f8cf139b10
Smoke-testing the first deploy uncovered three default-config issues
that no amount of Quadlet tuning would have caught:
1. DIALECTIC subsystem ignored DERIVER_MODEL_CONFIG__*. Honcho splits
dialectic into five reasoning levels (minimal/low/medium/high/max)
each with its own MODEL_CONFIG that defaults to OpenAI. Without
overrides, every /chat call fails with: ValidationException:
Missing API key for openai model config. Now setting all five
DIALECTIC_LEVELS__<level>__MODEL_CONFIG__* env vars to anthropic.
2. DERIVER batches representation tasks until a token threshold is
reached. For low-volume homelab use (one chatty operator), tasks
can sit unprocessed forever. Add DERIVER_FLUSH_ENABLED knob,
default true.
3. Embeddings default to OpenAI text-embedding-3-small. Anthropic
has no embedding API, so without an OpenAI key the embed step
fails the entire derivation. Default EMBED_MESSAGES=false until
a separate embedding provider is wired up (OpenAI for embeds-only
or a local BGE endpoint on astro-orbiter).
defaults/main.yml documents all three issues and the migration path
back to embeddings when ready.
68 lines
2.9 KiB
Django/Jinja
68 lines
2.9 KiB
Django/Jinja
# mk-labs Honcho deriver worker (background queue consumer)
|
|
# Managed by Ansible - honcho role
|
|
#
|
|
# Same image as the API; different command. The deriver pulls jobs off
|
|
# the DB-backed queue and calls the LLM provider to perform theory-of-mind
|
|
# derivations against user sessions.
|
|
|
|
[Unit]
|
|
Description=Honcho deriver worker
|
|
After=network-online.target {{ honcho_postgres_container_name }}.service {{ honcho_container_name }}.service
|
|
Wants=network-online.target
|
|
Requires={{ honcho_postgres_container_name }}.service
|
|
|
|
[Container]
|
|
Image={{ honcho_image }}
|
|
ContainerName={{ honcho_deriver_container_name }}
|
|
Network={{ honcho_network_name }}
|
|
|
|
# Run the deriver via the package's __main__ (not the helpers module).
|
|
# src/deriver/deriver.py has no __main__ guard — loading it exits 0 in
|
|
# ~3s and systemd treats that as a crash loop. The actual entry point
|
|
# lives in src/deriver/__main__.py and is invoked via "python -m src.deriver".
|
|
WorkingDir=/app
|
|
Exec=/app/.venv/bin/python -m src.deriver
|
|
|
|
# -- Database ---------------------------------------------------------------
|
|
Environment=DB_CONNECTION_URI=postgresql+psycopg://{{ honcho_db_user }}:{{ honcho_db_password }}@{{ honcho_postgres_container_name }}:5432/{{ honcho_db_name }}
|
|
|
|
# -- Auth -------------------------------------------------------------------
|
|
# Deriver does not serve HTTP, but it reads the same config object — keep
|
|
# secrets aligned with the API container.
|
|
Environment=AUTH_USE_AUTH=*** honcho_auth_enabled | string | lower }}
|
|
Environment=AUTH_JWT_SECRET=*** honcho_jwt_secret }}
|
|
|
|
# -- LLM provider keys ------------------------------------------------------
|
|
{% if honcho_llm_transport == 'anthropic' %}
|
|
Environment=LLM_ANTHROPIC_API_KEY=*** honcho_anthropic_api_key }}
|
|
{% endif %}
|
|
|
|
# -- Deriver runtime --------------------------------------------------------
|
|
Environment=DERIVER_ENABLED={{ honcho_deriver_enabled | string | lower }}
|
|
Environment=DERIVER_WORKERS={{ honcho_deriver_workers }}
|
|
Environment=DERIVER_POLLING_SLEEP_INTERVAL_SECONDS={{ honcho_deriver_polling_seconds }}
|
|
Environment=DERIVER_FLUSH_ENABLED={{ honcho_deriver_flush_enabled | string | lower }}
|
|
Environment=DERIVER_MODEL_CONFIG__TRANSPORT={{ honcho_llm_transport }}
|
|
Environment=DERIVER_MODEL_CONFIG__MODEL={{ honcho_deriver_model }}
|
|
|
|
# -- Summary subsystem (the deriver triggers summaries periodically) --------
|
|
Environment=SUMMARY_MODEL_CONFIG__TRANSPORT={{ honcho_llm_transport }}
|
|
Environment=SUMMARY_MODEL_CONFIG__MODEL={{ honcho_summary_model }}
|
|
|
|
# -- Embeddings (off by default — see defaults/main.yml for rationale) ------
|
|
Environment=EMBED_MESSAGES={{ honcho_embed_messages | string | lower }}
|
|
|
|
# -- Vector store -----------------------------------------------------------
|
|
Environment=VECTOR_STORE_TYPE=pgvector
|
|
|
|
# Timezone matches host baseline
|
|
Environment=TZ=America/Chicago
|
|
Environment=LOG_LEVEL=INFO
|
|
|
|
[Service]
|
|
Restart=always
|
|
TimeoutStartSec=180
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target default.target
|