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 -242, December 18, 2025

THE AI TOOLCHAIN NO. -242
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED DECEMBER 18, 2025 · 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   # 11 tools matched
AI & LLM Tooling
◆  AI Agent Frameworks

Agno (formerly Phidata)

Sources Release notes → v2.3.15 NOTES

Agno v2.3.15 adds OpenRouter cost tracking in run metrics and a migrate-all-DBs endpoint via AgentOS.

└──▷ GET THIS VERSION
$ git clone --branch v2.3.15 https://github.com/agno-agi/agno.git
# already have the repo? check out this version:
$ git checkout v2.3.15
  • Adds a cost field to run Metrics for OpenRouter-backed runs, enabling usage accounting across OpenRouter provider calls.
  • Adds an endpoint to migrate all databases at once via AgentOS.
Was this useful?
◆  AI Coding Agents

Charm Crush

Sources Release notes → v0.28.0 NOTES

Glamourous agentic coding for all

Crush v0.28.0 adds env-var overrides for config directories and Hyper/Copilot login via onboarding.

└──▷ GET THIS VERSION
$ git clone --branch v0.28.0 https://github.com/charmbracelet/crush.git
# already have the repo? check out this version:
$ git checkout v0.28.0
  • Adds ability to set environment variables to override config directories.
  • Enables Hyper and GitHub Copilot login directly through the onboarding flow.
Was this useful?

GitHub Copilot CLI

Sources Release notes → v0.0.370 NOTES

GitHub Copilot CLI v0.0.370 adds --available-tools and --excluded-tools flags, STDIO MCP server type, and SHA256 checksum publishing.

└──▷ GET THIS VERSION
$ git clone --branch v0.0.370 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v0.0.370
  • Adds --available-tools and --excluded-tools CLI flags to filter which tools the model can use during a session.
  • Adds STDIO as a synonymous type for Local when configuring MCP servers in the CLI configuration UI.
  • Publishes SHA256 checksums for CLI executables alongside each release.
  • Diff display now uses your configured git pager (e.g. delta, diff-so-fancy) instead of the default pager.
  • Loads CA certificates from system stores and environment variables, enabling use in corporate/proxy environments.
+4 moreshow less
  • Improves /model error messages to show which models are available and which are unavailable.
  • Model picker adopts a two-column layout with aligned multipliers and clearer visual indicators.
  • Log levels now output all messages at the specified level and higher severity.
  • Uses the platform-specific executable from npm install when available.
Was this useful?

Block Goose

Sources Release notes → v1.17.0 NOTES

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Goose v1.17.0 adds Inception provider, MCP elicitation, external server support, OpenAI streaming, and new built-in recipes.

└──▷ GET THIS VERSION
$ git clone --branch v1.17.0 https://github.com/block/goose.git
# already have the repo? check out this version:
$ git checkout v1.17.0
  • Adds Code Mode MCP platform extension for enhanced code execution capabilities via tool calling.
  • Supports MCP elicitation, enabling interactive prompts during tool execution.
  • Enables connection to an external goosed server backend.
  • Adds Inception provider, bringing Mercury model support to Goose.
  • Adds streaming support for the OpenAI responses API.
+5 moreshow less
  • Introduces canonical (standardized) model definitions across providers.
  • Adds search bar and filtering to the recipes view.
  • Enables automatic provider detection from API key during onboarding.
  • Adds built-in DataHub recipe for searching and understanding data in DataHub.
  • Adds built-in Flutter PR Code Review recipe for reviewing Flutter pull requests.
Was this useful?

OpenAI Codex CLI

Sources Release notes → rust-v0.74.0 NOTES

Lightweight coding agent that runs in your terminal

Codex CLI gains gpt-5.2-codex model, a new /experimental slash command, model picker UI, and configurable ghost-snapshot warnings.

└──▷ GET THIS VERSION
$ git clone --branch rust-v0.74.0 https://github.com/openai/codex.git
# already have the repo? check out this version:
$ git checkout rust-v0.74.0
└──▷ TRY IT
Access experimental features mid-session without restarting the CLI.
$ /experimental
  • New /experimental slash command for accessing experimental features from within the CLI.
  • New model picker UI for selecting models interactively.
  • Adds config option to disable ghost snapshot warnings.
  • Supports SYSTEM-level skills, expanding the skills system beyond user-defined entries.
  • Adds public skills discovery with improved repo skill discovery and error UX.
+4 moreshow less
  • TypeScript SDK gains xhigh reasoning effort support.
  • Model list loading is now non-blocking, improving startup responsiveness.
  • Constrains allowed values for approval_policy config field.
  • Sandboxes the .codex sub-folder as read-only when it resides inside a writable root.
Was this useful?

SST OpenCode

Sources Release notes → v1.0.168 2 RELEASES · 2025-12-18 NOTES STABLE

The open source coding agent.

OpenCode v1.0.168 adds Ty language server support, a TUI fork slash command, shell mode for desktop, and OIDC_BASE_URL for custom GitHub App installs.

└──▷ GET THIS VERSION
$ git clone --branch v1.0.168 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.168
└──▷ TRY IT
Fork the current session without leaving the keyboard when working in the TUI.
$ /fork
  • Adds experimental support for the Ty language server.
  • New /fork slash command in the TUI enables keyboard-friendly session forking.
  • Adds shell mode for the desktop app.
  • Supports OIDC_BASE_URL for custom GitHub App installs.
  • Removes interleaved thinking filter for certain Kimi K2 thinking model providers.
1 more release in this issue · 2025-12-18
v1.0.167 NOTES STABLE

OpenCode v1.0.167 adds a terminal title disable option, copy-logs button on server spawn failure, and improved MCP OAuth handling.

