🐤 Canary Build — v2.2.14-canary.1 Automated canary build from canary branch. Commit Information Based on changes since v2.2.13-canary.24 Commit count: 6 c83f86bc99 🐛 fix: improve acceptance check details (#17803) (Arvin Xu) c72f6e2068 📝 docs: fix Messenger overview MDX rendering (#17810) (Neko) a5769c22b6 🔖 chore(release): release version v2.2.12 [skip ci] (lobehubbot) ⚠️ Important Notes This is a…
Alpha release v0.33.0-alpha.179
PR Build Information Version: 0.0.0-nightly.pr17809.24432 Release Time: 2026-08-01T14:13:45.349Z PR: #17809 ⚠️ Important Notice This is a development build specifically created for testing purposes. Please note: This build is NOT intended for production use Features may be incomplete or unstable Use only for validating PR changes in a desktop environment May contain experimental code that hasn't b…
Alpha release v0.33.0-alpha.178
mtmd: add minicpmv46 downsample (#25993) add minicpmv46 downsample Signed-off-by: tc-mb tianchi_cai@icloud.com put downsample mode inside gguf. Signed-off-by: tc-mb tianchi_cai@icloud.com build mtmd_image_preprocessor_llava_uhd Signed-off-by: tc-mb tianchi_cai@icloud.com fix code Signed-off-by: tc-mb tianchi_cai@icloud.com add convert Signed-off-by: tc-mb tianchi_cai@icloud.com add 4x ignore vit m…
📦 Release v2.2.13 This release was automatically published from PR #17807. Changes See PR description: #17807 Commit Message 🚀 LobeHub Release (20260801) Release Date: August 1, 2026 Since v2.2.12: 86 merged PRs · 13 contributors Home becomes an Agent dashboard, the desktop shell keeps every tab alive, and local Agents connect through one wizard — with a long tail of runtime, model, and Windows fi…
koboldcpp-1.118 Row Split has been removed, selecting it will now default to tensor split. Rocwmma has been removed, matching upstream behavior. Added support for qwen3tts aliases for all voices. Breaking change for RPC to match upstream behavior, allowing llama.cpp RPC server and clients to be interchangeable with koboldcpp ones again. Fixed loading for SeFI image. Fixed a quality regression in Q…
PR Build Information Version: 0.0.0-nightly.pr17809.24425 Release Time: 2026-08-01T10:50:26.750Z PR: #17809 ⚠️ Important Notice This is a development build specifically created for testing purposes. Please note: This build is NOT intended for production use Features may be incomplete or unstable Use only for validating PR changes in a desktop environment May contain experimental code that hasn't b…
Alpha release v0.33.0-alpha.177
Defold version 1.13.2 Channel=alpha sha1: 7fa095b date = 2026-08-01 09:27:48
🐤 Canary Build — v2.2.13-canary.24 Automated canary build from canary branch. Commit Information Based on changes since v2.2.13-canary.23 Commit count: 2 d794195caf ✨ feat(onboarding): decouple task recommendation generation (#17783) (Neko) 59f16c15f7 🐛 fix(desktop): resolve UI language from the OS instead of the pruned app locale (#17804) (Innei) ⚠️ Important Notes This is an automated canary bui…
PR Build Information Version: 0.0.0-nightly.pr17807.24414 Release Time: 2026-08-01T08:10:26.396Z PR: #17807 ⚠️ Important Notice This is a development build specifically created for testing purposes. Please note: This build is NOT intended for production use Features may be incomplete or unstable Use only for validating PR changes in a desktop environment May contain experimental code that hasn't b…
PR Build Information Version: 0.0.0-nightly.pr17804.24405 Release Time: 2026-08-01T07:45:15.474Z PR: #17804 ⚠️ Important Notice This is a development build specifically created for testing purposes. Please note: This build is NOT intended for production use Features may be incomplete or unstable Use only for validating PR changes in a desktop environment May contain experimental code that hasn't b…
[DTensor] Answer as_strided when it is a permutation of the base dims…
