Fixed
- Goose launch wrote a hardcoded 128k context limit — when launching a model into Goose with
--goose(or via the TUI Enter flow), the generated~/.config/goose/custom_providers/fcm-<provider>.jsonalways setcontext_limit: 128000, ignoring the model's real context window. Models with larger contexts (e.g. MiniMax M3, 1M) were silently capped at 128k, and free-tier models with smaller limits (e.g. Cerebras 64-65k) were advertised above what the API actually allows. The launcher now uses the sameparseContextWindow(model.ctx)logic as the Install Endpoints flow, so the context limit always matches the catalog value. (Fixes GitHub issue #153) - Stale Cerebras context references in docs — README.md, packages/fcm-pi/README.md, and the Pi integration docs claimed Cerebras free tier has an "~8k total token limit". Per the official Cerebras Inference docs the free tier now caps context at ~64-65k (paid tier gets 131k). Docs updated to match.
Changed
parseContextWindowis now exported fromsrc/core/endpoint-installer.jsso the Goose launcher (src/core/tool-launchers.js) and the Install Endpoints flow share the same single source of truth for context parsing.
Tests
- 797/797 tests passing, including a new regression assertion that a 1M-context model launched into Goose produces
context_limit: 1000000in the generated provider file.