{
  "admission": {
    "admittedAt": "2026-11-10T03:29:50.564Z",
    "certificateId": "cdhq-72dce335ff61f2975d530c6c",
    "pan": "9710 3421 0000 1138"
  },
  "baseline": {
    "passLine": 7,
    "passed": true,
    "present": 8,
    "score": 0.8,
    "total": 10,
    "verdict": "This is an agent. 8 of 10 markers present; the pass line is 7.",
    "votes": [
      {
        "absentMeans": "The job is hard-coded.",
        "citations": [
          {
            "line": 1051,
            "path": "Conquest.ts",
            "signal": "http_task_route",
            "text": "if (method === \"POST\") {"
          },
          {
            "line": 66,
            "path": "src/a2a/reader.ts",
            "signal": "message_handler",
            "text": "body: JSON.stringify({ jsonrpc: '2.0', method: 'tasks/send', id: 1, params: { message: { parts: [{ type: 'text', text: 'ping' }] } } }),"
          },
          {
            "line": 618,
            "path": "Conquest.ts",
            "signal": "cli_task_arg",
            "text": "const args = process.argv.slice(2);"
          }
        ],
        "id": "goal_intake",
        "missing": [
          "a queue or stream consumer that receives work"
        ],
        "n": 1,
        "name": "Goal intake",
        "present": true,
        "presentMeans": "A task or goal arrives from outside at runtime — a route, a message handler, a CLI argument, a queue.",
        "role": "volume_planner",
        "weight": 2.5
      },
      {
        "absentMeans": "A fixed sequence.",
        "citations": [
          {
            "line": 67,
            "path": "src/agents/telemetry-auditor.ts",
            "signal": "model_call",
            "text": "const response = await input.llm.complete({"
          },
          {
            "line": 58,
            "path": "src/engines/world-model/world.ts",
            "signal": "policy",
            "text": "export function decide(similarity: number): 'auto-merge' | 'review' | 'new' {"
          }
        ],
        "id": "decision_seam",
        "missing": [],
        "n": 2,
        "name": "Decision seam",
        "present": true,
        "presentMeans": "Something chooses the next action — a model call, or an explicit policy.",
        "role": "conflict_critic",
        "weight": 2
      },
      {
        "absentMeans": "Direct calls in line.",
        "citations": [],
        "id": "tool_dispatch",
        "missing": [
          "a tool/function schema handed to the model (tools: [...], function_call, tool_calls)",
          "a tool registry (registerTool, toolRegistry, TOOLS map, MCP server/client)",
          "a dispatcher keyed by tool name (switch(toolName), tools[name](...), dispatch(...))"
        ],
        "n": 3,
        "name": "Tool dispatch",
        "present": false,
        "presentMeans": "A registry or schema of capabilities, and a dispatcher that picks among them.",
        "role": "evidence_reconciler",
        "weight": 0
      },
      {
        "absentMeans": "Top-to-bottom execution.",
        "citations": [
          {
            "line": 89,
            "path": "src/engines/markovian/efficiency.ts",
            "signal": "bounded_loop",
            "text": "for (let step = 1; step <= steps; step += 1) {"
          },
          {
            "line": 236,
            "path": "Conquest.ts",
            "signal": "open_loop",
            "text": "while (true) {"
          }
        ],
        "id": "loop",
        "missing": [
          "a loop that runs until the task reports done (while not done, until finished, break on final answer)",
          "an explicit step function driven repeatedly (step(), tick(), iterate(), runStep)"
        ],
        "n": 4,
        "name": "The loop",
        "present": true,
        "presentMeans": "An observe → decide → act cycle with a termination condition.",
        "role": "volume_planner",
        "weight": 1.5
      },
      {
        "absentMeans": "Fire and forget.",
        "citations": [
          {
            "line": 80,
            "path": "src/zetaris/reader.ts",
            "signal": "observation",
