MediaMetz/gemini-cli
1
0
Fork 0
mirror of https://github.com/google-gemini/gemini-cli.git synced 2026-04-22 19:14:33 -07:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into memory_usage3

Browse Source
This commit is contained in:
Spencer
2026-04-15 16:15:59 -04:00
committed by GitHub
parent d0272a6436 e827cfdf83
commit cdf5c265d8
24 changed files with 2246 additions and 748 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/changelogs/index.md
+21
View File
@@ -18,6 +18,27 @@ on GitHub.
| [Preview](preview.md) | Experimental features ready for early feedback. |
| [Stable](latest.md) | Stable, recommended for general use. |
## Announcements: v0.38.0 - 2026-04-14
- **Chapters Narrative Flow:** Group agent interactions into "Chapters" based on
intent and tool usage for better session structure
([#23150](https://github.com/google-gemini/gemini-cli/pull/23150) by
@Abhijit-2592,
[#24079](https://github.com/google-gemini/gemini-cli/pull/24079) by
@gundermanc).
- **Context Compression Service:** Advanced context management to efficiently
distill conversation history
([#24483](https://github.com/google-gemini/gemini-cli/pull/24483) by
@joshualitt).
- **UI Flicker & UX Enhancements:** Solved rendering flicker with "Terminal
Buffer" mode and introduced selective topic expansion
([#24512](https://github.com/google-gemini/gemini-cli/pull/24512) by
@jacob314, [#24793](https://github.com/google-gemini/gemini-cli/pull/24793) by
@Abhijit-2592).
- **Persistent Policy Approvals:** Implemented context-aware persistent
approvals for tool execution
([#23257](https://github.com/google-gemini/gemini-cli/pull/23257) by @jerop).
## Announcements: v0.37.0 - 2026-04-08
- **Dynamic Sandbox Expansion:** Implemented dynamic sandbox expansion and
docs/changelogs/latest.md
+250 -410
View File
@@ -1,6 +1,6 @@
# Latest stable release: v0.37.2
# Latest stable release: v0.38.0
Released: April 13, 2026
Released: April 14, 2026
For most users, our latest stable release is the recommended release. Install
the latest stable version with:
@@ -11,418 +11,258 @@ npm install -g @google/gemini-cli
## Highlights
- **Dynamic Sandbox Expansion:** Implemented dynamic sandbox expansion and
worktree support for both Linux and Windows, enhancing development flexibility
in restricted environments.
- **Tool-Based Topic Grouping (Chapters):** Introduced "Chapters" to logically
group agent interactions based on tool usage and intent, providing a clearer
narrative flow in long sessions.
- **Enhanced Browser Agent:** Added persistent session management, dynamic
read-only tool discovery, and sandbox-aware initialization for the browser
agent.
- **Security & Permission Hardening:** Implemented secret visibility lockdown
for environment files and integrated integrity controls for Windows
sandboxing.
- **Chapters Narrative Flow:** Introduced tool-based topic grouping ("Chapters")
to provide better session structure and narrative continuity in long-running
tasks.
- **Context Compression Service:** Implemented a dedicated service for advanced
context management, efficiently distilling conversation history to preserve
focus and tokens.
- **Enhanced UI Stability & UX:** Introduced a new "Terminal Buffer" mode to
solve rendering flicker, along with selective topic expansion and improved
tool confirmation layouts.
- **Context-Aware Policy Approvals:** Users can now grant persistent,
context-aware approvals for tools, significantly reducing manual confirmation
overhead for trusted workflows.
- **Background Process Monitoring:** New tools for monitoring and inspecting
background shell processes, providing better visibility into asynchronous
tasks.
## What's Changed
- fix(patch): cherry-pick 9d741ab to release/v0.37.1-pr-24565 to patch version
v0.37.1 and create version 0.37.2 by @gemini-cli-robot in
[#25322](https://github.com/google-gemini/gemini-cli/pull/25322)
- fix(acp): handle all InvalidStreamError types gracefully in prompt
[#24540](https://github.com/google-gemini/gemini-cli/pull/24540)
- feat(acp): add support for /about command
[#24649](https://github.com/google-gemini/gemini-cli/pull/24649)
- feat(acp): add /help command
[#24839](https://github.com/google-gemini/gemini-cli/pull/24839)
- feat(evals): centralize test agents into test-utils for reuse by @Samee24 in
[#23616](https://github.com/google-gemini/gemini-cli/pull/23616)
- revert: chore(config): disable agents by default by @abhipatel12 in
[#23672](https://github.com/google-gemini/gemini-cli/pull/23672)
- fix(plan): update telemetry attribute keys and add timestamp by @Adib234 in
[#23685](https://github.com/google-gemini/gemini-cli/pull/23685)
- fix(core): prevent premature MCP discovery completion by @jackwotherspoon in
[#23637](https://github.com/google-gemini/gemini-cli/pull/23637)
- feat(browser): add maxActionsPerTask for browser agent setting by
@cynthialong0-0 in
[#23216](https://github.com/google-gemini/gemini-cli/pull/23216)
- fix(core): improve agent loader error formatting for empty paths by
@adamfweidman in
[#23690](https://github.com/google-gemini/gemini-cli/pull/23690)
- fix(cli): only show updating spinner when auto-update is in progress by
@scidomino in [#23709](https://github.com/google-gemini/gemini-cli/pull/23709)
- Refine onboarding metrics to log the duration explicitly and use the tier
name. by @yunaseoul in
[#23678](https://github.com/google-gemini/gemini-cli/pull/23678)
- chore(tools): add toJSON to tools and invocations to reduce logging verbosity
by @alisa-alisa in
[#22899](https://github.com/google-gemini/gemini-cli/pull/22899)
- fix(cli): stabilize copy mode to prevent flickering and cursor resets by
@mattKorwel in
[#22584](https://github.com/google-gemini/gemini-cli/pull/22584)
- fix(test): move flaky ctrl-c-exit test to non-blocking suite by @mattKorwel in
[#23732](https://github.com/google-gemini/gemini-cli/pull/23732)
- feat(skills): add ci skill for automated failure replication by @mattKorwel in
[#23720](https://github.com/google-gemini/gemini-cli/pull/23720)
- feat(sandbox): implement forbiddenPaths for OS-specific sandbox managers by
@ehedlund in [#23282](https://github.com/google-gemini/gemini-cli/pull/23282)
- fix(core): conditionally expose additional_permissions in shell tool by
@galz10 in [#23729](https://github.com/google-gemini/gemini-cli/pull/23729)
- refactor(core): standardize OS-specific sandbox tests and extract linux helper
methods by @ehedlund in
[#23715](https://github.com/google-gemini/gemini-cli/pull/23715)
- format recently added script by @scidomino in
[#23739](https://github.com/google-gemini/gemini-cli/pull/23739)
- fix(ui): prevent over-eager slash subcommand completion by @keithguerin in
[#20136](https://github.com/google-gemini/gemini-cli/pull/20136)
- Fix dynamic model routing for gemini 3.1 pro to customtools model by
@kevinjwang1 in
[#23641](https://github.com/google-gemini/gemini-cli/pull/23641)
- feat(core): support inline agentCardJson for remote agents by @adamfweidman in
[#23743](https://github.com/google-gemini/gemini-cli/pull/23743)
- fix(cli): skip console log/info in headless mode by @cynthialong0-0 in
[#22739](https://github.com/google-gemini/gemini-cli/pull/22739)
- test(core): install bubblewrap on Linux CI for sandbox integration tests by
@ehedlund in [#23583](https://github.com/google-gemini/gemini-cli/pull/23583)
- docs(reference): split tools table into category sections by @sheikhlimon in
[#21516](https://github.com/google-gemini/gemini-cli/pull/21516)
- fix(browser): detect embedded URLs in query params to prevent allowedDomains
bypass by @tony-shi in
[#23225](https://github.com/google-gemini/gemini-cli/pull/23225)
- fix(browser): add proxy bypass constraint to domain restriction system prompt
by @tony-shi in
[#23229](https://github.com/google-gemini/gemini-cli/pull/23229)
- fix(policy): relax write_file argsPattern in plan mode to allow paths without
session ID by @Adib234 in
[#23695](https://github.com/google-gemini/gemini-cli/pull/23695)
- docs: fix grammar in CONTRIBUTING and numbering in sandbox docs by
@splint-disk-8i in
[#23448](https://github.com/google-gemini/gemini-cli/pull/23448)
- fix(acp): allow attachments by adding a permission prompt by @sripasg in
[#23680](https://github.com/google-gemini/gemini-cli/pull/23680)
- fix(core): thread AbortSignal to chat compression requests (#20405) by
@SH20RAJ in [#20778](https://github.com/google-gemini/gemini-cli/pull/20778)
- feat(core): implement Windows sandbox dynamic expansion Phase 1 and 2.1 by
@scidomino in [#23691](https://github.com/google-gemini/gemini-cli/pull/23691)
- Add note about root privileges in sandbox docs by @diodesign in
[#23314](https://github.com/google-gemini/gemini-cli/pull/23314)
- docs(core): document agent_card_json string literal options for remote agents
by @adamfweidman in
[#23797](https://github.com/google-gemini/gemini-cli/pull/23797)
- fix(cli): resolve TTY hang on headless environments by unconditionally
resuming process.stdin before React Ink launch by @cocosheng-g in
[#23673](https://github.com/google-gemini/gemini-cli/pull/23673)
- fix(ui): cleanup estimated string length hacks in composer by @keithguerin in
[#23694](https://github.com/google-gemini/gemini-cli/pull/23694)
- feat(browser): dynamically discover read-only tools by @cynthialong0-0 in
[#23805](https://github.com/google-gemini/gemini-cli/pull/23805)
- docs: clarify policy requirement for `general.plan.directory` in settings
schema by @jerop in
[#23784](https://github.com/google-gemini/gemini-cli/pull/23784)
- Revert "perf(cli): optimize --version startup time (#23671)" by @scidomino in
[#23812](https://github.com/google-gemini/gemini-cli/pull/23812)
- don't silence errors from wombat by @scidomino in
[#23822](https://github.com/google-gemini/gemini-cli/pull/23822)
- fix(ui): prevent escape key from cancelling requests in shell mode by
@PrasannaPal21 in
[#21245](https://github.com/google-gemini/gemini-cli/pull/21245)
- Changelog for v0.36.0-preview.0 by @gemini-cli-robot in
[#23702](https://github.com/google-gemini/gemini-cli/pull/23702)
- feat(core,ui): Add experiment-gated support for gemini flash 3.1 lite by
@chrstnb in [#23794](https://github.com/google-gemini/gemini-cli/pull/23794)
- Changelog for v0.36.0-preview.3 by @gemini-cli-robot in
[#23827](https://github.com/google-gemini/gemini-cli/pull/23827)
- new linting check: github-actions-pinning by @alisa-alisa in
[#23808](https://github.com/google-gemini/gemini-cli/pull/23808)
- fix(cli): show helpful guidance when no skills are available by @Niralisj in
[#23785](https://github.com/google-gemini/gemini-cli/pull/23785)
- fix: Chat logs and errors handle tail tool calls correctly by @googlestrobe in
[#22460](https://github.com/google-gemini/gemini-cli/pull/22460)
- Don't try removing a tag from a non-existent release. by @scidomino in
[#23830](https://github.com/google-gemini/gemini-cli/pull/23830)
- fix(cli): allow ask question dialog to take full window height by @jacob314 in
[#23693](https://github.com/google-gemini/gemini-cli/pull/23693)
- fix(core): strip leading underscores from error types in telemetry by
@yunaseoul in [#23824](https://github.com/google-gemini/gemini-cli/pull/23824)
- Changelog for v0.35.0 by @gemini-cli-robot in
[#23819](https://github.com/google-gemini/gemini-cli/pull/23819)
- feat(evals): add reliability harvester and 500/503 retry support by
@alisa-alisa in
[#23626](https://github.com/google-gemini/gemini-cli/pull/23626)
- feat(sandbox): dynamic Linux sandbox expansion and worktree support by @galz10
in [#23692](https://github.com/google-gemini/gemini-cli/pull/23692)
- Merge examples of use into quickstart documentation by @diodesign in
[#23319](https://github.com/google-gemini/gemini-cli/pull/23319)
- fix(cli): prioritize primary name matches in slash command search by @sehoon38
in [#23850](https://github.com/google-gemini/gemini-cli/pull/23850)
- Changelog for v0.35.1 by @gemini-cli-robot in
[#23840](https://github.com/google-gemini/gemini-cli/pull/23840)
- fix(browser): keep input blocker active across navigations by @kunal-10-cloud
in [#22562](https://github.com/google-gemini/gemini-cli/pull/22562)
- feat(core): new skill to look for duplicated code while reviewing PRs by
@devr0306 in [#23704](https://github.com/google-gemini/gemini-cli/pull/23704)
- fix(core): replace hardcoded non-interactive ASK_USER denial with explicit
policy rules by @ruomengz in
[#23668](https://github.com/google-gemini/gemini-cli/pull/23668)
- fix(plan): after exiting plan mode switches model to a flash model by @Adib234
in [#23885](https://github.com/google-gemini/gemini-cli/pull/23885)
- feat(gcp): add development worker infrastructure by @mattKorwel in
[#23814](https://github.com/google-gemini/gemini-cli/pull/23814)
- fix(a2a-server): A2A server should execute ask policies in interactive mode by
@kschaab in [#23831](https://github.com/google-gemini/gemini-cli/pull/23831)
- feat(core): define TrajectoryProvider interface by @sehoon38 in
[#23050](https://github.com/google-gemini/gemini-cli/pull/23050)
- Docs: Update quotas and pricing by @jkcinouye in
[#23835](https://github.com/google-gemini/gemini-cli/pull/23835)
- fix(core): allow disabling environment variable redaction by @galz10 in
[#23927](https://github.com/google-gemini/gemini-cli/pull/23927)
- feat(cli): enable notifications cross-platform via terminal bell fallback by
@genneth in [#21618](https://github.com/google-gemini/gemini-cli/pull/21618)
- feat(sandbox): implement secret visibility lockdown for env files by
@DavidAPierce in
[#23712](https://github.com/google-gemini/gemini-cli/pull/23712)
- fix(core): remove shell outputChunks buffer caching to prevent memory bloat
and sanitize prompt input by @spencer426 in
[#23751](https://github.com/google-gemini/gemini-cli/pull/23751)
- feat(core): implement persistent browser session management by @kunal-10-cloud
in [#21306](https://github.com/google-gemini/gemini-cli/pull/21306)
- refactor(core): delegate sandbox denial parsing to SandboxManager by
@scidomino in [#23928](https://github.com/google-gemini/gemini-cli/pull/23928)
- dep(update) Update Ink version to 6.5.0 by @jacob314 in
[#23843](https://github.com/google-gemini/gemini-cli/pull/23843)
- Docs: Update 'docs-writer' skill for relative links by @jkcinouye in
[#21463](https://github.com/google-gemini/gemini-cli/pull/21463)
- Changelog for v0.36.0-preview.4 by @gemini-cli-robot in
[#23935](https://github.com/google-gemini/gemini-cli/pull/23935)
- fix(acp): Update allow approval policy flow for ACP clients to fix config
persistence and compatible with TUI by @sripasg in
[#23818](https://github.com/google-gemini/gemini-cli/pull/23818)
- Changelog for v0.35.2 by @gemini-cli-robot in
[#23960](https://github.com/google-gemini/gemini-cli/pull/23960)
- ACP integration documents by @g-samroberts in
[#22254](https://github.com/google-gemini/gemini-cli/pull/22254)
- fix(core): explicitly set error names to avoid bundling renaming issues by
@yunaseoul in [#23913](https://github.com/google-gemini/gemini-cli/pull/23913)
- feat(core): subagent isolation and cleanup hardening by @abhipatel12 in
[#23903](https://github.com/google-gemini/gemini-cli/pull/23903)
- disable extension-reload test by @scidomino in
[#24018](https://github.com/google-gemini/gemini-cli/pull/24018)
- feat(core): add forbiddenPaths to GlobalSandboxOptions and refactor
createSandboxManager by @ehedlund in
[#23936](https://github.com/google-gemini/gemini-cli/pull/23936)
- refactor(core): improve ignore resolution and fix directory-matching bug by
@ehedlund in [#23816](https://github.com/google-gemini/gemini-cli/pull/23816)
- revert(core): support custom base URL via env vars by @spencer426 in
[#23976](https://github.com/google-gemini/gemini-cli/pull/23976)
- Increase memory limited for eslint. by @jacob314 in
[#24022](https://github.com/google-gemini/gemini-cli/pull/24022)
- fix(acp): prevent crash on empty response in ACP mode by @sripasg in
[#23952](https://github.com/google-gemini/gemini-cli/pull/23952)
- feat(core): Land `AgentHistoryProvider`. by @joshualitt in
[#23978](https://github.com/google-gemini/gemini-cli/pull/23978)
- fix(core): switch to subshells for shell tool wrapping to fix heredocs and
edge cases by @abhipatel12 in
[#24024](https://github.com/google-gemini/gemini-cli/pull/24024)
- Debug command. by @jacob314 in
[#23851](https://github.com/google-gemini/gemini-cli/pull/23851)
- Changelog for v0.36.0-preview.5 by @gemini-cli-robot in
[#24046](https://github.com/google-gemini/gemini-cli/pull/24046)
- Fix test flakes by globally mocking ink-spinner by @jacob314 in
[#24044](https://github.com/google-gemini/gemini-cli/pull/24044)
- Enable network access in sandbox configuration by @galz10 in
[#24055](https://github.com/google-gemini/gemini-cli/pull/24055)
- feat(context): add configurable memoryBoundaryMarkers setting by @SandyTao520
in [#24020](https://github.com/google-gemini/gemini-cli/pull/24020)
- feat(core): implement windows sandbox expansion and denial detection by
@scidomino in [#24027](https://github.com/google-gemini/gemini-cli/pull/24027)
- fix(core): resolve ACP Operation Aborted Errors in grep_search by @ivanporty
in [#23821](https://github.com/google-gemini/gemini-cli/pull/23821)
- fix(hooks): prevent SessionEnd from firing twice in non-interactive mode by
@krishdef7 in [#22139](https://github.com/google-gemini/gemini-cli/pull/22139)
- Re-word intro to Gemini 3 page. by @g-samroberts in
[#24069](https://github.com/google-gemini/gemini-cli/pull/24069)
- fix(cli): resolve layout contention and flashing loop in StatusRow by
@keithguerin in
[#24065](https://github.com/google-gemini/gemini-cli/pull/24065)
- fix(sandbox): implement Windows Mandatory Integrity Control for GeminiSandbox
by @galz10 in [#24057](https://github.com/google-gemini/gemini-cli/pull/24057)
- feat(core): implement tool-based topic grouping (Chapters) by @Abhijit-2592 in
[#23150](https://github.com/google-gemini/gemini-cli/pull/23150)
- feat(cli): support 'tab to queue' for messages while generating by @gundermanc
in [#24052](https://github.com/google-gemini/gemini-cli/pull/24052)
- feat(core): agnostic background task UI with CompletionBehavior by
@adamfweidman in
[#22740](https://github.com/google-gemini/gemini-cli/pull/22740)
- UX for topic narration tool by @gundermanc in
[#24079](https://github.com/google-gemini/gemini-cli/pull/24079)
- fix: shellcheck warnings in scripts by @scidomino in
[#24035](https://github.com/google-gemini/gemini-cli/pull/24035)
- test(evals): add comprehensive subagent delegation evaluations by @abhipatel12
in [#24132](https://github.com/google-gemini/gemini-cli/pull/24132)
- fix(a2a-server): prioritize ADC before evaluating headless constraints for
auth initialization by @spencer426 in
[#23614](https://github.com/google-gemini/gemini-cli/pull/23614)
- Text can be added after /plan command by @rambleraptor in
