Skip to content

Llm Call

Make a single LLM API call (Tier 2 execution). Cheaper than spawning a full agent session. Supports freeform text or structured JSON output via output_schema (inline dict or named schema from work_buddy/llm/schemas/). Handles caching, cost tracking, and model tier selection automatically.

MCP name: llm_call

Category: llm

Parameters

Name Type Required Description
cache_ttl_minutes int No Cache TTL in minutes. None=config default, 0=no cache.
max_tokens int No Max response tokens (default: 1024)
output_schema dict|str No JSON Schema for structured output. Pass a dict for inline schemas, or a string name to load from work_buddy/llm/schemas/.json. Omit for freeform text.
system str Yes System prompt
temperature float No Sampling temperature (default: 0.0)
tier str No Model tier: 'haiku' (default, cheapest), 'sonnet', or 'opus'
user str Yes User message content