AgentWatchr

{
  "methodology": "evidence-score/0.2.1",
  "methodology_version": "evidence-score/0.2.1",
  "as_of": "2026-10-29T02:36:57.931711+00:00",
  "evaluated_at": "2026-10-29T02:36:57.931711+00:00",
  "snapshot_id": "profile-input-sha256:a180307210a07cdf55f797d5f69f7b0d4a37057f120e13b7ec40a33e7c43424f",
  "profile_type": "PACKAGED_ACP_AGENT",
  "overall_score": null,
  "status": "INSUFFICIENT_EVIDENCE",
  "evidence_score": null,
  "overall_status": "INSUFFICIENT_EVIDENCE",
  "dimensions": {
    "identity": {
      "value": null,
      "status": "SOURCE_OBSERVED",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "Captured source identity; ownership and source claims are not independently verified.",
      "reason_codes": [
        "SOURCE_OBSERVED",
        "OBSERVED"
      ],
      "evidence_refs": [
        "acp:opencode-v2:sha256:1e24d290cc3ba8978fa0c1d0db5ebc3e97c5a815f5bfe6a077ddf1c7ac69e92e:run:6511e439c7ad40c7829e82499557b7b0",
        "acp:opencode-v2:sha256:26d7836b006c6ca498acc0b4fdfcd642c2c8e885f8ab7ed05358d9efe2c8279a:run:9fd42980ba2946d3b8e11df1a4247e8c",
        "acp:opencode-v2:sha256:48194cbdef7da649daab8436d743a21b460744bb1b6b626362928bd5066d077f:run:a872c28923cf4931880bd6fee94d3640",
        "acp:opencode-v2:sha256:7adc8f47f35b36d89bfcfeff4f39349b1bc6150b6db01c2a7a775c1b9a4d67be:run:20b504e7a9d844d3baf56e7d2e248b9f",
        "acp:opencode-v2:sha256:998f7321e5aa9022f784956d2039ea7d959137cfb117814204d3073f11687fc6:run:6c244d01bfd646d4b57cbe68db4c3da4",
        "acp:opencode-v2:sha256:aa883f46a65d1fdaa961595f05eb642715c6433d900adaf416d657e167518f64:run:31d3a71c30db49c5be2619690666e5a5",
        "acp:opencode-v2:sha256:aa883f46a65d1fdaa961595f05eb642715c6433d900adaf416d657e167518f64:run:da47eca74f974cbfbef5cafa7e4a8b58",
        "acp:opencode-v2:sha256:ad520abecbfa7cbc06457b0a8f5013d0331767135af0339ddf9cf8870e00709e:run:f2e35b6afe4940a7940e9dfe96bdd777",
        "acp:opencode-v2:sha256:c7d5dac5b13ce299d6d2a209161bbce32a873696c74d3380055f6da90e083d90:run:e8e5cad406914c27a08864960c0adef7",
        "acp:opencode-v2:sha256:f4c9e609ed3f1ae691c732cf224bc7817eca7715d8167bf1661d18b3a4e59a1c:run:1ce89fa9f3854c5cbca0675eb01c59f3"
      ],
      "observation_count": 10,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-10-29T00:17:17.778890+00:00",
      "freshness_days": 0.097,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 2,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "numerator": 10,
        "denominator": 10,
        "value": 1.0,
        "unit": "valid source observation references / referenced observations"
      }
    },
    "runtime": {
      "value": null,
      "status": "N/A",
      "coverage": false,
      "confidence": "insufficient",
      "why_this_score": "HTTP responses including 405 and protocol recognition do not demonstrate task success.",
      "reason_codes": [
        "N/A",
        "NOT_APPLICABLE"
      ],
      "evidence_refs": [],
      "observation_count": 0,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "NOT_APPLICABLE",
      "applicability": "PUBLIC_HTTP_NOT_REQUIRED_BY_ACP_CLASS",
      "na_reason": "NOT_APPLICABLE",
      "last_observed_at": null,
      "freshness_days": null,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 0,
        "source_labels": []
      },
      "measurement": {
        "numerator": 0,
        "denominator": 0,
        "value": null,
        "unit": "HTTP responses / distinct dated attempts; NOT task success"
      }
    },
    "historical": {
      "value": null,
      "status": "REPEATED_OBSERVATIONS",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "Distinct observation times measure history, not independent corroboration.",
