Changelog for v0.32.0-preview.0

[gemini-cli-robot]

This PR contains the auto-generated changelog for the v0.32.0-preview.0 release.

Please review and merge.

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request updates the preview.md changelog file to reflect the new v0.32.0-preview.0 release. It includes a comprehensive summary of the latest enhancements across Plan Mode, agent capabilities, CLI user experience, billing, security, and various stability improvements and bug fixes.

Highlights

• Plan Mode Enhancements: Significant updates to Plan Mode, including support for modifying plans in external editors, adaptive workflows based on task complexity, and new integration tests.
• Agent and Core Engine Updates: Enabled the generalist agent, introduced Kind.Agent for sub-agent classification, implemented task tracking foundation, and improved Agent-to-Agent (A2A) streaming and content extraction.
• CLI & User Experience: Introduced interactive shell autocompletion, added a new verbosity mode for cleaner error reporting, enabled parallel loading of extensions, and improved UI hints and shortcut handling.
• Billing and Security: Implemented G1 AI credits overage flow with enhanced billing telemetry, updated the authentication handshake to specification, and added support for a policy engine in extensions.
• Stability and Bug Fixes: Addressed numerous issues including 100% CPU consumption by orphaned processes, enhanced retry logic for Code Assist, reduced intrusive MCP errors, and merged duplicate imports across packages.

Changelog

• docs/changelogs/preview.md
  • feat(plan): add integration tests for plan mode by @Adib234 in feat(plan): add integration tests for plan mode  #20214
  • fix(acp): update auth handshake to spec by @skeshive in fix(acp): update auth handshake to spec #19725
  • feat(core): implement robust A2A streaming reassembly and fix task continuity by @adamfweidman in feat(core): implement robust A2A streaming reassembly and fix task continuity #20091
  • feat(cli): load extensions in parallel by @scidomino in feat(cli): load extensions in parallel #20229
  • Plumb the maxAttempts setting through Config args by @kevinjwang1 in Plumb the maxAttempts setting through Config args #20239
  • fix(cli): skip 404 errors in setup-github file downloads by @h30s in fix(cli): skip 404 errors in setup-github file downloads #20287
  • fix(cli): expose model.name setting in settings dialog for persistence by @achaljhawar in fix(cli): expose model.name setting in settings dialog for persistence #19605
  • docs: remove legacy cmd examples in favor of powershell by @scidomino in docs: remove legacy cmd examples in favor of powershell #20323
  • feat(core): Enable model steering in workspace. by @joshualitt in feat(core): Enable model steering in workspace. #20343
  • fix: remove trailing comma in issue triage workflow settings json by @Nixxx19 in fix: remove trailing comma in issue triage workflow settings json #20265
  • feat(core): implement task tracker foundation and service by @anj-s in feat(core): implement task tracker foundation and service #19464
  • test: support tests that include color information by @jacob314 in test: support tests that include color information #20220
  • feat(core): introduce Kind.Agent for sub-agent classification by @abhipatel12 in feat(core): introduce Kind.Agent for sub-agent classification #20369
  • Changelog for v0.30.0 by @gemini-cli-robot in Changelog for v0.30.0 #20252
  • Update changelog workflow to reject nightly builds by @g-samroberts in Update changelog workflow to reject nightly builds #20248
  • Changelog for v0.31.0-preview.0 by @gemini-cli-robot in Changelog for v0.31.0-preview.0 #20249
  • feat(cli): hide workspace policy update dialog and auto-accept by default by @Abhijit-2592 in feat(cli): hide workspace policy update dialog and auto-accept by default #20351
  • feat(core): rename grep_search include parameter to include_pattern by @SandyTao520 in feat(core): rename grep_search include parameter to include_pattern #20328
  • feat(plan): support opening and modifying plan in external editor by @Adib234 in feat(plan): support opening and modifying plan in external editor #20348
  • feat(cli): implement interactive shell autocompletion by @mrpmohiburrahman in feat(cli): implement interactive shell autocompletion #20082
  • fix(core): allow /memory add to work in plan mode by @Jefftree in fix(core): allow /memory add to work in plan mode #20353
  • feat(core): add HTTP 499 to retryable errors and map to RetryableQuotaError by @bdmorgan in feat(core): add HTTP 499 to retryable errors and map to RetryableQuotaError #20432
  • feat(core): Enable generalist agent by @joshualitt in feat(core): Enable generalist agent #19665
  • Updated tests in TableRenderer.test.tsx to use SVG snapshots by @devr0306 in Updated tests in TableRenderer.test.tsx to use SVG snapshots #20450
  • Refactor Github Action per b/485167538 by @google-admin in Refactor Github Action per b/485167538 #19443
  • fix(github): resolve actionlint and yamllint regressions from Refactor Github Action per b/485167538 #19443 by @jerop in fix(github): resolve actionlint and yamllint regressions from #19443 #20467
  • fix: action var usage by @galz10 in fix: action var usage #20492
  • feat(core): improve A2A content extraction by @adamfweidman in feat(core): improve A2A content extraction #20487
  • fix(cli): support quota error fallbacks for all authentication types by @sehoon38 in fix(cli): support quota error fallbacks for all authentication types #20475
  • fix(core): flush transcript for pure tool-call responses to ensure BeforeTool hooks see complete state by @krishdef7 in fix(core): flush transcript for pure tool-call responses to ensure BeforeTool hooks see complete state #20419
  • feat(plan): adapt planning workflow based on complexity of task by @jerop in feat(plan): adapt planning workflow based on complexity of task #20465
  • fix: prevent orphaned processes from consuming 100% CPU when terminal closes by @yuvrajangadsingh in fix: prevent orphaned processes from consuming 100% CPU when terminal closes #16965
  • feat(core): increase fetch timeout and fix [object Object] error stringification by @bdmorgan in feat(core): increase fetch timeout and fix [object Object] error stringification #20441
  • [Gemma x Gemini CLI] Add an Experimental Gemma Router that uses a LiteRT-LM shim into the Composite Model Classifier Strategy by @sidwan02 in [Gemma x Gemini CLI] Add an Experimental Gemma Router that uses a LiteRT-LM shim into the Composite Model Classifier Strategy #17231
  • docs(plan): update documentation regarding supporting editing of plan files during plan approval by @Adib234 in docs(plan): update documentation regarding supporting editing of plan files during plan approval #20452
  • test(cli): fix flaky ToolResultDisplay overflow test by @jwhelangoog in test(cli): fix flaky ToolResultDisplay overflow test #20518
  • ui(cli): reduce length of Ctrl+O hint by @jwhelangoog in ui(cli): reduce length of Ctrl+O hint #20490
  • fix(ui): correct styled table width calculations by @devr0306 in fix(ui): correct styled table width calculations #20042
  • Avoid overaggressive unescaping by @scidomino in Avoid overaggressive unescaping #20520
  • feat(telemetry) Instrument traces with more attributes and make them available to OTEL users by @heaventourist in feat(telemetry) Instrument traces with more attributes and make them available to OTEL users #20237
  • Add support for policy engine in extensions by @chrstnb in Add support for policy engine in extensions #20049
  • Docs: Update to Terms of Service & FAQ by @jkcinouye in Docs: Update to Terms of Service & FAQ #20488
  • Fix bottom border rendering for search and add a regression test. by @jacob314 in Fix bottom border rendering for search and add a regression test. #20517
  • fix(core): apply retry logic to CodeAssistServer for all users by @bdmorgan in fix(core): apply retry logic to CodeAssistServer for all users #20507
  • Fix extension MCP server env var loading by @chrstnb in Fix extension MCP server env var loading #20374
  • feat(ui): add 'ctrl+o' hint to truncated content message by @jerop in feat(ui): add 'ctrl+o' hint to truncated content message #20529
  • Fix flicker showing message to press ctrl-O again to collapse. by @jacob314 in Fix flicker showing message to press ctrl-O again to collapse. #20414
  • fix(cli): hide shortcuts hint while model is thinking or the user has typed a prompt + add debounce to avoid flicker by @jacob314 in fix(cli): hide shortcuts hint while model is thinking or the user has typed a prompt + add debounce to avoid flicker #19389
  • feat(plan): update planning workflow to encourage multi-select with descriptions of options by @Adib234 in feat(plan): update planning workflow to encourage multi-select with descriptions of options #20491
  • refactor(core,cli): useAlternateBuffer read from config by @psinha40898 in refactor(core,cli): useAlternateBuffer read from config #20346
  • fix(cli): ensure dialogs stay scrolled to bottom in alternate buffer mode by @jacob314 in fix(cli): ensure dialogs stay scrolled to bottom in alternate buffer mode #20527
  • fix(core): revert auto-save of policies to user space by @Abhijit-2592 in fix(core): revert auto-save of policies to user space #20531
  • Demote unreliable test. by @gundermanc in Demote unreliable test. #20571
  • fix(core): handle optional response fields from code assist API by @sehoon38 in fix(core): handle optional response fields from code assist API #20345
  • fix(cli): keep thought summary when loading phrases are off by @LyalinDotCom in fix(cli): keep thought summary when loading phrases are off #20497
  • feat(cli): add temporary flag to disable workspace policies by @Abhijit-2592 in feat(cli): add temporary flag to disable workspace policies #20523
  • Disable expensive and scheduled workflows on personal forks by @dewitt in Disable expensive and scheduled workflows on personal forks #20449
  • Moved markdown parsing logic to a separate util file by @devr0306 in Moved markdown parsing logic to a separate util file #20526
  • fix(plan): prevent agent from using ask_user for shell command confirmation by @Adib234 in fix(plan): prevent agent from using ask_user for shell command confirmation #20504
  • fix(core): disable retries for code assist streaming requests by @sehoon38 in fix(core): disable retries for code assist streaming requests #20561
  • feat(billing): implement G1 AI credits overage flow with billing telemetry by @gsquared94 in feat(billing): implement G1 AI credits overage flow with billing telemetry #18590
  • feat: better error messages by @gsquared94 in feat: better error messages #20577
  • fix(ui): persist expansion in AskUser dialog when navigating options by @jerop in fix(ui): persist expansion in AskUser dialog when navigating options #20559
  • fix(cli): prevent sub-agent tool calls from leaking into UI by @abhipatel12 in fix(cli): prevent sub-agent tool calls from leaking into UI #20580
  • fix(cli): Shell autocomplete polish by @jacob314 in fix(cli): Shell autocomplete polish #20411
  • Changelog for v0.31.0-preview.1 by @gemini-cli-robot in Changelog for v0.31.0-preview.1 #20590
  • Add slash command for promoting behavioral evals to CI blocking by @gundermanc in Add slash command for promoting behavioral evals to CI blocking #20575
  • Changelog for v0.30.1 by @gemini-cli-robot in Changelog for v0.30.1 #20589
  • Add low/full CLI error verbosity mode for cleaner UI by @LyalinDotCom in Add low/full CLI error verbosity mode for cleaner UI #20399
  • Disable Gemini PR reviews on draft PRs. by @gundermanc in Disable Gemini PR reviews on draft PRs. #20362
  • Docs: FAQ update by @jkcinouye in Docs: FAQ update #20585
  • fix(core): reduce intrusive MCP errors and deduplicate diagnostics by @spencer426 in fix(core): reduce intrusive MCP errors and deduplicate diagnostics #20232
  • docs: fix spelling typos in installation guide by @campox747 in docs: fix spelling typos in installation guide #20579
  • Promote stable tests to CI blocking. by @gundermanc in Promote stable tests to CI blocking. #20581
  • feat(core): enable contiguous parallel admission for Kind.Agent tools by @abhipatel12 in feat(core): enable contiguous parallel admission for Kind.Agent tools #20583
  • Enforce import/no-duplicates as error by @Nixxx19 in Enforce import/no-duplicates as error #19797
  • fix: merge duplicate imports in sdk and test-utils packages (1/4) by @Nixxx19 in fix: merge duplicate imports in sdk and test-utils packages (1/4) #19777
  • fix: merge duplicate imports in a2a-server package (2/4) by @Nixxx19 in fix: merge duplicate imports in a2a-server package (2/4) #19781

