feat: Add run_to_completion feature for synchronous script execution #472
Conversation
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
- Introduced a new configuration option `run_to_completion` in YAML tools, allowing scripts to wait indefinitely for completion and return final results. - Updated the `YamlToolBase` class to handle synchronous execution when `run_to_completion` is enabled, including error handling and post-processing. - Added a new example tool demonstrating the `run_to_completion` feature with various platform-specific scripts. - Implemented integration tests to validate the functionality of the `run_to_completion` feature across different scenarios, including success, failure, and output limits. This enhancement significantly improves the flexibility of script execution, allowing for more controlled and predictable outcomes in tool operations.
…pt output
The tests were failing because shell command redirection wasn't capturing
output from compound commands using &&. Fixed by:
1. Using shell command grouping {{ }} (becomes { } after Python formatting)
to ensure all commands in the group have their output redirected
2. Escaping braces in bash loops to prevent Python format string conflicts
3. Using appropriate command separators for each platform:
- Linux/Darwin: && for conditional execution within groups
- Windows: ; for command separation within groups
All 5 integration tests now pass, including the 3 that were originally failing.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
plusplusoneplusplus
force-pushed
the
feature/feat-add-run-to-completion-feature-for-synchronous
branch
from
68092d7 to
34de6e5
Compare
…atibility
The test_run_to_completion_with_output_limits was failing in CI because
bash brace expansion {1..20} was not working in the CI environment.
Replaced with more portable seq command:
- Linux/Darwin: seq 1 20 | while read i; do echo "Line $i of output"; done
- Windows: for /l %i in (1,1,20) do echo Line %i of output
This ensures the test generates multiple lines of output for testing
the output truncation functionality across different environments.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
plusplusoneplusplus
force-pushed
the
feature/feat-add-run-to-completion-feature-for-synchronous
branch
from
34de6e5 to
de5ccaa
Compare
plusplusoneplusplus
deleted the
feature/feat-add-run-to-completion-feature-for-synchronous
branch
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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
This PR includes the following commits:
c26d216 feat: Add run_to_completion feature for synchronous script execution
Changes
🤖 Generated with automated submission script