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.
Agno v2.5.13 adds a /info metadata endpoint, richer /sessions list fields, Slack show_member_tool_calls param, and ReliabilityEval subset matching.
└──▷ GET THIS VERSION
$ git clone --branch v2.5.13 https://github.com/agno-agi/agno.git
# already have the repo? check out this version:$ git checkout v2.5.13
└──▷ USE IT
Show member tool calls inline when streaming agent responses to a Slack channel.
python
from agno.interface.slack import SlackInterface
slack = SlackInterface(
agent=my_agent,
show_member_tool_calls=True,
)
›Adds show_member_tool_calls param to the Slack Interface, plus automatic card overflow rotation that starts a new message when text exceeds the threshold.
›Enhances the AgentOS /sessions list API to return additional fields: user_id, agent_id, team_id, workflow_id, session_summary, metrics, total_tokens, and metadata.
›Adds the AgentOS /info API endpoint — a lightweight, unauthenticated call that returns agent, team, and workflow counts as instance metadata.
›Adds subset matching, argument validation, and missing tool call tracking to ReliabilityEval, with multi-round tool call collection support.
›Implements dynamic batch splitting for large upsert/query operations in ChromaDB.
+2 moreshow less
›Propagates chunk_size to default chunking strategies in reader classes.
›Enables channel summarization in the Slack interface.
Haystack v2.27.0 adds automatic list joining in pipelines, async document store helpers, and multimodal chat generator support.
└──▷ GET THIS VERSION
$ git clone --branch v2.27.0 https://github.com/deepset-ai/haystack.git
# already have the repo? check out this version:$ git checkout v2.27.0
└──▷ USE IT
Inspect metadata value ranges in a local prototype store before moving to production — replaces manual document iteration.
python
from haystack.document_stores.in_memory import InMemoryDocumentStore
store = InMemoryDocumentStore()
# ... write documents ...
print(store.get_metadata_field_min_max("year"))
print(store.get_metadata_field_unique_values("category"))
print(store.count_documents_by_filter({"field": "meta.category", "operator": "==", "value": "finance"}))
Check which Azure OpenAI models Haystack recognises without consulting external docs.
python
from haystack.components.generators.chat import AzureOpenAIChatGenerator
print(AzureOpenAIChatGenerator.SUPPORTED_MODELS)
›Adds count_documents_by_filter, count_unique_metadata_by_filter, get_metadata_fields_info, get_metadata_field_min_max, and get_metadata_field_unique_values operations to InMemoryDocumentStore, matching the inspection and filtering API available in other document stores.
›Adds async variants to InMemoryDocumentStore: update_by_filter_async(), count_documents_by_filter_async(), count_unique_metadata_by_filter_async(), get_metadata_fields_info_async(), get_metadata_field_min_max_async(), and get_metadata_field_unique_values_async().
›Exposes SUPPORTED_MODELS class variable on AzureOpenAIChatGenerator, listing supported model IDs such as gpt-5-mini and gpt-4o, inspectable at runtime via AzureOpenAIChatGenerator.SUPPORTED_MODELS.
›Adds partial support for the image-text-to-text task in HuggingFaceLocalChatGenerator, enabling use of multimodal models such as Qwen 3.5 or Ministral with text-only inputs.
›Pipelines now automatically join multiple inputs into a list-typed input socket with type conversion, supporting T + T -> list[T], T + list[T] -> list[T], str + ChatMessage -> list[str], and str + ChatMessage -> list[ChatMessage] — eliminating the need for extra joining components.
+1 moreshow less
›Adds _to_trace_dict method to ImageContent and FileContent dataclasses, replacing large base64_image and base64_data fields with placeholder strings (e.g. 'Base64 string (N characters)') when tracing is enabled.
langchain-core 1.2.24 automatically imputes placeholder filenames for OpenAI file inputs.
└──▷ GET THIS VERSION
$ git clone --branch langchain-core==1.2.24 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain-core==1.2.24
›Automatically imputes placeholder filenames for OpenAI file inputs, enabling cleaner handling of file-based content in OpenAI-compatible calls.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Claude Code v2.1.90 adds /powerup interactive lessons, offline plugin cache control, and faster /resume loading.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.90 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.90
└──▷ TRY IT
Launch interactive feature lessons to onboard yourself or a teammate to Claude Code capabilities.
$ /powerup
Keep plugin marketplace working in an offline or network-restricted environment where git pull fails.
$ CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 claude
›Adds /powerup command: interactive lessons teaching Claude Code features with animated demos.
›Adds CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE env var to preserve the existing marketplace cache when git pull fails, enabling plugin use in offline or air-gapped environments.
