Repository navigation
Description
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
startAutofixonly when there's no previous run or the previous run'sstatusiserror. - L209-225: any other terminal run (
completed, waiting for input) is returned as-is withFound existing analysis (Run ID: …).params.instructionis only passed tostartAutofix(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 neitherrun_idnorsentry_run_idis passed (src/sentry/seer/endpoints/group_ai_autofix.pyL286-299). 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.pyL558-575). So the gap is on the MCP side only.
Evidence from the report
- The sampled
analyze_issue_with_seercall madeGET …/issues/{id}/andGET …/issues/{id}/autofix/and no POST. It returnedFound existing analysis (Run ID: …)/## Analysis Completewith the old root cause. That sampled call had noinstructionargument; 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: #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.
--
Activity
linear-code commentedon Nov 14, 2026
MCP-1231