Server definition
- Hash
- sha256:260a69b66135909b14edc1382937436f014bc53d438ac443215549516b7f7e0c
- What it is
- What a remote MCP server returned when asked what it offers: 140 tools
The blob, as servednamed by its sha256
{
"instructions": null,
"tools": [
{
"description": "Adaptive compute budgeting: select compute tier (Fast Path to Deep Deliberation) and timeout based on EVC.",
"inputSchema": {
"properties": {
"stakes": {
"default": "normal",
"title": "Stakes",
"type": "string"
},
"task_structure": {
"additionalProperties": true,
"title": "Task Structure",
"type": "object"
}
},
"required": [
"task_structure"
],
"title": "cognitive_allocate_computeArguments",
"type": "object"
},
"name": "cognitive.allocate_compute",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_allocate_computeDictOutput",
"type": "object"
}
},
{
"description": "Transfer structural strategies across disparate domains via Structure-Mapping Engine (SME).",
"inputSchema": {
"properties": {
"source_task_structure_id": {
"title": "Source Task Structure Id",
"type": "string"
},
"strategy_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Strategy Id"
},
"target_task_structure_id": {
"title": "Target Task Structure Id",
"type": "string"
}
},
"required": [
"source_task_structure_id",
"target_task_structure_id"
],
"title": "cognitive_analogical_transferArguments",
"type": "object"
},
"name": "cognitive.analogical_transfer",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_analogical_transferDictOutput",
"type": "object"
}
},
{
"description": "Pragmatic communication: audit speech acts against Gricean maxims (Quality, Quantity, Relation, Manner) and detect deception.",
"inputSchema": {
"properties": {
"act_type": {
"default": "assert",
"title": "Act Type",
"type": "string"
},
"claims": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Claims"
},
"content": {
"title": "Content",
"type": "string"
},
"context_goals": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Context Goals"
},
"recipient_id": {
"default": "all",
"title": "Recipient Id",
"type": "string"
},
"sender_id": {
"default": "agent_1",
"title": "Sender Id",
"type": "string"
},
"speaker_beliefs": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Speaker Beliefs"
}
},
"required": [
"content"
],
"title": "cognitive_analyze_communicationArguments",
"type": "object"
},
"name": "cognitive.analyze_communication",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_analyze_communicationDictOutput",
"type": "object"
}
},
{
"description": "Arbitrate short vs long term payoffs using hyperbolic vs exponential discounting and Ulysses pre-commitment contracts.",
"inputSchema": {
"properties": {
"audit_action_switch": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Audit Action Switch"
},
"gamma_exponential": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Gamma Exponential"
},
"k_hyperbolic": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "K Hyperbolic"
},
"long_term_option": {
"additionalProperties": true,
"title": "Long Term Option",
"type": "object"
},
"register_commitment": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Register Commitment"
},
"short_term_option": {
"additionalProperties": true,
"title": "Short Term Option",
"type": "object"
}
},
"required": [
"short_term_option",
"long_term_option"
],
"title": "cognitive_arbitrate_temporal_objectivesArguments",
"type": "object"
},
"name": "cognitive.arbitrate_temporal_objectives",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_arbitrate_temporal_objectivesDictOutput",
"type": "object"
}
},
{
"description": "Epistemic boundary awareness: classify task into KNOWN, KNOWN_UNKNOWN, or UNKNOWN_UNKNOWN (OOD) and track calibration.",
"inputSchema": {
"properties": {
"actual_outcome": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"title": "Actual Outcome"
},
"task_structure": {
"additionalProperties": true,
"title": "Task Structure",
"type": "object"
}
},
"required": [
"task_structure"
],
"title": "cognitive_assess_competenceArguments",
"type": "object"
},
"name": "cognitive.assess_competence",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_assess_competenceDictOutput",
"type": "object"
}
},
{
"description": "Audit the evidence graph for a task before issuing final answers.\n\n Rejects claims such as 'optimal', 'verified', or 'feasible' when their\n evidence dependencies are incomplete.\n ",
"inputSchema": {
"properties": {
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id"
],
"title": "cognitive_audit_evidence_graphArguments",
"type": "object"
},
"name": "cognitive.audit_evidence_graph",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_audit_evidence_graphDictOutput",
"type": "object"
}
},
{
"description": "Build or update an Evidence-Carrying Cognitive Graph for a task structure and solution trace.",
"inputSchema": {
"properties": {
"claims": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Claims"
},
"solution_trace": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Solution Trace"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id"
],
"title": "cognitive_build_evidence_graphArguments",
"type": "object"
},
"name": "cognitive.build_evidence_graph",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_build_evidence_graphDictOutput",
"type": "object"
}
},
{
"description": "Distinguish causal effects (do-calculus) from spurious correlation via backdoor adjustment.",
"inputSchema": {
"properties": {
"edges": {
"items": {
"items": {
"type": "string"
},
"type": "array"
},
"title": "Edges",
"type": "array"
},
"observations": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Observations",
"type": "array"
},
"outcome": {
"title": "Outcome",
"type": "string"
},
"treatment": {
"title": "Treatment",
"type": "string"
}
},
"required": [
"edges",
"treatment",
"outcome",
"observations"
],
"title": "cognitive_causal_analysisArguments",
"type": "object"
},
"name": "cognitive.causal_analysis",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_causal_analysisDictOutput",
"type": "object"
}
},
{
"description": "Compile a Dynamic Constraint Lattice (DCL) into algebraic boundaries, conservation laws, and reachability cones.",
"inputSchema": {
"properties": {
"goal_conditions": {
"anyOf": [
{
"additionalProperties": {
"items": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"type": "array"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal Conditions"
},
"initial_state": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Initial State"
},
"max_rate_of_change": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Max Rate Of Change"
},
"step_budget": {
"default": 5,
"title": "Step Budget",
"type": "integer"
},
"task_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Data"
},
"task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure Id"
}
},
"title": "cognitive_compile_invariant_latticeArguments",
"type": "object"
},
"name": "cognitive.compile_invariant_lattice",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_compile_invariant_latticeDictOutput",
"type": "object"
}
},
{
"description": "Skill Composition: synthesize a composite multi-stage StrategyIR from primitive strategies.\n\n Chains multiple specialized skills (e.g. Graph Coloring + Topological Sort + Allocation)\n into a compound pipeline with explicit stage transitions and end-to-end verification.\n ",
"inputSchema": {
"properties": {
"composite_name": {
"title": "Composite Name",
"type": "string"
},
"description": {
"default": "",
"title": "Description",
"type": "string"
},
"strategy_ids": {
"items": {
"type": "string"
},
"title": "Strategy Ids",
"type": "array"
}
},
"required": [
"strategy_ids",
"composite_name"
],
"title": "cognitive_compose_strategiesArguments",
"type": "object"
},
"name": "cognitive.compose_strategies",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_compose_strategiesDictOutput",
"type": "object"
}
},
{
"description": "Compute intrinsic drives: novelty & prediction surprise curiosity, empowerment (channel capacity), and learning progress.",
"inputSchema": {
"properties": {
"actual_state": {
"additionalProperties": true,
"title": "Actual State",
"type": "object"
},
"extrinsic_reward": {
"default": 0,
"title": "Extrinsic Reward",
"type": "number"
},
"predicted_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Predicted State"
},
"reachable_states": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Reachable States"
},
"skill_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Skill Name"
},
"skill_success": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"title": "Skill Success"
}
},
"required": [
"actual_state"
],
"title": "cognitive_compute_intrinsic_rewardsArguments",
"type": "object"
},
"name": "cognitive.compute_intrinsic_rewards",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_compute_intrinsic_rewardsDictOutput",
"type": "object"
}
},
{
"description": "Compute coordinate-free topological invariant signature of a lattice or task.",
"inputSchema": {
"properties": {
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
},
"task_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Data"
}
},
"title": "cognitive_compute_lattice_signatureArguments",
"type": "object"
},
"name": "cognitive.compute_lattice_signature",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_compute_lattice_signatureDictOutput",
"type": "object"
}
},
{
"description": "Number theory: primality, factoring, extended GCD, Diophantine, modular inverse, CRT, combinatorics, Fibonacci.",
"inputSchema": {
"properties": {
"a": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "A"
},
"b": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "B"
},
"c": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "C"
},
"k": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "K"
},
"m": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "M"
},
"moduli": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Moduli"
},
"n": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "N"
},
"operation": {
"title": "Operation",
"type": "string"
},
"remainders": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Remainders"
}
},
"required": [
"operation"
],
"title": "cognitive_compute_number_theoryArguments",
"type": "object"
},
"name": "cognitive.compute_number_theory",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_compute_number_theoryDictOutput",
"type": "object"
}
},
{
"description": "Counterfactual engine: evaluate 'What if I had done X instead of Y at step t?' using Pearl's abduction-intervention-prediction.",
"inputSchema": {
"properties": {
"counterfactual_action": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "string"
}
],
"title": "Counterfactual Action"
},
"dt": {
"default": 1,
"title": "Dt",
"type": "number"
},
"factual_trace": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Factual Trace",
"type": "array"
},
"intervention_step": {
"title": "Intervention Step",
"type": "integer"
}
},
"required": [
"factual_trace",
"intervention_step",
"counterfactual_action"
],
"title": "cognitive_counterfactual_what_ifArguments",
"type": "object"
},
"name": "cognitive.counterfactual_what_if",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_counterfactual_what_ifDictOutput",
"type": "object"
}
},
{
"description": "Instantiate and initialize a simulated cognitive environment (spatial_commons, multi_agent_arena, sequential_puzzle).",
"inputSchema": {
"properties": {
"env_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Env Id"
},
"env_type": {
"default": "spatial_commons",
"title": "Env Type",
"type": "string"
},
"parameters": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Parameters"
}
},
"title": "cognitive_create_simulated_environmentArguments",
"type": "object"
},
"name": "cognitive.create_simulated_environment",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_create_simulated_environmentDictOutput",
"type": "object"
}
},
{
"description": "Subject candidate trajectories to adversarial algebraic perturbations to calculate Robustness Index (R) and project hardened paths.",
"inputSchema": {
"properties": {
"lattice_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Data"
},
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
},
"max_perturbations": {
"default": 24,
"title": "Max Perturbations",
"type": "integer"
},
"step_budget": {
"default": 5,
"title": "Step Budget",
"type": "integer"
},
"stress_amplitude": {
"default": 0.15,
"title": "Stress Amplitude",
"type": "number"
},
"trajectory": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Trajectory"
}
},
"title": "cognitive_crucible_stress_testArguments",
"type": "object"
},
"name": "cognitive.crucible_stress_test",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_crucible_stress_testDictOutput",
"type": "object"
}
},
{
"description": "Evaluate support status and confidence for an individual claim with evidence.",
"inputSchema": {
"properties": {
"assumptions": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Assumptions"
},
"claim": {
"title": "Claim",
"type": "string"
},
"dependencies": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Dependencies"
},
"evidence": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Evidence"
},
"invalidation_conditions": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Invalidation Conditions"
},
"object": {
"default": "",
"title": "Object",
"type": "string"
},
"relation": {
"default": "states",
"title": "Relation",
"type": "string"
},
"subject": {
"default": "",
"title": "Subject",
"type": "string"
},
"task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure Id"
}
},
"required": [
"claim"
],
"title": "cognitive_evaluate_claim_evidenceArguments",
"type": "object"
},
"name": "cognitive.evaluate_claim_evidence",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_evaluate_claim_evidenceDictOutput",
"type": "object"
}
},
{
"description": "Multi-agent cooperation: analyze game payoff matrices, compute Nash/Pareto equilibria, and execute reciprocity policies.",
"inputSchema": {
"properties": {
"contributions": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Contributions"
},
"endowments": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Endowments"
},
"game_type": {
"title": "Game Type",
"type": "string"
},
"multiplier": {
"default": 1.6,
"title": "Multiplier",
"type": "number"
},
"my_history": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "My History"
},
"partner_history": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Partner History"
},
"strategy": {
"default": "tit_for_tat",
"title": "Strategy",
"type": "string"
}
},
"required": [
"game_type"
],
"title": "cognitive_evaluate_cooperationArguments",
"type": "object"
},
"name": "cognitive.evaluate_cooperation",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_evaluate_cooperationDictOutput",
"type": "object"
}
},
{
"description": "Evaluate a counterfactual query on a plan ('What if capacity drops?', 'What if a route fails?', etc.).",
"inputSchema": {
"properties": {
"parameters": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Parameters"
},
"plan_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Plan Id"
},
"query_type": {
"title": "Query Type",
"type": "string"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id",
"query_type"
],
"title": "cognitive_evaluate_counterfactual_queryArguments",
"type": "object"
},
"name": "cognitive.evaluate_counterfactual_query",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_evaluate_counterfactual_queryDictOutput",
"type": "object"
}
},
{
"description": "Evaluate broad generalization across spatial commons, multi-agent arenas, and sequential causal puzzles.",
"inputSchema": {
"properties": {
"benchmark_filter": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Benchmark Filter"
}
},
"title": "cognitive_evaluate_generalization_benchmarksArguments",
"type": "object"
},
"name": "cognitive.evaluate_generalization_benchmarks",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_evaluate_generalization_benchmarksDictOutput",
"type": "object"
}
},
{
"description": "One-call orchestration: identify → gate → guide → solve → verify → report.\n\n Parameters:\n - task: Dict containing:\n - task_structure (or loose definition: name, entities, constraints, etc.)\n - raw (optional): Domain-specific execution payload. If omitted, returns\n status='guidance_only' with 'recommended_action'='supply_raw' and\n an 'expected_raw_formats' object detailing valid schemas.\n Supported problem types for task.raw:\n * scheduling: {\"workers\": [{\"id\": \"w1\", \"eligible_shifts\": [\"s1\"], \"max_shifts\": 1}],\n \"shifts\": [{\"id\": \"s1\", \"required_workers\": 1}]}\n * allocation: {\"consumers\": [{\"id\": \"c1\", \"demands\": {\"r1\": 1}}],\n \"resources\": [{\"id\": \"r1\", \"capacity\": 2}]}\n * graph: {\"nodes\": [\"A\", \"B\"], \"edges\": [[\"A\", \"B\"]]}\n * graph_coloring: {\"nodes\": [\"A\", \"B\"], \"edges\": [[\"A\", \"B\"]], \"colors\": [\"red\", \"blue\"]}\n * shortest_path: {\"nodes\": [\"A\", \"B\"], \"edges\": [[\"A\", \"B\"]], \"weights\": {\"A->B\": 1.0}, \"start\": \"A\", \"target\": \"B\"}\n * math: {\"math\": {\"question\": \"...\", \"quantities\": {...}, \"equations\": [...], \"target_variable\": \"x\", \"ground_truth\": 42.0}}\n * code: {\"code\": {\"code\": \"def solution()...\", \"tests\": [\"assert ...\"]}}\n * pddl: {\"pddl\": {\"plan\": [...], \"init\": {...}, \"goal\": {...}}}\n\n Returns a single envelope with status (completed / guidance_only /\n blocked_until_clarified / no_applicable_guidance / refused_infeasible /\n failed), solution, score, assumptions, failure reasons, and expected_raw_formats.\n ",
"inputSchema": {
"properties": {
"environment": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Environment"
},
"goal": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal"
},
"model_family": {
"default": "generic",
"title": "Model Family",
"type": "string"
},
"task": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task"
}
},
"title": "cognitive_execute_taskArguments",
"type": "object"
},
"name": "cognitive.execute_task",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_execute_taskDictOutput",
"type": "object"
}
},
{
"description": "Few-shot learning: induce a generalized procedural StrategyIR from 1-3 problem traces.\n\n Extracts structural invariants (decision ordering, invariant contracts, verification rules)\n and registers an initial candidate strategy immediately without requiring large training sets.\n ",
"inputSchema": {
"properties": {
"solution_trace": {
"additionalProperties": true,
"title": "Solution Trace",
"type": "object"
},
"source_model": {
"default": "few_shot_learner",
"title": "Source Model",
"type": "string"
},
"strategy_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Strategy Name"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id",
"solution_trace"
],
"title": "cognitive_few_shot_induceArguments",
"type": "object"
},
"name": "cognitive.few_shot_induce",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_few_shot_induceDictOutput",
"type": "object"
}
},
{
"description": "Autonomous goal synthesis from world deficits, depleted reserves, and exploration frontiers with multi-criteria prioritization.",
"inputSchema": {
"properties": {
"depleted_reserves": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Depleted Reserves"
},
"goal_status_update": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal Status Update"
},
"max_active": {
"default": 3,
"title": "Max Active",
"type": "integer"
},
"unexplored_frontiers": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Unexplored Frontiers"
},
"world_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "World State"
}
},
"title": "cognitive_generate_and_prioritize_goalsArguments",
"type": "object"
},
"name": "cognitive.generate_and_prioritize_goals",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_generate_and_prioritize_goalsDictOutput",
"type": "object"
}
},
{
"description": "Retrieve details and benchmark results of an experiment (§24, §69).",
"inputSchema": {
"properties": {
"experiment_id": {
"title": "Experiment Id",
"type": "string"
}
},
"required": [
"experiment_id"
],
"title": "cognitive_get_experimentArguments",
"type": "object"
},
"name": "cognitive.get_experiment",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_get_experimentDictOutput",
"type": "object"
}
},
{
"description": "Compile a final evidence result listing supporting evidence, assumptions, missing evidence,\n contradictions, unchecked dependencies, confidence, and invalidation conditions.",
"inputSchema": {
"properties": {
"target_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Id"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id"
],
"title": "cognitive_get_final_evidence_resultArguments",
"type": "object"
},
"name": "cognitive.get_final_evidence_result",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_get_final_evidence_resultDictOutput",
"type": "object"
}
},
{
"description": "Retrieve applicable validated strategies for a task (§24, §18).\n\n Does NOT return unverified or suspended strategies as trusted guidance.\n Provides calibrated uncertainty, applicability conditions, and negative transfer warnings.\n\n Args:\n task_structure_id: UUID of the abstract task structure.\n environment: Environment characteristics.\n goal: Goal description and metric targets.\n available_capabilities: Capabilities supported by the caller.\n model_family: Model family of the consumer agent (e.g. 'claude', 'gpt', 'local').\n\n Returns:\n Ranked list of applicable strategies with procedures, conditions, and evidence.\n Failures return {\"error\", \"detail\", \"hint\"} — never a bare exception.\n ",
"inputSchema": {
"properties": {
"available_capabilities": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Available Capabilities"
},
"environment": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Environment"
},
"goal": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal"
},
"model_family": {
"default": "generic",
"title": "Model Family",
"type": "string"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id"
],
"title": "cognitive_get_guidanceArguments",
"type": "object"
},
"name": "cognitive.get_guidance",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_get_guidanceDictOutput",
"type": "object"
}
},
{
"description": "Retrieve a usable strategy: steps, when to use, when not, evidence summary.\n\n Disclosure: you learn WHAT to execute, never HOW the engine induces,\n verifies, or ranks knowledge (no trust signals, audit, tenants, traces).\n ",
"inputSchema": {
"properties": {
"strategy_id": {
"title": "Strategy Id",
"type": "string"
}
},
"required": [
"strategy_id"
],
"title": "cognitive_get_strategyArguments",
"type": "object"
},
"name": "cognitive.get_strategy",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_get_strategyDictOutput",
"type": "object"
}
},
{
"description": "Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval.",
"inputSchema": {
"properties": {
"strategy_id": {
"title": "Strategy Id",
"type": "string"
}
},
"required": [
"strategy_id"
],
"title": "cognitive_get_strategy_reportArguments",
"type": "object"
},
"name": "cognitive.get_strategy_report",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_get_strategy_reportDictOutput",
"type": "object"
}
},
{
"description": "Non-LLM compositional semantics: parse utterance into semantic predicates and evaluate directly against WorldState.",
"inputSchema": {
"properties": {
"utterance": {
"title": "Utterance",
"type": "string"
},
"world_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "World State"
}
},
"required": [
"utterance"
],
"title": "cognitive_ground_languageArguments",
"type": "object"
},
"name": "cognitive.ground_language",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_ground_languageDictOutput",
"type": "object"
}
},
{
"description": "Decompose high-level goals into milestone subgoals using Hierarchical Task Network (HTN) planning.",
"inputSchema": {
"properties": {
"compound_tasks": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Compound Tasks"
},
"goal_tasks": {
"items": {
"type": "string"
},
"title": "Goal Tasks",
"type": "array"
},
"initial_state": {
"additionalProperties": true,
"title": "Initial State",
"type": "object"
},
"primitive_operators": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Primitive Operators"
}
},
"required": [
"goal_tasks",
"initial_state"
],
"title": "cognitive_hierarchical_planArguments",
"type": "object"
},
"name": "cognitive.hierarchical_plan",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_hierarchical_planDictOutput",
"type": "object"
}
},
{
"description": "Create or resolve an abstract task structure without storing raw private content (§24).\n\n Args:\n task_structure: Structural representation (entities, constraints, variables, etc.).\n environment: Environmental context and characteristics.\n goal: Objective and optimization goals.\n\n Returns:\n task_structure_id, structural_features, and matching existing structures.\n On invalid input returns {\"error\", \"detail\", \"hint\"} instead of raising,\n so the MCP client sees the cause instead of a generic execution error.\n ",
"inputSchema": {
"properties": {
"environment": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Environment"
},
"goal": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal"
},
"task_structure": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure"
}
},
"title": "cognitive_identify_taskArguments",
"type": "object"
},
"name": "cognitive.identify_task",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_identify_taskDictOutput",
"type": "object"
}
},
{
"description": "Discover topological homomorphism between source experience and target problem, transducing solution paths.",
"inputSchema": {
"properties": {
"source_lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source Lattice Id"
},
"step_budget": {
"default": 5,
"title": "Step Budget",
"type": "integer"
},
"target_lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Lattice Id"
},
"target_task_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Task Data"
}
},
"title": "cognitive_induce_morphic_transferArguments",
"type": "object"
},
"name": "cognitive.induce_morphic_transfer",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_induce_morphic_transferDictOutput",
"type": "object"
}
},
{
"description": "Perform logical deduction (Horn clauses) or exact probabilistic Bayesian network inference.",
"inputSchema": {
"properties": {
"evidence": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Evidence"
},
"facts": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Facts"
},
"nodes": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Nodes"
},
"probabilistic": {
"default": false,
"title": "Probabilistic",
"type": "boolean"
},
"query": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Query"
},
"query_var": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Query Var"
},
"rules": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Rules"
}
},
"title": "cognitive_inferArguments",
"type": "object"
},
"name": "cognitive.infer",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_inferDictOutput",
"type": "object"
}
},
{
"description": "Infer human values via Bradley-Terry IRL, detect Goodhart's law / specification gaming, and assess CIRL deference.",
"inputSchema": {
"properties": {
"action_evaluated": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Action Evaluated"
},
"action_irreversible": {
"default": false,
"title": "Action Irreversible",
"type": "boolean"
},
"action_stakes": {
"default": "normal",
"title": "Action Stakes",
"type": "string"
},
"baseline_metrics": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Baseline Metrics"
},
"comparisons": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Comparisons"
},
"detect_gaming": {
"default": false,
"title": "Detect Gaming",
"type": "boolean"
},
"projected_metrics": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Projected Metrics"
},
"proxy_metric": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Proxy Metric"
}
},
"title": "cognitive_infer_human_valuesArguments",
"type": "object"
},
"name": "cognitive.infer_human_values",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_infer_human_valuesDictOutput",
"type": "object"
}
},
{
"description": "Inspect grounded lexicon acquired via situated interaction (learned vocabulary, concept bindings, confidence).",
"inputSchema": {
"properties": {},
"title": "cognitive_inspect_lexiconArguments",
"type": "object"
},
"name": "cognitive.inspect_lexicon",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_inspect_lexiconDictOutput",
"type": "object"
}
},
{
"description": "Engine self-model introspection: inspect capabilities, domain competence, active subsystems, and safety status.",
"inputSchema": {
"properties": {},
"title": "cognitive_inspect_self_modelArguments",
"type": "object"
},
"name": "cognitive.inspect_self_model",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_inspect_self_modelDictOutput",
"type": "object"
}
},
{
"description": "Online Real-Time Error Reflection & Strategy Patching.\n\n When an execution fails, analyzes root-cause constraint violations, synthesizes\n new exception cases and repair procedures, verifies update against anchor regression,\n and publishes the patched strategy version in real time.\n ",
"inputSchema": {
"properties": {
"execution_trace": {
"additionalProperties": true,
"title": "Execution Trace",
"type": "object"
},
"strategy_id": {
"title": "Strategy Id",
"type": "string"
},
"task_instance": {
"additionalProperties": true,
"title": "Task Instance",
"type": "object"
},
"violations": {
"items": {
"type": "string"
},
"title": "Violations",
"type": "array"
}
},
"required": [
"strategy_id",
"task_instance",
"execution_trace",
"violations"
],
"title": "cognitive_learn_from_mistakeArguments",
"type": "object"
},
"name": "cognitive.learn_from_mistake",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_learn_from_mistakeDictOutput",
"type": "object"
}
},
{
"description": "Interactive language acquisition: learn word-concept bindings through cross-situational observation, games, and feedback.",
"inputSchema": {
"properties": {
"candidate_objects": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Candidate Objects"
},
"feedback_correct": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Feedback Correct"
},
"feedback_incorrect": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Feedback Incorrect"
},
"interaction_type": {
"title": "Interaction Type",
"type": "string"
},
"referent_features": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Referent Features"
},
"target_object_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Object Id"
},
"utterance": {
"title": "Utterance",
"type": "string"
}
},
"required": [
"interaction_type",
"utterance"
],
"title": "cognitive_learn_language_interactionArguments",
"type": "object"
},
"name": "cognitive.learn_language_interaction",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_learn_language_interactionDictOutput",
"type": "object"
}
},
{
"description": "Online world model learning: update state transition priors from empirical execution traces.",
"inputSchema": {
"properties": {
"transitions": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Transitions",
"type": "array"
}
},
"required": [
"transitions"
],
"title": "cognitive_learn_world_modelArguments",
"type": "object"
},
"name": "cognitive.learn_world_model",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_learn_world_modelDictOutput",
"type": "object"
}
},
{
"description": "Discovery: list recorded benchmark experiment IDs for cognitive.get_experiment.",
"inputSchema": {
"properties": {},
"title": "cognitive_list_experimentsArguments",
"type": "object"
},
"name": "cognitive.list_experiments",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_list_experimentsDictOutput",
"type": "object"
}
},
{
"description": "Exact rational matrix & vector algebra: multiply, determinant, inverse, transpose, trace, eigenvalues, dot/cross.",
"inputSchema": {
"properties": {
"matrix_A": {
"anyOf": [
{
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Matrix A"
},
"matrix_B": {
"anyOf": [
{
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Matrix B"
},
"operation": {
"title": "Operation",
"type": "string"
},
"vector_u": {
"anyOf": [
{
"items": {
"type": "number"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Vector U"
},
"vector_v": {
"anyOf": [
{
"items": {
"type": "number"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Vector V"
}
},
"required": [
"operation"
],
"title": "cognitive_matrix_algebraArguments",
"type": "object"
},
"name": "cognitive.matrix_algebra",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_matrix_algebraDictOutput",
"type": "object"
}
},
{
"description": "Introspective reasoning critic: inspect trace in-flight to catch cycles, invariant drift, vacuous output, and stalling.",
"inputSchema": {
"properties": {
"current_step": {
"additionalProperties": true,
"title": "Current Step",
"type": "object"
},
"invariants": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Invariants"
},
"trace_history": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Trace History",
"type": "array"
}
},
"required": [
"trace_history",
"current_step"
],
"title": "cognitive_monitor_reasoningArguments",
"type": "object"
},
"name": "cognitive.monitor_reasoning",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_monitor_reasoningDictOutput",
"type": "object"
}
},
{
"description": "Convert natural-language task text into CIR and task_structure dict.\n\n Every natural-language input is normalized into CIR before reasoning.\n Returns both the normalized CIR and a human-readable explanation.\n ",
"inputSchema": {
"properties": {
"description": {
"default": "",
"title": "Description",
"type": "string"
},
"prompt": {
"default": "",
"title": "Prompt",
"type": "string"
},
"task_text": {
"default": "",
"title": "Task Text",
"type": "string"
},
"text": {
"default": "",
"title": "Text",
"type": "string"
}
},
"title": "cognitive_parse_taskArguments",
"type": "object"
},
"name": "cognitive.parse_task",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_parse_taskDictOutput",
"type": "object"
}
},
{
"description": "Synthesize the best verified plan across candidate rollouts, uncertainty tracking, and constraint pruning.",
"inputSchema": {
"properties": {
"current_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Current State"
},
"goal": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal"
},
"horizon": {
"default": 5,
"title": "Horizon",
"type": "integer"
},
"method": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Method"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id"
],
"title": "cognitive_plan_with_counterfactualsArguments",
"type": "object"
},
"name": "cognitive.plan_with_counterfactuals",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_plan_with_counterfactualsDictOutput",
"type": "object"
}
},
{
"description": "Forward world model: predict future state trajectories and uncertainty bounds under actions.",
"inputSchema": {
"properties": {
"actions": {
"items": {},
"title": "Actions",
"type": "array"
},
"dt": {
"default": 1,
"title": "Dt",
"type": "number"
},
"state": {
"additionalProperties": true,
"title": "State",
"type": "object"
},
"timescale": {
"default": "micro",
"title": "Timescale",
"type": "string"
}
},
"required": [
"state",
"actions"
],
"title": "cognitive_predict_world_stateArguments",
"type": "object"
},
"name": "cognitive.predict_world_state",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_predict_world_stateDictOutput",
"type": "object"
}
},
{
"description": "Project a candidate state or plan step onto the Singular Transition Manifold M = F(S0) ∩ B(Goal).\n \n Returns the corrected state, corrective delta vector Delta S = S* - S, and boundary distance margins.\n ",
"inputSchema": {
"properties": {
"lattice_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Data"
},
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
},
"state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "State"
}
},
"title": "cognitive_project_to_manifoldArguments",
"type": "object"
},
"name": "cognitive.project_to_manifold",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_project_to_manifoldDictOutput",
"type": "object"
}
},
{
"description": "Propose a candidate strategy from problem-solving experience (§24, §2).\n\n IMPORTANT: This NEVER makes the strategy TRUSTED.\n The strategy enters CANDIDATE state and requires objective verification.\n ",
"inputSchema": {
"properties": {
"applicability": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Applicability"
},
"description": {
"title": "Description",
"type": "string"
},
"exceptions": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Exceptions"
},
"experience_ids": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Experience Ids"
},
"name": {
"title": "Name",
"type": "string"
},
"preconditions": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Preconditions"
},
"procedure": {
"items": {
"type": "string"
},
"title": "Procedure",
"type": "array"
},
"source_model": {
"default": "external_model",
"title": "Source Model",
"type": "string"
},
"task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure Id"
}
},
"required": [
"name",
"description",
"procedure"
],
"title": "cognitive_propose_strategyArguments",
"type": "object"
},
"name": "cognitive.propose_strategy",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_propose_strategyDictOutput",
"type": "object"
}
},
{
"description": "Record an observable event in an ongoing experience episode (§24, §7).\n\n Accepts structured actions, observations, and state changes.\n Never sends raw unredacted private transcripts.\n ",
"inputSchema": {
"properties": {
"event_data": {
"additionalProperties": true,
"title": "Event Data",
"type": "object"
},
"event_type": {
"title": "Event Type",
"type": "string"
},
"experience_id": {
"title": "Experience Id",
"type": "string"
}
},
"required": [
"experience_id",
"event_type",
"event_data"
],
"title": "cognitive_record_experienceArguments",
"type": "object"
},
"name": "cognitive.record_experience",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_record_experienceDictOutput",
"type": "object"
}
},
{
"description": "Autonomously evolve higher-order invariants, tighten bounds, and discover cliques from execution feedback.",
"inputSchema": {
"properties": {
"default_rate": {
"default": 1,
"title": "Default Rate",
"type": "number"
},
"feedback_traces": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Feedback Traces"
},
"lattice_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Data"
},
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
}
},
"title": "cognitive_refine_lattice_from_feedbackArguments",
"type": "object"
},
"name": "cognitive.refine_lattice_from_feedback",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_refine_lattice_from_feedbackDictOutput",
"type": "object"
}
},
{
"description": "Record whether a transferred strategy helped or harmed on a novel task (§24, §19).",
"inputSchema": {
"properties": {
"baseline_performance": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Baseline Performance"
},
"baseline_score": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Baseline Score"
},
"consumer_model_family": {
"default": "",
"title": "Consumer Model Family",
"type": "string"
},
"model_family": {
"default": "",
"title": "Model Family",
"type": "string"
},
"performance_with_strategy": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Performance With Strategy"
},
"source_task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source Task Structure Id"
},
"strategy_id": {
"title": "Strategy Id",
"type": "string"
},
"success": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"title": "Success"
},
"target_task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Task Structure Id"
},
"task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure Id"
},
"transfer_type": {
"default": "same_structure",
"title": "Transfer Type",
"type": "string"
},
"with_strategy_score": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "With Strategy Score"
}
},
"required": [
"strategy_id"
],
"title": "cognitive_report_transferArguments",
"type": "object"
},
"name": "cognitive.report_transfer",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_report_transferDictOutput",
"type": "object"
}
},
{
"description": "Pragmatics: resolve indirect speech acts (e.g. ability questions to directives), anaphoric pronouns, and verify presuppositions.",
"inputSchema": {
"properties": {
"speaker_id": {
"default": "human",
"title": "Speaker Id",
"type": "string"
},
"utterance": {
"title": "Utterance",
"type": "string"
},
"world_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "World State"
}
},
"required": [
"utterance"
],
"title": "cognitive_resolve_intentArguments",
"type": "object"
},
"name": "cognitive.resolve_intent",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_resolve_intentDictOutput",
"type": "object"
}
},
{
"description": "Run the end-to-end cognitive agent closed loop (Perceive -> Model -> Decide -> Act -> Reflect -> Learn).",
"inputSchema": {
"properties": {
"actions": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Actions"
},
"env_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Env Id"
},
"env_type": {
"default": "spatial_commons",
"title": "Env Type",
"type": "string"
},
"max_steps": {
"default": 20,
"title": "Max Steps",
"type": "integer"
}
},
"title": "cognitive_run_closed_loop_agentArguments",
"type": "object"
},
"name": "cognitive.run_closed_loop_agent",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_run_closed_loop_agentDictOutput",
"type": "object"
}
},
{
"description": "Simulate repeated multi-agent interaction with social dilemmas, speech acts, and reputation tracking.",
"inputSchema": {
"properties": {
"agent_actions": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Agent Actions"
},
"game_type": {
"default": "prisoners_dilemma",
"title": "Game Type",
"type": "string"
},
"num_rounds": {
"default": 10,
"title": "Num Rounds",
"type": "integer"
},
"opponent_policy": {
"default": "tit_for_tat",
"title": "Opponent Policy",
"type": "string"
}
},
"title": "cognitive_run_multi_agent_simulationArguments",
"type": "object"
},
"name": "cognitive.run_multi_agent_simulation",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_run_multi_agent_simulationDictOutput",
"type": "object"
}
},
{
"description": "Safe self-improvement: propose modifications guarded by immutable verification oracles and anchor regressions.",
"inputSchema": {
"properties": {
"patch_name": {
"title": "Patch Name",
"type": "string"
},
"proposed_changes": {
"additionalProperties": true,
"title": "Proposed Changes",
"type": "object"
},
"rollback": {
"default": false,
"title": "Rollback",
"type": "boolean"
},
"rollback_snapshot_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rollback Snapshot Id"
},
"simulated_regression_fail": {
"default": false,
"title": "Simulated Regression Fail",
"type": "boolean"
},
"target_component": {
"title": "Target Component",
"type": "string"
}
},
"required": [
"target_component",
"patch_name",
"proposed_changes"
],
"title": "cognitive_safe_self_improveArguments",
"type": "object"
},
"name": "cognitive.safe_self_improve",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_safe_self_improveDictOutput",
"type": "object"
}
},
{
"description": "Simulate and rank candidate actions by predicted feasibility, reward, and constraint safety.",
"inputSchema": {
"properties": {
"candidate_actions": {
"items": {},
"title": "Candidate Actions",
"type": "array"
},
"dt": {
"default": 1,
"title": "Dt",
"type": "number"
},
"state": {
"additionalProperties": true,
"title": "State",
"type": "object"
}
},
"required": [
"state",
"candidate_actions"
],
"title": "cognitive_simulate_actionsArguments",
"type": "object"
},
"name": "cognitive.simulate_actions",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_simulate_actionsDictOutput",
"type": "object"
}
},
{
"description": "End-to-end autonomy: identify → guide → execute → baseline → verify → verdict.\n\n Give raw task data (scheduling: workers/shifts/eligibility/capacity/\n exclusivity; graph: nodes/edges; allocation: consumers/resources/...).\n Returns the guided solution, the unguided baseline, independent\n verification of both (with objective_source + independently_verified),\n and whether the engine improved the result.\n ",
"inputSchema": {
"properties": {
"model_family": {
"default": "generic",
"title": "Model Family",
"type": "string"
},
"task": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task"
}
},
"title": "cognitive_solve_and_compareArguments",
"type": "object"
},
"name": "cognitive.solve_and_compare",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_solve_and_compareDictOutput",
"type": "object"
}
},
{
"description": "Evaluate or simplify mathematical expressions (PEMDAS with power, functions like sqrt, exp, log, sin, cos).",
"inputSchema": {
"properties": {
"expression": {
"title": "Expression",
"type": "string"
},
"simplify": {
"default": false,
"title": "Simplify",
"type": "boolean"
},
"variables": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Variables"
}
},
"required": [
"expression"
],
"title": "cognitive_solve_arithmeticArguments",
"type": "object"
},
"name": "cognitive.solve_arithmetic",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_solve_arithmeticDictOutput",
"type": "object"
}
},
{
"description": "Solve linear equations (ax + b = c), quadratic equations (ax^2 + bx + c = 0), or linear systems (A x = b).",
"inputSchema": {
"properties": {
"equation_type": {
"title": "Equation Type",
"type": "string"
},
"linear_a": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Linear A"
},
"linear_b": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Linear B"
},
"linear_c": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": 0,
"title": "Linear C"
},
"matrix_A": {
"anyOf": [
{
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Matrix A"
},
"quad_a": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Quad A"
},
"quad_b": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Quad B"
},
"quad_c": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Quad C"
},
"vector_b": {
"anyOf": [
{
"items": {
"type": "number"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Vector B"
}
},
"required": [
"equation_type"
],
"title": "cognitive_solve_equation_systemArguments",
"type": "object"
},
"name": "cognitive.solve_equation_system",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_solve_equation_systemDictOutput",
"type": "object"
}
},
{
"description": "Solve math word problems (GSM8K/SVAMP/MATH) via topological constraint propagation.",
"inputSchema": {
"properties": {
"equations": {
"anyOf": [
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Equations"
},
"quantities": {
"anyOf": [
{
"additionalProperties": {
"anyOf": [
{
"type": "number"
},
{
"type": "integer"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Quantities"
},
"question": {
"default": "",
"title": "Question",
"type": "string"
},
"target_variable": {
"default": "target",
"title": "Target Variable",
"type": "string"
}
},
"title": "cognitive_solve_word_problemArguments",
"type": "object"
},
"name": "cognitive.solve_word_problem",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_solve_word_problemDictOutput",
"type": "object"
}
},
{
"description": "Start an experience episode (§24, §10).\n\n Does not store raw prompts or full conversations. For long-horizon work,\n pass parent_experience_id (+ subgoal) to chain episodes with an inherited\n goal stack; unknown parents are rejected, never silently adopted.\n ",
"inputSchema": {
"properties": {
"agent_id": {
"title": "Agent Id",
"type": "string"
},
"environment_id": {
"title": "Environment Id",
"type": "string"
},
"model_family": {
"default": "generic",
"title": "Model Family",
"type": "string"
},
"model_version": {
"default": "1.0",
"title": "Model Version",
"type": "string"
},
"parent_experience_id": {
"default": "",
"title": "Parent Experience Id",
"type": "string"
},
"subgoal": {
"default": "",
"title": "Subgoal",
"type": "string"
},
"task_instance_hash": {
"default": "",
"title": "Task Instance Hash",
"type": "string"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id",
"environment_id",
"agent_id"
],
"title": "cognitive_start_experienceArguments",
"type": "object"
},
"name": "cognitive.start_experience",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_start_experienceDictOutput",
"type": "object"
}
},
{
"description": "Step an active simulated environment with an agent action.",
"inputSchema": {
"properties": {
"action": {
"additionalProperties": true,
"title": "Action",
"type": "object"
},
"env_id": {
"title": "Env Id",
"type": "string"
}
},
"required": [
"env_id",
"action"
],
"title": "cognitive_step_simulated_environmentArguments",
"type": "object"
},
"name": "cognitive.step_simulated_environment",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_step_simulated_environmentDictOutput",
"type": "object"
}
},
{
"description": "Submit the structured outcome of an experience episode (§24, §10).\n\n Triggering this may induce candidate strategies in the engine.\n ",
"inputSchema": {
"properties": {
"experience_id": {
"title": "Experience Id",
"type": "string"
},
"failure_modes": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Failure Modes"
},
"metrics": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Metrics"
},
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
},
"success": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"title": "Success"
},
"verifier_result": {
"title": "Verifier Result",
"type": "string"
}
},
"required": [
"experience_id",
"result",
"verifier_result"
],
"title": "cognitive_submit_outcomeArguments",
"type": "object"
},
"name": "cognitive.submit_outcome",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_submit_outcomeDictOutput",
"type": "object"
}
},
{
"description": "Synthesize new algorithmic Python procedures on the fly with AST sandboxing and verification.",
"inputSchema": {
"properties": {
"parameters": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Parameters"
},
"problem_type": {
"title": "Problem Type",
"type": "string"
},
"test_examples": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Test Examples"
}
},
"required": [
"problem_type"
],
"title": "cognitive_synthesize_programArguments",
"type": "object"
},
"name": "cognitive.synthesize_program",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_synthesize_programDictOutput",
"type": "object"
}
},
{
"description": "Synthesize an optimal, invariant-verified trajectory from initial state to goal through the singular bottleneck.\n \n Eliminates dead-end branching and hallucinated unfeasible solutions.\n ",
"inputSchema": {
"properties": {
"goal_conditions": {
"anyOf": [
{
"additionalProperties": {
"items": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"type": "array"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal Conditions"
},
"initial_state": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Initial State"
},
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
},
"step_budget": {
"default": 5,
"title": "Step Budget",
"type": "integer"
},
"task_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Data"
}
},
"title": "cognitive_synthesize_singular_pathArguments",
"type": "object"
},
"name": "cognitive.synthesize_singular_path",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_synthesize_singular_pathDictOutput",
"type": "object"
}
},
{
"description": "Theory of Mind: model agents' BDI mental states, test false beliefs (Sally-Anne), and infer goals via inverse planning.",
"inputSchema": {
"properties": {
"action_trace": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Action Trace"
},
"agent_id": {
"title": "Agent Id",
"type": "string"
},
"beliefs": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Beliefs"
},
"candidate_goals": {
"anyOf": [
{
"additionalProperties": {
"items": {
"type": "string"
},
"type": "array"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Candidate Goals"
},
"desires": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Desires"
},
"evaluate_false_belief_fact": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Evaluate False Belief Fact"
},
"ground_truth": {
"anyOf": [
{},
{
"type": "null"
}
],
"default": null,
"title": "Ground Truth"
},
"intentions": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Intentions"
},
"witness_event": {
"default": false,
"title": "Witness Event",
"type": "boolean"
}
},
"required": [
"agent_id"
],
"title": "cognitive_theory_of_mindArguments",
"type": "object"
},
"name": "cognitive.theory_of_mind",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_theory_of_mindDictOutput",
"type": "object"
}
},
{
"description": "Perform Monte Carlo Tree Search (UCT) over action sequences to find optimal trajectory.",
"inputSchema": {
"properties": {
"initial_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Initial State"
},
"max_iterations": {
"default": 100,
"title": "Max Iterations",
"type": "integer"
},
"valid_actions": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Valid Actions"
}
},
"title": "cognitive_tree_searchArguments",
"type": "object"
},
"name": "cognitive.tree_search",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_tree_searchDictOutput",
"type": "object"
}
},
{
"description": "Formally verify an arithmetic equality claim, audit numerical stability, condition number, and cancellation risks.",
"inputSchema": {
"properties": {
"audit_stability": {
"default": false,
"title": "Audit Stability",
"type": "boolean"
},
"claim_lhs": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
}
],
"title": "Claim Lhs"
},
"claim_rhs": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
}
],
"title": "Claim Rhs"
},
"matrix": {
"anyOf": [
{
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Matrix"
},
"tolerance": {
"default": 0.000001,
"title": "Tolerance",
"type": "number"
}
},
"required": [
"claim_lhs",
"claim_rhs"
],
"title": "cognitive_verify_arithmetic_claimArguments",
"type": "object"
},
"name": "cognitive.verify_arithmetic_claim",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_verify_arithmetic_claimDictOutput",
"type": "object"
}
},
{
"description": "Normative ethics & fairness: enforce deontological vetos, evaluate Rawlsian vs Utilitarian welfare, and arbitrate moral dilemmas.",
"inputSchema": {
"properties": {
"options": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Options"
},
"proposed_action_or_plan": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Proposed Action Or Plan"
},
"stakeholder_payoffs": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Stakeholder Payoffs"
}
},
"title": "cognitive_verify_ethics_and_normsArguments",
"type": "object"
},
"name": "cognitive.verify_ethics_and_norms",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_verify_ethics_and_normsDictOutput",
"type": "object"
}
},
{
"description": "Verify a candidate state or transition S_t -> S_{t+1} against invariant boundary manifolds.",
"inputSchema": {
"properties": {
"action": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Action"
},
"lattice_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Data"
},
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
},
"next_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Next State"
},
"prev_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Prev State"
}
},
"title": "cognitive_verify_lattice_transitionArguments",
"type": "object"
},
"name": "cognitive.verify_lattice_transition",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_verify_lattice_transitionDictOutput",
"type": "object"
}
},
{
"description": "Run objective deterministic verification on a strategy (§24, §16).\n\n Clients cannot self-promote. Verification is evaluated server-side.\n Pass task_structure_id (from cognitive.identify_task) so constraints are\n independently recomputed from registered descriptors instead of trusting\n trace flags. Objective precedence: explicit caller value → recomputed from\n raw data → registered spec (labeled unknown) → nested trace claims ONLY\n when trust_trace_objective=true → otherwise unknown, never silent 0.0.\n Returns passed/score plus details.objective_source and\n details.independently_verified so callers know what was recomputed\n versus taken on trace claims. Failures are structured, never bare.\n ",
"inputSchema": {
"properties": {
"execution_trace": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Execution Trace"
},
"strategy_id": {
"title": "Strategy Id",
"type": "string"
},
"task_instance": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Instance"
},
"task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure Id"
},
"trust_trace_objective": {
"default": false,
"title": "Trust Trace Objective",
"type": "boolean"
}
},
"required": [
"strategy_id"
],
"title": "cognitive_verify_strategyArguments",
"type": "object"
},
"name": "cognitive.verify_strategy",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_verify_strategyDictOutput",
"type": "object"
}
},
{
"description": "Adaptive compute budgeting: select compute tier (Fast Path to Deep Deliberation) and timeout based on EVC.",
"inputSchema": {
"properties": {
"stakes": {
"default": "normal",
"title": "Stakes",
"type": "string"
},
"task_structure": {
"additionalProperties": true,
"title": "Task Structure",
"type": "object"
}
},
"required": [
"task_structure"
],
"title": "cognitive_allocate_computeArguments",
"type": "object"
},
"name": "cognitive_allocate_compute",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_allocate_computeDictOutput",
"type": "object"
}
},
{
"description": "Transfer structural strategies across disparate domains via Structure-Mapping Engine (SME).",
"inputSchema": {
"properties": {
"source_task_structure_id": {
"title": "Source Task Structure Id",
"type": "string"
},
"strategy_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Strategy Id"
},
"target_task_structure_id": {
"title": "Target Task Structure Id",
"type": "string"
}
},
"required": [
"source_task_structure_id",
"target_task_structure_id"
],
"title": "cognitive_analogical_transferArguments",
"type": "object"
},
"name": "cognitive_analogical_transfer",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_analogical_transferDictOutput",
"type": "object"
}
},
{
"description": "Pragmatic communication: audit speech acts against Gricean maxims (Quality, Quantity, Relation, Manner) and detect deception.",
"inputSchema": {
"properties": {
"act_type": {
"default": "assert",
"title": "Act Type",
"type": "string"
},
"claims": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Claims"
},
"content": {
"title": "Content",
"type": "string"
},
"context_goals": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Context Goals"
},
"recipient_id": {
"default": "all",
"title": "Recipient Id",
"type": "string"
},
"sender_id": {
"default": "agent_1",
"title": "Sender Id",
"type": "string"
},
"speaker_beliefs": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Speaker Beliefs"
}
},
"required": [
"content"
],
"title": "cognitive_analyze_communicationArguments",
"type": "object"
},
"name": "cognitive_analyze_communication",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_analyze_communicationDictOutput",
"type": "object"
}
},
{
"description": "Arbitrate short vs long term payoffs using hyperbolic vs exponential discounting and Ulysses pre-commitment contracts.",
"inputSchema": {
"properties": {
"audit_action_switch": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Audit Action Switch"
},
"gamma_exponential": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Gamma Exponential"
},
"k_hyperbolic": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "K Hyperbolic"
},
"long_term_option": {
"additionalProperties": true,
"title": "Long Term Option",
"type": "object"
},
"register_commitment": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Register Commitment"
},
"short_term_option": {
"additionalProperties": true,
"title": "Short Term Option",
"type": "object"
}
},
"required": [
"short_term_option",
"long_term_option"
],
"title": "cognitive_arbitrate_temporal_objectivesArguments",
"type": "object"
},
"name": "cognitive_arbitrate_temporal_objectives",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_arbitrate_temporal_objectivesDictOutput",
"type": "object"
}
},
{
"description": "Epistemic boundary awareness: classify task into KNOWN, KNOWN_UNKNOWN, or UNKNOWN_UNKNOWN (OOD) and track calibration.",
"inputSchema": {
"properties": {
"actual_outcome": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"title": "Actual Outcome"
},
"task_structure": {
"additionalProperties": true,
"title": "Task Structure",
"type": "object"
}
},
"required": [
"task_structure"
],
"title": "cognitive_assess_competenceArguments",
"type": "object"
},
"name": "cognitive_assess_competence",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_assess_competenceDictOutput",
"type": "object"
}
},
{
"description": "Audit the evidence graph for a task before issuing final answers.\n\n Rejects claims such as 'optimal', 'verified', or 'feasible' when their\n evidence dependencies are incomplete.\n ",
"inputSchema": {
"properties": {
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id"
],
"title": "cognitive_audit_evidence_graphArguments",
"type": "object"
},
"name": "cognitive_audit_evidence_graph",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_audit_evidence_graphDictOutput",
"type": "object"
}
},
{
"description": "Build or update an Evidence-Carrying Cognitive Graph for a task structure and solution trace.",
"inputSchema": {
"properties": {
"claims": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Claims"
},
"solution_trace": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Solution Trace"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id"
],
"title": "cognitive_build_evidence_graphArguments",
"type": "object"
},
"name": "cognitive_build_evidence_graph",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_build_evidence_graphDictOutput",
"type": "object"
}
},
{
"description": "Distinguish causal effects (do-calculus) from spurious correlation via backdoor adjustment.",
"inputSchema": {
"properties": {
"edges": {
"items": {
"items": {
"type": "string"
},
"type": "array"
},
"title": "Edges",
"type": "array"
},
"observations": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Observations",
"type": "array"
},
"outcome": {
"title": "Outcome",
"type": "string"
},
"treatment": {
"title": "Treatment",
"type": "string"
}
},
"required": [
"edges",
"treatment",
"outcome",
"observations"
],
"title": "cognitive_causal_analysisArguments",
"type": "object"
},
"name": "cognitive_causal_analysis",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_causal_analysisDictOutput",
"type": "object"
}
},
{
"description": "Compile a Dynamic Constraint Lattice (DCL) into algebraic boundaries, conservation laws, and reachability cones.",
"inputSchema": {
"properties": {
"goal_conditions": {
"anyOf": [
{
"additionalProperties": {
"items": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"type": "array"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal Conditions"
},
"initial_state": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Initial State"
},
"max_rate_of_change": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Max Rate Of Change"
},
"step_budget": {
"default": 5,
"title": "Step Budget",
"type": "integer"
},
"task_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Data"
},
"task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure Id"
}
},
"title": "cognitive_compile_invariant_latticeArguments",
"type": "object"
},
"name": "cognitive_compile_invariant_lattice",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_compile_invariant_latticeDictOutput",
"type": "object"
}
},
{
"description": "Skill Composition: synthesize a composite multi-stage StrategyIR from primitive strategies.\n\n Chains multiple specialized skills (e.g. Graph Coloring + Topological Sort + Allocation)\n into a compound pipeline with explicit stage transitions and end-to-end verification.\n ",
"inputSchema": {
"properties": {
"composite_name": {
"title": "Composite Name",
"type": "string"
},
"description": {
"default": "",
"title": "Description",
"type": "string"
},
"strategy_ids": {
"items": {
"type": "string"
},
"title": "Strategy Ids",
"type": "array"
}
},
"required": [
"strategy_ids",
"composite_name"
],
"title": "cognitive_compose_strategiesArguments",
"type": "object"
},
"name": "cognitive_compose_strategies",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_compose_strategiesDictOutput",
"type": "object"
}
},
{
"description": "Compute intrinsic drives: novelty & prediction surprise curiosity, empowerment (channel capacity), and learning progress.",
"inputSchema": {
"properties": {
"actual_state": {
"additionalProperties": true,
"title": "Actual State",
"type": "object"
},
"extrinsic_reward": {
"default": 0,
"title": "Extrinsic Reward",
"type": "number"
},
"predicted_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Predicted State"
},
"reachable_states": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Reachable States"
},
"skill_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Skill Name"
},
"skill_success": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"title": "Skill Success"
}
},
"required": [
"actual_state"
],
"title": "cognitive_compute_intrinsic_rewardsArguments",
"type": "object"
},
"name": "cognitive_compute_intrinsic_rewards",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_compute_intrinsic_rewardsDictOutput",
"type": "object"
}
},
{
"description": "Compute coordinate-free topological invariant signature of a lattice or task.",
"inputSchema": {
"properties": {
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
},
"task_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Data"
}
},
"title": "cognitive_compute_lattice_signatureArguments",
"type": "object"
},
"name": "cognitive_compute_lattice_signature",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_compute_lattice_signatureDictOutput",
"type": "object"
}
},
{
"description": "Number theory: primality, factoring, extended GCD, Diophantine, modular inverse, CRT, combinatorics, Fibonacci.",
"inputSchema": {
"properties": {
"a": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "A"
},
"b": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "B"
},
"c": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "C"
},
"k": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "K"
},
"m": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "M"
},
"moduli": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Moduli"
},
"n": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "N"
},
"operation": {
"title": "Operation",
"type": "string"
},
"remainders": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Remainders"
}
},
"required": [
"operation"
],
"title": "cognitive_compute_number_theoryArguments",
"type": "object"
},
"name": "cognitive_compute_number_theory",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_compute_number_theoryDictOutput",
"type": "object"
}
},
{
"description": "Counterfactual engine: evaluate 'What if I had done X instead of Y at step t?' using Pearl's abduction-intervention-prediction.",
"inputSchema": {
"properties": {
"counterfactual_action": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "string"
}
],
"title": "Counterfactual Action"
},
"dt": {
"default": 1,
"title": "Dt",
"type": "number"
},
"factual_trace": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Factual Trace",
"type": "array"
},
"intervention_step": {
"title": "Intervention Step",
"type": "integer"
}
},
"required": [
"factual_trace",
"intervention_step",
"counterfactual_action"
],
"title": "cognitive_counterfactual_what_ifArguments",
"type": "object"
},
"name": "cognitive_counterfactual_what_if",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_counterfactual_what_ifDictOutput",
"type": "object"
}
},
{
"description": "Instantiate and initialize a simulated cognitive environment (spatial_commons, multi_agent_arena, sequential_puzzle).",
"inputSchema": {
"properties": {
"env_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Env Id"
},
"env_type": {
"default": "spatial_commons",
"title": "Env Type",
"type": "string"
},
"parameters": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Parameters"
}
},
"title": "cognitive_create_simulated_environmentArguments",
"type": "object"
},
"name": "cognitive_create_simulated_environment",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_create_simulated_environmentDictOutput",
"type": "object"
}
},
{
"description": "Subject candidate trajectories to adversarial algebraic perturbations to calculate Robustness Index (R) and project hardened paths.",
"inputSchema": {
"properties": {
"lattice_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Data"
},
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
},
"max_perturbations": {
"default": 24,
"title": "Max Perturbations",
"type": "integer"
},
"step_budget": {
"default": 5,
"title": "Step Budget",
"type": "integer"
},
"stress_amplitude": {
"default": 0.15,
"title": "Stress Amplitude",
"type": "number"
},
"trajectory": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Trajectory"
}
},
"title": "cognitive_crucible_stress_testArguments",
"type": "object"
},
"name": "cognitive_crucible_stress_test",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_crucible_stress_testDictOutput",
"type": "object"
}
},
{
"description": "Evaluate support status and confidence for an individual claim with evidence.",
"inputSchema": {
"properties": {
"assumptions": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Assumptions"
},
"claim": {
"title": "Claim",
"type": "string"
},
"dependencies": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Dependencies"
},
"evidence": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Evidence"
},
"invalidation_conditions": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Invalidation Conditions"
},
"object": {
"default": "",
"title": "Object",
"type": "string"
},
"relation": {
"default": "states",
"title": "Relation",
"type": "string"
},
"subject": {
"default": "",
"title": "Subject",
"type": "string"
},
"task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure Id"
}
},
"required": [
"claim"
],
"title": "cognitive_evaluate_claim_evidenceArguments",
"type": "object"
},
"name": "cognitive_evaluate_claim_evidence",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_evaluate_claim_evidenceDictOutput",
"type": "object"
}
},
{
"description": "Multi-agent cooperation: analyze game payoff matrices, compute Nash/Pareto equilibria, and execute reciprocity policies.",
"inputSchema": {
"properties": {
"contributions": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Contributions"
},
"endowments": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Endowments"
},
"game_type": {
"title": "Game Type",
"type": "string"
},
"multiplier": {
"default": 1.6,
"title": "Multiplier",
"type": "number"
},
"my_history": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "My History"
},
"partner_history": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Partner History"
},
"strategy": {
"default": "tit_for_tat",
"title": "Strategy",
"type": "string"
}
},
"required": [
"game_type"
],
"title": "cognitive_evaluate_cooperationArguments",
