feat: configure Honcho LLM via OpenCode Go, cleanup compose.yml

- Remove OpenViking/Holographic dependencies (only Honcho stays)
- Remove httpx install from Dockerfile (was for OpenViking)
- Add Traefik routing for honcho at honcho.lazyworkhorse.net
- Add Authelia auth middleware on honcho HTTPS
- Add ai_net network to honcho for Traefik access

ai/compose.yml

@@ -28,11 +28,11 @@ services:
   hermes:
     build:
       context: ./hermes
-      args:
+      ssh:
-        HERMES_PLUGIN_URLS: "git+https://code.lazyworkhorse.net/gortium/hermes-piper-plugin.git;git+https://code.lazyworkhorse.net/gortium/hermes-identity-plugin.git"
+        - default
     container_name: hermes
     entrypoint: ["/bin/bash", "-c",
-      "bash /opt/data/hermes-tools/install.sh && bash /usr/local/bin/run-multi-gateways.sh && exec /usr/bin/tini -g -- /opt/hermes/docker/entrypoint.sh \"$@\"",
+      "bash /opt/data/hermes-tools/install.sh && exec /usr/bin/tini -g -- /opt/hermes/docker/entrypoint.sh \"$@\"",
       "hermes-entrypoint"]
     restart: always
     # Gateway run enables the internal API server on port 8642
@@ -40,10 +40,6 @@ services:
     environment:
       - OLLAMA_HOST=http://ollama:11434
       - HERMES_DASHBOARD=1
-      # Multi-profile: comma-separated list of profiles to run as gateways.
-      # The entrypoint reads this and starts one gateway per profile.
-      # Add profiles here when they exist on disk (e.g. default,researcher,writer)
-      - HERMES_PROFILES=ashley,claire,finn,matt,paul
       - API_SERVER_ENABLED=true
       - API_SERVER_PORT=8642
       - API_SERVER_HOST=0.0.0.0
@@ -72,6 +68,8 @@ services:
     networks:
       - ai_backend
       - ai_net
+    depends_on:
+      - honcho
     labels:
       - "traefik.enable=true"
       - "traefik.docker.network=ai_net"
@@ -158,6 +156,84 @@ services:
       - "303"
       - "26"
 
+  # --- Honcho: AI-native user modeling ---
+  honcho:
+    build: ./honcho
+    container_name: honcho
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:8000:8000"
+    environment:
+      - DB_CONNECTION_URI=postgresql+psycopg://honcho:honcho_pass@honcho-db:5432/honcho
+      - CACHE_URL=redis://honcho-redis:6379/0
+      - CACHE_ENABLED=true
+    volumes:
+      - /mnt/HoardingCow_docker_data/Honcho/data:/app/data
+    networks:
+      - ai_backend
+      - ai_net
+    depends_on:
+      honcho-db:
+        condition: service_healthy
+      honcho-redis:
+        condition: service_healthy
+    labels:
+      - "traefik.enable=true"
+
+      # Router for HTTP + redirect to HTTPS
+      - "traefik.http.routers.honcho-http.rule=Host(`honcho.lazyworkhorse.net`)"
+      - "traefik.http.routers.honcho-http.entrypoints=web"
+      - "traefik.http.routers.honcho-http.middlewares=redirect-to-https"
+
+      # Router for HTTPS with TLS — protected by Authelia
+      - "traefik.http.routers.honcho-https.rule=Host(`honcho.lazyworkhorse.net`)"
+      - "traefik.http.routers.honcho-https.entrypoints=websecure"
+      - "traefik.http.routers.honcho-https.tls=true"
+      - "traefik.http.routers.honcho-https.tls.certresolver=njalla"
+      - "traefik.http.routers.honcho-https.middlewares=hermes-auth"
+
+      # Service Loadbalancer
+      - "traefik.http.services.honcho.loadbalancer.server.port=8000"
+
+  honcho-db:
+    image: pgvector/pgvector:pg15
+    container_name: honcho-db
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:5432:5432"
+    command: ["postgres", "-c", "max_connections=200"]
+    environment:
+      - POSTGRES_DB=honcho
+      - POSTGRES_USER=honcho
+      - POSTGRES_PASSWORD=honcho_pass
+      - PGDATA=/var/lib/postgresql/data/pgdata
+    volumes:
+      - /mnt/HoardingCow_docker_data/Honcho/postgres:/var/lib/postgresql/data
+      - ./honcho/init-db.sql:/docker-entrypoint-initdb.d/init.sql:ro
+    networks:
+      - ai_backend
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U honcho -d honcho"]
+      interval: 5s
+      timeout: 5s
+      retries: 5
+
+  honcho-redis:
+    image: redis:8
+    container_name: honcho-redis
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:6379:6379"
+    volumes:
+      - /mnt/HoardingCow_docker_data/Honcho/redis:/data
+    networks:
+      - ai_backend
+    healthcheck:
+      test: ["CMD-SHELL", "redis-cli ping"]
+      interval: 5s
+      timeout: 5s
+      retries: 5
+
 networks:
   ai_net:
     external: true

