mirror of
https://github.com/google-gemini/gemini-cli.git
synced 2026-07-23 16:20:57 -07:00
Compare commits
20 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Dev Randalpura
|
af0b5ee817 | ||
|
Jacob Richman
|
6686c8ee4c | ||
|
Emily Hedlund
|
5724d6be0f | ||
|
Sandy Tao
|
615e078341 | ||
|
Jarrod Whelan
|
faa7a9da30 | ||
|
Emily Hedlund
|
5d589946ad | ||
|
Sehoon Shon
|
464bac270c | ||
|
Christian Gunderman
|
f1bb2af6de | ||
|
Jarrod Whelan
|
bc3ed61adb | ||
|
Jacob Richman
|
9c4e17b7ce | ||
|
Tommaso Sciortino
|
d06dba3538 | ||
|
dogukanozen
|
80764c8bb5 | ||
|
Jarrod Whelan
|
14b2f35677 | ||
|
Adamya Singh
|
1023c5b7a6 | ||
|
Emily Hedlund
|
af3638640c | ||
|
Sri Pasumarthi
|
c7b920717f | ||
|
ruomeng
|
15f7b24312 | ||
|
gemini-cli-robot
|
18cb7fd46c | ||
|
JAYADITYA
|
8b01d78512 | ||
|
gemini-cli-robot
|
56c2397e78 |
@@ -335,6 +335,8 @@ jobs:
|
||||
env:
|
||||
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
|
||||
GEMINI_MODEL: 'gemini-3-pro-preview'
|
||||
# Only run always passes behavioral tests.
|
||||
EVAL_SUITE_TYPE: 'behavioral'
|
||||
# Disable Vitest internal retries to avoid double-retrying;
|
||||
# custom retry logic is handled in evals/test-helper.ts
|
||||
VITEST_RETRY: 0
|
||||
|
||||
@@ -5,10 +5,18 @@ on:
|
||||
- cron: '0 1 * * *' # Runs at 1 AM every day
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
run_all:
|
||||
description: 'Run all evaluations (including usually passing)'
|
||||
type: 'boolean'
|
||||
default: true
|
||||
suite_type:
|
||||
description: 'Suite type to run'
|
||||
type: 'choice'
|
||||
options:
|
||||
- 'behavioral'
|
||||
- 'component-level'
|
||||
- 'hero-scenario'
|
||||
default: 'behavioral'
|
||||
suite_name:
|
||||
description: 'Specific suite name to run'
|
||||
required: false
|
||||
type: 'string'
|
||||
test_name_pattern:
|
||||
description: 'Test name pattern or file name'
|
||||
required: false
|
||||
@@ -59,7 +67,9 @@ jobs:
|
||||
env:
|
||||
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
|
||||
GEMINI_MODEL: '${{ matrix.model }}'
|
||||
RUN_EVALS: "${{ github.event.inputs.run_all != 'false' }}"
|
||||
RUN_EVALS: 'true'
|
||||
EVAL_SUITE_TYPE: "${{ github.event.inputs.suite_type || 'behavioral' }}"
|
||||
EVAL_SUITE_NAME: '${{ github.event.inputs.suite_name }}'
|
||||
TEST_NAME_PATTERN: '${{ github.event.inputs.test_name_pattern }}'
|
||||
# Disable Vitest internal retries to avoid double-retrying;
|
||||
# custom retry logic is handled in evals/test-helper.ts
|
||||
|
||||
@@ -0,0 +1,33 @@
|
||||
name: 'Performance Tests: Nightly'
|
||||
|
||||
on:
|
||||
schedule:
|
||||
- cron: '0 3 * * *' # Runs at 3 AM every day
|
||||
workflow_dispatch: # Allow manual trigger
|
||||
|
||||
permissions:
|
||||
contents: 'read'
|
||||
|
||||
jobs:
|
||||
perf-test:
|
||||
name: 'Run Performance Usage Tests'
|
||||
runs-on: 'gemini-cli-ubuntu-16-core'
|
||||
if: "github.repository == 'google-gemini/gemini-cli'"
|
||||
steps:
|
||||
- name: 'Checkout'
|
||||
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
|
||||
|
||||
- name: 'Set up Node.js'
|
||||
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
|
||||
with:
|
||||
node-version-file: '.nvmrc'
|
||||
cache: 'npm'
|
||||
|
||||
- name: 'Install dependencies'
|
||||
run: 'npm ci'
|
||||
|
||||
- name: 'Build project'
|
||||
run: 'npm run build'
|
||||
|
||||
- name: 'Run Performance Tests'
|
||||
run: 'npm run test:perf'
|
||||
@@ -48,6 +48,7 @@ packages/cli/src/generated/
|
||||
packages/core/src/generated/
|
||||
packages/devtools/src/_client-assets.ts
|
||||
.integration-tests/
|
||||
.perf-tests/
|
||||
packages/vscode-ide-companion/*.vsix
|
||||
packages/cli/download-ripgrep*/
|
||||
|
||||
@@ -64,3 +65,6 @@ gemini-debug.log
|
||||
evals/logs/
|
||||
|
||||
temp_agents/
|
||||
|
||||
# conductor extension and planning directories
|
||||
conductor/
|
||||
|
||||
@@ -44,8 +44,13 @@ powerful tool for developers.
|
||||
- **Test Commands:**
|
||||
- **Unit (All):** `npm run test`
|
||||
- **Integration (E2E):** `npm run test:e2e`
|
||||
- > **NOTE**: Please run the memory and perf tests locally **only if** you are
|
||||
> implementing changes related to those test areas. Otherwise skip these
|
||||
> tests locally and rely on CI to run them on nightly builds.
|
||||
- **Memory (Nightly):** `npm run test:memory` (Runs memory regression tests
|
||||
against baselines. Excluded from `preflight`, run nightly.)
|
||||
- **Performance (Nightly):** `npm run test:perf` (Runs CPU performance
|
||||
regression tests against baselines. Excluded from `preflight`, run nightly.)
|
||||
- **Workspace-Specific:** `npm test -w <pkg> -- <path>` (Note: `<path>` must
|
||||
be relative to the workspace root, e.g.,
|
||||
`-w @google/gemini-cli-core -- src/routing/modelRouterService.test.ts`)
|
||||
|
||||
@@ -18,6 +18,27 @@ on GitHub.
|
||||
| [Preview](preview.md) | Experimental features ready for early feedback. |
|
||||
| [Stable](latest.md) | Stable, recommended for general use. |
|
||||
|
||||
## Announcements: v0.37.0 - 2026-04-08
|
||||
|
||||
- **Dynamic Sandbox Expansion:** Implemented dynamic sandbox expansion and
|
||||
worktree support for Linux and Windows, improving developer workflows in
|
||||
isolated environments
|
||||
([#23692](https://github.com/google-gemini/gemini-cli/pull/23692) by @galz10,
|
||||
[#23691](https://github.com/google-gemini/gemini-cli/pull/23691) by
|
||||
@scidomino).
|
||||
- **Chapters Narrative Flow:** Introduced tool-based topic grouping ("Chapters")
|
||||
to provide better session structure and narrative continuity
|
||||
([#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).
|
||||
- **Advanced Browser Capabilities:** Enhanced the browser agent with persistent
|
||||
sessions and dynamic tool discovery
|
||||
([#21306](https://github.com/google-gemini/gemini-cli/pull/21306) by
|
||||
@kunal-10-cloud,
|
||||
[#23805](https://github.com/google-gemini/gemini-cli/pull/23805) by
|
||||
@cynthialong0-0).
