mirror of
https://github.com/katanemo/plano.git
synced 2026-06-17 15:25:17 +02:00
5a4f8cb321
- Update all demo config files to version v0.3.0
- Rename llm_providers → model_providers across all configs
- Modernize listener format from object to array style
(e.g. listeners: [{type: model, name:, port:}])
- Replace chatbot_ui with AnythingLLM in 6 docker-compose files
- Remove prometheus/grafana services from llm_gateway and
preference_based_routing docker-compose files
- Add tracing: random_sampling: 100 to configs that lacked it
- Update 3 CLI init templates (coding_agent_routing,
preference_aware_routing, conversational_state_v1_responses)
- Fix test_init.py assertion for model_providers key
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
41 lines
1.1 KiB
YAML
41 lines
1.1 KiB
YAML
version: v0.3.0
|
|
|
|
model_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-haiku-4-5
|
|
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-haiku-4-5
|
|
|
|
listeners:
|
|
- type: model
|
|
name: model_listener
|
|
port: 12000
|
|
|
|
tracing:
|
|
random_sampling: 100
|