open-swe/agent/tools
Johannes du Plessis ace71b0fd0
feat: add reviewer graph + eval target wiring (#1241)
* feat: add reviewer graph + eval target wiring

- New `reviewer` graph (`agent/reviewer.py`) registered in langgraph.json
  alongside the main `agent` graph. Reuses the same sandbox lifecycle,
  GH proxy auth, and middleware primitives from `agent.server`, but with
  a narrower tool set, a reviewer-specific system prompt, no
  commit/push, and the `task` (subagent) tool stripped via
  `_ToolExclusionMiddleware` so review stays in one context.

- New `github_comment` tool: agents call it once per issue with
  `(file, line, body, severity)` and the eval scores those calls
  against golden comments.

- `ensure_no_empty_msg` middleware (the no_op nudge) is intentionally
  *not* on the reviewer's stack — that middleware exists to enforce the
  main agent's "always finalize via Slack/Linear/PR" contract, which
  the reviewer doesn't have. The main agent's behavior is unchanged.

- `evals/reviewer/target.py`: send PR info as a user message, extract
  every `github_comment` tool call (multiple expected per review) into
  the run output.

- `evals/reviewer/judge.py`: per-example evaluator now returns a list
  of metrics under `{"results": [...]}` so LangSmith averages each
  numeric key (f1/precision/recall/tp/fp/fn) across the experiment in
  the UI. Dropped the broken `aggregate_pr` summary evaluator that
  reached for an attribute that doesn't exist on `RunTree`.

- `evals/reviewer/run_eval.py`: `--limit` now slices the dataset via
  `client.list_examples(limit=N)` since `aevaluate` doesn't accept
  `max_examples`.

- Makefile: `dev` and `run` targets now use `uv run` so they work
  without an activated venv.

* resolve comments

---------

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-05-06 10:15:58 -07:00
..
__init__.py feat: add reviewer graph + eval target wiring (#1241) 2026-05-06 10:15:58 -07:00
fetch_url.py fix: Shell injection and ssrf issues (#1155) 2026-04-01 12:37:35 -07:00
github_comment.py feat: add reviewer graph + eval target wiring (#1241) 2026-05-06 10:15:58 -07:00
http_request.py feat: move github workflows to gh cli (#1238) 2026-05-04 18:03:53 -07:00
linear_comment.py feat: move github workflows to gh cli (#1238) 2026-05-04 18:03:53 -07:00
linear_create_issue.py feat: add linear tools for listing teams, get/create/update/delete issues, and get issue comments (#1105) 2026-03-23 14:32:44 -07:00
linear_delete_issue.py feat: add linear tools for listing teams, get/create/update/delete issues, and get issue comments (#1105) 2026-03-23 14:32:44 -07:00
linear_get_issue.py feat: add linear tools for listing teams, get/create/update/delete issues, and get issue comments (#1105) 2026-03-23 14:32:44 -07:00
linear_get_issue_comments.py feat: add linear tools for listing teams, get/create/update/delete issues, and get issue comments (#1105) 2026-03-23 14:32:44 -07:00
linear_list_teams.py feat: add linear tools for listing teams, get/create/update/delete issues, and get issue comments (#1105) 2026-03-23 14:32:44 -07:00
linear_update_issue.py feat: add linear tools for listing teams, get/create/update/delete issues, and get issue comments (#1105) 2026-03-23 14:32:44 -07:00
slack_read_thread_messages.py feat: give agent ability to read cross-posted Slack message links [closes OPE-37] (#1200) 2026-04-29 17:42:27 -07:00
slack_thread_reply.py fix: convert @Name(USER_ID) mentions to Slack's <@USER_ID> format in thread replies (#1126) 2026-03-25 11:51:11 -07:00
web_search.py fix: add Exa web search tool [closes: OPE-29] (#1133) 2026-03-25 16:24:31 -07:00