Backfill issue -334 — 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   # 8 tools matched

AI & LLM Tooling

◆ AI Coding Agents

Continue

@continuedev/[email protected] 3 RELEASES · 2025-09-16 NOTES STABLE

Continue config-yaml 1.15.0 adds capability-based exclusion of single-file edit mode for capable models.

└──▷ GET THIS VERSION

$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]

›Adds exclusion of single-file edit mode for models flagged as capable, allowing more powerful models to bypass single-file edit constraints.

2 more releases in this issue · 2025-09-16

@continuedev/[email protected] NOTES STABLE

Continue fetch 1.2.0 adds the ability to exclude single-file edit mode for capable models.

└──▷ GET THIS VERSION

$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]

›Adds the ability to exclude single-file edit mode for models that support more capable editing workflows.

@continuedev/[email protected] NOTES STABLE

Continue 1.14.0 adds HuggingFace router detection, Qwen2.5VL image autodetect, and diff stats in the find-and-replace toolbar.

└──▷ GET THIS VERSION

$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:
$ git checkout @continuedev/[email protected]

›Adds HuggingFace OpenAI-compatible router auto-detection so models served through HuggingFace's routing layer are identified correctly without manual configuration.
›Autodetects image support for Qwen2.5VL models, enabling vision workflows without manually flagging the capability.
›Shows diff stats (lines added/removed) in the find-and-replace toolbar for at-a-glance change awareness.
›Includes model identity in tool call stats, making it possible to attribute latency and usage to specific models.
›Auto-selects scope for org API keys in Continue Network, reducing setup friction for organization-level deployments.

Was this useful?

SST OpenCode

v0.9.3 NOTES

The open source coding agent.

OpenCode v0.9.3 adds npm package tracking and special reasoning support for the opencode provider.

└──▷ GET THIS VERSION

$ git clone --branch v0.9.3 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v0.9.3

›Adds npm package tracking to provider model mapping for more accurate model resolution.
›Implements special reasoning handling for the opencode provider.
›Updates provider options mapping to use npm package names.

Was this useful?

◆ AI Agent Frameworks

LangChain

langchain-tests==1.0.0a1 NOTES

langchain-tests 1.0.0a1 ships initial standard test suites for chat models, vector stores, tools, retrievers, embeddings, caches, and BaseStore.

└──▷ GET THIS VERSION

$ git clone --branch langchain-tests==1.0.0a1 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:
$ git checkout langchain-tests==1.0.0a1

›Adds a property to skip relevant tests when a vector store does not support get_by_ids().
›Adds a property to set the name of the parameter for the number of results to return in vector store tests.
›Adds standard unit and integration test suites for vector stores, including get_by_ids, aget_by_ids, upsert, and aupsert_by_ids coverage.
›Adds standard read/write test suite for vector stores.
›Adds combined sync/async vector store standard test suites.

+15 moreshow less

›Adds standard tests for BaseStore, including an idempotent test_set_values_is_idempotent assertion.
›Adds standard tests for cache.
›Adds standard tests for embeddings.
›Adds standard tests for retrievers.
›Adds standard tests for tool calling, including async tool calling, runnables as tools, binding regular Python functions as tools, and content_and_artifact tool handling.
›Adds standard tests for structured output including BaseModel variations, async structured output, and JSON mode.
›Adds standard tests for chat model capabilities: basic conversation, few-shot examples, stop sequences, tool call messages, ToolMessage.status='error', Message.name, streaming usage metadata, and double-message sequences.
›Adds standard tests for serialization/deserialization (test_serdes) and initialization from environment variables.
›Supports PDF and audio input in Chat Completions format standard tests.
›Adds simple agent loop standard test.
›Adds cache_control to Anthropic inputs standard test.
›Allows subclasses to add additional non-standard tests.
›Allows test_serdes for packages outside the default valid namespaces.
›Adds benchmarks to the standard test suite.
›Drops Python 3.9 support for langchain-tests.

└──▷ BREAKING ON UPGRADE

!Python 3.9 is no longer supported by langchain-tests; the minimum supported version is now Python 3.10.

Was this useful?

