mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 12:43:16 +00:00
* feat: tune reviewer for precision — web/wiki tools + recalibrated prompt Reviewer agent now has web_search, fetch_url, and http_request alongside the finding tools, so it can verify library semantics and consult the DeepWiki auto-generated wiki for public repos (https://deepwiki.com/<owner>/<repo>) before flagging cross-file or architectural concerns. Prompt rewritten to push precision over recall: - explicit severity ladder pushing reviews toward bimodal high/low instead of defaulting to medium - ≤200-char description target (gold set averages ~186 chars; we were at ~436) - mandatory docs / wiki / code lookup before flagging concurrency, security, or perf — the three categories that dominated false positives - "do not flag" list covering compiler/linter-catchable nits, speculative claims without a concrete attacker/interleaving/scale, style preferences the codebase doesn't share, and test-quality nits on non-test diffs - smart file-selection guidance for large PRs (deprioritize generated / vendored / pure-rename hunks) Eval config switched to openai:gpt-5.5 + high reasoning effort for the next benchmark run. * trim prompt * subagent prompting * confidence ratings * added medium * enforce confidence threshold * . * reviewer: precision-tuned prompt + drop confidence gate Rewrites the reviewer system prompt around a defensibility bar (anchor + failure mode + maintainer wouldn't say "not a bug"), an explicit do-not-file list (style nits, speculation, scope-policing, same-bug fan-out), and a checklist of 10 bug archetypes drawn from a per-PR audit of the eval golden set. The audit showed 145 FPs in the last eval split ~28% speculative, ~26% style-nit, ~31% real-but-unscored (mostly same-archetype fan-out); the new prompt targets each class directly. Confidence is still recorded on every finding for post-hoc calibration but no longer gates publication — the audit showed the gate was a no-op (agent self-rated 65% of findings "high" regardless), and the prompt's defensibility bar is the actual discipline. Drops CONFIDENCE_ORDER, CONFIDENCE_THRESHOLD, the confidence_threshold kwarg on filter_findings_for_publish, the confidence_filtered score_mode, and the min_confidence kwarg on the eval target's _extract_comments — all dead once the gate is gone. Also removes the "informational" severity tier from the Severity enum, SEVERITY_ORDER, and all validators / tests / docstrings. It was reserved for FYI observations the dataset never rewards. * benchmax * adding google provider * slight steering * tuning * more tuning * fix * cleanup * reducing overfitting * Add per-repo review style profiles and inject them into the reviewer. Dashboard users can analyze historical PR review feedback per repository, edit the resulting style guide, and have it loaded from LangGraph Store at reviewer runtime (including Martian eval runs) keyed by owner/name. Co-authored-by: Cursor <cursoragent@cursor.com> * Fix review style job errors leaking exception details to clients. Return generic dashboard messages while logging full stack traces server-side. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Cursor <cursoragent@cursor.com>
111 lines
4.5 KiB
Python
111 lines
4.5 KiB
Python
"""Tool: ``update_finding``. Mutate an existing finding by id."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
from typing import Any
|
|
|
|
from langgraph.config import get_config
|
|
|
|
from ..reviewer_findings import (
|
|
MAX_SUGGESTION_LINES,
|
|
clip_suggestion,
|
|
get_thread_id_from_runtime,
|
|
update_finding_fields,
|
|
)
|
|
|
|
|
|
def update_finding(
|
|
finding_id: str,
|
|
status: str | None = None,
|
|
severity: str | None = None,
|
|
confidence: str | None = None,
|
|
description: str | None = None,
|
|
suggestion: str | None = None,
|
|
note: str | None = None,
|
|
) -> dict[str, Any]:
|
|
"""Update fields on an existing finding.
|
|
|
|
Use this on a re-review run to mark an existing finding as resolved or
|
|
dismissed, or to revise its severity/description/suggestion if the new
|
|
commits changed the situation.
|
|
|
|
Args:
|
|
finding_id: The id returned by ``add_finding`` (or shown in the
|
|
``Existing findings`` block of the re-review user message).
|
|
status: New status (``open``, ``resolved``, ``dismissed``).
|
|
Use ``resolved`` when the new commits address the issue.
|
|
severity: New severity, if reassessing.
|
|
confidence: New confidence rating (``low``, ``medium``, ``high``), if
|
|
new commits change how sure you are the finding is a real issue.
|
|
description: New description body, if revising.
|
|
suggestion: New replacement text. Pass an empty string to clear it.
|
|
Capped at 4 lines — longer values are dropped (the finding keeps
|
|
its description). Only set this for small, obvious fixes.
|
|
note: Optional free-form note explaining the change. Persisted on the
|
|
finding under ``last_update_note``.
|
|
|
|
Returns:
|
|
Dictionary with ``success`` and (on success) the updated ``finding``.
|
|
"""
|
|
if status is not None and status not in {"open", "resolved", "dismissed"}:
|
|
return {"success": False, "error": f"Invalid status: {status}"}
|
|
if severity is not None and severity not in {"low", "medium", "high", "critical"}:
|
|
return {"success": False, "error": f"Invalid severity: {severity}"}
|
|
if confidence is not None and confidence not in {"low", "medium", "high"}:
|
|
return {"success": False, "error": f"Invalid confidence: {confidence}"}
|
|
|
|
updates: dict[str, Any] = {}
|
|
suggestion_dropped = False
|
|
if status is not None:
|
|
updates["status"] = status
|
|
if severity is not None:
|
|
updates["severity"] = severity
|
|
if confidence is not None:
|
|
updates["confidence"] = confidence
|
|
if description is not None:
|
|
updates["description"] = description
|
|
if suggestion is not None:
|
|
if suggestion == "":
|
|
updates["suggestion"] = None
|
|
else:
|
|
clipped, suggestion_dropped = clip_suggestion(suggestion)
|
|
if not suggestion_dropped:
|
|
updates["suggestion"] = clipped
|
|
if note is not None:
|
|
updates["last_update_note"] = note
|
|
|
|
config = get_config()
|
|
configurable = config.get("configurable", {}) if isinstance(config, dict) else {}
|
|
head_sha = configurable.get("head_sha", "") if isinstance(configurable, dict) else ""
|
|
if status == "open" and isinstance(head_sha, str) and head_sha:
|
|
updates["last_confirmed_sha"] = head_sha
|
|
|
|
if not updates:
|
|
if suggestion_dropped:
|
|
return {
|
|
"success": False,
|
|
"suggestion_dropped": True,
|
|
"error": (
|
|
f"Suggestion exceeded the {MAX_SUGGESTION_LINES}-line cap "
|
|
"and was rejected; no other fields were provided, so "
|
|
"nothing was updated. Only include `suggestion` for "
|
|
"small, obvious fixes."
|
|
),
|
|
}
|
|
return {"success": False, "error": "No fields provided to update"}
|
|
|
|
thread_id = get_thread_id_from_runtime()
|
|
updated = asyncio.run(update_finding_fields(thread_id, finding_id, updates))
|
|
if updated is None:
|
|
return {"success": False, "error": f"No finding found with id {finding_id}"}
|
|
result: dict[str, Any] = {"success": True, "finding": updated}
|
|
if suggestion_dropped:
|
|
result["suggestion_dropped"] = True
|
|
result["warning"] = (
|
|
f"Suggestion exceeded the {MAX_SUGGESTION_LINES}-line cap and was "
|
|
"rejected — the finding's prior `suggestion` was left unchanged "
|
|
"and other fields were updated normally. Only include "
|
|
"`suggestion` for small, obvious fixes."
|
|
)
|
|
return result
|