feat(ai-models): ADR-110 GCP-A Primary + 全任務模型升級 (v1.4.0)
Some checks failed
Code Review / ai-code-review (push) Failing after 18s
Some checks failed
Code Review / ai-code-review (push) Failing after 18s
models.json v1.3.0 → v1.4.0: - endpoint: 192.168.0.111 → GCP-A 34.143.170.20:11434 (ADR-110) - rca/drift_summary/playbook_draft/rag_generate: qwen2.5:7b → qwen3:14b - code_review: qwen2.5-coder:7b → qwen2.5-coder:32b (GCP SSD) - embedding: nomic-embed-text → bge-m3:latest (多語言更佳) - image_analysis: llava → minicpm-v:latest - 新增: trust_scoring/alert_triage/intent_classify/governance 四任務 config.py: - OLLAMA_REQUIRED_MODELS: 新增 qwen3:14b + hermes3:latest - OLLAMA_TOOL_MODEL: llama3.1:8b → hermes3:latest - OPENCLAW_DEFAULT_MODEL: qwen2.5:7b-instruct → qwen3:14b 111 背景安裝 minicpm-v + qwen3:14b (fallback 補齊) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -1,9 +1,9 @@
|
||||
{
|
||||
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||
"name": "OpenClaw AI Router Configuration",
|
||||
"version": "1.3.0",
|
||||
"description": "AI 模型路由與備援設定 (ADR-006 + ADR-036 Nemotron + D1 ADR-067 五大應用 2026-04-11)",
|
||||
"updated_at": "2026-04-11",
|
||||
"version": "1.4.0",
|
||||
"description": "AI 模型路由與備援設定 (ADR-006 + ADR-036 Nemotron + D1 ADR-067 五大應用 2026-04-11 + ADR-110 GCP 三層容災 2026-05-04)",
|
||||
"updated_at": "2026-05-04",
|
||||
|
||||
"default_provider": "ollama",
|
||||
"fallback_order": ["ollama", "gemini", "claude"],
|
||||
@@ -11,24 +11,28 @@
|
||||
|
||||
"providers": {
|
||||
"ollama": {
|
||||
"name": "Ollama (Local M1 Pro)",
|
||||
"name": "Ollama (GCP-A Primary)",
|
||||
"enabled": true,
|
||||
"priority": 1,
|
||||
"endpoint": "http://192.168.0.111:11434",
|
||||
"endpoint": "http://34.143.170.20:11434",
|
||||
"api_path": "/api/generate",
|
||||
"models": {
|
||||
"default": "qwen2.5:7b-instruct",
|
||||
"rca": "qwen2.5:7b-instruct",
|
||||
"rca": "qwen3:14b",
|
||||
"summary": "gemma3:4b",
|
||||
"drift_summary": "qwen2.5:7b-instruct",
|
||||
"drift_summary": "qwen3:14b",
|
||||
"drift_intent": "qwen2.5:7b-instruct",
|
||||
"log_anomaly": "deepseek-r1:14b",
|
||||
"nemoclaw": "deepseek-r1:14b",
|
||||
"playbook_draft": "qwen2.5:7b-instruct",
|
||||
"code_review": "qwen2.5-coder:7b",
|
||||
"embedding": "nomic-embed-text",
|
||||
"rag_generate": "qwen2.5:7b-instruct",
|
||||
"image_analysis": "llava:latest"
|
||||
"playbook_draft": "qwen3:14b",
|
||||
"code_review": "qwen2.5-coder:32b",
|
||||
"embedding": "bge-m3:latest",
|
||||
"rag_generate": "qwen3:14b",
|
||||
"image_analysis": "minicpm-v:latest",
|
||||
"trust_scoring": "hermes3:latest",
|
||||
"alert_triage": "hermes3:latest",
|
||||
"intent_classify": "qwen2.5:7b-instruct",
|
||||
"governance": "deepseek-r1:14b"
|
||||
},
|
||||
"options": {
|
||||
"temperature": 0.1,
|
||||
@@ -154,12 +158,12 @@
|
||||
},
|
||||
|
||||
"adr067_ollama_applications": {
|
||||
"description": "ADR-067 五大 Ollama 本地 AI 應用 (Phase 30-34),endpoint: http://192.168.0.111:11434",
|
||||
"endpoint": "http://192.168.0.111:11434",
|
||||
"description": "ADR-067 五大 Ollama 本地 AI 應用 (Phase 30-34),2026-05-04 ogt + Claude Sonnet 4.6: endpoint 升級至 GCP-A Primary",
|
||||
"endpoint": "http://34.143.170.20:11434",
|
||||
"applications": {
|
||||
"drift_summary": {
|
||||
"phase": 30,
|
||||
"model": "qwen2.5:7b-instruct",
|
||||
"model": "qwen3:14b",
|
||||
"timeout_seconds": 90,
|
||||
"purpose": "Config Drift 報告中文摘要"
|
||||
},
|
||||
@@ -171,28 +175,28 @@
|
||||
},
|
||||
"pr_code_review": {
|
||||
"phase": 32,
|
||||
"model": "qwen2.5-coder:7b",
|
||||
"model": "qwen2.5-coder:32b",
|
||||
"timeout_seconds": 120,
|
||||
"purpose": "Gitea PR 自動審查"
|
||||
},
|
||||
"rag_embed": {
|
||||
"phase": 33,
|
||||
"model": "nomic-embed-text",
|
||||
"dimensions": 768,
|
||||
"model": "bge-m3:latest",
|
||||
"dimensions": 1024,
|
||||
"timeout_seconds": 30,
|
||||
"purpose": "RAG 知識庫向量化,pgvector 儲存"
|
||||
"purpose": "RAG 知識庫向量化,pgvector 儲存(bge-m3 多語言 1024 維)"
|
||||
},
|
||||
"rag_generate": {
|
||||
"phase": 33,
|
||||
"model": "qwen2.5:7b-instruct",
|
||||
"model": "qwen3:14b",
|
||||
"timeout_seconds": 60,
|
||||
"purpose": "RAG 查詢回答生成,top_k=5"
|
||||
},
|
||||
"image_analysis": {
|
||||
"phase": 34,
|
||||
"model": "llava:latest",
|
||||
"model": "minicpm-v:latest",
|
||||
"timeout_seconds": 60,
|
||||
"purpose": "Telegram 圖片分析"
|
||||
"purpose": "Telegram 圖片分析(minicpm-v 多模態精度優於 llava)"
|
||||
}
|
||||
}
|
||||
},
|
||||
|
||||
@@ -376,8 +376,9 @@ class Settings(BaseSettings):
|
||||
description="OllamaHealthMonitor 推理測試使用模型(P1.1)",
|
||||
)
|
||||
# 2026-04-12 ogt: 心跳必須確認載入的 Ollama 模型清單
|
||||
# 2026-05-04 ogt + Claude Sonnet 4.6: ADR-110 GCP 升級,更新必要模型清單(nomic→bge-m3 + 新增 qwen3:14b + hermes3)
|
||||
OLLAMA_REQUIRED_MODELS: list[str] = Field(
|
||||
default=["nomic-embed-text", "qwen2.5:7b-instruct", "deepseek-r1:14b"],
|
||||
default=["bge-m3:latest", "qwen2.5:7b-instruct", "qwen3:14b", "deepseek-r1:14b", "hermes3:latest"],
|
||||
description="HeartbeatReportService 探測必要模型是否載入",
|
||||
)
|
||||
# 2026-04-25 critic-fix Part2 H7 by Claude Engineer-C2
|
||||
@@ -492,8 +493,9 @@ class Settings(BaseSettings):
|
||||
default=True,
|
||||
description="使用 Ollama 本機做 Tool Calling,取代 NVIDIA NIM 雲端 (44s→5s)",
|
||||
)
|
||||
# 2026-05-04 ogt + Claude Sonnet 4.6: ADR-110 GCP 升級,改 hermes3:latest(工具調用能力優於 llama3.1:8b)
|
||||
OLLAMA_TOOL_MODEL: str = Field(
|
||||
default="llama3.1:8b",
|
||||
default="hermes3:latest",
|
||||
description="Ollama Tool Calling 模型 (支援 function calling 格式)",
|
||||
)
|
||||
|
||||
@@ -571,8 +573,9 @@ class Settings(BaseSettings):
|
||||
default="http://192.168.0.188:8088", # 🔧 修正: OpenClaw 實際 port 是 8088
|
||||
description="OpenClaw AI Agent service URL",
|
||||
)
|
||||
# 2026-05-04 ogt + Claude Sonnet 4.6: ADR-110 GCP 升級,改 qwen3:14b(GCP-A SSD 算力,RCA 推理更強)
|
||||
OPENCLAW_DEFAULT_MODEL: str = Field(
|
||||
default="qwen2.5:7b-instruct", # 2026-04-30: DIAGNOSE/RCA 優先低延遲本地模型
|
||||
default="qwen3:14b",
|
||||
description="Default Ollama model for RCA analysis",
|
||||
)
|
||||
OPENCLAW_TIMEOUT: int = Field(
|
||||
|
||||
Reference in New Issue
Block a user