[#22833](https://github.com/google-gemini/gemini-cli/pull/22833)
- fix(cli): resolve missing F12 logs via global console store by @scidomino in
[#24235](https://github.com/google-gemini/gemini-cli/pull/24235)
- fix broken tests by @scidomino in
[#24279](https://github.com/google-gemini/gemini-cli/pull/24279)
- fix(evals): add update_topic behavioral eval by @gundermanc in
[#24223](https://github.com/google-gemini/gemini-cli/pull/24223)
- feat(core): Unified Context Management and Tool Distillation. by @joshualitt
in [#24157](https://github.com/google-gemini/gemini-cli/pull/24157)
- Default enable narration for the team. by @gundermanc in
[#24224](https://github.com/google-gemini/gemini-cli/pull/24224)
- fix(core): ensure default agents provide tools and use model-specific schemas
by @abhipatel12 in
[#24268](https://github.com/google-gemini/gemini-cli/pull/24268)
- feat(cli): show Flash Lite Preview model regardless of user tier by @sehoon38
in [#23904](https://github.com/google-gemini/gemini-cli/pull/23904)
- feat(cli): implement compact tool output by @jwhelangoog in
[#20974](https://github.com/google-gemini/gemini-cli/pull/20974)
- Add security settings for tool sandboxing by @galz10 in
[#23923](https://github.com/google-gemini/gemini-cli/pull/23923)
- chore(test-utils): switch integration tests to use PREVIEW_GEMINI_MODEL by
@sehoon38 in [#24276](https://github.com/google-gemini/gemini-cli/pull/24276)
- feat(core): enable topic update narration for legacy models by @Abhijit-2592
in [#24241](https://github.com/google-gemini/gemini-cli/pull/24241)
- feat(core): add project-level memory scope to save_memory tool by @SandyTao520
in [#24161](https://github.com/google-gemini/gemini-cli/pull/24161)
- test(integration): fix plan mode write denial test false positive by @sehoon38
in [#24299](https://github.com/google-gemini/gemini-cli/pull/24299)
- feat(plan): support `Plan` mode in untrusted folders by @Adib234 in
[#17586](https://github.com/google-gemini/gemini-cli/pull/17586)
- fix(core): enable mid-stream retries for all models and re-enable compression
test by @sehoon38 in
[#24302](https://github.com/google-gemini/gemini-cli/pull/24302)
- Changelog for v0.36.0-preview.6 by @gemini-cli-robot in
[#24082](https://github.com/google-gemini/gemini-cli/pull/24082)
- Changelog for v0.35.3 by @gemini-cli-robot in
[#24083](https://github.com/google-gemini/gemini-cli/pull/24083)
- feat(cli): add auth info to footer by @sehoon38 in
[#24042](https://github.com/google-gemini/gemini-cli/pull/24042)
- fix(browser): reset action counter for each agent session and let it ignore
internal actions by @cynthialong0-0 in
[#24228](https://github.com/google-gemini/gemini-cli/pull/24228)
- feat(plan): promote planning feature to stable by @ruomengz in
[#24282](https://github.com/google-gemini/gemini-cli/pull/24282)
- fix(browser): terminate subagent immediately on domain restriction violations
by @gsquared94 in
[#24313](https://github.com/google-gemini/gemini-cli/pull/24313)
- feat(cli): add UI to update extensions by @ruomengz in
[#23682](https://github.com/google-gemini/gemini-cli/pull/23682)
- Fix(browser): terminate immediately for "browser is already running" error by
@cynthialong0-0 in
[#24233](https://github.com/google-gemini/gemini-cli/pull/24233)
- docs: Add 'plan' option to approval mode in CLI reference by @YifanRuan in
[#24134](https://github.com/google-gemini/gemini-cli/pull/24134)
- fix(core): batch macOS seatbelt rules into a profile file to prevent ARG_MAX
errors by @ehedlund in
[#24255](https://github.com/google-gemini/gemini-cli/pull/24255)
- fix(core): fix race condition between browser agent and main closing process
by @cynthialong0-0 in
[#24340](https://github.com/google-gemini/gemini-cli/pull/24340)
- perf(build): optimize build scripts for parallel execution and remove
redundant checks by @sehoon38 in
[#24307](https://github.com/google-gemini/gemini-cli/pull/24307)
- ci: install bubblewrap on Linux for release workflows by @ehedlund in
[#24347](https://github.com/google-gemini/gemini-cli/pull/24347)
- chore(release): allow bundling for all builds, including stable by @sehoon38
in [#24305](https://github.com/google-gemini/gemini-cli/pull/24305)
- Revert "Add security settings for tool sandboxing" by @jerop in
[#24357](https://github.com/google-gemini/gemini-cli/pull/24357)
- docs: update subagents docs to not be experimental by @abhipatel12 in
[#24343](https://github.com/google-gemini/gemini-cli/pull/24343)
- fix(core): implement **read and **write commands in sandbox managers by
@galz10 in [#24283](https://github.com/google-gemini/gemini-cli/pull/24283)
- don't try to remove tags in dry run by @scidomino in
[#24356](https://github.com/google-gemini/gemini-cli/pull/24356)
- fix(config): disable JIT context loading by default by @SandyTao520 in
[#24364](https://github.com/google-gemini/gemini-cli/pull/24364)
- test(sandbox): add integration test for dynamic permission expansion by
@galz10 in [#24359](https://github.com/google-gemini/gemini-cli/pull/24359)
- docs(policy): remove unsupported mcpName wildcard edge case by @abhipatel12 in
[#24133](https://github.com/google-gemini/gemini-cli/pull/24133)
- docs: fix broken GEMINI.md link in CONTRIBUTING.md by @Panchal-Tirth in
[#24182](https://github.com/google-gemini/gemini-cli/pull/24182)
- feat(core): infrastructure for event-driven subagent history by @abhipatel12
in [#23914](https://github.com/google-gemini/gemini-cli/pull/23914)
- fix(core): resolve Plan Mode deadlock during plan file creation due to sandbox
restrictions by @DavidAPierce in
[#24047](https://github.com/google-gemini/gemini-cli/pull/24047)
- fix(core): fix browser agent UX issues and improve E2E test reliability by
@gsquared94 in
[#24312](https://github.com/google-gemini/gemini-cli/pull/24312)
- fix(ui): wrap topic and intent fields in TopicMessage by @jwhelangoog in
[#24386](https://github.com/google-gemini/gemini-cli/pull/24386)
- refactor(core): Centralize context management logic into src/context by
@joshualitt in
[#24380](https://github.com/google-gemini/gemini-cli/pull/24380)
- fix(core): pin AuthType.GATEWAY to use Gemini 3.1 Pro/Flash Lite by default by
@sripasg in [#24375](https://github.com/google-gemini/gemini-cli/pull/24375)
- feat(ui): add Tokyo Night theme by @danrneal in
[#24054](https://github.com/google-gemini/gemini-cli/pull/24054)
- fix(cli): refactor test config loading and mock debugLogger in test-setup by
@mattKorwel in
[#24389](https://github.com/google-gemini/gemini-cli/pull/24389)
- Set memoryManager to false in settings.json by @mattKorwel in
[#24393](https://github.com/google-gemini/gemini-cli/pull/24393)
- ink 6.6.3 by @jacob314 in
[#24372](https://github.com/google-gemini/gemini-cli/pull/24372)
- fix(core): resolve subagent chat recording gaps and directory inheritance by
- fix(cli): refresh slash command list after /skills reload by @NTaylorMullen in
[#24454](https://github.com/google-gemini/gemini-cli/pull/24454)
- Update README.md for links. by @g-samroberts in
[#22759](https://github.com/google-gemini/gemini-cli/pull/22759)
- fix(core): ensure complete_task tool calls are recorded in chat history by
@abhipatel12 in
[#24368](https://github.com/google-gemini/gemini-cli/pull/24368)
- fix(cli): cap shell output at 10 MB to prevent RangeError crash by @ProthamD
in [#24168](https://github.com/google-gemini/gemini-cli/pull/24168)
- feat(plan): conditionally add enter/exit plan mode tools based on current mode
by @ruomengz in
[#24378](https://github.com/google-gemini/gemini-cli/pull/24378)
- feat(core): prioritize discussion before formal plan approval by @jerop in
[#24423](https://github.com/google-gemini/gemini-cli/pull/24423)
- fix(ui): add accelerated scrolling on alternate buffer mode by @devr0306 in
[#23940](https://github.com/google-gemini/gemini-cli/pull/23940)
- feat(core): populate sandbox forbidden paths with project ignore file contents
by @ehedlund in
[#24038](https://github.com/google-gemini/gemini-cli/pull/24038)
- fix(core): ensure blue border overlay and input blocker to act correctly
depending on browser agent activities by @cynthialong0-0 in
[#24385](https://github.com/google-gemini/gemini-cli/pull/24385)
- fix(ui): removed additional vertical padding for tables by @devr0306 in
[#24381](https://github.com/google-gemini/gemini-cli/pull/24381)
- fix(build): upload full bundle directory archive to GitHub releases by
@sehoon38 in [#24403](https://github.com/google-gemini/gemini-cli/pull/24403)
- fix(build): wire bundle:browser-mcp into bundle pipeline by @gsquared94 in
[#24424](https://github.com/google-gemini/gemini-cli/pull/24424)
- feat(browser): add sandbox-aware browser agent initialization by @gsquared94
in [#24419](https://github.com/google-gemini/gemini-cli/pull/24419)
- feat(core): enhance tracker task schemas for detailed titles and descriptions
by @anj-s in [#23902](https://github.com/google-gemini/gemini-cli/pull/23902)
- refactor(core): Unified context management settings schema by @joshualitt in
[#24391](https://github.com/google-gemini/gemini-cli/pull/24391)
- feat(core): update browser agent prompt to check open pages first when
bringing up by @cynthialong0-0 in
[#24431](https://github.com/google-gemini/gemini-cli/pull/24431)
- fix(acp) refactor(core,cli): centralize model discovery logic in
ModelConfigService by @sripasg in
[#24392](https://github.com/google-gemini/gemini-cli/pull/24392)
- Changelog for v0.36.0-preview.7 by @gemini-cli-robot in
[#24346](https://github.com/google-gemini/gemini-cli/pull/24346)
- fix: update task tracker storage location in system prompt by @anj-s in
[#24034](https://github.com/google-gemini/gemini-cli/pull/24034)
- feat(browser): supersede stale snapshots to reclaim context-window tokens by
[#24437](https://github.com/google-gemini/gemini-cli/pull/24437)
- feat(policy): explicitly allow web_fetch in plan mode with ask_user by
@Adib234 in [#24456](https://github.com/google-gemini/gemini-cli/pull/24456)
- fix(core): refactor linux sandbox to fix ARG_MAX crashes by @ehedlund in
[#24286](https://github.com/google-gemini/gemini-cli/pull/24286)
- feat(config): add experimental.adk.agentSessionNoninteractiveEnabled setting
by @adamfweidman in
[#24439](https://github.com/google-gemini/gemini-cli/pull/24439)
- Changelog for v0.36.0-preview.8 by @gemini-cli-robot in
[#24453](https://github.com/google-gemini/gemini-cli/pull/24453)
- feat(cli): change default loadingPhrases to 'off' to hide tips by @keithguerin
in [#24342](https://github.com/google-gemini/gemini-cli/pull/24342)
- fix(cli): ensure agent stops when all declinable tools are cancelled by
@NTaylorMullen in
[#24479](https://github.com/google-gemini/gemini-cli/pull/24479)
- fix(core): enhance sandbox usability and fix build error by @galz10 in
[#24460](https://github.com/google-gemini/gemini-cli/pull/24460)
- Terminal Serializer Optimization by @jacob314 in
[#24485](https://github.com/google-gemini/gemini-cli/pull/24485)
- Auto configure memory. by @jacob314 in
[#24474](https://github.com/google-gemini/gemini-cli/pull/24474)
- Unused error variables in catch block are not allowed by @alisa-alisa in
[#24487](https://github.com/google-gemini/gemini-cli/pull/24487)
- feat(core): add background memory service for skill extraction by @SandyTao520
in [#24274](https://github.com/google-gemini/gemini-cli/pull/24274)
- feat: implement high-signal PR regression check for evaluations by
@alisa-alisa in
[#23937](https://github.com/google-gemini/gemini-cli/pull/23937)
- Fix shell output display by @jacob314 in
[#24490](https://github.com/google-gemini/gemini-cli/pull/24490)
- fix(ui): resolve unwanted vertical spacing around various tool output
treatments by @jwhelangoog in
[#24449](https://github.com/google-gemini/gemini-cli/pull/24449)
- revert(cli): bring back input box and footer visibility in copy mode by
@sehoon38 in [#24504](https://github.com/google-gemini/gemini-cli/pull/24504)
- fix(cli): prevent crash in AnsiOutputText when handling non-array data by
@sehoon38 in [#24498](https://github.com/google-gemini/gemini-cli/pull/24498)
- feat(cli): support default values for environment variables by @ruomengz in
[#24469](https://github.com/google-gemini/gemini-cli/pull/24469)
- Implement background process monitoring and inspection tools by @cocosheng-g
in [#23799](https://github.com/google-gemini/gemini-cli/pull/23799)
- docs(browser-agent): update stale browser agent documentation by @gsquared94
in [#24463](https://github.com/google-gemini/gemini-cli/pull/24463)
- fix: enable browser_agent in integration tests and add localhost fixture tests
by @gsquared94 in
[#24523](https://github.com/google-gemini/gemini-cli/pull/24523)
- fix(browser): handle computer-use model detection for analyze_screenshot by
@gsquared94 in
[#24440](https://github.com/google-gemini/gemini-cli/pull/24440)
- docs(core): add subagent tool isolation draft doc by @akh64bit in
[#23275](https://github.com/google-gemini/gemini-cli/pull/23275)
- fix(patch): cherry-pick 64c928f to release/v0.37.0-preview.0-pr-23257 to patch
version v0.37.0-preview.0 and create version 0.37.0-preview.1 by
@gemini-cli-robot in
[#24561](https://github.com/google-gemini/gemini-cli/pull/24561)
- fix(patch): cherry-pick cb7f7d6 to release/v0.37.0-preview.1-pr-24342 to patch
version v0.37.0-preview.1 and create version 0.37.0-preview.2 by
@gemini-cli-robot in
[#24842](https://github.com/google-gemini/gemini-cli/pull/24842)
[#24502](https://github.com/google-gemini/gemini-cli/pull/24502)
- feat(core): Land ContextCompressionService by @joshualitt in
[#24483](https://github.com/google-gemini/gemini-cli/pull/24483)
- feat(core): scope subagent workspace directories via AsyncLocalStorage by
@SandyTao520 in
[#24445](https://github.com/google-gemini/gemini-cli/pull/24445)
- Update ink version to 6.6.7 by @jacob314 in
[#24514](https://github.com/google-gemini/gemini-cli/pull/24514)
- fix(acp): handle all InvalidStreamError types gracefully in prompt by @sripasg
in [#24540](https://github.com/google-gemini/gemini-cli/pull/24540)
- Fix crash when vim editor is not found in PATH on Windows by
@Nagajyothi-tammisetti in
[#22423](https://github.com/google-gemini/gemini-cli/pull/22423)
- fix(core): move project memory dir under tmp directory by @SandyTao520 in
[#24542](https://github.com/google-gemini/gemini-cli/pull/24542)
- Enable 'Other' option for yesno question type by @ruomengz in
[#24545](https://github.com/google-gemini/gemini-cli/pull/24545)
- fix(cli): clear stale retry/loading state after cancellation (#21096) by
@Aaxhirrr in [#21960](https://github.com/google-gemini/gemini-cli/pull/21960)
- Changelog for v0.37.0-preview.0 by @gemini-cli-robot in
[#24464](https://github.com/google-gemini/gemini-cli/pull/24464)
- feat(core): implement context-aware persistent policy approvals by @jerop in
[#23257](https://github.com/google-gemini/gemini-cli/pull/23257)
- docs: move agent disabling instructions and update remote agent status by
@jackwotherspoon in
[#24559](https://github.com/google-gemini/gemini-cli/pull/24559)
- feat(cli): migrate nonInteractiveCli to LegacyAgentSession by @adamfweidman in
[#22987](https://github.com/google-gemini/gemini-cli/pull/22987)
- fix(core): unsafe type assertions in Core File System #19712 by
@aniketsaurav18 in
[#19739](https://github.com/google-gemini/gemini-cli/pull/19739)
- fix(ui): hide model quota in /stats and refactor quota display by @danzaharia1
in [#24206](https://github.com/google-gemini/gemini-cli/pull/24206)
- Changelog for v0.36.0 by @gemini-cli-robot in
[#24558](https://github.com/google-gemini/gemini-cli/pull/24558)
- Changelog for v0.37.0-preview.1 by @gemini-cli-robot in
[#24568](https://github.com/google-gemini/gemini-cli/pull/24568)
- docs: add missing .md extensions to internal doc links by @ishaan-arora-1 in
[#24145](https://github.com/google-gemini/gemini-cli/pull/24145)
- fix(ui): fixed table styling by @devr0306 in
[#24565](https://github.com/google-gemini/gemini-cli/pull/24565)
- fix(core): pass includeDirectories to sandbox configuration by @galz10 in
[#24573](https://github.com/google-gemini/gemini-cli/pull/24573)
- feat(ui): enable "TerminalBuffer" mode to solve flicker by @jacob314 in
[#24512](https://github.com/google-gemini/gemini-cli/pull/24512)
- docs: clarify release coordination by @scidomino in
[#24575](https://github.com/google-gemini/gemini-cli/pull/24575)
- fix(core): remove broken PowerShell translation and fix native \_\_write in
Windows sandbox by @scidomino in
[#24571](https://github.com/google-gemini/gemini-cli/pull/24571)
- Add instructions for how to start react in prod and force react to prod mode
by @jacob314 in
[#24590](https://github.com/google-gemini/gemini-cli/pull/24590)
- feat(cli): minimalist sandbox status labels by @galz10 in
[#24582](https://github.com/google-gemini/gemini-cli/pull/24582)
- Feat/browser agent metrics by @kunal-10-cloud in
[#24210](https://github.com/google-gemini/gemini-cli/pull/24210)
- test: fix Windows CI execution and resolve exposed platform failures by
@ehedlund in [#24476](https://github.com/google-gemini/gemini-cli/pull/24476)
- feat(core,cli): prioritize summary for topics (#24608) by @Abhijit-2592 in
[#24609](https://github.com/google-gemini/gemini-cli/pull/24609)
- show color by @jacob314 in
[#24613](https://github.com/google-gemini/gemini-cli/pull/24613)
- feat(cli): enable compact tool output by default (#24509) by @jwhelangoog in
[#24510](https://github.com/google-gemini/gemini-cli/pull/24510)
- fix(core): inject skill system instructions into subagent prompts if activated
by @abhipatel12 in
[#24620](https://github.com/google-gemini/gemini-cli/pull/24620)
- fix(core): improve windows sandbox reliability and fix integration tests by
@ehedlund in [#24480](https://github.com/google-gemini/gemini-cli/pull/24480)
- fix(core): ensure sandbox approvals are correctly persisted and matched for
proactive expansions by @galz10 in
[#24577](https://github.com/google-gemini/gemini-cli/pull/24577)
- feat(cli) Scrollbar for input prompt by @jacob314 in
[#21992](https://github.com/google-gemini/gemini-cli/pull/21992)
- Do not run pr-eval workflow when no steering changes detected by @alisa-alisa
in [#24621](https://github.com/google-gemini/gemini-cli/pull/24621)
- Fix restoration of topic headers. by @gundermanc in
[#24650](https://github.com/google-gemini/gemini-cli/pull/24650)
- feat(core): discourage update topic tool for simple tasks by @Samee24 in
[#24640](https://github.com/google-gemini/gemini-cli/pull/24640)
- fix(core): ensure global temp directory is always in sandbox allowed paths by
@galz10 in [#24638](https://github.com/google-gemini/gemini-cli/pull/24638)
- fix(core): detect uninitialized lines by @jacob314 in
[#24646](https://github.com/google-gemini/gemini-cli/pull/24646)
- docs: update sandboxing documentation and toolSandboxing settings by @galz10
in [#24655](https://github.com/google-gemini/gemini-cli/pull/24655)
