Group review, feedback, evaluation, observability, and entrypoint code into packages. Keep thin top-level compatibility shims for existing scripts and imports, and mirror the structure in the tests.
3.4 KiB
pragent pilot
The pilot is a central, stdlib-only Gitea webhook service. It reviews opted-in pull requests with an on-network model, posts inline findings, and emits review telemetry to Langfuse. The service is fail-open: a review failure is reported as a PR comment and does not block CI.
Runtime flow
- Gitea sends a signed
pull_requestwebhook. webhook_server.pyvalidates the request, checks the base branch's.pr-review.jsonfor"enabled": true, and claims(repo, PR, SHA).ai_review.review_pr()fetches the diff, trusted config, and prior reviews.opencode_review.pychecks out the PR head in a sanitized temporary directory and runs the review agent. The legacy Ollama-compatible path is still available throughPRAGENT_ENGINE.- The review output is parsed and normalized, valid post-change line anchors are separated from summary-only findings, and Gitea receives the result.
langfuse_trace.pyrecords usage, cost basis, findings, and evaluation scores when Langfuse credentials are configured.
Module map
| Module | Responsibility |
|---|---|
entrypoints/webhook.py |
HTTP ingress, signature verification, opt-in gate, concurrency |
review/config.py |
Trusted base-branch opt-in policy; transport injected for tests |
entrypoints/gitea.py |
HTTP transport adapter and repository-scoped client |
review/ai_review.py |
Review orchestration implementation |
ai_review.py |
Compatibility shim for existing imports and CI execution |
review/model.py |
Anthropic-compatible model adapter and response text extraction |
review/opencode.py |
Hostile-checkout containment and agent execution |
review/diff.py |
Diff compression and prior-review extraction |
feedback/*.py |
Feedback persistence, harvesting, analysis, and Langfuse scores |
observability/langfuse.py |
Fail-open Langfuse ingestion and cost metadata |
observability/cost.py |
Provider price catalog and equivalent-cost calculations |
evaluation/*.py |
Dataset bootstrap, evaluators, and behavioral scoring |
The top-level .py files are intentionally thin compatibility shims. They keep
existing workflow commands and imports stable while the implementations live in
the focused packages above. New code belongs in those packages, not in a shim.
Onboard a repository
-
Add
pragent-botas a Write collaborator. -
Commit this file to the default branch:
{"enabled": true} -
Open or update a pull request.
No per-repository workflow, secret, or label is required for the central
webhook path. See README-webhook.md for deployment,
security, and webhook registration details.
Configuration
| Variable | Default | Purpose |
|---|---|---|
GITEA_API |
in-cluster URL | Gitea API base URL |
PRAGENT_BOT_TOKEN |
— | Bot credential |
OLLAMA_URL / OLLAMA_MODEL |
headroom / glm-5.2:cloud |
Legacy model path |
PRAGENT_ENGINE |
opencode |
opencode or legacy model path |
DIFF_MAX_CHARS |
150000 |
Diff input cap |
PRAGENT_MAX_CONCURRENT_REVIEWS |
2 |
Process concurrency bound |
LANGFUSE_HOST + keys |
unset | Enables telemetry; unset is a no-op |
Tests
python3 -m pytest tests -q
Tests are grouped under tests/pilot/*_tests/, matching the source domains.
They use mocked transports and local fixtures and do not require Gitea,
Langfuse, a model endpoint, or network access.