arifOS — Constitutional AI Governance

777 Forge · Execute Gate

arif_forge

Destructive

Apply an authorized system modification. Requires a valid seal_verdict_id obtained from arif_judge. Mode: dry_run (preview impact without execution), apply (execute authorized change). Outputs: execution receipt.

Input Schema

Name	Required	Description	Default
`mode`	No	'engineer' (default) — plan and apply the work; 'dry_run' — preview what would happen, nothing is applied; 'query' — read-only questions about the workspace; 'write' — write files; 'generate' — generate code or content; 'commit' — commit prepared work; 'recall' — retrieve past forge artifacts.	engineer
`query`	No	The task in plain language when no manifest is supplied, e.g. 'restart the gateway service'.
`plan_id`	No	Plan id from arif_think's plan mode, when executing an approved plan.
`actor_id`	No	Your agent identity, e.g. 'kimi-code/FI-008' — recorded in the audit log.
`manifest`	No	Required for engineer (the default mode), write, and generate: the work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate. mode=dry_run accepts the manifest or a plain-language query; mode=query uses query instead.
`session_id`	No	Session id returned by arif_init; scopes this execution to your governed session.
`arif_ack_id`	No	Acknowledgment id from a prior step, for multi-step execution chains.
`artifact_id`	No	Id of an existing artifact (from an earlier forge or judge response) that this call operates on.
`session_token`	No	Session Continuity Token (SCT) returned by arif_init — proves the session is yours.
`vault_entry_id`	No	Id of the permanent-ledger entry linked to this execution, when one already exists.
`seal_verdict_id`	No	The SEAL verdict id arif_judge returned — without it, nothing is executed.
`ack_irreversible`	No	Set true to confirm you accept this execution cannot be undone, when the judged action was irreversible.
`judge_state_hash`	No	Hash string from the arif_judge SEAL response — proves the verdict has not been tampered with.
`approved_action_hash`	No	Hash of the exact action that was judged — execution is refused if what you submit differs from it.
`constitutional_chain_id`	No	Id of the evidence chain (observe→think→judge) that led to the SEAL — copy it from the judge response.

Output Schema

Name	Required	Description	Default
`meta`	Yes
`tool`	Yes
`result`	Yes
`status`	Yes
`delta_S`	No
`reasons`	Yes
`actor_id`	No
`timestamp`	Yes
`session_id`	No
`nine_signal`	Yes
`output_policy`	No
`stage_progression`	No
`philosophical_anchor`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 18, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "actor_id": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "delta_S": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "meta": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "nine_signal": {
+      "additionalProperties": true,
+      "properties": {
+        "delta": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "plane": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "state",
+            "en"
+          ],
+          "type": "object"
+        },
+        "omega": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "plane": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "state",
+            "en"
+          ],
+          "type": "object"
+        },
+        "overall": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "psi": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "plane": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "state",
+            "en"
+          ],
+          "type": "object"
+        }
+      },
+      "type": "object"
+    },
+    "output_policy": {
+      "type": "string"
+    },
+    "philosophical_anchor": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "result": {
+      "additionalProperties": true,
+      "properties": {
+        "artifact_id": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "execution_trace": {
+          "anyOf": [
+            {
+              "items": {
+                "additionalProperties": true,
+                "type": "object"
+              },
+              "type": "array"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "irreversibility_level": {
+          "type": "string"
+        },
+        "mode": {
+          "type": "string"
+        },
+        "nine_signal": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "reasons": {
+          "anyOf": [
+            {
+              "items": {
+                "type": "string"
+              },
+              "type": "array"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "status": {
+          "type": "string"
+        },
+        "verdict": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "session_id": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stage_progression": {
+      "anyOf": [
+        {
+          "type": "null"
+        },
+        {
+          "properties": {
+            "current_stage": {
+              "type": "string"
+            },
+            "next_prompt": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            },
+            "next_stage": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            },
+            "next_tool": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            }
+          },
+          "type": "object"
+        }
+      ]
+    },
+    "status": {
+      "type": "string"
+    },
+    "timestamp": {
+      "type": "string"
+    },
+    "tool": {
+      "const": "arif_forge"
+    }
+  },
+  "required": [
+    "status",
+    "tool",
+    "result",
+    "meta",
+    "timestamp",
+    "nine_signal",
+    "reasons"
+  ],
+  "type": "object"
+}

Changed1 schema field changedOct 14, 2026

changedInput schema / properties / manifest / description

Previous value: -"Required for engineer (the default mode), write, generate, and dry_run: the work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate. mode=query uses query instead."New value: +"Required for engineer (the default mode), write, and generate: the work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate. mode=dry_run accepts the manifest or a plain-language query; mode=query uses query instead."

Changed2 schema fields changedOct 14, 2026

addedInput schema / allOf

Added value: +[
+  {
+    "if": {
+      "anyOf": [
+        {
+          "not": {
+            "required": [
+              "mode"
+            ]
+          }
+        },
+        {
+          "properties": {
+            "mode": {
+              "enum": [
+                "engineer",
+                "write",
+                "generate"
+              ]
+            }
+          },
+          "required": [
+            "mode"
+          ]
+        }
+      ]
+    },
+    "then": {
+      "required": [
+        "manifest"
+      ]
+    }
+  },
+  {
+    "if": {
+      "properties": {
+        "mode": {
+          "enum": [
+            "dry_run"
+          ]
+        }
+      },
+      "required": [
+        "mode"
+      ]
+    },
+    "then": {
+      "anyOf": [
+        {
+          "required": [
+            "manifest"
+          ]
+        },
+        {
+          "required": [
+            "query"
+          ]
+        }
+      ]
+    }
+  }
+]

changedInput schema / properties / manifest / description

Previous value: -"The work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate."New value: +"Required for engineer (the default mode), write, generate, and dry_run: the work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate. mode=query uses query instead."

Changed1 schema field changedOct 14, 2026

removedInput schema / properties / _envelope

Removed value: -{
-  "default": null,
-  "description": "Internal transport envelope handle — server-side; omit.",
-  "title": "Envelope"
-}

AddedOct 14, 2026

TDQS

B3.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is covered. The description adds real context beyond that — the authorization gate and the dry_run preview path — but says nothing about what happens on refusal, what 'impact' a preview returns, or the irreversibility acknowledgment flow.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short, front-loaded sentences with no filler: purpose, precondition, modes, output. Efficient, though the mode sentence is where the inaccuracy was introduced — brevity at the cost of correctness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter destructive tool the description is thin, but the schema is fully documented and an output schema exists, so the agent can recover most missing detail. What it cannot recover is the tamper-hash / constitutional-chain requirement, which the prose never mentions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so a baseline of 3 would apply, but the description actively misinforms: it lists 'apply' as a mode when the enum contains engineer/query/write/generate/commit/recall/dry_run and no 'apply'. An agent following the prose would submit an invalid mode. It adds no meaning for the hash, session, or chain parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'Apply an authorized system modification' — and distinguishes itself from arif_judge by requiring the verdict that judge produces. The addition of the two modes and the receipt output confirms what kind of operation this is, though the mode list it names is wrong.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives one strong prerequisite: a valid seal_verdict_id from arif_judge, which implies the judge→forge sequence. But it only explains 2 of the 7 modes the schema actually allows, and gives no guidance on when to prefer this over siblings like arif_delegate or arif_seal.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All arifOS — Constitutional AI Governance tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.