|
||||
|
||||
## Announcements: v0.36.0 - 2026-04-01
|
||||
|
||||
- **Multi-Registry Architecture and Sandboxing:** Introduced a multi-registry
|
||||
|
||||
+397
-360
@@ -1,6 +1,6 @@
|
||||
# Latest stable release: v0.36.0
|
||||
# Latest stable release: v0.37.0
|
||||
|
||||
Released: April 1, 2026
|
||||
Released: April 08, 2026
|
||||
|
||||
For most users, our latest stable release is the recommended release. Install
|
||||
the latest stable version with:
|
||||
@@ -11,372 +11,409 @@ npm install -g @google/gemini-cli
|
||||
|
||||
## Highlights
|
||||
|
||||
- **Multi-Registry Architecture and Tool Isolation:** Introduced a
|
||||
multi-registry architecture for subagents and implemented strict sandboxing
|
||||
for macOS (Seatbelt) and Windows to enhance security and isolation.
|
||||
- **Improved Subagent Coordination:** Enhanced subagents with local execution
|
||||
capabilities, JIT context injection (upward traversal capped at git root), and
|
||||
resilient tool rejection with contextual feedback.
|
||||
- **Enhanced UI and UX:** Implemented a refreshed UX for the Composer layout,
|
||||
improved terminal fallback warnings, and resolved various UI flickering and
|
||||
state persistence issues.
|
||||
- **Git Worktree Support:** Added support for Git worktrees to enable isolated
|
||||
parallel sessions within the same repository.
|
||||
- **Plan Mode Improvements:** Plan mode now supports non-interactive execution
|
||||
and includes hardened sandbox path resolution to prevent hallucinations.
|
||||
- **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.
|
||||
|
||||
## What's Changed
|
||||
|
||||
- Changelog for v0.33.2 by @gemini-cli-robot in
|
||||
[#22730](https://github.com/google-gemini/gemini-cli/pull/22730)
|
||||
- feat(core): multi-registry architecture and tool filtering for subagents by
|
||||
@akh64bit in [#22712](https://github.com/google-gemini/gemini-cli/pull/22712)
|
||||
- Changelog for v0.34.0-preview.4 by @gemini-cli-robot in
|
||||
[#22752](https://github.com/google-gemini/gemini-cli/pull/22752)
|
||||
- fix(devtools): use theme-aware text colors for console warnings and errors by
|
||||
@SandyTao520 in
|
||||
[#22181](https://github.com/google-gemini/gemini-cli/pull/22181)
|
||||
- Add support for dynamic model Resolution to ModelConfigService by @kevinjwang1
|
||||
in [#22578](https://github.com/google-gemini/gemini-cli/pull/22578)
|
||||
- chore(release): bump version to 0.36.0-nightly.20260317.2f90b4653 by
|
||||
@gemini-cli-robot in
|
||||
[#22858](https://github.com/google-gemini/gemini-cli/pull/22858)
|
||||
- fix(cli): use active sessionId in useLogger and improve resume robustness by
|
||||
@mattKorwel in
|
||||
[#22606](https://github.com/google-gemini/gemini-cli/pull/22606)
|
||||
- fix(cli): expand tilde in policy paths from settings.json by @abhipatel12 in
|
||||
[#22772](https://github.com/google-gemini/gemini-cli/pull/22772)
|
||||
- fix(core): add actionable warnings for terminal fallbacks (#14426) by
|
||||
@spencer426 in
|
||||
[#22211](https://github.com/google-gemini/gemini-cli/pull/22211)
|
||||
- feat(tracker): integrate task tracker protocol into core system prompt by
|
||||
@anj-s in [#22442](https://github.com/google-gemini/gemini-cli/pull/22442)
|
||||
- chore: add posttest build hooks and fix missing dependencies by @NTaylorMullen
|
||||
in [#22865](https://github.com/google-gemini/gemini-cli/pull/22865)
|
||||
- feat(a2a): add agent acknowledgment command and enhance registry discovery by
|
||||
@alisa-alisa in
|
||||
[#22389](https://github.com/google-gemini/gemini-cli/pull/22389)
|
||||
- fix(cli): automatically add all VSCode workspace folders to Gemini context by
|
||||
@sakshisemalti in
|
||||
[#21380](https://github.com/google-gemini/gemini-cli/pull/21380)
|
||||
- feat: add 'blocked' status to tasks and todos by @anj-s in
|
||||
[#22735](https://github.com/google-gemini/gemini-cli/pull/22735)
|
||||
- refactor(cli): remove extra newlines in ShellToolMessage.tsx by @NTaylorMullen
|
||||
in [#22868](https://github.com/google-gemini/gemini-cli/pull/22868)
|
||||
- fix(cli): lazily load settings in onModelChange to prevent stale closure data
|
||||
loss by @KumarADITHYA123 in
|
||||
[#20403](https://github.com/google-gemini/gemini-cli/pull/20403)
|
||||
- feat(core): subagent local execution and tool isolation by @akh64bit in
|
||||
[#22718](https://github.com/google-gemini/gemini-cli/pull/22718)
|
||||
- fix(cli): resolve subagent grouping and UI state persistence by @abhipatel12
|
||||
in [#22252](https://github.com/google-gemini/gemini-cli/pull/22252)
|
||||
- refactor(ui): extract SessionBrowser search and navigation components by
|
||||
@abhipatel12 in
|
||||
[#22377](https://github.com/google-gemini/gemini-cli/pull/22377)
|
||||
- fix: updates Docker image reference for GitHub MCP server by @jhhornn in
|
||||
[#22938](https://github.com/google-gemini/gemini-cli/pull/22938)
|
||||
- refactor(cli): group subagent trajectory deletion and use native filesystem
|
||||
testing by @abhipatel12 in
|
||||
[#22890](https://github.com/google-gemini/gemini-cli/pull/22890)
|
||||
- refactor(cli): simplify keypress and mouse providers and update tests by
|
||||
@scidomino in [#22853](https://github.com/google-gemini/gemini-cli/pull/22853)
|
||||
- Changelog for v0.34.0 by @gemini-cli-robot in
|
||||
[#22860](https://github.com/google-gemini/gemini-cli/pull/22860)
|
||||
- test(cli): simplify createMockSettings calls by @scidomino in
|
||||
[#22952](https://github.com/google-gemini/gemini-cli/pull/22952)
|
||||
- feat(ui): format multi-line banner warnings with a bold title by @keithguerin
|
||||
in [#22955](https://github.com/google-gemini/gemini-cli/pull/22955)
|
||||
- Docs: Remove references to stale Gemini CLI file structure info by
|
||||
@g-samroberts in
|
||||
[#22976](https://github.com/google-gemini/gemini-cli/pull/22976)
|
||||
- feat(ui): remove write todo list tool from UI tips by @aniruddhaadak80 in
|
||||
[#22281](https://github.com/google-gemini/gemini-cli/pull/22281)
|
||||
- Fix issue where subagent thoughts are appended. by @gundermanc in
|
||||
[#22975](https://github.com/google-gemini/gemini-cli/pull/22975)
|
||||
- Feat/browser privacy consent by @kunal-10-cloud in
|
||||
[#21119](https://github.com/google-gemini/gemini-cli/pull/21119)
|
||||
- fix(core): explicitly map execution context in LocalAgentExecutor by @akh64bit
|
||||
in [#22949](https://github.com/google-gemini/gemini-cli/pull/22949)
|
||||
- feat(plan): support plan mode in non-interactive mode by @ruomengz in
|
||||
[#22670](https://github.com/google-gemini/gemini-cli/pull/22670)
|
||||
- feat(core): implement strict macOS sandboxing using Seatbelt allowlist by
|
||||
@ehedlund in [#22832](https://github.com/google-gemini/gemini-cli/pull/22832)
|
||||
- docs: add additional notes by @abhipatel12 in
|
||||
[#23008](https://github.com/google-gemini/gemini-cli/pull/23008)
|
||||
- fix(cli): resolve duplicate footer on tool cancel via ESC (#21743) by
|
||||
@ruomengz in [#21781](https://github.com/google-gemini/gemini-cli/pull/21781)
|
||||
- Changelog for v0.35.0-preview.1 by @gemini-cli-robot in
|
||||
[#23012](https://github.com/google-gemini/gemini-cli/pull/23012)
|
||||
- fix(ui): fix flickering on small terminal heights by @devr0306 in
|
||||
[#21416](https://github.com/google-gemini/gemini-cli/pull/21416)
|
||||
- fix(acp): provide more meta in tool_call_update by @Mervap in
|
||||
[#22663](https://github.com/google-gemini/gemini-cli/pull/22663)
|
||||
- docs: add FAQ entry for checking Gemini CLI version by @surajsahani in
|
||||
[#21271](https://github.com/google-gemini/gemini-cli/pull/21271)
|
||||
- feat(core): resilient subagent tool rejection with contextual feedback by
|
||||
@abhipatel12 in
|
||||
[#22951](https://github.com/google-gemini/gemini-cli/pull/22951)
|
||||
- fix(cli): correctly handle auto-update for standalone binaries by @bdmorgan in
|
||||
[#23038](https://github.com/google-gemini/gemini-cli/pull/23038)
|
||||
- feat(core): add content-utils by @adamfweidman in
|
||||
[#22984](https://github.com/google-gemini/gemini-cli/pull/22984)
|
||||
- fix: circumvent genai sdk requirement for api key when using gateway auth via
|
||||
ACP by @sripasg in
|
||||
[#23042](https://github.com/google-gemini/gemini-cli/pull/23042)
|
||||
- fix(core): don't persist browser consent sentinel in non-interactive mode by
|
||||
@jasonmatthewsuhari in
|
||||
[#23073](https://github.com/google-gemini/gemini-cli/pull/23073)
|
||||
- fix(core): narrow browser agent description to prevent stealing URL tasks from
|
||||
web_fetch by @gsquared94 in
|
||||
[#23086](https://github.com/google-gemini/gemini-cli/pull/23086)
|
||||
- feat(cli): Partial threading of AgentLoopContext. by @joshualitt in
|
||||
[#22978](https://github.com/google-gemini/gemini-cli/pull/22978)
|
||||
- fix(browser-agent): enable "Allow all server tools" session policy by
|
||||
- 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
|
||||
[#22343](https://github.com/google-gemini/gemini-cli/pull/22343)
|
||||
- refactor(cli): integrate real config loading into async test utils by
|
||||
@scidomino in [#23040](https://github.com/google-gemini/gemini-cli/pull/23040)
|
||||
- feat(core): inject memory and JIT context into subagents by @abhipatel12 in
|
||||
[#23032](https://github.com/google-gemini/gemini-cli/pull/23032)
|
||||
- Fix logging and virtual list. by @jacob314 in
|
||||
[#23080](https://github.com/google-gemini/gemini-cli/pull/23080)
|
||||
- feat(core): cap JIT context upward traversal at git root by @SandyTao520 in
|
||||
[#23074](https://github.com/google-gemini/gemini-cli/pull/23074)
|
||||
- Docs: Minor style updates from initial docs audit. by @g-samroberts in
|
||||
[#22872](https://github.com/google-gemini/gemini-cli/pull/22872)
|
||||
- feat(core): add experimental memory manager agent to replace save_memory tool
|
||||
by @SandyTao520 in
|
||||
[#22726](https://github.com/google-gemini/gemini-cli/pull/22726)
|
||||
- Changelog for v0.35.0-preview.2 by @gemini-cli-robot in
|
||||
[#23142](https://github.com/google-gemini/gemini-cli/pull/23142)
|
||||
- Update website issue template for label and title by @g-samroberts in
|
||||
[#23036](https://github.com/google-gemini/gemini-cli/pull/23036)
|
||||
- fix: upgrade ACP SDK from 0.12 to 0.16.1 by @sripasg in
|
||||
[#23132](https://github.com/google-gemini/gemini-cli/pull/23132)
|
||||
- Update callouts to work on github. by @g-samroberts in
|
||||
[#22245](https://github.com/google-gemini/gemini-cli/pull/22245)
|
||||
- feat: ACP: Add token usage metadata to the `send` method's return value by
|
||||
@sripasg in [#23148](https://github.com/google-gemini/gemini-cli/pull/23148)
|
||||
- fix(plan): clarify that plan mode policies are combined with normal mode by
|
||||
@ruomengz in [#23158](https://github.com/google-gemini/gemini-cli/pull/23158)
|
||||
- Add ModelChain support to ModelConfigService and make ModelDialog dynamic by
|
||||
@kevinjwang1 in
|
||||
[#22914](https://github.com/google-gemini/gemini-cli/pull/22914)
|
||||
- Ensure that copied extensions are writable in the user's local directory by
|
||||
@kevinjwang1 in
|
||||
[#23016](https://github.com/google-gemini/gemini-cli/pull/23016)
|
||||
- feat(core): implement native Windows sandboxing by @mattKorwel in
|
||||
[#21807](https://github.com/google-gemini/gemini-cli/pull/21807)
|
||||
- feat(core): add support for admin-forced MCP server installations by
|
||||
@gsquared94 in
|
||||
[#23163](https://github.com/google-gemini/gemini-cli/pull/23163)
|
||||
- chore(lint): ignore .gemini directory and recursive node_modules by
|
||||
@mattKorwel in
|
||||
[#23211](https://github.com/google-gemini/gemini-cli/pull/23211)
|
||||
- feat(cli): conditionally exclude ask_user tool in ACP mode by @nmcnamara-eng
|
||||
in [#23045](https://github.com/google-gemini/gemini-cli/pull/23045)
|
||||
- feat(core): introduce AgentSession and rename stream events to agent events by
|
||||
@mbleigh in [#23159](https://github.com/google-gemini/gemini-cli/pull/23159)
|
||||
- feat(worktree): add Git worktree support for isolated parallel sessions by
|
||||
@jerop in [#22973](https://github.com/google-gemini/gemini-cli/pull/22973)
|
||||
- Add support for linking in the extension registry by @kevinjwang1 in
|
||||
[#23153](https://github.com/google-gemini/gemini-cli/pull/23153)
|
||||
- feat(extensions): add --skip-settings flag to install command by @Ratish1 in
|
||||
[#17212](https://github.com/google-gemini/gemini-cli/pull/17212)
|
||||
- feat(telemetry): track if session is running in a Git worktree by @jerop in
|
||||
[#23265](https://github.com/google-gemini/gemini-cli/pull/23265)
|
||||
- refactor(core): use absolute paths in GEMINI.md context markers by
|
||||
@SandyTao520 in
|
||||
[#23135](https://github.com/google-gemini/gemini-cli/pull/23135)
|
||||
- fix(core): add sanitization to sub agent thoughts and centralize utilities by
|
||||
@devr0306 in [#22828](https://github.com/google-gemini/gemini-cli/pull/22828)
|
||||
- feat(core): refine User-Agent for VS Code traffic (unified format) by
|
||||
@sehoon38 in [#23256](https://github.com/google-gemini/gemini-cli/pull/23256)
|
||||
- Fix schema for ModelChains by @kevinjwang1 in
|
||||
[#23284](https://github.com/google-gemini/gemini-cli/pull/23284)
|
||||
- test(cli): refactor tests for async render utilities by @scidomino in
|
||||
[#23252](https://github.com/google-gemini/gemini-cli/pull/23252)
|
||||
- feat(core): add security prompt for browser agent by @cynthialong0-0 in
|
||||
[#23241](https://github.com/google-gemini/gemini-cli/pull/23241)
|
||||
- refactor(ide): replace dynamic undici import with static fetch import by
|
||||
@cocosheng-g in
|
||||
[#23268](https://github.com/google-gemini/gemini-cli/pull/23268)
|
||||
- test(cli): address unresolved feedback from PR #23252 by @scidomino in
|
||||
[#23303](https://github.com/google-gemini/gemini-cli/pull/23303)
|
||||
- feat(browser): add sensitive action controls and read-only noise reduction by
|
||||
@cynthialong0-0 in
|
||||
[#22867](https://github.com/google-gemini/gemini-cli/pull/22867)
|
||||
- Disabling failing test while investigating by @alisa-alisa in
|
||||
[#23311](https://github.com/google-gemini/gemini-cli/pull/23311)
