Heads up This site is currently under heavy development.
Subscribe Get it delivered — the daily firehose, filtered to the tools you run, plus the documentation changes vendors never announce. Compare plans →

The AI Toolchain — issue -116, April 25, 2026

THE AI TOOLCHAIN NO. -116
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED APRIL 25, 2026 · EVERY WEEKDAY
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   # 6 tools matched
AI & LLM Tooling
◆  AI Agent Frameworks

OpenClaw

Sources Release notes → v2026.4.24 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2026.4.24 adds Google Meet, DeepSeek V4, realtime voice loops, coordinate-click browser automation, and OTEL diagnostics.

└──▷ GET THIS VERSION
$ git clone --branch v2026.4.24 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.24
└──▷ TRY IT
Verify Twilio/provider readiness before placing a live voice test call — the smoke command is dry-run by default.
$ openclaw voicecall smoke
Click a specific viewport coordinate during headless browser automation, useful when element selectors are unavailable.
$ openclaw browser click-coords 640 480
Recover an already-open Google Meet tab so the agent can inspect it without opening a duplicate, and check OAuth health.
$ openclaw googlemeet doctor --oauth
Establish full cross-signing identity trust for self-device verification on a Matrix deployment.
$ openclaw matrix verify self
  • Adds a bundled Google Meet participant plugin with personal Google auth, Chrome/Twilio realtime transports, paired-node chrome-node support, artifact/attendance exports, and googlemeet doctor --oauth / recover-tab recovery tooling.
  • Adds DeepSeek V4 Flash and V4 Pro to the bundled model catalog; V4 Flash becomes the new onboarding default.
  • Enables realtime voice loops backed by the full OpenClaw agent (openclaw_agent_consult) in Talk, Voice Call, and Google Meet sessions.
  • Adds a Gemini Live realtime voice provider for Voice Call and Google Meet audio bridges, with bidirectional audio and function-call support.
  • Adds a Gateway realtime brain WebSocket endpoint backed by Gemini Live, with owner-auth gating and async OpenClaw tool handoff.
+19 moreshow less
  • Adds viewport coordinate-click support for browser automation, accessible via openclaw browser click-coords for CLI use.
  • Adds browser.actionTimeoutMs config with a 60-second default action budget to prevent healthy long browser waits from timing out.
  • Supports per-profile browser.profiles.<name>.headless overrides so individual browser profiles can run headless independently.
  • Adds voicecall setup and a dry-run-by-default voicecall smoke command to verify Twilio/provider readiness before a live call.
  • Adds openclaw matrix verify self to establish full cross-signing identity trust for self-device verification from the CLI.
  • Adds a bundled Gradium text-to-speech provider with voice-note and telephony output support.
  • Exposes raw vectorScore and textScore alongside the combined score on hybrid memory search results for retrieval contribution inspection.
  • Adds agents.defaults.contextInjection: "never" config option to disable workspace bootstrap file injection for agents that fully own their prompt lifecycle.
  • Adds disabled-by-default gateway.nodes.pairing.autoApproveCidrs for automated first-time node pairing from explicit trusted CIDRs.
  • Exports run, model-call, and tool-execution lifecycle events as OTEL spans, with opt-in diagnostics.otel.captureContent controls for content attributes.
  • Refines the agent Tool Access panel with compact live-tool chips, collapsible tool groups, direct per-tool toggles, and runtime/source provenance display.
  • Adds a Steer action on queued chat messages so a browser follow-up can be injected into the active run without retyping it.
  • Adds a modelCatalog plugin manifest contract for provider-owned model rows, aliases, and suppression rules without loading plugin runtime.
  • Moves local PDF extraction into a bundled document-extract plugin, decoupling pdfjs-dist from core.
  • Moves Bonjour LAN Gateway discovery advertising into a default-enabled bundled plugin so users can disable it without affecting wide-area discovery.
  • Adds a central plugin compatibility registry with dated migration metadata for SDK/config/setup/runtime deprecation records.
  • Speeds up openclaw models list with static catalogs for bundled providers and narrower registry enumeration.
  • Lets Gemini TTS prepend configured audioProfile and speakerName prompt text for reusable speech-style control.
  • Exposes activation plan reasons and a richer plan API so callers can inspect why a plugin was selected.
└──▷ BREAKING ON UPGRADE
  • !The Pi-only api.registerEmbeddedExtensionFactory(...) compatibility path is removed; bundled tool-result rewrites must now use api.registerAgentToolResultMiddleware(...) with contracts.agentToolResultMiddleware declaring the targeted harnesses.
Was this useful?

PydanticAI

Sources Release notes → v1.87.0 NOTES

PydanticAI v1.87.0 adds deferred tool call handling, event stream processing capability, and GPT-5.5 thinking support.

└──▷ GET THIS VERSION
$ git clone --branch v1.87.0 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:
$ git checkout v1.87.0
  • Adds HandleDeferredToolCalls capability and handle_deferred_tool_calls hook for handling deferred tool calls in agent workflows.
  • Adds ProcessEventStream capability for processing event streams from model responses.
  • Supports the thinking setting for GPT-5.5 models.
Was this useful?
◆  AI Coding Agents

SST OpenCode

Sources Release notes → v1.14.25 NOTES

The open source coding agent.

OpenCode v1.14.25 adds Roslyn LSP support for Razor, .cshtml, and C# script files, and richer LSP permission prompts.

└──▷ GET THIS VERSION
$ git clone --branch v1.14.25 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.14.25
  • Adds Roslyn LSP support for Razor, .cshtml, and C# script files.
  • LSP permission prompts now include request details such as the operation, file, and cursor position.
Was this useful?
◆  Local LLM Runtimes

llama.cpp

Sources Release notes → b8929 NOTES

llama.cpp b8929 changes the default quantization type in llama_model_quantize_params from Q5_1 to Q8_0.

└──▷ GET THIS VERSION
$ git clone --branch b8929 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8929
  • Changes the default ftype in llama_model_quantize_params from LLAMA_FTYPE_MOSTLY_Q5_1 to LLAMA_FTYPE_MOSTLY_Q8_0, so programs using default quantization params now produce higher-quality Q8_0 models instead of the older Q5_1 format.
└──▷ BREAKING ON UPGRADE
  • !The default ftype field in llama_model_quantize_params is changed from LLAMA_FTYPE_MOSTLY_Q5_1 to LLAMA_FTYPE_MOSTLY_Q8_0; any code that relies on the default quantization type without explicitly setting ftype will now produce Q8_0 output instead of Q5_1.
Was this useful?
Other / Uncategorized
◆  AI OBSERVABILITY

Arize Phoenix

Sources Release notes → arize-phoenix-client-v2.5.0 NOTES

Phoenix client v2.5.0 adds a trace note REST endpoint for the Phoenix CLI.

└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-client-v2.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.5.0
  • Adds a trace note REST endpoint accessible via the Phoenix CLI, enabling programmatic annotation of traces.
Was this useful?
◆  MCP TOOLING

Composio

Sources Release notes → @composio/[email protected] NOTES

Composio CLI gains a connection removal command in v0.2.26.

└──▷ GET THIS VERSION
$ git clone --branch @composio/[email protected] https://github.com/ComposioHQ/composio.git
# already have the repo? check out this version:
$ git checkout @composio/[email protected]
  • Adds a connection removal command to the Composio CLI, enabling practitioners to delete existing connections directly from the command line.
Was this useful?
my-toolchain — 0 tools
paste an install list to detect your tools

A brew list, a Brewfile, requirements.txt, a Dockerfile — or just the product names, free-form. Nothing leaves your browser.

    browse all tools →