Complete guide to configuring Honcho for development and production
.env
file (for local development)config.toml
file (base configuration)[app]
- Application-level settings (log level, host, port, embedding settings)[db]
- Database connection and pool settings[auth]
- Authentication configuration[llm]
- LLM provider API keys and general settings[dialectic]
- Dialectic API configuration (provider, model, search settings)[deriver]
- Background worker settings and theory of mind configuration[summary]
- Session summarization settings[sentry]
- Error tracking and monitoring settings{SECTION}_{KEY}
for nested settings{KEY}
for app-level settingsDB_CONNECTION_URI
→ [db].CONNECTION_URI
DB_POOL_SIZE
→ [db].POOL_SIZE
AUTH_JWT_SECRET
→ [auth].JWT_SECRET
DIALECTIC_MODEL
→ [dialectic].MODEL
LOG_LEVEL
(no section) → [app].LOG_LEVEL
config.toml
for base configuration.env
files for local development without modifying config.tomlconfig.toml
:
[llm]
section, while specific features use their own configuration sections.
LLM_
prefix:
EMBED_MESSAGES=true
)DB_CONNECTION_URI
uses postgresql+psycopg://
prefixAUTH_USE_AUTH=true
for productionAUTH_JWT_SECRET
if authentication is enabledpython scripts/generate_jwt_secret.py
to create a secure secretDERIVER_WORKERS
for better performanceDERIVER_STALE_SESSION_TIMEOUT_MINUTES
for session cleanup