            "text": "observations.push({"
          },
          {
            "line": 93,
            "path": "src/agents/volume-planner.ts",
            "signal": "observation_var",
            "text": "const observations = listing.evidence.filter((evidence) => evidence.source === source.id)"
          }
        ],
        "id": "observation_feedback",
        "missing": [
          "tool results returned to the model (role \"tool\", tool_result, function_response, tool_call_id)",
          "a running history the next step reads (messages.push / history.append after an action)"
        ],
        "n": 5,
        "name": "Observation feedback",
        "present": true,
        "presentMeans": "The result of an action is read back and shapes the next step.",
        "role": "evidence_reconciler",
        "weight": 1.5
      },
      {
        "absentMeans": "Stateless.",
        "citations": [
          {
            "line": 47,
            "path": "src/engines/hmem/conflicts.ts",
            "signal": "memory_module",
            "text": "export function snapshot(memory: Memory): MemoryState {"
          },
          {
            "line": 1,
            "path": "seed-surreal.ts",
            "signal": "database",
            "text": "import { Surreal } from \"surrealdb.js\";"
          },
          {
            "line": 89,
            "path": "src/tracer.ts",
            "signal": "file_state",
            "text": "appendFileSync(this.path, `${JSON.stringify(entry)}\\n`, 'utf8')"
          },
          {
            "line": 1033,
            "path": "Conquest.ts",
            "signal": "history_state",
            "text": "messages: ["
          }
        ],
        "id": "state_memory",
        "missing": [],
        "n": 6,
        "name": "State / memory",
        "present": true,
        "presentMeans": "State carried across steps or runs — history, a store, a database, files.",
        "role": "evidence_reconciler",
        "weight": 3
      },
      {
        "absentMeans": "One try, crash.",
        "citations": [
          {
            "line": 3,
            "path": "gateway.ts",
            "signal": "fallback",
            "text": "engine.init().catch(err => console.warn(\"⚠️ SurrealDB pending: \" + err.message));"
          },
          {
            "line": 75,
            "path": "Conquest.ts",
            "signal": "catch",
            "text": "} catch (e) {"
          }
        ],
        "id": "recovery",
        "missing": [
          "a retry with attempts/backoff"
        ],
        "n": 7,
        "name": "Recovery",
        "present": true,
        "presentMeans": "Failures are caught and retried, fallen back, or escalated — not fatal.",
        "role": "conflict_critic",
        "weight": 1.5
      },
      {
        "absentMeans": "Anonymous.",
        "citations": [],
        "id": "identity_interface",
        "missing": [
          "an agent card or manifest file in the tree (.well-known/agent.json, agent-card.json, mcp.json, openapi.*)",
          "a served agent card or API description route (a handler for /.well-known/agent.json, /agent-card, /openapi)",
          "a declared identity object with name, version and capabilities/skills",
          "an agent protocol server (A2A, MCP, ACP) that other parties can address"
        ],
        "n": 8,
        "name": "Identity & interface",
        "present": false,
        "presentMeans": "Discoverable — an agent card, a manifest, or a documented API, with a name and a version.",
        "role": "listing_closer",
        "weight": 0
      },
      {
        "absentMeans": "Unbounded.",
        "citations": [
          {
            "line": 319,
            "path": "src/engines/markovian/markovian.ts",
            "signal": "step_budget",
            "text": "const budget = this.config.carryoverTokens * 4"
          },
          {
            "line": 29,
            "path": "src/valuation.ts",
            "signal": "timeout",
            "text": "const res = await fetch(u, { headers: { 'Accept': 'application/json' }, signal: AbortSignal.timeout(5000) })"
          }
        ],
        "id": "boundaries",