- feat(cli): enhance tool confirmation UI and selection layout by @galz10 in
[#24376](https://github.com/google-gemini/gemini-cli/pull/24376)
- feat(acp): add support for `/about` command by @sripasg in
[#24649](https://github.com/google-gemini/gemini-cli/pull/24649)
- feat(cli): add role specific metrics to /stats by @cynthialong0-0 in
[#24659](https://github.com/google-gemini/gemini-cli/pull/24659)
- split context by @jacob314 in
[#24623](https://github.com/google-gemini/gemini-cli/pull/24623)
- fix(cli): remove -S from shebang to fix Windows and BSD execution by
@scidomino in [#24756](https://github.com/google-gemini/gemini-cli/pull/24756)
- Fix issue where topic headers can be posted back to back by @gundermanc in
[#24759](https://github.com/google-gemini/gemini-cli/pull/24759)
- fix(core): handle partial llm_request in BeforeModel hook override by
@krishdef7 in [#22326](https://github.com/google-gemini/gemini-cli/pull/22326)
- fix(ui): improve narration suppression and reduce flicker by @gundermanc in
[#24635](https://github.com/google-gemini/gemini-cli/pull/24635)
- fix(ui): fixed auth race condition causing logo to flicker by @devr0306 in
[#24652](https://github.com/google-gemini/gemini-cli/pull/24652)
- fix(browser): remove premature browser cleanup after subagent invocation by
@gsquared94 in
[#24753](https://github.com/google-gemini/gemini-cli/pull/24753)
- Revert "feat(core,cli): prioritize summary for topics (#24608)" by
@Abhijit-2592 in
[#24777](https://github.com/google-gemini/gemini-cli/pull/24777)
- relax tool sandboxing overrides for plan mode to match defaults. by
@DavidAPierce in
[#24762](https://github.com/google-gemini/gemini-cli/pull/24762)
- fix(cli): respect global environment variable allowlist by @scidomino in
[#24767](https://github.com/google-gemini/gemini-cli/pull/24767)
- fix(cli): ensure skills list outputs to stdout in non-interactive environments
by @spencer426 in
[#24566](https://github.com/google-gemini/gemini-cli/pull/24566)
- Add an eval for and fix unsafe cloning behavior. by @gundermanc in
[#24457](https://github.com/google-gemini/gemini-cli/pull/24457)
- fix(policy): allow complete_task in plan mode by @abhipatel12 in
[#24771](https://github.com/google-gemini/gemini-cli/pull/24771)
- feat(telemetry): add browser agent clearcut metrics by @gsquared94 in
[#24688](https://github.com/google-gemini/gemini-cli/pull/24688)
- feat(cli): support selective topic expansion and click-to-expand by
@Abhijit-2592 in
[#24793](https://github.com/google-gemini/gemini-cli/pull/24793)
- temporarily disable sandbox integration test on windows by @ehedlund in
[#24786](https://github.com/google-gemini/gemini-cli/pull/24786)
- Remove flakey test by @scidomino in
[#24837](https://github.com/google-gemini/gemini-cli/pull/24837)
- Alisa/approve button by @alisa-alisa in
[#24645](https://github.com/google-gemini/gemini-cli/pull/24645)
- feat(hooks): display hook system messages in UI by @mbleigh in
[#24616](https://github.com/google-gemini/gemini-cli/pull/24616)
- fix(core): propagate BeforeModel hook model override end-to-end by @krishdef7
in [#24784](https://github.com/google-gemini/gemini-cli/pull/24784)
- chore: fix formatting for behavioral eval skill reference file by @abhipatel12
in [#24846](https://github.com/google-gemini/gemini-cli/pull/24846)
- fix: use directory junctions on Windows for skill linking by @enjoykumawat in
[#24823](https://github.com/google-gemini/gemini-cli/pull/24823)
- fix(cli): prevent multiple banner increments on remount by @sehoon38 in
[#24843](https://github.com/google-gemini/gemini-cli/pull/24843)
- feat(acp): add /help command by @sripasg in
[#24839](https://github.com/google-gemini/gemini-cli/pull/24839)
- fix(core): remove tmux alternate buffer warning by @jackwotherspoon in
[#24852](https://github.com/google-gemini/gemini-cli/pull/24852)
- Improve sandbox error matching and caching by @DavidAPierce in
[#24550](https://github.com/google-gemini/gemini-cli/pull/24550)
- feat(core): add agent protocol UI types and experimental flag by @mbleigh in
[#24275](https://github.com/google-gemini/gemini-cli/pull/24275)
- feat(core): use experiment flags for default fetch timeouts by @yunaseoul in
[#24261](https://github.com/google-gemini/gemini-cli/pull/24261)
- Revert "fix(ui): improve narration suppression and reduce flicker (#2… by
@gundermanc in
[#24857](https://github.com/google-gemini/gemini-cli/pull/24857)
- refactor(cli): remove duplication in interactive shell awaiting input hint by
@JayadityaGit in
[#24801](https://github.com/google-gemini/gemini-cli/pull/24801)
- refactor(core): make LegacyAgentSession dependencies optional by @mbleigh in
[#24287](https://github.com/google-gemini/gemini-cli/pull/24287)
- Changelog for v0.37.0-preview.2 by @gemini-cli-robot in
[#24848](https://github.com/google-gemini/gemini-cli/pull/24848)
- fix(cli): always show shell command description or actual command by @jacob314
in [#24774](https://github.com/google-gemini/gemini-cli/pull/24774)
- Added flag for ept size and increased default size by @devr0306 in
[#24859](https://github.com/google-gemini/gemini-cli/pull/24859)
- fix(core): dispose Scheduler to prevent McpProgress listener leak by
@Anjaligarhwal in
[#24870](https://github.com/google-gemini/gemini-cli/pull/24870)
- fix(cli): switch default back to terminalBuffer=false and fix regressions
introduced for that mode by @jacob314 in
[#24873](https://github.com/google-gemini/gemini-cli/pull/24873)
- feat(cli): switch to ctrl+g from ctrl-x by @jacob314 in
[#24861](https://github.com/google-gemini/gemini-cli/pull/24861)
- fix: isolate concurrent browser agent instances by @gsquared94 in
[#24794](https://github.com/google-gemini/gemini-cli/pull/24794)
- docs: update MCP server OAuth redirect port documentation by @adamfweidman in
[#24844](https://github.com/google-gemini/gemini-cli/pull/24844)
**Full Changelog**:
https://github.com/google-gemini/gemini-cli/compare/v0.36.0...v0.37.2
https://github.com/google-gemini/gemini-cli/compare/v0.37.2...v0.38.0
docs/changelogs/preview.md
+236 -247
View File
@@ -1,6 +1,6 @@
# Preview release: v0.38.0-preview.0
# Preview release: v0.39.0-preview.0
Released: April 08, 2026
Released: April 14, 2026
Our preview release includes the latest, new, and experimental features. This
release may not be as stable as our [latest weekly release](latest.md).
@@ -13,256 +13,245 @@ npm install -g @google/gemini-cli@preview
## Highlights
- **Context Management:** Introduced a Context Compression Service to optimize
context window usage and landed a background memory service for skill
extraction.
- **Enhanced Security:** Implemented context-aware persistent policy approvals
for smarter tool permissions and enabled `web_fetch` in plan mode with user
confirmation.
- **Workflow Monitoring:** Added background process monitoring and inspection
tools for better visibility into long-running tasks.
- **UI/UX Refinements:** Enhanced the tool confirmation UI, selection layout,
and added support for selective topic expansion and click-to-expand.
- **Core Stability:** Improved sandbox reliability on Linux and Windows,
resolved shebang compatibility issues, and fixed various crashes in the CLI
and core services.
- **Refactored Subagents and Unified Tooling:** Consolidate subagent tools into
a single `invoke_subagent` tool, removed legacy wrapping tools, and improved
turn limits for codebase investigator.
- **Advanced Memory and Skill Management:** Introduced `/memory` inbox for
reviewing extracted skills and added skill patching support, enhancing agent
learning and persistence.
- **Expanded Test and Evaluation Infrastructure:** Added memory and CPU
performance integration test harnesses and generalized evaluation
infrastructure for better suite organization.
- **Sandbox and Security Hardening:** Centralized sandbox paths for Linux and
macOS, enforced read-only security for async git worktree resolution, and
optimized Windows sandbox initialization.
- **Enhanced CLI UX and UI Stability:** Improved scroll momentum, added a
`debugRainbow` setting, and resolved various memory leaks and PTY exhaustion
issues for a smoother terminal experience.
## What's Changed
- fix(cli): refresh slash command list after /skills reload by @NTaylorMullen in
[#24454](https://github.com/google-gemini/gemini-cli/pull/24454)
- Update README.md for links. by @g-samroberts in
[#22759](https://github.com/google-gemini/gemini-cli/pull/22759)
- fix(core): ensure complete_task tool calls are recorded in chat history by
@abhipatel12 in
[#24437](https://github.com/google-gemini/gemini-cli/pull/24437)
- feat(policy): explicitly allow web_fetch in plan mode with ask_user by
@Adib234 in [#24456](https://github.com/google-gemini/gemini-cli/pull/24456)
- fix(core): refactor linux sandbox to fix ARG_MAX crashes by @ehedlund in
[#24286](https://github.com/google-gemini/gemini-cli/pull/24286)
- feat(config): add experimental.adk.agentSessionNoninteractiveEnabled setting
by @adamfweidman in
[#24439](https://github.com/google-gemini/gemini-cli/pull/24439)
- Changelog for v0.36.0-preview.8 by @gemini-cli-robot in
[#24453](https://github.com/google-gemini/gemini-cli/pull/24453)
- feat(cli): change default loadingPhrases to 'off' to hide tips by @keithguerin
in [#24342](https://github.com/google-gemini/gemini-cli/pull/24342)
- fix(cli): ensure agent stops when all declinable tools are cancelled by
@NTaylorMullen in
[#24479](https://github.com/google-gemini/gemini-cli/pull/24479)
- fix(core): enhance sandbox usability and fix build error by @galz10 in
[#24460](https://github.com/google-gemini/gemini-cli/pull/24460)
- Terminal Serializer Optimization by @jacob314 in
[#24485](https://github.com/google-gemini/gemini-cli/pull/24485)
- Auto configure memory. by @jacob314 in
[#24474](https://github.com/google-gemini/gemini-cli/pull/24474)
- Unused error variables in catch block are not allowed by @alisa-alisa in
[#24487](https://github.com/google-gemini/gemini-cli/pull/24487)
- feat(core): add background memory service for skill extraction by @SandyTao520
in [#24274](https://github.com/google-gemini/gemini-cli/pull/24274)
- feat: implement high-signal PR regression check for evaluations by
@alisa-alisa in
[#23937](https://github.com/google-gemini/gemini-cli/pull/23937)
- Fix shell output display by @jacob314 in
[#24490](https://github.com/google-gemini/gemini-cli/pull/24490)
- fix(ui): resolve unwanted vertical spacing around various tool output
treatments by @jwhelangoog in
[#24449](https://github.com/google-gemini/gemini-cli/pull/24449)
- revert(cli): bring back input box and footer visibility in copy mode by
@sehoon38 in [#24504](https://github.com/google-gemini/gemini-cli/pull/24504)
- fix(cli): prevent crash in AnsiOutputText when handling non-array data by
@sehoon38 in [#24498](https://github.com/google-gemini/gemini-cli/pull/24498)
- feat(cli): support default values for environment variables by @ruomengz in
[#24469](https://github.com/google-gemini/gemini-cli/pull/24469)
- Implement background process monitoring and inspection tools by @cocosheng-g
in [#23799](https://github.com/google-gemini/gemini-cli/pull/23799)
- docs(browser-agent): update stale browser agent documentation by @gsquared94
in [#24463](https://github.com/google-gemini/gemini-cli/pull/24463)
- fix: enable browser_agent in integration tests and add localhost fixture tests
by @gsquared94 in
[#24523](https://github.com/google-gemini/gemini-cli/pull/24523)
- fix(browser): handle computer-use model detection for analyze_screenshot by
@gsquared94 in
[#24502](https://github.com/google-gemini/gemini-cli/pull/24502)
- feat(core): Land ContextCompressionService by @joshualitt in
[#24483](https://github.com/google-gemini/gemini-cli/pull/24483)
- feat(core): scope subagent workspace directories via AsyncLocalStorage by
- refactor(plan): simplify policy priorities and consolidate read-only rules by
@ruomengz in [#24849](https://github.com/google-gemini/gemini-cli/pull/24849)
- feat(test-utils): add memory usage integration test harness by @sripasg in
[#24876](https://github.com/google-gemini/gemini-cli/pull/24876)
- feat(memory): add /memory inbox command for reviewing extracted skills by
@SandyTao520 in
[#24445](https://github.com/google-gemini/gemini-cli/pull/24445)
- Update ink version to 6.6.7 by @jacob314 in
[#24514](https://github.com/google-gemini/gemini-cli/pull/24514)
- fix(acp): handle all InvalidStreamError types gracefully in prompt by @sripasg
in [#24540](https://github.com/google-gemini/gemini-cli/pull/24540)
- Fix crash when vim editor is not found in PATH on Windows by
@Nagajyothi-tammisetti in
[#22423](https://github.com/google-gemini/gemini-cli/pull/22423)
- fix(core): move project memory dir under tmp directory by @SandyTao520 in
[#24542](https://github.com/google-gemini/gemini-cli/pull/24542)
- Enable 'Other' option for yesno question type by @ruomengz in
[#24545](https://github.com/google-gemini/gemini-cli/pull/24545)
- fix(cli): clear stale retry/loading state after cancellation (#21096) by
@Aaxhirrr in [#21960](https://github.com/google-gemini/gemini-cli/pull/21960)
- Changelog for v0.37.0-preview.0 by @gemini-cli-robot in
[#24464](https://github.com/google-gemini/gemini-cli/pull/24464)
- feat(core): implement context-aware persistent policy approvals by @jerop in
[#23257](https://github.com/google-gemini/gemini-cli/pull/23257)
- docs: move agent disabling instructions and update remote agent status by
@jackwotherspoon in
[#24559](https://github.com/google-gemini/gemini-cli/pull/24559)
- feat(cli): migrate nonInteractiveCli to LegacyAgentSession by @adamfweidman in
[#22987](https://github.com/google-gemini/gemini-cli/pull/22987)
- fix(core): unsafe type assertions in Core File System #19712 by
@aniketsaurav18 in
[#19739](https://github.com/google-gemini/gemini-cli/pull/19739)
- fix(ui): hide model quota in /stats and refactor quota display by @danzaharia1
in [#24206](https://github.com/google-gemini/gemini-cli/pull/24206)
- Changelog for v0.36.0 by @gemini-cli-robot in
[#24558](https://github.com/google-gemini/gemini-cli/pull/24558)
- Changelog for v0.37.0-preview.1 by @gemini-cli-robot in
[#24568](https://github.com/google-gemini/gemini-cli/pull/24568)
- docs: add missing .md extensions to internal doc links by @ishaan-arora-1 in
[#24145](https://github.com/google-gemini/gemini-cli/pull/24145)
- fix(ui): fixed table styling by @devr0306 in
[#24565](https://github.com/google-gemini/gemini-cli/pull/24565)
- fix(core): pass includeDirectories to sandbox configuration by @galz10 in
[#24573](https://github.com/google-gemini/gemini-cli/pull/24573)
- feat(ui): enable "TerminalBuffer" mode to solve flicker by @jacob314 in
[#24512](https://github.com/google-gemini/gemini-cli/pull/24512)
- docs: clarify release coordination by @scidomino in
[#24575](https://github.com/google-gemini/gemini-cli/pull/24575)
- fix(core): remove broken PowerShell translation and fix native \_\_write in
Windows sandbox by @scidomino in
[#24571](https://github.com/google-gemini/gemini-cli/pull/24571)
- Add instructions for how to start react in prod and force react to prod mode
by @jacob314 in
[#24590](https://github.com/google-gemini/gemini-cli/pull/24590)
- feat(cli): minimalist sandbox status labels by @galz10 in
[#24582](https://github.com/google-gemini/gemini-cli/pull/24582)
- Feat/browser agent metrics by @kunal-10-cloud in
[#24210](https://github.com/google-gemini/gemini-cli/pull/24210)
- test: fix Windows CI execution and resolve exposed platform failures by
@ehedlund in [#24476](https://github.com/google-gemini/gemini-cli/pull/24476)
- feat(core,cli): prioritize summary for topics (#24608) by @Abhijit-2592 in
[#24609](https://github.com/google-gemini/gemini-cli/pull/24609)
- show color by @jacob314 in
[#24613](https://github.com/google-gemini/gemini-cli/pull/24613)
- feat(cli): enable compact tool output by default (#24509) by @jwhelangoog in
[#24510](https://github.com/google-gemini/gemini-cli/pull/24510)
- fix(core): inject skill system instructions into subagent prompts if activated
by @abhipatel12 in
[#24620](https://github.com/google-gemini/gemini-cli/pull/24620)
- fix(core): improve windows sandbox reliability and fix integration tests by
@ehedlund in [#24480](https://github.com/google-gemini/gemini-cli/pull/24480)
- fix(core): ensure sandbox approvals are correctly persisted and matched for
proactive expansions by @galz10 in
[#24577](https://github.com/google-gemini/gemini-cli/pull/24577)
- feat(cli) Scrollbar for input prompt by @jacob314 in
[#21992](https://github.com/google-gemini/gemini-cli/pull/21992)
- Do not run pr-eval workflow when no steering changes detected by @alisa-alisa
in [#24621](https://github.com/google-gemini/gemini-cli/pull/24621)
- Fix restoration of topic headers. by @gundermanc in
[#24650](https://github.com/google-gemini/gemini-cli/pull/24650)
- feat(core): discourage update topic tool for simple tasks by @Samee24 in
[#24640](https://github.com/google-gemini/gemini-cli/pull/24640)
- fix(core): ensure global temp directory is always in sandbox allowed paths by
@galz10 in [#24638](https://github.com/google-gemini/gemini-cli/pull/24638)
- fix(core): detect uninitialized lines by @jacob314 in
[#24646](https://github.com/google-gemini/gemini-cli/pull/24646)
- docs: update sandboxing documentation and toolSandboxing settings by @galz10
in [#24655](https://github.com/google-gemini/gemini-cli/pull/24655)
- feat(cli): enhance tool confirmation UI and selection layout by @galz10 in
[#24376](https://github.com/google-gemini/gemini-cli/pull/24376)
- feat(acp): add support for `/about` command by @sripasg in
[#24649](https://github.com/google-gemini/gemini-cli/pull/24649)
- feat(cli): add role specific metrics to /stats by @cynthialong0-0 in
[#24659](https://github.com/google-gemini/gemini-cli/pull/24659)
- split context by @jacob314 in
[#24623](https://github.com/google-gemini/gemini-cli/pull/24623)
- fix(cli): remove -S from shebang to fix Windows and BSD execution by
@scidomino in [#24756](https://github.com/google-gemini/gemini-cli/pull/24756)
- Fix issue where topic headers can be posted back to back by @gundermanc in
[#24759](https://github.com/google-gemini/gemini-cli/pull/24759)
- fix(core): handle partial llm_request in BeforeModel hook override by
@krishdef7 in [#22326](https://github.com/google-gemini/gemini-cli/pull/22326)
- fix(ui): improve narration suppression and reduce flicker by @gundermanc in
[#24635](https://github.com/google-gemini/gemini-cli/pull/24635)
- fix(ui): fixed auth race condition causing logo to flicker by @devr0306 in
[#24652](https://github.com/google-gemini/gemini-cli/pull/24652)
- fix(browser): remove premature browser cleanup after subagent invocation by
@gsquared94 in
[#24753](https://github.com/google-gemini/gemini-cli/pull/24753)
- Revert "feat(core,cli): prioritize summary for topics (#24608)" by
@Abhijit-2592 in
