Module intelligent_behavior

Expand description

intelligent_behavior lives in mockforge_intelligence::intelligent_behavior (Issue #562 phase 2). Re-exported here so existing crate::intelligent_behavior::* call sites inside core (voice, reality, graph, ai_contract_diff, ai_studio, contract_drift, failure_analysis) and external mockforge_core::intelligent_behavior::* consumers keep compiling without churn. Data types had already been promoted to mockforge-foundation (A12/A17); this PR moved the LLM-bound engines too. Intelligent Mock Behavior System

This module provides LLM-powered stateful mock behavior that maintains consistency across multiple API requests, simulating a real, thinking backend.

§Features

Stateful Context Management: Tracks state across requests using sessions
LLM-Powered Decision Making: Uses AI to generate intelligent, context-aware responses
Vector Memory: Semantic search over past interactions for long-term memory
Consistency Rules: Enforces logical behavior patterns (e.g., auth requirements)
State Machines: Resources follow realistic lifecycle transitions

§Architecture

Request → Context Manager → Behavior Model → LLM + Vector Store → Response
             ↓                    ↓                    ↓
        Session State      Consistency Rules    Past Interactions

§Example Usage

use mockforge_intelligence::intelligent_behavior::{
    StatefulAiContext, BehaviorModel, IntelligentBehaviorConfig,
};

// Create a stateful context
let config = IntelligentBehaviorConfig::default();
let mut context = StatefulAiContext::new("session_123", config);

// Record an interaction
context.record_interaction(
    "POST",
    "/api/users",
    Some(serde_json::json!({"name": "Alice"})),
    Some(serde_json::json!({"id": "user_1", "name": "Alice"})),
).await?;

// Get current state
let state = context.get_state();

Modules§

behavior: Behavior model for LLM-powered decision making
cache: Response caching for intelligent behavior
condition_evaluator: Re-exported from mockforge_foundation::state_machine (Phase 6 / A4).
config: Configuration for the Intelligent Mock Behavior system
context: Stateful AI context management
embedding_client: Embedding client for vector memory
history: Re-exported from mockforge_foundation::state_machine (Phase 6 / A4).
llm_client: LLM client wrapper for intelligent behavior
memory: Vector memory store for long-term semantic memory
mockai: Unified MockAI interface
mutation_analyzer: Request mutation detection and context analysis
openapi_generator: OpenAPI specification generator from recorded traffic
pagination_intelligence: Context-aware pagination intelligence
relationship_inference: Relationship Inference for Smart Personas
rule_generator: Rule auto-generation engine for MockAI
rules: Re-exported from mockforge_foundation::state_machine (Phase 6 / A3).
session: Re-exported from mockforge_foundation::intelligent_behavior::session (Phase 6 / A7).
spec_suggestion: AI-powered specification suggestion and generation
sub_scenario: Re-exported from mockforge_foundation::state_machine (Phase 6 / A3).
types: Core types for the Intelligent Mock Behavior system
validation_generator: AI-driven validation error generation
visual_layout: Re-exported from mockforge_foundation::state_machine (Phase 6 / A3).

Structs§

BehaviorModel: Behavior model that uses LLMs to generate intelligent responses
BehaviorRules: Behavior rules that define how the mock API should behave
ConditionEvaluator: Condition evaluator for state machine transitions
ConfidenceScore: Confidence score for an inferred OpenAPI element
ConsistencyRule: Consistency rule that enforces logical behavior patterns
CrudExample: CRUD example for state machine generation
EndpointSuggestion: Individual endpoint suggestion
ErrorExample: Error example for learning validation rules
ExamplePair: Example request/response pair for learning
FieldChange: Change detected in a field
FieldError: Field-level error
HistoryManager: History manager for state machine edits
HttpExchange: Captured HTTP request/response exchange used for behavioral analysis.
IntelligentBehaviorConfig: Configuration for the Intelligent Mock Behavior system
InteractionRecord: A single interaction record (request + response pair)
LlmUsage: LLM usage information
MockAI: MockAI unified interface
MutationAnalysis: Analysis of changes between requests
MutationAnalyzer: Mutation analyzer
OpenApiGenerationConfig: Configuration for OpenAPI spec generation
OpenApiGenerationMetadata: Metadata about the generated OpenAPI spec
OpenApiGenerationResult: Result of OpenAPI spec generation
OpenApiSpecGenerator: OpenAPI specification generator from recorded traffic
PaginatedResponse: Paginated response example
PaginationIntelligence: Pagination intelligence engine
PaginationMetadata: Pagination metadata for response
PaginationRequest: Pagination request parameters
PaginationRule: Pagination rule learned from examples
ParameterInfo: Parameter information
PatternMatch: Pattern match information
Persona: A persona defines consistent data patterns across endpoints
PersonasConfig: Personas configuration for consistent data generation
Relationship: Represents a relationship between two entities
RelationshipInference: Relationship inference engine
Request: HTTP request for MockAI processing.
RequestContext: Request context for error generation
Response: HTTP response from MockAI.
RuleExplanation: Rule explanation metadata
RuleGenerator: Rule generator that learns from examples
SessionManager: Session manager for tracking and managing sessions
SessionTracking: Session tracking configuration
SpecSuggestionEngine: Engine for AI-powered spec suggestion
StateMachine: State machine for resource lifecycle management
StateTransition: State transition definition
StatefulAiContext: Stateful AI context manager
SubScenario: Sub-scenario definition for nested state machine execution
SuggestionConfig: Configuration for spec suggestion
SuggestionMetadata: Metadata about the suggestion generation
SuggestionResult: Result from spec suggestion
ValidationErrorExample: Example error response for learning validation error formats
ValidationErrorResponse: Validation error response
ValidationGenerator: Validation error generator
ValidationIssue: Validation issue detected from mutation
ValidationRule: Validation rule inferred from examples
VectorMemoryStore: Vector memory store for persistent, searchable interaction history
Viewport: Viewport information for the visual editor
VisualEdge: Visual representation of a transition edge
VisualLayout: Visual layout for a state machine graph
VisualNode: Visual representation of a state node

Enums§

ChangeType: Type of change detected
ConditionError: Error types for condition evaluation
ErrorFormat: Error response format
MutationType: Type of mutation detected
OutputFormat: Output format for generated specs
PaginationFormat: Pagination format type
ResponseType: Response type inferred from mutation
RuleAction: Action to take when a consistency rule matches
RuleType: Rule type classification
SuggestionInput: Input type for spec suggestion
ValidationIssueType: Type of validation issue
ValidationSeverity: Severity of validation issue

Type Aliases§

ConditionResult: Result type for condition evaluation