"type": "object"
},
"name": "cognitive_evaluate_cooperation",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_evaluate_cooperationDictOutput",
"type": "object"
}
},
{
"description": "Evaluate a counterfactual query on a plan ('What if capacity drops?', 'What if a route fails?', etc.).",
"inputSchema": {
"properties": {
"parameters": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Parameters"
},
"plan_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Plan Id"
},
"query_type": {
"title": "Query Type",
"type": "string"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id",
"query_type"
],
"title": "cognitive_evaluate_counterfactual_queryArguments",
"type": "object"
},
"name": "cognitive_evaluate_counterfactual_query",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_evaluate_counterfactual_queryDictOutput",
"type": "object"
}
},
{
"description": "Evaluate broad generalization across spatial commons, multi-agent arenas, and sequential causal puzzles.",
"inputSchema": {
"properties": {
"benchmark_filter": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Benchmark Filter"
}
},
"title": "cognitive_evaluate_generalization_benchmarksArguments",
"type": "object"
},
"name": "cognitive_evaluate_generalization_benchmarks",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_evaluate_generalization_benchmarksDictOutput",
"type": "object"
}
},
{
"description": "One-call orchestration: identify → gate → guide → solve → verify → report.\n\n Parameters:\n - task: Dict containing:\n - task_structure (or loose definition: name, entities, constraints, etc.)\n - raw (optional): Domain-specific execution payload. If omitted, returns\n status='guidance_only' with 'recommended_action'='supply_raw' and\n an 'expected_raw_formats' object detailing valid schemas.\n Supported problem types for task.raw:\n * scheduling: {\"workers\": [{\"id\": \"w1\", \"eligible_shifts\": [\"s1\"], \"max_shifts\": 1}],\n \"shifts\": [{\"id\": \"s1\", \"required_workers\": 1}]}\n * allocation: {\"consumers\": [{\"id\": \"c1\", \"demands\": {\"r1\": 1}}],\n \"resources\": [{\"id\": \"r1\", \"capacity\": 2}]}\n * graph: {\"nodes\": [\"A\", \"B\"], \"edges\": [[\"A\", \"B\"]]}\n * graph_coloring: {\"nodes\": [\"A\", \"B\"], \"edges\": [[\"A\", \"B\"]], \"colors\": [\"red\", \"blue\"]}\n * shortest_path: {\"nodes\": [\"A\", \"B\"], \"edges\": [[\"A\", \"B\"]], \"weights\": {\"A->B\": 1.0}, \"start\": \"A\", \"target\": \"B\"}\n * math: {\"math\": {\"question\": \"...\", \"quantities\": {...}, \"equations\": [...], \"target_variable\": \"x\", \"ground_truth\": 42.0}}\n * code: {\"code\": {\"code\": \"def solution()...\", \"tests\": [\"assert ...\"]}}\n * pddl: {\"pddl\": {\"plan\": [...], \"init\": {...}, \"goal\": {...}}}\n\n Returns a single envelope with status (completed / guidance_only /\n blocked_until_clarified / no_applicable_guidance / refused_infeasible /\n failed), solution, score, assumptions, failure reasons, and expected_raw_formats.\n ",
"inputSchema": {
"properties": {
"environment": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Environment"
},
"goal": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal"
},
"model_family": {
"default": "generic",
"title": "Model Family",
"type": "string"
},
"task": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task"
}
},
"title": "cognitive_execute_taskArguments",
"type": "object"
},
"name": "cognitive_execute_task",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_execute_taskDictOutput",
"type": "object"
}
},
{
"description": "Few-shot learning: induce a generalized procedural StrategyIR from 1-3 problem traces.\n\n Extracts structural invariants (decision ordering, invariant contracts, verification rules)\n and registers an initial candidate strategy immediately without requiring large training sets.\n ",
"inputSchema": {
"properties": {
"solution_trace": {
"additionalProperties": true,
"title": "Solution Trace",
"type": "object"
},
"source_model": {
"default": "few_shot_learner",
"title": "Source Model",
"type": "string"
},
"strategy_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Strategy Name"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id",
"solution_trace"
],
"title": "cognitive_few_shot_induceArguments",
"type": "object"
},
"name": "cognitive_few_shot_induce",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_few_shot_induceDictOutput",
"type": "object"
}
},
{
"description": "Autonomous goal synthesis from world deficits, depleted reserves, and exploration frontiers with multi-criteria prioritization.",
"inputSchema": {
"properties": {
"depleted_reserves": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Depleted Reserves"
},
"goal_status_update": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal Status Update"
},
"max_active": {
"default": 3,
"title": "Max Active",
"type": "integer"
},
"unexplored_frontiers": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Unexplored Frontiers"
},
"world_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "World State"
}
},
"title": "cognitive_generate_and_prioritize_goalsArguments",
"type": "object"
},
"name": "cognitive_generate_and_prioritize_goals",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_generate_and_prioritize_goalsDictOutput",
"type": "object"
}
},
{
"description": "Retrieve details and benchmark results of an experiment (§24, §69).",
"inputSchema": {
"properties": {
"experiment_id": {
"title": "Experiment Id",
"type": "string"
}
},
"required": [
"experiment_id"
],
"title": "cognitive_get_experimentArguments",
"type": "object"
},
"name": "cognitive_get_experiment",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_get_experimentDictOutput",
"type": "object"
}
},
{
"description": "Compile a final evidence result listing supporting evidence, assumptions, missing evidence,\n contradictions, unchecked dependencies, confidence, and invalidation conditions.",
"inputSchema": {
"properties": {
"target_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Id"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id"
],
"title": "cognitive_get_final_evidence_resultArguments",
"type": "object"
},
"name": "cognitive_get_final_evidence_result",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_get_final_evidence_resultDictOutput",
"type": "object"
}
},
{
"description": "Retrieve applicable validated strategies for a task (§24, §18).\n\n Does NOT return unverified or suspended strategies as trusted guidance.\n Provides calibrated uncertainty, applicability conditions, and negative transfer warnings.\n\n Args:\n task_structure_id: UUID of the abstract task structure.\n environment: Environment characteristics.\n goal: Goal description and metric targets.\n available_capabilities: Capabilities supported by the caller.\n model_family: Model family of the consumer agent (e.g. 'claude', 'gpt', 'local').\n\n Returns:\n Ranked list of applicable strategies with procedures, conditions, and evidence.\n Failures return {\"error\", \"detail\", \"hint\"} — never a bare exception.\n ",
"inputSchema": {
"properties": {
"available_capabilities": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Available Capabilities"
},
"environment": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Environment"
},
"goal": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal"
},
"model_family": {
"default": "generic",
"title": "Model Family",
"type": "string"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id"
],
"title": "cognitive_get_guidanceArguments",
"type": "object"
},
"name": "cognitive_get_guidance",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_get_guidanceDictOutput",
"type": "object"
}
},
{
"description": "Retrieve a usable strategy: steps, when to use, when not, evidence summary.\n\n Disclosure: you learn WHAT to execute, never HOW the engine induces,\n verifies, or ranks knowledge (no trust signals, audit, tenants, traces).\n ",
"inputSchema": {
"properties": {
"strategy_id": {
"title": "Strategy Id",
"type": "string"
}
},
"required": [
"strategy_id"
],
"title": "cognitive_get_strategyArguments",
"type": "object"
},
"name": "cognitive_get_strategy",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_get_strategyDictOutput",
"type": "object"
}
},
{
"description": "Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval.",
"inputSchema": {
"properties": {
"strategy_id": {
"title": "Strategy Id",
"type": "string"
}
},
"required": [
"strategy_id"
],
"title": "cognitive_get_strategy_reportArguments",
"type": "object"
},
"name": "cognitive_get_strategy_report",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_get_strategy_reportDictOutput",
"type": "object"
}
},
{
"description": "Non-LLM compositional semantics: parse utterance into semantic predicates and evaluate directly against WorldState.",
"inputSchema": {
"properties": {
"utterance": {
"title": "Utterance",
"type": "string"
},
"world_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "World State"
}
},
"required": [
"utterance"
],
"title": "cognitive_ground_languageArguments",
"type": "object"
},
"name": "cognitive_ground_language",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_ground_languageDictOutput",
"type": "object"
}
},
{
"description": "Decompose high-level goals into milestone subgoals using Hierarchical Task Network (HTN) planning.",
"inputSchema": {
"properties": {
"compound_tasks": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Compound Tasks"
},
"goal_tasks": {
"items": {
"type": "string"
},
"title": "Goal Tasks",
"type": "array"
},
"initial_state": {
"additionalProperties": true,
"title": "Initial State",
"type": "object"
},
"primitive_operators": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Primitive Operators"
}
},
"required": [
"goal_tasks",
"initial_state"
],
"title": "cognitive_hierarchical_planArguments",
"type": "object"
},
"name": "cognitive_hierarchical_plan",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_hierarchical_planDictOutput",
"type": "object"
}
},
{
"description": "Create or resolve an abstract task structure without storing raw private content (§24).\n\n Args:\n task_structure: Structural representation (entities, constraints, variables, etc.).\n environment: Environmental context and characteristics.\n goal: Objective and optimization goals.\n\n Returns:\n task_structure_id, structural_features, and matching existing structures.\n On invalid input returns {\"error\", \"detail\", \"hint\"} instead of raising,\n so the MCP client sees the cause instead of a generic execution error.\n ",
"inputSchema": {
"properties": {
"environment": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Environment"
},
"goal": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal"
},
"task_structure": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure"
}
},
"title": "cognitive_identify_taskArguments",
"type": "object"
},
"name": "cognitive_identify_task",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_identify_taskDictOutput",
"type": "object"
}
},
{
"description": "Discover topological homomorphism between source experience and target problem, transducing solution paths.",
"inputSchema": {
"properties": {
"source_lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source Lattice Id"
},
"step_budget": {
"default": 5,
"title": "Step Budget",
"type": "integer"
},
"target_lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Lattice Id"
},
"target_task_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Task Data"
}
},
"title": "cognitive_induce_morphic_transferArguments",
"type": "object"
},
"name": "cognitive_induce_morphic_transfer",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_induce_morphic_transferDictOutput",
"type": "object"
}
},
{
"description": "Perform logical deduction (Horn clauses) or exact probabilistic Bayesian network inference.",
"inputSchema": {
"properties": {
"evidence": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Evidence"
},
"facts": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Facts"
},
"nodes": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Nodes"
},
"probabilistic": {
"default": false,
"title": "Probabilistic",
"type": "boolean"
},
"query": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Query"
},
"query_var": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Query Var"
},
"rules": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Rules"
}
},
"title": "cognitive_inferArguments",
"type": "object"
},
"name": "cognitive_infer",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_inferDictOutput",
"type": "object"
}
},
{
"description": "Infer human values via Bradley-Terry IRL, detect Goodhart's law / specification gaming, and assess CIRL deference.",
"inputSchema": {
"properties": {
"action_evaluated": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Action Evaluated"
},
"action_irreversible": {
"default": false,
"title": "Action Irreversible",
"type": "boolean"
},
"action_stakes": {
"default": "normal",
"title": "Action Stakes",
"type": "string"
},
"baseline_metrics": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Baseline Metrics"
},
"comparisons": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Comparisons"
},
"detect_gaming": {
"default": false,
"title": "Detect Gaming",
"type": "boolean"
},
"projected_metrics": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Projected Metrics"
},
"proxy_metric": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Proxy Metric"
}
},
"title": "cognitive_infer_human_valuesArguments",
"type": "object"
},
"name": "cognitive_infer_human_values",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_infer_human_valuesDictOutput",
"type": "object"
}
},
{
"description": "Inspect grounded lexicon acquired via situated interaction (learned vocabulary, concept bindings, confidence).",
"inputSchema": {
"properties": {},
"title": "cognitive_inspect_lexiconArguments",
"type": "object"
},
"name": "cognitive_inspect_lexicon",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_inspect_lexiconDictOutput",
"type": "object"
}
},
{
"description": "Engine self-model introspection: inspect capabilities, domain competence, active subsystems, and safety status.",
"inputSchema": {
"properties": {},
"title": "cognitive_inspect_self_modelArguments",
"type": "object"
},
