9 Commits

Author SHA1 Message Date
kite db5bc4b8a9 feat(rules): add include/exclude file filter support in rule.json
Allow users to configure include/exclude glob patterns in
  .open-code-review/rule.json (global or project-level) to control
  which files are reviewed. Exclude has highest priority, include
  penetrates default path exclusions but not the extension allowlist.
  Only one layer takes effect following --rule > project > global priority.
2026-05-25 20:19:02 +08:00
kite d44fd31989 feat(rules): unify rule resolution behind Resolver interface with four-layer priority
Consolidate review rules into a composedResolver that supports four layers
  (--rule flag > project .open-code-review/rule.json > global ~/rule.json >
  embedded system default), each with first-match-wins fall-through semantics.
2026-05-25 17:45:53 +08:00
kite 29564a891b refactor(diff): Simplify hunk resolution logic with helper functions
This change refactors the `resolveFromHunk` function by introducing several helper functions (`extractSideLines`, `matchConsecutive`) to improve readability and maintainability. The new implementation attempts to match against both new and old sides of the diff hunk, making comment resolution more robust.
2026-05-23 00:36:51 +08:00
kite 35424d18bf feat(config): add path exclusion patterns for file filtering
This change introduces a new configuration mechanism for excluding specific file paths during code reviews. It adds support for glob patterns including recursive directory matching (**), single-segment wildcards (*), and brace expansion ({a,b}), allowing more flexible control over which files should be reviewed or skipped based on their location within the repository.
2026-05-23 00:11:35 +08:00
kite 8ceceaf3e7 build: Remove version from binary names and update related scripts 2026-05-22 23:11:37 +08:00
kite 63d6108db0 fix(agent): Update file counting logic for accurate review metrics
This change refines how file counts are tracked during the agent's review process. It now correctly excludes deleted files when calculating the number of files being reviewed, ensuring telemetry and error reporting reflect actual processing rather than total diffs. This improves accuracy in monitoring and debugging scenarios.
2026-05-22 22:28:52 +08:00
kite d345ef9707 feat: add llm.extra_body config support to disable thinking mode 2026-05-22 21:28:32 +08:00
kite f054bb799e fix: propagate LLM API errors instead of showing misleading "Looks good to me"
When all subtask LLM calls fail (e.g. invalid API key), dispatchSubtasks
now returns an error instead of empty comments with nil error. Partial
failures are recorded as subtask_error warnings so output functions can
distinguish "no issues found" from "review failed".
2026-05-22 15:28:26 +08:00
kite 7c8b8562aa feat: init 2026-05-20 22:03:52 +08:00