Backfill issue -321 — 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   # 10 tools matched

AI & LLM Tooling

◆ AI Coding Agents

Cline

v3.32.4 2 RELEASES · 2025-09-29 NOTES STABLE

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Cline v3.32.4 adds Amazon Bedrock us-west-1 region support.

└──▷ GET THIS VERSION

$ git clone --branch v3.32.4 https://github.com/cline/cline.git
# already have the repo? check out this version:
$ git checkout v3.32.4

›Supports Amazon Bedrock in the us-west-1 region, expanding model access for users in that geography.

1 more release in this issue · 2025-09-29

v3.32.2 NOTES STABLE

Cline v3.32.2 adds a /task deep link handler and Claude Sonnet 4.5 model support.

└──▷ GET THIS VERSION

$ git clone --branch v3.32.2 https://github.com/cline/cline.git
# already have the repo? check out this version:
$ git checkout v3.32.2

›Adds /task deep link handler for launching tasks directly via URL.
›Adds support for Claude Sonnet 4.5 as an available model.

Was this useful?

Continue

@continuedev/[email protected] NOTES

Continue 1.23.0 adds --id option to connect to existing remote agents via tunnel and a boolean mode for cn serve.

└──▷ 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]

└──▷ TRY IT

Reconnect to an already-running remote agent by its ID rather than launching a new tunnel session.

$ cn serve --id <agent-id>

›Adds --id option to connect to an existing remote agent via tunnel instead of spinning up a new one.
›Adds boolean support to cn serve command.

Was this useful?

GitHub Copilot CLI

v0.0.329 NOTES

GitHub Copilot CLI v0.0.329 adds Claude Sonnet 4.5 as default, a /model command, and glob matching for shell tool rules.

└──▷ GET THIS VERSION

$ git clone --branch v0.0.329 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v0.0.329

└──▷ TRY IT

Switch to a specific model mid-session without leaving the CLI.

$ /model claude-sonnet-4-5

Restrict the agent to only npm test variants while blocking all other shell commands, using glob syntax.

$ copilot --allow-tool 'shell(npm run test:*)' --deny-tool 'shell(*)'

›Adds /model slash command to switch models interactively (/model opens a picker; /model <model> sets the model directly).
›Adds glob matching to --allow-tool and --deny-tool shell rules, e.g. shell(npm run test:*) matches any shell command beginning with npm run test.
›Adds Claude Sonnet 4.5 support and makes it the default model.
›Displays the currently selected model above the input text box.
›Improves copilot --resume interface with relative time display and session message count.

+2 moreshow less

›Changes Ctrl+r to expand only recent timeline items; Ctrl+e then expands all.
›Limits the input text box to 10 scrollable lines so long prompts no longer fill the screen.

Was this useful?

Alibaba Qwen Code

v0.0.14 2 RELEASES · 2025-09-29 NOTES STABLE

Qwen Code v0.0.14 adds Plan Mode for safe code planning, Qwen3-VL-Plus token limits, and DashScope cache control.

└──▷ GET THIS VERSION

$ git clone --branch v0.0.14 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.0.14

›Adds support for Qwen3-VL-Plus model with token limits of 256K input and 32K output.
›Implements Plan Mode for safe code planning, allowing the agent to plan changes before executing them.
›Enhances DashScope cache control for improved API caching behavior.

1 more release in this issue · 2025-09-29

v0.0.14-nightly.2 NOTES STABLE

Qwen Code v0.0.14-nightly.2 adds Plan Mode for safe code planning and Qwen3-VL-Plus support with 256K input / 32K output token limits.

└──▷ GET THIS VERSION

$ git clone --branch v0.0.14-nightly.2 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.0.14-nightly.2

›Adds Qwen3-VL-Plus model support with 256K input and 32K output token limits.
›Implements Plan Mode for safe code planning, letting the agent plan changes before executing them.

Was this useful?

Zed

v0.205.8 NOTES

Zed v0.205.8 adds Claude Sonnet 4.5 BYOK support and makes Sonnet 4.5 the recommended Anthropic model.

└──▷ GET THIS VERSION

$ git clone --branch v0.205.8 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.205.8

›Adds Claude Sonnet 4.5 as a supported model for Bring-Your-Own-Key (BYOK) Anthropic configurations.
›Promotes Claude Sonnet 4.5 and Claude Sonnet 4.5 Thinking to the recommended Anthropic models.

Was this useful?

Google gemini-cli

v0.8.0-nightly.20250929.ae387b61 3 RELEASES · 2025-09-29 NOTES STABLE

An open-source AI agent that brings the power of Gemini directly into your terminal.

gemini-cli v0.8.0-nightly adds a confirmation dialog for extension updates and a red threshold indicator for status color.

└──▷ GET THIS VERSION

$ git clone --branch v0.8.0-nightly.20250929.ae387b61 https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:
$ git checkout v0.8.0-nightly.20250929.ae387b61

›Adds a confirmation dialog when updating extensions, giving users a chance to review before applying changes.
›Adds a red threshold level to the status color utility, enabling clearer visual alerting at critical usage levels.
›Improves narrow-screen layout by reducing margins and reflowing footer contents for better usability on small terminals.

2 more releases in this issue · 2025-09-29

v0.8.0-nightly.20250929.a49a09f1 NOTES STABLE

gemini-cli v0.8.0-nightly adds content-based retries for JSON generation to improve reliability.

└──▷ GET THIS VERSION

$ git clone --branch v0.8.0-nightly.20250929.a49a09f1 https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:
$ git checkout v0.8.0-nightly.20250929.a49a09f1

›Adds content-based retries for JSON generation, automatically retrying when the model returns malformed or invalid JSON responses.

v0.8.0-nightly.20250929.042288e7 NOTES STABLE

gemini-cli v0.8.0-nightly adds IAP/Cloud Run MCP support, terminal-title status display, and default tool output truncation.

└──▷ GET THIS VERSION

$ git clone --branch v0.8.0-nightly.20250929.042288e7 https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:
$ git checkout v0.8.0-nightly.20250929.042288e7

›Adds service account impersonation provider to MCPServers, enabling IAP authentication for Cloud Run-hosted MCP endpoints.
›New setting to display Gemini status (or model thoughts) in the terminal title bar and taskbar icon.
›Enables tool output truncation by default to manage large tool responses.
›Makes context compression more aggressive and uses lastPromptTokenCount to more accurately trigger compression.

└──▷ BREAKING ON UPGRADE

!Tool output truncation is now enabled by default, which may change behavior for workflows that relied on full, untruncated tool output being passed to the model.

Was this useful?

◆ AI Agent Frameworks

deepset Haystack

v2.18.1 NOTES

Haystack v2.18.1 lets agents accept a runtime tools parameter to swap or subset tools per invocation.

└──▷ GET THIS VERSION

$ git clone --branch v2.18.1 https://github.com/deepset-ai/haystack.git
# already have the repo? check out this version:
$ git checkout v2.18.1

›Adds tools to agent run parameters, allowing callers to pass a list of tool names (subset selection) or Tool objects / a Toolset (full replacement) at runtime.

Was this useful?

LangChain LangGraph

0.6.8 NOTES

Build resilient agents.

LangGraph 0.6.8 adds guardrails that prevent arbitrary resumes when multiple interrupts are pending.

└──▷ GET THIS VERSION

$ git clone --branch 0.6.8 https://github.com/langchain-ai/langgraph.git
# already have the repo? check out this version:
$ git checkout 0.6.8

›Adds enforcement that prevents arbitrary graph resumes when multiple pending interrupts exist, ensuring interrupt handling is ordered and intentional.

Was this useful?

browser-use

0.7.10 NOTES

browser-use 0.7.10 adds Laminar debug tags, improved auto PDF download, and parallel multi-agent and domain-prohibition examples.

└──▷ GET THIS VERSION

$ git clone --branch 0.7.10 https://github.com/browser-use/browser-use.git
# already have the repo? check out this version:
$ git checkout 0.7.10

›Adds Laminar debug tags integration for tracing agent runs.
›Improves auto PDF download capabilities for browser-driven workflows.
›Adds parallel multi-agent example demonstrating concurrent agent execution.
›Adds ModelScope example and documentation for using ModelScope-hosted models.
›Adds examples showing how to prohibit specific domains in agent configurations.

+2 moreshow less

›Relaxes Pydantic length limit for Amazon Bedrock ARN strings in model config.
›Multiple speed-up improvements reducing latency across agent execution paths.

Was this useful?

Other / Uncategorized

◆ AI OBSERVABILITY

Arize Phoenix

arize-phoenix-client-v1.21.0 2 RELEASES · 2025-09-29 NOTES STABLE

Arize Phoenix client v1.21.0 adds methods for annotating traces and sessions programmatically.

└──▷ GET THIS VERSION

$ git clone --branch arize-phoenix-client-v1.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.21.0

›Adds client methods for adding annotations to traces and sessions, enabling programmatic labeling of LLM trace data and session-level feedback.

1 more release in this issue · 2025-09-29

arize-phoenix-v12.0.0 NOTES STABLE

Phoenix v12 adds session/trace annotation APIs, dataset splits, experiment repetitions view, and Google GenAI SDK support.

└──▷ GET THIS VERSION

$ git clone --branch arize-phoenix-v12.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.0.0

›Adds client methods for adding trace and session annotations via the Phoenix client library.
›Adds GraphQL mutations and a database table for session annotations, surfacing annotation columns in the sessions table UI.
›Adds user_id column to the datasets and dataset_versions tables, enabling per-user dataset attribution.
›Introduces dataset splits: backend support, 'Add Split' dialog UI, and split labels displayed in the examples table.
›Snapshots examples into a junction table when an experiment is inserted, preserving the exact dataset state used.

+5 moreshow less

›Adds experiment tags on experiments and datasets.
›Adds a 'viewer' role row to the database, expanding role-based access control.
›Experiment repetitions are now shown as a column in the experiments table UI.
›Upgrades the Playground to use the Google GenAI SDK.
›Enforces a minimum client version requirement, ensuring server/client compatibility.

└──▷ BREAKING ON UPGRADE

!Version 12 is a major release with breaking changes (see PR #9695); existing databases require migration before upgrading.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · September 29, 2025
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -321, September 29, 2025