Ship a GitHub Action so agent PRs are verified in CI
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 45/100
Research direction
Start with the existing backcheck --json schema and the CLI entry points for --format github, --format markdown, and fail-on. The main action and transcript transport still need a design decision among the three options described. A smaller contribution is done when one listed output mode or the documented exit-code contract has defined behavior and supporting coverage.
Written by the indexing model from the issue text.
Description
Locally, backcheck runs as a Stop hook and catches an unsupported claim the moment it is made.
That only protects the person who installed it. The claims that do the most damage are the ones
in a pull request description that a reviewer takes at face value.
The idea
- uses: VectorInstitute/backcheck@v1
with:
transcript: .backcheck/session.jsonl # committed or uploaded as an artifact
fail-on: unsupported # unsupported | contradicted | never
comment: true # post findings as a PR review comment
The action would post something a reviewer can act on:
backcheck — 1 claim not fully supported
- tests pass:
pytestpassed, but only a subset ran (tests/test_billing.py)- test integrity: a skip marker was added to
tests/test_billing.py
Why it needs design first
The hard part is not the action, it is getting the transcript to CI. Options, none obviously
right:
- A
SessionEndhook writes a redacted summary into the repo, committed with the work. - The agent uploads the transcript as a workflow artifact.
backcheckemits a signed, minimal "evidence receipt" (claims + verdicts + the commands
that ran, no file contents) small enough to live in a commit trailer or PR body.
Option 3 is the interesting one and the most privacy-preserving — a transcript is far too
sensitive to commit, but the conclusions are not.
Worth discussing the shape here before anyone writes code. backcheck --json already produces
a stable schema that could be the basis for the receipt.
Smaller pieces anyone can pick up
- a
--format githuboutput mode producing workflow annotations (::warning file=...) - a
--format markdownmode suitable for a PR comment - a documented exit-code contract for
fail-onbehaviour
- Dominant language
- Rust
- Stars
- 0
- Forks
- 2
- PR merge metrics
- No merged PRs in 30d
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from VectorInstitute/backcheck
-
accuracy false-negative false-positive help wanted
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
-
good first issue help wanted runner
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
-
accuracy enhancement help wanted
Difficulty 5/5 Over a week Newbie friendliness 32/100
VectorInstitute/backcheck#11 ·
-
enhancement good first issue help wanted
Difficulty 4/5 3-5 days Newbie friendliness 55/100
VectorInstitute/backcheck#10 ·
-
enhancement good first issue help wanted
Difficulty 3/5 1-2 days Newbie friendliness 68/100
All issues in VectorInstitute/backcheck
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
Eynzof/Hermes-CN-Desktop#610 ·
-
bug team:backend track:services-maintenance
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
cowprotocol/services#4950 ·
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
gitbutlerapp/gitbutler#15998 · 1 comment ·
-
bug triage:deciding
Difficulty 1/5 Under an hour Newbie friendliness 88/100
open-telemetry/otel-arrow#4132 ·