0016. Any LLM provider, one model per task
- Status: Accepted
- Date: 2026-11-03
Context
Self-hosters bring their own LLM key (0002) and many have a provider already chosen for them. Triage and root-cause analysis have different needs: triage should be fast, investigation thorough. Using different models also reduces shared blind spots.
Decision
- Models are named
provider:model, as in the AI SDK provider registry. Supported: Anthropic, OpenAI, Google Gemini, OpenRouter, DeepSeek, Ollama, and any OpenAI-compatible API viaSTROMBOLI_PROVIDER_<NAME>_BASE_URL. An id with a slash and no prefix (openai/gpt-5) goes through Vercel AI Gateway. - Claude is the default (
anthropic:claude-opus-5-5). - Each task picks its own model and effort:
STROMBOLI_TRIAGE_MODELuntil the mitigation is published,STROMBOLI_INVESTIGATE_MODELfor the root cause and report, both defaulting toSTROMBOLI_MODEL. The investigate model takes over the triage conversation, so it sees everything triage saw. - Two adapters: Anthropic Messages (prompt caching, effort, refusal fallbacks) and OpenAI Chat Completions for everything else (effort as
reasoning_effort). Reasoning a provider returns is sent back to it on later turns. - The model must support tool calling. Stable prompt parts come first so caching applies.
Consequences
- No vendor lock-in; users can run fully local with Ollama.
- Behaviour and quality vary by model, which makes evaluation (0019) more important.
- Switching models between tasks resets the prompt cache once.