Impact Score: 5/10
Ollama v0.40.7 — Release Notes & Engineering Impact
Source available — automated, not human-reviewed
Component: ollama · Channel: stable. Automated analysis, not a compatibility certification. How this works.
Analysis updated: 2026-11-01.
⚡ Executive Summary (TL;DR)
Ollama v0.40.7. Source highlight: pplx-decider is a 27B decision model from Perplexity, fine-tuned from
Who Does This Impact? (Role-Based Analysis)
💻 Software Engineers & Devs
Check the source notes against the package and APIs you use before upgrading.
📊 Product & Engineering Leads
Use the documented changes to assess relevance to your product; release frequency alone is not a quality measure.
⚙️ DevOps & Security
Verify the target version, runtime requirements and rollback procedure in the official documentation.
🔧 Bug Fixes & Patches (1)
- Fixed streaming Responses requests where client tool calls (e.g. Codex with web search) could emit before open
📄 View Raw Release Notes (Original Developer Log)
## What's Changed
* [pplx-decider](https://ollama.com/library/pplx-decider) is a 27B decision model from Perplexity, fine-tuned from
Qwen3.8-27B
* Continuing an OpenAI-compatible Responses conversation no longer fails when switching between models with and without
thinking, or when the history contains another provider's compaction items
* Fixed streaming Responses requests where client tool calls (e.g. Codex with web search) could emit before open
reasoning items, producing misordered/duplicate tool call events
* Requests routed to remote models are now cancelled on ollama.com when the client disconnects, instead of continuing
to run
* `ollama show` now reports which renderer and parser a model uses and where its chat template comes from; the API
exposes the same values in new `renderer`, `parser`, and `template_source` fields
* More draft models now work with speculative decoding: llama-server infers the draft type automatically instead of
requiring Ollama to identify it
* `ollama launch claude` now clamps `CLAUDE_CODE_AUTO_COMPACT_WINDOW` to Claude Code's supported range, avoiding a
"window too large" warning
* Updated llama.cpp and MLX
**Full Changelog**: https://github.com/ollama/ollama/compare/v0.40.6...v0.40.7