perf(worker): compute prewarm pieces and code steps server-side ( #15310 )
> 📌 **Upgrading a self-hosted instance?** Review the [Breaking Changes](https://www.activepieces.com/docs/install/reference/breaking-changes) page for any actions required before you upgrade.
## Thanks ❤️
## Use Ollama models in ChatGPT Desktop
Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS.
<img width="1374" height="1300" alt="CleanShot 2026-09-08 at 11 04 07 AM@2x" src="https://github.com/user-attachments/assets/e10e299d-c11f-447d-9234-afa855824efe" />
This release also improves structured output performance on Apple Silicon, adds support for OpenAI-compatible client tool search and response compaction.
**Full Changelog**: https://github.com/ollama/ollama/compare/v0.33.3...v0.34.0
## What's Changed
### Features
- Add Clipper integrations client
- Add `now()` to the CEL expression environment
- Record how a crew run ended for every user
- Report machine size as a coarse band, not a core count
- Add injectable client for CrewAI platform tools
### Bug Fixes
- Fix reading of octet-stream and xlsx URLs in `urlreadtool`
- Fix appending trailing user turn in native Gemini provider
- Normalize scheme and port in Ollama base URL
- Preserve reusable scope configs in memory
- Bump `pypdf` to 6.16.2 for security vulnerability
- Bump `nltk` to 3.10.3 for security vulnerability
- Fix native structured outputs for current Claude models and Snowflake CVE floor
- Run model call hooks on every path and propagate a deny
### Documentation
- Remove `CodeInterpreterTool` from AI/ML overview examples
- Point `prompt-template` link at its current path
- Update channels guide to current CopilotKit channels API
- Refresh retired Gemini model IDs
## Contributors
@Vidit-Ostwal, @a-yey
## What's Changed
* gemma4 now supports images and audio on MLX engine
* Report cached prompt tokens
* Honor GGUF model defined default parameters
* MLX, MLX-C, llama.cpp update
## New Contributors
* @marcelpetrick made their first contribution in https://github.com/ollama/ollama/pull/17579
**Full Changelog**: https://github.com/ollama/ollama/compare/v0.33.2...v0.33.3
## What's Changed
* Ollama's app now follows the system appearance again, restoring dark mode support
* Fixed the macOS app to properly hand off to an already-running instance instead of starting a second one
* The Claude Desktop proxy no longer interrupts in-flight requests when the model catalog updates
**Full Changelog**: https://github.com/ollama/ollama/compare/v0.33.1...v0.33.2
## 1.16.0 (2026-08-27)
<!-- Release notes generated using configuration in .github/release.yml at main -->
## What's Changed
### Features
* feat(settings): select supported LLM providers by @keeltrace in https://github.com/OpenHands/OpenHands/pull/16772
* feat: add linux desktop installer build (CI + deb maintainer fix) by @georgeglarson in https://github.com/OpenHands/OpenHands/pull/16656
* feat(automations): show a run's live phase by @aartem1 in https://github.com/OpenHands/OpenHands/pull/16740
* feat(settings): expose the LLM-switching toggle in Agent settings by @georgeglarson in https://github.com/OpenHands/OpenHands/pull/16441
* feat(skills): replace the all-on skill catalog with an explicit allow-list by @VascoSch92 in https://github.com/OpenHands/OpenHands/pull/16860
* feat: link chat file paths to the Files drawer by @ShashwatXD in https://github.com/OpenHands/OpenHands/pull/16181
* feat: pin a favorite sidebar page as the home route by @hieptl in https://github.com/OpenHan
## What's Changed
### Features
- Promote conversational flows to stable
- Record a created deployment with the given UUID
- Enhance conversational flow documentation and APIs
- Let a declaration name the router's response format
- Let a chat flow declare its own state shape
- Accept crew-style LLM config in a conversational declaration
- Report project creation with the minted ID
- Record whether a run had inputs, without recording the inputs
- Backfill project ID from every user-invoked project command
### Bug Fixes
- Preserve tool results when the final answer is empty
- Map default Claude Sonnet 4.6 to its 1M context window
- Raise Anthropic default max_tokens for large tool calls
- Render message content parts as text, not as a Python repr
- Keep message roles when Agent.kickoff gets a conversation
- Skip interception hooks on crewai-internal flows
- Record task failures as failures, not successes
- Emit the flow lifecycle on a suppressed resume
- Open the conversational TUI for
## What's Changed
* MLX: Qwen3.8 Flash Next support
* cmake: make external compat patches idempotent
* MLX and llama.cpp update
* mlxrunner: add structured output support
* mlxrunner: avoid Metal GPU timeouts when loading models from slow storage
## New Contributors
* @pd95 made their first contribution in https://github.com/ollama/ollama/pull/17948
**Full Changelog**: https://github.com/ollama/ollama/compare/v0.33.0...v0.33.1
## New Features
**Agent: E2B Sandbox, Home Snapshots, and Skill Management**
- **E2B sandbox backend**: agent shell/code execution can now run on [E2B](https://e2b.dev) cloud sandboxes in addition to the local sandbox. Select the backend with `DIFY_AGENT_RUNTIME_BACKEND`; a new `docker-compose.e2b.yaml` ships the E2B stack, E2B traffic is authenticated, and the E2B template is synced on release (#39480, #39705, #39873, #39996, #40858, #40871, #40891, #40892).
