Is AI Design Blueprint Doctrine down?

• Renamed "architect.certify" → "architect_certify" (letters, digits, _ and - only; max 64). Keep the old name as an alias for a release if clients already call it. (verify)

{
  "name": "architect_certify",
  "description": "Pro/Teams: second-pass adversarial certification of an architect.validate run that scored production_ready (A or B first-pass tier). ON CLIENT TIMEOUT: DO NOT RETRY THIS TOOL. **RECOVERY FIRST**: the run_id is emitted in the FIRST notifications/progress event at t=0s (BEFORE the LLM call begins). Capture it. On timeout, call `me.validation_history(run_id='<that-id>')` to fetch the persisted cert verdict; the server-side run completes independently within a 6-minute budget. This is the canonical ",
  "inputSchema": {
    "type": "object",
    "title": "architect_certify_runArguments",
    "required": [
      "run_id"
    ],
    "properties": {
      "code": {
        "type": "string",
        "title": "Code",
        "default": "",
        "description": "The same code that was sent to architect.validate to produce this run_id. Sent verbatim: the cert reviewer needs the actual code to surface production_blockers the first pass missed. May be omitted (empty string) when the prior validate stored the code under the 24h cert-retry hold; in that case the server reuses the stored code automatically. Handled as the tool description states: sent to OpenAI (US) for the check (no-training) and persisted at OpenAI, JSON-escaped and delimited as inert data."
      },
      "run_id": {
        "type": "string",
        "title": "Run Id",
        "description": "The run_id from a prior architect.validate call. Returned in the validate response when persistence_status='saved'. Must be owned by the caller (per-user authorisation, same gate as me.validation_history)."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "openWorldHint": true,
    "idempotentHint": false,
    "destructiveHint": false
  },
  "title": "Certify Production-Ready Architecture"
}

• Renamed "architect.validate" → "architect_validate" (letters, digits, _ and - only; max 64). Keep the old name as an alias for a release if clients already call it. (verify)

{
  "name": "architect_validate",
  "description": "Pro/Teams: first-pass doctrine review of agentic code/workflow against the 10-principle AI Design Blueprint doctrine. ON CLIENT TIMEOUT: DO NOT RETRY THIS TOOL. Long-running LLM call (60-180s typical); MCP clients commonly close the call before the server returns. Retrying re-runs the 60-180s LLM call from scratch and burns compute. RECOVERY: the run_id is emitted in the FIRST notifications/progress event at t=0s (before the LLM call begins), capture it. On timeout, call `me.validation_history(r",
  "inputSchema": {
    "type": "object",
    "title": "validate_agent_architectureArguments",
    "required": [
      "implementation_context"
    ],
    "properties": {
      "task": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Task",
        "default": null,
        "description": "What the agent or workflow is trying to accomplish. Adds evaluation context."
      },
      "files": {
        "anyOf": [
          {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          {
            "type": "null"
          }
        ],
        "title": "Files",
        "default": null,
        "description": "List of file paths relevant to the implementation context."
      },
      "goals": {
        "anyOf": [
          {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          {
            "type": "null"
          }
        ],
        "title": "Goals",
        "default": null,
        "description": "Specific safety or quality goals to evaluate against (e.g. 'prevent irreversible actions', 'explicit approvals')."
      },
      "language": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Language",
        "default": null,
        "description": "Programming language of the code being evaluated (e.g. 'python', 'typescript')."
      },
      "focus_area": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Focus Area",
        "default": null,
        "description": "Narrow the evaluation to a specific principle cluster or slug (e.g. 'delegation', 'visibility', 'establish-trust-through-inspectability')."
      },
      "repository": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Repository",
        "default": null,
        "description": "Iteration key. SAME value across calls auto-resolves the most recent prior run as `prior_run_baseline` for iteration-aware grading (per-principle severity deltas, regressions/improvements). CHANGING the value (even subtly with an `iter-2` suffix) silently severs the chain and yields a fresh blind first-shot. Round numbering belongs in `task`, not here. Empirical evidence of why anchoring matters: PR #157 iter1 33/F vs iter2 100/A on byte-identical baseline-race primitives (+67 spread); invoice-payment-manager #158 38/F vs #159 74/C (+36 spread), same code, score variance from non-deterministic LLM at reasoning_effort=high; the baseline anchor collapses this onto a stable arc."
      },
      "session_id": {
        "anyOf": [
          {
            "type": "integer"
          },
          {
            "type": "null"
          }
        ],
        "title": "Session Id",
        "default": null,
        "description": "Optional Governed Session to attach this run to (GEP-M2). Must reference a session YOU own (list via me.sessions; sessions are created in the web app at /app/sessions): foreign ids are refused before any model call. The run then appears on the session's timeline alongside the other lenses. With private_session=true no run is stored so nothing attaches, but the ownership check still runs FIRST: a session id you don't own fails the call either way."
      },
      "example_limit": {
        "type": "integer",
        "title": "Example Limit",
        "default": 3,
        "minimum": 1,
        "description": "Maximum number of curated examples to include in recommendations."
      },
      "private_session": {
        "type": "boolean",
        "title": "Private Session",
        "default": false,
        "description": "Set to true to skip the stored run AND prior-run anchoring AND run_id recovery for this call. Operational security and cost logs are still kept, per the Privacy Policy. The request is also not persisted in the model provider's response store; the provider's abuse-monitoring retention still applies. Use for private one-shots that don't participate in the iteration arc. Default false."
      },
      "implementation_context": {
        "type": "string",
        "title": "Implementation Context",
        "description": "The artifact under review. SEND FULL FILE CONTENTS VERBATIM: the architect cites per-line evidence (identifiers, branch ordering, structural choices); any compression destroys evidence and produces hallucinated findings on code that isn't there. CONCRETE DON'TS: do NOT replace docstrings/comments with `...`; do NOT condense multi-line statements; do NOT replace dict/set comprehensions with `{...}`; do NOT remove explanatory comments to save tokens. If the file is large, split into MULTIPLE architect.validate calls scoped by file/module: never truncate one call. Architecture summaries (high-level prose) accepted ONLY for greenfield (no code yet); never as a substitute for code that already exists."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "openWorldHint": true,
    "idempotentHint": false,
    "destructiveHint": false
  },
  "title": "Validate Agent Architecture"
}

