CodeRabbit Generated Unit Tests: Generate unit tests#62
Merged
Conversation
Revert the parallel-tool prompt regression, clarify that end must run in its own round after reading tool results, and defer end execution after other tools succeed instead of skipping it and forcing another LLM turn. Co-authored-by: Cursor <cursoragent@cursor.com>
When end is bundled with other tools in one turn, run the other tools normally but return an explicit rejection for end; clarify this in prompts and each.md so models do not expect end to succeed in the same round. Co-authored-by: Cursor <cursoragent@cursor.com>
Keep assistant plain-text in messages and use a generic retry hint instead of hardcoding send_message/end, avoiding misleading follow-up tool calls. Co-authored-by: Cursor <cursoragent@cursor.com>
Wire config_class as the canonical Config, slim loader to a compat shim, and restore root lazy re-exports so library embed tests can inject config without config.toml. Co-authored-by: Cursor <cursoragent@cursor.com>
Extract ai, handlers, attachments, cognitive, memes, coordinator, onebot, and agent runner into subpackages with compatibility shims; add python-api docs and py.typed; trim noisy inline comments across runtime code. Co-authored-by: Cursor <cursoragent@cursor.com>
Strip agent-generated label comments and duplicate section headers without changing runtime behavior. Co-authored-by: Cursor <cursoragent@cursor.com>
Extract shared meme image utilities, consolidate ingest lock model, and simplify memes API and bilibili WBI nav parsing. Co-authored-by: Cursor <cursoragent@cursor.com>
The ai/client/setup.py module is one level deeper than the old client.py, so Path(__file__).parents[1] pointed at Undefined/ai/ and loaded zero builtin tools. Centralize package root resolution and add regression tests. Co-authored-by: Cursor <cursoragent@cursor.com>
Export set_config from the root package, update python-api.md, and expand README with a simpler core-feature bullet plus a Skills-focused embed example. Co-authored-by: Cursor <cursoragent@cursor.com>
Delete unreachable monolith files shadowed by subpackages, sync set_config with ConfigManager, declare py.typed in the wheel, and add layout regressions. Co-authored-by: Cursor <cursoragent@cursor.com>
Configure base_branches to .* so CodeRabbit reviews PRs targeting any branch.
Harden queued LLM retries, pending-call cleanup, tool filtering, config bounds, attachment rendering, and privacy-safe prompt cache keys. Co-authored-by: Cursor <cursoragent@cursor.com>
3 tasks
Contributor
Author
|
Important Review skippedThis PR was authored by the user configured for CodeRabbit reviews. CodeRabbit does not review PRs authored by this user. It's recommended to use a dedicated user account to post CodeRabbit review feedback. ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
Comment |
Merge bugfix/clean-is-better so split modules resolve, fix three incorrect assertions, remove unused imports, normalize thinking type casing for non-DeepSeek providers, and satisfy strict mypy in tests. Co-authored-by: Cursor <cursoragent@cursor.com>
Keep v3.5.0 lazy root exports and combine thinking override normalization. Co-authored-by: Cursor <cursoragent@cursor.com>
|
tql |
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
2 participants
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.
Unit test generation was requested by @69gg.
The following files were modified:
tests/test_ai_client_setup.pytests/test_llm_sanitize.pytests/test_llm_streaming.pytests/test_llm_thinking.pytests/test_root_lazy_import.py