Spaces:
Running
Running
| { | |
| "schema_version": "evalarc.trace-input.v1", | |
| "run_id": "mcp-delivery-bbc3c08e-7dc7-434a-9c65-8d745bcc8547", | |
| "provenance": { | |
| "kind": "recorded", | |
| "description": "Actual local stdio MCP instruction delivery, collected by scripts/record-load.mjs using an authored skill. No model or AWS evaluation; evaluator results intentionally absent." | |
| }, | |
| "dataset": { | |
| "id": "mcp-delivery-control", | |
| "version": "1", | |
| "cases": [ | |
| { | |
| "id": "load-evidence-review", | |
| "goal": "Load the authored evidence-review skill through MCP.", | |
| "expected_skills": [ | |
| "evidence-review" | |
| ] | |
| } | |
| ] | |
| }, | |
| "configuration": { | |
| "model": "none: local MCP client", | |
| "model_parameters": {}, | |
| "prompt_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", | |
| "tools_sha256": "2c52bc1da3c4285bb25979f13097557ea48d74d978902a278c9d869ab5ff7aa9", | |
| "skills": { | |
| "evidence-review": "f93102cb0592a462afb43cc6cf78b09096208aa1772bcaa341e75a20c1deffd0" | |
| } | |
| }, | |
| "evaluators": [ | |
| { | |
| "id": "goal-review", | |
| "revision": "not-run", | |
| "level": "session", | |
| "rating": { | |
| "kind": "numeric", | |
| "min": 0, | |
| "max": 1, | |
| "pass_at_least": 1 | |
| } | |
| }, | |
| { | |
| "id": "Builtin.SkillInstructionFollowing", | |
| "revision": "not-run", | |
| "level": "skill", | |
| "rating": { | |
| "kind": "numeric", | |
| "min": 0, | |
| "max": 1, | |
| "pass_at_least": 1 | |
| } | |
| } | |
| ], | |
| "cases": [ | |
| { | |
| "case_id": "load-evidence-review", | |
| "session_id": "bbc3c08e-7dc7-434a-9c65-8d745bcc8547", | |
| "trace_ids": [ | |
| "7419e7e182a245919fc3c49b1c02b7a7" | |
| ], | |
| "skill_observation_complete": true, | |
| "spans": [ | |
| { | |
| "traceId": "7419e7e182a245919fc3c49b1c02b7a7", | |
| "spanId": "481d88f854ae4e7c", | |
| "name": "open_skill", | |
| "startTimeUnixNano": "1789490688827000000", | |
| "endTimeUnixNano": "1789490688898000000", | |
| "attributes": { | |
| "session.id": "bbc3c08e-7dc7-434a-9c65-8d745bcc8547", | |
| "gen_ai.tool.name": "open_skill", | |
| "mcp.protocol.version": "2026-07-28" | |
| } | |
| } | |
| ], | |
| "skill_calls": [ | |
| { | |
| "name": "evidence-review", | |
| "trace_id": "7419e7e182a245919fc3c49b1c02b7a7", | |
| "span_id": "481d88f854ae4e7c", | |
| "receipt": { | |
| "schema": "skills-anywhere-load-1", | |
| "load_id": "dff92916-a748-4b3b-aca9-293d0043c6c1", | |
| "loaded_at": "2026-09-15T16:44:48.892Z", | |
| "provider": "dsh-skills-anywhere", | |
| "provider_version": "0.12.0", | |
| "name": "evidence-review", | |
| "skill_sha256": "8e08d5d07d0b7f9683145ef435653e4cfe1d8a312d1255ed79a6d0241e5c7542", | |
| "content_sha256": "473876db0cd9579138f1cd7905f6037855bea94c4c3740eb2c7f698aef2ddc0b", | |
| "bundle_sha256": "f93102cb0592a462afb43cc6cf78b09096208aa1772bcaa341e75a20c1deffd0", | |
| "declared_tools": [ | |
| "Read" | |
| ], | |
| "permissions_enforced": false | |
| } | |
| } | |
| ], | |
| "evaluation_response": { | |
| "evaluationResults": [] | |
| } | |
| } | |
| ] | |
| } | |