mirror of
https://github.com/PX4/PX4-Autopilot.git
synced 2026-11-23 07:00:49 +08:00
Tools/ci/ai_review reviews a PR with Claude Code on Amazon Bedrock and writes a pr-review artifact for pr-review-poster.py. - Pipeline: gather (metadata, linked issues, commits, CI status, per-file patches, earlier comments), a reviewer pass returning line findings, PR-level findings and a contribution checklist, an independent validator pass per finding, and code-owned routing: inline only at high confidence, otherwise a before-merge list or a collapsed section. No PR is skipped for size; generated files are listed but not diffed. - Trust: the PR is untrusted data. The agent runs --bare --restricted with read-only tools. Code it writes to check its math runs only in a px4-dev container (no network, no credentials, read-only checkout, gVisor in CI), and `harden` blocks the runner's metadata service first. Output containing a credential is never written. - A model refusal produces no review and passes the provider's exact reason, category and request ID through. - Models and per-role defaults live in models.json; models-check verifies access before switching. - Process checks (tests, description, upgrade notes, docs) live in a CI-only prompt so the interactive skill stays lean. Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Ramon Roche <mrpollo@gmail.com>
12 lines
290 B
Python
Executable File
12 lines
290 B
Python
Executable File
#!/usr/bin/env python3
|
|
"""Entry point the review agent may call; see ai_review/sandbox.py."""
|
|
import os
|
|
import sys
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(
|
|
os.path.realpath(__file__)))))
|
|
|
|
from ai_review import sandbox # noqa: E402
|
|
|
|
sys.exit(sandbox.main())
|