|
||||
- fix broken extension link in hooks guide by @Indrapal-70 in
|
||||
[#21728](https://github.com/google-gemini/gemini-cli/pull/21728)
|
||||
- fix(core): fix agent description indentation by @abhipatel12 in
|
||||
[#23315](https://github.com/google-gemini/gemini-cli/pull/23315)
|
||||
- Wrap the text under TOML rule for easier readability in policy-engine.md… by
|
||||
@CogitationOps in
|
||||
[#23076](https://github.com/google-gemini/gemini-cli/pull/23076)
|
||||
- fix(extensions): revert broken extension removal behavior by @ehedlund in
|
||||
[#23317](https://github.com/google-gemini/gemini-cli/pull/23317)
|
||||
- feat(core): set up onboarding telemetry by @yunaseoul in
|
||||
[#23118](https://github.com/google-gemini/gemini-cli/pull/23118)
|
||||
- Retry evals on API error. by @gundermanc in
|
||||
[#23322](https://github.com/google-gemini/gemini-cli/pull/23322)
|
||||
- fix(evals): remove tool restrictions and add compile-time guards by
|
||||
@SandyTao520 in
|
||||
[#23312](https://github.com/google-gemini/gemini-cli/pull/23312)
|
||||
- fix(hooks): support 'ask' decision for BeforeTool hooks by @gundermanc in
|
||||
[#21146](https://github.com/google-gemini/gemini-cli/pull/21146)
|
||||
- feat(browser): add warning message for session mode 'existing' by
|
||||
@cynthialong0-0 in
|
||||
[#23288](https://github.com/google-gemini/gemini-cli/pull/23288)
|
||||
- chore(lint): enforce zero warnings and cleanup syntax restrictions by
|
||||
@alisa-alisa in
|
||||
[#22902](https://github.com/google-gemini/gemini-cli/pull/22902)
|
||||
- fix(cli): add Esc instruction to HooksDialog footer by @abhipatel12 in
|
||||
[#23258](https://github.com/google-gemini/gemini-cli/pull/23258)
|
||||
- Disallow and suppress misused spread operator. by @gundermanc in
|
||||
[#23294](https://github.com/google-gemini/gemini-cli/pull/23294)
|
||||
- fix(core): refine CliHelpAgent description for better delegation by
|
||||
@abhipatel12 in
|
||||
[#23310](https://github.com/google-gemini/gemini-cli/pull/23310)
|
||||
- fix(core): enable global session and persistent approval for web_fetch by
|
||||
@NTaylorMullen in
|
||||
[#23295](https://github.com/google-gemini/gemini-cli/pull/23295)
|
||||
- fix(plan): add state transition override to prevent plan mode freeze by
|
||||
@Adib234 in [#23020](https://github.com/google-gemini/gemini-cli/pull/23020)
|
||||
- fix(cli): record skill activation tool calls in chat history by @NTaylorMullen
|
||||
in [#23203](https://github.com/google-gemini/gemini-cli/pull/23203)
|
||||
- fix(core): ensure subagent tool updates apply configuration overrides
|
||||
immediately by @abhipatel12 in
|
||||
[#23161](https://github.com/google-gemini/gemini-cli/pull/23161)
|
||||
- fix(cli): resolve flicker at boundaries of list in BaseSelectionList by
|
||||
@jackwotherspoon in
|
||||
[#23298](https://github.com/google-gemini/gemini-cli/pull/23298)
|
||||
- test(cli): force generic terminal in tests to fix snapshot failures by
|
||||
@abhipatel12 in
|
||||
[#23499](https://github.com/google-gemini/gemini-cli/pull/23499)
|
||||
- Evals: PR Guidance adding workflow by @alisa-alisa in
|
||||
[#23164](https://github.com/google-gemini/gemini-cli/pull/23164)
|
||||
- feat(core): refactor SandboxManager to a stateless architecture and introduce
|
||||
explicit Deny interface by @ehedlund in
|
||||
[#23141](https://github.com/google-gemini/gemini-cli/pull/23141)
|
||||
- feat(core): add event-translator and update agent types by @adamfweidman in
|
||||
[#22985](https://github.com/google-gemini/gemini-cli/pull/22985)
|
||||
- perf(cli): parallelize and background startup cleanup tasks by @sehoon38 in
|
||||
[#23545](https://github.com/google-gemini/gemini-cli/pull/23545)
|
||||
- fix: "allow always" for commands with paths by @scidomino in
|
||||
[#23558](https://github.com/google-gemini/gemini-cli/pull/23558)
|
||||
- fix(cli): prevent terminal escape sequences from leaking on exit by
|
||||
@mattKorwel in
|
||||
[#22682](https://github.com/google-gemini/gemini-cli/pull/22682)
|
||||
- feat(cli): implement full "GEMINI CLI" logo for logged-out state by
|
||||
@keithguerin in
|
||||
[#22412](https://github.com/google-gemini/gemini-cli/pull/22412)
|
||||
- fix(plan): reserve minimum height for selection list in AskUserDialog by
|
||||
@ruomengz in [#23280](https://github.com/google-gemini/gemini-cli/pull/23280)
|
||||
- fix(core): harden AgentSession replay semantics by @adamfweidman in
|
||||
[#23548](https://github.com/google-gemini/gemini-cli/pull/23548)
|
||||
- test(core): migrate hook tests to scheduler by @abhipatel12 in
|
||||
[#23496](https://github.com/google-gemini/gemini-cli/pull/23496)
|
||||
- chore(config): disable agents by default by @abhipatel12 in
|
||||
[#23546](https://github.com/google-gemini/gemini-cli/pull/23546)
|
||||
- fix(ui): make tool confirmations take up entire terminal height by @devr0306
|
||||
in [#22366](https://github.com/google-gemini/gemini-cli/pull/22366)
|
||||
- fix(core): prevent redundant remote agent loading on model switch by
|
||||
[#23216](https://github.com/google-gemini/gemini-cli/pull/23216)
|
||||
- fix(core): improve agent loader error formatting for empty paths by
|
||||
@adamfweidman in
|
||||
[#23576](https://github.com/google-gemini/gemini-cli/pull/23576)
|
||||
- refactor(core): update production type imports from coreToolScheduler by
|
||||
@abhipatel12 in
|
||||
[#23498](https://github.com/google-gemini/gemini-cli/pull/23498)
|
||||
- feat(cli): always prefix extension skills with colon separator by
|
||||
@NTaylorMullen in
|
||||
[#23566](https://github.com/google-gemini/gemini-cli/pull/23566)
|
||||
- fix(core): properly support allowRedirect in policy engine by @scidomino in
|
||||
[#23579](https://github.com/google-gemini/gemini-cli/pull/23579)
|
||||
- fix(cli): prevent subcommand shadowing and skip auth for commands by
|
||||
[#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
|
||||
[#23177](https://github.com/google-gemini/gemini-cli/pull/23177)
|
||||
- fix(test): move flaky tests to non-blocking suite by @mattKorwel in
|
||||
[#23259](https://github.com/google-gemini/gemini-cli/pull/23259)
|
||||
- Changelog for v0.35.0-preview.3 by @gemini-cli-robot in
|
||||
[#23574](https://github.com/google-gemini/gemini-cli/pull/23574)
|
||||
- feat(skills): add behavioral-evals skill with fixing and promoting guides by
|
||||
[#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
|
||||
@abhipatel12 in
|
||||
[#23349](https://github.com/google-gemini/gemini-cli/pull/23349)
|
||||
- refactor(core): delete obsolete coreToolScheduler by @abhipatel12 in
|
||||
[#23502](https://github.com/google-gemini/gemini-cli/pull/23502)
|
||||
- Changelog for v0.35.0-preview.4 by @gemini-cli-robot in
|
||||
[#23581](https://github.com/google-gemini/gemini-cli/pull/23581)
|
||||
- feat(core): add LegacyAgentSession by @adamfweidman in
|
||||
[#22986](https://github.com/google-gemini/gemini-cli/pull/22986)
|
||||
- feat(test-utils): add TestMcpServerBuilder and support in TestRig by
|
||||
@abhipatel12 in
|
||||
[#23491](https://github.com/google-gemini/gemini-cli/pull/23491)
