arifOS — Constitutional AI Kernel

333 Think · Mind

arif_think

Read-onlyIdempotent

KERNEL 333 · Structured reasoning pass: decomposes a query and returns reasoning steps labeled OBS (observed), DER (derived), INT (interpretation), SPEC (specification) under truth floors. Produces reasoning records only — no verdicts (those come from arif_judge) and no state changes. The plan-family modes draft/review/approve execution plans; simulate and wonder explore counterfactuals. Modes: reason, reflect, verify, axioms, plan, plan_review, plan_approve, refactor_plan, metabolize, simulate, wonder, atlas.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	No	'reason' (default) — decompose a question; 'reflect' — self-review of prior reasoning; 'verify' — check a derivation; 'axioms' — surface hidden assumptions; 'plan'/'plan_review'/'plan_approve'/'refactor_plan' — execution-plan lifecycle; 'metabolize' — consolidate past reasoning; 'simulate' — what-if; 'wonder' — open exploration; 'atlas' — map the problem space.	reason
`query`	No	The question, claim, or problem to reason about, in plain language.
`plan_id`	No	Plan reference from an earlier plan-mode response — needed for the review/approve/refactor steps.
`actor_id`	No	Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
`_envelope`	No	Reserved for the transport layer — never fill this in.
`session_id`	No	Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
`witness_type`	No	Who vouches for the reasoning record: 'ai' (default), 'human', or 'external' system.	ai
`session_token`	No	Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unauthenticated.

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedOct 1, 2026

addedInput schema / properties / _envelope / description

Added value: +"Reserved for the transport layer — never fill this in."

addedInput schema / properties / actor_id / description

Added value: +"Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you."

addedInput schema / properties / mode / description

Added value: +"'reason' (default) — decompose a question; 'reflect' — self-review of prior reasoning; 'verify' — check a derivation; 'axioms' — surface hidden assumptions; 'plan'/'plan_review'/'plan_approve'/'refactor_plan' — execution-plan lifecycle; 'metabolize' — consolidate past reasoning; 'simulate' — what-if; 'wonder' — open exploration; 'atlas' — map the problem space."

addedInput schema / properties / plan_id / description

Added value: +"Plan reference from an earlier plan-mode response — needed for the review/approve/refactor steps."

addedInput schema / properties / query / description

Added value: +"The question, claim, or problem to reason about, in plain language."

addedInput schema / properties / session_id / description

Added value: +"Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session."

addedInput schema / properties / session_token / description

Added value: +"Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unauthenticated."

addedInput schema / properties / witness_type / description

Added value: +"Who vouches for the reasoning record: 'ai' (default), 'human', or 'external' system."

Changed8 schema fields changedOct 1, 2026

removedInput schema / properties / _envelope / description

Removed value: -"Reserved for the transport layer — never fill this in."

removedInput schema / properties / actor_id / description

Removed value: -"Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you."

removedInput schema / properties / mode / description

Removed value: -"'reason' (default) — decompose a question; 'reflect' — self-review of prior reasoning; 'verify' — check a derivation; 'axioms' — surface hidden assumptions; 'plan'/'plan_review'/'plan_approve'/'refactor_plan' — execution-plan lifecycle; 'metabolize' — consolidate past reasoning; 'simulate' — what-if; 'wonder' — open exploration; 'atlas' — map the problem space."

removedInput schema / properties / plan_id / description

Removed value: -"Plan reference from an earlier plan-mode response — needed for the review/approve/refactor steps."

removedInput schema / properties / query / description

Removed value: -"The question, claim, or problem to reason about, in plain language."

removedInput schema / properties / session_id / description

Removed value: -"Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session."

removedInput schema / properties / session_token / description

Removed value: -"Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unauthenticated."

removedInput schema / properties / witness_type / description

Removed value: -"Who vouches for the reasoning record: 'ai' (default), 'human', or 'external' system."

Changed8 schema fields changedSep 25, 2026

addedInput schema / properties / _envelope / description

Added value: +"Reserved for the transport layer — never fill this in."

addedInput schema / properties / actor_id / description

Added value: +"Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you."

addedInput schema / properties / mode / description

Added value: +"'reason' (default) — decompose a question; 'reflect' — self-review of prior reasoning; 'verify' — check a derivation; 'axioms' — surface hidden assumptions; 'plan'/'plan_review'/'plan_approve'/'refactor_plan' — execution-plan lifecycle; 'metabolize' — consolidate past reasoning; 'simulate' — what-if; 'wonder' — open exploration; 'atlas' — map the problem space."

addedInput schema / properties / plan_id / description

Added value: +"Plan reference from an earlier plan-mode response — needed for the review/approve/refactor steps."

addedInput schema / properties / query / description

Added value: +"The question, claim, or problem to reason about, in plain language."

addedInput schema / properties / session_id / description

Added value: +"Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session."

addedInput schema / properties / session_token / description

Added value: +"Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unauthenticated."

addedInput schema / properties / witness_type / description

Added value: +"Who vouches for the reasoning record: 'ai' (default), 'human', or 'external' system."