chat : enable tool call in thinking for DS4 (#26269) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (ROCm 7.2) Ubuntu x64 (OpenVINO) Ubuntu x64 (SYCL FP32) Ubuntu x64 (SYCL FP16…
When a test times out, CI logs today contain no way to tell what timed out on a line that also says it timed out. retry_shell prints Command took >30min, returning 124 which names nothing, so the log classifier -- which picks a single line and uses its capture as the HUD grouping key -- collapses every timeout in the fleet into one bucket. A single test file that starts hanging is invisible; it lo…
Fix torchcomms bug of destroying one subgroup wipes every live group …
Hey everyone! Kimi K3 can now run locally with Unsloth Dynamic GGUFs, Unsloth can keep multiple chats generating in parallel, and the new Deep Research mode plans, reads and cites sources using your local model. This release also brings better AMD and Intel GPU support, DoRA training, and many installer, MLX, export and inference fixes. Kimi K3 Moonshot AI’s Kimi K3 is a 2.8T-parameter MoE model w…
Provider errors forwarded through the Vercel AI Gateway now surface the real upstream message (e.g. "This model's maximum context length is 40960 tokens...") instead of a raw Zod issue dump, and opaque object errors no longer render as [object Object] fetchClineRecommendedModels now returns display-ready model names, resolved through the model catalog (including Vercel and OpenRouter id aliases) u…
@cline/core@0.0.68
@cline/agents@0.0.68
@cline/llms@0.0.68
@cline/shared@0.0.68
🐤 Canary Build — v2.2.13-canary.23 Automated canary build from canary branch. Commit Information Based on changes since v2.2.13-canary.22 Commit count: 3 2faf1dfe7b ✨ feat(home): refine activity and topic sections (#17798) (Arvin Xu) ca4e7159d4 📝 docs(builtin-skills): add structured report-round reference to acceptance skill (#17799) (Arvin Xu) 9990347f88 ✨ feat(quota): sample Claude Code quota fr…
This PR is auto-generated nightly by this action. Update the pinned torchcomms hash. Pull Request resolved: #191421 Approved by: https://github.com/pytorchbot
This PR is auto-generated nightly by this action. Update the pinned vision hash. Pull Request resolved: #191422 Approved by: https://github.com/pytorchbot
What's Changed feat: preserve sandbox environment secret references by @seratch in #1547 fix: preserve raw realtime transport event payloads by @seratch in #1550 fix: reject ephemeral paths during sandbox archive hydration by @seratch in #1553 fix: redact endpoint credentials from MCP transport errors by @seratch in #1551 fix: redact MCP URL credentials from external metadata by @seratch in #1552…
test_reductions_large_half_tensors was failing on the trunk macos-py3-arm64 default shard in a way that looked commit-induced (two adjacent SHAs red, then green) but is really a flaky skip gate. Root cause: the test is gated by largeTensorTest("8GB"), which on MPS reduces to psutil.virtual_memory().available >= 8GiB. On a 16GB m1-stable runner that sits right at the threshold, so the skip fires or…
🐤 Canary Build — v2.2.13-canary.22 Automated canary build from canary branch. Commit Information Based on changes since v2.2.13-canary.21 Commit count: 3 24fc237d89 🐛 fix: resolve globFiles/searchFiles scope against user workspace on Windows (#17676) (Northword) aa06851a9c 🐛 fix(agent-runtime): preserve grouped sub-agent final answers (#17725) (Coooolfan) 3d4c2631ee 💄 style(lobe-agent): align todo…
isFwGradDefined is called a lot in torch/csrc/autograd/generated/VariableType*.cpp. Many of these calls pass a Tensor into the function. The original implementation of this function only accepted an optional. This forced a call to the optional constructor every time that function is called and an unnecessary call to optional::has_value() later. This commit adds an overload that accepts Tensor. I g…