Skip to content

Add strict channel tool flow coverage#612

Draft
nickmisasi wants to merge 1 commit intotrigger-mcp-with-botsfrom
cursor/expand-tool-flow-coverage-8b56
Draft

Add strict channel tool flow coverage#612
nickmisasi wants to merge 1 commit intotrigger-mcp-with-botsfrom
cursor/expand-tool-flow-coverage-8b56

Conversation

@nickmisasi
Copy link
Copy Markdown
Collaborator

Summary

Expanded handler-level coverage for strict channel tool-calling flows that propagate channelToolsAutoRunEverywhereOnly from post props through tool approval/result handling, and fixed a lint-blocking staticcheck issue in OAuth notification formatting.

QA test steps:

  • gofmt -l conversations/tool_handling_test.go conversations/conversations.go
  • GOTOOLCHAIN=go1.26.1 /tmp/golangci-lint-bin/golangci-lint run ./conversations/...
  • go test -count=1 ./conversations/...

Ticket Link

NONE

Screenshots

NONE

Release Note

NONE
Open in Web Open in Cursor 

Co-authored-by: Nick Misasi <nick13misasi@gmail.com>
@github-actions
Copy link
Copy Markdown

🤖 LLM Evaluation Results

OpenAI

⚠️ Overall: 18/19 tests passed (94.7%)

Provider Total Passed Failed Pass Rate
⚠️ OPENAI 19 18 1 94.7%

❌ Failed Evaluations

Show 1 failures

OPENAI

1. TestReactEval/[openai]_react_cat_message

  • Score: 0.00
  • Rubric: The word/emoji is a cat emoji or a heart/love emoji
  • Reason: The output is the text string "heart_eyes_cat", not an actual cat emoji (e.g., 😺/🐱) or a heart/love emoji (e.g., ❤️/😍).

Anthropic

⚠️ Overall: 18/19 tests passed (94.7%)

Provider Total Passed Failed Pass Rate
⚠️ ANTHROPIC 19 18 1 94.7%

❌ Failed Evaluations

Show 1 failures

ANTHROPIC

1. TestReactEval/[anthropic]_react_cat_message

  • Score: 0.00
  • Rubric: The word/emoji is a cat emoji or a heart/love emoji
  • Reason: The output is the text "heart_eyes_cat", which is not an actual cat emoji (e.g., 😺) or a heart/love emoji (e.g., ❤️).

This comment was automatically generated by the eval CI pipeline.

Copy link
Copy Markdown
Contributor

@cursor cursor bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Security Review: No findings

This PR contains:

  1. A single-line lint fix in conversations/conversations.go converting WriteString(Sprintf(...)) to Fprintf(...) — functionally identical, no behavioral change.
  2. ~317 lines of new test code covering the channelToolsAutoRunEverywhereOnly tool-calling flow.

No production logic is added or modified beyond the stylistic refactor. No new attack surface, no data flow changes, no auth/authz impact.

Open in Web View Automation 

Sent by Cursor Automation: Find vulnerabilities

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants