This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+8 more
Summary
AI summaryLaunch now auto‑installs Cline CLI, cmd/launch adds Qwen code integration, and llm updates improve model limits, token counting, stall detection, URL handling, and add the Laguna architecture.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Security | High |
Hardens app markdown URL handling to prevent injection attacks. Hardens app markdown URL handling to prevent injection attacks. Source: llm_adapter@2026-06-03 Confidence: high |
— |
| Security | High |
Further hardens app markdown URL handling against edge cases. Further hardens app markdown URL handling against edge cases. Source: llm_adapter@2026-06-03 Confidence: high |
— |
| Feature | Low |
Adds Qwen code integration to the launch command. Adds Qwen code integration to the launch command. Source: llm_adapter@2026-06-03 Confidence: high |
— |
| Feature | Low |
Allows Radeon 8060S iGPU by default in discovery. Allows Radeon 8060S iGPU by default in discovery. Source: llm_adapter@2026-06-03 Confidence: high |
— |
| Feature | Low |
Isolates Codex launch configuration for cleaner setup. Isolates Codex launch configuration for cleaner setup. Source: llm_adapter@2026-06-03 Confidence: high |
— |
| Feature | Low |
Adds automatic installation of Cline CLI on launch. Adds automatic installation of Cline CLI on launch. Source: llm_adapter@2026-06-03 Confidence: low |
— |
| Feature | Low |
Shows and auto‑installs Cline CLI on launch. Shows and auto‑installs Cline CLI on launch. Source: granite4.1:30b@2026-06-03-audit Confidence: low |
— |
| Dependency | Medium |
Updates llama.cpp to the latest version. Updates llama.cpp to the latest version. Source: llm_adapter@2026-06-03 Confidence: high |
— |
| Performance | Medium |
Includes cached prompt tokens in llama-server token counts. Includes cached prompt tokens in llama-server token counts. Source: llm_adapter@2026-06-03 Confidence: high |
— |
| Performance | Medium |
Detects llama-server load stalls from output streams. Detects llama-server load stalls from output streams. Source: llm_adapter@2026-06-03 Confidence: high |
— |
| Bugfix | Medium |
Fixes local model limits in opencode during launch. Fixes local model limits in opencode during launch. Source: llm_adapter@2026-06-03 Confidence: high |
— |
Full changelog
What's Changed
- feat(launch): show and auto-install Cline CLI by @hoyyeva in https://github.com/ollama/ollama/pull/16402
- log template details to aid troubleshooting by @dhiltgen in https://github.com/ollama/ollama/pull/16403
- cmd/launch: add Qwen code integration by @hoyyeva in https://github.com/ollama/ollama/pull/15900
- launch: fix opencode local model limits by @dhiltgen in https://github.com/ollama/ollama/pull/16425
- llm: include cached prompt tokens in llama-server counts by @dhiltgen in https://github.com/ollama/ollama/pull/16428
- Harden app markdown URL handling by @dhiltgen in https://github.com/ollama/ollama/pull/16380
- discover: allow Radeon 8060S iGPU by default by @dhiltgen in https://github.com/ollama/ollama/pull/16429
- llm: detect llama-server load stalls from output by @dhiltgen in https://github.com/ollama/ollama/pull/16427
- More harden app markdown URL handling by @dhiltgen in https://github.com/ollama/ollama/pull/16436
- llama.cpp version update by @dhiltgen in https://github.com/ollama/ollama/pull/16426
- launch: isolate Codex launch configuration by @ParthSareen in https://github.com/ollama/ollama/pull/16437
- llama: add laguna (poolside) arch via a llama.cpp patch under llama/c… by @dhiltgen in https://github.com/ollama/ollama/pull/16396
- docs: configure hermes desktop app by @BruceMacD in https://github.com/ollama/ollama/pull/16440
- llm: ignore llama-server SSE ping comments by @dhiltgen in https://github.com/ollama/ollama/pull/16443
- fix laguna patch build breakage by @dhiltgen in https://github.com/ollama/ollama/pull/16445
Full Changelog: https://github.com/ollama/ollama/compare/v0.30.0...v0.30.2-rc0
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About ollama
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Related context
Related tools
Beta — feedback welcome: [email protected]