🔧 AI Nachrichten GitHub Release: ollama/ollama v0.34.0-rc0 (04.09.2026)(04.09.2026 um 23:04 Uhr)
🔧 AI Nachrichten GitHub Release: ollama/ollama v0.34.0 (10.09.2026)(10.09.2026 um 08:18 Uhr)
🔧 AI Nachrichten GitHub Release: anomalyco/opencode v1.18.26 (01.09.2026)(01.09.2026 um 23:52 Uhr)
🔧 AI Nachrichten GitHub Release: anomalyco/opencode v1.18.29 (05.09.2026)(05.09.2026 um 01:47 Uhr)
🔧 AI Nachrichten GitHub Release: anomalyco/opencode v1.18.30 (09.09.2026)(09.09.2026 um 05:34 Uhr)
🔧 AI Nachrichten GitHub Release: cline/cline v4.1.17 (02.09.2026)(02.09.2026 um 07:40 Uhr)
🔧 AI Nachrichten GitHub Release: cline/cline vdesktop-v0.0.25 (10.09.2026)(10.09.2026 um 06:57 Uhr)
🔧 AI Nachrichten GitHub Release: dbeaver/dbeaver v26.2.0 (30.08.2026)(30.08.2026 um 20:08 Uhr)
🔧 AI Nachrichten GitHub Release: openclaw/openclaw v2026.9.4 (11.09.2026)(11.09.2026 um 06:12 Uhr)
🔧 AI Nachrichten GitHub Release: ollama/ollama v0.34.0-rc0 (04.09.2026)(04.09.2026 um 23:04 Uhr)
🔧 AI Nachrichten GitHub Release: ollama/ollama v0.34.0 (10.09.2026)(10.09.2026 um 08:18 Uhr)
🔧 AI Nachrichten GitHub Release: anomalyco/opencode v1.18.26 (01.09.2026)(01.09.2026 um 23:52 Uhr)
🔧 AI Nachrichten GitHub Release: anomalyco/opencode v1.18.29 (05.09.2026)(05.09.2026 um 01:47 Uhr)
🔧 AI Nachrichten GitHub Release: anomalyco/opencode v1.18.30 (09.09.2026)(09.09.2026 um 05:34 Uhr)
🔧 AI Nachrichten GitHub Release: cline/cline v4.1.17 (02.09.2026)(02.09.2026 um 07:40 Uhr)
🔧 AI Nachrichten GitHub Release: cline/cline vdesktop-v0.0.25 (10.09.2026)(10.09.2026 um 06:57 Uhr)
🔧 AI Nachrichten GitHub Release: dbeaver/dbeaver v26.2.0 (30.08.2026)(30.08.2026 um 20:08 Uhr)
🔧 AI Nachrichten GitHub Release: openclaw/openclaw v2026.9.4 (11.09.2026)(11.09.2026 um 06:12 Uhr)

🔧 AI Nachrichten 🕛 vor 2 Tagen 3 Min Lesezeit
0

GitHub Release: cline/cline vdesktop-v0.0.25 (10.09.2026)

↗ Quelle (GitHub · cline/cline)
🗣️ Stimme:
GitHub Release: cline/cline vdesktop-v0.0.25 (10.09.2026)
Avatar
$ git clone https://github.com/cline/cline.git

  • ChatGPT Subscription (Codex) now lists only the models your plan can actually use. Two separate paths filled the picker from the shared OpenAI catalog, so GPT-4o, GPT-4.1, and chatgpt-image-latest showed up alongside the Codex models, and the runtime lost the Codex context caps. The model rules also match what the backend now accepts: gpt-5.4 and gpt-5.4-mini were retired for ChatGPT accounts on 2026-08-31 and are gone, the default moves to gpt-5.6-terra, and every Codex model is capped at the real 400K/272K/128K backend budget instead of inheriting the API's 1.05M limits

  • Windows updates no longer fail with "Error opening file for writing". The compiled sidecar re-executes itself as the detached Cline Hub daemon, which outlives the app by design, and Tauri's NSIS installer only kills the main binary — so the daemon still held code-sidecar.exe and the install stopped until you killed the process by hand. The installer now stops it first, matched on the full path so updating one channel does not take down a side-by-side Cline Beta's sessions

  • Your prompt is no longer lost when a send fails before the turn starts — switching to Codex and having the OAuth refresh throw, for instance. The runtime never took the prompt, so post-send hydration wiped the optimistic bubble and you had to retype it. The text and attachments now come back to the composer, merged with anything you attached while the send was pending, and left alone if you have already started typing something else

  • Providers that authenticate through a local CLI — Claude Code, Codex CLI — can now start sessions without an API key. They showed as Configured in Settings via their local-auth capability, but session start still refused them with "Missing API key"

  • OpenCode is now treated as a local CLI provider rather than an OAuth one, so it shows the local CLI notice instead of a browser sign-in button that could not do anything. It authenticates from the credentials the opencode CLI itself stores

  • Session import from Claude Code, Codex, and opencode has its own page in Settings instead of a row buried in General

  • The composer's provider picker now marks which providers you have already configured

  • The model picker distinguishes models that share a name, and Cline Pass subscription models are listed separately from the free fallback tier

  • Published DMGs use the intended window layout and background again. Tauri skips the Finder AppleScript that applies them whenever CI is set, which GitHub Actions always sets, so every DMG since the artwork landed shipped with a stock Finder window even though the artwork was generated and validated

  • Cline's recommended, free, and subscribed model lists now ship with the app, so they are correct at first launch instead of waiting on a live catalog fetch

  • Refreshed the model catalog. Adds NaN (nan.builders) and changes the resolved default model for 36 providers — including Bedrock, Vertex, OpenRouter, Kilo, GitHub Copilot, Gemini, Cerebras, Fireworks, Requesty, and Vercel AI Gateway. Several move off Claude Fable 5.1 to GPT-6 Astra, Vertex goes to Gemini 3.8 Flash, and OpenRouter/Kilo to Inception Mercury 2.5. If you use one of those without pinning a model, expect a different default


Full Changelog: desktop-v0.0.24...desktop-v0.0.25

Vollständiger Original-Bericht
Ausführliche Details, Code-Beispiele & Hersteller-Stellungnahme auf github.com.
↗ Original-Artikel auf github.com lesen
Wie bewertest du diesen Beitrag?
1 Klick Feedback
Teilen mit Netzwerk & Team:

Community-Analysen & Experten-Meinungen 0

Verfasse deine eigene Analyse, teile Workarounds oder diskutiere diesen Vorfall im Blog.
Noch keine Community-Analyse verfasst. Markiere einen Textabschnitt oder klicke oben auf Eigene Analyse verfassen“!
Community Pulse: Relevanz-Einschätzung
1 Klick Experten-Votum
🔴 Akute Relevanz 0%
🟡 In Evaluierung 0%
🟢 Keine Auswirkung 0%
Spannende Innovation 0%
Verwandte Story-Cluster & Quellen (Vektor-KI)
Port 8095 Engine
2 Quellen
Hands-On with ChatGPT Work’s New Cloud Browser Feature
1 Quelle
Prime Video: KI soll Synchronfassungen natürlicher wirken lassen
1 Quelle
iPhone Duo design & MagSafe problems on the AppleInsider Podcast