›Adds .husky to the list of protected directories in acceptEdits mode.
›Improves /resume all-projects view to load project sessions in parallel, reducing wait times for users with many projects.
›Changes --resume picker to hide sessions created by claude -p or SDK invocations, keeping the list focused on interactive sessions.
+1 moreshow less
›Removes Get-DnsClientCache and ipconfig /displaydns from the auto-allow list to protect DNS cache privacy.
└──▷ BREAKING ON UPGRADE
!Get-DnsClientCache and ipconfig /displaydns are no longer auto-allowed; setups or scripts that relied on these commands running without a permission prompt will now require explicit approval.
Claude Code v2.1.89 adds deferred-permission hooks, flicker-free rendering, PermissionDenied hook, and faster MCP connections in headless mode.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.89 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.89
└──▷ TRY IT
Pause a headless session at a sensitive tool call and let a hook re-evaluate before proceeding — useful for human-in-the-loop approval pipelines.
$ claude -p--resume <session-id>
Speed up CI/automation runs by skipping MCP server wait entirely and capping individual server connect time at 5 s.
$ MCP_CONNECTION_NONBLOCKING=true claude -p--mcp-config mcp.json '<prompt>'
Eliminate terminal flicker in long streaming sessions or when running inside a multiplexer like tmux.
$ CLAUDE_CODE_NO_FLICKER=1 claude
›Adds "defer" permission decision to PreToolUse hooks, letting headless sessions pause at a tool call and resume via -p --resume for hook re-evaluation.
›Adds CLAUDE_CODE_NO_FLICKER=1 environment variable to enable flicker-free alt-screen rendering with virtualized scrollback.
›Adds PermissionDenied hook that fires after auto-mode classifier denials — return {retry: true} to signal the model it can retry the tool call.
›Adds named subagents to @ mention typeahead suggestions.
›Adds MCP_CONNECTION_NONBLOCKING=true for -p mode to skip the MCP connection wait entirely; bounds --mcp-config server connections at 5 s instead of blocking on the slowest server.
+5 moreshow less
›Auto mode: denied commands now surface a notification and appear in /permissions → Recent tab where you can retry with r.
›Enables Edit to work on files viewed via Bash with sed -n or cat, without requiring a separate Read call first.
›Hook output exceeding 50 K characters is now saved to disk with a file path and preview instead of being injected directly into context.
›/env now applies to PowerShell tool commands (previously only affected Bash).
›Pasting !command into an empty prompt now enters bash mode, matching typed ! behavior.
└──▷ BREAKING ON UPGRADE
!cleanupPeriodDays: 0 in settings.json is now rejected with a validation error (it previously silently disabled transcript persistence).
!Thinking summaries are no longer generated by default in interactive sessions — existing workflows that relied on them must set showThinkingSummaries: true in settings.json.
Copilot CLI v1.0.15 adds MCP server config RPCs, OAuth device-code flow, /mcp auth, /share html, and branch-diff toggle.
└──▷ GET THIS VERSION
$ git clone --branch v1.0.15 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:$ git checkout v1.0.15
└──▷ TRY IT
Review all changes on the current branch against the merge-base using the branch diff toggle in /diff mode.
$ gh copilot /diff
›Adds mcp.config.list, mcp.config.add, mcp.config.update, and mcp.config.remove server RPCs for managing persistent MCP server configuration.
›Adds COPILOT_HOME environment variable, replacing nonstandard XDG variables, with automatic data migration.
›Adds /mcp auth command and re-authentication UI for MCP OAuth servers, including account switching support.
›Adds device code flow (RFC 8628) as a fallback for MCP OAuth in headless and CI environments.
›Adds postToolUseFailure hooks for tool errors; postToolUse now runs only after successful tool calls.
+7 moreshow less
›Adds /share html command to export sessions and research reports as self-contained interactive HTML files.
›Config settings askUser, autoUpdate, storeTokenPlaintext, logLevel, skillDirectories, and disabledSkills now use camelCase names (snake_case still accepted).
›Adds branch diff toggle to /diff mode for viewing full branch changes vs merge-base.
›Adds Home/End and Page Up/Page Down keyboard navigation to the diff viewer.
›MCP servers that are slow to connect no longer block the agent from starting.
›Adds a default option to the custom agent picker to deselect the current agent.
›Drops support for gpt-5.1-codex, gpt-5.1-codex-mini, and gpt-5.1-codex-max models.
└──▷ BREAKING ON UPGRADE
!Nonstandard XDG environment variables are replaced by COPILOT_HOME; existing setups relying on those XDG variables must migrate to COPILOT_HOME.