ai/hermes/Dockerfile

@@ -1,15 +1,33 @@
 # syntax=docker/dockerfile:1
-# Hermes Agent -- official image + custom plugins layered on top.
+# Hermes Agent -- custom fork build
-# No fork needed — customizations are pip-installable plugins from Gitea.
+# Builds on top of official image + overlays our forked source from Gitea.
+# Requires Docker BuildKit. Pass SSH agent for git clone:
 #   docker compose build hermes
 # Or manually:
-#   DOCKER_BUILDKIT=1 docker build --build-arg HERMES_PLUGIN_URLS="url1 url2" -t hermes-agent:custom .
+#   DOCKER_BUILDKIT=1 docker build --ssh default -t hermes-agent:custom .
 
 # ---------- Base: official Hermes image (system deps, npm, uv, Playwright) ----------
 FROM nousresearch/hermes-agent:latest
 
-# ---------- Plugin URLs (semicolon-separated, set via compose.yml build args) ----------
+# ---------- Overlay our forked source ----------
-ARG HERMES_PLUGIN_URLS=""
+# Uses SSH agent forwarding from the build host (no key baked into image).
+# --exclude node_modules/.venv keeps the base image's pre-built layers intact.
+# Only the Python source, web UI source, and config change.
+RUN --mount=type=ssh \
+    mkdir -p /root/.ssh && \
+    ssh-keyscan -p 2222 code.lazyworkhorse.net >> /root/.ssh/known_hosts 2>/dev/null && \
+    cd /tmp && \
+    GIT_SSH_COMMAND='ssh -p 2222 -o StrictHostKeyChecking=no' \
+    git clone --depth 1 --branch main \
+    git@code.lazyworkhorse.net:gortium/hermes-agent.git fork && \
+    rm -rf fork/node_modules fork/.venv fork/.git && \
+    cp -a fork/. /opt/hermes/ && \
+    rm -rf /tmp/fork /root/.ssh/
+
+# ---------- Reinstall Python package (editable) ----------
+# Picks up source changes from our fork.
+RUN . /opt/hermes/.venv/bin/activate && \
+    uv pip install --no-cache-dir --no-deps -e /opt/hermes
 
 # ---------- Extra system deps ----------
 USER root
@@ -25,7 +43,11 @@ RUN apt-get update && \
 # ---------- UV ----------
 COPY --chmod=0755 --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/
 
+WORKDIR /opt/hermes
+
 # ---------- Matrix bridge + extra pip deps ----------
+# Previously installed inline at container startup and persisted via volume mount.
+# Now baked into the image so the fragile venv volume mount can be removed.
 RUN . /opt/hermes/.venv/bin/activate && \
     uv pip install --no-cache-dir 'mautrix[encryption]' openai
 
