
Ollama version 0.35 introduces support for Jev-style decision models through a new /v1/systemone endpoint, allowing local execution of structured queries via the TypeSafe API. The update includes three initial models: Bespoke Lab’s nimble (9B), Together AI’s teev1 (4B), and teev1:0.8b (0.8B). These models are optimized for low-latency tasks such as ticket triage and content moderation, with nimble achieving 91ms response times on M5 Max hardware. The feature enables developers to send state and named questions in a single request, receiving typed outputs like choices, scores, or boolean flags.
Read originalAnthropic quietly upgrades its local coding agent with Sonnet 5.5 as the new default, bringing a massive 1M context window to developers' terminals. This isn't just a model swap; it fundamentally changes how much codebase history you can keep in memory without manual chunking. The release also patches critical stability issues like malformed image crashes and broken MCP reconnections, making the tool significantly more reliable for complex workflows. For builders, this means deeper context awareness and fewer interruptions during long coding sessions.
This release prioritizes security hygiene and session reliability over new features. The addition of CLAUDE_CODE_DISABLE_WEB_FETCH is a critical control for enterprise environments needing to restrict external data access. Bug fixes address subtle race conditions in cloud sessions and artifact publishing that could lead to data loss or incorrect state. SSH and plugin installation issues are resolved, ensuring smoother remote workflows. It’s a maintenance update that tightens the tool's operational boundaries.