Compare commits
19 Commits
58b5355780
...
261536d74d
| Author | SHA1 | Date | |
|---|---|---|---|
| 261536d74d | |||
| 9b20dfe67f | |||
| 8e99fb8809 | |||
| 057f1b0f4e | |||
| 69e0b7383a | |||
| 7404e1e466 | |||
| 81a12afe39 | |||
| 3d90f57e7f | |||
| c1cd9d31e9 | |||
| 5765dc6004 | |||
| e8075fb71b | |||
| 645d519030 | |||
| 146add2a64 | |||
| eb3795d9e3 | |||
| ef6e0e57b6 | |||
| d8a1ebcd96 | |||
| 45a224eb7f | |||
| bce336c4fd | |||
| e4117cd3d5 |
@@ -32,7 +32,7 @@ services:
|
|||||||
- default
|
- default
|
||||||
container_name: hermes
|
container_name: hermes
|
||||||
entrypoint: ["/bin/bash", "-c",
|
entrypoint: ["/bin/bash", "-c",
|
||||||
"bash /opt/data/hermes-tools/install.sh && exec /usr/bin/tini -g -- /opt/hermes/docker/entrypoint.sh \"$@\"",
|
"bash /opt/data/hermes-tools/install.sh && bash /usr/local/bin/run-multi-gateways.sh && exec /usr/bin/tini -g -- /opt/hermes/docker/entrypoint.sh \"$@\"",
|
||||||
"hermes-entrypoint"]
|
"hermes-entrypoint"]
|
||||||
restart: always
|
restart: always
|
||||||
# Gateway run enables the internal API server on port 8642
|
# Gateway run enables the internal API server on port 8642
|
||||||
@@ -40,6 +40,10 @@ services:
|
|||||||
environment:
|
environment:
|
||||||
- OLLAMA_HOST=http://ollama:11434
|
- OLLAMA_HOST=http://ollama:11434
|
||||||
- HERMES_DASHBOARD=1
|
- 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_ENABLED=true
|
||||||
- API_SERVER_PORT=8642
|
- API_SERVER_PORT=8642
|
||||||
- API_SERVER_HOST=0.0.0.0
|
- API_SERVER_HOST=0.0.0.0
|
||||||
@@ -123,6 +127,7 @@ services:
|
|||||||
- "traefik.http.routers.syncthing-https.tls.certresolver=njalla"
|
- "traefik.http.routers.syncthing-https.tls.certresolver=njalla"
|
||||||
- "traefik.http.services.syncthing.loadbalancer.server.port=8384"
|
- "traefik.http.services.syncthing.loadbalancer.server.port=8384"
|
||||||
|
|
||||||
|
|
||||||
ollama:
|
ollama:
|
||||||
build:
|
build:
|
||||||
context: ./ollama
|
context: ./ollama
|
||||||
|
|||||||
@@ -43,6 +43,12 @@ RUN apt-get update && \
|
|||||||
# ---------- UV ----------
|
# ---------- UV ----------
|
||||||
COPY --chmod=0755 --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/
|
COPY --chmod=0755 --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/
|
||||||
|
|
||||||
|
# ---------- 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
|
||||||
|
|
||||||
WORKDIR /opt/hermes
|
WORKDIR /opt/hermes
|
||||||
|
|
||||||
# ---------- Matrix bridge + extra pip deps ----------
|
# ---------- Matrix bridge + extra pip deps ----------
|
||||||
@@ -78,6 +84,10 @@ os.remove(tgz)
|
|||||||
print('himalaya v1.2.0 installed')
|
print('himalaya v1.2.0 installed')
|
||||||
PYEOF
|
PYEOF
|
||||||
|
|
||||||
|
# ---------- 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 ----------
|
# ---------- Runtime ----------
|
||||||
USER hermes
|
USER hermes
|
||||||
ENV HERMES_HOME=/opt/data
|
ENV HERMES_HOME=/opt/data
|
||||||
|
|||||||
32
ai/hermes/run-multi-gateways.sh
Executable file
32
ai/hermes/run-multi-gateways.sh
Executable file
@@ -0,0 +1,32 @@
|
|||||||
|
#!/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}"
|
||||||
@@ -29,7 +29,7 @@ URL = "redis://honcho-redis:6379/0"
|
|||||||
[llm]
|
[llm]
|
||||||
DEFAULT_MAX_TOKENS = 4096
|
DEFAULT_MAX_TOKENS = 4096
|
||||||
|
|
||||||
# Embeddings via Ollama local (nomic-embed-text)
|
# Embeddings via Ollama (nomic-embed-text recommended on this system)
|
||||||
[embedding]
|
[embedding]
|
||||||
VECTOR_DIMENSIONS = 768
|
VECTOR_DIMENSIONS = 768
|
||||||
MAX_INPUT_TOKENS = 8192
|
MAX_INPUT_TOKENS = 8192
|
||||||
@@ -40,7 +40,6 @@ model = "nomic-embed-text"
|
|||||||
