Files
AutoGPT/docs/integrations/github/checks.md
Nicholas Tindle c1a1767034 feat(docs): Add block documentation auto-generation system (#11707)
- Add generate_block_docs.py script that introspects block code to
generate markdown
- Support manual content preservation via <!-- MANUAL: --> markers
- Add migrate_block_docs.py to preserve existing manual content from git
HEAD
- Add CI workflow (docs-block-sync.yml) to fail if docs drift from code
- Add Claude PR review workflow (docs-claude-review.yml) for doc changes
- Add manual LLM enhancement workflow (docs-enhance.yml)
- Add GitBook configuration (.gitbook.yaml, SUMMARY.md)
- Fix non-deterministic category ordering (categories is a set)
- Add comprehensive test suite (32 tests)
- Generate docs for 444 blocks with 66 preserved manual sections

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

<!-- Clearly explain the need for these changes: -->

### Changes 🏗️

<!-- Concisely describe all of the changes made in this pull request:
-->

### Checklist 📋

#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
  <!-- Put your test plan here: -->
  - [x] Extensively test code generation for the docs pages



<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> Introduces an automated documentation pipeline for blocks and
integrates it into CI.
> 
> - Adds `scripts/generate_block_docs.py` (+ tests) to introspect blocks
and generate `docs/integrations/**`, preserving `<!-- MANUAL: -->`
sections
> - New CI workflows: **docs-block-sync** (fails if docs drift),
**docs-claude-review** (AI review for block/docs PRs), and
**docs-enhance** (optional LLM improvements)
> - Updates existing Claude workflows to use `CLAUDE_CODE_OAUTH_TOKEN`
instead of `ANTHROPIC_API_KEY`
> - Improves numerous block descriptions/typos and links across backend
blocks to standardize docs output
> - Commits initial generated docs including
`docs/integrations/README.md` and many provider/category pages
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
631e53e0f6. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-19 07:03:19 +00:00

4.2 KiB

GitHub Checks

Blocks for creating and updating GitHub check runs, enabling custom CI integration and detailed status reporting on commits and pull requests.

Github Create Check Run

What it is

Creates a new check run for a specific commit in a GitHub repository

How it works

This block creates a new check run associated with a specific commit using the GitHub Checks API. Check runs represent individual test suites, linting tools, or other CI processes that report status against commits or pull requests.

You specify the commit SHA, check name, and current status. For completed checks, provide a conclusion (success, failure, or neutral) and optional detailed output including title, summary, and extended text for rich reporting in the GitHub UI.

Inputs

Input Description Type Required
repo_url URL of the GitHub repository str Yes
name The name of the check run (e.g., 'code-coverage') str Yes
head_sha The SHA of the commit to check str Yes
status Current status of the check run "queued" | "in_progress" | "completed" | "waiting" | "requested" | "pending" No
conclusion The final conclusion of the check (required if status is completed) "success" | "failure" | "neutral" | "cancelled" | "timed_out" | "action_required" | "skipped" No
details_url The URL for the full details of the check str No
output_title Title of the check run output str No
output_summary Summary of the check run output str No
output_text Detailed text of the check run output str No

Outputs

Output Description Type
error Error message if check run creation failed str
check_run Details of the created check run CheckRunResult

Possible use case

Custom CI Integration: Create check runs for external CI systems that aren't natively integrated with GitHub.

Code Quality Reporting: Report linting, security scan, or test coverage results directly on commits and PRs.

Deployment Status: Track deployment progress by creating check runs that show pending, in-progress, and completed states.


Github Update Check Run

What it is

Updates an existing check run in a GitHub repository

How it works

This block updates an existing check run's status, conclusion, and output details via the GitHub Checks API. Use it to report progress as your CI process advances through different stages.

You can update the status from queued to in_progress to completed, and set the final conclusion when done. The output fields allow you to provide detailed results, annotations, and summaries visible in the GitHub UI.

Inputs

Input Description Type Required
repo_url URL of the GitHub repository str Yes
check_run_id The ID of the check run to update int Yes
status New status of the check run "queued" | "in_progress" | "completed" | "waiting" | "requested" | "pending" Yes
conclusion The final conclusion of the check (required if status is completed) "success" | "failure" | "neutral" | "cancelled" | "timed_out" | "action_required" | "skipped" Yes
output_title New title of the check run output str No
output_summary New summary of the check run output str No
output_text New detailed text of the check run output str No

Outputs

Output Description Type
error Error message if the operation failed str
check_run Details of the updated check run CheckRunResult

Possible use case

Progress Reporting: Update check runs as your CI pipeline progresses through build, test, and deployment stages.

Real-Time Feedback: Provide immediate feedback on pull requests as tests complete, rather than waiting for the entire suite.

Failure Details: Update check runs with detailed error messages and output when tests fail.