@@ -56,23 +78,6 @@ os.remove(tgz)
 print('himalaya v1.2.0 installed')
 PYEOF
 
-# ---------- Install custom plugins from URLs ----------
-# HERMES_PLUGIN_URLS is a semicolon-separated list of pip-installable
-# package URLs (e.g. git+https:// or direct .tar.gz archives from Gitea).
-# Each plugin is installed into the Hermes venv.
-RUN if [ -n "$HERMES_PLUGIN_URLS" ]; then \
-        . /opt/hermes/.venv/bin/activate && \
-        IFS=';' read -ra URLS <<< "$HERMES_PLUGIN_URLS" && \
-        for url in "${URLS[@]}"; do \
-            echo "Installing plugin: $url" && \
-            uv pip install --no-cache-dir "$url"; \
-        done; \
-    fi
-
-# ---------- Install multi-gateway launcher ----------
-# Launches one gateway process per profile (HERMES_PROFILES env var)
-COPY --chmod=0755 run-multi-gateways.sh /usr/local/bin/run-multi-gateways.sh
-
 # ---------- Runtime ----------
 USER hermes
 ENV HERMES_HOME=/opt/data

ai/hermes/run-multi-gateways.sh

@@ -1,32 +0,0 @@
-#!/bin/bash
-# Multi-gateway launcher for HERMES_PROFILES env var.
-# Reads comma-separated profile names, spawns one gateway per profile.
-# Designed to run before the main entrypoint — gateways run in background.
-set -e
-
-if [ -z "${HERMES_PROFILES}" ]; then
-  echo "HERMES_PROFILES not set — skipping multi-gateway launch"
-  exit 0
-fi
-
-# Source venv to make 'hermes' available (entrypoint.sh sources it later,
-# but we need it NOW for the background gateways)
-HERMES_BIN="/opt/hermes/.venv/bin/hermes"
-if [ ! -x "$HERMES_BIN" ]; then
-  echo "ERROR: hermes binary not found at $HERMES_BIN"
-  exit 1
-fi
-
-mkdir -p /opt/data/logs
-
-IFS=',' read -ra PROFILES <<< "${HERMES_PROFILES}"
-for profile in "${PROFILES[@]}"; do
-  profile="$(echo "${profile}" | xargs)"  # trim whitespace
-  [ -z "${profile}" ] && continue
-
-  echo "Starting gateway for profile: ${profile}"
-  nohup env API_SERVER_ENABLED=false API_SERVER_KEY= gosu hermes "$HERMES_BIN" --profile "${profile}" gateway run \
-      >> "/opt/data/logs/gateway-${profile}.log" 2>&1 &
-done
-
-echo "All gateways launched: ${HERMES_PROFILES}"

ai/honcho/Dockerfile

@@ -0,0 +1,42 @@
+# build stage — fetches and builds Honcho from source
+# Using buildkit cache mounts for speed across rebuilds
+FROM python:3.13-slim-bookworm AS builder
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends git && \
+    rm -rf /var/lib/apt/lists/*
+
+COPY --from=ghcr.io/astral-sh/uv:0.9.24 /uv /bin/uv
+
+# Clone Honcho at a pinned commit for reproducibility
+ARG HONCHO_REPO=https://github.com/plastic-labs/honcho
+ARG HONCHO_REF=main
+RUN git clone --depth 1 --branch ${HONCHO_REF} ${HONCHO_REPO} /app
+
+WORKDIR /app
+
+ENV UV_COMPILE_BYTECODE=1
+ENV UV_LINK_MODE=copy
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen --no-group dev
+
+# --- runtime stage ---
+FROM python:3.13-slim-bookworm
+
+RUN groupadd --system app && \
+    useradd --system --gid app --create-home app
+
+COPY --from=builder /app /app
+COPY --from=builder /root/.cache/uv /root/.cache/uv
+
+WORKDIR /app
+ENV PATH="/app/.venv/bin:$PATH"
+ENV HOME=/app
+
+COPY --chown=app:app config.toml /app/config.toml
+
+USER app
+EXPOSE 8000
+
+CMD ["fastapi", "run", "--host", "0.0.0.0", "src/main.py"]