Activity

• The pull request was auto-generated by gemini-cli-robot to update the changelog for the v0.32.0-preview.0 release.
• The author has requested a review and merge of the updated changelog.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[github-actions]

Size Change: -2 B (0%)

Total Size: 25.8 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	25.3 MB	-2 B (0%)
./bundle/node_modules/@google/gemini-cli-devtools/dist/client/main.js	221 kB	0 B
./bundle/node_modules/@google/gemini-cli-devtools/dist/src/_client-assets.js	227 kB	0 B
./bundle/node_modules/@google/gemini-cli-devtools/dist/src/index.js	11.5 kB	0 B
./bundle/node_modules/@google/gemini-cli-devtools/dist/src/types.js	132 B	0 B
./bundle/sandbox-macos-permissive-open.sb	890 B	0 B
./bundle/sandbox-macos-permissive-proxied.sb	1.31 kB	0 B
./bundle/sandbox-macos-restrictive-open.sb	3.36 kB	0 B
./bundle/sandbox-macos-restrictive-proxied.sb	3.56 kB	0 B
./bundle/sandbox-macos-strict-open.sb	4.82 kB	0 B
./bundle/sandbox-macos-strict-proxied.sb	5.02 kB	0 B

_{compressed-size-action}

[gemini-code-assist]

Code Review

This pull request updates the preview changelog for the v0.32.0-preview.0 release. While the update reflects a new set of changes, there are critical issues with the generated content that violate established changelog rules. The changelog incorrectly includes PRs for previous changelogs, making it confusing and violating the rule that only specific patch changes should be listed. More importantly, the 'Full Changelog' link skips several preview versions, potentially omitting important changes and violating the rule that the link must compare the immediate previous version. These issues must be addressed to ensure the changelog is accurate and useful for users.