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 -266, November 24, 2025

THE AI TOOLCHAIN NO. -266
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED NOVEMBER 24, 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   # 9 tools matched
AI & LLM Tooling
◆  AI Coding Agents

GitHub Copilot CLI

Sources Release notes → v0.0.363 NOTES

GitHub Copilot CLI v0.0.363 adds three new models, GITHUB_ASKPASS auth support, and MCP servers in --prompt mode.

└──▷ GET THIS VERSION
$ git clone --branch v0.0.363 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v0.0.363
  • ›Adds GITHUB_ASKPASS environment variable support for non-interactive authentication flows.
  • ›Enables MCP servers to work in --prompt mode.
  • ›Adds Opus 4.5, GPT-4.1, and GPT-5-Mini as available models in GitHub Copilot CLI.
  • ›Image data paste now prioritizes pasting the contents of image files instead of their file icons.
Was this useful?

SST OpenCode

Sources Release notes → v1.0.109 2 RELEASES · 2025-11-24 NOTES STABLE

The open source coding agent.

OpenCode v1.0.109 adds --refresh flag for model list updates and an autoupdate notification feature.

└──▷ GET THIS VERSION
$ git clone --branch v1.0.109 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.109
└──▷ TRY IT
Force-refresh the cached model list after adding a new provider or when models seem stale.
$ opencode models --refresh
  • ›Adds --refresh flag to the models command to force-refresh the available model list.
  • ›Adds autoupdate notification feature to alert users when a new version is available.
1 more release in this issue · 2025-11-24
v1.0.107 NOTES STABLE

OpenCode v1.0.107 adds clearer GitHub Copilot model errors and improved conversation title generation.

└──▷ GET THIS VERSION
$ git clone --branch v1.0.107 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.107
  • ›Adds actionable error message for unsupported GitHub Copilot models, including a direct link to enable models in Copilot settings.
  • ›Adds explicit fallback model handling when the opencode provider is unavailable.
  • ›Improves title generation guidelines for more meaningful conversation titles.
Was this useful?

Alibaba Qwen Code

Sources Release notes → v0.3.0-preview.0 2 RELEASES · 2025-11-24 NOTES STABLE

Qwen Code v0.3.0-preview.0 adds stream-JSON I/O for programmatic headless use and full internationalization support.

└──▷ GET THIS VERSION
$ git clone --branch v0.3.0-preview.0 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.3.0-preview.0
└──▷ TRY IT
Pipe structured JSON commands into Qwen Code headlessly and receive stream-JSON responses for programmatic integration in a CI pipeline or script.
$ qwen --input-format stream-json --output-format stream-json
  • ›Adds stream-json as a supported value for --input-format and --output-format in headless mode, enabling programmatic machine-readable I/O.
  • ›Adds internationalization (i18n) support for both UI strings and LLM output.
1 more release in this issue · 2025-11-24
v0.3.0-nightly.20251124.c9af7481 NOTES STABLE

Qwen Code v0.3.0-nightly adds stream-json format for programmatic headless use and full internationalization support.

└──▷ GET THIS VERSION
$ git clone --branch v0.3.0-nightly.20251124.c9af7481 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.3.0-nightly.20251124.c9af7481
└──▷ TRY IT
Pipe structured commands into Qwen Code headlessly and receive streaming JSON output — useful for driving the tool from scripts or CI pipelines.
$ qwen --input-format stream-json --output-format stream-json
  • ›Adds stream-json as a supported value for --input-format and --output-format in headless mode, enabling programmatic/machine-readable streaming JSON I/O.
  • ›Adds internationalization (i18n) support for both UI strings and LLM output.
Was this useful?

Zed

Sources Release notes → v0.213.7 NOTES

Zed v0.213.7 adds Claude Opus 4.5 model support.

└──▷ GET THIS VERSION
$ git clone --branch v0.213.7 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.213.7
  • ›Adds support for Claude Opus 4.5 as an available AI model.
  • ›Adds workspace panels as soon as they are ready, reducing startup latency before panels are usable.
Was this useful?
◆  AI Agent Frameworks

LangChain

Sources Release notes → langchain==1.1.0 2 RELEASES · 2025-11-24 NOTES STABLE

LangChain 1.1 adds ModelRetryMiddleware, async summarization, and SystemMessage support in create_agent.

└──▷ GET THIS VERSION
$ git clone --branch langchain==1.1.0 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:
$ git checkout langchain==1.1.0
  • ›Adds ModelRetryMiddleware for automatic retry handling at the model middleware layer.
  • ›Supports SystemMessage via the system_prompt parameter in create_agent.
  • ›Supports async summarization in SummarizationMiddleware.
  • ›Adds model context window awareness to SummarizationMiddleware to control when summarization is triggered.
  • ›Distributes model profiles data across packages, enabling provider strategy references for model selection.
1 more release in this issue · 2025-11-24
langchain-perplexity==1.1.0 NOTES STABLE

langchain-perplexity 1.1 adds a dedicated output parser for Perplexity reasoning model responses.

└──▷ GET THIS VERSION
$ git clone --branch langchain-perplexity==1.1.0 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:
$ git checkout langchain-perplexity==1.1.0
  • ›Adds a dedicated output parser to correctly handle and structure responses from Perplexity reasoning models.
  • ›Extends usage metadata to include the full set of keys returned by the Perplexity API.
Was this useful?

