AI coding agent release tracker

Release 0.164.0-alpha.11

## What's Changed
* Changelog for v0.66.0-preview.0 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29852
* feat(cli): bridge the IDE companion into container sandboxes over exec stdio by @elberthc-byte in https://github.com/google-gemini/gemini-cli/pull/29858
* fix(core): prevent duplicate agent loading when workspace is home directory (#27692) by @urielefrenvirtusa in https://github.com/google-gemini/gemini-cli/pull/29847
* fix(ide): exclude IDE settings and GEMINI.md files from open file con text by @villahernandez-coder in https://github.com/google-gemini/gemini-cl

Release 0.164.0-alpha.10

Release 0.163.0-alpha.11.1

## What's changed

- Added `/claude-api api-version` to move Claude API code to API version `2026-10-21`
- Added the `claude_code.safety_event` OpenTelemetry event for each tool call a permission rule, auto mode, a safety check, a hook or the sandbox stopped, prompted or sent back
- Fixed requests failing with a model-not-found error when `CLAUDE_CODE_DISABLE_1M_CONTEXT` is set and the model is an alias with the `[1m]` suffix, such as `opus[1m]`
- Fixed the `prompt-caching-scope` beta header being sent behind custom `ANTHROPIC_BASE_URL` gateways and on Foundry, where it has no effect
- Fixed M

Release 0.164.0-alpha.9

## What's changed

- Fixed `claude -p` inside cloud sessions reporting "Not logged in" when started without the session's environment variables
- Fixed an API error being replaced by "prompt is too long", and an unneeded compaction, in sessions with many MCP tools

## What's Changed
* chore: migrate gsutil usage to gcloud storage by @gurusai-voleti in https://github.com/google-gemini/gemini-cli/pull/29839
* fix(core): preserve user-level ~/.gitconfig in shell and git environments by @jesussamuel-byte in https://github.com/google-gemini/gemini-cli/pull/29832
* fix(core): prevent false positive matches in isAuthenticationError by @urielefrenvirtusa in https://github.com/google-gemini/gemini-cli/pull/29835
* fix(core): support opt-in private network endpoints for MCP OAuth flows by @luisfelipe-alt in https://github.com/google-gemini/gemini-cli/pull/29844
* 

Release 0.164.0-alpha.8

## What's Changed
* fix(cli): enforce read-only workspace settings in untrusted folders by @jvargassanchez-dot in https://github.com/google-gemini/gemini-cli/pull/29583
* fix(core): avoid duplicate tool response turns when resuming sessions by @diegogodinezr in https://github.com/google-gemini/gemini-cli/pull/29618
* fix(core): prevent deletion of resumed session history on quick exit (#29198) by @villahernandez-coder in https://github.com/google-gemini/gemini-cli/pull/29584
* Changelog for v0.64.0-preview.0 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29656
* Chang

## What's Changed
* Update ROADMAP.md to no longer reference outdated 2025 roadmap by @DavidAPierce in https://github.com/google-gemini/gemini-cli/pull/29723
* Changelog for v0.65.0-preview.0 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29739
* chore(release): bump version to 0.66.0-nightly.20261013.g204db94ae by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29740
* Changelog for v0.64.0 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29741
* fix(ui): implement synchronized output and isolate spinner rendering by @die

## What's changed

- Added `sandbox.allowNestedUserNamespaces` so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections
- Added `CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS` so unattended retry mode (`CLAUDE_CODE_RETRY_WATCHDOG`) notices a usage limit that was lifted before its reset
- Fixed every request failing on Vertex, Bedrock and other providers when the endpoint or a gateway rejects tool search, and behind gateways with ToolSearch disallowed or left out of `--tools` (a 2.1.304 regression): Claud

## What's Changed
* fix(ui): preserve terminal scrollback during viewport refreshes by @diegogodinezr in https://github.com/google-gemini/gemini-cli/pull/29792
* fix(cli): decode streamed Node HTTP activity chunks with StringDecoder by @jesussamuel-byte in https://github.com/google-gemini/gemini-cli/pull/29827


**Full Changelog**: https://github.com/google-gemini/gemini-cli/compare/v0.66.0-nightly.20261019.ged96faedf...v0.66.0-nightly.20261020.g76e4d7c04

## What's changed

- Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin
- Added `decider: "person"` to a mod's `tool.check` answer: only the permission dialog or a host's callback can approve the ask, and it is refused with the mod's reason where nobody can be asked
- Added `e.isReadOnly` to a mod's `tool.check` event, set when the tool call is read-only
- Added `/auto-mode-setup`: a guided setup that reads your project and recent sessions to teach auto mode about your environment, now also available on Bedrock, Vertex, Foundry,

## What's changed

- Bug fixes and reliability improvements

- GPT-6 models (such as `gpt-6-sol` and `gpt-6.1-sol`) work on OpenAI and Azure OpenAI-compatible endpoints. Before, every request was rejected because Cline sent `max_tokens` instead of `max_completion_tokens`
- The Cline provider's default model is Claude Sonnet 5.5 again, which is back at the top of Cline's recommended list
- Refreshed the model catalog. Adds the CommandCode and Reflection providers. Default models change for 302.AI (Gemini 4 Argon), Eden AI and Prime Inference (Muse Spark Open), CoreWeave (Reflection Beam 1.0), NanoGPT, Pioneer (Nemotron 3.5 Super VL), and Scaleway (DeepS