└──▷ GET THIS VERSION
$ git clone --branch v1.0.167 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.167
└──▷ TRY IT
Suppress terminal title changes when running OpenCode inside a multiplexer or logging pipeline that is sensitive to escape sequences.
$ OPENCODE_DISABLE_TERMINAL_TITLE=1 opencode
  • Adds option to disable terminal title in the TUI via the OPENCODE_DISABLE_TERMINAL_TITLE environment variable.
  • Adds a 'Copy Logs' button to the server spawn failure dialog in the Tauri desktop app for easier debugging.
  • Improves MCP authentication and OAuth state handling.
Was this useful?

Earendil Works Pi

Sources Release notes → v0.23.4 NOTES

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Pi v0.23.4 adds syntax highlighting for code blocks and word-level intra-line diff highlighting in the Edit tool.

└──▷ GET THIS VERSION
$ git clone --branch v0.23.4 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.23.4
  • Adds syntax highlighting for markdown code blocks, read tool output, and write tool content using theme-aware VS Code-style colors.
  • Edit tool now shows word-level (intra-line) diff highlighting with inverse highlighting for single-line changes; multi-line changes display all removed lines before added lines.
Was this useful?

Alibaba Qwen Code

Sources Release notes → v0.5.1-nightly.20251218.8106a6b0 NOTES

Qwen Code v0.5.1 adds a /resume command for session switching, a chat recording toggle, and a gitCoAuthor setting.

└──▷ GET THIS VERSION
$ git clone --branch v0.5.1-nightly.20251218.8106a6b0 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.5.1-nightly.20251218.8106a6b0
└──▷ USE IT
Persist a git co-author on all commits made through Qwen Code without typing it each time.
json
{
  "gitCoAuthor": "Jane Doe <[email protected]>"
}
Resume a previous session mid-conversation to continue work without losing context.
$ /resume
  • Adds gitCoAuthor setting to settings.json to configure git co-author attribution in commits.
  • Adds /resume slash command to switch between existing sessions from the CLI.
  • Adds a chat recording toggle accessible via CLI and the settings UI.
Was this useful?

Zed

Sources Release notes → v0.217.3 NOTES

Zed v0.217.3 adds unformatted paste support in the Agent panel via Ctrl/Cmd+Shift+V.

└──▷ GET THIS VERSION
$ git clone --branch v0.217.3 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.217.3
  • Adds ctrl/cmd+shift+v in the Agent panel to paste code without formatting.
Was this useful?
◆  AI Model & Data Infrastructure

Ollama

Sources Release notes → v0.13.5 NOTES

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Ollama v0.13.5 adds BERT model support, DeepSeek-V3.1 tool parsing, and the FunctionGemma function-calling model.

└──▷ GET THIS VERSION
$ git clone --branch v0.13.5 https://github.com/ollama/ollama.git
# already have the repo? check out this version:
$ git checkout v0.13.5
  • Adds built-in renderer and tool parsing for DeepSeek-V3.1, enabling structured function-calling workflows with that model.
  • New functiongemma model available: a Gemma 3 270M variant fine-tuned explicitly for function calling.
Was this useful?
Other / Uncategorized
◆  VECTOR DB RAG

Weaviate

Sources Release notes → v1.35.0 NOTES

Weaviate v1.35.0 adds object TTL, HFresh vector index, multi2multivec-weaviate module, zstd backup compression, and internal gRPC clustering.

└──▷ GET THIS VERSION
$ git clone --branch v1.35.0 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout v1.35.0
  • Adds Object TTL (Time To Live) support: objects automatically expire based on configurable time-to-live settings, with a dedicated TTL status endpoint, a post-search filter for TTL-based queries, and automatic enabling of index timestamps for creation and update times.
  • Introduces the multi2multivec-weaviate module, enabling multi-to-multi-vector embeddings using Weaviate as the backend vectorizer.
  • Adds dimensions setting support to Cohere vectorizer and reranker modules for controlling embedding output size.
  • Adds BaseURL setting to Cohere's reranker module, enabling routing to custom or self-hosted Cohere-compatible endpoints.
  • Adds batch API support to the text2vec-google module, reducing latency and API call overhead for large ingestion workloads.
+10 moreshow less
  • Adds naive batch processing logic across text2vec and multi2vec modules for more efficient vectorization during bulk operations.
  • Introduces VoyageAI v3.5 models and voyage-3-large support in the VoyageAI vectorizer module.
  • Adds knowledge setting support to the Contextual AI module integration.
  • Adds kagome tokenizer per-class user dictionary support for Japanese text processing.
  • Renames the SPFresh vector index to HFresh, with updated defaults, dedicated merge queue, metadata stored in LSM store, shared bucket architecture, and compressed centroids.
  • Adds zstd compression support for backups, reducing backup storage footprint.
  • Makes file chunk size configurable for the file replication service in distributed deployments.
  • Introduces an internal gRPC server as a REST cluster API equivalent, with connection manager, maintenance mode interceptor, and gzip compression for file copy service.
  • Introduces Acks sub-message to the BatchStreamReply gRPC message for improved replication acknowledgement signaling.
  • Adds replication scaling plan with a scale URL that includes collection and replication factor parameters.
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 →