# Honcho Configuration File
# This file demonstrates all available configuration options.
# Copy this to config.toml and modify as needed.
# Environment variables will override these values.

# Application-level settings
[app]
LOG_LEVEL = "INFO"
SESSION_OBSERVERS_LIMIT = 10
GET_CONTEXT_MAX_TOKENS = 100000
MAX_FILE_SIZE = 5242880  # 5MB
MAX_MESSAGE_SIZE = 25000 # Characters
EMBED_MESSAGES = true
MAX_EMBEDDING_TOKENS = 8192
MAX_EMBEDDING_TOKENS_PER_REQUEST = 300000
# LANGFUSE_HOST = "https://api.langfuse.com"
# LANGFUSE_PUBLIC_KEY = "your-public-key-here"
# COLLECT_METRICS_LOCAL = false
# LOCAL_METRICS_FILE = "metrics.jsonl"
# REASONING_TRACES_FILE = "traces.jsonl"  # Path to JSONL file for reasoning traces
NAMESPACE = "honcho"

# Database settings
[db]
CONNECTION_URI = "postgresql+psycopg://postgres:postgres@localhost:5432/postgres"
SCHEMA = "public"
POOL_CLASS = "default"
POOL_PRE_PING = true
POOL_SIZE = 10
MAX_OVERFLOW = 20
POOL_TIMEOUT = 30  # seconds
POOL_RECYCLE = 300  # seconds
POOL_USE_LIFO = true
SQL_DEBUG = false
TRACING = false

# Authentication settings
[auth]
USE_AUTH = false
JWT_SECRET = "your-secret-key-here"  # Must be set if USE_AUTH is true

# Sentry settings
[sentry]
ENABLED = false
DSN = ""
RELEASE = ""
ENVIRONMENT = "development"
TRACES_SAMPLE_RATE = 0.1
PROFILES_SAMPLE_RATE = 0.1

# LLM settings
[llm]
DEFAULT_MAX_TOKENS = 2500
EMBEDDING_PROVIDER = "openai"
MAX_TOOL_OUTPUT_CHARS = 10000  # Max chars for tool output (~2500 tokens)
MAX_MESSAGE_CONTENT_CHARS = 2000  # Max chars per message in tool results

# API Keys for LLM providers
# ANTHROPIC_API_KEY = "your-api-key"
# OPENAI_API_KEY = "your-api-key"
# OPENAI_COMPATIBLE_API_KEY = "your-api-key"
# GEMINI_API_KEY = "your-api-key"
# GROQ_API_KEY = "your-api-key"
# OPENAI_COMPATIBLE_BASE_URL = "your-base-url"

# Separate vLLM endpoint (for local models)
# VLLM_API_KEY = "your-api-key"
# VLLM_BASE_URL = "your-base-url"

# Deriver settings
[deriver]
ENABLED = true
WORKERS = 1
POLLING_SLEEP_INTERVAL_SECONDS = 1.0
STALE_SESSION_TIMEOUT_MINUTES = 5
# QUEUE_ERROR_RETENTION_SECONDS = 2592000  # 30 days
PROVIDER = "google"
MODEL = "gemini-2.5-flash-lite"
# TEMPERATURE = 0.0
# BACKUP_PROVIDER = "anthropic"
# BACKUP_MODEL = "claude-haiku-4-5"
DEDUPLICATE = true
MAX_OUTPUT_TOKENS = 4096
THINKING_BUDGET_TOKENS = 1024
LOG_OBSERVATIONS = false
MAX_INPUT_TOKENS = 23000
WORKING_REPRESENTATION_MAX_OBSERVATIONS = 100
REPRESENTATION_BATCH_MAX_TOKENS = 1024

# Peer card settings
[peer_card]
ENABLED = true

# Dialectic settings
[dialectic]
MAX_OUTPUT_TOKENS = 8192
MAX_INPUT_TOKENS = 100000
HISTORY_TOKEN_LIMIT = 8192
SESSION_HISTORY_MAX_TOKENS = 4096

# Per-level settings for reasoning levels
# MAX_OUTPUT_TOKENS is optional per level; if not set, uses global MAX_OUTPUT_TOKENS
[dialectic.levels.minimal]
PROVIDER = "google"
MODEL = "gemini-2.5-flash-lite"
THINKING_BUDGET_TOKENS = 0
MAX_TOOL_ITERATIONS = 1
MAX_OUTPUT_TOKENS = 250

[dialectic.levels.low]
PROVIDER = "google"
MODEL = "gemini-2.5-flash-lite"
THINKING_BUDGET_TOKENS = 0
MAX_TOOL_ITERATIONS = 5
# MAX_OUTPUT_TOKENS = 8192  # Optional: override global default

