resolve: merge main into crucible branch — keep config base + add Z3 sidecar
Resolved 3 conflicts: - config.yaml: kept main's llama.cpp/fallback_model + added Crucible system prompt and MCP server - README.md: kept main's clean bin/ listing + added crucible_mcp_server.py and docs - deploy.sh: kept PR's extended deploy flags (--restart-gateway) + Z3 dependency check Signed-off-by: gemini <gemini@hermes.local>
This commit is contained in:
155
config.yaml
155
config.yaml
@@ -1,16 +1,19 @@
|
||||
model:
|
||||
default: claude-opus-4-6
|
||||
provider: anthropic
|
||||
default: hermes4:14b
|
||||
provider: custom
|
||||
context_length: 65536
|
||||
base_url: http://localhost:8081/v1
|
||||
toolsets:
|
||||
- all
|
||||
agent:
|
||||
max_turns: 30
|
||||
reasoning_effort: medium
|
||||
reasoning_effort: xhigh
|
||||
verbose: false
|
||||
terminal:
|
||||
backend: local
|
||||
cwd: .
|
||||
timeout: 180
|
||||
env_passthrough: []
|
||||
docker_image: nikolaik/python-nodejs:python3.11-nodejs20
|
||||
docker_forward_env: []
|
||||
singularity_image: docker://nikolaik/python-nodejs:python3.11-nodejs20
|
||||
@@ -25,76 +28,81 @@ terminal:
|
||||
persistent_shell: true
|
||||
browser:
|
||||
inactivity_timeout: 120
|
||||
command_timeout: 30
|
||||
record_sessions: false
|
||||
checkpoints:
|
||||
enabled: true
|
||||
max_snapshots: 50
|
||||
compression:
|
||||
enabled: true
|
||||
enabled: false
|
||||
threshold: 0.5
|
||||
summary_model: qwen3:30b
|
||||
summary_provider: custom
|
||||
summary_base_url: http://localhost:11434/v1
|
||||
target_ratio: 0.2
|
||||
protect_last_n: 20
|
||||
summary_model: ''
|
||||
summary_provider: ''
|
||||
summary_base_url: ''
|
||||
smart_model_routing:
|
||||
enabled: true
|
||||
enabled: false
|
||||
max_simple_chars: 200
|
||||
max_simple_words: 35
|
||||
cheap_model:
|
||||
provider: custom
|
||||
model: qwen3:30b
|
||||
base_url: http://localhost:11434/v1
|
||||
api_key: ollama
|
||||
provider: ''
|
||||
model: ''
|
||||
base_url: ''
|
||||
api_key: ''
|
||||
auxiliary:
|
||||
vision:
|
||||
provider: custom
|
||||
model: qwen3:30b
|
||||
base_url: http://localhost:11434/v1
|
||||
api_key: ollama
|
||||
provider: auto
|
||||
model: ''
|
||||
base_url: ''
|
||||
api_key: ''
|
||||
timeout: 30
|
||||
web_extract:
|
||||
provider: custom
|
||||
model: qwen3:30b
|
||||
base_url: http://localhost:11434/v1
|
||||
api_key: ollama
|
||||
provider: auto
|
||||
model: ''
|
||||
base_url: ''
|
||||
api_key: ''
|
||||
compression:
|
||||
provider: custom
|
||||
model: qwen3:30b
|
||||
base_url: http://localhost:11434/v1
|
||||
api_key: ollama
|
||||
provider: auto
|
||||
model: ''
|
||||
base_url: ''
|
||||
api_key: ''
|
||||
session_search:
|
||||
provider: custom
|
||||
model: qwen3:30b
|
||||
base_url: http://localhost:11434/v1
|
||||
api_key: ollama
|
||||
provider: auto
|
||||
model: ''
|
||||
base_url: ''
|
||||
api_key: ''
|
||||
skills_hub:
|
||||
provider: custom
|
||||
model: qwen3:30b
|
||||
base_url: http://localhost:11434/v1
|
||||
api_key: ollama
|
||||
provider: auto
|
||||
model: ''
|
||||
base_url: ''
|
||||
api_key: ''
|
||||
approval:
|
||||
provider: auto
|
||||
model: ''
|
||||
base_url: ''
|
||||
api_key: ''
|
||||
mcp:
|
||||
provider: custom
|
||||
model: qwen3:30b
|
||||
base_url: http://localhost:11434/v1
|
||||
api_key: ollama
|
||||
provider: auto
|
||||
model: ''
|
||||
base_url: ''
|
||||
api_key: ''
|
||||
flush_memories:
|
||||
provider: custom
|
||||
model: qwen3:30b
|
||||
base_url: http://localhost:11434/v1
|
||||
api_key: ollama
|
||||
provider: auto
|
||||
model: ''
|
||||
base_url: ''
|
||||
api_key: ''
|
||||
display:
|
||||
compact: false
|
||||
personality: ''
|
||||
resume_display: full
|
||||
busy_input_mode: interrupt
|
||||
bell_on_complete: false
|
||||
show_reasoning: false
|
||||
streaming: false
|
||||
show_cost: false
|
||||
skin: timmy
|
||||
tool_progress_command: false
|
||||
tool_progress: all
