-
Notifications
You must be signed in to change notification settings - Fork 34
missing tool logs support #461
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
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
…riting (#66) * Initial plan * Add documentation for custom agentic engine marked as experimental Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Document how custom engines can write safe output entries manually via JSONL Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com>
…71) * Initial plan * Update step summary to include processed output from collect_output Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
…rt id/continue-on-error fields, and use environment variable for prompt file operations (#70) * Initial plan * Implement GITHUB_AW_PROMPT environment variable and id/continue-on-error support Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Improve prompt file generation with more robust heredoc delimiter Replace 'EOF' with 'GITHUB_AW_PROMPT_END' as the heredoc delimiter for writing prompt content to /tmp/aw-prompts/prompt.txt. This change prevents potential conflicts if user workflow content contains "EOF" on its own line, which could prematurely terminate the heredoc and break prompt file generation. The new delimiter is more unique and descriptive, making it extremely unlikely to collide with user markdown content while clearly indicating its purpose in the workflow context. Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Use environment variable $GITHUB_AW_PROMPT with EOF delimiter instead of hardcoded path and GITHUB_AW_PROMPT_END Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com>
* Initial plan * Add comprehensive JSON schema for agent output file with validation and documentation Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Remove extra files, keep only agent-output.json schema Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com>
…on (#76) * Custom engine ai inference improvements (#455) * Add documentation for custom agentic engine with manual safe output writing (#66) * Initial plan * Add documentation for custom agentic engine marked as experimental Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Document how custom engines can write safe output entries manually via JSONL Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com> * Add processed output display to step summary in workflow compilation (#71) * Initial plan * Update step summary to include processed output from collect_output Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Store prompt filename in GITHUB_AW_PROMPT environment variable, support id/continue-on-error fields, and use environment variable for prompt file operations (#70) * Initial plan * Implement GITHUB_AW_PROMPT environment variable and id/continue-on-error support Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Improve prompt file generation with more robust heredoc delimiter Replace 'EOF' with 'GITHUB_AW_PROMPT_END' as the heredoc delimiter for writing prompt content to /tmp/aw-prompts/prompt.txt. This change prevents potential conflicts if user workflow content contains "EOF" on its own line, which could prematurely terminate the heredoc and break prompt file generation. The new delimiter is more unique and descriptive, making it extremely unlikely to collide with user markdown content while clearly indicating its purpose in the workflow context. Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Use environment variable $GITHUB_AW_PROMPT with EOF delimiter instead of hardcoded path and GITHUB_AW_PROMPT_END Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com> * Add JSON Schema for Agent Output File Structure (#73) * Initial plan * Add comprehensive JSON schema for agent output file with validation and documentation Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Remove extra files, keep only agent-output.json schema Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com> --------- Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Initial plan * Document GITHUB_AW_PROMPT environment variable in custom engine section - Added comprehensive documentation for GITHUB_AW_PROMPT environment variable - Documented all available environment variables for custom engines - Added practical example showing how to access workflow prompt content - Improved custom engine documentation structure for better clarity Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
…nment variable (#77) * Custom engine ai inference improvements (#455) * Add documentation for custom agentic engine with manual safe output writing (#66) * Initial plan * Add documentation for custom agentic engine marked as experimental Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Document how custom engines can write safe output entries manually via JSONL Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com> * Add processed output display to step summary in workflow compilation (#71) * Initial plan * Update step summary to include processed output from collect_output Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Store prompt filename in GITHUB_AW_PROMPT environment variable, support id/continue-on-error fields, and use environment variable for prompt file operations (#70) * Initial plan * Implement GITHUB_AW_PROMPT environment variable and id/continue-on-error support Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Improve prompt file generation with more robust heredoc delimiter Replace 'EOF' with 'GITHUB_AW_PROMPT_END' as the heredoc delimiter for writing prompt content to /tmp/aw-prompts/prompt.txt. This change prevents potential conflicts if user workflow content contains "EOF" on its own line, which could prematurely terminate the heredoc and break prompt file generation. The new delimiter is more unique and descriptive, making it extremely unlikely to collide with user markdown content while clearly indicating its purpose in the workflow context. Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Use environment variable $GITHUB_AW_PROMPT with EOF delimiter instead of hardcoded path and GITHUB_AW_PROMPT_END Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com> * Add JSON Schema for Agent Output File Structure (#73) * Initial plan * Add comprehensive JSON schema for agent output file with validation and documentation Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Remove extra files, keep only agent-output.json schema Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com> --------- Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Initial plan * Implement agent output file storage and environment variable setting Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
…ncy (#74) * Initial plan * Implement missing-tool extraction and analysis in logs command Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Add tests for edge cases and finalize missing-tool support Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Switch missing-tool analysis to parse safe output artifact files instead of raw logs Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Change artifact name from aw_output.txt to aw_output.json for consistency Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Rename artifact from aw_output.json to safe_output.jsonl Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com>
This commit was automatically generated by the format-and-commit workflow. Changes include: - Code formatting (make fmt) - Linting fixes (make lint) - Build artifacts updates (make build) - Agent finish tasks (make agent-finish)
* Initial plan * Move agent_output.json file to /tmp/ folder Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
…tifact@v4 (#80) * Initial plan * Update compiler to upload GITHUB_AW_AGENT_OUTPUT and upgrade upload-artifact to v5 Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Clean up: Update ci.yml to v5 and remove orphaned workflow lock files Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Rollback actions/upload-artifact from v5 to v4 across all workflows and source files Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com>
pelikhan
commented
Sep 5, 2025
…smatch (#83) * Initial plan * Initial analysis of test failures Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Fix TestExtractMissingToolsFromRun by correcting artifact filename Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
github-actions bot
added a commit
that referenced
this pull request
Jan 4, 2026
…download.go Fixes alerts #461 and #460 by using more restrictive directory permissions (owner+group only) instead of world-readable permissions. This follows the principle of least privilege for log artifact directories. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
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.
Support for summarizing missing tools in logs command