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.
Qwen Code v0.2.1-nightly adds TodoWriteTool and TaskTool support in the Zed editor integration.
└──▷ GET THIS VERSION
$ git clone --branch v0.2.1-nightly.20251113.d5d96c72 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout v0.2.1-nightly.20251113.d5d96c72
›Adds TodoWriteTool and TaskTool support to the Zed editor integration, expanding agentic task and todo tracking workflows within Zed.
›Standardizes tool naming and configuration system across the codebase.
An open-source AI agent that brings the power of Gemini directly into your terminal.
gemini-cli v0.16.0-nightly adds hook result aggregation, a safety checker framework, and the write_todo tool.
└──▷ GET THIS VERSION
$ git clone --branch v0.16.0-nightly.20251113.ad1f0d99 https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:$ git checkout v0.16.0-nightly.20251113.ad1f0d99
›Adds Hook Result Aggregation, enabling multiple hook outputs to be combined and surfaced together.
›Introduces a safety checker framework for validating tool actions before execution.
›Enables the write_todo tool for managing task lists directly within the CLI.
›Always displays the internal tool name in /tools output for clearer tool identification.
›Adds AzureOpenAIResponsesChatGenerator component bringing the same Responses API capabilities to Azure OpenAI deployments, configured via azure_endpoint and azure_deployment.
›Returns logprobs in ChatMessage.meta for OpenAIChatGenerator and OpenAIResponsesChatGenerator when logprobs are enabled in generation_kwargs.
›Adds extra field to ToolCall and ToolCallDelta dataclasses to store provider-specific information.
›Adds run_async() method to SentenceWindowRetriever for use in async pipelines and workflows.
+8 moreshow less
›Adds warm_up() method to OpenAIChatGenerator, AzureOpenAIChatGenerator, HuggingFaceAPIChatGenerator, HuggingFaceLocalChatGenerator, and FallbackChatGenerator to initialize tools before pipeline execution without requiring an Agent component.
›Adds return_only_referenced_documents parameter (default: True) to AnswerBuilder, plus source_index (1-based) and referenced (boolean) fields in returned document meta dictionaries.
›Adds generation_kwargs parameter to the Agent component for run-time control over chat generation.
›Adds revision parameter to SentenceTransformersDocumentEmbedder, SentenceTransformersTextEmbedder, SentenceTransformersSparseDocumentEmbedder, and SentenceTransformersSparseTextEmbedder for pinning a specific model version from the Hugging Face Hub.
›Updates PipelineSnapshots serialization and deserialization to work with pydantic BaseModels.
›Updates Agent, LLMMetadataExtractor, LLMMessagesRouter, and LLMDocumentContentExtractor to automatically call self.warm_up() at runtime if not already warmed up, removing the need for a manual pre-call.
›Improves log-trace correlation for DatadogTracer using ddtrace.tracer.get_log_correlation_context().
›Redesigns Toolset.warm_up() so the base method warms all tools by default, with subclasses able to override for custom initialization; simplifies warm_up_tools() to delegate to Toolset.warm_up().
$ git clone --branch langchain-groq==1.0.1 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain-groq==1.0.1
›Adds prompt caching token usage details to Groq chat model responses, surfacing cache-related token counts alongside standard usage metrics.
langchain-deepseek 1.0.1 adds support for DeepSeek's strict beta structured output mode.
└──▷ GET THIS VERSION
$ git clone --branch langchain-deepseek==1.0.1 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain-deepseek==1.0.1
›Supports the strict beta structured output parameter for DeepSeek models, enabling stricter schema enforcement on model responses.
PydanticAI v1.15.0 adds run IDs across run/message classes and token-counting support for BedrockConverseModel.
└──▷ GET THIS VERSION
$ git clone --branch v1.15.0 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:$ git checkout v1.15.0
└──▷ USE IT
Enforce a pre-request token budget on a Bedrock-backed agent — now possible because BedrockConverseModel supports count_tokens.
python
from pydantic_ai import Agent
from pydantic_ai.models.bedrock import BedrockConverseModel
from pydantic_ai.usage import UsageLimits
model = BedrockConverseModel('anthropic.claude-3-5-sonnet-20241022-v2:0')
agent = Agent(model)
result = await agent.run(
'Summarise this document',
usage_limits=UsageLimits(request_tokens_limit=8000, count_tokens_before_request=True),
)
Correlate log entries or trace spans from a single agent run using the new run_id available on the result.
python
result = await agent.run('What is the capital of France?')
print(result.run_id) # e.g. 'a3f1c2d4-...'
# Use result.run_id to filter logs or link all messages from this run
›Adds BedrockConverseModel.count_tokens method, enabling UsageLimits.count_tokens_before_request to work with Bedrock-backed agents.
›Adds a unique run_id field to run, run result, and message (request and response) classes for correlating events across a single agent run.
›Wraps BedrockConverseModel errors in ModelHTTPError, making Bedrock failures handled correctly when used inside a FallbackModel.
Langfuse v3.132.0 adds comment exports, CSV schema mapping for datasets, expanded media types, and auth timeout options.
└──▷ GET THIS VERSION
$ git clone --branch v3.132.0 https://github.com/langfuse/langfuse.git
# already have the repo? check out this version:$ git checkout v3.132.0
›Adds LANGFUSE_AUTH_TIMEOUT (and related auth timeout options) plus auth proxy setup fixes via new environment variable support for self-hosted deployments.
›Exports now include comments for traces, observations, and sessions.
›Supports schema mapping when importing datasets via CSV in the datasets UI.
›Adds additional supported media content types for media attachments.
›Adds IO read-time extraction of compact representations in IO table cells.
THE AI TOOLCHAIN