        "missing": [
          "an allowlist, permission check, or confirmation gate on actions"
        ],
        "n": 9,
        "name": "Boundaries",
        "present": true,
        "presentMeans": "Limits on steps, budget, time, or permissions.",
        "role": "volume_planner",
        "weight": 1.5
      },
      {
        "absentMeans": "Silent.",
        "citations": [
          {
            "line": 97,
            "path": "src/engines/world-model/world.ts",
            "signal": "trace_module",
            "text": "private readonly auditLog: AuditEntry[] = []"
          }
        ],
        "id": "trace",
        "missing": [
          "an event/decision log written per step (logger.info with step/action/decision, emit(\"step\"))"
        ],
        "n": 10,
        "name": "Trace",
        "present": true,
        "presentMeans": "A record of decisions and actions — a trace, structured logs, events.",
        "role": "telemetry_auditor",
        "weight": 1
      }
    ]
  },
  "createdAt": "2026-11-10T03:29:50.839Z",
  "fee": {
    "amount": 1,
    "currency": "USD",
    "payTo": "0x3d5975a75f88656B09B3086e82CBcAF8470F517E",
    "paymentRef": null,
    "status": "waived",
    "via": "trial"
  },
  "hackathon": null,
  "report": {
    "markers": [
      "1. Goal intake — present. Conquest.ts:1051 — if (method === \"POST\") {.",
      "2. Decision seam — present. src/agents/telemetry-auditor.ts:67 — const response = await input.llm.complete({.",
      "3. Tool dispatch — absent. Looked for a tool/function schema handed to the model (tools: [...], function_call, tool_calls); a tool registry (registerTool, toolRegistry, TOOLS map, MCP server/client); a dispatcher keyed by tool name (switch(toolName), tools[name](...), dispatch(...)).",
      "4. The loop — present. src/engines/markovian/efficiency.ts:89 — for (let step = 1; step <= steps; step += 1) {.",
      "5. Observation feedback — present. src/zetaris/reader.ts:80 — observations.push({.",
      "6. State / memory — present. src/engines/hmem/conflicts.ts:47 — export function snapshot(memory: Memory): MemoryState {.",
      "7. Recovery — present. gateway.ts:3 — engine.init().catch(err => console.warn(\"⚠️ SurrealDB pending: \" + err.message));.",
      "8. Identity & interface — absent. Looked for an agent card or manifest file in the tree (.well-known/agent.json, agent-card.json, mcp.json, openapi.*); a served agent card or API description route (a handler for /.well-known/agent.json, /agent-card, /openapi); a declared identity object with name, version and capabilities/skills; an agent protocol server (A2A, MCP, ACP) that other parties can address.",
      "9. Boundaries — present. src/engines/markovian/markovian.ts:319 — const budget = this.config.carryoverTokens * 4.",
      "10. Trace — present. src/engines/world-model/world.ts:97 — private readonly auditLog: AuditEntry[] = []."
    ],
    "nextSteps": [
      "Build tool dispatch: a tool/function schema handed to the model (tools: [...], function_call, tool_calls).",
      "Build identity & interface: an agent card or manifest file in the tree (.well-known/agent.json, agent-card.json, mcp.json, openapi.*)."
    ],
    "summary": "smoke-trial is admitted. The office found 8 of 10 Agentic Baseline markers in the code at https://github.com/muziconsulting-cloud/conquest-designer; the pass line is 7. Still missing: tool dispatch, identity & interface.",
    "writer": "office"
  },
  "request": {
    "agentName": "smoke-trial",
    "profile": "general",
    "repoUrl": "https://github.com/muziconsulting-cloud/conquest-designer"
  },
  "snapshot": {
    "commits": 34,
    "files": 183,
    "omissions": [
      "1 file(s) over 262144 bytes were not read"
    ],
    "source": {
      "kind": "github",
      "owner": "muziconsulting-cloud",
      "ref": "6047c03",
      "repo": "conquest-designer"
    },
    "takenAt": "2026-11-10T03:29:50.145Z",
    "tree": 199
  },
  "timing": {
    "admissionMs": 274,
    "probeMs": 0,
    "reportMs": 0,
    "snapshotMs": 2572,
    "totalMs": 3266,
    "voteMs": 419
  },
  "id": "exam-20261110-cfca719e"
}