[dialectic.levels.medium]
PROVIDER = "anthropic"
MODEL = "claude-haiku-4-5"
THINKING_BUDGET_TOKENS = 1024
MAX_TOOL_ITERATIONS = 2
# MAX_OUTPUT_TOKENS = 8192  # Optional: override global default

[dialectic.levels.high]
PROVIDER = "anthropic"
MODEL = "claude-haiku-4-5"
THINKING_BUDGET_TOKENS = 1024
MAX_TOOL_ITERATIONS = 4
# MAX_OUTPUT_TOKENS = 8192  # Optional: override global default

[dialectic.levels.max]
PROVIDER = "anthropic"
MODEL = "claude-haiku-4-5"
THINKING_BUDGET_TOKENS = 2048
MAX_TOOL_ITERATIONS = 10
# MAX_OUTPUT_TOKENS = 8192  # Optional: override global default
# Backup provider example (optional, must set both or neither):
# BACKUP_PROVIDER = "google"
# BACKUP_MODEL = "gemini-2.5-pro"

# Summary settings
[summary]
ENABLED = true
MESSAGES_PER_SHORT_SUMMARY = 20
MESSAGES_PER_LONG_SUMMARY = 60
PROVIDER = "google"
MODEL = "gemini-2.5-flash"
MAX_TOKENS_SHORT = 1000
MAX_TOKENS_LONG = 4000
THINKING_BUDGET_TOKENS = 512
# BACKUP_PROVIDER = "google"
# BACKUP_MODEL = "gemini-2.5-flash"

# Dream settings
[dream]
ENABLED = true
DOCUMENT_THRESHOLD = 50
IDLE_TIMEOUT_MINUTES = 60
MIN_HOURS_BETWEEN_DREAMS = 8
ENABLED_TYPES = ["omni"]
PROVIDER = "anthropic"
MODEL = "claude-sonnet-4-20250514"
MAX_OUTPUT_TOKENS = 16384
THINKING_BUDGET_TOKENS = 8192
MAX_TOOL_ITERATIONS = 20
HISTORY_TOKEN_LIMIT = 16384
# BACKUP_PROVIDER = "google"
# BACKUP_MODEL = "gemini-2.5-flash"

# Specialist models (use same provider as main model)
DEDUCTION_MODEL = "claude-haiku-4-5"
INDUCTION_MODEL = "claude-haiku-4-5"

# Surprisal-based sampling subsystem
[dream.surprisal]
ENABLED = false
TREE_TYPE = "kdtree"  # Options: kdtree, balltree, rptree, covertree, lsh, graph, prototype
TREE_K = 5  # k for kNN-based trees
SAMPLING_STRATEGY = "recent"  # Options: recent, random, all
SAMPLE_SIZE = 200
TOP_PERCENT_SURPRISAL = 0.10  # Top 10% of observations
MIN_HIGH_SURPRISAL_FOR_REPLACE = 10
INCLUDE_LEVELS = ["explicit", "deductive"]

# Webhook settings
[webhook]
SECRET = ""
MAX_WORKSPACE_LIMIT = 10

# OpenTelemetry settings (push-based metrics via OTLP)
[otel]
ENABLED = false
# ENDPOINT = "https://mimir.example.com/otlp/v1/metrics"
# HEADERS = '{"X-Scope-OrgID": "honcho"}'  # JSON string for auth headers
EXPORT_INTERVAL_MILLIS = 60000
SERVICE_NAME = "honcho"
# SERVICE_NAMESPACE = "honcho"  # Inherits from app.NAMESPACE if not set

# CloudEvents telemetry settings (analytics events)
[telemetry]
ENABLED = false
# ENDPOINT = "https://telemetry.honcho.dev/v1/events"
# HEADERS = '{"Authorization": "Bearer your-token"}'  # JSON string for auth headers
BATCH_SIZE = 100
FLUSH_INTERVAL_SECONDS = 1.0
FLUSH_THRESHOLD = 50
MAX_RETRIES = 3
MAX_BUFFER_SIZE = 10000
# NAMESPACE = "honcho"  # Inherits from app.NAMESPACE if not set

# Cache settings
[cache]
ENABLED = false
URL = "redis://localhost:6379/0?suppress=true"
# NAMESPACE = "honcho"  # Inherits from app.NAMESPACE if not set
DEFAULT_TTL_SECONDS = 300
DEFAULT_LOCK_TTL_SECONDS = 5

# Vector store settings
[vector_store]
# Vector store type: "pgvector", "turbopuffer", or "lancedb"
TYPE = "pgvector"
# Migration flag: set to true when migration from pgvector is complete
MIGRATED = false
NAMESPACE = "honcho"
DIMENSIONS = 1536
# TURBOPUFFER_API_KEY = "your-turbopuffer-api-key"
# TURBOPUFFER_REGION = "us-east-1"
LANCEDB_PATH = "./lancedb_data"
RECONCILIATION_INTERVAL_SECONDS = 300