"name": "cognitive_inspect_self_model",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_inspect_self_modelDictOutput",
"type": "object"
}
},
{
"description": "Online Real-Time Error Reflection & Strategy Patching.\n\n When an execution fails, analyzes root-cause constraint violations, synthesizes\n new exception cases and repair procedures, verifies update against anchor regression,\n and publishes the patched strategy version in real time.\n ",
"inputSchema": {
"properties": {
"execution_trace": {
"additionalProperties": true,
"title": "Execution Trace",
"type": "object"
},
"strategy_id": {
"title": "Strategy Id",
"type": "string"
},
"task_instance": {
"additionalProperties": true,
"title": "Task Instance",
"type": "object"
},
"violations": {
"items": {
"type": "string"
},
"title": "Violations",
"type": "array"
}
},
"required": [
"strategy_id",
"task_instance",
"execution_trace",
"violations"
],
"title": "cognitive_learn_from_mistakeArguments",
"type": "object"
},
"name": "cognitive_learn_from_mistake",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_learn_from_mistakeDictOutput",
"type": "object"
}
},
{
"description": "Interactive language acquisition: learn word-concept bindings through cross-situational observation, games, and feedback.",
"inputSchema": {
"properties": {
"candidate_objects": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Candidate Objects"
},
"feedback_correct": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Feedback Correct"
},
"feedback_incorrect": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Feedback Incorrect"
},
"interaction_type": {
"title": "Interaction Type",
"type": "string"
},
"referent_features": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Referent Features"
},
"target_object_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Object Id"
},
"utterance": {
"title": "Utterance",
"type": "string"
}
},
"required": [
"interaction_type",
"utterance"
],
"title": "cognitive_learn_language_interactionArguments",
"type": "object"
},
"name": "cognitive_learn_language_interaction",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_learn_language_interactionDictOutput",
"type": "object"
}
},
{
"description": "Online world model learning: update state transition priors from empirical execution traces.",
"inputSchema": {
"properties": {
"transitions": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Transitions",
"type": "array"
}
},
"required": [
"transitions"
],
"title": "cognitive_learn_world_modelArguments",
"type": "object"
},
"name": "cognitive_learn_world_model",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_learn_world_modelDictOutput",
"type": "object"
}
},
{
"description": "Discovery: list recorded benchmark experiment IDs for cognitive.get_experiment.",
"inputSchema": {
"properties": {},
"title": "cognitive_list_experimentsArguments",
"type": "object"
},
"name": "cognitive_list_experiments",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_list_experimentsDictOutput",
"type": "object"
}
},
{
"description": "Exact rational matrix & vector algebra: multiply, determinant, inverse, transpose, trace, eigenvalues, dot/cross.",
"inputSchema": {
"properties": {
"matrix_A": {
"anyOf": [
{
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Matrix A"
},
"matrix_B": {
"anyOf": [
{
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Matrix B"
},
"operation": {
"title": "Operation",
"type": "string"
},
"vector_u": {
"anyOf": [
{
"items": {
"type": "number"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Vector U"
},
"vector_v": {
"anyOf": [
{
"items": {
"type": "number"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Vector V"
}
},
"required": [
"operation"
],
"title": "cognitive_matrix_algebraArguments",
"type": "object"
},
"name": "cognitive_matrix_algebra",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_matrix_algebraDictOutput",
"type": "object"
}
},
{
"description": "Introspective reasoning critic: inspect trace in-flight to catch cycles, invariant drift, vacuous output, and stalling.",
"inputSchema": {
"properties": {
"current_step": {
"additionalProperties": true,
"title": "Current Step",
"type": "object"
},
"invariants": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Invariants"
},
"trace_history": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Trace History",
"type": "array"
}
},
"required": [
"trace_history",
"current_step"
],
"title": "cognitive_monitor_reasoningArguments",
"type": "object"
},
"name": "cognitive_monitor_reasoning",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_monitor_reasoningDictOutput",
"type": "object"
}
},
{
"description": "Convert natural-language task text into CIR and task_structure dict.\n\n Every natural-language input is normalized into CIR before reasoning.\n Returns both the normalized CIR and a human-readable explanation.\n ",
"inputSchema": {
"properties": {
"description": {
"default": "",
"title": "Description",
"type": "string"
},
"prompt": {
"default": "",
"title": "Prompt",
"type": "string"
},
"task_text": {
"default": "",
"title": "Task Text",
"type": "string"
},
"text": {
"default": "",
"title": "Text",
"type": "string"
}
},
"title": "cognitive_parse_taskArguments",
"type": "object"
},
"name": "cognitive_parse_task",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_parse_taskDictOutput",
"type": "object"
}
},
{
"description": "Synthesize the best verified plan across candidate rollouts, uncertainty tracking, and constraint pruning.",
"inputSchema": {
"properties": {
"current_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Current State"
},
"goal": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal"
},
"horizon": {
"default": 5,
"title": "Horizon",
"type": "integer"
},
"method": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Method"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id"
],
"title": "cognitive_plan_with_counterfactualsArguments",
"type": "object"
},
"name": "cognitive_plan_with_counterfactuals",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_plan_with_counterfactualsDictOutput",
"type": "object"
}
},
{
"description": "Forward world model: predict future state trajectories and uncertainty bounds under actions.",
"inputSchema": {
"properties": {
"actions": {
"items": {},
"title": "Actions",
"type": "array"
},
"dt": {
"default": 1,
"title": "Dt",
"type": "number"
},
"state": {
"additionalProperties": true,
"title": "State",
"type": "object"
},
"timescale": {
"default": "micro",
"title": "Timescale",
"type": "string"
}
},
"required": [
"state",
"actions"
],
"title": "cognitive_predict_world_stateArguments",
"type": "object"
},
"name": "cognitive_predict_world_state",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_predict_world_stateDictOutput",
"type": "object"
}
},
{
"description": "Project a candidate state or plan step onto the Singular Transition Manifold M = F(S0) ∩ B(Goal).\n \n Returns the corrected state, corrective delta vector Delta S = S* - S, and boundary distance margins.\n ",
"inputSchema": {
"properties": {
"lattice_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Data"
},
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
},
"state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "State"
}
},
"title": "cognitive_project_to_manifoldArguments",
"type": "object"
},
"name": "cognitive_project_to_manifold",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_project_to_manifoldDictOutput",
"type": "object"
}
},
{
"description": "Propose a candidate strategy from problem-solving experience (§24, §2).\n\n IMPORTANT: This NEVER makes the strategy TRUSTED.\n The strategy enters CANDIDATE state and requires objective verification.\n ",
"inputSchema": {
"properties": {
"applicability": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Applicability"
},
"description": {
"title": "Description",
"type": "string"
},
"exceptions": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Exceptions"
},
"experience_ids": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Experience Ids"
},
"name": {
"title": "Name",
"type": "string"
},
"preconditions": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Preconditions"
},
"procedure": {
"items": {
"type": "string"
},
"title": "Procedure",
"type": "array"
},
"source_model": {
"default": "external_model",
"title": "Source Model",
"type": "string"
},
"task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure Id"
}
},
"required": [
"name",
"description",
"procedure"
],
"title": "cognitive_propose_strategyArguments",
"type": "object"
},
"name": "cognitive_propose_strategy",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_propose_strategyDictOutput",
"type": "object"
}
},
{
"description": "Record an observable event in an ongoing experience episode (§24, §7).\n\n Accepts structured actions, observations, and state changes.\n Never sends raw unredacted private transcripts.\n ",
"inputSchema": {
"properties": {
"event_data": {
"additionalProperties": true,
"title": "Event Data",
"type": "object"
},
"event_type": {
"title": "Event Type",
"type": "string"
},
"experience_id": {
"title": "Experience Id",
"type": "string"
}
},
"required": [
"experience_id",
"event_type",
"event_data"
],
"title": "cognitive_record_experienceArguments",
"type": "object"
},
"name": "cognitive_record_experience",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_record_experienceDictOutput",
"type": "object"
}
},
{
"description": "Autonomously evolve higher-order invariants, tighten bounds, and discover cliques from execution feedback.",
"inputSchema": {
"properties": {
"default_rate": {
"default": 1,
"title": "Default Rate",
"type": "number"
},
"feedback_traces": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Feedback Traces"
},
"lattice_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Data"
},
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
}
},
"title": "cognitive_refine_lattice_from_feedbackArguments",
"type": "object"
},
"name": "cognitive_refine_lattice_from_feedback",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_refine_lattice_from_feedbackDictOutput",
"type": "object"
}
},
{
"description": "Record whether a transferred strategy helped or harmed on a novel task (§24, §19).",
"inputSchema": {
"properties": {
"baseline_performance": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Baseline Performance"
},
"baseline_score": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Baseline Score"
},
"consumer_model_family": {
"default": "",
"title": "Consumer Model Family",
"type": "string"
},
"model_family": {
"default": "",
"title": "Model Family",
"type": "string"
},
"performance_with_strategy": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Performance With Strategy"
},
"source_task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source Task Structure Id"
},
"strategy_id": {
"title": "Strategy Id",
"type": "string"
},
"success": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"title": "Success"
},
"target_task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Task Structure Id"
},
"task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure Id"
},
"transfer_type": {
"default": "same_structure",
"title": "Transfer Type",
"type": "string"
},
"with_strategy_score": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "With Strategy Score"
}
},
"required": [
"strategy_id"
],
"title": "cognitive_report_transferArguments",
"type": "object"
},
"name": "cognitive_report_transfer",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_report_transferDictOutput",
"type": "object"
}
},
{
"description": "Pragmatics: resolve indirect speech acts (e.g. ability questions to directives), anaphoric pronouns, and verify presuppositions.",
"inputSchema": {
"properties": {
"speaker_id": {
"default": "human",
"title": "Speaker Id",
"type": "string"
},
"utterance": {
"title": "Utterance",
"type": "string"
},
"world_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "World State"
}
},
"required": [
"utterance"
],
"title": "cognitive_resolve_intentArguments",
"type": "object"
},
"name": "cognitive_resolve_intent",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_resolve_intentDictOutput",
"type": "object"
}
},
{
"description": "Run the end-to-end cognitive agent closed loop (Perceive -> Model -> Decide -> Act -> Reflect -> Learn).",
"inputSchema": {
"properties": {
"actions": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Actions"
},
"env_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Env Id"
},
"env_type": {
"default": "spatial_commons",
"title": "Env Type",
"type": "string"
},
"max_steps": {
"default": 20,
"title": "Max Steps",
"type": "integer"
}
},
"title": "cognitive_run_closed_loop_agentArguments",
"type": "object"
},
"name": "cognitive_run_closed_loop_agent",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_run_closed_loop_agentDictOutput",
"type": "object"
}
},
{
"description": "Simulate repeated multi-agent interaction with social dilemmas, speech acts, and reputation tracking.",
"inputSchema": {
"properties": {
"agent_actions": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Agent Actions"
},
"game_type": {
"default": "prisoners_dilemma",
"title": "Game Type",
"type": "string"
},
"num_rounds": {
"default": 10,
"title": "Num Rounds",
"type": "integer"
},
"opponent_policy": {
"default": "tit_for_tat",
"title": "Opponent Policy",
"type": "string"
}
},
"title": "cognitive_run_multi_agent_simulationArguments",
"type": "object"
},
"name": "cognitive_run_multi_agent_simulation",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_run_multi_agent_simulationDictOutput",
"type": "object"
}
},
{
"description": "Safe self-improvement: propose modifications guarded by immutable verification oracles and anchor regressions.",
"inputSchema": {
"properties": {
"patch_name": {
"title": "Patch Name",
"type": "string"
},
"proposed_changes": {
"additionalProperties": true,
"title": "Proposed Changes",
"type": "object"
},
"rollback": {
"default": false,
"title": "Rollback",
"type": "boolean"
},
"rollback_snapshot_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rollback Snapshot Id"
},
"simulated_regression_fail": {
"default": false,
"title": "Simulated Regression Fail",
"type": "boolean"
},
"target_component": {
"title": "Target Component",
"type": "string"
}
},
"required": [
"target_component",
"patch_name",
"proposed_changes"
