5-file batching, BulkRead tool, label preservation, cold-start retry#26
Merged
Merged
Conversation
Align the headless agent review with the backend's pragent-based flow (which now batches up to 5 files per session and exposes Read/Grep/Glob/LS/BulkRead). - splitIntoPerFileRequests: group files in chunks of 5 per agent session instead of 1, matching pragent's MAX_FILES_PER_BATCH. Concatenate diffs + merge file_contents per batch. - reviewHeadless: per-batch loop; pass file_path/file_content only on single-file batches (multi-file batches let the agent gather per-file context via tools). Progress messages report actual file counts, not batch counts. - Preserve generator labels through the reflector by matching reflector issue_content to generator one_sentence_summary (pragent's primary smart_match_feedback strategy). - BulkRead tool handler (mirrors backend pragent llm_tools), plus /workspace/ prefix stripping in the dispatcher so the agent's absolute-path tool calls resolve to the CLI's relative-cwd model. - fetchApi: undici Agent with 60s connect timeout + transient-error retry. Default 10s connect timeout caused UND_ERR_CONNECT_TIMEOUT during cold-start TLS handshakes under burst review load. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
|
CodeAnt AI is running Incremental review |
codeant-ai
Bot
added
the
size:L
|
CodeAnt AI Incremental review completed. |
![codeant-ai[bot]](https://avatars.githubusercontent.com/in/646884?s=60&v=4){kind=small}
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
User description
Summary
Align the headless agent review with the backend's pragent-based flow:
MAX_FILES_PER_BATCH=5. For an 8-file diff, the CLI fires 2 sessions (5+3) instead of 8, cutting backend session count by ~80%.llm_tools.bulk_read_toolso the agent can fetch up to 10 files in one tool call.labelfield; the CLI now matches reflectorissue_content↔ generatorone_sentence_summary(pragent's primarysmart_match_feedbackstrategy) to keep specific labels (security,null pointer,resource leak, …) instead of falling back to'Code Quality'.Agentwith 60s connect timeout + transient-error retry. Default 10s connect timeout causedUND_ERR_CONNECT_TIMEOUTduring cold-start TLS handshakes under burst review load./workspace/stripping) so the agent's absolute-path tool calls resolve in the CLI's relative-cwd model.Test plan
node src/index.js review --headlesson a multi-file diff against test backend — confirm batching reduces session count, labels are specific, progress shows actual file counts.file_path/file_contentso backendhead_file_strworks.UND_ERR_CONNECT_TIMEOUTand succeed.codeant review(not just headless) still works.issue_content/start_line/labelpreserved).🤖 Generated with Claude Code
CodeAnt-AI Description
Review multiple files in one session and keep reviews stable during cold starts
What Changed
/workspace/are handled correctlyImpact
✅ Fewer review sessions for large diffs✅ Clearer review progress for multi-file changes✅ Fewer failed reviews during cold starts💡 Usage Guide
Checking Your Pull Request
Every time you make a pull request, our system automatically looks through it. We check for security issues, mistakes in how you're setting up your infrastructure, and common code problems. We do this to make sure your changes are solid and won't cause any trouble later.
Talking to CodeAnt AI
Got a question or need a hand with something in your pull request? You can easily get in touch with CodeAnt AI right here. Just type the following in a comment on your pull request, and replace "Your question here" with whatever you want to ask:
This lets you have a chat with CodeAnt AI about your pull request, making it easier to understand and improve your code.
Example
Preserve Org Learnings with CodeAnt
You can record team preferences so CodeAnt AI applies them in future reviews. Reply directly to the specific CodeAnt AI suggestion (in the same thread) and replace "Your feedback here" with your input:
This helps CodeAnt AI learn and adapt to your team's coding style and standards.
Example
Retrigger review
Ask CodeAnt AI to review the PR again, by typing:
Check Your Repository Health
To analyze the health of your code repository, visit our dashboard at https://app.codeant.ai. This tool helps you identify potential issues and areas for improvement in your codebase, ensuring your repository maintains high standards of code health.