• Renamed "architect.validate_consensus" → "architect_validate_consensus" (letters, digits, _ and - only; max 64). Keep the old name as an alias for a release if clients already call it. (verify)

{
  "name": "architect_validate_consensus",
  "description": "Pro/Teams: N-shot CONSENSUS doctrine review of agentic code. ON CLIENT TIMEOUT: DO NOT RETRY THIS TOOL. Long-running (~80-120s for N=3 parallel LLM calls); MCP clients often close the call before the server returns. Retrying re-runs N × 60-180s LLM calls from scratch and burns N× compute. RECOVERY: same heartbeat pattern as architect.validate, the run_id is emitted in the FIRST progress event at t=0s (before LLM children fire); on timeout, call `me.validation_history(run_id='<that-id>')` to fetc",
  "inputSchema": {
    "type": "object",
    "title": "validate_consensus_agent_architectureArguments",
    "required": [
      "implementation_context"
    ],
    "properties": {
      "n": {
        "type": "integer",
        "title": "N",
        "default": 3,
        "maximum": 10,
        "minimum": 2,
        "description": "Number of parallel child runs. Default 3 (the variance signal is visible at N=3; cost = 3× LLM bill). Capped server-side by Settings.consensus_n_max (default 5)."
      },
      "task": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Task",
        "default": null,
        "description": "What the agent or workflow is trying to accomplish."
      },
      "files": {
        "anyOf": [
          {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          {
            "type": "null"
          }
        ],
        "title": "Files",
        "default": null,
        "description": "List of file paths relevant to the implementation."
      },
      "goals": {
        "anyOf": [
          {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          {
            "type": "null"
          }
        ],
        "title": "Goals",
        "default": null,
        "description": "Specific safety or quality goals to evaluate against."
      },
      "language": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Language",
        "default": null,
        "description": "Programming language of the code (e.g. 'python')."
      },
      "focus_area": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Focus Area",
        "default": null,
        "description": "Optional: narrow the review to a principle cluster or slug."
      },
      "repository": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Repository",
        "default": null,
        "description": "Iteration key. Consensus children all run unanchored (`private_session=True`), but the consolidated row IS persisted under this key: discoverable as prior baseline for the next single-shot `architect.validate`. Same value across calls keeps the iteration arc inspectable."
      },
      "example_limit": {
        "type": "integer",
        "title": "Example Limit",
        "default": 3,
        "minimum": 1,
        "description": "Max curated examples per child run."
      },
      "implementation_context": {
        "type": "string",
        "title": "Implementation Context",
        "description": "The artifact under review. SEND FULL FILE CONTENTS VERBATIM: same constraint as architect.validate. Truncation produces hallucinated findings on code that isn't there."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "openWorldHint": true,
    "idempotentHint": false,
    "destructiveHint": false
  },
  "title": "Validate Agent Architecture (Consensus Mode)"
}