Skip to content

fix: increase max-turns from 5 to 10 for structured output#2753

Merged
koxudaxi merged 1 commit intomainfrom
fix/increase-max-turns
Dec 23, 2025
Merged

fix: increase max-turns from 5 to 10 for structured output#2753
koxudaxi merged 1 commit intomainfrom
fix/increase-max-turns

Conversation

@koxudaxi
Copy link
Copy Markdown
Owner

@koxudaxi koxudaxi commented Dec 23, 2025

Summary by CodeRabbit

  • Chores
    • Updated system configuration to increase interaction capacity for automated operations, enabling improved handling of more complex tasks.

✏️ Tip: You can customize this high-level summary in your review settings.

@coderabbitai
Copy link
Copy Markdown

coderabbitai Bot commented Dec 23, 2025

Walkthrough

The workflow file .github/workflows/release-draft.yaml is updated to increase the max-turns parameter in the Claude Code Action arguments from 5 to 10, expanding the allowed interaction rounds for Claude analysis during release draft operations.

Changes

Cohort / File(s) Summary
Claude Code Action Configuration
.github/workflows/release-draft.yaml
Modified claude_args.max-turns value from 5 to 10, increasing the maximum interaction rounds permitted for Claude Code Action invocations

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title accurately describes the main change: increasing the max-turns parameter from 5 to 10 in the Claude analysis configuration.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
✨ Finishing touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch fix/increase-max-turns

📜 Recent review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 410f9e3 and 27053a2.

📒 Files selected for processing (1)
  • .github/workflows/release-draft.yaml
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (10)
  • GitHub Check: 3.11 on Windows
  • GitHub Check: 3.10 on macOS
  • GitHub Check: 3.10 on Windows
  • GitHub Check: 3.12 on Windows
  • GitHub Check: 3.14 on macOS
  • GitHub Check: 3.13 on Windows
  • GitHub Check: 3.14 on Windows
  • GitHub Check: 3.13 on macOS
  • GitHub Check: Analyze (python)
  • GitHub Check: benchmarks
🔇 Additional comments (1)
.github/workflows/release-draft.yaml (1)

79-79: LGTM! Reasonable increase for structured output complexity.

Increasing max-turns to 10 is appropriate for the complex breaking change analysis with strict JSON schema requirements. Structured output often requires multiple interaction rounds to satisfy format constraints.

Note that this change may increase execution time and API costs, though the 10-minute timeout should accommodate it comfortably.

If there was a specific failure case that prompted this fix, consider documenting it in the PR description or commit message for future reference.


Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@codecov
Copy link
Copy Markdown

codecov Bot commented Dec 23, 2025

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 99.37%. Comparing base (410f9e3) to head (27053a2).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files
@@           Coverage Diff           @@
##             main    #2753   +/-   ##
=======================================
  Coverage   99.37%   99.37%           
=======================================
  Files          83       83           
  Lines       12233    12233           
  Branches     1467     1467           
=======================================
  Hits        12156    12156           
  Misses         45       45           
  Partials       32       32           
Flag Coverage Δ
unittests 99.37% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ 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.

@codspeed-hq
Copy link
Copy Markdown

codspeed-hq Bot commented Dec 23, 2025

CodSpeed Performance Report

Merging #2753 will not alter performance

Comparing fix/increase-max-turns (27053a2) with main (410f9e3)

Summary

✅ 73 untouched
⏩ 10 skipped1

Footnotes

  1. 10 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports.

@koxudaxi koxudaxi merged commit 281973e into main Dec 23, 2025
36 checks passed
@koxudaxi koxudaxi deleted the fix/increase-max-turns branch December 23, 2025 08:20
@github-actions
Copy link
Copy Markdown
Contributor

Breaking Change Analysis

Result: No breaking changes detected

Reasoning: This PR only modifies a GitHub Actions workflow file (.github/workflows/release-draft.yaml), changing the --max-turns parameter from 5 to 10 for the Claude CLI used in automated release draft generation. This is a CI/CD infrastructure change that does not affect the datamodel-code-generator library's code generation output, templates, API, CLI, default behavior, Python version support, or error handling. Users of the library are completely unaffected by this change.


This analysis was performed by Claude Code Action

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

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant