The AI Toolchain — issue -265, November 25, 2025

Continue 1.6.0 adds a JCEF reload action and Klavis AI Strata to the MCP Cookbook.

$ 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 a JCEF reload action for the JetBrains embedded browser panel.
• ›Adds Klavis AI's Strata integration to the MCP Cookbook.

The open source coding agent.

OpenCode v1.0.112 adds async prompt support, richer session stats, and a revamped theme selector.

$ git clone --branch v1.0.112 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.112

• ›Adds prompt_async functionality to submit prompts and return immediately without blocking.
• ›Enhances the stats command to display average and median token counts per session.
• ›Improves theme selector UX with a current-theme indicator for easier selection.
• ›Separates session IDs from share IDs for a cleaner URL structure and improved security.
• ›Adds social share images for richer link previews when sharing sessions.

$ git clone --branch v1.0.111 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.111

$ opencode models

$ git clone --branch v1.0.110 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.110

Qwen Code v0.3.0-nightly adds stream-json I/O format for headless programmatic use and full i18n support.

$ git clone --branch v0.3.0-nightly.20251125.c9af7481 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.3.0-nightly.20251125.c9af7481

$ qwen --input-format stream-json --output-format stream-json

• ›Adds stream-json as a supported value for --input-format and --output-format to enable programmatic, headless use of Qwen Code via structured streaming JSON.
• ›Adds internationalization (i18n) support for UI text and LLM output, enabling localized experiences across languages.

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

gemini-cli v0.19.0-nightly adds hook lifecycle infrastructure, session stats, and model policy controls.

$ git clone --branch v0.19.0-nightly.20251125.f6d97d448 https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:
$ git checkout v0.19.0-nightly.20251125.f6d97d448

• ›Adds hook telemetry infrastructure, enabling hooks to emit and track telemetry events during execution.
• ›Adds hook event handling, allowing hooks to respond to and process agent events.
• ›Adds hook agent lifecycle integration, connecting hooks to agent start/stop and lifecycle transitions.
• ›Adds hook system orchestration, enabling coordinated hook execution across the agent system.
• ›Adds session subtask breakdown to the /stats command for finer-grained session inspection.

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

CrewAI 1.6.0 adds streaming results for flows and crews, Entra ID CLI login, a Merge Agent Handler tool, and Gemini 2.5 Pro preview support.

$ git clone --branch 1.6.0 https://github.com/crewAIInc/crewAI.git
# already have the repo? check out this version:
$ git checkout 1.6.0

• ›Adds streaming result support to flows and crews, enabling real-time output consumption.
• ›Supports CLI login with Entra ID (Microsoft Entra / Azure AD) for enterprise SSO authentication.
• ›Adds Merge Agent Handler tool for combining agent outputs.
• ›Enhances flow event state management for improved control over flow lifecycle events.

Letta 0.15.0 adds context window support for grok-4 models.

$ git clone --branch 0.15.0 https://github.com/letta-ai/letta.git
# already have the repo? check out this version:
$ git checkout 0.15.0

• ›Adds context window definitions for grok-4 models, enabling Letta agents to run against xAI's grok-4 model family.

Your own personal AI assistant. Any OS.

OpenClaw v0.1.3 adds configurable working-directory for command replies and file-based logging with level control.

$ git clone --branch v0.1.3 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v0.1.3

# In ~/.warelay/warelay.json
{
  "logging": {
    "level": "info"
  }
}

• ›Adds cwd option to command reply config so external reply commands run in the correct working directory.
• ›Adds configurable file-based logging (default /tmp/warelay/warelay.log) with log level controlled via logging.level in ~/.warelay/warelay.json; --verbose still forces debug.

$ git clone --branch v0.1.1 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v0.1.1

Phoenix v12.18.0 adds Claude Opus 4-5 support, dataset split assignment on upload, and server credential visibility in the Playground.

$ git clone --branch arize-phoenix-v12.18.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.18.0

• ›Supports split assignment directly from dataset upload, letting users label train/test/validation splits at ingest time.
• ›Adds support for Claude Opus 4-5 as a model option.
• ›Shows server credential setup inside the Playground API keys panel, surfacing pre-configured credentials alongside user-entered keys.

$ git clone --branch arize-phoenix-client-v1.26.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.26.0

Qdrant v1.16.1 brings up to 3× faster batch queries, active RocksDB-to-Gridstore migration on startup, and user-configurable inference request timeouts.

$ git clone --branch v1.16.1 https://github.com/qdrant/qdrant.git
# already have the repo? check out this version:
$ git checkout v1.16.1

• ›Makes timeout for inference requests user configurable.
• ›Makes batch queries up to 3× faster on full scans by reading each point only once.
• ›Actively migrates vector, payload, and payload index storage from RocksDB into Gridstore on startup for better and more predictable performance.
• ›Adds a 60-second internal timeout for telemetry/metrics endpoints to prevent long-hanging tasks.
• ›Adds validation to the restart shard transfer operation.