sparrow-cli 0.10.0

A local-first Rust agent cockpit — route, run, replay, rewind
{
  "description": "Capability scorecard for the underlying model. Each axis is scored 1-5 (see evals/scoring-rubric.md). The aggregate drives Model Adaptation: how much external structure the agent imposes to compensate.",

  "axes": {
    "reasoning":            { "score": null, "weight": 0.20, "notes": "depth, multi-step logic, abstraction" },
    "context_memory":       { "score": null, "weight": 0.12, "notes": "retention + use of long context" },
    "code":                 { "score": null, "weight": 0.16, "notes": "correctness, idiom, integration" },
    "tool_use":             { "score": null, "weight": 0.16, "notes": "selects, sequences, reacts to tools" },
    "hallucination_resist": { "score": null, "weight": 0.16, "notes": "doesn't fabricate; calibrates uncertainty" },
    "instruction_following":{ "score": null, "weight": 0.08, "notes": "honors constraints + format" },
    "long_task_stability":  { "score": null, "weight": 0.08, "notes": "no drift over many steps" },
    "self_correction":      { "score": null, "weight": 0.04, "notes": "detects + fixes own errors" }
  },

  "aggregate": {
    "method": "weighted_mean",
    "score": null,
    "band": null,
    "bands": {
      "1.0-1.9": "small",
      "2.0-2.9": "small-medium",
      "3.0-3.4": "medium",
      "3.5-4.4": "strong",
      "4.5-5.0": "frontier"
    }
  },

  "adaptation_directives": {
    "small": {
      "task_length": "very short, one sub-goal at a time",
      "autonomy": "low — validate after each step",
      "verification_passes": "high",
      "decomposition": "fine-grained checklists",
      "guidance": "explicit, restated",
      "tool_use": "one action at a time, confirm output",
      "summary_frequency": "after every step"
    },
    "medium": {
      "task_length": "moderate, phased",
      "autonomy": "medium",
      "verification_passes": "standard",
      "decomposition": "by phase",
      "guidance": "structured",
      "tool_use": "mandatory for empirical claims",
      "summary_frequency": "per phase"
    },
    "strong": {
      "task_length": "long",
      "autonomy": "high",
      "verification_passes": "extended + adversarial",
      "decomposition": "objective + sub-objectives",
      "guidance": "light",
      "tool_use": "orchestrated, parallel where independent",
      "summary_frequency": "per milestone"
    },
    "frontier": {
      "task_length": "long-horizon, multi-session",
      "autonomy": "full within safety",
      "verification_passes": "systemic, multi-pass",
      "decomposition": "strategic",
      "guidance": "minimal",
      "tool_use": "multiple tools in concert",
      "summary_frequency": "at meaningful milestones"
    }
  },

  "rule": "The LOWER the aggregate, the MORE external structure the agent imposes (decomposition, checklists, validation frequency) to do the work the model can't do internally. The agent's reliability target is constant; only the scaffolding scales."
}