- **Build-time Home Snapshots**: when an agent build is applied (published), the agent's sandbox home directory — installed packages, prepared files, working state — is captured and subsequent runs of the published agent restore their home directory from that snapshot, so the agent starts from the exact filesystem state it had at build time. (#39702, #40876, #40996).
- **Workspace-level Skill management**: Skills are reusable, versioned capabilities packaged with code and tool definitions that agents can discover and invoke.
### Bug fix
- Reverts #14889 ( released on 0.88.3 ) as it introduced a CPU spike in worker containers for flows that use old versioned pieces with large dependencies like google suite pieces .
> 📌 **Upgrading a self-hosted instance?** Review the [Breaking Changes](https://www.activepieces.com/docs/install/reference/breaking-changes) page for any actions required before you upgrade.
## Thanks ❤️
## Bug fixes
. fix(rate-limiter): promote parked jobs when a concurrency slot frees ( #15033 ) @MrChaker
## Note
. this release has been ported only on top of 0.87.0 as hotfix and it's currently planned to be ported to 0.89.0
> 📌 **Upgrading a self-hosted instance?** Review the [Breaking Changes](https://www.activepieces.com/docs/install/reference/breaking-changes) page for any actions required before you upgrade.
## Thanks ❤️
## What's Changed
### Claude Desktop
Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
<img width="1298" height="780" alt="image" src="https://github.com/user-attachments/assets/c02fd93b-f599-40a9-83c3-d0555c0ac182" />
### Improved caching
* Fixed a hang where agent clients that cancel long prefills
* 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
### Other improvements
* DeepSeek Harness launcher now f
## 1.15.0 (2026-08-21)
<!-- Release notes generated using configuration in .github/release.yml at main -->
## What's Changed
### Features
* feat(sidebar): add getting started checklist with settings toggle by @FraterCCCLXIII in https://github.com/OpenHands/OpenHands/pull/16182
* feat: show workspace path in Files view by @HurrairaBaloch in https://github.com/OpenHands/OpenHands/pull/16362
* feat(automations): install a catalog entry that ships a script bundle by @VascoSch92 in https://github.com/OpenHands/OpenHands/pull/16680
* feat: add LLM provider-connections UI (local agent-server) by @juanmichelini in https://github.com/OpenHands/OpenHands/pull/16616
* feat: polish automations dashboard, recommended rail, and Add/Import flow by @FraterCCCLXIII in https://github.com/OpenHands/OpenHands/pull/16688
* feat(conversation): add overview panel and unified commits drawer by @FraterCCCLXIII in https://github.com/OpenHands/OpenHands/pull/16230
* feat: send template provenance for versioned
## What's Changed
### Features
- Add declarative conversational flows documentation
- Synthesize built-in conversational methods for declarations
- Enable declarations to drive conversational mode
- Make conversational opt-in unmistakable
- Carry the AMP slug on tools resolved from a slug reference
- Handle oversized single messages during chunking
### Bug Fixes
- Fix usage of the URL hostname as MCP HTTP and SSE server_name
- Close the agent scope on every failed attempt
- Attribute tool errors to the tool that failed
- Pin SSRF checks to each redirect hop and peer IP
- Resolve issues with native tool calls broken over OpenAI Responses API
### Documentation
- Update documentation with a snapshot and changelog for v1.15.16
## Contributors
@Copilot, @Vidit-Ostwal, @github-code-quality[bot], @joaomdmoura, @lorenzejay, @lucasgomide, @theCyberTech
## What's Changed
* New desktop onboarding flow on first launch
* Caches resolved model metadata between requests, cutting time-to-first-token by roughly half (TTFT dropped from ~995 ms to ~524 ms in benchmarks)
* Fixes a bug where chat and generate could wedge after a mid-stream parser error
* **Qwen 3.8** system messages are now normalized so non-leading system messages are handled consistently
* MLX and llama.cpp dependency updates
## New Contributors
* @gaugarg-nv made their first contribution in https://github.com/ollama/ollama/pull/17752
**Full Changelog**: https://github.com/ollama/ollama/compare/v0.32.14...v0.32.15
## 1.14.0 (2026-08-17)
<!-- Release notes generated using configuration in .github/release.yml at main -->
## What's Changed
### Features
* feat(canvas): present structured error outcomes by @neubig in https://github.com/OpenHands/OpenHands/pull/16231
* feat: add LLM pre-flight validation to prevent saving misconfigured profiles by @neubig in https://github.com/OpenHands/OpenHands/pull/16417
* feat(automations): add a Git Sync page by @VascoSch92 in https://github.com/OpenHands/OpenHands/pull/16521
* feat: set Canvas default model to Kimi K3 and tag it free by @juanmichelini in https://github.com/OpenHands/OpenHands/pull/16657
### Bug Fixes
* fix(onboarding): preselect OpenHands LLM provider after picking OpenHands agent by @juanmichelini in https://github.com/OpenHands/OpenHands/pull/16531
* fix: preserve backend scope in conversation links by @neubig in https://github.com/OpenHands/OpenHands/pull/16091
* fix(dev): stop baking absolute VITE_BACKEND_BASE_URL in npm run dev by @neubig