mirror of
https://github.com/katanemo/plano.git
synced 2026-04-25 16:56:24 +02:00
4d53297c17
* feat: add passthrough_auth option for forwarding client Authorization header * fix tests * Update comment to reflect upstream forwarding * Apply suggestions from code review --------- Co-authored-by: Adil Hafeez <adil.hafeez@gmail.com> Co-authored-by: Adil Hafeez <adil@katanemo.com>
108 lines
3 KiB
YAML
108 lines
3 KiB
YAML
# Arch Gateway configuration version
|
|
version: v0.3.0
|
|
|
|
# External HTTP agents - API type is controlled by request path (/v1/responses, /v1/messages, /v1/chat/completions)
|
|
agents:
|
|
- id: weather_agent # Example agent for weather
|
|
url: http://host.docker.internal:10510
|
|
|
|
- id: flight_agent # Example agent for flights
|
|
url: http://host.docker.internal:10520
|
|
|
|
# MCP filters applied to requests/responses (e.g., input validation, query rewriting)
|
|
filters:
|
|
- id: input_guards # Example filter for input validation
|
|
url: http://host.docker.internal:10500
|
|
# type: mcp (default)
|
|
# transport: streamable-http (default)
|
|
# tool: input_guards (default - same as filter id)
|
|
|
|
# LLM provider configurations with API keys and model routing
|
|
model_providers:
|
|
- model: openai/gpt-4o
|
|
access_key: $OPENAI_API_KEY
|
|
default: true
|
|
|
|
- model: openai/gpt-4o-mini
|
|
access_key: $OPENAI_API_KEY
|
|
|
|
- model: anthropic/claude-sonnet-4-0
|
|
access_key: $ANTHROPIC_API_KEY
|
|
|
|
- model: mistral/ministral-3b-latest
|
|
access_key: $MISTRAL_API_KEY
|
|
|
|
# Example: Passthrough authentication for LiteLLM or similar proxies
|
|
# When passthrough_auth is true, client's Authorization header is forwarded
|
|
# instead of using the configured access_key
|
|
- model: openai/gpt-4o-litellm
|
|
base_url: https://litellm.example.com
|
|
passthrough_auth: true
|
|
|
|
# Model aliases - use friendly names instead of full provider model names
|
|
model_aliases:
|
|
fast-llm:
|
|
target: gpt-4o-mini
|
|
|
|
smart-llm:
|
|
target: gpt-4o
|
|
|
|
# HTTP listeners - entry points for agent routing, prompt targets, and direct LLM access
|
|
listeners:
|
|
# Agent listener for routing requests to multiple agents
|
|
- type: agent
|
|
name: travel_booking_service
|
|
port: 8001
|
|
router: plano_orchestrator_v1
|
|
address: 0.0.0.0
|
|
agents:
|
|
- id: rag_agent
|
|
description: virtual assistant for retrieval augmented generation tasks
|
|
filter_chain:
|
|
- input_guards
|
|
|
|
# Model listener for direct LLM access
|
|
- type: model
|
|
name: model_1
|
|
address: 0.0.0.0
|
|
port: 12000
|
|
|
|
# Prompt listener for function calling (for prompt_targets)
|
|
- type: prompt
|
|
name: prompt_function_listener
|
|
address: 0.0.0.0
|
|
port: 10000
|
|
# This listener is used for prompt_targets and function calling
|
|
|
|
# Reusable service endpoints
|
|
endpoints:
|
|
app_server:
|
|
endpoint: 127.0.0.1:80
|
|
connect_timeout: 0.005s
|
|
|
|
mistral_local:
|
|
endpoint: 127.0.0.1:8001
|
|
|
|
# Prompt targets for function calling and API orchestration
|
|
prompt_targets:
|
|
- name: get_current_weather
|
|
description: Get current weather at a location.
|
|
parameters:
|
|
- name: location
|
|
description: The location to get the weather for
|
|
required: true
|
|
type: string
|
|
format: City, State
|
|
- name: days
|
|
description: the number of days for the request
|
|
required: true
|
|
type: int
|
|
endpoint:
|
|
name: app_server
|
|
path: /weather
|
|
http_method: POST
|
|
|
|
# OpenTelemetry tracing configuration
|
|
tracing:
|
|
# Random sampling percentage (1-100)
|
|
random_sampling: 100
|