[limen GEN-organvm-reverse-engine-recursive-run-test-coverage-0620] Raise test coverage in organvm/reverse-engine-recursive-run#13
Conversation
limen task GEN-organvm-reverse-engine-recursive-run-test-coverage-0620
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e2b97e8b01
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| if env_overrides: | ||
| for k, v in env_overrides.items(): | ||
| old_env[k] = os.environ.get(k) | ||
| os.environ[k] = v |
There was a problem hiding this comment.
In environments where any RISK_W_* variable is already exported, calls to _run() without env_overrides leave those values in os.environ, so the default-weight hotspot tests exercise the caller's configuration instead of the documented defaults and can fail or assert the wrong risk formula. Since hotspot_merge explicitly reads these env vars, the helper should clear or set all four weight variables around every invocation, not only when a test passes overrides.
Useful? React with 👍 / 👎.
| assert all(x["type"] != "KNOWLEDGE_CONCENTRATION" for x in r["derived_risks"]) | ||
|
|
||
| def test_security_passthrough_with_remediation(self): | ||
| security = [{"id": "SEC-001", "severity": "HIGH", "remediation": "Patch it."}] |
There was a problem hiding this comment.
When the security input comes from the bundled parsers, remediation text is emitted as recommendation (scripts/parse_trivy.py:71, scripts/parse_semgrep.py:78, and the README documents that schema), but this new test feeds a non-standard remediation key. That lets risk_update continue to fall back to Review & patch. for real parser output while the coverage test passes; please cover the documented recommendation field, or both aliases, so the pipeline path is validated.
Useful? React with 👍 / 👎.
4444J99
deleted the
limen/gen-organvm-reverse-engine-recursive-run-test-coverage-0620-7858
branch
1 participant
Autonomous limen dispatch of task
GEN-organvm-reverse-engine-recursive-run-test-coverage-0620.Find the largest source module in organvm/reverse-engine-recursive-run with little or no test coverage and add a focused, PASSING test suite for it. Run the repo's own test command and confirm green. No placeholder tests. [auto-generated 2026-06-20 to keep the stream endless]
Produced in an isolated worktree off origin — review before merge.