{
"$schema": "http://json-schema.org/draft-07/schema#",
"$id": "https://slow-powers.dev/schemas/run-record.schema.json",
"title": "Portable Run Record",
"description": "Captures one subagent run. Harness-agnostic — each harness writes an adapter from its native transcript format to this shape. Downstream grading reads only this file.",
"type": "object",
"required": [
"eval_id",
"condition",
"skill_path",
"prompt",
"files",
"final_message",
"tool_invocations"
],
"additionalProperties": false,
"properties": {
"eval_id": {
"type": "string",
"description": "Matches the eval's id in evals.json."
},
"condition": {
"type": "string",
"description": "Reserved names: with_skill, without_skill, old_skill, new_skill."
},
"skill_path": {
"type": ["string", "null"],
"description": "Absolute path to the SKILL.md the subagent could load, or null if no skill was provided (without_skill condition)."
},
"prompt": {
"type": "string",
"description": "The user prompt as dispatched to the subagent."
},
"files": {
"type": "array",
"items": { "type": "string" },
"description": "Fixture files the subagent had access to (absolute paths inside the run's workspace)."
},
"final_message": {
"type": "string",
"description": "The agent's final user-facing text output."
},
"tool_invocations": {
"type": "array",
"description": "Ordered list of tool calls during the run.",
"items": {
"type": "object",
"required": ["name", "ordinal"],
"additionalProperties": false,
"properties": {
"name": {
"type": "string",
"description": "Tool name as recorded by the harness (e.g. Bash, Read, run_command). Adapters should preserve original names."
},
"args": {
"description": "Tool arguments. Object for structured tools, string for raw command-style tools.",
"type": ["object", "string", "array", "null"]
},
"result": {
"description": "Tool output, if captured. Truncate long outputs to ~2KB.",
"type": ["string", "object", "null"]
},
"ordinal": {
"type": "integer",
"minimum": 0,
"description": "0-indexed position in the run. Used by must_precede checks."
}
}
}
},
"total_tokens": {
"type": ["integer", "null"],
"description": "From the harness's task completion event, or derived from the persisted transcript by record-runs (usage summed across unique message ids, including cache creation/read tokens — a different accounting than the completion event). Canonical timing lives in the sibling timing.json, whose `source` field records which origin produced it. May be null if neither source is available."
},
"duration_ms": {
"type": ["integer", "null"],
"description": "From the harness's task completion event, or derived from the persisted transcript by record-runs (wall clock between the first and last transcript timestamps). Canonical timing lives in the sibling timing.json. May be null if neither source is available."
},
"run_index": {
"type": "integer",
"minimum": 1,
"description": "1-based run index within a multi-run (eval, condition) cell; absent for single-run cells."
}
}
}