- GPT-6 models (such as `gpt-6-sol` and `gpt-6.1-sol`) work on OpenAI and Azure OpenAI-compatible endpoints. Before, every request was rejected because Cline sent `max_tokens` instead of `max_completion_tokens`
- With no model chosen, the Cline provider uses Claude Sonnet 5.5 again, which is back at the top of Cline's recommended list
- Refreshed the model catalog. Adds the CommandCode and Reflection providers. Default models change for 302.AI (Gemini 4 Argon), Eden AI and Prime Inference (Muse Spark Open), CoreWeave (Reflection Beam 1.0), NanoGPT, Pioneer (Nemotron 3.5 Super VL), and Scalewa

- OpenAI-compatible requests for GPT-6 models (`gpt-6-sol`, `gpt-6.1-sol`, `gpt-6-1-sol`, and later gpt-5 through gpt-9 ids) send `max_completion_tokens` instead of `max_tokens`, so OpenAI and Azure no longer reject them. Azure's `gpt-35-turbo` keeps `max_tokens`
- The hub daemon records which client started it (`CLINE_HUB_LAUNCHER_CLIENT`, `CLINE_HUB_LAUNCHER_VERSION`, `CLINE_HUB_LAUNCHER_TRANSPORT`) and publishes that as OTel resource attributes. SSH remote hubs report the local client with transport `ssh`. `@cline/shared` adds `withHubLauncherIdentity`, `claimHubLauncherIdentity` and `read

## Core

### Improvements
- Configure model reasoning options to generate reasoning variants, replacing catalog variants while preserving your configured variant overrides.

### Added

- Cline Cloud sessions, rolling out gradually: run a task in a hosted sandbox on a GitHub repo and branch you pick. Turn it on in Settings. Cloud tasks show in Recent and History with their status, notify you when they finish, and keep running after you close your editor.

### Changed

- With no model chosen, the Cline provider now uses Gemini 4 Argon, the new first model in Cline's recommended list. OpenRouter stays on Claude Sonnet 5.5.
- Refreshed the model catalog. Adds the Boundless and Standard Compute providers, and SambaNova now comes from the catalog with MiniMax M3 as its

- Plugins now run only in worker threads (the default, `CLINE_PLUGIN_MODE=worker`) or in the subprocess sandbox (`sandbox`). The `in_process` mode is removed, along with its silent fallback. A host that ships no `plugin-sandbox-bootstrap.js` fails every plugin load with `PluginBootstrapMissingError`, which names `CLINE_PLUGIN_BOOTSTRAP_PATH`, instead of quietly running plugins inside the hub. The hub daemon's uncaught error handlers are fatal again. The SSH remote hub ships no bootstrap yet, so it reports plugin tools as missing
- Provider errors that arrive after a model stream has started a

## Core

### Bugfixes
- OpenCode 1 now stays on the 1.x release line: update checks use only the npm `opencode-ai` latest version, so 1.x installs are never offered a 2.x build as a regular update.
- Upgrading to OpenCode 2 remains a separate, explicit choice through the 2.0 offer in `/update` or `opencode upgrade --major`.
- Fix upgrades for installs managed by yarn.
- Skip 1.x updates for Homebrew Core installs, which now track OpenCode 2, and check tap and Chocolatey availability before offering an update.
- The install script refuses to install 2.x versions.

## Core

### Bugfixes
- Session sharing has been discontinued. Existing share links and session-sharing commands are no longer available, and importing sessions from share URLs is unsupported.

## Core

### Improvements
- Run `opencode upgrade --major` to upgrade to OpenCode 2.

### Bugfixes
- Allow the OpenAI `ultrafast` service tier.
- Validate PTY connection origins and tickets before checking whether a PTY exists.

## TUI

### Improvements
- Use `/update` to install OpenCode updates or upgrade to OpenCode 2; updates are no longer installed automatically.

**Thank you to 1 community contributor:**
- @dc85:
  - docs(web): add Exo Free to Zen docs (#53622)
  - fix(stats): attribute exo usage to an unknown provider (#53621)
  - docs(web): remove Fledge Alpha Free from Zen docs (#5398

## Core

### Improvements
- Added canonical redirects and JSON and Markdown data formats for agent-readable stats.

### Bugfixes
- xAI tool results now include supported images, while unsupported image formats are skipped. (@Jaaneek)

**Thank you to 3 community contributors:**
- @dc85:
  - docs(web): add Fledge Alpha Free to Zen docs (#52895)
- @jm0ney337:
  - docs(ecosystem): add opencode-supabase to ecosystem plugins (#49848)
- @Jaaneek:
  - fix(opencode): bump @ai-sdk/xai to 3.0.139 so tool-result images reach xAI (#53549)

(no notes)

(no notes)

Stable release of the Continue VS Code extension (final release): removes the CLI-install banner and Generate Rule feature, switches onboarding and the new-config template to explicit model definitions (no Hub slugs), and updates the deprecation banner export link. Re-cut of v1.2.23 which only partially published due to a transient Marketplace API timeout.

Stable release of the Continue VS Code extension (final release): removes the CLI-install banner and Generate Rule feature, switches onboarding and the new-config template to explicit model definitions (no Hub slugs), and updates the deprecation banner export link.

Pre-release of the Continue VS Code extension (final-release cleanup).