Skip to content
roborev
GitHub stars

Configuration Overview

roborev uses a layered configuration system with multiple sources.

Priority Order

Configuration is resolved in this order (highest to lowest priority):

  1. CLI flags (--agent, --reasoning)
  2. Per-repo .roborev.toml in your repository root
  3. Global ~/.roborev/config.toml
  4. Auto-detect first available agent; defaults to thorough for reviews, standard for refine

Configuration Files

Per-Repository

Create .roborev.toml in your repo root for project-specific settings:

agent = "claude-code"      # AI agent to use
review_context_count = 5   # Recent reviews to include as context
display_name = "backend"   # Custom name shown in TUI (optional)
excluded_branches = ["wip", "scratch"]  # Branches to skip reviews on


# Reasoning levels: thorough, standard, fast
review_reasoning = "thorough"  # For code reviews (default: thorough)
refine_reasoning = "standard"  # For refine command (default: standard)


# Project-specific review guidelines
review_guidelines = """
No database migrations needed - no production databases yet.
Prefer composition over inheritance.
All public APIs must have documentation comments.
"""

Global

Create ~/.roborev/config.toml for system-wide defaults:

default_agent = "codex"
server_addr = "127.0.0.1:7373"
max_workers = 4
job_timeout = "10m"  # Per-job timeout (default: 10m)

Most global settings are hot-reloaded when you edit the file—no daemon restart required. See Global Configuration for details on which settings hot-reload.

Data Directory

Override the data directory with the ROBOREV_DATA_DIR environment variable:

Terminal window
export ROBOREV_DATA_DIR=/custom/path  # Default: ~/.roborev

Next Steps