f9618a9bbf
- Add Bifrost (maximhq/bifrost) as LLM gateway: all inference routes through bifrost:8080/v1 with retry logic and observability; VRAMManager keeps direct Ollama access for VRAM flush/prewarm operations - Switch medium model from qwen3:4b to qwen2.5:1.5b (direct call, no tools) via _DirectModel wrapper; complex keeps create_deep_agent with qwen3:8b - Implement out-of-agent memory pipeline: _retrieve_memories pre-fetches relevant context (injected into all tiers), _store_memory runs as background task after each reply writing to openmemory/Qdrant - Add tests/unit/ with 133 tests covering router, channels, vram_manager, agent helpers; move integration test to tests/integration/ - Add bifrost-config.json with GPU Ollama (qwen2.5:0.5b/1.5b, qwen3:4b/8b, gemma3:4b) and CPU Ollama providers - Integration test 28/29 pass (only grammy fails — no TELEGRAM_BOT_TOKEN) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
59 lines
1.3 KiB
JSON
59 lines
1.3 KiB
JSON
{
|
|
"client": {
|
|
"drop_excess_requests": false
|
|
},
|
|
"providers": {
|
|
"ollama": {
|
|
"keys": [
|
|
{
|
|
"name": "ollama-gpu",
|
|
"value": "dummy",
|
|
"models": [
|
|
"qwen2.5:0.5b",
|
|
"qwen2.5:1.5b",
|
|
"qwen3:4b",
|
|
"gemma3:4b",
|
|
"qwen3:8b"
|
|
],
|
|
"weight": 1.0
|
|
}
|
|
],
|
|
"network_config": {
|
|
"base_url": "http://host.docker.internal:11436",
|
|
"default_request_timeout_in_seconds": 300,
|
|
"max_retries": 2,
|
|
"retry_backoff_initial_ms": 500,
|
|
"retry_backoff_max_ms": 10000
|
|
}
|
|
},
|
|
"ollama-cpu": {
|
|
"keys": [
|
|
{
|
|
"name": "ollama-cpu-key",
|
|
"value": "dummy",
|
|
"models": [
|
|
"gemma3:1b",
|
|
"qwen2.5:1.5b",
|
|
"qwen2.5:3b"
|
|
],
|
|
"weight": 1.0
|
|
}
|
|
],
|
|
"network_config": {
|
|
"base_url": "http://host.docker.internal:11435",
|
|
"default_request_timeout_in_seconds": 120,
|
|
"max_retries": 2,
|
|
"retry_backoff_initial_ms": 500,
|
|
"retry_backoff_max_ms": 10000
|
|
},
|
|
"custom_provider_config": {
|
|
"base_provider_type": "openai",
|
|
"allowed_requests": {
|
|
"chat_completion": true,
|
|
"chat_completion_stream": true
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|