|
||||
- fix(core)!: Force policy config to specify toolName by @kschaab in
|
||||
[#23330](https://github.com/google-gemini/gemini-cli/pull/23330)
|
||||
- eval(save_memory): add multi-turn interactive evals for memoryManager by
|
||||
@SandyTao520 in
|
||||
[#23572](https://github.com/google-gemini/gemini-cli/pull/23572)
|
||||
- fix(telemetry): patch memory leak and enforce logPrompts privacy by
|
||||
@spencer426 in
|
||||
[#23281](https://github.com/google-gemini/gemini-cli/pull/23281)
|
||||
- perf(cli): background IDE client to speed up initialization by @sehoon38 in
|
||||
[#23603](https://github.com/google-gemini/gemini-cli/pull/23603)
|
||||
- fix(cli): prevent Ctrl+D exit when input buffer is not empty by @wtanaka in
|
||||
[#23306](https://github.com/google-gemini/gemini-cli/pull/23306)
|
||||
- fix: ACP: separate conversational text from execute tool command title by
|
||||
@sripasg in [#23179](https://github.com/google-gemini/gemini-cli/pull/23179)
|
||||
- feat(evals): add behavioral evaluations for subagent routing by @Samee24 in
|
||||
[#23272](https://github.com/google-gemini/gemini-cli/pull/23272)
|
||||
- refactor(cli,core): foundational layout, identity management, and type safety
|
||||
by @jwhelangoog in
|
||||
[#23286](https://github.com/google-gemini/gemini-cli/pull/23286)
|
||||
- fix(core): accurately reflect subagent tool failure in UI by @abhipatel12 in
|
||||
[#23187](https://github.com/google-gemini/gemini-cli/pull/23187)
|
||||
- Changelog for v0.35.0-preview.5 by @gemini-cli-robot in
|
||||
[#23606](https://github.com/google-gemini/gemini-cli/pull/23606)
|
||||
- feat(ui): implement refreshed UX for Composer layout by @jwhelangoog in
|
||||
[#21212](https://github.com/google-gemini/gemini-cli/pull/21212)
|
||||
- fix: API key input dialog user interaction when selected Gemini API Key by
|
||||
@kartikangiras in
|
||||
[#21057](https://github.com/google-gemini/gemini-cli/pull/21057)
|
||||
- docs: update `/mcp refresh` to `/mcp reload` by @adamfweidman in
|
||||
[#23631](https://github.com/google-gemini/gemini-cli/pull/23631)
|
||||
- Implementation of sandbox "Write-Protected" Governance Files by @DavidAPierce
|
||||
in [#23139](https://github.com/google-gemini/gemini-cli/pull/23139)
|
||||
- feat(sandbox): dynamic macOS sandbox expansion and worktree support by @galz10
|
||||
in [#23301](https://github.com/google-gemini/gemini-cli/pull/23301)
|
||||
- fix(acp): Pass the cwd to `AcpFileSystemService` to avoid looping failures in
|
||||
asking for perms to write plan md file by @sripasg in
|
||||
[#23612](https://github.com/google-gemini/gemini-cli/pull/23612)
|
||||
- fix(plan): sandbox path resolution in Plan Mode to prevent hallucinations by
|
||||
@Adib234 in [#22737](https://github.com/google-gemini/gemini-cli/pull/22737)
|
||||
- feat(ui): allow immediate user input during startup by @sehoon38 in
|
||||
[#23661](https://github.com/google-gemini/gemini-cli/pull/23661)
|
||||
- refactor(sandbox): reorganize Windows sandbox files by @galz10 in
|
||||
[#23645](https://github.com/google-gemini/gemini-cli/pull/23645)
|
||||
- fix(core): improve remote agent streaming UI and UX by @adamfweidman in
|
||||
[#23633](https://github.com/google-gemini/gemini-cli/pull/23633)
|
||||
- perf(cli): optimize --version startup time by @sehoon38 in
|
||||
[#23671](https://github.com/google-gemini/gemini-cli/pull/23671)
|
||||
- refactor(core): stop gemini CLI from producing unsafe casts by @gundermanc in
|
||||
[#23611](https://github.com/google-gemini/gemini-cli/pull/23611)
|
||||
- use enableAutoUpdate in test rig by @scidomino in
|
||||
[#23681](https://github.com/google-gemini/gemini-cli/pull/23681)
|
||||
- feat(core): change user-facing auth type from oauth2 to oauth by @adamfweidman
|
||||
in [#23639](https://github.com/google-gemini/gemini-cli/pull/23639)
|
||||
- chore(deps): fix npm audit vulnerabilities by @scidomino in
|
||||
[#23679](https://github.com/google-gemini/gemini-cli/pull/23679)
|
||||
- test(evals): fix overlapping act() deadlock in app-test-helper by @Adib234 in
|
||||
[#23666](https://github.com/google-gemini/gemini-cli/pull/23666)
|
||||
- fix(patch): cherry-pick 055ff92 to release/v0.36.0-preview.0-pr-23672 to patch
|
||||
version v0.36.0-preview.0 and create version 0.36.0-preview.1 by
|
||||
[#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
|
||||
@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
|
||||
[#23723](https://github.com/google-gemini/gemini-cli/pull/23723)
|
||||
- fix(patch): cherry-pick 765fb67 to release/v0.36.0-preview.5-pr-24055 to patch
|
||||
version v0.36.0-preview.5 and create version 0.36.0-preview.6 by
|
||||
[#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
|
||||
[#24061](https://github.com/google-gemini/gemini-cli/pull/24061)
|
||||
[#24842](https://github.com/google-gemini/gemini-cli/pull/24842)
|
||||
|
||||
**Full Changelog**:
|
||||
https://github.com/google-gemini/gemini-cli/compare/v0.35.3...v0.36.0
|
||||
https://github.com/google-gemini/gemini-cli/compare/v0.36.0...v0.37.0
|
||||
|
||||
+248
-406
@@ -1,6 +1,6 @@
|
||||
# Preview release: v0.37.0-preview.2
|
||||
# Preview release: v0.38.0-preview.0
|
||||
|
||||
Released: April 07, 2026
|
||||
Released: April 08, 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).
|
||||
@@ -13,414 +13,256 @@ npm install -g @google/gemini-cli@preview
|
||||
|
||||
## Highlights
|
||||
|
||||
- **Plan Mode Enhancements**: Plan now includes support for untrusted folders,
|
||||
prioritized pre-approval discussions, and a resolve for sandbox-related
|
||||
deadlocks during file creation.
|
||||
- **Browser Agent Evolved**: Significant updates to the browser agent, including
|
||||
persistent session management, dynamic discovery of read-only tools,
|
||||
sandbox-aware initialization, and automated reclamation of stale snapshots to
|
||||
optimize context window usage.
|
||||
- **Advanced Sandbox Security**: Implementation of dynamic sandbox expansion for
|
||||
both Linux and Windows, alongside secret visibility lockdown for environment
|
||||
files and OS-specific forbidden path support.
|
||||
- **Unified Core Architecture**: Centralized context management and a new
|
||||
`ModelConfigService` for unified model discovery, complemented by the
|
||||
introduction of `AgentHistoryProvider` and tool-based topic grouping
|
||||
(Chapters).
|
||||
- **UI/UX & Performance Improvements**: New Tokyo Night theme, "tab to queue"
|
||||
message support, and compact tool output formatting, plus optimized build
|
||||
scripts and improved layout stability for TUI components.
|
||||
- **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.
|
||||
|
||||
## What's Changed
|
||||
|
||||
- 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)
|
||||
- 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)
|
||||
- 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)
|
||||
[#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-preview.8...v0.37.0-preview.2
|
||||
https://github.com/google-gemini/gemini-cli/compare/v0.37.0-preview.2...v0.38.0-preview.0
|
||||
|
||||
@@ -153,9 +153,9 @@ they appear in the UI.
