ollama/ollama v0.33.0
Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
Key points
- Prefill restore points are now trustworthy by construction: a cancelled prefill keeps every restore point it crossed, so retries resume where they stopped instead of restarting from scratch
- Resumed prefills no longer record restore points that fail to cover what they claim; on models with recurrent layers this previously forced a request matching 46k of 47k tokens to reprocess from zero
- Disabled Claude Code's "tokens left" token-countdown system message, which Ollama moved to the front of the prompt and broke the KV cache on every request
- DeepSeek Harness launcher now falls back to npx when the global npm install fails, with Windows command-shim support
Sources (1)
- [1]ollama/ollama v0.33.0GitHub: ollama/ollama · Aug 21, 10:52 PM
Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
* Prefill restore points are now trustworthy by construction: a cancelled prefill keeps every restore point it crossed, so retries resume where they stopped instead of restarting from scratch
Extractive summary: sentences quoted from the sources.