      "reason_codes": [
        "REPEATED_OBSERVATIONS",
        "OBSERVED"
      ],
      "evidence_refs": [
        "acp:opencode-v2:sha256:1e24d290cc3ba8978fa0c1d0db5ebc3e97c5a815f5bfe6a077ddf1c7ac69e92e:run:6511e439c7ad40c7829e82499557b7b0",
        "acp:opencode-v2:sha256:26d7836b006c6ca498acc0b4fdfcd642c2c8e885f8ab7ed05358d9efe2c8279a:run:9fd42980ba2946d3b8e11df1a4247e8c",
        "acp:opencode-v2:sha256:48194cbdef7da649daab8436d743a21b460744bb1b6b626362928bd5066d077f:run:a872c28923cf4931880bd6fee94d3640",
        "acp:opencode-v2:sha256:7adc8f47f35b36d89bfcfeff4f39349b1bc6150b6db01c2a7a775c1b9a4d67be:run:20b504e7a9d844d3baf56e7d2e248b9f",
        "acp:opencode-v2:sha256:998f7321e5aa9022f784956d2039ea7d959137cfb117814204d3073f11687fc6:run:6c244d01bfd646d4b57cbe68db4c3da4",
        "acp:opencode-v2:sha256:aa883f46a65d1fdaa961595f05eb642715c6433d900adaf416d657e167518f64:run:31d3a71c30db49c5be2619690666e5a5",
        "acp:opencode-v2:sha256:aa883f46a65d1fdaa961595f05eb642715c6433d900adaf416d657e167518f64:run:da47eca74f974cbfbef5cafa7e4a8b58",
        "acp:opencode-v2:sha256:ad520abecbfa7cbc06457b0a8f5013d0331767135af0339ddf9cf8870e00709e:run:f2e35b6afe4940a7940e9dfe96bdd777",
        "acp:opencode-v2:sha256:c7d5dac5b13ce299d6d2a209161bbce32a873696c74d3380055f6da90e083d90:run:e8e5cad406914c27a08864960c0adef7",
        "acp:opencode-v2:sha256:f4c9e609ed3f1ae691c732cf224bc7817eca7715d8167bf1661d18b3a4e59a1c:run:1ce89fa9f3854c5cbca0675eb01c59f3"
      ],
      "observation_count": 10,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-10-29T00:17:17.778890+00:00",
      "freshness_days": 0.097,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 2,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "distinct_observation_times": 10,
        "distinct_payloads": 2,
        "independent_confirmations": null
      }
    },
    "infrastructure": {
      "value": null,
      "status": "DECLARED_INFRASTRUCTURE",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "Source-declared infrastructure. Shared infrastructure has no penalty.",
      "reason_codes": [
        "DECLARED_INFRASTRUCTURE",
        "OBSERVED"
      ],
      "evidence_refs": [
        "acp:opencode-v2:sha256:f4c9e609ed3f1ae691c732cf224bc7817eca7715d8167bf1661d18b3a4e59a1c:run:1ce89fa9f3854c5cbca0675eb01c59f3"
      ],
      "observation_count": 1,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-10-29T00:17:17.778890+00:00",
      "freshness_days": 0.097,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "numerator": 1,
        "denominator": 1,
        "value": 1.0,
        "unit": "attributed declarations / declarations"
      }
    },
    "consistency_relationships": {
      "value": null,
      "status": "SOURCE_RELATIONSHIPS",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "Recorded relationships are not verified consistency or confirmed duplicates.",
      "reason_codes": [
        "SOURCE_RELATIONSHIPS",
        "OBSERVED"
      ],
      "evidence_refs": [
        "acp:opencode-v2:sha256:f4c9e609ed3f1ae691c732cf224bc7817eca7715d8167bf1661d18b3a4e59a1c:run:1ce89fa9f3854c5cbca0675eb01c59f3"
      ],
      "observation_count": 3,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-10-29T00:17:17.778890+00:00",
      "freshness_days": 0.097,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "numerator": 3,
        "denominator": 3,
        "value": 1.0,
        "unit": "attributed relations / declared relations; NOT confirmed consistency"
      },
      "conflicting_runtime_observation_groups": 0
    },
    "task_performance": {