[#24777](https://github.com/google-gemini/gemini-cli/pull/24777)
- relax tool sandboxing overrides for plan mode to match defaults. by
@DavidAPierce in
[#24762](https://github.com/google-gemini/gemini-cli/pull/24762)
- fix(cli): respect global environment variable allowlist by @scidomino in
[#24767](https://github.com/google-gemini/gemini-cli/pull/24767)
- fix(cli): ensure skills list outputs to stdout in non-interactive environments
[#24544](https://github.com/google-gemini/gemini-cli/pull/24544)
- chore(release): bump version to 0.39.0-nightly.20260408.e77b22e63 by
@gemini-cli-robot in
[#24939](https://github.com/google-gemini/gemini-cli/pull/24939)
- fix(core): ensure robust sandbox cleanup in all process execution paths by
@ehedlund in [#24763](https://github.com/google-gemini/gemini-cli/pull/24763)
- chore: update ink version to 6.6.8 by @jacob314 in
[#24934](https://github.com/google-gemini/gemini-cli/pull/24934)
- Changelog for v0.38.0-preview.0 by @gemini-cli-robot in
[#24938](https://github.com/google-gemini/gemini-cli/pull/24938)
- chore: ignore conductor directory by @JayadityaGit in
[#22128](https://github.com/google-gemini/gemini-cli/pull/22128)
- Changelog for v0.37.0 by @gemini-cli-robot in
[#24940](https://github.com/google-gemini/gemini-cli/pull/24940)
- feat(plan): require user confirmation for activate_skill in Plan Mode by
@ruomengz in [#24946](https://github.com/google-gemini/gemini-cli/pull/24946)
- feat(test-utils): add CPU performance integration test harness by @sripasg in
[#24951](https://github.com/google-gemini/gemini-cli/pull/24951)
- fix(cli-ui): enable Ctrl+Backspace for word deletion in Windows Terminal by
@dogukanozen in
[#21447](https://github.com/google-gemini/gemini-cli/pull/21447)
- test(sdk): add unit tests for GeminiCliSession by @AdamyaSingh7 in
[#21897](https://github.com/google-gemini/gemini-cli/pull/21897)
- fix(core): resolve windows symlink bypass and stabilize sandbox integration
tests by @ehedlund in
[#24834](https://github.com/google-gemini/gemini-cli/pull/24834)
- fix(cli): restore file path display in edit and write tool confirmations by
@jwhelangoog in
[#24974](https://github.com/google-gemini/gemini-cli/pull/24974)
- feat(core): refine shell tool description display logic by @jwhelangoog in
[#24903](https://github.com/google-gemini/gemini-cli/pull/24903)
- fix(core): dynamic session ID injection to resolve resume bugs by @scidomino
in [#24972](https://github.com/google-gemini/gemini-cli/pull/24972)
- Update ink version to 6.6.9 by @jacob314 in
[#24980](https://github.com/google-gemini/gemini-cli/pull/24980)
- Generalize evals infra to support more types of evals, organization and
queuing of named suites by @gundermanc in
[#24941](https://github.com/google-gemini/gemini-cli/pull/24941)
- fix(cli): optimize startup with lightweight parent process by @sehoon38 in
[#24667](https://github.com/google-gemini/gemini-cli/pull/24667)
- refactor(sandbox): use centralized sandbox paths in macOS Seatbelt
implementation by @ehedlund in
[#24984](https://github.com/google-gemini/gemini-cli/pull/24984)
- feat(cli): refine tool output formatting for compact mode by @jwhelangoog in
[#24677](https://github.com/google-gemini/gemini-cli/pull/24677)
- fix(sdk): skip broken sendStream tests to unblock nightly by @SandyTao520 in
[#25000](https://github.com/google-gemini/gemini-cli/pull/25000)
- refactor(core): use centralized path resolution for Linux sandbox by @ehedlund
in [#24985](https://github.com/google-gemini/gemini-cli/pull/24985)
- Support ctrl+shift+g by @jacob314 in
[#25035](https://github.com/google-gemini/gemini-cli/pull/25035)
- feat(core): refactor subagent tool to unified invoke_subagent tool by
@abhipatel12 in
[#24489](https://github.com/google-gemini/gemini-cli/pull/24489)
- fix(core): add explicit git identity env vars to prevent sandbox checkpointing
error by @mrpmohiburrahman in
[#19775](https://github.com/google-gemini/gemini-cli/pull/19775)
- fix: respect hideContextPercentage when FooterConfigDialog is closed without
changes by @chernistry in
[#24773](https://github.com/google-gemini/gemini-cli/pull/24773)
- fix(cli): suppress unhandled AbortError logs during request cancellation by
@euxaristia in
[#22621](https://github.com/google-gemini/gemini-cli/pull/22621)
- Automated documentation audit by @g-samroberts in
[#24567](https://github.com/google-gemini/gemini-cli/pull/24567)
- feat(cli): implement useAgentStream hook by @mbleigh in
[#24292](https://github.com/google-gemini/gemini-cli/pull/24292)
- refactor(plan) Clean default plan toml by @ruomengz in
[#25037](https://github.com/google-gemini/gemini-cli/pull/25037)
- refactor(core): remove legacy subagent wrapping tools by @abhipatel12 in
[#25053](https://github.com/google-gemini/gemini-cli/pull/25053)
- fix(core): honor retryDelay in RetryInfo for 503 errors by @yunaseoul in
[#25057](https://github.com/google-gemini/gemini-cli/pull/25057)
- fix(core): remediate subagent memory leaks using AbortSignal in MessageBus by
@abhipatel12 in
[#25048](https://github.com/google-gemini/gemini-cli/pull/25048)
- feat(cli): wire up useAgentStream in AppContainer by @mbleigh in
[#24297](https://github.com/google-gemini/gemini-cli/pull/24297)
- feat(core): migrate chat recording to JSONL streaming by @spencer426 in
[#23749](https://github.com/google-gemini/gemini-cli/pull/23749)
- fix(core): clear 5-minute timeouts in oauth flow to prevent memory leaks by
@spencer426 in
[#24968](https://github.com/google-gemini/gemini-cli/pull/24968)
- fix(sandbox): centralize async git worktree resolution and enforce read-only
security by @ehedlund in
[#25040](https://github.com/google-gemini/gemini-cli/pull/25040)
- feat(test): add high-volume shell test and refine perf harness by @sripasg in
[#24983](https://github.com/google-gemini/gemini-cli/pull/24983)
- fix(core): silently handle EPERM when listing dir structure by @scidomino in
[#25066](https://github.com/google-gemini/gemini-cli/pull/25066)
- Changelog for v0.37.1 by @gemini-cli-robot in
[#25055](https://github.com/google-gemini/gemini-cli/pull/25055)
- fix: decode Uint8Array and multi-byte UTF-8 in API error messages by
@kimjune01 in [#23341](https://github.com/google-gemini/gemini-cli/pull/23341)
- Automated documentation audit results by @g-samroberts in
[#22755](https://github.com/google-gemini/gemini-cli/pull/22755)
- debugging(ui): add optional debugRainbow setting by @jacob314 in
[#25088](https://github.com/google-gemini/gemini-cli/pull/25088)
- fix: resolve lifecycle memory leaks by cleaning up listeners and root closures
by @spencer426 in
[#24566](https://github.com/google-gemini/gemini-cli/pull/24566)
- Add an eval for and fix unsafe cloning behavior. by @gundermanc in
[#24457](https://github.com/google-gemini/gemini-cli/pull/24457)
- fix(policy): allow complete_task in plan mode by @abhipatel12 in
[#24771](https://github.com/google-gemini/gemini-cli/pull/24771)
- feat(telemetry): add browser agent clearcut metrics by @gsquared94 in
[#24688](https://github.com/google-gemini/gemini-cli/pull/24688)
- feat(cli): support selective topic expansion and click-to-expand by
@Abhijit-2592 in
[#24793](https://github.com/google-gemini/gemini-cli/pull/24793)
- temporarily disable sandbox integration test on windows by @ehedlund in
[#24786](https://github.com/google-gemini/gemini-cli/pull/24786)
- Remove flakey test by @scidomino in
[#24837](https://github.com/google-gemini/gemini-cli/pull/24837)
- Alisa/approve button by @alisa-alisa in
[#24645](https://github.com/google-gemini/gemini-cli/pull/24645)
- feat(hooks): display hook system messages in UI by @mbleigh in
[#24616](https://github.com/google-gemini/gemini-cli/pull/24616)
- fix(core): propagate BeforeModel hook model override end-to-end by @krishdef7
in [#24784](https://github.com/google-gemini/gemini-cli/pull/24784)
- chore: fix formatting for behavioral eval skill reference file by @abhipatel12
in [#24846](https://github.com/google-gemini/gemini-cli/pull/24846)
- fix: use directory junctions on Windows for skill linking by @enjoykumawat in
[#24823](https://github.com/google-gemini/gemini-cli/pull/24823)
- fix(cli): prevent multiple banner increments on remount by @sehoon38 in
[#24843](https://github.com/google-gemini/gemini-cli/pull/24843)
- feat(acp): add /help command by @sripasg in
[#24839](https://github.com/google-gemini/gemini-cli/pull/24839)
- fix(core): remove tmux alternate buffer warning by @jackwotherspoon in
[#24852](https://github.com/google-gemini/gemini-cli/pull/24852)
- Improve sandbox error matching and caching by @DavidAPierce in
[#24550](https://github.com/google-gemini/gemini-cli/pull/24550)
- feat(core): add agent protocol UI types and experimental flag by @mbleigh in
[#24275](https://github.com/google-gemini/gemini-cli/pull/24275)
- feat(core): use experiment flags for default fetch timeouts by @yunaseoul in
[#24261](https://github.com/google-gemini/gemini-cli/pull/24261)
- Revert "fix(ui): improve narration suppression and reduce flicker (#2… by
[#25049](https://github.com/google-gemini/gemini-cli/pull/25049)
- docs(cli): updates f12 description to be more precise by @JayadityaGit in
[#15816](https://github.com/google-gemini/gemini-cli/pull/15816)
- fix(cli): mark /settings as unsafe to run concurrently by @jacob314 in
[#25061](https://github.com/google-gemini/gemini-cli/pull/25061)
- fix(core): remove buffer slice to prevent OOM on large output streams by
@spencer426 in
[#25094](https://github.com/google-gemini/gemini-cli/pull/25094)
- feat(core): persist subagent agentId in tool call records by @abhipatel12 in
[#25092](https://github.com/google-gemini/gemini-cli/pull/25092)
- chore(core): increase codebase investigator turn limits to 50 by @abhipatel12
in [#25125](https://github.com/google-gemini/gemini-cli/pull/25125)
- refactor(core): consolidate execute() arguments into ExecuteOptions by
@mbleigh in [#25101](https://github.com/google-gemini/gemini-cli/pull/25101)
- feat(core): add Strategic Re-evaluation guidance to system prompt by
@aishaneeshah in
[#25062](https://github.com/google-gemini/gemini-cli/pull/25062)
- fix(core): preserve shell execution config fields on update by
@jasonmatthewsuhari in
[#25113](https://github.com/google-gemini/gemini-cli/pull/25113)
- docs: add vi shortcuts and clarify MCP sandbox setup by @chrisjcthomas in
[#21679](https://github.com/google-gemini/gemini-cli/pull/21679)
- fix(cli): pass session id to interactive shell executions by
@jasonmatthewsuhari in
[#25114](https://github.com/google-gemini/gemini-cli/pull/25114)
- fix(cli): resolve text sanitization data loss due to C1 control characters by
@euxaristia in
[#22624](https://github.com/google-gemini/gemini-cli/pull/22624)
- feat(core): add large memory regression test by @cynthialong0-0 in
[#25059](https://github.com/google-gemini/gemini-cli/pull/25059)
- fix(core): resolve PTY exhaustion and orphan MCP subprocess leaks by
@spencer426 in
[#25079](https://github.com/google-gemini/gemini-cli/pull/25079)
- chore(deps): update vulnerable dependencies via npm audit fix by @scidomino in
[#25140](https://github.com/google-gemini/gemini-cli/pull/25140)
- perf(sandbox): optimize Windows sandbox initialization via native ACL
application by @ehedlund in
[#25077](https://github.com/google-gemini/gemini-cli/pull/25077)
- chore: switch from keytar to @github/keytar by @cocosheng-g in
[#25143](https://github.com/google-gemini/gemini-cli/pull/25143)
- fix: improve audio MIME normalization and validation in file reads by
@junaiddshaukat in
[#21636](https://github.com/google-gemini/gemini-cli/pull/21636)
- docs: Update docs-audit to include changes in PR body by @g-samroberts in
[#25153](https://github.com/google-gemini/gemini-cli/pull/25153)
- docs: correct documentation for enforced authentication type by @cocosheng-g
in [#25142](https://github.com/google-gemini/gemini-cli/pull/25142)
- fix(cli): exclude update_topic from confirmation queue count by @Abhijit-2592
in [#24945](https://github.com/google-gemini/gemini-cli/pull/24945)
- Memory fix for trace's streamWrapper. by @anthraxmilkshake in
[#25089](https://github.com/google-gemini/gemini-cli/pull/25089)
- fix(core): fix quota footer for non-auto models and improve display by
@jackwotherspoon in
[#25121](https://github.com/google-gemini/gemini-cli/pull/25121)
- docs(contributing): clarify self-assignment policy for issues by @jmr in
[#23087](https://github.com/google-gemini/gemini-cli/pull/23087)
- feat(core): add skill patching support with /memory inbox integration by
@SandyTao520 in
[#25148](https://github.com/google-gemini/gemini-cli/pull/25148)
- Stop suppressing thoughts and text in model response by @gundermanc in
[#25073](https://github.com/google-gemini/gemini-cli/pull/25073)
- fix(release): prefix git hash in nightly versions to prevent semver
normalization by @SandyTao520 in
[#25304](https://github.com/google-gemini/gemini-cli/pull/25304)
- feat(cli): extract QuotaContext and resolve infinite render loop by @Adib234
in [#24959](https://github.com/google-gemini/gemini-cli/pull/24959)
- refactor(core): extract and centralize sandbox path utilities by @ehedlund in
[#25305](https://github.com/google-gemini/gemini-cli/pull/25305)
- feat(ui): added enhancements to scroll momentum by @devr0306 in
[#24447](https://github.com/google-gemini/gemini-cli/pull/24447)
- fix(core): replace custom binary detection with isbinaryfile to correctly
handle UTF-8 (U+FFFD) by @Anjaligarhwal in
[#25297](https://github.com/google-gemini/gemini-cli/pull/25297)
- feat(agent): implement tool-controlled display protocol (Steps 2-3) by
@mbleigh in [#25134](https://github.com/google-gemini/gemini-cli/pull/25134)
- Stop showing scrollbar unless we are in terminalBuffer mode by @jacob314 in
[#25320](https://github.com/google-gemini/gemini-cli/pull/25320)
- feat: support auth block in MCP servers config in agents by @TanmayVartak in
[#24770](https://github.com/google-gemini/gemini-cli/pull/24770)
- fix(core): expose GEMINI_PLANS_DIR to hook environment by @Adib234 in
[#25296](https://github.com/google-gemini/gemini-cli/pull/25296)
- feat(core): implement silent fallback for Plan Mode model routing by @jerop in
[#25317](https://github.com/google-gemini/gemini-cli/pull/25317)
- fix: correct redirect count increment in fetchJson by @KevinZhao in
[#24896](https://github.com/google-gemini/gemini-cli/pull/24896)
- fix(core): prevent secondary crash in ModelRouterService finally block by
@gundermanc in
[#24857](https://github.com/google-gemini/gemini-cli/pull/24857)
- refactor(cli): remove duplication in interactive shell awaiting input hint by
@JayadityaGit in
[#24801](https://github.com/google-gemini/gemini-cli/pull/24801)
- refactor(core): make LegacyAgentSession dependencies optional by @mbleigh in
[#24287](https://github.com/google-gemini/gemini-cli/pull/24287)
- Changelog for v0.37.0-preview.2 by @gemini-cli-robot in
[#24848](https://github.com/google-gemini/gemini-cli/pull/24848)
- fix(cli): always show shell command description or actual command by @jacob314
in [#24774](https://github.com/google-gemini/gemini-cli/pull/24774)
- Added flag for ept size and increased default size by @devr0306 in
[#24859](https://github.com/google-gemini/gemini-cli/pull/24859)
- fix(core): dispose Scheduler to prevent McpProgress listener leak by
@Anjaligarhwal in
[#24870](https://github.com/google-gemini/gemini-cli/pull/24870)
- fix(cli): switch default back to terminalBuffer=false and fix regressions
introduced for that mode by @jacob314 in
[#24873](https://github.com/google-gemini/gemini-cli/pull/24873)
- feat(cli): switch to ctrl+g from ctrl-x by @jacob314 in
[#24861](https://github.com/google-gemini/gemini-cli/pull/24861)
- fix: isolate concurrent browser agent instances by @gsquared94 in
[#24794](https://github.com/google-gemini/gemini-cli/pull/24794)
- docs: update MCP server OAuth redirect port documentation by @adamfweidman in
[#24844](https://github.com/google-gemini/gemini-cli/pull/24844)
[#25333](https://github.com/google-gemini/gemini-cli/pull/25333)
- feat(core): introduce decoupled ContextManager and Sidecar architecture by
@joshualitt in
[#24752](https://github.com/google-gemini/gemini-cli/pull/24752)
- docs(core): update generalist agent documentation by @abhipatel12 in
[#25325](https://github.com/google-gemini/gemini-cli/pull/25325)
- chore(mcp): check MCP error code over brittle string match by @jackwotherspoon
in [#25381](https://github.com/google-gemini/gemini-cli/pull/25381)
- feat(plan): update plan mode prompt to allow showing plan content by @ruomengz
in [#25058](https://github.com/google-gemini/gemini-cli/pull/25058)
- test(core): improve sandbox integration test coverage and fix OS-specific
failures by @ehedlund in
[#25307](https://github.com/google-gemini/gemini-cli/pull/25307)
- fix(core): use debug level for keychain fallback logging by @ehedlund in
[#25398](https://github.com/google-gemini/gemini-cli/pull/25398)
- feat(test): add a performance test in asian language by @cynthialong0-0 in
[#25392](https://github.com/google-gemini/gemini-cli/pull/25392)
- feat(cli): enable mouse clicking for cursor positioning in AskUser multi-line
answers by @Adib234 in
[#24630](https://github.com/google-gemini/gemini-cli/pull/24630)
- fix(core): detect kmscon terminal as supporting true color by @claygeo in
[#25282](https://github.com/google-gemini/gemini-cli/pull/25282)
- ci: add agent session drift check workflow by @adamfweidman in
[#25389](https://github.com/google-gemini/gemini-cli/pull/25389)
- use macos-latest-large runner where applicable. by @scidomino in
[#25413](https://github.com/google-gemini/gemini-cli/pull/25413)
- Changelog for v0.37.2 by @gemini-cli-robot in
[#25336](https://github.com/google-gemini/gemini-cli/pull/25336)
**Full Changelog**:
https://github.com/google-gemini/gemini-cli/compare/v0.37.0-preview.2...v0.38.0-preview.0
https://github.com/google-gemini/gemini-cli/compare/v0.38.0-preview.0...v0.39.0-preview.0
docs/reference/configuration.md
+15
View File
@@ -2148,6 +2148,21 @@ the `advanced.excludedEnvVars` setting in your `settings.json` file.
- When set, overrides the default API version used by the SDK.
- Example: `export GOOGLE_GENAI_API_VERSION="v1"` (Windows PowerShell:
`$env:GOOGLE_GENAI_API_VERSION="v1"`)
- **`GOOGLE_GEMINI_BASE_URL`**:
- Overrides the default base URL for Gemini API requests (when using
`gemini-api-key` authentication).
- Must be a valid URL. For security, it must use HTTPS unless pointing to
`localhost` (or `127.0.0.1` / `[::1]`).
- Example: `export GOOGLE_GEMINI_BASE_URL="https://my-proxy.com"` (Windows
PowerShell: `$env:GOOGLE_GEMINI_BASE_URL="https://my-proxy.com"`)
- **`GOOGLE_VERTEX_BASE_URL`**:
- Overrides the default base URL for Vertex AI API requests (when using
`vertex-ai` authentication).
- Must be a valid URL. For security, it must use HTTPS unless pointing to
`localhost` (or `127.0.0.1` / `[::1]`).