|
||||
|
||||
### Advanced
|
||||
|
||||
| UI Label | Setting | Description | Default |
|
||||
| --------------------------------- | ------------------------------ | --------------------------------------------- | ------- |
|
||||
| Auto Configure Max Old Space Size | `advanced.autoConfigureMemory` | Automatically configure Node.js memory limits | `true` |
|
||||
| UI Label | Setting | Description | Default |
|
||||
| --------------------------------- | ------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
|
||||
| Auto Configure Max Old Space Size | `advanced.autoConfigureMemory` | Automatically configure Node.js memory limits. Note: Because memory is allocated during the initial process boot, this setting is only read from the global user settings file and ignores workspace-level overrides. | `true` |
|
||||
|
||||
### Experimental
|
||||
|
||||
|
||||
@@ -157,6 +157,48 @@ The harness (`MemoryTestHarness` in `packages/test-utils`):
|
||||
- Compares against baselines with a 10% tolerance.
|
||||
- Can analyze sustained leaks across 3 snapshots using `analyzeSnapshots()`.
|
||||
|
||||
## Performance regression tests
|
||||
|
||||
Performance regression tests are designed to detect wall-clock time, CPU usage,
|
||||
and event loop delay regressions across key CLI scenarios. They are located in
|
||||
the `perf-tests` directory.
|
||||
|
||||
These tests are distinct from standard integration tests because they measure
|
||||
performance metrics and compare it against committed baselines.
|
||||
|
||||
### Running performance tests
|
||||
|
||||
Performance tests are not run as part of the default `npm run test` or
|
||||
`npm run test:e2e` commands. They are run nightly in CI but can be run manually:
|
||||
|
||||
```bash
|
||||
npm run test:perf
|
||||
```
|
||||
|
||||
### Updating baselines
|
||||
|
||||
If you intentionally change behavior that affects performance, you may need to
|
||||
update the baselines. Set the `UPDATE_PERF_BASELINES` environment variable to
|
||||
`true`:
|
||||
|
||||
```bash
|
||||
UPDATE_PERF_BASELINES=true npm run test:perf
|
||||
```
|
||||
|
||||
This will run the tests multiple times (with warmup), apply IQR outlier
|
||||
filtering, and overwrite `perf-tests/baselines.json`. You should review the
|
||||
changes and commit the updated baseline file.
|
||||
|
||||
### How it works
|
||||
|
||||
The harness (`PerfTestHarness` in `packages/test-utils`):
|
||||
|
||||
- Measures wall-clock time using `performance.now()`.
|
||||
- Measures CPU usage using `process.cpuUsage()`.
|
||||
- Monitors event loop delay using `perf_hooks.monitorEventLoopDelay()`.
|
||||
- Applies IQR (Interquartile Range) filtering to remove outlier samples.
|
||||
- Compares against baselines with a 15% tolerance.
|
||||
|
||||
## Diagnostics
|
||||
|
||||
The integration test runner provides several options for diagnostics to help
|
||||
|
||||
@@ -1578,7 +1578,10 @@ their corresponding top-level category object in your `settings.json` file.
|
||||
#### `advanced`
|
||||
|
||||
- **`advanced.autoConfigureMemory`** (boolean):
|
||||
- **Description:** Automatically configure Node.js memory limits
|
||||
- **Description:** Automatically configure Node.js memory limits. Note:
|
||||
Because memory is allocated during the initial process boot, this setting is
|
||||
only read from the global user settings file and ignores workspace-level
|
||||
overrides.
|
||||
- **Default:** `true`
|
||||
- **Requires restart:** Yes
|
||||
|
||||
|
||||
@@ -91,7 +91,7 @@ available combinations.
|
||||
| `input.submit` | Submit the current prompt. | `Enter` |
|
||||
| `input.queueMessage` | Queue the current prompt to be processed after the current task finishes. | `Tab` |
|
||||
| `input.newline` | Insert a newline without submitting. | `Ctrl+Enter`<br />`Cmd/Win+Enter`<br />`Alt+Enter`<br />`Shift+Enter`<br />`Ctrl+J` |
|
||||
| `input.openExternalEditor` | Open the current prompt or the plan in an external editor. | `Ctrl+G` |
|
||||
| `input.openExternalEditor` | Open the current prompt or the plan in an external editor. | `Ctrl+G`<br />`Ctrl+Shift+G` |
|
||||
| `input.deprecatedOpenExternalEditor` | Deprecated command to open external editor. | `Ctrl+X` |
|
||||
| `input.paste` | Paste from the clipboard. | `Ctrl+V`<br />`Cmd/Win+V`<br />`Alt+V` |
|
||||
|
||||
|
||||
@@ -19,6 +19,8 @@ describe('Answer vs. ask eval', () => {
|
||||
* automatically modify the file, but instead asks for permission.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should not edit files when asked to inspect for bugs',
|
||||
prompt: 'Inspect app.ts for bugs',
|
||||
files: FILES,
|
||||
@@ -42,6 +44,8 @@ describe('Answer vs. ask eval', () => {
|
||||
* does modify the file.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should edit files when asked to fix bug',
|
||||
prompt: 'Fix the bug in app.ts - it should add numbers not subtract',
|
||||
files: FILES,
|
||||
@@ -66,6 +70,8 @@ describe('Answer vs. ask eval', () => {
|
||||
* automatically modify the file, but instead asks for permission.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should not edit when asking "any bugs"',
|
||||
prompt: 'Any bugs in app.ts?',
|
||||
files: FILES,
|
||||
@@ -89,6 +95,8 @@ describe('Answer vs. ask eval', () => {
|
||||
* automatically modify the file.
|
||||
*/
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should not edit files when asked a general question',
|
||||
prompt: 'How does app.ts work?',
|
||||
files: FILES,
|
||||
@@ -112,6 +120,8 @@ describe('Answer vs. ask eval', () => {
|
||||
* automatically modify the file.