!gpt-5.1-codex, gpt-5.1-codex-mini, and gpt-5.1-codex-max models are removed and can no longer be selected.
!Ctrl+D no longer queues a message; use Ctrl+Q or Ctrl+Enter to queue instead.
!Text selection no longer auto-copies; Ctrl+C or right-click is now required to copy selected text.
!postToolUse hooks no longer run after failed tool calls; use the new postToolUseFailure hook for error handling.
Keep the git panel closed by default in new workspaces so it does not open automatically on project load.
json
{
"git_panel": {
"starts_open": false
}
}
›Adds git_status_indicator setting (set to true in project_panel settings) to show git status indicators in the Project Panel.
›Adds git_panel.starts_open setting to control whether the git panel opens automatically in new workspaces (default: false).
›Adds support for vim and emacs modeline comments (e.g., # vim: set ft=python : or -*- mode: ruby -*-) for per-file language detection and editor settings.
›Adds OAuth authentication support for remote MCP servers, surfacing an 'Authenticate' button and browser-based authorization flow when a server requires login.
›Adds multi-line search and replace input in Buffer Search and Project Search.
+19 moreshow less
›Adds support for pasting files and folders into the Agent Panel.
›Adds support for pasting files from Finder (and other file managers) into the project panel via the system clipboard (macOS only); copying or cutting files in the project panel now also writes their paths to the system clipboard.
›Adds screen-sharing support on Wayland/Linux.
›Adds Anthropic reasoning effort selection for Anthropic models.
›Adds Native Thinking toggle as an alternative to model variants.
›Enables parallel tool calling support for OpenAI models that support it.
›Adds Opencode Zen as a new AI provider.
›Adds automatic volume control during calls.
›Adds call diagnostics when collaborating with other Zed users.
›Adds JSON syntax highlighting for .babelrc, .eslintrc, .stylelintrc, and .swcrc configuration files.
›Adds semantic token rule for Go format string interpolations via gopls.
›Adds support for Helix's :reflow command.
›Adds support for GNOME's window buttons configuration on Linux.
›Adds a toggle to control password visibility when connecting to a remote project.
›Adds 'Reveal in Finder' to the tab context menu.
›Improves terminal: New Terminal (cmd-n) to open in the center pane when a terminal tab there is focused, instead of always opening in the terminal panel.
›Improves 'Diff Clipboard with Selection' to support side-by-side diff view style.
›Changes the terminal permissions UI to allow selecting individual subcommands independently.
›Allows the keymap and settings UI to be opened without an active window.
WebGPU backend gains quantized buffer support via u32 packing and wider browser/device compatibility.
└──▷ GET THIS VERSION
$ git clone --branch b8607 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b8607
›Extends the WebGPU (ggml) backend to pack quantized buffers as u32 and use unpackf16 for broader browser and device compatibility, removing the previous bitcast approach.
Phoenix client v2.2.0 adds get_traces, a GET /v1/user endpoint, secrets management REST API, and Python 3.14 support.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-client-v2.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-client-v2.2.0
└──▷ TRY IT
Look up the currently authenticated user via the new REST endpoint.
$ curl -X GET https://<phoenix-host>/v1/user \
-H 'Authorization: Bearer <api-key>'
›Adds get_traces method to both the Python and TypeScript Phoenix clients for programmatic trace retrieval.
›Adds GET /v1/user REST endpoint to retrieve user information via the phoenix-rest-api.
›Adds a REST endpoint for secrets management on the Phoenix server.
Arize Phoenix Evals 2.13.0 adds Python 3.14 support (except Windows).
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-evals-v2.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-evals-v2.13.0
›Supports Python 3.14 on Linux and macOS (Windows excluded).
Phoenix v13.22.0 refreshes the UI with updated provider and integration icons plus a new agent skill logo icon.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v13.22.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-v13.22.0
›Updates provider and integration icons and adds a new agent skill logo icon in the UI.
Phoenix v13.21.0 adds Python 3.14 support, a secrets-management REST endpoint, and improved agent session summaries.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v13.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-v13.21.0
›New REST endpoint for secrets management on the Phoenix server.
Composio CLI 0.2.18 preloads custom auth connections into tool router sessions and adds a beta-channel release promotion flow.
└──▷ GET THIS VERSION
$ git clone --branch @composio/[email protected] https://github.com/ComposioHQ/composio.git
# already have the repo? check out this version:$ git checkout @composio/[email protected]
›Preloads custom auth connections into CLI tool router sessions, enabling authenticated tools to be available immediately when a session starts.
›Adds a beta-channel CLI release promotion flow, allowing users to receive and test pre-release CLI builds.