LangChain LangGraph

Sources Release notes → sdk==0.2.10 NOTES

Build resilient agents.

LangGraph Python SDK 0.2.10 adds name filtering to Assistants search and cursory Python 3.14 support.

└──▷ GET THIS VERSION
$ git clone --branch sdk==0.2.10 https://github.com/langchain-ai/langgraph.git
# already have the repo? check out this version:
$ git checkout sdk==0.2.10
└──▷ USE IT
Filter the Assistants search results to a specific assistant name instead of iterating all assistants.
python 
assistants = await client.assistants.search(name="my-assistant")
  • ›Adds name parameter to the Assistants search API, enabling filtering assistants by name.
  • ›Adds cursory Python 3.14 support.
└──▷ BREAKING ON UPGRADE
  • !Python 3.9 is no longer supported; projects running on Python 3.9 must upgrade their runtime.
Was this useful?
Other / Uncategorized
◆  AI OBSERVABILITY

Arize Phoenix

Sources Release notes → arize-phoenix-client-v1.25.0 2 RELEASES · 2025-11-24 NOTES STABLE

Phoenix client v1.25.0 adds evaluation helpers for pulling RAG spans.

└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-client-v1.25.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.25.0
  • ›Adds evaluation helper utilities to simplify pulling RAG spans for downstream evaluation workflows.
1 more release in this issue · 2025-11-24
arize-phoenix-v12.17.0 NOTES STABLE

Phoenix 12.17.0 enables playground repetitions for manual invocations and relicenses the client to Apache 2.0.

└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v12.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.17.0
  • ›Enables repetitions for manual playground invocations, allowing users to run the same prompt multiple times in a single session.
  • ›Switches the Phoenix client license to Apache 2.0.
  • ›Improves the UX of the retention policy form.
Was this useful?

Langfuse

Sources Release notes → v3.134.0 NOTES

Langfuse v3.134.0 adds extra TLS options for Redis and new ClickHouse performance tuning controls.

└──▷ GET THIS VERSION
$ git clone --branch v3.134.0 https://github.com/langfuse/langfuse.git
# already have the repo? check out this version:
$ git checkout v3.134.0
  • ›Adds extra TLS configuration options for Redis connections via new REDIS_* TLS settings.
  • ›Adds support for ClickHouse lightweight delete mode (requires ClickHouse >=25.5), configurable via a new environment variable, improving storage reclaim performance.
  • ›Improves query performance for OpenTelemetry projects by opting out of the FINAL modifier on observations reads in ClickHouse.
Was this useful?
◆  VECTOR DB RAG

Weaviate

Sources Release notes → v1.33.5 2 RELEASES · 2025-11-24 NOTES STABLE

Weaviate v1.33.5 adds Geo HNSW index config, replication scaling API, VoyageAI v3.5 models, Cohere dimensions setting, and Google batch API support.

└──▷ GET THIS VERSION
$ git clone --branch v1.33.5 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout v1.33.5
└──▷ TRY IT
Configure a Cohere vectorizer with a specific output dimensions value when creating a class schema.
$ curl -X POST 'http://localhost:8080/v1/schema' -H 'Content-Type: application/json' -d '{"class": "Article", "vectorizer": "text2vec-cohere", "moduleConfig": {"text2vec-cohere": {"dimensions": 256}}}'
  • ›Adds a replication scaling API endpoint accepting collection and replication factor parameters via the updated replication scale URL to trigger replica scaling operations.
  • ›Adds dimensions setting support in Cohere vectorizer modules, enabling control over output embedding dimensions.
  • ›Adds batch API support in the text2vec-google module for more efficient bulk vectorization.
  • ›Adds ability to configure Geo HNSW Index settings, enabling tuning of the HNSW index for geo-type properties.
  • ›Introduces VoyageAI's v3.5 models as supported embedding options in the VoyageAI module.
+2 moreshow less
  • ›Adds support for Amazon Nova Multimodal Embeddings model in Weaviate modules.
  • ›Adds support for the newest Anthropic models in the generative-anthropic module.
1 more release in this issue · 2025-11-24
v1.32.17 NOTES STABLE

Weaviate v1.32.17 adds VoyageAI v3.5 models, Amazon Nova Multimodal Embeddings, Geo HNSW config, replication scaling, and Cohere dimensions support.

└──▷ GET THIS VERSION
$ git clone --branch v1.32.17 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout v1.32.17
  • ›Adds dimensions setting to Cohere modules for controlling embedding output size.
  • ›Adds Geo HNSW Index settings configuration, enabling tunable HNSW parameters for geo-indexed collections.
  • ›Adds a replication scaling plan API, updated to include collection and replication factor parameters in the scale URL.
  • ›Adds support for batch API in the text2vec-google module for higher-throughput vectorization.
  • ›Introduces VoyageAI v3.5 models as supported embedding options.
+2 moreshow less
  • ›Adds support for Amazon Nova Multimodal Embeddings model in the modules layer.
  • ›Adds support for the newest Anthropic models in the generative-anthropic module.
Was this useful?
// END OF TRANSMISSION

The AI Toolchain · curated daily · November 24, 2025
Releases & features from the open-source and commercial AI tools that practitioners actually run.

▷ Subscribe
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 →