Backfill issue -067 — The AI Toolchain

EDITIONS tail grep head diff uniq

The daily firehose — everything the toolchain shipped today, already filtered.

// HOW THIS ISSUE IS MADE

We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.

VIEW

ISSUE VIEW full issue

Do you prefer this view?

$ tct list   # 5 tools matched

AI & LLM Tooling

◆ AI Coding Agents

GitHub Copilot CLI

v1.0.62 NOTES

Copilot CLI v1.0.62 adds Kerberos proxy auth, diff file tree, session-scoped extensions, /app command, and schedulable slash commands.

└──▷ GET THIS VERSION

$ git clone --branch v1.0.62 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v1.0.62

└──▷ TRY IT

Schedule a daily standup summary without leaving the chat — useful for teams running recurring agent workflows.

$ /every 1d /chronicle standup

Configure a subagent's model and reasoning effort for a heavier analysis task via the picker.

$ /subagents

›Adds session.create and session.resume SDK methods to configure session memory for SDK clients.
›Adds /app slash command to open the GitHub app or a browser fallback.
›Adds /every and /after slash commands that can now schedule other slash commands (e.g. /every 1d /chronicle standup).
›Adds allow-all state to custom statusLine.command and shows a 'YOLO' (allow all) indicator in the footer.
›Adds file tree sidebar and inline comment editor to the /diff view.

+12 moreshow less

›Adds content search, match highlighting, and n/N navigation in diff view.
›Supports configuring subagent model, reasoning effort, and context tier via user settings or the /subagents (also /agents) picker.
›Automatically authenticates through corporate forward proxies using Kerberos/Negotiate (SPNEGO).
›Adds session-scoped extensions and canvases.
›Enables plugins to ship extensions, making them installable via the plugin marketplace.
›Discovers custom agents in nested .github/agents and .claude/agents directories when the session starts from a subdirectory of the repository root.
›Pressing W on an expanded issue or pull request details view creates a worktree.
›Pressing / on the Issues or Pull Requests tab searches GitHub with server-side filtering.
›Makes the MCP server config form easier to use with a picker-based flow.
›Maps MCP server names containing dots and slashes to valid Responses API namespaces.
›Honors max_output_tokens for BYOK Responses providers.
›Runs shell commands via lightweight process spawning instead of a pseudo-terminal.

└──▷ BREAKING ON UPGRADE

!Shell commands now run via lightweight process spawning instead of a pseudo-terminal; interactive input via write_bash is no longer supported.

Was this useful?

SST OpenCode

v1.17.5 NOTES

The open source coding agent.

OpenCode v1.17.5 adds external browser OAuth for Snowflake Cortex and refreshed oc-2 color theme.

└──▷ GET THIS VERSION

$ git clone --branch v1.17.5 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.17.5

›Adds external browser OAuth support for the Snowflake Cortex provider.
›Refreshes the oc-2 color theme in the desktop app.

Was this useful?

◆ Local LLM Runtimes

LocalAI

v4.4.3 NOTES

LocalAI v4.4.3 adds open-vocabulary object detection, OmniVoice TTS with voice cloning, Kokoro TTS, 60 new Piper voices, and declarative distributed scheduling.

└──▷ GET THIS VERSION

$ git clone --branch v4.4.3 https://github.com/mudler/LocalAI.git
# already have the repo? check out this version:
$ git checkout v4.4.3

›Adds declarative per-model scheduling for distributed deployments, configurable via environment variables and CLI arguments (feat(distributed): declarative per-model scheduling via env/args).
›Adds locate-anything-cpp backend for open-vocabulary object detection via ggml.
›Adds omnivoice-cpp backend supporting OmniVoice TTS with file and streaming output, voice cloning, and voice design.
›Adds Kokoro TTS and multilingual Piper voices to the sherpa-onnx backend.
›Migrates qwen3-tts-cpp to ServeurpersoCom/qwentts.cpp, adding streaming, multiple speakers, and voice design support.

+6 moreshow less

›Bundles espeak-ng with crispasr and adds Piper TTS voices to the model gallery.
›Expands the gallery with 60 Piper TTS voices across 42 languages (Phase 2).
›Enables GGML_CUDA_GRAPHS in the CUBLAS build for parakeet-cpp, improving GPU inference performance.
›Adds voice-recognition gating for realtime pipeline voice models.
›Adds Indonesian language support to the React UI.
›Adds Korean (ko) translation to the UI.

Was this useful?

SGLang

v0.5.13 NOTES

SGLang v0.5.13 ships Spec V2 as default, nine new models, DeepSeek V4 context parallelism, and HiCache for hybrid models.

