提供商管理

# ~/.librefang/providers/my-endpoint.toml
id = "my-endpoint"
display_name = "My Private Endpoint"
driver = "openai_compatible"
base_url = "https://llm.internal.company.com/v1"
api_key_env = "MY_ENDPOINT_KEY"
key_required = true

[[models]]
id = "my-model-7b"
display_name = "My Model 7B"
tier = "Balanced"
context_window = 32768
max_output_tokens = 4096
input_cost_per_m = 0.0
output_cost_per_m = 0.0
supports_tools = true
supports_vision = false

# config.toml
[provider_urls]
volcengine = "https://open.volcengineapi.com/v1"
tongyi     = "https://dashscope.aliyuncs.com/compatible-mode/v1"

export VOLCENGINE_API_KEY="sk-..."
export TONGYI_API_KEY="sk-..."

# 在提供商的注册表 TOML 中：
[provider.regions.intl]
base_url = "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"

[provider.regions.china]
base_url = "https://api.minimaxi.com/v1"
api_key_env = "MINIMAX_CN_API_KEY"    # 可选：覆盖默认的 API 密钥环境变量

[provider_regions]
qwen = "intl"
minimax = "china"

# 全局默认模型
[agents.defaults]
model = "claude-sonnet-4-20250514"

# 逐 Agent 覆盖：使用别名或完整模型 ID
[[agents]]
name = "orchestrator"
model = "opus"                      # claude-opus-4-20250514 的别名

[[agents]]
name = "ops"
model = "llama-3.3-70b-versatile"   # 便宜的 Groq 模型，用于简单运维

[[agents]]
name = "coder"
model = "gemini-2.5-flash"          # 快速 + 便宜 + 100 万上下文

[[agents]]
name = "researcher"
model = "sonar-pro"                 # Perplexity，内置网页搜索

# 也可以在 agent manifest TOML 中固定模型
[[agents]]
name = "production-bot"
pinned_model = "claude-sonnet-4-20250514"  # 永不自动路由

# 在 agent manifest 文件中
[routing]
simple_model = "claude-haiku-4-5-20251001"
medium_model = "gemini-2.5-flash"
complex_model = "claude-sonnet-4-20250514"
simple_threshold = 100
complex_threshold = 500

cost = (input_tokens / 1,000,000) * input_rate + (output_tokens / 1,000,000) * output_rate

# config.toml 中的逐 Agent 配额
[[agents]]
name = "chatbot"
[agents.resources]
max_cost_per_hour_usd = 5.00   # 每小时上限 $5

> Cost: $0.0042 | Tokens: 1,200 in / 340 out | Model: claude-sonnet-4-20250514

# 示例：主用 Anthropic，后备 Gemini，然后 Groq
[[agents]]
name = "production-bot"
model = "claude-sonnet-4-20250514"
fallback_models = ["gemini-2.5-flash", "llama-3.3-70b-versatile"]

GET /api/models

[
  {
    "id": "claude-sonnet-4-20250514",
    "display_name": "Claude Sonnet 4",
    "provider": "anthropic",
    "tier": "Smart",
    "context_window": 200000,
    "max_output_tokens": 64000,
    "input_cost_per_m": 3.0,
    "output_cost_per_m": 15.0,
    "supports_tools": true,
    "supports_vision": true,
    "supports_streaming": true,
    "aliases": ["sonnet", "claude-sonnet"]
  }
]

GET /api/models/{id}

GET /api/models/sonnet
GET /api/models/claude-sonnet-4-20250514

GET /api/models/aliases

{
  "sonnet": "claude-sonnet-4-20250514",
  "haiku": "claude-haiku-4-5-20251001",
  "flash": "gemini-2.5-flash",
  "grok": "grok-2"
}

GET /api/providers

[
  {
    "id": "anthropic",
    "display_name": "Anthropic",
    "api_key_env": "ANTHROPIC_API_KEY",
    "base_url": "https://api.anthropic.com",
    "key_required": true,
    "auth_status": "Configured",
    "model_count": 3
  },
  {
    "id": "ollama",
    "display_name": "Ollama",
    "api_key_env": "OLLAMA_API_KEY",
    "base_url": "http://localhost:11434/v1",
    "key_required": false,
    "auth_status": "NotRequired",
    "model_count": 5
  }
]

POST /api/providers/{name}/key
Content-Type: application/json

{ "api_key": "sk-..." }

DELETE /api/providers/{name}/key

POST /api/providers/{name}/test

/models

Available models (12):

Frontier:
  claude-opus-4-20250514 (Anthropic) — 200K ctx
  gemini-2.5-pro (Google Gemini) — 1M ctx

Smart:
  claude-sonnet-4-20250514 (Anthropic) — 200K ctx
  gemini-2.5-flash (Google Gemini) — 1M ctx
  deepseek-chat (DeepSeek) — 64K ctx

Balanced:
  llama-3.3-70b-versatile (Groq) — 128K ctx

Fast:
  claude-haiku-4-5-20251001 (Anthropic) — 200K ctx
  gemini-2.0-flash (Google Gemini) — 1M ctx

Local:
  llama3.2 (Ollama) — 128K ctx

/providers

LLM Providers (49):

  Anthropic          ANTHROPIC_API_KEY       Configured    3 models
  OpenAI             OPENAI_API_KEY          Missing       6 models
  Google Gemini      GEMINI_API_KEY          Configured    3 models
  DeepSeek           DEEPSEEK_API_KEY        Missing       2 models
  Groq               GROQ_API_KEY            Configured    4 models
  Ollama             (no key needed)         Ready         3 models
  vLLM               (no key needed)         Ready         1 model
  LM Studio          (no key needed)         Ready         1 model
  ...

[[providers.fallback_chain]]
name = "anthropic"
model = "claude-sonnet-4-5"

[[providers.fallback_chain]]
name = "openai"
model = "gpt-4o"

[[providers.fallback_chain]]
name = "openai-compatible"
base_url = "http://localhost:11434/v1"
model = "llama3.1:8b"

[providers.anthropic]
rotation_strategy = "round_robin"  # fill_first | round_robin | random | least_used

[[providers.anthropic.keys]]
key = "sk-ant-key-1"

[[providers.anthropic.keys]]
key = "sk-ant-key-2"

[[providers.anthropic.keys]]
key = "sk-ant-key-3"

anthropic  [████████░░░░░░░░░░░░]  req: 847/1000  tok: 42.3K/90K
openai     [██████████████░░░░░░]  req: 712/1000  tok: 61.1K/90K

# Current rate-limit snapshot for all providers
curl http://127.0.0.1:4545/api/providers/rate-limits

{
  "anthropic": {
    "requests": { "limit": 1000, "remaining": 153, "reset_in_seconds": 34 },
    "tokens":   { "limit": 90000, "remaining": 47700, "reset_in_seconds": 34 }
  }
}