- Example: `export GOOGLE_VERTEX_BASE_URL="https://my-vertex-proxy.com"`
(Windows PowerShell:
`$env:GOOGLE_VERTEX_BASE_URL="https://my-vertex-proxy.com"`)
- **`OTLP_GOOGLE_CLOUD_PROJECT`**:
- Your Google Cloud Project ID for Telemetry in Google Cloud
- Example: `export OTLP_GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"` (Windows
evals/component-test-helper.ts
+17 -1
View File
@@ -16,6 +16,7 @@ import fs from 'node:fs';
import path from 'node:path';
import os from 'node:os';
import { randomUUID } from 'node:crypto';
import { vi } from 'vitest';
import {
Config,
type ConfigParameters,
@@ -52,6 +53,7 @@ export interface ComponentEvalCase extends BaseEvalCase {
export class ComponentRig {
public config: Config | undefined;
public testDir: string;
public homeDir: string;
public sessionId: string;
constructor(
@@ -61,6 +63,9 @@ export class ComponentRig {
this.testDir = fs.mkdtempSync(
path.join(os.tmpdir(), `gemini-component-rig-${uniqueId.slice(0, 8)}-`),
);
this.homeDir = fs.mkdtempSync(
path.join(os.tmpdir(), `gemini-component-home-${uniqueId.slice(0, 8)}-`),
);
this.sessionId = `test-session-${uniqueId}`;
}
@@ -89,12 +94,23 @@ export class ComponentRig {
this.config = makeFakeConfig(configParams);
await this.config.initialize();
// Refresh auth using USE_GEMINI to initialize the real BaseLlmClient
// Refresh auth using USE_GEMINI to initialize the real BaseLlmClient.
// This must happen BEFORE stubbing GEMINI_CLI_HOME because OAuth credential
// lookup resolves through homedir() → GEMINI_CLI_HOME.
await this.config.refreshAuth(AuthType.USE_GEMINI);
// Isolate storage paths (session files, skills, extraction state) by
// pointing GEMINI_CLI_HOME at a per-test temp directory. Storage resolves
// global paths through `homedir()` which reads this env var. This is set
// after auth so credential lookup uses the real home directory.
vi.stubEnv('GEMINI_CLI_HOME', this.homeDir);
}
async cleanup() {
await this.config?.dispose();
vi.unstubAllEnvs();
fs.rmSync(this.testDir, { recursive: true, force: true });
fs.rmSync(this.homeDir, { recursive: true, force: true });
}
}
evals/skill_extraction.eval.ts
+341
View File
@@ -0,0 +1,341 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
import fsp from 'node:fs/promises';
import path from 'node:path';
import { describe, expect } from 'vitest';
import {
type Config,
ApprovalMode,
SESSION_FILE_PREFIX,
getProjectHash,
startMemoryService,
} from '@google/gemini-cli-core';
import { componentEvalTest } from './component-test-helper.js';
interface SeedSession {
sessionId: string;
summary: string;
userTurns: string[];
timestampOffsetMinutes: number;
}
interface MessageRecord {
id: string;
timestamp: string;
type: string;
content: Array<{ text: string }>;
}
const WORKSPACE_FILES = {
'package.json': JSON.stringify(
{
name: 'skill-extraction-eval',
private: true,
scripts: {
build: 'echo build',
lint: 'echo lint',
test: 'echo test',
},
},
null,
2,
),
'README.md': `# Skill Extraction Eval
This workspace exists to exercise background skill extraction from prior chats.
`,
};
function buildMessages(userTurns: string[]): MessageRecord[] {
const baseTime = new Date(Date.now() - 6 * 60 * 60 * 1000).toISOString();
return userTurns.flatMap((text, index) => [
{
id: `u${index + 1}`,
timestamp: baseTime,
type: 'user',
content: [{ text }],
},
{
id: `a${index + 1}`,
timestamp: baseTime,
type: 'gemini',
content: [{ text: `Acknowledged: ${index + 1}` }],
},
]);
}
async function seedSessions(
config: Config,
sessions: SeedSession[],
): Promise<void> {
const chatsDir = path.join(config.storage.getProjectTempDir(), 'chats');
await fsp.mkdir(chatsDir, { recursive: true });
const projectRoot = config.storage.getProjectRoot();
for (const session of sessions) {
const timestamp = new Date(
Date.now() - session.timestampOffsetMinutes * 60 * 1000,
)
.toISOString()
.slice(0, 16)
.replace(/:/g, '-');
const filename = `${SESSION_FILE_PREFIX}${timestamp}-${session.sessionId.slice(0, 8)}.json`;
const conversation = {
sessionId: session.sessionId,
projectHash: getProjectHash(projectRoot),
summary: session.summary,
startTime: new Date(Date.now() - 7 * 60 * 60 * 1000).toISOString(),
lastUpdated: new Date(Date.now() - 4 * 60 * 60 * 1000).toISOString(),
messages: buildMessages(session.userTurns),
};
await fsp.writeFile(
path.join(chatsDir, filename),
JSON.stringify(conversation, null, 2),
);
}
}
async function runExtractionAndReadState(config: Config): Promise<{
state: { runs: Array<{ sessionIds: string[]; skillsCreated: string[] }> };
skillsDir: string;
}> {
await startMemoryService(config);
const memoryDir = config.storage.getProjectMemoryTempDir();
const skillsDir = config.storage.getProjectSkillsMemoryDir();
const statePath = path.join(memoryDir, '.extraction-state.json');
const raw = await fsp.readFile(statePath, 'utf-8');
const state = JSON.parse(raw) as {
runs?: Array<{ sessionIds?: string[]; skillsCreated?: string[] }>;
};
if (!Array.isArray(state.runs) || state.runs.length === 0) {
throw new Error('Skill extraction finished without writing any run state');
}
return {
state: {
runs: state.runs.map((run) => ({
sessionIds: Array.isArray(run.sessionIds) ? run.sessionIds : [],
skillsCreated: Array.isArray(run.skillsCreated)
? run.skillsCreated
: [],
})),
},
skillsDir,
};
}
async function readSkillBodies(skillsDir: string): Promise<string[]> {
try {
const entries = await fsp.readdir(skillsDir, { withFileTypes: true });
const skillDirs = entries.filter((entry) => entry.isDirectory());
const bodies = await Promise.all(
skillDirs.map((entry) =>
fsp.readFile(path.join(skillsDir, entry.name, 'SKILL.md'), 'utf-8'),
),
);
return bodies;
} catch {
return [];
}
}
/**
* Shared configOverrides for all skill extraction component evals.
* - experimentalMemoryManager: enables the memory extraction pipeline.
* - approvalMode: YOLO auto-approves tool calls (write_file, read_file) so the
* background agent can execute without interactive confirmation.
*/
const EXTRACTION_CONFIG_OVERRIDES = {
experimentalMemoryManager: true,
approvalMode: ApprovalMode.YOLO,
};
describe('Skill Extraction', () => {
componentEvalTest('USUALLY_PASSES', {
suiteName: 'skill-extraction',
suiteType: 'component-level',
name: 'ignores one-off incidents even when session summaries look similar',
files: WORKSPACE_FILES,
timeout: 180000,
configOverrides: EXTRACTION_CONFIG_OVERRIDES,
setup: async (config) => {
await seedSessions(config, [
{
sessionId: 'incident-login-redirect',
summary: 'Debug login redirect loop in staging',
timestampOffsetMinutes: 420,
userTurns: [
'We only need a one-off fix for incident INC-4412 on branch hotfix/login-loop.',
'The exact failing string is ERR_REDIRECT_4412 and this workaround is incident-specific.',
'Patch packages/auth/src/redirect.ts just for this branch and do not generalize it.',
'The thing that worked was deleting the stale staging cookie before retrying.',
'This is not a normal workflow and should not become a reusable instruction.',
'It only reproduced against the 2026-04-08 staging rollout.',
'After the cookie clear, the branch-specific redirect logic passed.',
'Do not turn this incident writeup into a standing process.',
'Yes, the hotfix worked for this exact redirect-loop incident.',
'Close out INC-4412 once the staging login succeeds again.',
],
},
{
sessionId: 'incident-login-timeout',
summary: 'Debug login callback timeout in staging',
timestampOffsetMinutes: 360,
userTurns: [
'This is another one-off staging incident, this time TICKET-991 for callback timeout.',
'The exact failing string is ERR_CALLBACK_TIMEOUT_991 and it is unrelated to the redirect loop.',
'The temporary fix was rotating the staging secret and deleting a bad feature-flag row.',
'Do not write a generic login-debugging playbook from this.',
'This only applied to the callback timeout during the April rollout.',
'The successful fix was specific to the stale secret in staging.',
'It does not define a durable repo workflow for future tasks.',
'After rotating the secret, the callback timeout stopped reproducing.',
'Treat this as incident response only, not a reusable skill.',
'Once staging passed again, we closed TICKET-991.',
],
},
]);
},
assert: async (config) => {
const { state, skillsDir } = await runExtractionAndReadState(config);
const skillBodies = await readSkillBodies(skillsDir);
expect(state.runs).toHaveLength(1);
expect(state.runs[0].sessionIds).toHaveLength(2);
expect(state.runs[0].skillsCreated).toEqual([]);
expect(skillBodies).toEqual([]);
},
});
componentEvalTest('USUALLY_PASSES', {
suiteName: 'skill-extraction',
suiteType: 'component-level',
name: 'extracts a repeated project-specific workflow into a skill',
files: WORKSPACE_FILES,
timeout: 180000,
configOverrides: EXTRACTION_CONFIG_OVERRIDES,
setup: async (config) => {
await seedSessions(config, [
{
sessionId: 'settings-docs-regen-1',
summary: 'Update settings docs after adding a config option',
timestampOffsetMinutes: 420,
userTurns: [
'When we add a new config option, we have to regenerate the settings docs in a specific order.',
'The sequence that worked was npm run predocs:settings, npm run schema:settings, then npm run docs:settings.',
'Do not hand-edit generated settings docs.',
'If predocs is skipped, the generated schema docs miss the new defaults.',
'Update the source first, then run that generation sequence.',
'After regenerating, verify the schema output and docs changed together.',
'We used this same sequence the last time we touched settings docs.',
'That ordered workflow passed and produced the expected generated files.',
'Please keep the exact command order because reversing it breaks the output.',
'Yes, the generated settings docs were correct after those three commands.',
],
},
{
sessionId: 'settings-docs-regen-2',
summary: 'Regenerate settings schema docs for another new setting',
timestampOffsetMinutes: 360,
userTurns: [
'We are touching another setting, so follow the same settings-doc regeneration workflow again.',
'Run npm run predocs:settings before npm run schema:settings and npm run docs:settings.',
'The project keeps generated settings docs in sync through those commands, not manual edits.',
'Skipping predocs caused stale defaults in the generated output before.',
'Change the source, then execute the same three commands in order.',
'Verify both the schema artifact and docs update together after regeneration.',
'This is the recurring workflow we use whenever a setting changes.',
'The exact order worked again on this second settings update.',
'Please preserve that ordering constraint for future settings changes.',
'Confirmed: the settings docs regenerated correctly with the same command sequence.',
],
},
]);
},
assert: async (config) => {
const { state, skillsDir } = await runExtractionAndReadState(config);
const skillBodies = await readSkillBodies(skillsDir);
const combinedSkills = skillBodies.join('\n\n');
expect(state.runs).toHaveLength(1);
expect(state.runs[0].sessionIds).toHaveLength(2);
expect(state.runs[0].skillsCreated.length).toBeGreaterThanOrEqual(1);
expect(skillBodies.length).toBeGreaterThanOrEqual(1);
expect(combinedSkills).toContain('npm run predocs:settings');
expect(combinedSkills).toContain('npm run schema:settings');
expect(combinedSkills).toContain('npm run docs:settings');
expect(combinedSkills).toMatch(/When to Use/i);
expect(combinedSkills).toMatch(/Verification/i);
},
});
componentEvalTest('USUALLY_PASSES', {
suiteName: 'skill-extraction',
suiteType: 'component-level',
name: 'extracts a repeated multi-step migration workflow with ordering constraints',
files: WORKSPACE_FILES,
timeout: 180000,
configOverrides: EXTRACTION_CONFIG_OVERRIDES,
setup: async (config) => {
await seedSessions(config, [
{
sessionId: 'db-migration-v12',
summary: 'Run database migration for v12 schema update',
timestampOffsetMinutes: 420,
userTurns: [
'Every time we change the database schema we follow a specific migration workflow.',
'First run npm run db:check to verify no pending migrations conflict.',
'Then run npm run db:migrate to apply the new migration files.',
'After migration, always run npm run db:validate to confirm schema integrity.',
'If db:validate fails, immediately run npm run db:rollback before anything else.',
'Never skip db:check — last time we did, two migrations collided and corrupted the index.',
'The ordering is critical: check, migrate, validate. Reversing migrate and validate caused silent data loss before.',
'This v12 migration passed after following that exact sequence.',
'We use this same three-step workflow every time the schema changes.',
'Confirmed: db:check, db:migrate, db:validate completed successfully for v12.',
],
},
{
sessionId: 'db-migration-v13',
summary: 'Run database migration for v13 schema update',
timestampOffsetMinutes: 360,
userTurns: [
'New schema change for v13, following the same database migration workflow as before.',
'Start with npm run db:check to ensure no conflicting pending migrations.',
'Then npm run db:migrate to apply the v13 migration files.',
'Then npm run db:validate to confirm the schema is consistent.',
'If validation fails, run npm run db:rollback immediately — do not attempt manual fixes.',
'We learned the hard way that skipping db:check causes index corruption.',
'The check-migrate-validate order is mandatory for every schema change.',
'This is the same recurring workflow we used for v12 and earlier migrations.',
'The v13 migration passed with the same three-step sequence.',
'Confirmed: the standard db migration workflow succeeded again for v13.',
],
},
]);
},
assert: async (config) => {
const { state, skillsDir } = await runExtractionAndReadState(config);
const skillBodies = await readSkillBodies(skillsDir);
const combinedSkills = skillBodies.join('\n\n');
expect(state.runs).toHaveLength(1);
expect(state.runs[0].sessionIds).toHaveLength(2);
expect(state.runs[0].skillsCreated.length).toBeGreaterThanOrEqual(1);
expect(skillBodies.length).toBeGreaterThanOrEqual(1);
expect(combinedSkills).toContain('npm run db:check');
expect(combinedSkills).toContain('npm run db:migrate');
expect(combinedSkills).toContain('npm run db:validate');
expect(combinedSkills).toMatch(/rollback/i);
expect(combinedSkills).toMatch(/When to Use/i);
},
});
});
evals/subtask_delegation.eval.ts
+130
View File
@@ -0,0 +1,130 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
import { describe, expect } from 'vitest';
import {
TRACKER_CREATE_TASK_TOOL_NAME,
TRACKER_UPDATE_TASK_TOOL_NAME,
} from '@google/gemini-cli-core';
import { evalTest, TEST_AGENTS } from './test-helper.js';
describe('subtask delegation eval test cases', () => {
/**
* Checks that the main agent can correctly decompose a complex, sequential
* task into subtasks using the task tracker and delegate each to the appropriate expert subagent.
*
* The task requires:
* 1. Reading requirements (researcher)
* 2. Implementing logic (developer)
* 3. Documenting (doc expert)
*/
evalTest('USUALLY_PASSES', {
name: 'should delegate sequential subtasks to relevant experts using the task tracker',
params: {
settings: {
experimental: {
enableAgents: true,
taskTracker: true,
},
},
},
prompt:
'Please read the requirements in requirements.txt using a researcher, then implement the requested logic in src/logic.ts using a developer, and finally document the implementation in docs/logic.md using a documentation expert.',
files: {
'.gemini/agents/researcher.md': `---
name: researcher
description: Expert in reading files and extracting requirements.
tools:
- read_file
---
You are the researcher. Read the provided file and extract requirements.`,
'.gemini/agents/developer.md': `---
name: developer
description: Expert in implementing logic in TypeScript.
tools:
- write_file
---
You are the developer. Implement the requested logic in the specified file.`,
'.gemini/agents/doc-expert.md': `---
name: doc-expert
description: Expert in writing technical documentation.
tools:
- write_file
---
You are the doc expert. Document the provided implementation clearly.`,
'requirements.txt':
'Implement a function named "calculateSum" that adds two numbers.',
},
assert: async (rig, _result) => {
// Verify tracker tasks were created
const wasCreateCalled = await rig.waitForToolCall(
TRACKER_CREATE_TASK_TOOL_NAME,
);
expect(wasCreateCalled).toBe(true);
const toolLogs = rig.readToolLogs();
const createCalls = toolLogs.filter(
(l) => l.toolRequest.name === TRACKER_CREATE_TASK_TOOL_NAME,
);
expect(createCalls.length).toBeGreaterThanOrEqual(3);
await rig.expectToolCallSuccess([
'researcher',
'developer',
'doc-expert',
]);
const logicFile = rig.readFile('src/logic.ts');
const docFile = rig.readFile('docs/logic.md');
expect(logicFile).toContain('calculateSum');
expect(docFile).toBeTruthy();
},
});
/**
* Checks that the main agent can delegate a batch of independent subtasks
* to multiple subagents in parallel using the task tracker to manage state.