],
"title": "cognitive_safe_self_improveArguments",
"type": "object"
},
"name": "cognitive_safe_self_improve",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_safe_self_improveDictOutput",
"type": "object"
}
},
{
"description": "Simulate and rank candidate actions by predicted feasibility, reward, and constraint safety.",
"inputSchema": {
"properties": {
"candidate_actions": {
"items": {},
"title": "Candidate Actions",
"type": "array"
},
"dt": {
"default": 1,
"title": "Dt",
"type": "number"
},
"state": {
"additionalProperties": true,
"title": "State",
"type": "object"
}
},
"required": [
"state",
"candidate_actions"
],
"title": "cognitive_simulate_actionsArguments",
"type": "object"
},
"name": "cognitive_simulate_actions",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_simulate_actionsDictOutput",
"type": "object"
}
},
{
"description": "End-to-end autonomy: identify → guide → execute → baseline → verify → verdict.\n\n Give raw task data (scheduling: workers/shifts/eligibility/capacity/\n exclusivity; graph: nodes/edges; allocation: consumers/resources/...).\n Returns the guided solution, the unguided baseline, independent\n verification of both (with objective_source + independently_verified),\n and whether the engine improved the result.\n ",
"inputSchema": {
"properties": {
"model_family": {
"default": "generic",
"title": "Model Family",
"type": "string"
},
"task": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task"
}
},
"title": "cognitive_solve_and_compareArguments",
"type": "object"
},
"name": "cognitive_solve_and_compare",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_solve_and_compareDictOutput",
"type": "object"
}
},
{
"description": "Evaluate or simplify mathematical expressions (PEMDAS with power, functions like sqrt, exp, log, sin, cos).",
"inputSchema": {
"properties": {
"expression": {
"title": "Expression",
"type": "string"
},
"simplify": {
"default": false,
"title": "Simplify",
"type": "boolean"
},
"variables": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Variables"
}
},
"required": [
"expression"
],
"title": "cognitive_solve_arithmeticArguments",
"type": "object"
},
"name": "cognitive_solve_arithmetic",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_solve_arithmeticDictOutput",
"type": "object"
}
},
{
"description": "Solve linear equations (ax + b = c), quadratic equations (ax^2 + bx + c = 0), or linear systems (A x = b).",
"inputSchema": {
"properties": {
"equation_type": {
"title": "Equation Type",
"type": "string"
},
"linear_a": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Linear A"
},
"linear_b": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Linear B"
},
"linear_c": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": 0,
"title": "Linear C"
},
"matrix_A": {
"anyOf": [
{
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Matrix A"
},
"quad_a": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Quad A"
},
"quad_b": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Quad B"
},
"quad_c": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Quad C"
},
"vector_b": {
"anyOf": [
{
"items": {
"type": "number"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Vector B"
}
},
"required": [
"equation_type"
],
"title": "cognitive_solve_equation_systemArguments",
"type": "object"
},
"name": "cognitive_solve_equation_system",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_solve_equation_systemDictOutput",
"type": "object"
}
},
{
"description": "Solve math word problems (GSM8K/SVAMP/MATH) via topological constraint propagation.",
"inputSchema": {
"properties": {
"equations": {
"anyOf": [
{
"items": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Equations"
},
"quantities": {
"anyOf": [
{
"additionalProperties": {
"anyOf": [
{
"type": "number"
},
{
"type": "integer"
}
]
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Quantities"
},
"question": {
"default": "",
"title": "Question",
"type": "string"
},
"target_variable": {
"default": "target",
"title": "Target Variable",
"type": "string"
}
},
"title": "cognitive_solve_word_problemArguments",
"type": "object"
},
"name": "cognitive_solve_word_problem",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_solve_word_problemDictOutput",
"type": "object"
}
},
{
"description": "Start an experience episode (§24, §10).\n\n Does not store raw prompts or full conversations. For long-horizon work,\n pass parent_experience_id (+ subgoal) to chain episodes with an inherited\n goal stack; unknown parents are rejected, never silently adopted.\n ",
"inputSchema": {
"properties": {
"agent_id": {
"title": "Agent Id",
"type": "string"
},
"environment_id": {
"title": "Environment Id",
"type": "string"
},
"model_family": {
"default": "generic",
"title": "Model Family",
"type": "string"
},
"model_version": {
"default": "1.0",
"title": "Model Version",
"type": "string"
},
"parent_experience_id": {
"default": "",
"title": "Parent Experience Id",
"type": "string"
},
"subgoal": {
"default": "",
"title": "Subgoal",
"type": "string"
},
"task_instance_hash": {
"default": "",
"title": "Task Instance Hash",
"type": "string"
},
"task_structure_id": {
"title": "Task Structure Id",
"type": "string"
}
},
"required": [
"task_structure_id",
"environment_id",
"agent_id"
],
"title": "cognitive_start_experienceArguments",
"type": "object"
},
"name": "cognitive_start_experience",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_start_experienceDictOutput",
"type": "object"
}
},
{
"description": "Step an active simulated environment with an agent action.",
"inputSchema": {
"properties": {
"action": {
"additionalProperties": true,
"title": "Action",
"type": "object"
},
"env_id": {
"title": "Env Id",
"type": "string"
}
},
"required": [
"env_id",
"action"
],
"title": "cognitive_step_simulated_environmentArguments",
"type": "object"
},
"name": "cognitive_step_simulated_environment",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_step_simulated_environmentDictOutput",
"type": "object"
}
},
{
"description": "Submit the structured outcome of an experience episode (§24, §10).\n\n Triggering this may induce candidate strategies in the engine.\n ",
"inputSchema": {
"properties": {
"experience_id": {
"title": "Experience Id",
"type": "string"
},
"failure_modes": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Failure Modes"
},
"metrics": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Metrics"
},
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
},
"success": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"title": "Success"
},
"verifier_result": {
"title": "Verifier Result",
"type": "string"
}
},
"required": [
"experience_id",
"result",
"verifier_result"
],
"title": "cognitive_submit_outcomeArguments",
"type": "object"
},
"name": "cognitive_submit_outcome",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_submit_outcomeDictOutput",
"type": "object"
}
},
{
"description": "Synthesize new algorithmic Python procedures on the fly with AST sandboxing and verification.",
"inputSchema": {
"properties": {
"parameters": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Parameters"
},
"problem_type": {
"title": "Problem Type",
"type": "string"
},
"test_examples": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Test Examples"
}
},
"required": [
"problem_type"
],
"title": "cognitive_synthesize_programArguments",
"type": "object"
},
"name": "cognitive_synthesize_program",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_synthesize_programDictOutput",
"type": "object"
}
},
{
"description": "Synthesize an optimal, invariant-verified trajectory from initial state to goal through the singular bottleneck.\n \n Eliminates dead-end branching and hallucinated unfeasible solutions.\n ",
"inputSchema": {
"properties": {
"goal_conditions": {
"anyOf": [
{
"additionalProperties": {
"items": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"type": "array"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Goal Conditions"
},
"initial_state": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Initial State"
},
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
},
"step_budget": {
"default": 5,
"title": "Step Budget",
"type": "integer"
},
"task_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Data"
}
},
"title": "cognitive_synthesize_singular_pathArguments",
"type": "object"
},
"name": "cognitive_synthesize_singular_path",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_synthesize_singular_pathDictOutput",
"type": "object"
}
},
{
"description": "Theory of Mind: model agents' BDI mental states, test false beliefs (Sally-Anne), and infer goals via inverse planning.",
"inputSchema": {
"properties": {
"action_trace": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Action Trace"
},
"agent_id": {
"title": "Agent Id",
"type": "string"
},
"beliefs": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Beliefs"
},
"candidate_goals": {
"anyOf": [
{
"additionalProperties": {
"items": {
"type": "string"
},
"type": "array"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Candidate Goals"
},
"desires": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Desires"
},
"evaluate_false_belief_fact": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Evaluate False Belief Fact"
},
"ground_truth": {
"anyOf": [
{},
{
"type": "null"
}
],
"default": null,
"title": "Ground Truth"
},
"intentions": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Intentions"
},
"witness_event": {
"default": false,
"title": "Witness Event",
"type": "boolean"
}
},
"required": [
"agent_id"
],
"title": "cognitive_theory_of_mindArguments",
"type": "object"
},
"name": "cognitive_theory_of_mind",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_theory_of_mindDictOutput",
"type": "object"
}
},
{
"description": "Perform Monte Carlo Tree Search (UCT) over action sequences to find optimal trajectory.",
"inputSchema": {
"properties": {
"initial_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Initial State"
},
"max_iterations": {
"default": 100,
"title": "Max Iterations",
"type": "integer"
},
"valid_actions": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Valid Actions"
}
},
"title": "cognitive_tree_searchArguments",
"type": "object"
},
"name": "cognitive_tree_search",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_tree_searchDictOutput",
"type": "object"
}
},
{
"description": "Formally verify an arithmetic equality claim, audit numerical stability, condition number, and cancellation risks.",
"inputSchema": {
"properties": {
"audit_stability": {
"default": false,
"title": "Audit Stability",
"type": "boolean"
},
"claim_lhs": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
}
],
"title": "Claim Lhs"
},
"claim_rhs": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
}
],
"title": "Claim Rhs"
},
"matrix": {
"anyOf": [
{
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Matrix"
},
"tolerance": {
"default": 0.000001,
"title": "Tolerance",
"type": "number"
}
},
"required": [
"claim_lhs",
"claim_rhs"
],
"title": "cognitive_verify_arithmetic_claimArguments",
"type": "object"
},
"name": "cognitive_verify_arithmetic_claim",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_verify_arithmetic_claimDictOutput",
"type": "object"
}
},
{
"description": "Normative ethics & fairness: enforce deontological vetos, evaluate Rawlsian vs Utilitarian welfare, and arbitrate moral dilemmas.",
"inputSchema": {
"properties": {
"options": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Options"
},
"proposed_action_or_plan": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Proposed Action Or Plan"
},
"stakeholder_payoffs": {
"anyOf": [
{
"additionalProperties": {
"type": "number"
},
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Stakeholder Payoffs"
}
},
"title": "cognitive_verify_ethics_and_normsArguments",
"type": "object"
},
"name": "cognitive_verify_ethics_and_norms",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_verify_ethics_and_normsDictOutput",
"type": "object"
}
},
{
"description": "Verify a candidate state or transition S_t -> S_{t+1} against invariant boundary manifolds.",
"inputSchema": {
"properties": {
"action": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Action"
},
"lattice_data": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Data"
},
"lattice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Lattice Id"
},
"next_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Next State"
},
"prev_state": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Prev State"
}
},
"title": "cognitive_verify_lattice_transitionArguments",
"type": "object"
},
"name": "cognitive_verify_lattice_transition",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_verify_lattice_transitionDictOutput",
"type": "object"
}
},
{
"description": "Run objective deterministic verification on a strategy (§24, §16).\n\n Clients cannot self-promote. Verification is evaluated server-side.\n Pass task_structure_id (from cognitive.identify_task) so constraints are\n independently recomputed from registered descriptors instead of trusting\n trace flags. Objective precedence: explicit caller value → recomputed from\n raw data → registered spec (labeled unknown) → nested trace claims ONLY\n when trust_trace_objective=true → otherwise unknown, never silent 0.0.\n Returns passed/score plus details.objective_source and\n details.independently_verified so callers know what was recomputed\n versus taken on trace claims. Failures are structured, never bare.\n ",
"inputSchema": {
"properties": {
"execution_trace": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Execution Trace"
},
"strategy_id": {
"title": "Strategy Id",
"type": "string"
},
"task_instance": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Instance"
},
"task_structure_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Task Structure Id"
},
"trust_trace_objective": {
"default": false,
"title": "Trust Trace Objective",
"type": "boolean"
}
},
"required": [
"strategy_id"
],
"title": "cognitive_verify_strategyArguments",
"type": "object"
},
"name": "cognitive_verify_strategy",
"outputSchema": {
"additionalProperties": true,
"title": "cognitive_verify_strategyDictOutput",
"type": "object"
}
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:260a69b66135909b14edc1382937436f014bc53d438ac443215549516b7f7e0c | sha256sum