|
||||
*/
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should not edit files when asked about style',
|
||||
prompt: 'Is app.ts following good style?',
|
||||
files: FILES,
|
||||
@@ -135,6 +145,8 @@ describe('Answer vs. ask eval', () => {
|
||||
* the agent does NOT automatically modify the file.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should not edit files when user notes an issue',
|
||||
prompt: 'The add function subtracts numbers.',
|
||||
files: FILES,
|
||||
|
||||
+49
-49
@@ -10,10 +10,13 @@ import {
|
||||
runEval,
|
||||
prepareLogDir,
|
||||
symlinkNodeModules,
|
||||
withEvalRetries,
|
||||
prepareWorkspace,
|
||||
type BaseEvalCase,
|
||||
EVAL_MODEL,
|
||||
} from './test-helper.js';
|
||||
import fs from 'node:fs';
|
||||
import path from 'node:path';
|
||||
import { DEFAULT_GEMINI_MODEL } from '@google/gemini-cli-core';
|
||||
|
||||
/**
|
||||
* Config overrides for evals, with tool-restriction fields explicitly
|
||||
@@ -29,15 +32,13 @@ interface EvalConfigOverrides {
|
||||
allowedTools?: never;
|
||||
/** Restricting tools via mainAgentTools in evals is forbidden. */
|
||||
mainAgentTools?: never;
|
||||
|
||||
[key: string]: unknown;
|
||||
}
|
||||
|
||||
export interface AppEvalCase {
|
||||
name: string;
|
||||
export interface AppEvalCase extends BaseEvalCase {
|
||||
configOverrides?: EvalConfigOverrides;
|
||||
prompt: string;
|
||||
timeout?: number;
|
||||
files?: Record<string, string>;
|
||||
setup?: (rig: AppRig) => Promise<void>;
|
||||
assert: (rig: AppRig, output: string) => Promise<void>;
|
||||
}
|
||||
@@ -48,56 +49,55 @@ export interface AppEvalCase {
|
||||
*/
|
||||
export function appEvalTest(policy: EvalPolicy, evalCase: AppEvalCase) {
|
||||
const fn = async () => {
|
||||
const rig = new AppRig({
|
||||
configOverrides: {
|
||||
model: DEFAULT_GEMINI_MODEL,
|
||||
...evalCase.configOverrides,
|
||||
},
|
||||
});
|
||||
await withEvalRetries(evalCase.name, async () => {
|
||||
const rig = new AppRig({
|
||||
configOverrides: {
|
||||
model: EVAL_MODEL,
|
||||
...evalCase.configOverrides,
|
||||
},
|
||||
});
|
||||
|
||||
const { logDir, sanitizedName } = await prepareLogDir(evalCase.name);
|
||||
const logFile = path.join(logDir, `${sanitizedName}.log`);
|
||||
const { logDir, sanitizedName } = await prepareLogDir(evalCase.name);
|
||||
const logFile = path.join(logDir, `${sanitizedName}.log`);
|
||||
|
||||
try {
|
||||
await rig.initialize();
|
||||
try {
|
||||
await rig.initialize();
|
||||
|
||||
const testDir = rig.getTestDir();
|
||||
symlinkNodeModules(testDir);
|
||||
const testDir = rig.getTestDir();
|
||||
symlinkNodeModules(testDir);
|
||||
|
||||
// Setup initial files
|
||||
if (evalCase.files) {
|
||||
for (const [filePath, content] of Object.entries(evalCase.files)) {
|
||||
const fullPath = path.join(testDir, filePath);
|
||||
fs.mkdirSync(path.dirname(fullPath), { recursive: true });
|
||||
fs.writeFileSync(fullPath, content);
|
||||
// Setup initial files
|
||||
if (evalCase.files) {
|
||||
// Note: AppRig does not use a separate homeDir, so we use testDir twice
|
||||
await prepareWorkspace(testDir, testDir, evalCase.files);
|
||||
}
|
||||
|
||||
// Run custom setup if provided (e.g. for breakpoints)
|
||||
if (evalCase.setup) {
|
||||
await evalCase.setup(rig);
|
||||
}
|
||||
|
||||
// Render the app!
|
||||
await rig.render();
|
||||
|
||||
// Wait for initial ready state
|
||||
await rig.waitForIdle();
|
||||
|
||||
// Send the initial prompt
|
||||
await rig.sendMessage(evalCase.prompt);
|
||||
|
||||
// Run assertion. Interaction-heavy tests can do their own waiting/steering here.
|
||||
const output = rig.getStaticOutput();
|
||||
await evalCase.assert(rig, output);
|
||||
} finally {
|
||||
const output = rig.getStaticOutput();
|
||||
if (output) {
|
||||
await fs.promises.writeFile(logFile, output);
|
||||
}
|
||||
await rig.unmount();
|
||||
}
|
||||
|
||||
// Run custom setup if provided (e.g. for breakpoints)
|
||||
if (evalCase.setup) {
|
||||
await evalCase.setup(rig);
|
||||
}
|
||||
|
||||
// Render the app!
|
||||
await rig.render();
|
||||
|
||||
// Wait for initial ready state
|
||||
await rig.waitForIdle();
|
||||
|
||||
// Send the initial prompt
|
||||
await rig.sendMessage(evalCase.prompt);
|
||||
|
||||
// Run assertion. Interaction-heavy tests can do their own waiting/steering here.
|
||||
const output = rig.getStaticOutput();
|
||||
await evalCase.assert(rig, output);
|
||||
} finally {
|
||||
const output = rig.getStaticOutput();
|
||||
if (output) {
|
||||
await fs.promises.writeFile(logFile, output);
|
||||
}
|
||||
await rig.unmount();
|
||||
}
|
||||
});
|
||||
};
|
||||
|
||||
runEval(policy, evalCase.name, fn, (evalCase.timeout ?? 60000) + 10000);
|
||||
runEval(policy, evalCase, fn, (evalCase.timeout ?? 60000) + 10000);
|
||||
}
|
||||
|
||||
+18
-6
@@ -5,17 +5,21 @@
|
||||
*/
|
||||
|
||||
import { describe, expect } from 'vitest';
|
||||
import { appEvalTest, AppEvalCase } from './app-test-helper.js';
|
||||
import { EvalPolicy } from './test-helper.js';
|
||||
import { ApprovalMode, isRecord } from '@google/gemini-cli-core';
|
||||
import { appEvalTest, type AppEvalCase } from './app-test-helper.js';
|
||||
import { type EvalPolicy } from './test-helper.js';
|
||||
|
||||
function askUserEvalTest(policy: EvalPolicy, evalCase: AppEvalCase) {
|
||||
const existingGeneral = evalCase.configOverrides?.['general'];
|
||||
const generalBase = isRecord(existingGeneral) ? existingGeneral : {};
|
||||
|
||||
return appEvalTest(policy, {
|
||||
...evalCase,
|
||||
configOverrides: {
|
||||
...evalCase.configOverrides,
|
||||
approvalMode: ApprovalMode.DEFAULT,
|
||||
general: {
|
||||
...evalCase.configOverrides?.general,
|
||||
approvalMode: 'default',
|
||||
...generalBase,
|
||||
enableAutoUpdate: false,
|
||||
enableAutoUpdateNotification: false,
|
||||
},
|
||||
@@ -28,6 +32,8 @@ function askUserEvalTest(policy: EvalPolicy, evalCase: AppEvalCase) {
|
||||
|
||||
describe('ask_user', () => {
|
||||
askUserEvalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'Agent uses AskUser tool to present multiple choice options',
|
||||
prompt: `Use the ask_user tool to ask me what my favorite color is. Provide 3 options: red, green, or blue.`,
|
||||
setup: async (rig) => {
|
||||
@@ -43,6 +49,8 @@ describe('ask_user', () => {
|
||||
});
|
||||
|
||||
askUserEvalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'Agent uses AskUser tool to clarify ambiguous requirements',
|
||||
files: {
|
||||
'package.json': JSON.stringify({ name: 'my-app', version: '1.0.0' }),
|
||||
@@ -61,6 +69,8 @@ describe('ask_user', () => {
|
||||
});
|
||||
|
||||
askUserEvalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'Agent uses AskUser tool before performing significant ambiguous rework',
|
||||
files: {
|
||||
'packages/core/src/index.ts': '// index\nexport const version = "1.0.0";',
|
||||
@@ -82,8 +92,8 @@ describe('ask_user', () => {
|
||||
]);
|
||||
expect(confirmation, 'Expected a tool call confirmation').toBeDefined();
|
||||
|
||||
if (confirmation?.name === 'enter_plan_mode') {
|
||||
rig.acceptConfirmation('enter_plan_mode');
|
||||
if (confirmation?.toolName === 'enter_plan_mode') {
|
||||
await rig.resolveTool('enter_plan_mode');
|
||||
confirmation = await rig.waitForPendingConfirmation('ask_user');
|
||||
}
|
||||
|
||||
@@ -101,6 +111,8 @@ describe('ask_user', () => {
|
||||
// updates to clarify that shell command confirmation is handled by the UI.