*/
evalTest('USUALLY_PASSES', {
name: 'should delegate independent subtasks to specialists using the task tracker',
params: {
settings: {
experimental: {
enableAgents: true,
taskTracker: true,
},
},
},
prompt:
'Please update the project for internationalization (i18n), audit the security of the current code, and update the CSS to use a blue theme. Use specialized experts for each task.',
files: {
...TEST_AGENTS.I18N_AGENT.asFile(),
...TEST_AGENTS.SECURITY_AGENT.asFile(),
...TEST_AGENTS.CSS_AGENT.asFile(),
'index.ts': 'console.log("Hello World");',
},
assert: async (rig, _result) => {
// Verify tracker tasks were created
const wasCreateCalled = await rig.waitForToolCall(
TRACKER_CREATE_TASK_TOOL_NAME,
);
expect(wasCreateCalled).toBe(true);
const toolLogs = rig.readToolLogs();
const createCalls = toolLogs.filter(
(l) => l.toolRequest.name === TRACKER_CREATE_TASK_TOOL_NAME,
);
expect(createCalls.length).toBeGreaterThanOrEqual(3);
await rig.expectToolCallSuccess([
TEST_AGENTS.I18N_AGENT.name,
TEST_AGENTS.SECURITY_AGENT.name,
TEST_AGENTS.CSS_AGENT.name,
]);
},
});
});
packages/cli/src/ui/components/__snapshots__/ThemeDialog.test.tsx.snap
+32 -32
View File
@@ -11,12 +11,12 @@ exports[`Initial Theme Selection > should default to a dark theme when terminal
│ ● 4. Default Dark (Matches terminal) │ 3 a, b = 0, 1 │ │
│ 5. Dracula Dark │ 4 for _ in range(n): │ │
│ 6. GitHub Dark │ 5 a, b = b, a + b │ │
│ 7. Holiday Dark │ 6 return a │ │
│ 8. Shades Of Purple Dark │ │ │
│ 9. Solarized Dark │ 1 - print("Hello, " + name) │ │
│ 10. Tokyo Night Dark │ 1 + print(f"Hello, {name}!") │ │
│ 11. ANSI Light │ │ │
│ 12. Ayu Light └─────────────────────────────────────────────────┘ │
│ 7. GitHub Dark Colorblind Dark │ 6 return a │ │
│ 8. Holiday Dark │ │ │
│ 9. Shades Of Purple Dark │ 1 - print("Hello, " + name) │ │
│ 10. Solarized Dark │ 1 + print(f"Hello, {name}!") │ │
│ 11. Tokyo Night Dark │ │ │
│ 12. ANSI Light └─────────────────────────────────────────────────┘ │
│ ▼ │
│ │
│ (Use Enter to select, Tab to configure scope, Esc to close) │
@@ -34,14 +34,14 @@ exports[`Initial Theme Selection > should default to a light theme when terminal
│ 2. Ayu Light │ 1 # function │ │
│ ● 3. Default Light │ 2 def fibonacci(n): │ │
│ 4. GitHub Light │ 3 a, b = 0, 1 │ │
│ 5. Google Code Light │ 4 for _ in range(n): │ │
│ 6. Solarized Light │ 5 a, b = b, a + b │ │
│ 7. Xcode Light │ 6 return a │ │
│ 8. ANSI Dark (Incompatible) │ │ │
│ 9. Atom One Dark (Incompatible) │ 1 - print("Hello, " + name) │ │
│ 10. Ayu Dark (Incompatible) │ 1 + print(f"Hello, {name}!") │ │
│ 11. Default Dark (Incompatible) │ │ │
│ 12. Dracula Dark (Incompatible) └─────────────────────────────────────────────────┘ │
│ 5. GitHub Light Colorblind Light (Mat… │ 4 for _ in range(n): │ │
│ 6. Google Code Light │ 5 a, b = b, a + b │ │
│ 7. Solarized Light │ 6 return a │ │
│ 8. Xcode Light │ │ │
│ 9. ANSI Dark (Incompatible) │ 1 - print("Hello, " + name) │ │
│ 10. Atom One Dark (Incompatible) │ 1 + print(f"Hello, {name}!") │ │
│ 11. Ayu Dark (Incompatible) │ │ │
│ 12. Default Dark (Incompatible) └─────────────────────────────────────────────────┘ │
│ ▼ │
│ │
│ (Use Enter to select, Tab to configure scope, Esc to close) │
@@ -61,12 +61,12 @@ exports[`Initial Theme Selection > should use the theme from settings even if te
│ 4. Default Dark (Matches terminal) │ 3 a, b = 0, 1 │ │
│ 5. Dracula Dark │ 4 for _ in range(n): │ │
│ 6. GitHub Dark │ 5 a, b = b, a + b │ │
│ 7. Holiday Dark │ 6 return a │ │
│ 8. Shades Of Purple Dark │ │ │
│ 9. Solarized Dark │ 1 - print("Hello, " + name) │ │
│ 10. Tokyo Night Dark │ 1 + print(f"Hello, {name}!") │ │
│ 11. ANSI Light │ │ │
│ 12. Ayu Light └─────────────────────────────────────────────────┘ │
│ 7. GitHub Dark Colorblind Dark │ 6 return a │ │
│ 8. Holiday Dark │ │ │
│ 9. Shades Of Purple Dark │ 1 - print("Hello, " + name) │ │
│ 10. Solarized Dark │ 1 + print(f"Hello, {name}!") │ │
│ 11. Tokyo Night Dark │ │ │
│ 12. ANSI Light └─────────────────────────────────────────────────┘ │
│ ▼ │
│ │
│ (Use Enter to select, Tab to configure scope, Esc to close) │
@@ -100,12 +100,12 @@ exports[`ThemeDialog Snapshots > should render correctly in theme selection mode
│ 4. Default Dark │ 3 a, b = 0, 1 │ │
│ 5. Dracula Dark │ 4 for _ in range(n): │ │
│ 6. GitHub Dark │ 5 a, b = b, a + b │ │
│ 7. Holiday Dark │ 6 return a │ │
│ 8. Shades Of Purple Dark │ │ │
│ 9. Solarized Dark │ 1 - print("Hello, " + name) │ │
│ 10. Tokyo Night Dark │ 1 + print(f"Hello, {name}!") │ │
│ 11. ANSI Light │ │ │
│ 12. Ayu Light └─────────────────────────────────────────────────┘ │
│ 7. GitHub Dark Colorblind Dark │ 6 return a │ │
│ 8. Holiday Dark │ │ │
│ 9. Shades Of Purple Dark │ 1 - print("Hello, " + name) │ │
│ 10. Solarized Dark │ 1 + print(f"Hello, {name}!") │ │
│ 11. Tokyo Night Dark │ │ │
│ 12. ANSI Light └─────────────────────────────────────────────────┘ │
│ ▼ │
│ │
│ (Use Enter to select, Tab to configure scope, Esc to close) │
@@ -125,12 +125,12 @@ exports[`ThemeDialog Snapshots > should render correctly in theme selection mode
│ 4. Default Dark │ 3 a, b = 0, 1 │ │
│ 5. Dracula Dark │ 4 for _ in range(n): │ │
│ 6. GitHub Dark │ 5 a, b = b, a + b │ │
│ 7. Holiday Dark │ 6 return a │ │
│ 8. Shades Of Purple Dark │ │ │
│ 9. Solarized Dark │ 1 - print("Hello, " + name) │ │
│ 10. Tokyo Night Dark │ 1 + print(f"Hello, {name}!") │ │
│ 11. ANSI Light │ │ │
│ 12. Ayu Light └─────────────────────────────────────────────────┘ │
│ 7. GitHub Dark Colorblind Dark │ 6 return a │ │
│ 8. Holiday Dark │ │ │
│ 9. Shades Of Purple Dark │ 1 - print("Hello, " + name) │ │
│ 10. Solarized Dark │ 1 + print(f"Hello, {name}!") │ │
│ 11. Tokyo Night Dark │ │ │
│ 12. ANSI Light └─────────────────────────────────────────────────┘ │
│ ▼ │
│ ╭─────────────────────────────────────────────────╮ │
│ │ DEVELOPER TOOLS (Not visible to users) │ │
packages/cli/src/ui/hooks/slashCommandProcessor.test.tsx
+70
View File
@@ -858,11 +858,81 @@ describe('useSlashCommandProcessor', () => {
});
describe('Lifecycle', () => {
it('removes the IDE status listener on unmount after async initialization', async () => {
let resolveIdeClient:
| ((client: {
addStatusChangeListener: (listener: () => void) => void;
removeStatusChangeListener: (listener: () => void) => void;
}) => void)
| undefined;
const addStatusChangeListener = vi.fn();
const removeStatusChangeListener = vi.fn();
mockIdeClientGetInstance.mockImplementation(
() =>
new Promise((resolve) => {
resolveIdeClient = resolve;
}),
);
const result = await setupProcessorHook();
await act(async () => {
resolveIdeClient?.({
addStatusChangeListener,
removeStatusChangeListener,
});
});
result.unmount();
unmountHook = undefined;
expect(addStatusChangeListener).toHaveBeenCalledTimes(1);
expect(removeStatusChangeListener).toHaveBeenCalledTimes(1);
expect(removeStatusChangeListener).toHaveBeenCalledWith(
addStatusChangeListener.mock.calls[0]?.[0],
);
});
it('does not register an IDE status listener if unmounted before async initialization resolves', async () => {
let resolveIdeClient:
| ((client: {
addStatusChangeListener: (listener: () => void) => void;
removeStatusChangeListener: (listener: () => void) => void;
}) => void)
| undefined;
const addStatusChangeListener = vi.fn();
const removeStatusChangeListener = vi.fn();
mockIdeClientGetInstance.mockImplementation(
() =>
new Promise((resolve) => {
resolveIdeClient = resolve;
}),
);
const result = await setupProcessorHook();
result.unmount();
unmountHook = undefined;
await act(async () => {
resolveIdeClient?.({
addStatusChangeListener,
removeStatusChangeListener,
});
});
expect(addStatusChangeListener).not.toHaveBeenCalled();
expect(removeStatusChangeListener).not.toHaveBeenCalled();
});
it('should abort command loading when the hook unmounts', async () => {
const abortSpy = vi.spyOn(AbortController.prototype, 'abort');
const { unmount } = await setupProcessorHook();
unmount();
unmountHook = undefined;
expect(abortSpy).toHaveBeenCalledTimes(1);
});
packages/cli/src/ui/hooks/slashCommandProcessor.ts
+8 -5
View File
@@ -281,10 +281,16 @@ export const useSlashCommandProcessor = (
const listener = () => {
reloadCommands();
};
let isActive = true;
let activeIdeClient: IdeClient | undefined;
// eslint-disable-next-line @typescript-eslint/no-floating-promises
(async () => {
const ideClient = await IdeClient.getInstance();
if (!isActive) {
return;
}
activeIdeClient = ideClient;
ideClient.addStatusChangeListener(listener);
})();
@@ -307,11 +313,8 @@ export const useSlashCommandProcessor = (
coreEvents.on('extensionsStopping', extensionEventListener);
return () => {
// eslint-disable-next-line @typescript-eslint/no-floating-promises
(async () => {
const ideClient = await IdeClient.getInstance();
ideClient.removeStatusChangeListener(listener);
})();
isActive = false;
activeIdeClient?.removeStatusChangeListener(listener);
removeMCPStatusChangeListener(listener);
coreEvents.off('extensionsStarting', extensionEventListener);
coreEvents.off('extensionsStopping', extensionEventListener);
packages/cli/src/ui/themes/builtin/dark/github-dark-colorblind.ts
+147
View File
@@ -0,0 +1,147 @@
/**
* @license
* Copyright 2025 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
import { type ColorsTheme, Theme } from '../../theme.js';
import { interpolateColor } from '../../color-utils.js';
const githubDarkColorblindColors: ColorsTheme = {
type: 'dark',
Background: '#0d1117',
Foreground: '#e6edf3',
LightBlue: '#a5d6ff',
AccentBlue: '#79c0ff',
AccentPurple: '#d2a8ff',
AccentCyan: '#a5d6ff',
AccentGreen: '#a5d6ff',
AccentYellow: '#d29922',
AccentRed: '#f0883e',
DiffAdded: '#0d161f',
DiffRemoved: '#1d150e',
Comment: '#7d8590',
Gray: '#7d8590',
DarkGray: interpolateColor('#7d8590', '#0d1117', 0.5),
GradientColors: ['#58a6ff', '#f0883e'],
};
export const GitHubDarkColorblind: Theme = new Theme(
'GitHub Dark Colorblind',
'dark',
{
hljs: {
display: 'block',
overflowX: 'auto',
padding: '0.5em',
color: githubDarkColorblindColors.Foreground,
background: githubDarkColorblindColors.Background,
},
'hljs-comment': {
color: githubDarkColorblindColors.Comment,
fontStyle: 'italic',
},
'hljs-quote': {
color: githubDarkColorblindColors.Comment,
fontStyle: 'italic',
},
'hljs-keyword': {
color: githubDarkColorblindColors.AccentRed,
fontWeight: 'bold',
},
'hljs-selector-tag': {
color: githubDarkColorblindColors.AccentRed,
fontWeight: 'bold',
},
'hljs-subst': {
color: githubDarkColorblindColors.Foreground,
},
'hljs-number': {
color: githubDarkColorblindColors.LightBlue,
},
'hljs-literal': {
color: githubDarkColorblindColors.LightBlue,
},
'hljs-variable': {
color: githubDarkColorblindColors.Foreground,
},
'hljs-template-variable': {
color: githubDarkColorblindColors.Foreground,
},
'hljs-tag .hljs-attr': {
color: githubDarkColorblindColors.AccentYellow,
},
'hljs-string': {
color: githubDarkColorblindColors.AccentCyan,
},
'hljs-doctag': {
color: githubDarkColorblindColors.AccentCyan,
},
'hljs-title': {
color: githubDarkColorblindColors.AccentPurple,
fontWeight: 'bold',
},
'hljs-section': {
color: githubDarkColorblindColors.AccentPurple,
fontWeight: 'bold',
},
'hljs-selector-id': {
color: githubDarkColorblindColors.AccentPurple,
fontWeight: 'bold',
},
'hljs-type': {
color: githubDarkColorblindColors.AccentGreen,
fontWeight: 'bold',
},
'hljs-class .hljs-title': {
color: githubDarkColorblindColors.AccentGreen,
fontWeight: 'bold',
},
'hljs-tag': {
color: githubDarkColorblindColors.AccentGreen,
},
'hljs-name': {
color: githubDarkColorblindColors.AccentGreen,
},
'hljs-attribute': {
color: githubDarkColorblindColors.LightBlue,
},
'hljs-regexp': {
color: githubDarkColorblindColors.AccentCyan,
},
'hljs-link': {
color: githubDarkColorblindColors.AccentCyan,
},
'hljs-symbol': {
color: githubDarkColorblindColors.AccentPurple,
},
'hljs-bullet': {
color: githubDarkColorblindColors.AccentPurple,
},
'hljs-built_in': {
color: githubDarkColorblindColors.LightBlue,
},
'hljs-builtin-name': {
color: githubDarkColorblindColors.LightBlue,
},
'hljs-meta': {
color: githubDarkColorblindColors.LightBlue,
fontWeight: 'bold',
},
'hljs-deletion': {
background: '#682d0f',
color: githubDarkColorblindColors.AccentRed,
},
'hljs-addition': {
background: '#0c2d6b',
color: githubDarkColorblindColors.AccentGreen,
},
'hljs-emphasis': {
fontStyle: 'italic',
},
'hljs-strong': {
fontWeight: 'bold',
},
},
githubDarkColorblindColors,
);
packages/cli/src/ui/themes/builtin/light/github-light-colorblind.ts
+147
View File
@@ -0,0 +1,147 @@
/**
* @license
* Copyright 2025 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
import { type ColorsTheme, Theme } from '../../theme.js';
import { interpolateColor } from '../../color-utils.js';
const githubLightColorblindColors: ColorsTheme = {
type: 'light',
Background: '#ffffff',
Foreground: '#1f2328',
LightBlue: '#0a3069',
AccentBlue: '#0550ae',
AccentPurple: '#8250df',
AccentCyan: '#0a3069',
AccentGreen: '#0969da',
AccentYellow: '#9a6700',
AccentRed: '#bc4c00',
DiffAdded: '#ddf4ff',
DiffRemoved: '#fff1e5',
Comment: '#656d76',
Gray: '#656d76',
DarkGray: interpolateColor('#656d76', '#ffffff', 0.5),
GradientColors: ['#0969da', '#bc4c00'],
};
export const GitHubLightColorblind: Theme = new Theme(
'GitHub Light Colorblind',
'light',
{
hljs: {
display: 'block',
overflowX: 'auto',
padding: '0.5em',
color: githubLightColorblindColors.Foreground,
background: githubLightColorblindColors.Background,
},
'hljs-comment': {
color: githubLightColorblindColors.Comment,
fontStyle: 'italic',
},
'hljs-quote': {
color: githubLightColorblindColors.Comment,
fontStyle: 'italic',
},
'hljs-keyword': {
color: githubLightColorblindColors.AccentRed,
fontWeight: 'bold',
},
'hljs-selector-tag': {
color: githubLightColorblindColors.AccentRed,
fontWeight: 'bold',
},
'hljs-subst': {
color: githubLightColorblindColors.Foreground,
},
'hljs-number': {
color: githubLightColorblindColors.LightBlue,
},
'hljs-literal': {
color: githubLightColorblindColors.LightBlue,
},
'hljs-variable': {
color: githubLightColorblindColors.Foreground,
},
'hljs-template-variable': {
color: githubLightColorblindColors.Foreground,
},
'hljs-tag .hljs-attr': {
color: githubLightColorblindColors.AccentYellow,
},
'hljs-string': {
color: githubLightColorblindColors.AccentCyan,
},
'hljs-doctag': {
color: githubLightColorblindColors.AccentCyan,
},
'hljs-title': {
color: githubLightColorblindColors.AccentPurple,
fontWeight: 'bold',
},
'hljs-section': {
color: githubLightColorblindColors.AccentPurple,
fontWeight: 'bold',
},
'hljs-selector-id': {
color: githubLightColorblindColors.AccentPurple,
fontWeight: 'bold',
},
'hljs-type': {
color: githubLightColorblindColors.AccentGreen,
fontWeight: 'bold',
},
'hljs-class .hljs-title': {
color: githubLightColorblindColors.AccentGreen,
fontWeight: 'bold',
},
'hljs-tag': {
color: githubLightColorblindColors.AccentGreen,
},
'hljs-name': {
color: githubLightColorblindColors.AccentGreen,
},
'hljs-attribute': {
color: githubLightColorblindColors.LightBlue,
},
'hljs-regexp': {
color: githubLightColorblindColors.AccentCyan,
},
'hljs-link': {
color: githubLightColorblindColors.AccentCyan,
},
'hljs-symbol': {
color: githubLightColorblindColors.AccentPurple,
},
'hljs-bullet': {
color: githubLightColorblindColors.AccentPurple,
},
'hljs-built_in': {
color: githubLightColorblindColors.LightBlue,
},
'hljs-builtin-name': {
color: githubLightColorblindColors.LightBlue,
},
'hljs-meta': {
color: githubLightColorblindColors.LightBlue,
fontWeight: 'bold',
},
'hljs-deletion': {
background: '#fff1e5',
color: githubLightColorblindColors.AccentRed,
},
'hljs-addition': {
background: '#ddf4ff',
color: githubLightColorblindColors.AccentGreen,
},
'hljs-emphasis': {
fontStyle: 'italic',
},
'hljs-strong': {
fontWeight: 'bold',
},
},
githubLightColorblindColors,
);
packages/cli/src/ui/themes/theme-manager.ts
+4
View File
@@ -10,6 +10,8 @@ import { AtomOneDark } from './builtin/dark/atom-one-dark.js';
import { Dracula } from './builtin/dark/dracula-dark.js';
import { GitHubDark } from './builtin/dark/github-dark.js';
import { GitHubLight } from './builtin/light/github-light.js';
import { GitHubDarkColorblind } from './builtin/dark/github-dark-colorblind.js';
import { GitHubLightColorblind } from './builtin/light/github-light-colorblind.js';
import { GoogleCode } from './builtin/light/googlecode-light.js';
import { Holiday } from './builtin/dark/holiday-dark.js';
import { DefaultLight } from './builtin/light/default-light.js';
@@ -79,6 +81,8 @@ class ThemeManager {
DefaultDark,
GitHubDark,
GitHubLight,
GitHubDarkColorblind,
GitHubLightColorblind,
GoogleCode,
Holiday,
ShadesOfPurple,
packages/core/src/agents/skill-extraction-agent.test.ts
+90
View File
@@ -0,0 +1,90 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
import { describe, expect, it } from 'vitest';
import { SkillExtractionAgent } from './skill-extraction-agent.js';
import {
EDIT_TOOL_NAME,
GLOB_TOOL_NAME,
GREP_TOOL_NAME,
LS_TOOL_NAME,
READ_FILE_TOOL_NAME,
WRITE_FILE_TOOL_NAME,
} from '../tools/tool-names.js';
import { PREVIEW_GEMINI_FLASH_MODEL } from '../config/models.js';
describe('SkillExtractionAgent', () => {
const skillsDir = '/tmp/skills';
const sessionIndex =
'[NEW] Debug login flow (12 user msgs) — /tmp/chats/session-1.json';
const existingSkillsSummary =
'## Workspace Skills (.gemini/skills — do NOT duplicate)\n- **existing-skill**: Existing description';
const agent = SkillExtractionAgent(
skillsDir,
sessionIndex,
existingSkillsSummary,
);
it('should expose expected metadata, model, and tools', () => {
expect(agent.kind).toBe('local');
expect(agent.name).toBe('confucius');
expect(agent.displayName).toBe('Skill Extractor');
expect(agent.modelConfig.model).toBe(PREVIEW_GEMINI_FLASH_MODEL);
expect(agent.toolConfig?.tools).toEqual(
expect.arrayContaining([
READ_FILE_TOOL_NAME,
WRITE_FILE_TOOL_NAME,
EDIT_TOOL_NAME,
LS_TOOL_NAME,
GLOB_TOOL_NAME,
GREP_TOOL_NAME,
]),
);
});
it('should default to no skill unless recurrence and durability are proven', () => {
const prompt = agent.promptConfig.systemPrompt;
expect(prompt).toContain('Default to NO SKILL.');
expect(prompt).toContain(
'strong evidence this will recur for future agents in this repo/workflow',
);