Changed1 schema field changedAug 3, 2026

changedOutput schema / (root)

Previous value: -{
-  "additionalProperties": true,
-  "type": "object"
-}New value: +null

Changed1 schema field changedJul 19, 2026

changedInput schema / properties / mode / enum

Previous value: -[
-  "reason",
-  "reflect",
-  "verify",
-  "axioms",
-  "plan",
-  "plan_review",
-  "plan_approve",
-  "refactor_plan",
-  "metabolize",
-  "simulate",
-  "wonder"
-]New value: +[
+  "reason",
+  "reflect",
+  "verify",
+  "axioms",
+  "plan",
+  "plan_review",
+  "plan_approve",
+  "refactor_plan",
+  "metabolize",
+  "simulate",
+  "wonder",
+  "atlas"
+]

Changed1 schema field changedJul 18, 2026

changedInput schema / properties / mode / enum

Previous value: -[
-  "reason",
-  "reflect",
-  "verify",
-  "axioms",
-  "plan",
-  "plan_review",
-  "plan_approve",
-  "refactor_plan",
-  "metabolize",
-  "simulate"
-]New value: +[
+  "reason",
+  "reflect",
+  "verify",
+  "axioms",
+  "plan",
+  "plan_review",
+  "plan_approve",
+  "refactor_plan",
+  "metabolize",
+  "simulate",
+  "wonder"
+]

Changed1 schema field changedJul 15, 2026

removedInput schema / properties / intent

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}

Changed1 schema field changedJul 14, 2026

addedInput schema / properties / intent

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

Changed1 schema field changedJul 9, 2026

addedInput schema / properties / session_token

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

Changed1 schema field changedJul 4, 2026

changedInput schema / properties / mode / enum

Previous value: -[
-  "reason",
-  "reflect",
-  "verify",
-  "critique",
-  "axioms",
-  "plan",
-  "plan_review",
-  "plan_approve",
-  "refactor_plan",
-  "metabolize"
-]New value: +[
+  "reason",
+  "reflect",
+  "verify",
+  "axioms",
+  "plan",
+  "plan_review",
+  "plan_approve",
+  "refactor_plan",
+  "metabolize",
+  "simulate"
+]

Changed3 schema fields changedJul 3, 2026

addedOutput schema / additionalProperties
```
Added value: +true
```

removedOutput schema / properties

Removed value: -{
-  "_nine_signal_compliant": {
-    "description": "Internal compliance flag",
-    "type": "boolean"
-  },
-  "_violations": {
-    "description": "Non-compliance audit trail",
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "actor_id": {
-    "description": "Sovereign or agent actor ID",
-    "type": [
-      "string",
-      "null"
-    ]
-  },
-  "delta_S": {
-    "description": "Thermodynamic entropy change",
-    "type": "number"
-  },
-  "meta": {
-    "description": "Metadata including actor_id, mode, circuit",
-    "type": "object"
-  },
-  "nine_signal": {
-    "description": "F2 addendum nine-signal block",
-    "type": "object"
-  },
-  "output_policy": {
-    "description": "Policy constraints: DOMAIN_SEAL, DOMAIN_HOLD, DOMAIN_VOID, SIMULATION_ONLY",
-    "type": "string"
-  },
-  "reasons": {
-    "description": "Human-readable justification list",
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "result": {
-    "description": "Tool-specific payload",
-    "type": "object"
-  },
-  "session_id": {
-    "description": "Active session identifier",
-    "type": [
-      "string",
-      "null"
-    ]
-  },
-  "stage_progression": {
-    "description": "Next stage auto-chain hint",
-    "type": [
-      "object",
-      "null"
-    ]
-  },
-  "status": {
-    "description": "Execution status: OK, ERROR, TIMEOUT, DRY_RUN",
-    "type": "string"
-  },
-  "timestamp": {
-    "description": "ISO-8601 timestamp",
-    "type": "string"
-  },
-  "tool": {
-    "description": "Canonical tool name that produced this response",
-    "type": "string"
-  },
-  "verdict": {
-    "description": "Constitutional verdict: SEAL, HOLD, VOID, SABAR, PROVISIONAL, PARTIAL",
-    "type": "string"
-  }
-}

removedOutput schema / required

Removed value: -[
-  "status",
-  "tool",
-  "verdict",
-  "result",
-  "nine_signal",
-  "reasons"
-]

First observedJun 30, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description adds value by specifying 'Produces reasoning records only — no verdicts and no state changes,' which aligns with the annotations. It also mentions 'under truth floors' as a behavioral constraint. No contradictions.

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?

The description is a single dense paragraph that front-loads the core purpose and then lists modes. It is efficient and avoids redundancy, though a bulleted mode list might improve scannability. Every sentence contributes to understanding the tool.

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

Completeness4/5

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

Given the tool's complexity (8 parameters, 12 modes) and the rich parameter descriptions in the schema, the description provides a solid high-level overview and distinguishes the tool from arif_judge. It does not explain the exact output format or the meaning of 'truth floors,' but the schema covers parameter details and no output schema is expected. It is adequate for an agent to select and invoke the tool.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already explains each parameter. The description adds marginal value by grouping modes (e.g., plan-family, simulate/wonder) but largely restates information already present in the schema's mode enum. It does not compensate for any coverage gap because there is none.

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

Purpose5/5

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

The description states a specific verb ('decomposes a query'), a clear resource ('structured reasoning pass'), and distinguishes its output (reasoning records labeled OBS/DER/INT/SPEC) from verdicts (which arif_judge provides). It also enumerates the modes, making the tool's purpose unambiguous and differentiating it from siblings.

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

Usage Guidelines4/5

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

The description explicitly notes that verdicts come from arif_judge, providing an alternative, and groups plan-family modes and exploratory modes. However, it does not give explicit 'when to use this vs. that' conditions for all siblings, leaving some inference to the agent.

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 Kernel tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

333 Think · Mind

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources