mirror of
https://github.com/katanemo/plano.git
synced 2026-06-17 15:25:17 +02:00
deploy: 4d53297c17
This commit is contained in:
salmanap
parent
be238fcaef
commit
670388c0bb
6 changed files with 233 additions and 106 deletions
|
|
@ -1,6 +1,6 @@
|
|||
Plano Docs v0.4.2
|
||||
llms.txt (auto-generated)
|
||||
Generated (UTC): 2026-01-14T19:37:47.390683+00:00
|
||||
Generated (UTC): 2026-01-14T23:06:59.315217+00:00
|
||||
|
||||
Table of contents
|
||||
- Agents (concepts/agents)
|
||||
|
|
@ -1956,6 +1956,76 @@ llm_providers:
|
|||
- name: creative_writing
|
||||
description: creative content generation, storytelling, and writing assistance
|
||||
|
||||
|
||||
|
||||
Passthrough Authentication
|
||||
|
||||
When deploying Plano in front of LLM proxy services that manage their own API key validation (such as LiteLLM, OpenRouter, or custom gateways), you may want to forward the client’s original Authorization header instead of replacing it with a configured access_key.
|
||||
|
||||
The passthrough_auth option enables this behavior:
|
||||
|
||||
llm_providers:
|
||||
# Forward client's Authorization header to LiteLLM
|
||||
- model: openai/gpt-4o-litellm
|
||||
base_url: https://litellm.example.com
|
||||
passthrough_auth: true
|
||||
default: true
|
||||
|
||||
# Forward to OpenRouter
|
||||
- model: openai/claude-3-opus
|
||||
base_url: https://openrouter.ai/api/v1
|
||||
passthrough_auth: true
|
||||
|
||||
How it works:
|
||||
|
||||
Client sends a request with Authorization: Bearer <virtual-key>
|
||||
|
||||
Plano preserves this header instead of replacing it with access_key
|
||||
|
||||
The upstream service (e.g., LiteLLM) validates the virtual key
|
||||
|
||||
Response flows back through Plano to the client
|
||||
|
||||
Use Cases:
|
||||
|
||||
LiteLLM Integration: Route requests to LiteLLM which manages virtual keys and rate limits
|
||||
|
||||
OpenRouter: Forward requests to OpenRouter with per-user API keys
|
||||
|
||||
Custom API Gateways: Integrate with internal gateways that have their own authentication
|
||||
|
||||
Multi-tenant Deployments: Allow different clients to use their own credentials
|
||||
|
||||
Important Notes:
|
||||
|
||||
When passthrough_auth: true is set, the access_key field is ignored (a warning is logged if both are configured)
|
||||
|
||||
If the client doesn’t provide an Authorization header, the request is forwarded without authentication (upstream will likely return 401)
|
||||
|
||||
The base_url is typically required when using passthrough_auth
|
||||
|
||||
Configuration with LiteLLM example:
|
||||
|
||||
# plano_config.yaml
|
||||
version: v0.3.0
|
||||
|
||||
listeners:
|
||||
- name: llm
|
||||
type: model
|
||||
port: 10000
|
||||
|
||||
model_providers:
|
||||
- model: openai/gpt-4o
|
||||
base_url: https://litellm.example.com
|
||||
passthrough_auth: true
|
||||
default: true
|
||||
|
||||
# Client request - virtual key is forwarded to upstream
|
||||
curl http://localhost:10000/v1/chat/completions \
|
||||
-H "Authorization: Bearer sk-litellm-virtual-key-abc123" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello"}]}'
|
||||
|
||||
Model Selection Guidelines
|
||||
|
||||
For Production Applications:
|
||||
|
|
@ -5424,29 +5494,25 @@ where prompts get routed to, apply guardrails, and enable critical agent observa
|
|||
|
||||
Plano Configuration - Full Reference
|
||||
|
||||
|
||||
# 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
|
||||
- id: weather_agent # Example agent for weather
|
||||
url: http://host.docker.internal:10510
|
||||
|
||||
- id: flight_agent # Example agent for flights
|
||||
- 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
|
||||
- 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
|
||||
|
|
@ -5462,6 +5528,12 @@ model_providers:
|
|||
- 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:
|
||||
|
|
@ -5471,7 +5543,6 @@ model_aliases:
|
|||
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
|
||||
|
|
@ -5499,7 +5570,6 @@ listeners:
|
|||
port: 10000
|
||||
# This listener is used for prompt_targets and function calling
|
||||
|
||||
|
||||
# Reusable service endpoints
|
||||
endpoints:
|
||||
app_server:
|
||||
|
|
@ -5509,7 +5579,6 @@ endpoints:
|
|||
mistral_local:
|
||||
endpoint: 127.0.0.1:8001
|
||||
|
||||
|
||||
# Prompt targets for function calling and API orchestration
|
||||
prompt_targets:
|
||||
- name: get_current_weather
|
||||
|
|
@ -5529,7 +5598,6 @@ prompt_targets:
|
|||
path: /weather
|
||||
http_method: POST
|
||||
|
||||
|
||||
# OpenTelemetry tracing configuration
|
||||
tracing:
|
||||
# Random sampling percentage (1-100)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue