|
| 1 | +name: Nightly SDK Gap Audit |
| 2 | + |
| 3 | +on: |
| 4 | + schedule: |
| 5 | + - cron: "0 6 * * *" |
| 6 | + workflow_dispatch: |
| 7 | + |
| 8 | +permissions: |
| 9 | + contents: read |
| 10 | + |
| 11 | +concurrency: |
| 12 | + group: provider-gap-audit-${{ github.ref }} |
| 13 | + cancel-in-progress: false |
| 14 | + |
| 15 | +jobs: |
| 16 | + audit-sdk-coverage: |
| 17 | + name: Audit SDK Coverage |
| 18 | + runs-on: ubuntu-latest |
| 19 | + timeout-minutes: 45 |
| 20 | + steps: |
| 21 | + - name: Generate GitHub App token |
| 22 | + id: app-token |
| 23 | + uses: actions/create-github-app-token@f8d387b68d61c58ab83c6c016672934102569859 # v3.0.0 |
| 24 | + with: |
| 25 | + app-id: ${{ secrets.BRAINTRUST_BOT_APP_ID }} |
| 26 | + private-key: ${{ secrets.BRAINTRUST_BOT_PRIVATE_KEY }} |
| 27 | + owner: braintrustdata |
| 28 | + repositories: | |
| 29 | + braintrust-sdk-python |
| 30 | + permission-contents: read |
| 31 | + permission-issues: write |
| 32 | + |
| 33 | + - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1 |
| 34 | + with: |
| 35 | + persist-credentials: false |
| 36 | + |
| 37 | + - name: Run Claude provider gap audit |
| 38 | + uses: anthropics/claude-code-action@df37d2f0760a4b5683a6e617c9325bc1a36443f6 # v1.0.75 |
| 39 | + with: |
| 40 | + anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }} |
| 41 | + # Pass our own app token so the Claude action does not try to mint its |
| 42 | + # own GitHub token via OIDC. That OIDC path currently fails for this |
| 43 | + # workflow shape upstream, and this app token also lets us tightly scope |
| 44 | + # Claude's remote permissions to repo contents read + issues write only. |
| 45 | + github_token: ${{ steps.app-token.outputs.token }} |
| 46 | + prompt: | |
| 47 | + # Goal |
| 48 | +
|
| 49 | + Find important instrumentation gaps in this repository's AI-facing integrations. |
| 50 | +
|
| 51 | + A gap means the upstream SDK or framework clearly supports something that this repository does not yet instrument, or instruments with materially less detail. |
| 52 | +
|
| 53 | + # Scope |
| 54 | +
|
| 55 | + This repository is the Braintrust Python SDK. Focus exclusively on the Python integrations it ships. |
| 56 | + Discover them by inspecting the following directories in the checked-out repository: |
| 57 | +
|
| 58 | + - `py/src/braintrust/wrappers/` — AI provider wrappers and framework integrations |
| 59 | + - `py/src/braintrust/contrib/` — additional contributed integrations |
| 60 | + - `py/examples/` — usage examples that reveal what surfaces are considered supported |
| 61 | +
|
| 62 | + Do not look at the `integrations/` directory (deprecated old integrations). |
| 63 | +
|
| 64 | + - Infer additional relevant surfaces from the checked-out repository itself (tests, noxfile.py, pyproject.toml). |
| 65 | + - Ignore generic runtime or infrastructure integrations that do not have an upstream AI API surface to compare against. |
| 66 | + - Do not open parity issues for deprecated or no-op surfaces unless you find real deprecation drift or docs drift worth reporting. |
| 67 | +
|
| 68 | + # Process |
| 69 | +
|
| 70 | + 1. Inspect local code, tests, docs, examples, and e2e scenarios to understand what is already instrumented. |
| 71 | + 2. For each relevant surface, independently discover the current official upstream docs and recent official releases or changelogs. |
| 72 | + 3. Compare current upstream capabilities to current Braintrust instrumentation in this repo. |
| 73 | + 4. Always check the latest Braintrust docs at https://www.braintrust.dev/docs before deciding how to describe a gap. |
| 74 | + 5. Search existing GitHub issues for duplicates before creating anything. |
| 75 | + 6. Only act on high-confidence, concrete gaps tied to missing APIs, unsupported call patterns, or missing instrumentation detail. |
| 76 | +
|
| 77 | + # Examples |
| 78 | +
|
| 79 | + ## Good |
| 80 | +
|
| 81 | + - The upstream SDK now has a stable `responses.stream()` helper, but this repo does not instrument it at all, or instruments it without final result metadata that other similar APIs already capture here. |
| 82 | + - This repo instruments a provider's basic text generation API, but not its newer tool-calling or agent tracing API even though that API is now official and documented. |
| 83 | +
|
| 84 | + ## Bad |
| 85 | +
|
| 86 | + - A vague suspicion that "something in streaming may be missing" without a concrete upstream API and a concrete repo gap. |
| 87 | + - Opening a separate issue for every release note bullet when they all describe the same missing instrumentation area. |
| 88 | +
|
| 89 | + # If You Find Actionable Non-Duplicate Gaps |
| 90 | +
|
| 91 | + - Create at most 5 issues in this run. |
| 92 | + - Create one issue per distinct gap. |
| 93 | + - Keep each issue concise, concrete, and source-backed. |
| 94 | + - Include a hidden marker comment near the top of the issue body in this exact form: |
| 95 | +
|
| 96 | + ```html |
| 97 | + <!-- provider-gap-audit: <gap_id> --> |
| 98 | + ``` |
| 99 | +
|
| 100 | + Each issue should clearly include: |
| 101 | +
|
| 102 | + - what instrumentation is missing |
| 103 | + - whether Braintrust docs suggest the capability is `supported`, `unclear`, or `not_found` |
| 104 | + - exact upstream sources |
| 105 | + - exact Braintrust docs source or sources |
| 106 | + - exact local repo files you inspected |
| 107 | +
|
| 108 | + # Duplicate Handling |
| 109 | +
|
| 110 | + - Do not create an issue if an open issue already covers the same gap. |
| 111 | + - Treat a matching hidden marker comment or a clearly equivalent open issue as a duplicate. |
| 112 | + - If duplicate checking is inconclusive, do not create the issue. |
| 113 | +
|
| 114 | + # Constraints |
| 115 | +
|
| 116 | + - Discover source URLs yourself. Do not rely on a preset list. |
| 117 | + - Prefer official docs and official release sources. |
| 118 | + - Do not create comments. |
| 119 | + - Do not update, close, or label existing issues. |
| 120 | + - Do not create pull requests. |
| 121 | + - If there are no high-confidence non-duplicate gaps, do nothing. |
| 122 | + # The Claude action includes base GitHub tools by default, and --allowedTools adds to that set |
| 123 | + # rather than replacing it. Keep the deny-list so Claude cannot use other remote write tools. |
| 124 | + claude_args: | |
| 125 | + --model claude-opus-4-6 |
| 126 | + --max-turns 20 |
| 127 | + --allowedTools "Read,Glob,Grep,LS,WebSearch,WebFetch,mcp__github__get_issue,mcp__github__get_issue_comments,mcp__github__search_issues,mcp__github__list_issues,mcp__github__create_issue" |
| 128 | + --disallowedTools "Bash,Edit,MultiEdit,Write,Replace,NotebookEditCell,mcp__github__create_issue_comment,mcp__github__update_issue,mcp__github__create_pr,mcp__github__create_or_update_file,mcp__github__delete_file,mcp__github_file_ops__commit_files,mcp__github_file_ops__delete_files" |
0 commit comments