Skip to main content

Crate resq_ai

Crate resq_ai 

Source
Expand description

Multi-provider LLM abstraction for ResQ developer tools.

Supports Anthropic, OpenAI, and Google Gemini APIs with a unified complete() interface and cascading config resolution.

Structs§

AiConfig
AI configuration.

Enums§

Provider
Supported LLM providers.

Functions§

complete
Send a completion request to the configured provider.
estimate_tokens
Estimate token count using the chars/4 heuristic.
load_config
Load config with cascade: env vars -> ~/.resq/ai.toml -> .resq/ai.toml.
truncate_to_budget
Truncate text to fit within a token budget. Cuts at line boundaries to avoid broken diff hunks.