The AI Toolchain — issue -297, October 24, 2025

GitHub Copilot CLI v0.0.350 trims default MCP tool set for context efficiency and adds --enable-all-github-mcp-tools flag.

$ git clone --branch v0.0.350 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v0.0.350

$ gh copilot --enable-all-github-mcp-tools

• ›Adds --enable-all-github-mcp-tools flag to opt back into the full set of GitHub MCP server tools when needed.
• ›Limits the default GitHub MCP server tool set to a curated subset — covering code/repo navigation (get_file_contents, search_code, search_repositories, list_branches, list_commits, get_commit), issue management (get_issue, list_issues, get_issue_comments, search_issues), PR management (pull_request_read, list_pull_requests, search_pull_requests), workflow info (list_workflows, list_workflow_runs, get_workflow_run, get_job_logs, get_workflow_run_logs), and user search (user_search) — to conserve context window space.

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

Goose v1.12.0 adds system diagnostics, extension search, code snippet saving, and two new built-in recipes.

$ git clone --branch v1.12.0 https://github.com/block/goose.git
# already have the repo? check out this version:
$ git checkout v1.12.0

• ›Adds system diagnostics tools for inspecting Goose's runtime environment.
• ›Adds extension search functionality to quickly find and manage extensions.
• ›Adds code snippet formatting and saving directly from conversations.
• ›Introduces a Test Coverage Optimizer built-in recipe.
• ›Introduces a Smart Task Organizer built-in recipe.

The open source coding agent.

OpenCode v0.15.15 adds wildcard flag parsing support for the bash tool.

$ git clone --branch v0.15.15 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v0.15.15

• ›Adds wildcard parsing support for flags in the bash tool, enabling broader glob-style argument matching.

langchain-core 1.0.1 automatically marks all properties as required when strict mode is enabled.

$ git clone --branch langchain-core==1.0.1 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:
$ git checkout langchain-core==1.0.1

• ›In strict mode, automatically sets required to include all properties in the schema, eliminating the need to manually specify required fields.

Letta 0.13.0 adds Claude Haiku 4.5 as a supported reasoning model.

$ git clone --branch 0.13.0 https://github.com/letta-ai/letta.git
# already have the repo? check out this version:
$ git checkout 0.13.0

• ›Adds Claude Haiku 4.5 as a supported reasoning model option.

OpenAI Agents SDK v0.4.2 enables async tool calling in Realtime sessions and custom reasoning effort for LiteLLM providers.

$ git clone --branch v0.4.2 https://github.com/openai/openai-agents-python.git
# already have the repo? check out this version:
$ git checkout v0.4.2

• ›Enables async tool calling in Realtime sessions, allowing asynchronous tools to be invoked during real-time agent interactions.
• ›Supports passing custom reasoning effort when using LiteLLM providers.

PydanticAI v1.6.0 adds FastMCPToolset and a vLLM Responses API compatibility flag for OpenAI model profiles.

$ git clone --branch v1.6.0 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:
$ git checkout v1.6.0

from pydantic_ai.models.openai import OpenAIModelProfile

profile = OpenAIModelProfile(openai_responses_requires_function_call_status_none=True)

• ›Adds OpenAIModelProfile.openai_responses_requires_function_call_status_none flag to enable compatibility with vLLM's Responses API.
• ›Adds FastMCPToolset for integrating FastMCP tools into PydanticAI agents.
• ›Auto-generated output tool names are now sanitized to support generic types.

$ git clone --branch v1.5.0 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:
$ git checkout v1.5.0

$ git clone --branch v1.4.0 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:
$ git checkout v1.4.0

from pydantic_ai.tools import MCPServerTool

Phoenix 12.7.0 adds dataset splits support across experiments and datasets, plus label filtering for datasets and prompts.

$ git clone --branch arize-phoenix-v12.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.7.0

• ›Enables label filtering on the datasets table, allowing practitioners to narrow the dataset list by label in the UI.
• ›Enables label filtering on the prompts page, so prompt versions can be browsed by label.
• ›Supports querying dataset examples by splits, surfacing split-aware data in the playground and experiment workflows.
• ›Makes the Experiment Compare page split-aware, so experiment runs can be compared across dataset splits.
• ›Adds ExperimentRuns scoped over dataset splits, enabling per-split evaluation tracking.

Weaviate v1.32.14 adds backup list sorting with size reporting and GOMEMLIMIT to usage module payload.

$ git clone --branch v1.32.14 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout v1.32.14

• ›Backup list API now supports ascending/descending sort order and returns backup size per entry.
• ›Adds GOMEMLIMIT to the usage module payload, surfacing Go memory limit data in usage telemetry.