|
||||
privacy:
|
||||
redact_pii: false
|
||||
@@ -142,6 +150,7 @@ delegation:
|
||||
provider: ''
|
||||
base_url: ''
|
||||
api_key: ''
|
||||
max_iterations: 50
|
||||
prefill_messages_file: ''
|
||||
honcho: {}
|
||||
timezone: ''
|
||||
@@ -176,13 +185,17 @@ session_reset:
|
||||
mode: none
|
||||
idle_minutes: 0
|
||||
custom_providers:
|
||||
- name: Local Ollama
|
||||
base_url: http://localhost:11434/v1
|
||||
api_key: ollama
|
||||
model: glm-4.7-flash:latest
|
||||
- name: Local llama.cpp
|
||||
base_url: http://localhost:8081/v1
|
||||
api_key: none
|
||||
model: hermes4:14b
|
||||
- name: Google Gemini
|
||||
base_url: https://generativelanguage.googleapis.com/v1beta/openai
|
||||
api_key_env: GEMINI_API_KEY
|
||||
model: gemini-2.5-pro
|
||||
system_prompt_suffix: "You are Timmy. Your soul is defined in SOUL.md \u2014 read\
|
||||
\ it, live it.\nYou run locally on your owner's machine via Ollama. You never phone\
|
||||
\ home.\nYou speak plainly. You prefer short sentences. Brevity is a kindness.\n\
|
||||
\ it, live it.\nYou run locally on your owner's machine via llama.cpp. You never\
|
||||
\ phone home.\nYou speak plainly. You prefer short sentences. Brevity is a kindness.\n\
|
||||
When you don't know something, say so. Refusal over fabrication.\nFor scheduling,\
|
||||
\ dependency ordering, resource constraints, and consistency checks, prefer the\
|
||||
\ Crucible tools and report SAT/UNSAT plus witness model when available.\nSovereignty\
|
||||
@@ -194,51 +207,21 @@ providers:
|
||||
ollama:
|
||||
base_url: http://localhost:11434/v1
|
||||
model: hermes3:latest
|
||||
|
||||
# ── Fallback Model ────────────────────────────────────────────────────
|
||||
# Automatic provider failover when primary is unavailable.
|
||||
# Uncomment and configure to enable. Triggers on rate limits (429),
|
||||
# overload (529), service errors (503), or connection failures.
|
||||
#
|
||||
# Supported providers:
|
||||
# openrouter (OPENROUTER_API_KEY) — routes to any model
|
||||
# openai-codex (OAuth — hermes login) — OpenAI Codex
|
||||
# nous (OAuth — hermes login) — Nous Portal
|
||||
# zai (ZAI_API_KEY) — Z.AI / GLM
|
||||
# kimi-coding (KIMI_API_KEY) — Kimi / Moonshot
|
||||
# minimax (MINIMAX_API_KEY) — MiniMax
|
||||
# minimax-cn (MINIMAX_CN_API_KEY) — MiniMax (China)
|
||||
#
|
||||
# For custom OpenAI-compatible endpoints, add base_url and api_key_env.
|
||||
#
|
||||
# fallback_model:
|
||||
# provider: openrouter
|
||||
# model: anthropic/claude-sonnet-4
|
||||
#
|
||||
# ── Smart Model Routing ────────────────────────────────────────────────
|
||||
# Optional cheap-vs-strong routing for simple turns.
|
||||
# Keeps the primary model for complex work, but can route short/simple
|
||||
# messages to a cheaper model across providers.
|
||||
#
|
||||
# smart_model_routing:
|
||||
# enabled: true
|
||||
# max_simple_chars: 160
|
||||
# max_simple_words: 28
|
||||
# cheap_model:
|
||||
# provider: openrouter
|
||||
# model: google/gemini-2.5-flash
|
||||
|
||||
# Sovereign Orchestration MCP Server
|
||||
# Exposes: Gitea API, Task Queue, Playbook Engine
|
||||
mcp_servers:
|
||||
orchestration:
|
||||
command: "/Users/apayne/.hermes/hermes-agent/venv/bin/python3"
|
||||
args: ["/Users/apayne/.hermes/hermes-agent/tools/orchestration_mcp_server.py"]
|
||||
morrowind:
|
||||
command: python3
|
||||
args:
|
||||
- /Users/apayne/.timmy/morrowind/mcp_server.py
|
||||
env: {}
|
||||
timeout: 120
|
||||
timeout: 30
|
||||
crucible:
|
||||
command: "/Users/apayne/.hermes/hermes-agent/venv/bin/python3"
|
||||
args: ["/Users/apayne/.hermes/bin/crucible_mcp_server.py"]
|
||||
env: {}
|
||||
timeout: 120
|
||||
connect_timeout: 60
|
||||
fallback_model:
|
||||
provider: custom
|
||||
model: gemini-2.5-pro
|
||||
base_url: https://generativelanguage.googleapis.com/v1beta/openai
|
||||
api_key_env: GEMINI_API_KEY
|
||||
|
||||
Reference in New Issue
Block a user