Microsoft Semantic Kernel

python-1.37.0 NOTES

Semantic Kernel Python 1.37.0 adds an NVIDIA chat completion AI connector.

└──▷ GET THIS VERSION

$ git clone --branch python-1.37.0 https://github.com/microsoft/semantic-kernel.git
# already have the repo? check out this version:
$ git checkout python-1.37.0

›Adds NvidiaChatCompletion AI connector, enabling NVIDIA-hosted models as a chat completion backend in Semantic Kernel pipelines.

Was this useful?

holmesgpt

0.14.2 NOTES

SRE Agent - CNCF Sandbox Project

HolmesGPT 0.14.2 adds improved Tempo integration, Claude Sonnet 1M token model support, and context window optimizations for metrics and trace data.

└──▷ GET THIS VERSION

$ git clone --branch 0.14.2 https://github.com/HolmesGPT/holmesgpt.git
# already have the repo? check out this version:
$ git checkout 0.14.2

›Supports the Sonnet 1M token model for extended context analysis.
›Improves Tempo integration to enable latency increase and HTTP 500 error root-cause queries.
›Optimizes context window handling for metrics and trace data, increasing answer accuracy.
›Improves Datadog integration accuracy through multiple small changes.

Was this useful?

Other / Uncategorized

◆ AI OBSERVABILITY

Arize Phoenix

arize-phoenix-v11.34.0 NOTES

Phoenix v11.34.0 adds an experiment compare details slideover in the list view and caps span queue capacity.

└──▷ GET THIS VERSION

$ git clone --branch arize-phoenix-v11.34.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.34.0

›Adds an experiment compare details slideover to the experiments list view, letting practitioners inspect side-by-side experiment results without leaving the list.
›Puts a capacity limit on the internal span queue to bound memory usage under high ingestion load.

Was this useful?

◆ VECTOR DB RAG

Chroma

1.1.0 NOTES

Chroma 1.1.0 adds a search API with BM25/SPLADE support, id filters in where clauses, GC control interface, and mem0 integration.

└──▷ GET THIS VERSION

$ git clone --branch 1.1.0 https://github.com/chroma-core/chroma.git
# already have the repo? check out this version:
$ git checkout 1.1.0

└──▷ USE IT

Filter query results by specific document IDs inside a where clause, combining ID and metadata filters.

python

results = collection.query(
    query_texts=["network intrusion"],
    where={"id": {"$in": ["doc-001", "doc-042", "doc-099"]}},
    n_results=5
)

›Adds query_config on collection configuration supporting splade and bm25 EFS settings for configurable full-text search behavior.
›Supports id filter in where clause, enabling document-ID-based filtering alongside metadata filters in queries.
›Implements IDF modifier for the BM25 index, improving relevance scoring for full-text search.
›Makes rank expressions operational in the search API, enabling custom ranking logic at query time.
›Adds quota enforcement to the search API to cap resource usage per request.

+5 moreshow less

›Adds validation for metadata and sparse vectors submitted to the search API.
›Adds new methods to ClientManager for expanded programmatic client lifecycle control.
›Adds a control interface for garbage collection (GC), enabling operational management of compaction cleanup.
›Integrates Chroma with mem0 for persistent memory layer support.
›Increases cloud quotas and updates defaults, expanding the operational envelope for hosted deployments.

Was this useful?

◆ MCP TOOLING

Composio

0.8.14 2 RELEASES · 2025-09-16 NOTES STABLE

Composio 0.8.14 adds versioning support for tools.

└──▷ GET THIS VERSION

$ git clone --branch 0.8.14 https://github.com/ComposioHQ/composio.git
# already have the repo? check out this version:
$ git checkout 0.8.14

›Adds versioning support for tools, enabling management of multiple tool versions.

1 more release in this issue · 2025-09-16

v0.8.13 NOTES STABLE

Composio v0.8.13 adds versioning support for tools.

└──▷ GET THIS VERSION

$ git clone --branch v0.8.13 https://github.com/ComposioHQ/composio.git
# already have the repo? check out this version:
$ git checkout v0.8.13

›Adds versioning support for tools, enabling practitioners to pin or target specific tool versions.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · September 16, 2025
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -334, September 16, 2025