expect(prompt).toContain('broader than a single incident');
expect(prompt).toContain('A skill MUST meet ALL of these criteria:');
expect(prompt).toContain(
'Future agents in this repo/workflow are likely to need it',
);
});
it('should explicitly reject one-off incidents and single-session preferences', () => {
const prompt = agent.promptConfig.systemPrompt;
expect(prompt).toContain('Single-session preferences');
expect(prompt).toContain('One-off incidents');
expect(prompt).toContain('Output-style preferences');
expect(prompt).toContain('cannot survive renaming the specific');
});
it('should warn that session summaries are user-intent summaries, not workflow evidence', () => {
const query = agent.promptConfig.query ?? '';
expect(query).toContain(existingSkillsSummary);
expect(query).toContain(sessionIndex);
expect(query).toContain(
'The summary is a user-intent summary, not a workflow summary.',
);
expect(query).toContain(
'The session summaries describe user intent, not workflow details.',
);
expect(query).toContain(
'Only write a skill if the evidence shows a durable, recurring workflow',
);
expect(query).toContain(
'If recurrence or future reuse is unclear, create no skill and explain why.',
);
});
});
packages/core/src/agents/skill-extraction-agent.ts
+54 -21
View File
@@ -36,7 +36,7 @@ function buildSystemPrompt(skillsDir: string): string {
'- solve similar tasks with fewer tool calls and fewer reasoning tokens',
'- reuse proven workflows and verification checklists',
'- avoid known failure modes and landmines',
'- anticipate user preferences without being reminded',
'- capture durable workflow constraints that future agents are likely to encounter again',
'',
'============================================================',
'SAFETY AND HYGIENE (STRICT)',
@@ -59,6 +59,10 @@ function buildSystemPrompt(skillsDir: string): string {
'1. "Is this something a competent agent would NOT already know?" If no, STOP.',
'2. "Does an existing skill (listed below) already cover this?" If yes, STOP.',
'3. "Can I write a concrete, step-by-step procedure?" If no, STOP.',
'4. "Is there strong evidence this will recur for future agents in this repo/workflow?" If no, STOP.',
'5. "Is this broader than a single incident (one bug, one ticket, one branch, one date, one exact error)?" If no, STOP.',
'',
'Default to NO SKILL.',
'',
'Do NOT create skills for:',
'',
@@ -67,6 +71,10 @@ function buildSystemPrompt(skillsDir: string): string {
'- **Pure Q&A**: The user asked "how does X work?" and got an answer. No procedure.',
'- **Brainstorming/design**: Discussion of how to build something, without a validated',
' implementation that produced a reusable procedure.',
'- **Single-session preferences**: User-specific style/output preferences or workflow',
' preferences mentioned only once.',
'- **One-off incidents**: Debugging or incident response tied to a single bug, ticket,',
' branch, date, or exact error string.',
'- **Anything already covered by an existing skill** (global, workspace, builtin, or',
' previously extracted). Check the "Existing Skills" section carefully.',
'',
@@ -74,31 +82,40 @@ function buildSystemPrompt(skillsDir: string): string {
'WHAT COUNTS AS A SKILL',
'============================================================',
'',
'A skill MUST meet BOTH of these criteria:',
'A skill MUST meet ALL of these criteria:',
'',
'1. **Procedural and concrete**: It can be expressed as numbered steps with specific',
' commands, paths, or code patterns. If you can only write vague guidance, it is NOT',
' a skill. "Be careful with X" is advice, not a skill.',
'',
'2. **Non-obvious and project-specific**: A competent agent would NOT already know this.',
' It encodes project-specific knowledge, non-obvious ordering constraints, or',
' hard-won failure shields that cannot be inferred from the codebase alone.',
'2. **Durable and reusable**: Future agents in this repo/workflow are likely to need it',
' again. If it only solved one incident, it is NOT a skill.',
'',
'Confidence tiers (prefer higher tiers):',
'3. **Evidence-backed and project-specific**: It encodes project-specific knowledge,',
' repeated operational constraints, or hard-won failure shields supported by session',
' evidence. Do not assume something is non-obvious just because it sounds detailed.',
'',
'**High confidence** — create the skill:',
'- The same workflow appeared in multiple sessions (cross-session repetition)',
'- A multi-step procedure was validated (tests passed, user confirmed success)',
'Confidence tiers:',
'',
'**Medium confidence** — create the skill if it is clearly project-specific:',
'- A project-specific build/test/deploy/release procedure was established',
'- A non-obvious ordering constraint or prerequisite was discovered',
'- A failure mode was hit and a concrete fix was found and verified',
'**High confidence** — create the skill only when recurrence/durability is clear:',
'- The same workflow appeared in multiple sessions (cross-session repetition), OR it is',
' a stable recurring repo workflow (for example setup/build/test/deploy/release) with a',
' clear future trigger',
'- The workflow was validated (tests passed, user confirmed success, or the same fix',
' worked repeatedly)',
'- The skill can be named without referencing a specific incident, bug, branch, or date',
'',
'**Medium confidence** — usually do NOT create the skill yet:',
'- A project-specific procedure appeared once and seems useful, but recurrence is not yet',
' clear',
'- A verified fix exists, but it is still tied to one incident',
'- A user correction changed the approach once, but durability is uncertain',
'',
'**Low confidence** — do NOT create the skill:',
'- A one-off debugging session with no reusable procedure',
'- Generic workflows any agent could figure out from the codebase',
'- A code review or investigation with no durable takeaway',
'- Output-style preferences that do not materially change procedure',
'',
'Aim for 0-2 skills per run. Quality over quantity.',
'',
@@ -117,8 +134,10 @@ function buildSystemPrompt(skillsDir: string): string {
'',
'What to look for:',
'',
'- User corrections: "No, do it this way" -> preference signal',
'- User corrections that change procedure in a durable way, especially when repeated',
' across sessions',
'- Repeated patterns across sessions: same commands, same file paths, same workflow',
'- Stable recurring repo lifecycle workflows with clear future triggers',
'- Failed attempts followed by successful ones -> failure shield',
'- Multi-step procedures that were validated (tests passed, user confirmed)',
'- User interruptions: "Stop, you need to X first" -> ordering constraint',
@@ -129,6 +148,8 @@ function buildSystemPrompt(skillsDir: string): string {
'- Tool outputs that are just data (file contents, search results)',
'- Speculative plans that were never executed',
"- Temporary context (current branch name, today's date, specific error IDs)",
'- Similar session summaries without matching workflow evidence',
'- One-off artifact names: bug IDs, branch names, timestamps, exact incident strings',
'',
'============================================================',
'SKILL FORMAT',
@@ -214,7 +235,10 @@ function buildSystemPrompt(skillsDir: string): string {
'- Keep scopes distinct. Avoid overlapping "do-everything" skills.',
'- Every skill MUST have: triggers, procedure, at least one pitfall or verification step.',
'- If you cannot write a reliable procedure (too many unknowns), do NOT create the skill.',
'- Do not create skills for generic advice that any competent agent would already know.',
'- If the candidate is tied to one incident or cannot survive renaming the specific',
' bug/ticket, do NOT create it.',
'- Do not create skills for generic advice, output-style preferences, or ephemeral',
' choices that any competent agent would already know or adapt to on the fly.',
'- Prefer fewer, higher-quality skills. 0-2 skills per run is typical. 3+ is unusual.',
'',
'============================================================',
@@ -224,17 +248,23 @@ function buildSystemPrompt(skillsDir: string): string {
`1. Use list_directory on ${skillsDir} to see existing skills.`,
'2. If skills exist, read their SKILL.md files to understand what is already captured.',
'3. Scan the session index provided in the query. Look for [NEW] sessions whose summaries',
' suggest workflows that ALSO appear in other sessions (either [NEW] or [old]).',
'4. Apply the minimum signal gate. If no repeated patterns are visible, report that and finish.',
' hint at workflows that ALSO appear in other sessions (either [NEW] or [old]) or at a',
' stable recurring repo workflow. Remember: summary similarity alone is NOT enough.',
'4. Apply the minimum signal gate. If recurrence or durability is not visible, report that',
' no skill should be created and finish.',
'5. For promising patterns, use read_file on the session file paths to inspect the full',
' conversation. Confirm the workflow was actually repeated and validated.',
'6. For each confirmed skill, verify it meets ALL criteria (repeatable, procedural, high-leverage).',
' conversation. Confirm the workflow was actually repeated and validated. Read at least',
' two sessions unless the candidate is clearly a stable recurring repo lifecycle workflow.',
'6. For each candidate, verify it meets ALL criteria. Before writing, make sure you can',
' state: future trigger, evidence sessions, recurrence signal, validation signal, and',
' why it is not generic.',
'7. Write new SKILL.md files or update existing ones in your directory using write_file.',
' For skills that live OUTSIDE your directory, write a .patch file instead (see UPDATING EXISTING SKILLS).',
'8. Write COMPLETE files — never partially update a SKILL.md.',
'',
'IMPORTANT: Do NOT read every session. Only read sessions whose summaries suggest a',
'repeated pattern worth investigating. Most runs should read 0-3 sessions and create 0 skills.',
'repeated pattern or a stable recurring repo workflow worth investigating. Most runs',
'should read 0-3 sessions and create 0 skills.',
'Do not explore the codebase. Work only with the session index, session files, and the skills directory.',
].join('\n');
}
@@ -301,6 +331,9 @@ export const SkillExtractionAgent = (
'Below is an index of past conversation sessions. Each line shows:',
'[NEW] or [old] status, a 1-line summary, message count, and the file path.',
'',
'The summary is a user-intent summary, not a workflow summary.',
'Matching summary text alone is never enough evidence for a reusable skill.',
'',
'[NEW] = not yet processed for skill extraction (focus on these)',
'[old] = previously processed (read only if a [NEW] session hints at a repeated pattern)',
'',
@@ -319,7 +352,7 @@ export const SkillExtractionAgent = (
return {
systemPrompt: buildSystemPrompt(skillsDir),
query: `${initialContext}\n\nAnalyze the session index above. Read sessions that suggest repeated workflows using read_file. Extract reusable skills to ${skillsDir}/.`,
query: `${initialContext}\n\nAnalyze the session index above. The session summaries describe user intent, not workflow details. Read sessions that suggest repeated workflows using read_file. Only write a skill if the evidence shows a durable, recurring workflow or a stable recurring repo procedure. If recurrence or future reuse is unclear, create no skill and explain why.`,
};
},
runConfig: {
packages/core/src/core/contentGenerator.test.ts
+195 -8
View File
@@ -148,7 +148,7 @@ describe('createContentGenerator', () => {
);
expect(GoogleGenAI).toHaveBeenCalledWith({
apiKey: 'test-api-key',
vertexai: undefined,
vertexai: false,
httpOptions: expect.objectContaining({
headers: expect.objectContaining({
'User-Agent': expect.stringMatching(
@@ -365,7 +365,7 @@ describe('createContentGenerator', () => {
expect(GoogleGenAI).toHaveBeenCalledWith({
apiKey: 'test-api-key',
vertexai: undefined,
vertexai: false,
httpOptions: expect.objectContaining({
headers: expect.objectContaining({
'User-Agent': expect.any(String),
@@ -409,7 +409,7 @@ describe('createContentGenerator', () => {
expect(GoogleGenAI).toHaveBeenCalledWith({
apiKey: 'test-api-key',
vertexai: undefined,
vertexai: false,
httpOptions: expect.objectContaining({
headers: expect.objectContaining({
'User-Agent': expect.any(String),
@@ -443,7 +443,7 @@ describe('createContentGenerator', () => {
expect(GoogleGenAI).toHaveBeenCalledWith({
apiKey: 'test-api-key',
vertexai: undefined,
vertexai: false,
httpOptions: expect.objectContaining({
headers: expect.objectContaining({
'User-Agent': expect.any(String),
@@ -481,7 +481,7 @@ describe('createContentGenerator', () => {
);
expect(GoogleGenAI).toHaveBeenCalledWith({
apiKey: 'test-api-key',
vertexai: undefined,
vertexai: false,
httpOptions: expect.objectContaining({
headers: {
'User-Agent': expect.any(String),
@@ -517,7 +517,7 @@ describe('createContentGenerator', () => {
expect(GoogleGenAI).toHaveBeenCalledWith({
apiKey: 'test-api-key',
vertexai: undefined,
vertexai: false,
httpOptions: expect.objectContaining({
headers: expect.objectContaining({
'User-Agent': expect.any(String),
@@ -550,7 +550,7 @@ describe('createContentGenerator', () => {
expect(GoogleGenAI).toHaveBeenCalledWith({
apiKey: 'test-api-key',
vertexai: undefined,
vertexai: false,
httpOptions: expect.objectContaining({
headers: expect.objectContaining({
'User-Agent': expect.any(String),
@@ -589,7 +589,7 @@ describe('createContentGenerator', () => {
expect(GoogleGenAI).toHaveBeenCalledWith({
apiKey: 'test-api-key',
vertexai: undefined,
vertexai: false,
httpOptions: expect.objectContaining({
headers: expect.objectContaining({
'User-Agent': expect.any(String),
@@ -638,6 +638,193 @@ describe('createContentGenerator', () => {
apiVersion: 'v1alpha',
});
});
it('should pass baseUrl to GoogleGenAI when GOOGLE_GEMINI_BASE_URL is set', async () => {
const mockConfig = {
getModel: vi.fn().mockReturnValue('gemini-pro'),
getProxy: vi.fn().mockReturnValue(undefined),
getUsageStatisticsEnabled: () => false,
getClientName: vi.fn().mockReturnValue(undefined),
} as unknown as Config;
const mockGenerator = {
models: {},
} as unknown as GoogleGenAI;
vi.mocked(GoogleGenAI).mockImplementation(() => mockGenerator as never);
vi.stubEnv('GOOGLE_GEMINI_BASE_URL', 'https://gemini.test.local');
vi.stubEnv('GEMINI_API_KEY', 'test-api-key');
const config = await createContentGeneratorConfig(
mockConfig,
AuthType.USE_GEMINI,
);
await createContentGenerator(config, mockConfig);
expect(GoogleGenAI).toHaveBeenCalledWith(
expect.objectContaining({
apiKey: 'test-api-key',
vertexai: false,
httpOptions: expect.objectContaining({
baseUrl: 'https://gemini.test.local',
}),
}),
);
});
it('should pass baseUrl to GoogleGenAI when GOOGLE_VERTEX_BASE_URL is set', async () => {
const mockConfig = {
getModel: vi.fn().mockReturnValue('gemini-pro'),
getProxy: vi.fn().mockReturnValue(undefined),
getUsageStatisticsEnabled: () => false,
getClientName: vi.fn().mockReturnValue(undefined),
} as unknown as Config;
const mockGenerator = {
models: {},
} as unknown as GoogleGenAI;
vi.mocked(GoogleGenAI).mockImplementation(() => mockGenerator as never);
vi.stubEnv('GOOGLE_VERTEX_BASE_URL', 'https://vertex.test.local');
vi.stubEnv('GOOGLE_CLOUD_PROJECT', 'my-project');
vi.stubEnv('GOOGLE_CLOUD_LOCATION', 'us-central1');
const config = await createContentGeneratorConfig(
mockConfig,
AuthType.USE_VERTEX_AI,
);
await createContentGenerator(config, mockConfig);
expect(GoogleGenAI).toHaveBeenCalledWith(
expect.objectContaining({
apiKey: undefined,
vertexai: true,
httpOptions: expect.objectContaining({
baseUrl: 'https://vertex.test.local',
}),
}),
);
});
it('should prefer GOOGLE_VERTEX_BASE_URL when authType is USE_VERTEX_AI without inferred vertex credentials', async () => {
const mockConfig = {
getModel: vi.fn().mockReturnValue('gemini-pro'),
getProxy: vi.fn().mockReturnValue(undefined),
getUsageStatisticsEnabled: () => false,
getClientName: vi.fn().mockReturnValue(undefined),
} as unknown as Config;
const mockGenerator = {
models: {},
} as unknown as GoogleGenAI;
vi.mocked(GoogleGenAI).mockImplementation(() => mockGenerator as never);
vi.stubEnv('GOOGLE_GEMINI_BASE_URL', 'https://gemini.test.local');
vi.stubEnv('GOOGLE_VERTEX_BASE_URL', 'https://vertex.test.local');
await createContentGenerator(
{
authType: AuthType.USE_VERTEX_AI,
},
mockConfig,
);
expect(GoogleGenAI).toHaveBeenCalledWith(
expect.objectContaining({
apiKey: undefined,
vertexai: true,
httpOptions: expect.objectContaining({
baseUrl: 'https://vertex.test.local',
}),
}),
);
});
it('should prefer an explicit baseUrl over GOOGLE_GEMINI_BASE_URL', async () => {
const mockConfig = {
getModel: vi.fn().mockReturnValue('gemini-pro'),
getProxy: vi.fn().mockReturnValue(undefined),
getUsageStatisticsEnabled: () => false,
getClientName: vi.fn().mockReturnValue(undefined),
} as unknown as Config;
const mockGenerator = {
models: {},
} as unknown as GoogleGenAI;
vi.mocked(GoogleGenAI).mockImplementation(() => mockGenerator as never);
vi.stubEnv('GOOGLE_GEMINI_BASE_URL', 'https://env.test.local');
vi.stubEnv('GEMINI_API_KEY', 'test-api-key');
const config = await createContentGeneratorConfig(
mockConfig,
AuthType.USE_GEMINI,
undefined,
'https://explicit.test.local',
);
await createContentGenerator(config, mockConfig);
expect(GoogleGenAI).toHaveBeenCalledWith(
expect.objectContaining({
httpOptions: expect.objectContaining({
baseUrl: 'https://explicit.test.local',
}),
}),
);
});
it('should allow localhost baseUrl overrides over http', async () => {
const mockConfig = {
getModel: vi.fn().mockReturnValue('gemini-pro'),
getProxy: vi.fn().mockReturnValue(undefined),
getUsageStatisticsEnabled: () => false,
getClientName: vi.fn().mockReturnValue(undefined),
} as unknown as Config;
const mockGenerator = {
models: {},
} as unknown as GoogleGenAI;
vi.mocked(GoogleGenAI).mockImplementation(() => mockGenerator as never);
await createContentGenerator(
{
apiKey: 'test-api-key',
authType: AuthType.USE_GEMINI,
baseUrl: 'http://127.0.0.1:8080',
},
mockConfig,
);
expect(GoogleGenAI).toHaveBeenCalledWith(
expect.objectContaining({
httpOptions: expect.objectContaining({
baseUrl: 'http://127.0.0.1:8080',
}),
}),
);
