55f8e0fe6e
- RoutingEngine with RouteDecision (model_pattern → provider) - config/routing.toml: rules, fallback chain, cost gating - Per-provider Usage tracking in /v1/usage response - 12 gateway tests green
61 lines
1.0 KiB
TOML
61 lines
1.0 KiB
TOML
# Phase 40: Routing Engine Configuration
|
|
#
|
|
# Human-editable rules for model → provider routing.
|
|
# Matching order: first match wins.
|
|
|
|
[[rule]]
|
|
model_pattern = "gpt-4*"
|
|
provider = "openrouter"
|
|
max_tokens = 4096
|
|
temperature = 0.7
|
|
|
|
[[rule]]
|
|
model_pattern = "claude*"
|
|
provider = "claude"
|
|
max_tokens = 4096
|
|
temperature = 0.7
|
|
|
|
[[rule]]
|
|
model_pattern = "gemini*"
|
|
provider = "gemini"
|
|
max_tokens = 8192
|
|
temperature = 0.9
|
|
|
|
[[rule]]
|
|
model_pattern = "qwen3.5*"
|
|
provider = "ollama"
|
|
max_tokens = 4096
|
|
temperature = 0.3
|
|
|
|
[[rule]]
|
|
model_pattern = "qwen3*"
|
|
provider = "ollama"
|
|
max_tokens = 2048
|
|
temperature = 0.3
|
|
|
|
[[rule]]
|
|
model_pattern = "gpt-oss*"
|
|
provider = "ollama"
|
|
temperature = 0.1
|
|
|
|
[[rule]]
|
|
model_pattern = "*"
|
|
provider = "ollama"
|
|
temperature = 0.5
|
|
|
|
# Fallback chain: if primary fails, try these in order
|
|
fallback = ["ollama", "openrouter"]
|
|
|
|
# Cost gating (tokens = cents per 1M)
|
|
[cost]
|
|
ollama = 0
|
|
openrouter = 15
|
|
claude = 15
|
|
gemini = 0
|
|
|
|
# Daily budget per provider (cents)
|
|
[daily_budget]
|
|
ollama = 0
|
|
openrouter = 1000
|
|
claude = 500
|
|
gemini = 0 |