└──▷ GET THIS VERSION

$ git clone --branch v0.5.13 https://github.com/sgl-project/sglang.git
# already have the repo? check out this version:
$ git checkout v0.5.13

›Adds flash_mla_sparse_fwd sparse FlashMLA kernel for DeepSeek V4, exposed via sgl_kernel.flashmla in sgl-kernel 0.4.3.
›Spec V2 is now the default speculative-decoding path; tree drafting with topk > 1 and page_size > 1 is production-ready across triton, FA3, MLA, and aiter backends including Mamba/hybrid-linear models.
›Adds adaptive speculative decoding with batch-size-aware num_steps and observability metrics.
›Extends Spec V2 to the FlashMLA backend.
›HybridModel (SWA/Mamba) now launches HiCache via UnifiedTree by default, bringing hierarchical KV-cache offload to sliding-window and Mamba hybrids out of the box.

+21 moreshow less

›Adds decode-side HiCache integration for incremental KV-cache transfer in PD disaggregation.
›Adds HiSparse support for DeepSeek V4 with PD disaggregation.
›Adds Pipeline Parallelism (PP) + PD support for DeepSeek V4.
›Adds context-parallel serving for DeepSeek V4, including Context Parallel + MTP and Context Parallel + fused MoE kernel (non-DeepEP).
›Adds DeepEP waterfill load balancing for DeepSeek V4.
›Adds FP4 indexer support and SM120 support for DeepSeek V4.
›Adds Piecewise CUDA Graph (PCG) support for DSA models and Kimi-K2.5.
›Adds Breakable CUDA Graph (BCG) support for DeepSeek V4.
›Adds draft-extend CUDA Graph for the trtllm mha attention backend.
›Adds CuTeDSL MLA attention kernels from FlashInfer.
›Adds FlashInfer Gated DeltaNet (GDN) kernels and a CuTeDSL GDN prefill kernel for Qwen 3.5 on Blackwell GPUs.
›Adds prefill context parallelism for MLA models (Kimi K2.5, DeepSeek V3) and support for batch size > 1 during prefill CP.
›Adds optimistic prefill for improved TTFT in PD disaggregation.
›Adds EPD disaggregation support for MiMo-V2.
›Heterogeneous CPU + GPU EPD disaggregation: offloads VLM vision encoding onto Intel Xeon CPUs, delivering up to ~1.3x P99 TTFT and request-throughput gains under load.
›Adds MoRI communication library integration for AMD Instinct MI355X, enabling cost-competitive DeepSeek-R1 disaggregated inference.
›Adds realtime video generation for SGLang-Diffusion with msgpack frame streaming, a standalone browser WebUI, continuous camera controls, super-resolution controls, and progressive-resolution growing across FLUX, FLUX.2, Qwen-Image, Wan, and Z-Image.
›Adds support for new autoregressive models: Nemotron 3 Ultra (Day-0 with kernel optimizations), Step-3.7-Flash, and Command A+ (Cohere 2 family).
›Adds support for new diffusion models: Cosmos3-Nano/Super (T2V/I2V/T2I), Ernie-Image, LingBot-World (realtime/causal-DMD), SANA-WM (streaming + realtime), FLUX.2-Klein 4B/9B, and Ideogram 4 (FP8/NVFP4 with tensor parallelism).
›Reduces per-step scheduler overhead via unified async value passing through FutureMap and moving prefill input transfer onto the forward stream.
›Spec V1 is deprecated; EAGLE/MTP now run on the unified V2 worker.

└──▷ BREAKING ON UPGRADE

!Spec V1 is deprecated; EAGLE/MTP now run on the unified Spec V2 worker — configurations relying on the Spec V1 path will need to migrate to Spec V2.

Was this useful?

llama.cpp

b9626 2 RELEASES · 2026-06-13 NOTES STABLE

llama.cpp b9626 adds architecture support for the cohere2-MoE (cohere2moe) model family.

└──▷ GET THIS VERSION

$ git clone --branch b9626 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9626

›Adds cohere2moe architecture support, enabling inference for Cohere2 Mixture-of-Experts models (including North-Mini-Code-1.0) with iSWA-based sliding window attention, sigmoid expert selection, and LayerNorm support for Command variants.
›Adds cohere2moe to the Llama Model Saver supported architecture list, enabling GGUF conversion of cohere2moe models.

1 more release in this issue · 2026-06-13

b9624 NOTES STABLE

llama.cpp b9624 adds build-time gzip compression to the web UI for faster asset delivery.

└──▷ GET THIS VERSION

$ git clone --branch b9624 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9624

›Adds build-time gzip compression for web UI assets, reducing payload size for browser clients.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · June 13, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -067, June 13, 2026

GitHub Copilot CLI

SST OpenCode

LocalAI

SGLang

llama.cpp