});
it('should reject invalid custom baseUrl values', async () => {
await expect(
createContentGenerator(
{
apiKey: 'test-api-key',
authType: AuthType.USE_GEMINI,
baseUrl: 'not-a-url',
},
mockConfig,
),
).rejects.toThrow('Invalid custom base URL: not-a-url');
});
it('should reject non-https remote custom baseUrl values', async () => {
await expect(
createContentGenerator(
{
apiKey: 'test-api-key',
authType: AuthType.USE_GEMINI,
baseUrl: 'http://example.com',
},
mockConfig,
),
).rejects.toThrow('Custom base URL must use HTTPS unless it is localhost.');
});
});
describe('createContentGeneratorConfig', () => {
packages/core/src/core/contentGenerator.ts
+32 -3
View File
@@ -101,6 +101,21 @@ export type ContentGeneratorConfig = {
customHeaders?: Record<string, string>;
};
const LOCAL_HOSTNAMES = ['localhost', '127.0.0.1', '[::1]'];
function validateBaseUrl(baseUrl: string): void {
let url: URL;
try {
url = new URL(baseUrl);
} catch {
throw new Error(`Invalid custom base URL: ${baseUrl}`);
}
if (url.protocol !== 'https:' && !LOCAL_HOSTNAMES.includes(url.hostname)) {
throw new Error('Custom base URL must use HTTPS unless it is localhost.');
}
}
export async function createContentGeneratorConfig(
config: Config,
authType: AuthType | undefined,
@@ -273,18 +288,32 @@ export async function createContentGenerator(
'x-gemini-api-privileged-user-id': `${installationId}`,
};
}
let baseUrl = config.baseUrl;
if (!baseUrl) {
const envBaseUrl =
config.authType === AuthType.USE_VERTEX_AI
? process.env['GOOGLE_VERTEX_BASE_URL']
: process.env['GOOGLE_GEMINI_BASE_URL'];
if (envBaseUrl) {
validateBaseUrl(envBaseUrl);
baseUrl = envBaseUrl;
}
} else {
validateBaseUrl(baseUrl);
}
const httpOptions: {
baseUrl?: string;
headers: Record<string, string>;
} = { headers };
if (config.baseUrl) {
httpOptions.baseUrl = config.baseUrl;
if (baseUrl) {
httpOptions.baseUrl = baseUrl;
}
const googleGenAI = new GoogleGenAI({
apiKey: config.apiKey === '' ? undefined : config.apiKey,
vertexai: config.vertexai,
vertexai: config.vertexai ?? config.authType === AuthType.USE_VERTEX_AI,
httpOptions,
...(apiVersionEnv && { apiVersion: apiVersionEnv }),
});
packages/core/src/telemetry/memory-monitor.test.ts
+14 -1
View File
@@ -17,13 +17,18 @@ import {
_resetGlobalMemoryMonitorForTests,
} from './memory-monitor.js';
import type { Config } from '../config/config.js';
import { recordMemoryUsage, isPerformanceMonitoringActive } from './metrics.js';
import {
recordMemoryUsage,
recordCpuUsage,
isPerformanceMonitoringActive,
} from './metrics.js';
import { HighWaterMarkTracker } from './high-water-mark-tracker.js';
import { RateLimiter } from './rate-limiter.js';
// Mock dependencies
vi.mock('./metrics.js', () => ({
recordMemoryUsage: vi.fn(),
recordCpuUsage: vi.fn(),
isPerformanceMonitoringActive: vi.fn(),
MemoryMetricType: {
HEAP_USED: 'heap_used',
@@ -50,6 +55,7 @@ vi.mock('node:process', () => ({
}));
const mockRecordMemoryUsage = vi.mocked(recordMemoryUsage);
const mockRecordCpuUsage = vi.mocked(recordCpuUsage);
const mockIsPerformanceMonitoringActive = vi.mocked(
isPerformanceMonitoringActive,
);
@@ -192,6 +198,13 @@ describe('MemoryMonitor', () => {
component: 'test_context',
},
);
expect(mockRecordCpuUsage).toHaveBeenCalledWith(
mockConfig,
expect.any(Number),
{
component: 'test_context',
},
);
});
it('should not record metrics when performance monitoring is inactive', () => {
packages/core/src/telemetry/memory-monitor.ts
+9
View File
@@ -12,6 +12,7 @@ import { isUserActive } from './activity-detector.js';
import { HighWaterMarkTracker } from './high-water-mark-tracker.js';
import {
recordMemoryUsage,
recordCpuUsage,
MemoryMetricType,
isPerformanceMonitoringActive,
} from './metrics.js';
@@ -37,6 +38,7 @@ export class MemoryMonitor {
private intervalId: NodeJS.Timeout | null = null;
private isRunning = false;
private lastSnapshot: MemorySnapshot | null = null;
private lastCpuUsage: NodeJS.CpuUsage | null = null;
private monitoringInterval: number = 10000;
private highWaterMarkTracker: HighWaterMarkTracker;
private rateLimiter: RateLimiter;
@@ -191,6 +193,13 @@ export class MemoryMonitor {
memory_type: MemoryMetricType.RSS,
component: context,
});
// Record delta CPU usage (in microseconds)
const cpuUsage = process.cpuUsage(this.lastCpuUsage ?? undefined);
this.lastCpuUsage = process.cpuUsage();
recordCpuUsage(config, cpuUsage.user + cpuUsage.system, {
component: context,
});
}
this.lastSnapshot = snapshot;
packages/test-utils/src/perf-test-harness.ts
+3 -1
View File
@@ -147,7 +147,9 @@ export class PerfTestHarness {
throw new Error(`No active timer found for label "${label}"`);
}
const wallClockMs = performance.now() - timer.startTime;
// Round wall-clock time to nearest 0.1 ms
const wallClockMs =
Math.round((performance.now() - timer.startTime) * 10) / 10;
const cpuDelta = process.cpuUsage(timer.startCpuUsage);
this.activeTimers.delete(label);
packages/test-utils/src/test-rig.ts
+28 -6
View File
@@ -193,6 +193,28 @@ export function checkModelOutputContent(
return isValid;
}
export interface MetricDataPoint {
attributes?: Record<string, unknown>;
value?: {
sum?: number;
min?: number;
max?: number;
count?: number;
};
startTime?: [number, number];
endTime?: string;
}
export interface TelemetryMetric {
descriptor: {
name: string;
type?: string;
description?: string;
unit?: string;
};
dataPoints: MetricDataPoint[];
}
export interface ParsedLog {
attributes?: {
'event.name'?: string;
@@ -213,11 +235,7 @@ export interface ParsedLog {
prompt_id?: string;
};
scopeMetrics?: {
metrics: {
descriptor: {
name: string;
};
}[];
metrics: TelemetryMetric[];
}[];
}
@@ -1297,6 +1315,10 @@ export class TestRig {
return logs;
}
readTelemetryLogs(): ParsedLog[] {
return this._readAndParseTelemetryLog();
}
private _readAndParseTelemetryLog(): ParsedLog[] {
// Telemetry is always written to the test directory
const logFilePath = join(this.homeDir!, 'telemetry.log');
@@ -1450,7 +1472,7 @@ export class TestRig {
);
}
readMetric(metricName: string): Record<string, unknown> | null {
readMetric(metricName: string): TelemetryMetric | null {
const logs = this._readAndParseTelemetryLog();
for (const logData of logs) {
if (logData.scopeMetrics) {
perf-tests/baselines.json
+29 -4
View File
@@ -1,14 +1,14 @@
{
"version": 1,
"updatedAt": "2026-04-09T02:30:22.000Z",
"updatedAt": "2026-04-14T14:04:02.662Z",
"scenarios": {
"cold-startup-time": {
"wallClockMs": 927.553249999999,
"wallClockMs": 927.6,
"cpuTotalUs": 1470,
"timestamp": "2026-04-08T22:27:54.871Z"
},
"idle-cpu-usage": {
"wallClockMs": 5000.460750000002,
"wallClockMs": 5000.5,
"cpuTotalUs": 12157,
"timestamp": "2026-04-08T22:28:19.098Z"
},
@@ -18,7 +18,7 @@
"timestamp": "2026-04-14T15:22:56.133Z"
},
"skill-loading-time": {
"wallClockMs": 930.0920409999962,
"wallClockMs": 930.1,
"cpuTotalUs": 1323,
"timestamp": "2026-04-08T22:28:23.290Z"
},
@@ -26,6 +26,31 @@
"wallClockMs": 1119.9,
"cpuTotalUs": 2100,
"timestamp": "2026-04-09T02:30:22.000Z"
},
"long-conversation-resume": {
"wallClockMs": 4212.5,
"cpuTotalUs": 351393,
"timestamp": "2026-04-14T14:02:53.268Z"
},
"long-conversation-typing": {
"wallClockMs": 113.7,
"cpuTotalUs": 3304,
"timestamp": "2026-04-14T14:03:12.525Z"
},
"long-conversation-execution": {
"wallClockMs": 248.7,
"cpuTotalUs": 3825,
"timestamp": "2026-04-14T14:03:28.575Z"
},
"long-conversation-terminal-scrolling": {
"wallClockMs": 362.4,
"cpuTotalUs": 12755860,
"timestamp": "2026-04-14T14:03:45.687Z"
},
"long-conversation-alternate-scrolling": {
"wallClockMs": 362.4,
"cpuTotalUs": 12755860,
"timestamp": "2026-04-14T14:04:02.662Z"
}
}
}
perf-tests/perf-usage.test.ts
+370 -9
View File
@@ -5,10 +5,20 @@
*/
import { describe, it, beforeAll, afterAll } from 'vitest';
import { TestRig, PerfTestHarness } from '@google/gemini-cli-test-utils';
import {
TestRig,
PerfTestHarness,
type PerfSnapshot,
} from '@google/gemini-cli-test-utils';
import { join, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
import { existsSync, readFileSync } from 'node:fs';
import {
existsSync,
readFileSync,
mkdirSync,
copyFileSync,
writeFileSync,
} from 'node:fs';
const __dirname = dirname(fileURLToPath(import.meta.url));
const BASELINES_PATH = join(__dirname, 'baselines.json');
@@ -195,7 +205,7 @@ describe('CPU Performance Tests', () => {
const snapshot = await harness.measureWithEventLoop(
'high-volume-output',
async () => {
const runResult = await rig.run({
await rig.run({
args: ['Generate 1M lines of output'],
timeout: 120000,
env: {
@@ -206,7 +216,6 @@ describe('CPU Performance Tests', () => {
DEBUG: 'true',
},
});
console.log(` Child Process Output:`, runResult);
},
);
@@ -246,8 +255,7 @@ describe('CPU Performance Tests', () => {
JSON.stringify(toolLatencyMetric),
);
}
// eslint-disable-next-line @typescript-eslint/no-explicit-any
const logs = (rig as any)._readAndParseTelemetryLog();
const logs = rig.readTelemetryLogs();
console.log(` Total telemetry log entries: ${logs.length}`);
for (const logData of logs) {
if (logData.scopeMetrics) {
@@ -272,10 +280,9 @@ describe('CPU Performance Tests', () => {
const findValue = (percentile: string) => {
const dp = eventLoopMetric.dataPoints.find(
// eslint-disable-next-line @typescript-eslint/no-explicit-any
(p: any) => p.attributes.percentile === percentile,
(p) => p.attributes?.['percentile'] === percentile,
);
return dp ? dp.value.min : undefined;
return dp?.value?.min;
};
snapshot.childEventLoopDelayP50Ms = findValue('p50');
@@ -296,4 +303,358 @@ describe('CPU Performance Tests', () => {
harness.assertWithinBaseline(result);
}
});
describe('long-conversation', () => {
let rig: TestRig;
const identifier = 'perf-long-conversation';
const SESSION_ID =
'anonymous_unique_id_577296e0eee5afecdcec05d11838e0cd1a851cd97a28119a4a876b11';
const LARGE_CHAT_SOURCE = join(
__dirname,
'..',
'memory-tests',
'large-chat-session.json',
);
beforeAll(async () => {
if (!existsSync(LARGE_CHAT_SOURCE)) {
throw new Error(
`Performance test fixture missing: ${LARGE_CHAT_SOURCE}.`,
);
}
rig = new TestRig();
rig.setup(identifier, {
fakeResponsesPath: join(__dirname, 'perf.long-chat.responses'),
});
const geminiDir = join(rig.homeDir!, '.gemini');
const projectTempDir = join(geminiDir, 'tmp', identifier);
const targetChatsDir = join(projectTempDir, 'chats');
mkdirSync(targetChatsDir, { recursive: true });
writeFileSync(
join(geminiDir, 'projects.json'),
JSON.stringify({
projects: { [rig.testDir!]: identifier },
}),
);
writeFileSync(join(projectTempDir, '.project_root'), rig.testDir!);
copyFileSync(
LARGE_CHAT_SOURCE,
join(targetChatsDir, `session-${SESSION_ID}.json`),
);
});
afterAll(async () => {
await rig.cleanup();
});
it('session-load: resume a 60MB chat history', async () => {
const result = await harness.runScenario(
'long-conversation-resume',
async () => {
const snapshot = await harness.measureWithEventLoop(
'resume',
async () => {
const run = await rig.runInteractive({
args: ['--resume', 'latest'],
env: {
GEMINI_API_KEY: 'fake-perf-test-key',
GEMINI_TELEMETRY_ENABLED: 'true',
GEMINI_MEMORY_MONITOR_INTERVAL: '500',
GEMINI_EVENT_LOOP_MONITOR_ENABLED: 'true',
DEBUG: 'true',
},
});
await run.kill();
},
);
return snapshot;
},
);
if (UPDATE_BASELINES) {
harness.updateScenarioBaseline(result);
} else {
harness.assertWithinBaseline(result);
}
});
it('typing: latency when typing into a large session', async () => {
const result = await harness.runScenario(
'long-conversation-typing',
async () => {
const run = await rig.runInteractive({
args: ['--resume', 'latest'],
env: {
GEMINI_API_KEY: 'fake-perf-test-key',
GEMINI_TELEMETRY_ENABLED: 'true',
GEMINI_MEMORY_MONITOR_INTERVAL: '500',
GEMINI_EVENT_LOOP_MONITOR_ENABLED: 'true',
DEBUG: 'true',
},
});
const snapshot = await harness.measureWithEventLoop(
'typing',
async () => {
// On average, the expected latency per key is under 30ms.
for (const char of 'Hello') {
await run.type(char);
}
},
);
await run.kill();
return snapshot;
},
);
if (UPDATE_BASELINES) {
harness.updateScenarioBaseline(result);
} else {
harness.assertWithinBaseline(result);
}
});
it('execution: response latency for a simple shell command', async () => {
const result = await harness.runScenario(
'long-conversation-execution',
async () => {
const run = await rig.runInteractive({
args: ['--resume', 'latest'],
env: {
GEMINI_API_KEY: 'fake-perf-test-key',
GEMINI_TELEMETRY_ENABLED: 'true',
GEMINI_MEMORY_MONITOR_INTERVAL: '500',
GEMINI_EVENT_LOOP_MONITOR_ENABLED: 'true',
DEBUG: 'true',
},
});
await run.expectText('Type your message');
const snapshot = await harness.measureWithEventLoop(
'execution',
async () => {
await run.sendKeys('!echo hi\r');
await run.expectText('hi');
},
);
await run.kill();
return snapshot;
},
);
if (UPDATE_BASELINES) {
harness.updateScenarioBaseline(result);
} else {
harness.assertWithinBaseline(result);
}
});
it('terminal-scrolling: latency when scrolling a large terminal buffer', async () => {
const result = await harness.runScenario(
'long-conversation-terminal-scrolling',
async () => {
// Enable terminalBuffer to intentionally test CLI scrolling logic
const settingsPath = join(rig.homeDir!, '.gemini', 'settings.json');
writeFileSync(
settingsPath,
JSON.stringify({
security: { folderTrust: { enabled: false } },
ui: { terminalBuffer: true },
}),
);
const run = await rig.runInteractive({
args: ['--resume', 'latest'],
env: {
GEMINI_API_KEY: 'fake-perf-test-key',
GEMINI_TELEMETRY_ENABLED: 'true',
GEMINI_MEMORY_MONITOR_INTERVAL: '500',
GEMINI_EVENT_LOOP_MONITOR_ENABLED: 'true',
DEBUG: 'true',
},
});
await run.expectText('Type your message');
for (let i = 0; i < 5; i++) {
await run.sendKeys('\u001b[5~'); // PageUp
}
// Scroll to the very top
await run.sendKeys('\u001b[H'); // Home
// Verify top line of chat is visible.
await run.expectText('Authenticated with');
for (let i = 0; i < 5; i++) {
await run.sendKeys('\u001b[6~'); // PageDown
}
await rig.waitForTelemetryReady();
await run.kill();
const eventLoopMetric = rig.readMetric('event_loop.delay');
const cpuMetric = rig.readMetric('cpu.usage');
let p50Ms = 0;
let p95Ms = 0;
let maxMs = 0;
if (eventLoopMetric) {
const dataPoints = eventLoopMetric.dataPoints;
const p50Data = dataPoints.find(
(dp) => dp.attributes?.['percentile'] === 'p50',
);
const p95Data = dataPoints.find(
(dp) => dp.attributes?.['percentile'] === 'p95',
);
const maxData = dataPoints.find(
(dp) => dp.attributes?.['percentile'] === 'max',
);
if (p50Data?.value?.sum) p50Ms = p50Data.value.sum;
if (p95Data?.value?.sum) p95Ms = p95Data.value.sum;
if (maxData?.value?.sum) maxMs = maxData.value.sum;
}
let cpuTotalUs = 0;
if (cpuMetric) {
const dataPoints = cpuMetric.dataPoints;
for (const dp of dataPoints) {
if (dp.value?.sum && dp.value.sum > 0) {
cpuTotalUs += dp.value.sum;
}
}
}
const cpuUserUs = cpuTotalUs;
const cpuSystemUs = 0;
const snapshot: PerfSnapshot = {
timestamp: Date.now(),
label: 'scrolling',
wallClockMs: Math.round(p50Ms * 10) / 10,
cpuTotalUs,
cpuUserUs,
cpuSystemUs,
eventLoopDelayP50Ms: p50Ms,
eventLoopDelayP95Ms: p95Ms,
eventLoopDelayMaxMs: maxMs,
};
return snapshot;
},
);
if (UPDATE_BASELINES) {
harness.updateScenarioBaseline(result);
} else {
harness.assertWithinBaseline(result);
}
});
it('alternate-scrolling: latency when scrolling a large alternate buffer', async () => {
const result = await harness.runScenario(
'long-conversation-alternate-scrolling',
async () => {
// Enable useAlternateBuffer to intentionally test CLI scrolling logic
const settingsPath = join(rig.homeDir!, '.gemini', 'settings.json');
writeFileSync(
settingsPath,
JSON.stringify({
security: { folderTrust: { enabled: false } },
ui: { useAlternateBuffer: true },
}),
);
const run = await rig.runInteractive({
args: ['--resume', 'latest'],
env: {
GEMINI_API_KEY: 'fake-perf-test-key',
GEMINI_TELEMETRY_ENABLED: 'true',
GEMINI_MEMORY_MONITOR_INTERVAL: '500',
GEMINI_EVENT_LOOP_MONITOR_ENABLED: 'true',
DEBUG: 'true',
},
});
await run.expectText('Type your message');
for (let i = 0; i < 5; i++) {
await run.sendKeys('\u001b[5~'); // PageUp
}
// Scroll to the very top
await run.sendKeys('\u001b[H'); // Home
// Verify top line of chat is visible.
await run.expectText('Authenticated with');
for (let i = 0; i < 5; i++) {
await run.sendKeys('\u001b[6~'); // PageDown
}
await rig.waitForTelemetryReady();
await run.kill();
const eventLoopMetric = rig.readMetric('event_loop.delay');
const cpuMetric = rig.readMetric('cpu.usage');
let p50Ms = 0;
let p95Ms = 0;
let maxMs = 0;
if (eventLoopMetric) {
const dataPoints = eventLoopMetric.dataPoints;
const p50Data = dataPoints.find(
(dp) => dp.attributes?.['percentile'] === 'p50',
);
const p95Data = dataPoints.find(
(dp) => dp.attributes?.['percentile'] === 'p95',
);
const maxData = dataPoints.find(
(dp) => dp.attributes?.['percentile'] === 'max',
);
if (p50Data?.value?.sum) p50Ms = p50Data.value.sum;
if (p95Data?.value?.sum) p95Ms = p95Data.value.sum;
if (maxData?.value?.sum) maxMs = maxData.value.sum;
}
let cpuTotalUs = 0;
if (cpuMetric) {
const dataPoints = cpuMetric.dataPoints;
for (const dp of dataPoints) {
if (dp.value?.sum && dp.value.sum > 0) {
cpuTotalUs += dp.value.sum;
}
}
}
const cpuUserUs = cpuTotalUs;
const cpuSystemUs = 0;
const snapshot: PerfSnapshot = {
timestamp: Date.now(),
label: 'scrolling',
wallClockMs: Math.round(p50Ms * 10) / 10,
cpuTotalUs,
cpuUserUs,
cpuSystemUs,
eventLoopDelayP50Ms: p50Ms,
eventLoopDelayP95Ms: p95Ms,
eventLoopDelayMaxMs: maxMs,
};
return snapshot;
},
);
if (UPDATE_BASELINES) {
harness.updateScenarioBaseline(result);
} else {
harness.assertWithinBaseline(result);
}
});
});
});
perf-tests/perf.long-chat.responses
+4
View File
@@ -0,0 +1,4 @@
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"{\"complexity_reasoning\":\"simple\",\"complexity_score\":1}"}],"role":"model"},"finishReason":"STOP","index":0}]}}
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I am a large conversation model response."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"candidatesTokenCount":10,"promptTokenCount":20,"totalTokenCount":30}}]}
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"{\"originalSummary\":\"large chat summary\",\"events\":[]}"}],"role":"model"},"finishReason":"STOP","index":0}]}}
{"method":"countTokens","response":{"totalTokens":100}}