Configuration¶

// evolve configuration — every value below is the built-in default.
// Generated by `evolve docs --format config`.
{
  "$schema": "https://raw.githubusercontent.com/bitwise-media-group/evolve/main/docs/config/config.schema.json",

  // Terraform-style semver constraint ("0.4.0", "~> 0.4", ">= 0.4, < 1") the
  // evolve binary must satisfy before run triggers/evals/all or report will
  // rewrite results. Non-release builds (dev and snapshot/prerelease
  // versions) warn and skip the check.
  // Default: unset — any evolve version may run.
  // "version": "~> 0.4",

  // Repository layout: auto, marketplace, multi, or single.
  "layout": "auto",

  // Restriction on which models exist: provider ids, canonical model ids
  // (anthropic/claude-sonnet-4-6), or all. Unlisted models are unavailable.
  // --model filters within it.
  // Default: unset — every model runnable by an available harness.
  // "models": ["anthropic/claude-sonnet-4-6"],

  // Restriction on which agent CLIs (claude, codex, gemini, cursor, copilot,
  // antigravity, grok) may drive models. --harness filters within it.
  // Default: unset — every harness found on PATH.
  // "harnesses": ["claude","copilot"],

  // Directory holding the token-count cache.
  // Default: unset — the OS user cache dir.
  // "cache_dir": "~/.cache/evolve",

  // Format for committed results files and the EVALUATION rollup: json,
  // jsonc, or yaml.
  "results_format": "json",

  "telemetry": {
    // Directory for the OpenTelemetry JSON exporter (traces.json,
    // metrics.json, logs.json); the --telemetry-dir flag overrides it and both
    // win over OTEL_* env vars.
    // Default: unset — telemetry disabled.
    // "dir": "./telemetry",
  },

  // Default maximum agent turns per behavioral eval; --max-turns and a
  // per-eval max_turns override it.
  "max_turns": 20,

  // Model that grades LLM assertions (a canonical or bare model id), driven
  // by any installed harness that supports it; --judge-model overrides for
  // one run. Keep it consistent across runs so verdicts stay comparable
  // between them and the providers under test.
  "judge_model": "anthropic/claude-sonnet-5",

  // Benchmark each eval without the skill (the skill's lift over no skill),
  // recomputed only when the eval or its fixtures change. --baseline
  // overrides for one run.
  "baseline": true,

  // How run/report treat stored results for models outside the `models`
  // restriction: keep or drop. --stale-results overrides.
  // Default: unset — prompt on a terminal, otherwise keep.
  // "stale_results": "keep",

  "remote": {
    // Patchy remote-evaluation service URL, used by evolve login/logout and
    // remote runs; --remote-url overrides for one command.
    // Default: unset — no remote configured.
    // "url": "https://patchy-evals.example.com",

    // Execute runs on the configured remote by default; --remote/--local force
    // either way for one run. False runs locally unless --remote.
    "default": false
  },

  "sandbox": {
    // Confine agent writes with an OS sandbox (sandbox-exec on macOS,
    // bubblewrap on Linux); --no-sandbox overrides for one run.
    "enabled": true

    // Directories kept read-only to agent runs so an escaping agent cannot
    // modify other source repositories; the workspace stays writable. Reads,
    // the network, and tool caches outside these roots are unaffected.
    // Default: unset — the parent directory of the repository under test.
    // "protected_roots": ["~/Repos"],
  },

  "checks": {
    // License every SKILL.md must declare; when unset, skills must not declare
    // one.
    // Default: unset — the license field is forbidden.
    // "license": "MIT",

    // Regex every skill description must match.
    "description_pattern": "Use (when|after|before)",

    // Maximum SKILL.md line count.
    "max_skill_lines": 500,

    // Ideal SKILL.md line count for the advisory size signal (full at or
    // below; zero at the cap).
    "ideal_skill_lines": 200,

    // Emit the advisory skill-quality signals after run checks; the
    // --no-signals flag forces them off.
    "signals": true,

    // Plugin manifests every plugin must ship: claude
    // (.claude-plugin/plugin.json) and/or codex (.codex-plugin/plugin.json).
    // With both, a hooks/ directory is forbidden (codex and claude hooks.json
    // are incompatible).
    "plugin_manifests": ["claude","codex"],

    // Validate marketplace manifests (marketplace layout only).
    "marketplace": true
  },

  "report": {
    "thresholds": {
      // Minimum triggers pass rate (0-1); report --check exits 1 below it and
      // the run dashboard rolls a failing group to an orange check while its
      // rate stays at or above it.
      "triggers_min_pass_rate": 0.5,

      // Minimum evals pass rate (0-1); report --check exits 1 below it and the
      // run dashboard rolls a failing group to an orange check while its rate
      // stays at or above it.
      "evals_min_pass_rate": 0.66,

      // Model keys (provider/model-id) the thresholds apply to.
      // Default: unset — every model with stored results.
      // "models": ["anthropic/claude-fable-5"],

      // Plugin maturity levels whose Tier 1/Tier 2 evidence issues fail report
      // --check; other levels only warn (evidence still renders). A plugin's
      // maturity comes from its manifest version: stable (>= 1.0.0), unstable (<
      // 1.0.0), or prerelease (a SemVer prerelease tag). The --maturity flag
      // overrides it.
      "maturity": ["stable","unstable","prerelease"]
    },

    // Path for a JUnit XML test-results file (one testcase per eval/trigger
    // case per model); the --junit flag overrides it.
    // Default: unset — no JUnit file written.
    // "junit": "coverage/junit.xml",

    // Path for a Cobertura XML coverage file marking each skill covered by a
    // current eval result; the --cobertura flag overrides it.
    // Default: unset — no Cobertura file written.
    // "cobertura": "coverage/cobertura-coverage.xml",

    // Require the configured model matrix: report --check holds every defined
    // model to the thresholds, and the Cobertura output covers a skill only
    // when every defined model has a current result. The --strict flag
    // overrides it.
    "strict": false
  }

  // Per-provider overrides: providers.<name>.models replaces that provider's
  // builtin model matrix (model ids, display names, USD-per-mtok pricing).
  // Default: unset — every provider keeps its builtin models.
  // "providers": {
  //   "cursor": {
  //     "models": [
  //       { "id": "composer-2.5", "display": "Cursor Composer 2.5", "input_per_mtok": 3.0, "output_per_mtok": 15.0 }
  //     ]
  //   }
  // }
}