base_url = "http://ollama:11434/v1"
|
base_url = "http://ollama:11434/v1"
|
||||||
|
|
||||||
# --- Deriver (user representation builder) ---
|
# --- Deriver (user representation builder) ---
|
||||||
# Uses DeepSeek V3 Flash via OpenCode Go
|
|
||||||
[deriver]
|
[deriver]
|
||||||
ENABLED = true
|
ENABLED = true
|
||||||
WORKERS = 1
|
WORKERS = 1
|
||||||
@@ -49,11 +48,10 @@ FLUSH_ENABLED = true
|
|||||||
|
|
||||||
[deriver.model_config]
|
[deriver.model_config]
|
||||||
transport = "openai"
|
transport = "openai"
|
||||||
model = "deepseek/deepseek-v3-flash"
|
model = "hermes-3"
|
||||||
base_url = "https://opencode.ai/zen/go/v1"
|
base_url = "http://ollama:11434/v1"
|
||||||
|
|
||||||
# --- Dialectic ---
|
# --- Dialectic ---
|
||||||
# All levels use DeepSeek V3 Flash via OpenCode Go
|
|
||||||
[dialectic]
|
[dialectic]
|
||||||
MAX_INPUT_TOKENS = 4096
|
MAX_INPUT_TOKENS = 4096
|
||||||
SESSION_HISTORY_MAX_TOKENS = 8192
|
SESSION_HISTORY_MAX_TOKENS = 8192
|
||||||
@@ -63,36 +61,36 @@ MAX_TOOL_ITERATIONS = 1
|
|||||||
MAX_OUTPUT_TOKENS = 512
|
MAX_OUTPUT_TOKENS = 512
|
||||||
[dialectic.levels.minimal.model_config]
|
[dialectic.levels.minimal.model_config]
|
||||||
transport = "openai"
|
transport = "openai"
|
||||||
model = "deepseek/deepseek-v3-flash"
|
model = "hermes-3"
|
||||||
base_url = "https://opencode.ai/zen/go/v1"
|
base_url = "http://ollama:11434/v1"
|
||||||
|
|
||||||
[dialectic.levels.low]
|
[dialectic.levels.low]
|
||||||
MAX_TOOL_ITERATIONS = 3
|
MAX_TOOL_ITERATIONS = 3
|
||||||
[dialectic.levels.low.model_config]
|
[dialectic.levels.low.model_config]
|
||||||
transport = "openai"
|
transport = "openai"
|
||||||
model = "deepseek/deepseek-v3-flash"
|
model = "hermes-3"
|
||||||
base_url = "https://opencode.ai/zen/go/v1"
|
base_url = "http://ollama:11434/v1"
|
||||||
|
|
||||||
[dialectic.levels.medium]
|
[dialectic.levels.medium]
|
||||||
MAX_TOOL_ITERATIONS = 2
|
MAX_TOOL_ITERATIONS = 2
|
||||||
[dialectic.levels.medium.model_config]
|
[dialectic.levels.medium.model_config]
|
||||||
transport = "openai"
|
transport = "openai"
|
||||||
model = "deepseek/deepseek-v3-flash"
|
model = "hermes-3"
|
||||||
base_url = "https://opencode.ai/zen/go/v1"
|
base_url = "http://ollama:11434/v1"
|
||||||
|
|
||||||
[dialectic.levels.high]
|
[dialectic.levels.high]
|
||||||
MAX_TOOL_ITERATIONS = 4
|
MAX_TOOL_ITERATIONS = 4
|
||||||
[dialectic.levels.high.model_config]
|
[dialectic.levels.high.model_config]
|
||||||
transport = "openai"
|
transport = "openai"
|
||||||
model = "deepseek/deepseek-v3-flash"
|
model = "hermes-3"
|
||||||
base_url = "https://opencode.ai/zen/go/v1"
|
base_url = "http://ollama:11434/v1"
|
||||||
|
|
||||||
[dialectic.levels.max]
|
[dialectic.levels.max]
|
||||||
MAX_TOOL_ITERATIONS = 10
|
MAX_TOOL_ITERATIONS = 10
|
||||||
[dialectic.levels.max.model_config]
|
[dialectic.levels.max.model_config]
|
||||||
transport = "openai"
|
transport = "openai"
|
||||||
model = "deepseek/deepseek-v3-flash"
|
model = "hermes-3"
|
||||||
base_url = "https://opencode.ai/zen/go/v1"
|
base_url = "http://ollama:11434/v1"
|
||||||
|
|
||||||
# --- Summary ---
|
# --- Summary ---
|
||||||
[summary]
|
[summary]
|
||||||
@@ -102,8 +100,8 @@ MESSAGES_PER_LONG_SUMMARY = 60
|
|||||||
|
|
||||||
[summary.model_config]
|
[summary.model_config]
|
||||||
transport = "openai"
|
transport = "openai"
|
||||||
model = "deepseek/deepseek-v3-flash"
|
model = "hermes-3"
|
||||||
base_url = "https://opencode.ai/zen/go/v1"
|
base_url = "http://ollama:11434/v1"
|
||||||
|
|
||||||
# --- Dream ---
|
# --- Dream ---
|
||||||
[dream]
|
[dream]
|
||||||
|
|||||||
Reference in New Issue
Block a user