Map the Ruby repository
Codna builds a dependency and blast-radius graph of the repository from its import patterns. No model call, zero tokens.
Codna maps your Ruby app for zero tokens, fixes from evidence, and runs RSpec or minitest until it passes.
The problem
Codna builds a dependency and blast-radius graph of the repository from its import patterns. No model call, zero tokens. require and include chains are the edges, so the agent follows them from the failing spec to the module that stopped providing the method.
How Codna fixes it
Codna builds a dependency and blast-radius graph of the repository from its import patterns. No model call, zero tokens.
The agent receives an evidence bundle scoped to the issue: the suspect files, the call paths, the failing test. Codna prints the raw-to-bundle token size on every run. Every fix reports root cause, confidence, blast radius and regression risk, and passes a risk gate before it is applied or a pull request opens.
Run codna fix --tests --apply and Codna runs your tests in a sandbox and re-fixes until they pass, up to the iteration limit you set. Set fix.test_command in codna.yaml, or pass --test-cmd, when your runner is not pytest. With --open-pr, or through the GitHub App, the pull request states the issue, the root cause, the symbols touched and a confidence score, and asks for review before merging. Codna never merges.
pip install codna codna fix . --issue "OrdersController#create raises NoMethodError after concern refactor" --tests --apply --test-cmd "bundle exec rspec --format RspecJunitFormatter --out $CODNA_JUNIT"
What you get
Set fix.test_command or pass --test-cmd with a JUnit-writing formatter.
On-device recall parses .rb files with tree-sitter.
Framework code is part of the graph like any other module.
The proof
Codna builds a dependency and blast-radius graph of the repository from its import patterns. No model call, zero tokens. The agent receives an evidence bundle scoped to the issue: the suspect files, the call paths, the failing test. Codna prints the raw-to-bundle token size on every run. Every fix reports root cause, confidence, blast radius and regression risk, and passes a risk gate before it is applied or a pull request opens.
No. Understanding runs on your machine and spends no tokens. Only the evidence bundle or the diff reaches your model provider, with your key from the OS keychain. Set privacy.egress to fail-closed in codna.yaml and Codna runs your tests only under kernel-level network denial. Secret redaction is always on.
Yes, through your test command with a JUnit formatter.
The map follows requires and includes; dynamic dispatch is a lower bound. Your specs verify the behaviour.
On 87 matched bug-fix cases against Cursor, Codna averaged 16,159 total tokens and about $0.02 of model spend per verified fix, 5× fewer tokens and 1.7× faster. With your own key you pay your provider directly.
Codna ships as a CLI, an MCP server for Cursor and Claude, a GitHub Action (thyn-ai/codna-action@v1) and a GitHub App that reviews every pull request and opens fix PRs from a label, a comment or a red check.
Related