analyze_issue_with_seer can't replace a completed Seer run

オープン
  • 何か問題がありますか？
#2,273 コメント 1 件 リアクション 0 件 担当者 0 名 GitHub で見る

メンテナーはふだん 1 日以内に返信

まだ誰も着手していません。

評価

難易度
3/5
見積もり時間
1〜2日
初心者へのやさしさ
68/100
issue の種類
機能追加
明瞭さ
明確に書かれている
活発さ
活発
技術スタック
typescript
領域
tooling

調査の方向性

Read packages/mcp-core/src/tools/catalog/analyze-issue-with-seer.ts around L149 (the startAutofix gate), L209-225 (the path that returns an existing terminal run), and the input schema at L83-92 with its Results are cached description at L80. Check the related getsentry/toolkit#1270 runId guard before changing the branch, since the new parameter has to coexist with it and with the fact that starting a run spends Seer credits. Done means a caller can explicitly request a fresh analysis, instruction is honoured or rejected rather than silently dropped, and the tool's existing tests are updated to cover both the reuse and refresh paths.

索引モデルが issue の本文から書いたものです。

説明

MCP mcp-feedback-pattern

Pattern: once an issue has a completed Seer run, analyze_issue_with_seer always returns that run. Callers can't start a fresh analysis through MCP, even when the stored root cause is stale (for example, it points at code that has since been fixed and shipped), and the instruction argument is dropped without notice.

Reports: 1 (user feedback, MCP server 0.42.0, analyze_issue_with_seer, impact: blocked)

Current behavior (packages/mcp-core/src/tools/catalog/analyze-issue-with-seer.ts @ 516cad4)

  • L149: the tool calls startAutofix only when there's no previous run or the previous run's status is error.
  • L209-225: any other terminal run (completed, waiting for input) is returned as-is with Found existing analysis (Run ID: …). params.instruction is only passed to startAutofix (L155), so on this path it is silently ignored.
  • The input schema (L83-92) has no way to ask for a new run, and the description says Results are cached - subsequent calls return instantly (L80).

Sentry API (getsentry/sentry@fe43ef0)

  • POST /issues/{id}/autofix/ starts a new run whenever neither run_id nor sentry_run_id is passed (src/sentry/seer/endpoints/group_ai_autofix.py L286-299). An existing completed run doesn't block it.
  • GET /issues/{id}/autofix/ returns the group's latest run (get_autofix_agent_state → fetch_latest_run_state, src/sentry/seer/autofix/autofix_agent.py L558-575). So the gap is on the MCP side only.

Evidence from the report

  • The sampled analyze_issue_with_seer call made GET …/issues/{id}/ and GET …/issues/{id}/autofix/ and no POST. It returned Found existing analysis (Run ID: …) / ## Analysis Complete with the old root cause. That sampled call had no instruction argument; the reporter says an earlier call did pass one. We sample 30% of traces, so that call may not have been recorded.

Reporter's proposal: a force/refresh parameter on analyze_issue_with_seer.

Related: getsentry/toolkit#1270 adds a runId guard on the same code path that stops the tool from starting a new run. Any change here needs to fit with it. Starting a new run spends Seer credits, which is likely why the tool reuses the existing run today.

via automation evt_905b9c478746fd9deeb853f85ad7441b · Run ID dispatch_603ac936cce8aaa570e9b7eae0aa9519.

--

View Session [Sentry]

主要言語
TypeScript
スター
961
フォーク
179
平均マージ
15時間 33分
マージ済み PR（30日）
476

環境構築

このプロジェクトには開発コンテナ、Dockerfile、コントリビューションガイドがありません。まず README を読み、一般的な手順ははじめてのコントリビューションガイドを参照してください。

はじめの一歩

  1. issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
  2. 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
  3. リポジトリをフォークし、ブランチを切って変更します。
  4. issue 番号を参照したプルリクエストを送ります。

getsentry/toolkit のほかの issue

getsentry/toolkit の issue をすべて見る

似ている issue

TypeScript の issue をもっと見る

新しい issue をメールで受け取る

初心者向けの GitHub issue を短くまとめたダイジェスト。