mirror of
https://github.com/PX4/PX4-Autopilot.git
synced 2026-11-22 14:19:57 +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>
18 lines
512 B
JSON
18 lines
512 B
JSON
{
|
|
"_comment": "Models the review may use. To upgrade, change bedrock_profile and label here; see README.md, Updating models.",
|
|
"models": {
|
|
"opus": {
|
|
"bedrock_profile": "global.anthropic.claude-opus-5-5",
|
|
"label": "Claude Opus 5.5"
|
|
},
|
|
"sonnet": {
|
|
"bedrock_profile": "global.anthropic.claude-sonnet-5-5",
|
|
"label": "Claude Sonnet 5.5"
|
|
}
|
|
},
|
|
"defaults": {
|
|
"reviewer": {"model": "opus", "effort": "xhigh"},
|
|
"validator": {"model": "opus", "effort": "high"}
|
|
}
|
|
}
|