From 58b5355780855c4c1ced5d7424d332174e1dd0bc Mon Sep 17 00:00:00 2001
From: Hermes <hermes@lazyworkhorse.net>
Date: Fri, 22 May 2026 22:07:53 -0400
Subject: [PATCH] feat: configure Honcho LLM via OpenCode Go, cleanup
 compose.yml

---
 ai/compose.yml        |  6 +-----
 ai/honcho/config.toml | 32 +++++++++++++++++---------------
 2 files changed, 18 insertions(+), 20 deletions(-)

diff --git a/ai/compose.yml b/ai/compose.yml
index 744a20d..bd25ca6 100755
--- a/ai/compose.yml
+++ b/ai/compose.yml
@@ -32,7 +32,7 @@ services:
         - default
     container_name: hermes
     entrypoint: ["/bin/bash", "-c",
-      "bash /opt/data/hermes-tools/install.sh && bash /opt/data/hermes-tools/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
diff --git a/ai/honcho/config.toml b/ai/honcho/config.toml
index 0578f57..b242d16 100644
--- a/ai/honcho/config.toml
+++ b/ai/honcho/config.toml
@@ -29,7 +29,7 @@ URL = "redis://honcho-redis:6379/0"
 [llm]
 DEFAULT_MAX_TOKENS = 4096
 
-# Embeddings via Ollama (nomic-embed-text recommended on this system)
+# Embeddings via Ollama local (nomic-embed-text)
 [embedding]
 VECTOR_DIMENSIONS = 768
 MAX_INPUT_TOKENS = 8192
@@ -40,6 +40,7 @@ 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
@@ -48,10 +49,11 @@ FLUSH_ENABLED = true
 
 [deriver.model_config]
 transport = "openai"
-model = "hermes-3"
-base_url = "http://ollama:11434/v1"
+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
@@ -61,36 +63,36 @@ MAX_TOOL_ITERATIONS = 1
 MAX_OUTPUT_TOKENS = 512
 [dialectic.levels.minimal.model_config]
 transport = "openai"
-model = "hermes-3"
-base_url = "http://ollama:11434/v1"
+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 = "hermes-3"
-base_url = "http://ollama:11434/v1"
+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 = "hermes-3"
-base_url = "http://ollama:11434/v1"
+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 = "hermes-3"
-base_url = "http://ollama:11434/v1"
+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 = "hermes-3"
-base_url = "http://ollama:11434/v1"
+model = "deepseek/deepseek-v3-flash"
+base_url = "https://opencode.ai/zen/go/v1"
 
 # --- Summary ---
 [summary]
@@ -100,8 +102,8 @@ MESSAGES_PER_LONG_SUMMARY = 60
 
 [summary.model_config]
 transport = "openai"
-model = "hermes-3"
-base_url = "http://ollama:11434/v1"
+model = "deepseek/deepseek-v3-flash"
+base_url = "https://opencode.ai/zen/go/v1"
 
 # --- Dream ---
 [dream]