v0.46.1

• Ensure roborev fix only discovers reviews for the current Git worktree.
• Restore post-commit hook execution in linked Git worktrees.

v0.46.0

• Honor *_cmd configuration overrides when checking agent availability, so custom agent commands are detected correctly.

• Show the stored branch name in the review screen instead of the active worktree branch.

• Use the main repository root for the post-commit hook when running inside git worktrees.

v0.45.0

• Add --min-severity to roborev fix and roborev refine to target only findings at or above a chosen severity.

• Include review comments when copying a review, making shared output more complete.

• Reuse compatible review sessions on the current branch more safely, preserving context without crossing branch boundaries.

• Add clearer documentation to TOML config files that roborev writes automatically.

• Fix roborev compact in git worktrees so it uses the correct branch.

v0.44.3

Improvements

• Hide daemon status details in the TUI review view to keep review output focused.
• Improve job logging and make timeout cleanup more reliable for long-running daemon work.

Bug Fixes

• Remove tool-call narration from review output so agent reviews stay concise and readable.

v0.44.2

• Clarify review prompts so agents do not run builds or tests during roborev review.

v0.44.1

• review, analyze, fix, and refine now fall back to the selected agent’s own default model when no workflow-specific model is configured.

• Queued and CI-triggered review jobs use the correct agent/model fallback behavior for the configured agent.

v0.44.0

• Add a global config flag to disable mouse interactions in the TUI.

• Add roborev postcommit and hook settings to control post-commit reviews, including branch review workflows.

• Add webhook review hooks for external integrations.

• Support excluded_commit_patterns for single-commit and range reviews.

• Add auto_filter_branch to automatically filter the TUI to the current branch.

• Tighten review prompts and make verdict parsing more consistent.

• Surface daemon/client mismatch warnings through daemon status output.

• Retry fix daemon calls automatically after a daemon restart.

• Fix daemon startup restart loops.

• Fix Enter key handling in the TUI inside embedded terminals.

• Fix cases where the TUI fails to close cleanly.

v0.43.0

• Add default_backup_model so you can configure a fallback model for agent-driven commands.

• Add Ctrl-D as a TUI shortcut to quit.

• Require explicit config to enable advanced TUI task workflows.

• Refresh bundled Codex and Claude skill definitions for review, fix, respond, and design review workflows.

• Expand agent documentation for model selection and fallback behavior.

• Fix TUI left/right arrow navigation so movement matches the key pressed.

• Fix agent selection so configured agents and --agent overrides use the correct model settings.

v0.42.0

• Add multi-repo workspace support.

• Add Cursor agent support.

• Add Pi coding agent support.

• Allow saving generated patch files to disk.

• Skip review throttling when a new push supersedes an in-progress review.

• Validate configured agent names and reject unknown agents earlier.

• Improve Claude review failure reporting so agent errors are captured and surfaced correctly.

v0.41.0

• Restore a separate P/F verdict column in the TUI queue so review outcomes are easier to scan.