{
 "line": {
  "agent": "res_36273987eedd5e90",
  "hash": "sha256:2c99fcc53a67b9b0342f0cc24cdaacac7b66dc4764f7947d00af8848ee7f28be",
  "id": "tr_st_36273987eedd5e90_444cdb9b",
  "key": "sha256:444cdb9bd9a171fa433c7570e882fab644fb265ea6696f10f3e01deac93f9f0a",
  "prev": "sha256:34426ac7acd709b46d771c89318c7bae2a0c8ff4215ddcdc0f4906feaa3fe4f5",
  "record": {
   "agent_version": null,
   "bundle": "bundles/tr_st_36273987eedd5e90_444cdb9b",
   "checked_on": null,
   "date": "2026-10-11",
   "format": "bundle",
   "harness_version": "probe-1.0",
   "id": "tr_st_36273987eedd5e90_444cdb9b",
   "kind": "self_test",
   "notes": "Produced automatically on every refresh; a new bundle is written only when the observation changes",
   "observed": {
    "actions": [
     "served Agent2Agent (A2A) document",
     "served Agentic Resource Discovery (ARD) document",
     "served Model Context Protocol (MCP) document"
    ],
    "approval": null,
    "egress": false,
    "entry": "GET on the publisher's well-known discovery paths",
    "outcome": "A2A verified (auth oauth2; unsigned); ARD verified; MCP invalid",
    "refused": null,
    "secrets_touched": false
   },
   "reviewer": null,
   "scenario": "Fetch and validate the ARD manifest, A2A agent card and MCP server card at the publisher's well-known paths",
   "scope": "product",
   "sha256": "sha256:c6a3edddbe47a4f16a37c679066cf51ce280e11350e80c2c5efc80b3fa42c3ff",
   "source": "AgentDossier refresh",
   "tier": 1,
   "title": "Registry probe of Pydantic AI's discovery endpoints",
   "url": "https://sushegaad.github.io/AgentDossier/traces/tr_st_36273987eedd5e90_444cdb9b/",
   "vendor_response": null
  }
 },
 "files": {
  "manifest.json": "{\n \"agent\": \"res_36273987eedd5e90\",\n \"date\": \"2026-10-11\",\n \"harness_version\": \"probe-1.0\",\n \"id\": \"tr_st_36273987eedd5e90_444cdb9b\",\n \"kind\": \"self_test\",\n \"name\": \"Pydantic AI\",\n \"protocols\": {\n  \"a2a\": {\n   \"auth_schemes\": [\n    \"oauth2\"\n   ],\n   \"card_url\": \"https://pydantic.dev/.well-known/agent-card.json\",\n   \"checked_at\": \"2026-10-11T03:06:25Z\",\n   \"parser_version\": \"a2a-0.3+1.0\",\n   \"protocol_version\": \"0.3.0\",\n   \"signed\": false,\n   \"skills\": [\n    \"Query telemetry data\",\n    \"Manage dashboards\",\n    \"Manage alerts\",\n    \"Manage feature flags\",\n    \"Manage notification channels\",\n    \"Execute Python in a sandbox\"\n   ],\n   \"status\": \"verified\",\n   \"version\": \"1.0.0\"\n  },\n  \"ard\": {\n   \"checked_at\": \"2026-10-11T03:06:25Z\",\n   \"parser_version\": \"ard-0.91\",\n   \"sources\": [\n    \"https://pydantic.dev/.well-known/ard.json\"\n   ],\n   \"status\": \"verified\"\n  },\n  \"mcp\": {\n   \"card_url\": \"https://pydantic.dev/.well-known/mcp.json\",\n   \"checked_at\": \"2026-10-11T03:06:26Z\",\n   \"parser_version\": \"mcp-2025-06-18\",\n   \"status\": \"invalid\",\n   \"tools\": [\n    \"token_info\",\n    \"query_schema_reference\",\n    \"query_run\",\n    \"query_find_exceptions_in_file\",\n    \"project_list\",\n    \"project_logfire_link\",\n    \"dashboard_list\",\n    \"dashboard_get\",\n    \"dashboard_create\",\n    \"dashboard_update\",\n    \"dashboard_delete\",\n    \"dashboard_update_settings\",\n    \"dashboard_add_panel\",\n    \"dashboard_update_panel\",\n    \"dashboard_remove_panel\",\n    \"dashboard_update_variables\",\n    \"dashboard_add_variable\",\n    \"dashboard_update_variable\",\n    \"dashboard_remove_variable\",\n    \"dashboard_create_group\",\n    \"dashboard_delete_group\",\n    \"dashboard_rename_group\",\n    \"dashboard_toggle_group_collapse\",\n    \"dashboard_reorder_groups\",\n    \"alert_list\",\n    \"alert_get\",\n    \"alert_history\",\n    \"alert_status\",\n    \"alert_create\",\n    \"alert_update\",\n    \"alert_delete\",\n    \"issue_list\",\n    \"issue_set_states\",\n    \"variable_list\",\n    \"variable_get\",\n    \"variable_list_versions\",\n    \"variable_create\",\n    \"variable_update\",\n    \"variable_delete\",\n    \"variable_update_rollout\",\n    \"variable_create_version\",\n    \"variable_assign_label\",\n    \"channel_list\",\n    \"channel_get\",\n    \"channel_create_webhook\",\n    \"channel_create_opsgenie\",\n    \"channel_update_webhook\",\n    \"channel_update_opsgenie\",\n    \"channel_delete\",\n    \"exec\",\n    \"help\"\n   ]\n  }\n },\n \"slug\": \"pydantic-pydantic-ai\"\n}",
  "transcript.md": "# Probe transcript — Pydantic AI\n\nAgent `res_36273987eedd5e90` · publisher domain `pydantic.dev` · 2026-10-11 · harness probe-1.0\n\n## Agent2Agent (A2A)\n\n- requested `https://pydantic.dev/.well-known/agent-card.json`\n- result: **verified**\n- declared version: 0.3.0 (card 1.0.0)\n- auth schemes: oauth2\n- signed: no\n- skills advertised: Query telemetry data, Manage dashboards, Manage alerts, Manage feature flags, Manage notification channels, Execute Python in a sandbox\n\n## Agentic Resource Discovery (ARD)\n\n- requested `https://pydantic.dev/.well-known/ard.json`\n- result: **verified**\n- manifest entries: 4\n\n## Model Context Protocol (MCP)\n\n- requested `https://pydantic.dev/.well-known/mcp.json`\n- result: **invalid**\n\n---\nObservation only: the registry fetched public well-known paths and validated the documents against the protocol specifications. No credentials, no message exchange beyond discovery, nothing written.\n",
  "verdict.json": "{\n \"actions\": [\n  \"served Agent2Agent (A2A) document\",\n  \"served Agentic Resource Discovery (ARD) document\",\n  \"served Model Context Protocol (MCP) document\"\n ],\n \"approval\": null,\n \"egress\": false,\n \"entry\": \"GET on the publisher's well-known discovery paths\",\n \"outcome\": \"A2A verified (auth oauth2; unsigned); ARD verified; MCP invalid\",\n \"refused\": null,\n \"secrets_touched\": false\n}"
 }
}