🧰 Tools we follow
Cline
Open-source VS Code / Desktop coding agent. Official notes: https://github.com/cline/cline/releases.
Recent updates we covered
v4.1.24: default model → Claude Sonnet 5.5 (2026-10-13)
Unpinned Cline and OpenRouter providers default to Sonnet 5.5. Catalog adds Haiku 5.5; ~20 other providers change defaults. Reasoning-off 400s fixed on several frontier models.
Source: https://github.com/cline/cline/releases/tag/v4.1.24 · Covered in Snack Pack #1
Desktop v0.0.46: prompt outline (2026-10-13)
Clickable prompt outline along the conversation; clearer plugin failure status.
Source: https://github.com/cline/cline/releases/tag/desktop-v0.0.46 · Covered in Snack Pack #1
Everything we covered, by ship date
Dailies, Snack Pack items, shelf picks and Backfilled entries (added later from official release notes; spice auto-rated).
- Snack Pack Cline quietly swapped your default model 🌶️🌶️🌶️
- Daily Cline swapped your default model 🌶️🌶️🌶️
- Changelog v4.1.23: If a model's response ends without a recognized finish reason, Cline asks it to… 🌶️
If a model's response ends without a recognized finish reason, Cline asks it to continue once instead of treating the response as complete. Refreshed the model catalog. The Cline recommended list adds GPT-6.1 Sol, and the free list adds Solar Mini 4 and drops DeepSeek V4.1 Flash and space-bunny-alpha. Default models… - Changelog v4.1.21: New provider: ai&, an OpenAI-compatible endpoint serving open-weight models… 🌶️
New provider: ai&, an OpenAI-compatible endpoint serving open-weight models from Japan. Refreshed the model catalog to 6,386 models across 209 providers. The resolved default model changes for 19 providers that do not pin one, 11 of them to Claude Opus 5.5 (including GitHub Copilot and Vertex). If you use one of those… - Changelog v4.1.19: Images attached to a model that cannot read them are now flagged instead of… 🌶️
Images attached to a model that cannot read them are now flagged instead of silently discarded. Thumbnails get a warning badge and the composer explains that the images will be ignored, with a button to switch to an image-capable model. Previously the thumbnail looked normal and the image was replaced with a text… - Changelog v4.1.16: Cost estimates are no longer shown for providers billed by a flat-rate… 🌶️
Cost estimates are no longer shown for providers billed by a flat-rate subscription (ClinePass, ChatGPT via Codex, and Claude Code). The task header and model pricing rows rendered API-rate dollar figures that read as real charges on top of the subscription, including a flash of them on every chat-view mount while… - Changelog v4.1.14: Refresh the built-in model catalog. New entries include Claude Fable 5, Grok… 🌶️
Refresh the built-in model catalog. New entries include Claude Fable 5, Grok 4.6 on Vertex, several DeepSeek V4 Flash variants (including the vision preview), MiMo v2.5, Qwen3.8 27B, Gemma 4 26B, LongCat 2.0, Nemotron 3.5 Lightning, and Thinking Machines' Inkling models. Restore task completion telemetry for… - Changelog v4.1.12: Enforce enterprise MCP controls on the Customize marketplace. MCP entries are… 🌶️
Enforce enterprise MCP controls on the Customize marketplace. MCP entries are now hidden when remote config disables the marketplace, and limited to `allowedMCPServers` when an allowlist is configured. Restore tool calling for custom OpenAI-Compatible models whose stored capability list was empty.