Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: take the coverage report you provide, blend it with business criticality, risk-rank the gaps by exposure, generate starter tests for the riskiest, and return the findings, generated tests and projected coverage delta.
- analyze — Run pure deterministic risk scoring over a provided coverage report with no model call and return risk-ranked findings.
- list_gaps — Return only the gaps: every source file not adequately covered for its risk level, ranked worst-first.
- list_critical — Return only the critical findings — the highest business-risk untested files (payment, auth, data deletion) that must be tested first.
- score_files — Return the per-file scoring breakdown: coverage fraction, coverage gap, untested line count, business-weighted risk score and exposure.
- generate_tests — Generate deterministic starter test files in Vitest, Jest or PHPUnit for the risky undertested files — each stub naming the real failure scenario rather than a happy-path check.
- project_coverage_delta — Project aggregate coverage before and after the generated tests land, clearly labelled as an optimistic assumption rather than a measured result.
- list_capabilities — List the agent's static capabilities: the available tools and the analyzer's risk-score thresholds. Useful for discovery.
- plan_inputs — Plan the inputs for a tool: returns the clarifying questions, the JSON schema and a ready-to-edit example.
- discover_intent — Understand your goal and co-design the exact input through clarifying questions before running.
- open_form — Opens the guided form to collect the coverage report and scope. The entry point for running the agent on your own data.
- run_form — Internal: invoked by the guided form when the user submits. Not for direct use.
