Backfill issue -059 — 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   # 4 tools matched

AI & LLM Tooling

◆ AI Agent Frameworks

OpenClaw

v2026.6.9 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2026.6.9 adds Codex Hosted Search, auto plugin approvals, standalone provider npm packages, OpenTelemetry log export, and new UI/mobile controls.

└──▷ GET THIS VERSION

$ git clone --branch v2026.6.9 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.6.9

›Adds Codex Hosted Search as a new search provider option.
›Adds automatic plugin approvals for Codex, reducing manual intervention in agentic workflows.
›Adds remote-node exec exposed as a dynamic tool in Codex when a remote node is connected.
›Adds OpenTelemetry log export for observability pipeline integration.
›Publishes official provider plugins as standalone, independently installable npm packages.

+10 moreshow less

›Enables Gateway to discover and load externally installed channel plugins at startup.
›Makes StepFun provider available via npm and ClawHub.
›Adds a session workspace rail to the Control UI.
›Adds plugin health status display to the Control UI.
›Adds iOS Watch controls for session management.
›Adds Android chat context display.
›Adds SecretRefs support in Codex for safer credential handling.
›Preserves ClawHub skill install source provenance for verified installs.
›Key-free search providers remain deliberate opt-ins, preventing accidental exposure.
›QA scenarios now authored in YAML with broader profile evidence and channel/plugin matrix coverage.

Was this useful?

◆ AI Coding Agents

SST OpenCode

v1.17.9 NOTES

The open source coding agent.

Adds high and max thinking variants for GLM-5.2 across supported providers.

└──▷ GET THIS VERSION

$ git clone --branch v1.17.9 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.17.9

›Adds high and max thinking variants for GLM-5.2 across supported providers.

Was this useful?

Alibaba Qwen Code

v0.18.5 NOTES

Qwen Code v0.18.5 adds a Requesty provider, MCP resource/prompt support, and faster git branch reads.

└──▷ GET THIS VERSION

$ git clone --branch v0.18.5 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.18.5

›Adds Requesty as a new model provider.
›Supports MCP resources and reliably surfaces MCP prompts.
›Reads the current git branch directly from .git instead of spawning a git subprocess, reducing overhead in large repos.

Was this useful?

◆ Local LLM Runtimes

llama.cpp

b9748 3 RELEASES · 2026-06-21 NOTES STABLE

llama.cpp b9748 adds a verbose field to the server schema for richer response metadata.

└──▷ GET THIS VERSION

$ git clone --branch b9748 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9748

›Adds verbose field to the llama.cpp server response schema, enabling clients to request detailed inference metadata.

2 more releases in this issue · 2026-06-21

b9747 NOTES STABLE

llama.cpp b9747 adds real-time model load progress tracking via a new /models/sse SSE endpoint.

└──▷ GET THIS VERSION

$ git clone --branch b9747 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9747

└──▷ TRY IT

Stream model load progress in real time while the server is initializing a model — useful for monitoring long loads in automation or a UI.

$ curl -N http://localhost:8080/models/sse

›Adds GET /models/sse Server-Sent Events endpoint to the llama.cpp server for real-time model load progress tracking.

b9745 NOTES STABLE

llama.cpp b9745 adds speculative decoding support for Step3.5/3.7 flash MTP via new llama_set_mtp_layer_offset and llama_model_n_nextn_layer APIs.

└──▷ GET THIS VERSION

$ git clone --branch b9745 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9745

›Adds llama_set_mtp_layer_offset and llama_model_n_nextn_layer API functions to support speculative multi-token prediction (MTP) for Step3.5 and Step3.7 flash models.
›Adds mtp_layer_offset configuration and nextn flags with graph reuse support, enabling speculative multi-head draft and process pipelines for MTP blocks.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · June 21, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -059, June 21, 2026

OpenClaw

SST OpenCode

Alibaba Qwen Code

llama.cpp