mirror of
https://github.com/katanemo/plano.git
synced 2026-04-27 09:46:28 +02:00
f00870dccb
* fixed for claude code routing. first commit * removing redundant enum tags for cache_control * making sure that claude code can run via the archgw cli * fixing broken config * adding a README.md and updated the cli to use more of our defined patterns for params * fixed config.yaml * minor fixes to make sure PR is clean. Ready to ship * adding claude-sonnet-4-5 to the config * fixes based on PR * fixed alias for README * fixed 400 error handling tests, now that we write temperature to 1.0 for GPT-5 --------- Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-257.local> Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local>
41 lines
1.1 KiB
YAML
41 lines
1.1 KiB
YAML
version: v0.1
|
|
|
|
listeners:
|
|
egress_traffic:
|
|
address: 0.0.0.0
|
|
port: 12000
|
|
message_format: openai
|
|
timeout: 30s
|
|
|
|
llm_providers:
|
|
# OpenAI Models
|
|
- model: openai/gpt-5-2025-08-07
|
|
access_key: $OPENAI_API_KEY
|
|
routing_preferences:
|
|
- name: code generation
|
|
description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
|
|
|
|
- model: openai/gpt-4.1-2025-04-14
|
|
access_key: $OPENAI_API_KEY
|
|
routing_preferences:
|
|
- name: code understanding
|
|
description: understand and explain existing code snippets, functions, or libraries
|
|
|
|
# Anthropic Models
|
|
- model: anthropic/claude-sonnet-4-5
|
|
default: true
|
|
access_key: $ANTHROPIC_API_KEY
|
|
|
|
- model: anthropic/claude-3-haiku-20240307
|
|
access_key: $ANTHROPIC_API_KEY
|
|
|
|
# Ollama Models
|
|
- model: ollama/llama3.1
|
|
base_url: http://host.docker.internal:11434
|
|
|
|
|
|
# Model aliases - friendly names that map to actual provider names
|
|
model_aliases:
|
|
# Alias for a small faster Claude model
|
|
arch.claude.code.small.fast:
|
|
target: claude-3-haiku-20240307
|