Skip to content

add tool info to return to evaluator when tool fails#914

Open
saisakul wants to merge 1 commit intodevfrom
bugfix/surface_tool_error
Open

add tool info to return to evaluator when tool fails#914
saisakul wants to merge 1 commit intodevfrom
bugfix/surface_tool_error

Conversation

@saisakul
Copy link
Copy Markdown
Collaborator

Signed-off-by: DBT pre-commit check

Context

Surface error from tool call to evaluator rather than application crashing due to None

What

  • when tool returns None, change tool result to failure info

Have you written unit tests?

  • Yes
  • No (add why you have not)

Are there any specific instructions on how to test this change?

  • Yes (if so provide more detail)
  • No

Relevant links

Signed-off-by: DBT pre-commit check
@saisakul saisakul requested a review from a team as a code owner March 18, 2026 11:10
@github-actions
Copy link
Copy Markdown
Contributor

⚠️ Python Vulnerabilities detected: 17 unique issues.

High:

Moderate:

Low:

Unknown (to be checked):

@codecov-commenter
Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 82.67%. Comparing base (bfd0462) to head (585a6f7).

Additional details and impacted files
@@            Coverage Diff             @@
##              dev     #914      +/-   ##
==========================================
+ Coverage   82.37%   82.67%   +0.29%     
==========================================
  Files         197      163      -34     
  Lines        8081     4017    -4064     
==========================================
- Hits         6657     3321    -3336     
+ Misses       1424      696     -728     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.


if response is None:
log.warning(f"{future_tool_name} Tool has failed or timed out")
response = f"{future_tool_name} Tool has failed or timed out"
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

should we add check for is_loop and if so set to appropriate tuple?

ie. response = ("Tool has failed or timed out", "fail", "False") if is_loop else "Tool..."

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.

3 participants