mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 04:33:12 +00:00
Adam Moussa
62d9945df4
Part of the domain-reorg adoption (build plan step C2): fork content,
upstream layout. Nine 1:1 module moves (reviewer_diff/eval_store/
findings/groups/publish/reconcile/trace_context + review_style_
collector/guidance) into agent/review/, with internal relative
imports re-wired to the new package depth. agent/review/__init__.py
mirrors upstream's thin re-export shim (one of the 21 verified "A"
structural adds).
Rewrote the 38 grep hits across importer files (agent/{analyzer,
ci_autofix,reviewer,webapp}.py, agent/dashboard/*, agent/middleware/
settle_review_check.py, agent/tools/*, agent/utils/github_feedback.py,
agent/webhooks/github.py, evals/reviewer/*, and the reviewer test
suite) to point at agent.review.*; 4 of the 38 hits were name
collisions (list_reviewer_findings, reviewer_outcomes,
_reviewer_thread_id, reviewer_thread_id — not the moved modules) and
were left untouched. tests/test_github_checks.py's module-alias
import (`from agent import reviewer_publish`) follows upstream's own
`from agent.review import publish as reviewer_publish` pattern so
downstream `reviewer_publish.*` call sites needed no changes.
agent/reviewer.py and agent/webapp.py stay in place per the hard
rule (fork content, import-only rewire) and are not part of this
package.
Gates: ruff check + ruff format --check, pytest --co -q (1637
collected), full unit suite (1637 passed), and the reviewer/findings
suite in isolation (pytest -k "review or finding", 421 passed).
17 lines
890 B
Python
17 lines
890 B
Python
"""Reviewer themes to steer repository style analysis."""
|
|
|
|
REVIEWER_STYLE_THEMES = """
|
|
The downstream reviewer agent looks for high-signal, diff-anchored defects — not nits.
|
|
When learning this repo's style, note how human reviewers align (or don't) with:
|
|
|
|
**Usually flag:** correctness regressions, wrong operators/variables, async footguns,
|
|
read-modify-write races, API/signature drift, nil/None deref, security boundaries (SSRF,
|
|
auth/cache asymmetry), broken tests, migration/ORM bypass, template/React contract breaks.
|
|
|
|
**Usually skip:** rename/style preferences, speculative "might break someday", scope-policing,
|
|
pre-existing issues, duplicate findings for the same bug across files, generic perf opinions.
|
|
|
|
**Severity:** tie labels to user-visible/runtime consequence, not taste.
|
|
|
|
**Tone:** prefer direct, concrete failure modes; cite the line; suggest only tiny obvious fixes.
|
|
"""
|