e0d72021e4
Routing fix: - New provider_for_model(name): a model name containing '/' is treated as an OpenRouter slug, bare names (llama3.2:3b) as Ollama. Previously the global PROVIDER variable routed all calls, so a per-agent override 'llama3.2:3b' would have hit OpenRouter and 404'd. - decide_tool now uses provider_for_model() so per-agent models route correctly regardless of global PROVIDER setting. - New provider_for_agent() helper for callers that need the provider of a specific agent. Live mix: Anchor + Flora on OpenRouter (claude-haiku, gpt-4o-mini); Lovely + Spark on Ollama (llama3.2:3b, free local). .env: - Provider set to 'auto' (uses OpenRouter when key is set) - Per-agent assignments documented in .env.example - Cost estimate updated: 2 OR + 2 Ollama = ~$0.10-0.30/day for OR portion, $0 for Ollama portion Tests: 100 passing (was 99). New test_provider_for_model() covers the routing heuristic. Existing tests updated to pass model=... explicitly so they don't depend on env-loaded .env overrides.
38 lines
1.2 KiB
Text
38 lines
1.2 KiB
Text
# Emergence-Mini environment configuration
|
|
# COPY this file to .env and fill in your own values.
|
|
# .env is git-ignored; do not commit secrets.
|
|
|
|
# === LLM PROVIDER ===
|
|
# "auto" picks OpenRouter if key is set, else Ollama.
|
|
# "ollama" forces local-only. "openrouter" requires the key below.
|
|
EMERGENCE_LLM_PROVIDER=auto
|
|
|
|
# === OPENROUTER (only if EMERGENCE_LLM_PROVIDER=openrouter) ===
|
|
# Get a key at https://openrouter.ai/keys
|
|
# Free models exist but tool-use support is limited; see README.
|
|
OPENROUTER_API_KEY=
|
|
|
|
# Default OpenRouter model
|
|
EMERGENCE_OPENROUTER_MODEL=anthropic/claude-3.5-haiku
|
|
|
|
# === OLLAMA (default, free, local) ===
|
|
# Get Ollama at https://ollama.com. Pull once:
|
|
# ollama pull llama3.2:3b
|
|
EMERGENCE_OLLAMA_URL=http://127.0.0.1:11434
|
|
EMERGENCE_OLLAMA_MODEL=llama3.2:3b
|
|
|
|
# === PER-AGENT MODEL ASSIGNMENT ===
|
|
# Example: 2 cheap cloud models + 2 free local models.
|
|
# Uncomment and edit to assign models per agent.
|
|
|
|
# Cloud (cheap, good tool-use):
|
|
# EMERGENCE_AGENT_ANCHOR_MODEL=anthropic/claude-3.5-haiku
|
|
# EMERGENCE_AGENT_FLORA_MODEL=openai/gpt-4o-mini
|
|
|
|
# Local (free, requires Ollama running):
|
|
# EMERGENCE_AGENT_LOVELY_MODEL=llama3.2:3b
|
|
# EMERGENCE_AGENT_SPARK_MODEL=llama3.2:3b
|
|
|
|
# === BEHAVIOUR ===
|
|
EMERGENCE_LLM_ENABLED=1
|
|
EMERGENCE_LLM_TIMEOUT=30
|