UNPKG

@bitkyc08/opencodex

Version:

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM with Codex CLI/App/SDK and Claude Code

8 lines (7 loc) • 515 B
/** Proxy-owned refusal text for an exhausted late-attribution budget. A compaction on the same * Ollama route resends the same history, so the only reliable recovery is a new thread. * * Kept in its own module so combo failover can recognize this proxy-owned 413 without pulling * the Ollama adapter into its import graph. */ export const OLLAMA_LATE_ATTRIBUTION_LIMIT_MESSAGE = "Late tool-output attribution for this conversation exceeded the 256 KiB per-request limit. Start a new thread to continue.";