Daniele
7e3fa3caad
Nightly Build / build (push) Successful in 3m48s
Against a self-hosted Honcho 3.0.11 every read path came back empty while the server was healthy and full of derived facts: the plugin parsed a `conclusions`/`summary` shape the API no longer emits. - honcho-client: typed models for the real schema — `PeerContext` (`representation` markdown + `peer_card`), `SessionContext` (`summary` as an object, `peer_representation`), wrapped `PeerCard` (a bare array on PUT is a 422, which also broke `honcho_profile` writes). - plugin: the turn-time injection and `honcho_context` read the representation; `honcho_search` and the page's /search now use `conclusions/query` (observer/observed scoping inside `filters`) — a real ranked semantic search with fact ids, which `peer_context?search_query` never provided; /overview returns card + representation + conclusions. - compose: pin the Honcho image by digest (3.0.11) — ghcr publishes no v3 semver tags, and an untracked `:latest` pull is what drifted the schema. - tests: fixture tests from payloads captured on the live server, plus an env-gated live smoke test (HONCHO_E2E_URL/_WS/_PEER, `cargo test -p honcho-client -- --ignored`) — run it before any future Honcho bump.
119 lines
4.9 KiB
YAML
119 lines
4.9 KiB
YAML
# Honcho — self-hosted memory server
|
|
#
|
|
# Runs four services:
|
|
# api — HTTP API on :8000
|
|
# deriver — background worker: extracts conclusions, builds peer representations
|
|
# db — PostgreSQL 17 + pgvector (needed for embedding search)
|
|
# redis — fast cache for session context
|
|
#
|
|
# Usage:
|
|
# cp .env.example .env
|
|
# # edit .env and set at least LLM_OPENAI_API_KEY (or another provider)
|
|
# docker compose up -d
|
|
#
|
|
# The API will be available at http://localhost:8000
|
|
# Interactive docs: http://localhost:8000/docs
|
|
#
|
|
# The Honcho image is PINNED BY DIGEST (ghcr publishes no v3 semver tags, only
|
|
# `latest`): this digest is Honcho 3.0.11. The plugin parses a version-specific
|
|
# API schema (`representation`/`peer_card`, wrapped card, `conclusions/query`
|
|
# filters) — bump the digest deliberately and re-verify, never via `:latest`.
|
|
|
|
services:
|
|
|
|
# ── Migrate (run-once) ────────────────────────────────────────────────────
|
|
# Applies Alembic migrations before the API starts.
|
|
# Exits with code 0 when done; Docker Compose marks it "completed".
|
|
migrate:
|
|
image: ghcr.io/plastic-labs/honcho@sha256:59f099ad85713105608c9b239a4f1386fbebd8647323d3a04646bb3c975d8c6b # Honcho 3.0.11, pinned — see header
|
|
env_file: .env
|
|
environment:
|
|
DB_CONNECTION_URI: postgresql+psycopg://${POSTGRES_USER:-honcho}:${POSTGRES_PASSWORD:-honcho}@db:5432/${POSTGRES_DB:-honcho}
|
|
CACHE_URL: redis://redis:6379/0?suppress=true
|
|
command: ["/app/.venv/bin/alembic", "upgrade", "head"]
|
|
depends_on:
|
|
db:
|
|
condition: service_healthy
|
|
restart: "no"
|
|
|
|
# ── API ────────────────────────────────────────────────────────────────────
|
|
api:
|
|
image: ghcr.io/plastic-labs/honcho@sha256:59f099ad85713105608c9b239a4f1386fbebd8647323d3a04646bb3c975d8c6b # Honcho 3.0.11, pinned — see header
|
|
restart: unless-stopped
|
|
ports:
|
|
- "${HONCHO_PORT:-8000}:8000"
|
|
env_file: .env
|
|
environment:
|
|
DB_CONNECTION_URI: postgresql+psycopg://${POSTGRES_USER:-honcho}:${POSTGRES_PASSWORD:-honcho}@db:5432/${POSTGRES_DB:-honcho}
|
|
CACHE_URL: redis://redis:6379/0?suppress=true
|
|
depends_on:
|
|
db:
|
|
condition: service_healthy
|
|
redis:
|
|
condition: service_healthy
|
|
migrate:
|
|
condition: service_completed_successfully
|
|
healthcheck:
|
|
test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
start_period: 60s
|
|
|
|
# ── Deriver (background worker) ───────────────────────────────────────────
|
|
# Processes incoming messages to:
|
|
# - extract observations (conclusions) about users
|
|
# - build peer representations / user cards
|
|
# - generate session summaries
|
|
# - run "dream" consolidation passes
|
|
#
|
|
# Without a working LLM key this service will fail to process messages;
|
|
# the API itself will still work but no long-term memory will be built.
|
|
deriver:
|
|
image: ghcr.io/plastic-labs/honcho@sha256:59f099ad85713105608c9b239a4f1386fbebd8647323d3a04646bb3c975d8c6b # Honcho 3.0.11, pinned — see header
|
|
restart: unless-stopped
|
|
command: ["/app/.venv/bin/python", "-m", "src.deriver"]
|
|
env_file: .env
|
|
environment:
|
|
DB_CONNECTION_URI: postgresql+psycopg://${POSTGRES_USER:-honcho}:${POSTGRES_PASSWORD:-honcho}@db:5432/${POSTGRES_DB:-honcho}
|
|
CACHE_URL: redis://redis:6379/0?suppress=true
|
|
depends_on:
|
|
api:
|
|
condition: service_healthy
|
|
db:
|
|
condition: service_healthy
|
|
redis:
|
|
condition: service_healthy
|
|
|
|
# ── PostgreSQL + pgvector ─────────────────────────────────────────────────
|
|
db:
|
|
image: pgvector/pgvector:pg17
|
|
restart: unless-stopped
|
|
environment:
|
|
POSTGRES_USER: ${POSTGRES_USER:-honcho}
|
|
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-honcho}
|
|
POSTGRES_DB: ${POSTGRES_DB:-honcho}
|
|
volumes:
|
|
- honcho_db:/var/lib/postgresql/data
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-honcho} -d ${POSTGRES_DB:-honcho}"]
|
|
interval: 5s
|
|
timeout: 5s
|
|
retries: 10
|
|
|
|
# ── Redis ─────────────────────────────────────────────────────────────────
|
|
redis:
|
|
image: redis:7-alpine
|
|
restart: unless-stopped
|
|
volumes:
|
|
- honcho_redis:/data
|
|
healthcheck:
|
|
test: ["CMD", "redis-cli", "ping"]
|
|
interval: 5s
|
|
timeout: 3s
|
|
retries: 10
|
|
|
|
volumes:
|
|
honcho_db:
|
|
honcho_redis:
|