feature_configs

AI Agent Feature Configuration Classes for PraisonAI Agents. Provides dataclasses for consolidated feature configuration:

MemoryConfig: Memory and session management
KnowledgeConfig: RAG and knowledge retrieval
PlanningConfig: Planning mode settings
ReflectionConfig: Self-reflection settings
GuardrailConfig: Safety and validation
WebConfig: Web search and fetch
ToolSearchConfig: Progressive tool disclosure

All configs follow the agent-centric pattern:

False: Feature disabled (zero overhead)
True: Feature enabled with safe defaults
Config: Custom configuration
Instance: Pre-configured manager/engine

Usage:

from praisonaiagents import Agent, MemoryConfig, KnowledgeConfig, ToolSearchConfig

# Simple enable
agent = Agent(instructions="...", memory=True, tool_search=True)

# With config
agent = Agent(
    instructions="...",
    memory=MemoryConfig(backend="redis", user_id="user123"),
    knowledge=KnowledgeConfig(sources=["docs/"], rerank=True),
    tool_search=ToolSearchConfig(enabled="auto", threshold_pct=15),
)

Import

from praisonaiagents.config import feature_configs

Classes

MemoryBackend

Memory storage backends.

LearnScope

Scope for learning data visibility.

LearnMode

Learning mode for automatic learning extraction.

LearnBackend

Storage backend for learning data.

LearnConfig

Configuration for continuous learning within memory system.

MemoryConfig

Configuration for agent memory and session management.

ChunkingStrategy

Knowledge chunking strategies.

KnowledgeConfig

Configuration for RAG and knowledge retrieval.

PlanningConfig

Configuration for planning mode.

ReflectionConfig

Configuration for self-reflection.

RulesConfig

Configuration for auto-applying per-project rules/instructions.

GuardrailAction

Action to take when guardrail fails.

GuardrailConfig

Configuration for guardrails and safety validation.

WebSearchProvider

Web search providers.

WebConfig

Configuration for web search and fetch capabilities.

OutputPreset

Output style presets.

OutputConfig

Configuration for agent output behavior.

ExecutionPreset

Execution mode presets.

PreCompactionMemoryFlushConfig

Bounded policy for extracting durable memories before compaction.

ExecutionConfig

Configuration for agent execution limits.

LLMConfig

Configuration for LLM model settings.

ToolConfig

Configuration for tool execution behavior.

TemplateConfig

Configuration for prompt templates.

CachingConfig

Configuration for caching behavior.

HooksConfig

Configuration for agent hooks/callbacks.

SkillsConfig

Configuration for agent skills.

MultiAgentHooksConfig

Configuration for multi-agent orchestration hooks/callbacks.

MultiAgentOutputConfig

Configuration for multi-agent output behavior.

MultiAgentExecutionConfig

Configuration for multi-agent execution limits.

MultiAgentPlanningConfig

Configuration for multi-agent planning mode.

MultiAgentMemoryConfig

Configuration for multi-agent shared memory.

AutonomyLevel

Autonomy levels for agent behavior.

RuntimeConfig

Configuration for agent runtime capabilities and requirements.

Functions

resolve_memory()

Resolve memory= parameter following precedence ladder.

resolve_knowledge()

Resolve knowledge= parameter following precedence ladder.

resolve_planning()

Resolve planning= parameter following precedence ladder.

resolve_reflection()

Resolve reflection= parameter following precedence ladder.

resolve_guardrails()

Resolve guardrails= parameter following precedence ladder.

resolve_web()

Resolve web= parameter following precedence ladder.

resolve_caching()

Resolve caching= parameter following precedence ladder.

resolve_autonomy()

Resolve autonomy= parameter following precedence ladder.

resolve_tool_search()

Resolve tool_search= parameter following precedence ladder.

resolve_tools()

Resolve tools= parameter following precedence ladder.

resolve_runtime()

Resolve runtime= parameter following precedence ladder.

Constants

Name	Value
`DEFAULT_TOOL_OUTPUT_LIMIT`	`16000`
`_TOOL_SEARCH_CONFIG_CACHE`	`None`

​feature_configs

​Import

​Classes