and only gates the engine on when doc excerpts need judging
- **The judge** reads a projected `judge-input.json` (question + excerpt
text, no embedding vectors) and reports
`confidence`/`answer`/`related_excerpts` through a typed safe-output
job, capped at 5 turns with no GitHub toolset and no tool egress. Its
prompt is the former `judgeAnswer` system prompt, including the
untrusted-input rule
- **The safe-output job** validates the verdict (length-capped, tolerant
id parsing) and composes/posts the comment with the same confidence
thresholds, answer sanitizer, link dedup and feedback metadata (now
including the run id) as before, and re-checks `alreadyAnswered` to
avoid duplicate answers from overlapping runs

This removes the last GitHub Models consumer: `modelsApi.cjs` and the
eval's `--answers` mode are gone, and no workflow requests `models:
read` anymore.

## Validation

- Mocked end-to-end dry run against real rebuilt indexes: on-topic
question → handoff with the right excerpts, engine gated on; off-topic →
everything gated off; judge verdict → correctly composed comment with
doc links
- Unit tests cover the render thresholds, all four comment shapes, the
answer gates, and a prepare→post round trip pinning the handoff
contract; `gh aw compile` clean, all 156 bot-script tests pass

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Fabl... (continued)

493 of 4531 branches covered (10.88%)

Branch coverage included in aggregate %.

938 of 7002 relevant lines covered (13.4%)

2.08 hits per line

Coverage Regressions

Lines Coverage ∆ File
9
67.33
-5.45% api/lib/logger.ts
Jobs
ID Job ID Ran Files Coverage
1 30525098149.1 30 Jul 2026 08:03AM UTC 50
12.41
GitHub Action Run
Source Files on build 30525098149
  • Tree
  • List 50
  • Changed 1
  • Source Changed 0
  • Coverage Changed 1
Coverage ∆ File Lines Relevant Covered Missed Hits/Line Branch Hits Branch Misses
  • Back to Repo
  • 5169a12b on github
  • Prev Build on master (#30358332220)
  • Delete
STATUS · Troubleshooting · Open an Issue · Sales · Support · CAREERS · ENTERPRISE · START FREE TRIAL · SCHEDULE DEMO
ANNOUNCEMENTS · TWITTER · TOS & SLA · Supported CI Services · What's a CI service? · Automated Testing

© 2026 Coveralls, Inc