LLMProxy.TokenPool.Server (llm_proxy v0.1.0)

Copy Markdown View Source

Manages provider tokens with rate-limit cooldowns.

Picks tokens using FNV-1a hash for cache affinity. Priority: OAuth tokens first, then API keys as fallback.

Summary

Functions

child_spec(init_arg)

Returns a specification to start this module under a supervisor.

clear_rate_limits()
mark_rate_limited(token, cooldown_ms \\ LLMProxy.Config.token_cooldown_ms())
pick_token(provider, user_id \\ "")
pick_token_by_kind(provider, kind, user_id \\ "")
start_link(opts)

Functions

child_spec(init_arg)

Returns a specification to start this module under a supervisor.

See Supervisor.

clear_rate_limits()

mark_rate_limited(token, cooldown_ms \\ LLMProxy.Config.token_cooldown_ms())

pick_token(provider, user_id \\ "")

pick_token_by_kind(provider, kind, user_id \\ "")

start_link(opts)