Uh oh!
There was an error while loading. Please reload this page.
Add reusable debug-live trigger evaluation - #130
Merged
Oz Zafar (ozzafar) merged 1 commit intoAug 19, 2026
Merged
Conversation
Add contract coverage and an opt-in live Copilot evaluation for debug-live discovery, and bump the extension version to 2.3.1.\n\nCo-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>\nCopilot-Session: 32ca52f0-95b2-4ab4-8de8-cc870a9df789
Uh oh!
There was an error while loading. Please reload this page.
Matthias Hertel (MatthiasHertelArm) pushed a commit
to MatthiasHertelArm/CMSIS-Developer-Assistant
that referenced
this pull request
Aug 20, 2026
Port of microsoft/DebugMCP#130. debugSkillGuidance.test.ts pins the skill trigger words, the debugger-first wording, and that the skill, the MCP instructions and the get_debug_instructions guide agree. The opt-in npm run test:skill-trigger-agent launches a real Copilot CLI session in a scratch worktree carrying only cmsis-debug-live, with an embedded prompt, and asserts the skill is its first tool call - separate from npm test because it needs Copilot auth, spends credits and is nondeterministic. scripts/** is now excluded from the VSIX. Upstream's version bump is not taken.
Sourabh Mehta (soumeh01) pushed a commit
to Open-CMSIS-Pack/CMSIS-Developer-Assistant
that referenced
this pull request
Aug 21, 2026
Port of microsoft/DebugMCP#130. debugSkillGuidance.test.ts pins the skill trigger words, the debugger-first wording, and that the skill, the MCP instructions and the get_debug_instructions guide agree. The opt-in npm run test:skill-trigger-agent launches a real Copilot CLI session in a scratch worktree carrying only cmsis-debug-live, with an embedded prompt, and asserts the skill is its first tool call - separate from npm test because it needs Copilot auth, spends credits and is nondeterministic. scripts/** is now excluded from the VSIX. Upstream's version bump is not taken.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
pm run test:skill-trigger-agent evaluation that launches a real Copilot session and asserts debug-live is its first tool call
Validation
pm run compile
n- pm run lintn-pm test (140 passing)
pm run test:skill-trigger-agent (Copilot invoked debug-live first; next tool was
g)
The live-agent evaluation is intentionally separate from
pm test because it requires Copilot authentication, consumes AI credits, and is nondeterministic.