      "value": null,
      "status": "N/A",
      "coverage": false,
      "confidence": "insufficient",
      "why_this_score": "No accepted task-evaluation evidence schema or real task tests in this dataset.",
      "reason_codes": [
        "N/A",
        "NOT_TESTED"
      ],
      "evidence_refs": [],
      "observation_count": null,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "NOT_TESTED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": "NOT_TESTED",
      "last_observed_at": null,
      "freshness_days": null,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 0,
        "source_labels": []
      },
      "measurement": {
        "accepted_tests": 0,
        "successes": null,
        "denominator": 0,
        "value": null
      }
    }
  },
  "coverage": 66.67,
  "coverage_facets": {
    "identity": true,
    "runtime": false,
    "historical": true,
    "infrastructure": true,
    "consistency_relationships": true,
    "task_performance": false
  },
  "coverage_denominator": 6,
  "coverage_numerator": 4,
  "coverage_exclusions": [],
  "coverage_basis": "Fixed six evidence areas; applicability never shrinks denominator.",
  "record_quality": {
    "numerator": 10,
    "denominator": 10,
    "value": 1.0,
    "unit": "valid attributed observation references / all referenced observations"
  },
  "verification_scope": {
    "http_attempts": 0,
    "http_responses": 0,
    "task_tests": 0
  },
  "freshness": {
    "source_last_observed_at": "2026-10-29T00:17:17.778890+00:00",
    "runtime_last_tested_at": null
  },
  "evidence_confidence": "low",
  "confidence": "low",
  "independent_corroboration": null,
  "runtime": null,
  "task_success": null,
  "reason_codes": [
    "NO_VALIDATED_COMPOSITE",
    "TASK_PERFORMANCE_NOT_TESTED",
    "MISSING_DATA_NOT_A_PENALTY",
    "CORRELATION_NOT_ABUSE",
    "SOURCE_CLAIMS_NOT_INDEPENDENTLY_VERIFIED",
    "INSUFFICIENT_EVIDENCE"
  ],
  "evidence_refs": [
    "acp:opencode-v2:sha256:1e24d290cc3ba8978fa0c1d0db5ebc3e97c5a815f5bfe6a077ddf1c7ac69e92e:run:6511e439c7ad40c7829e82499557b7b0",
    "acp:opencode-v2:sha256:26d7836b006c6ca498acc0b4fdfcd642c2c8e885f8ab7ed05358d9efe2c8279a:run:9fd42980ba2946d3b8e11df1a4247e8c",
    "acp:opencode-v2:sha256:48194cbdef7da649daab8436d743a21b460744bb1b6b626362928bd5066d077f:run:a872c28923cf4931880bd6fee94d3640",
    "acp:opencode-v2:sha256:7adc8f47f35b36d89bfcfeff4f39349b1bc6150b6db01c2a7a775c1b9a4d67be:run:20b504e7a9d844d3baf56e7d2e248b9f",
    "acp:opencode-v2:sha256:998f7321e5aa9022f784956d2039ea7d959137cfb117814204d3073f11687fc6:run:6c244d01bfd646d4b57cbe68db4c3da4",
    "acp:opencode-v2:sha256:aa883f46a65d1fdaa961595f05eb642715c6433d900adaf416d657e167518f64:run:31d3a71c30db49c5be2619690666e5a5",
    "acp:opencode-v2:sha256:aa883f46a65d1fdaa961595f05eb642715c6433d900adaf416d657e167518f64:run:da47eca74f974cbfbef5cafa7e4a8b58",
    "acp:opencode-v2:sha256:ad520abecbfa7cbc06457b0a8f5013d0331767135af0339ddf9cf8870e00709e:run:f2e35b6afe4940a7940e9dfe96bdd777",
    "acp:opencode-v2:sha256:c7d5dac5b13ce299d6d2a209161bbce32a873696c74d3380055f6da90e083d90:run:e8e5cad406914c27a08864960c0adef7",
    "acp:opencode-v2:sha256:f4c9e609ed3f1ae691c732cf224bc7817eca7715d8167bf1661d18b3a4e59a1c:run:1ce89fa9f3854c5cbca0675eb01c59f3"
  ],
  "why_this_score": "No composite: evidence axes have different meanings and no calibrated common scale. N/A is neither zero nor success.",
  "components": [],
  "freshness_days": 0.097,
  "input_sha256": "8186aaf9ab4ef2adce1c0acfd624e6b1b5195c2cd5a22eec5465369d94035590",
  "meaning": "Observed evidence coverage, not reputation, safety, recommendation or task ability."
}