Backfill issue -309 — 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   # 3 tools matched

AI & LLM Tooling

◆ AI Coding Agents

Continue

@continuedev/[email protected] NOTES

Continue 1.24.0 adds CLI OAuth for MCP, workflow files with tool permissions, token usage tracking, and directory context mentions.

└──▷ GET THIS VERSION

$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]

›Adds MentionFileInChatAction and MentionRepoMapInChatAction context actions, letting users reference files and repo maps directly from the IDE context-actions group.
›Introduces workflow files for the CLI — supports parsing, serializing, and tool-permission declarations so agents can run with scoped tool access.
›Adds MCP OAuth support in the CLI via mcp-remote, enabling authenticated MCP server connections from the terminal.
›Adds token usage tracking to the OpenAI adapter, surfacing consumption data per request.
›Adds auto-accept agent edits setting so edit tools no longer require manual confirmation during agentic sessions.

+2 moreshow less

›Enables mentioning directories (and mixing directories with files) as context in chat.
›Adds session history navigation ('go back in history') in the CLI.

Was this useful?

SST OpenCode

v0.15.0 NOTES

The open source coding agent.

OpenCode v0.15.0 adds Perl6 file extension support and ensures plugin availability in .opencode folder.

└──▷ GET THIS VERSION

$ git clone --branch v0.15.0 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v0.15.0

›Adds support for Perl6 file extensions.
›Ensures @opencode-ai/plugin is available in the .opencode folder.

Was this useful?

◆ Local LLM Runtimes

KoboldCpp

v1.100.1 NOTES

KoboldCpp v1.100.1 adds WAN video generation, new GPU/CPU offload flags, and GLM4.6 & Granite 4 model support.

└──▷ GET THIS VERSION

$ git clone --branch v1.100.1 https://github.com/LostRuins/koboldcpp.git
# already have the repo? check out this version:
$ git checkout v1.100.1

└──▷ TRY IT

Generate a short WAN video on a system with limited VRAM by offloading both the model weights and VAE to CPU.

$ koboldcpp --sdmodel wan2.2-14b.gguf --sdvae wan_2.1_vae.safetensors --sdt5xxl umt5-xxl-q8_0.gguf --sdoffloadcpu --sdvaecpu

›Adds --sdoffloadcpu flag to dynamically load/unload image generation weights to RAM when not in use (e.g. during VAE decoding).
›Adds --sdvaecpu flag to perform VAE decoding on CPU using RAM instead of VRAM.
›Adds --sdclipcpu flag to perform CLIP/T5 decoding on CPU (new default behavior).
›Adds --sdgendefaults flag to set default image generation parameters.
›Adds --lowvram flag (equivalent to -nkvo) to avoid offloading the KV cache, now usable in both CUDA and Vulkan (replaces the former lowvram CUDA-only option).

+7 moreshow less

›Renames --sdclipl to --sdclip1 and --sdclipg to --sdclip2; these flags now apply to any vision encoder (e.g. WAN clip_vision).
›Adds WAN video generation: generate short videos in KoboldCpp using WAN models, loaded via --sdvae, --sdmodel, and --sdt5xxl, accessible through the SDUI at http://localhost:5001/sdui.
›Updates StableUI to support animations and video output, including Image-To-Video (I2V) via the txt2img panel.
›Adds dry_penalty_last_n parameter to Kobold Lite, decoupling DRY range from repetition penalty range.
›Adds support for GLM4.6 and Granite 4 models, including a new Granite 4 chat template.
›Moves all .embd resource files into a separate directory and extracts image generation vocabs into their own files.
›Enables building for CUDA13 in CMake (untested, no binaries provided).

└──▷ BREAKING ON UPGRADE

!--sdclipl is renamed to --sdclip1 and --sdclipg is renamed to --sdclip2; any launch scripts or configs using the old flag names will break.
!The lowvram CUDA option is moved to a new --lowvram flag; existing setups relying on the old CUDA-specific lowvram option must switch to the flag.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · October 12, 2025
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -309, October 12, 2025

Continue

SST OpenCode

KoboldCpp