From 62a157125cc957f848efca10cf9c429bf28eb91b Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Mon, 27 Apr 2026 12:32:39 +0000 Subject: [PATCH 1/2] Initial plan From 4d0d578bebc0d7657933e0a038387e7224a44164 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Mon, 27 Apr 2026 12:37:49 +0000 Subject: [PATCH 2/2] fix: update tool name references in issue-triage.md to match actual MCP tool names The agentic triage workflow prompt referenced `get_issue` and `get_issue_comments` tools, but the actual GitHub MCP tools use `issue_read` with method parameters (`get` and `get_comments`). This mismatch caused the agent to fail to produce safe outputs (no labels, comments, or noop) when triaging issue #10496. Agent-Logs-Url: https://github.com/microsoft/typespec/sessions/b07993be-49ed-4ac4-a954-66be4043ddeb Co-authored-by: timotheeguerin <1031227+timotheeguerin@users.noreply.github.com> --- .github/workflows/issue-triage.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/issue-triage.md b/.github/workflows/issue-triage.md index 699c47ad98f..eee83d1284a 100644 --- a/.github/workflows/issue-triage.md +++ b/.github/workflows/issue-triage.md @@ -58,10 +58,10 @@ Only use labels defined in that file. ## Instructions -1. Retrieve the issue content using the `get_issue` tool. If the issue is obviously spam, generated by a bot, or not an actual issue to be worked on, then add an issue comment with a one-sentence analysis and exit the workflow. +1. Retrieve the issue content using the `issue_read` tool (method: `get`). If the issue is obviously spam, generated by a bot, or not an actual issue to be worked on, then add an issue comment with a one-sentence analysis and exit the workflow. 2. Gather additional context about the issue: - - Fetch any comments on the issue using the `get_issue_comments` tool + - Fetch any comments on the issue using the `issue_read` tool (method: `get_comments`) 3. **Duplicate detection**: Search for existing issues that may cover the same problem. - Extract 2-3 distinct keyword queries from the issue title and body (e.g., key error messages, feature names, affected components).