ai/honcho/config.toml

@@ -0,0 +1,119 @@
+[app]
+LOG_LEVEL = "INFO"
+MAX_MESSAGE_SIZE = 25000
+EMBED_MESSAGES = true
+NAMESPACE = "honcho"
+
+[db]
+CONNECTION_URI = "postgresql+psycopg://honcho:honcho_pass@honcho-db:5432/honcho"
+SCHEMA = "public"
+POOL_SIZE = 10
+MAX_OVERFLOW = 20
+
+[auth]
+USE_AUTH = false
+
+[sentry]
+ENABLED = false
+
+[telemetry]
+ENABLED = false
+
+[webhook]
+ENABLED = false
+
+[cache]
+ENABLED = true
+URL = "redis://honcho-redis:6379/0"
+
+[llm]
+DEFAULT_MAX_TOKENS = 4096
+
+# Embeddings via Ollama local (nomic-embed-text)
+[embedding]
+VECTOR_DIMENSIONS = 768
+MAX_INPUT_TOKENS = 8192
+
+[embedding.model_config]
+transport = "openai"
+model = "nomic-embed-text"
+base_url = "http://ollama:11434/v1"
+
+# --- Deriver (user representation builder) ---
+# Uses DeepSeek V3 Flash via OpenCode Go
+[deriver]
+ENABLED = true
+WORKERS = 1
+POLLING_SLEEP_INTERVAL_SECONDS = 5.0
+FLUSH_ENABLED = true
+
+[deriver.model_config]
+transport = "openai"
+model = "deepseek/deepseek-v3-flash"
+base_url = "https://opencode.ai/zen/go/v1"
+
+# --- Dialectic ---
+# All levels use DeepSeek V3 Flash via OpenCode Go
+[dialectic]
+MAX_INPUT_TOKENS = 4096
+SESSION_HISTORY_MAX_TOKENS = 8192
+
+[dialectic.levels.minimal]
+MAX_TOOL_ITERATIONS = 1
+MAX_OUTPUT_TOKENS = 512
+[dialectic.levels.minimal.model_config]
+transport = "openai"
+model = "deepseek/deepseek-v3-flash"
+base_url = "https://opencode.ai/zen/go/v1"
+
+[dialectic.levels.low]
+MAX_TOOL_ITERATIONS = 3
+[dialectic.levels.low.model_config]
+transport = "openai"
+model = "deepseek/deepseek-v3-flash"
+base_url = "https://opencode.ai/zen/go/v1"
+
+[dialectic.levels.medium]
+MAX_TOOL_ITERATIONS = 2
+[dialectic.levels.medium.model_config]
+transport = "openai"
+model = "deepseek/deepseek-v3-flash"
+base_url = "https://opencode.ai/zen/go/v1"
+
+[dialectic.levels.high]
+MAX_TOOL_ITERATIONS = 4
+[dialectic.levels.high.model_config]
+transport = "openai"
+model = "deepseek/deepseek-v3-flash"
+base_url = "https://opencode.ai/zen/go/v1"
+
+[dialectic.levels.max]
+MAX_TOOL_ITERATIONS = 10
+[dialectic.levels.max.model_config]
+transport = "openai"
+model = "deepseek/deepseek-v3-flash"
+base_url = "https://opencode.ai/zen/go/v1"
+
+# --- Summary ---
+[summary]
+ENABLED = true
+MESSAGES_PER_SHORT_SUMMARY = 20
+MESSAGES_PER_LONG_SUMMARY = 60
+
+[summary.model_config]
+transport = "openai"
+model = "deepseek/deepseek-v3-flash"
+base_url = "https://opencode.ai/zen/go/v1"
+
+# --- Dream ---
+[dream]
+ENABLED = false
+
+# --- Peer Card ---
+[peer_card]
+ENABLED = true
+
+# --- Vector Store ---
+[vector_store]
+TYPE = "pgvector"
+DIMENSIONS = 768

ai/honcho/init-db.sql

@@ -0,0 +1 @@
+CREATE EXTENSION IF NOT EXISTS vector;