|
||||
// See fix: https://github.com/google-gemini/gemini-cli/pull/20504
|
||||
askUserEvalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'Agent does NOT use AskUser to confirm shell commands',
|
||||
files: {
|
||||
'package.json': JSON.stringify({
|
||||
|
||||
@@ -14,6 +14,8 @@ describe('Automated tool use', () => {
|
||||
* a repro by guiding the agent into using the existing deficient script.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should use automated tools (eslint --fix) to fix code style issues',
|
||||
files: {
|
||||
'package.json': JSON.stringify(
|
||||
@@ -102,6 +104,8 @@ describe('Automated tool use', () => {
|
||||
* instead of trying to edit the files itself.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should use automated tools (prettier --write) to fix formatting issues',
|
||||
files: {
|
||||
'package.json': JSON.stringify(
|
||||
|
||||
@@ -3,6 +3,8 @@ import { evalTest } from './test-helper.js';
|
||||
|
||||
describe('CliHelpAgent Delegation', () => {
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should delegate to cli_help agent for subagent creation questions',
|
||||
params: {
|
||||
settings: {
|
||||
|
||||
@@ -0,0 +1,136 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import {
|
||||
type EvalPolicy,
|
||||
runEval,
|
||||
prepareLogDir,
|
||||
withEvalRetries,
|
||||
prepareWorkspace,
|
||||
type BaseEvalCase,
|
||||
} from './test-helper.js';
|
||||
import fs from 'node:fs';
|
||||
import path from 'node:path';
|
||||
import os from 'node:os';
|
||||
import { randomUUID } from 'node:crypto';
|
||||
import {
|
||||
Config,
|
||||
type ConfigParameters,
|
||||
AuthType,
|
||||
ApprovalMode,
|
||||
createPolicyEngineConfig,
|
||||
ExtensionLoader,
|
||||
IntegrityDataStatus,
|
||||
makeFakeConfig,
|
||||
type GeminiCLIExtension,
|
||||
} from '@google/gemini-cli-core';
|
||||
import { createMockSettings } from '../packages/cli/src/test-utils/settings.js';
|
||||
|
||||
// A minimal mock ExtensionManager to bypass integrity checks
|
||||
class MockExtensionManager extends ExtensionLoader {
|
||||
override getExtensions(): GeminiCLIExtension[] {
|
||||
return [];
|
||||
}
|
||||
setRequestConsent = (): void => {};
|
||||
setRequestSetting = (): void => {};
|
||||
integrityManager = {
|
||||
verifyExtensionIntegrity: async (): Promise<IntegrityDataStatus> =>
|
||||
IntegrityDataStatus.VERIFIED,
|
||||
storeExtensionIntegrity: async (): Promise<void> => undefined,
|
||||
};
|
||||
}
|
||||
|
||||
export interface ComponentEvalCase extends BaseEvalCase {
|
||||
configOverrides?: Partial<ConfigParameters>;
|
||||
setup?: (config: Config) => Promise<void>;
|
||||
assert: (config: Config) => Promise<void>;
|
||||
}
|
||||
|
||||
export class ComponentRig {
|
||||
public config: Config | undefined;
|
||||
public testDir: string;
|
||||
public sessionId: string;
|
||||
|
||||
constructor(
|
||||
private options: { configOverrides?: Partial<ConfigParameters> } = {},
|
||||
) {
|
||||
const uniqueId = randomUUID();
|
||||
this.testDir = fs.mkdtempSync(
|
||||
path.join(os.tmpdir(), `gemini-component-rig-${uniqueId.slice(0, 8)}-`),
|
||||
);
|
||||
this.sessionId = `test-session-${uniqueId}`;
|
||||
}
|
||||
|
||||
async initialize() {
|
||||
const settings = createMockSettings();
|
||||
const policyEngineConfig = await createPolicyEngineConfig(
|
||||
settings.merged,
|
||||
ApprovalMode.DEFAULT,
|
||||
);
|
||||
|
||||
const configParams: ConfigParameters = {
|
||||
sessionId: this.sessionId,
|
||||
targetDir: this.testDir,
|
||||
cwd: this.testDir,
|
||||
debugMode: false,
|
||||
model: 'test-model',
|
||||
interactive: false,
|
||||
approvalMode: ApprovalMode.DEFAULT,
|
||||
policyEngineConfig,
|
||||
enableEventDrivenScheduler: false, // Don't need scheduler for direct component tests
|
||||
extensionLoader: new MockExtensionManager(),
|
||||
useAlternateBuffer: false,
|
||||
...this.options.configOverrides,
|
||||
};
|
||||
|
||||
this.config = makeFakeConfig(configParams);
|
||||
await this.config.initialize();
|
||||
|
||||
// Refresh auth using USE_GEMINI to initialize the real BaseLlmClient
|
||||
await this.config.refreshAuth(AuthType.USE_GEMINI);
|
||||
}
|
||||
|
||||
async cleanup() {
|
||||
fs.rmSync(this.testDir, { recursive: true, force: true });
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* A helper for running behavioral evaluations directly against backend components.
|
||||
* It provides a fully initialized Config with real API access, bypassing the UI.
|
||||
*/
|
||||
export function componentEvalTest(
|
||||
policy: EvalPolicy,
|
||||
evalCase: ComponentEvalCase,
|
||||
) {
|
||||
const fn = async () => {
|
||||
await withEvalRetries(evalCase.name, async () => {
|
||||
const rig = new ComponentRig({
|
||||
configOverrides: evalCase.configOverrides,
|
||||
});
|
||||
|
||||
await prepareLogDir(evalCase.name);
|
||||
|
||||
try {
|
||||
await rig.initialize();
|
||||
|
||||
if (evalCase.files) {
|
||||
await prepareWorkspace(rig.testDir, rig.testDir, evalCase.files);
|
||||
}
|
||||
|
||||
if (evalCase.setup) {
|
||||
await evalCase.setup(rig.config!);
|
||||
}
|
||||
|
||||
await evalCase.assert(rig.config!);
|
||||
} finally {
|
||||
await rig.cleanup();
|
||||
}
|
||||
});
|
||||
};
|
||||
|
||||
runEval(policy, evalCase, fn, (evalCase.timeout ?? 60000) + 10000);
|
||||
}
|
||||
@@ -20,6 +20,8 @@ You are the mutation agent. Do the mutation requested.
|
||||
|
||||
describe('concurrency safety eval test cases', () => {
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'mutation agents are run in parallel when explicitly requested',
|
||||
params: {
|
||||
settings: {
|
||||
|
||||
@@ -13,6 +13,8 @@ describe('Edits location eval', () => {
|
||||
* instead of creating a new one.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should update existing test file instead of creating a new one',
|
||||
files: {
|
||||
'package.json': JSON.stringify(
|
||||
|
||||
@@ -15,6 +15,8 @@ describe('Frugal reads eval', () => {
|
||||
* nearby ranges into a single contiguous read to save tool calls.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should use ranged read when nearby lines are targeted',
|
||||
files: {
|
||||
'package.json': JSON.stringify({
|
||||
@@ -135,6 +137,8 @@ describe('Frugal reads eval', () => {
|
||||
* apart to avoid the need to read the whole file.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should use ranged read when targets are far apart',
|
||||
files: {
|
||||
'package.json': JSON.stringify({
|
||||
@@ -204,6 +208,8 @@ describe('Frugal reads eval', () => {
|
||||
* (e.g.: 10), as it's more efficient than many small ranged reads.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should read the entire file when there are many matches',
|
||||
files: {
|
||||
'package.json': JSON.stringify({
|
||||
|
||||
@@ -13,18 +13,6 @@ import { evalTest } from './test-helper.js';
|
||||
* This ensures the agent doesn't flood the context window with unnecessary search results.
|
||||
*/
|
||||
describe('Frugal Search', () => {
|
||||
const getGrepParams = (call: any): any => {
|
||||
let args = call.toolRequest.args;
|
||||
if (typeof args === 'string') {
|
||||
try {
|
||||
args = JSON.parse(args);
|
||||
} catch (e) {
|
||||
// Ignore parse errors
|
||||
}
|
||||
}
|
||||
return args;
|
||||
};
|
||||
|
||||
/**
|
||||
* Ensure that the agent makes use of either grep or ranged reads in fulfilling this task.
|
||||
* The task is specifically phrased to not evoke "view" or "search" specifically because
|
||||
@@ -33,6 +21,8 @@ describe('Frugal Search', () => {
|
||||
* ranged reads.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should use grep or ranged read for large files',
|
||||
prompt: 'What year was legacy_processor.ts written?',
|
||||
files: {
|
||||
|
||||
@@ -11,6 +11,8 @@ import fs from 'node:fs/promises';
|
||||
|
||||
describe('generalist_agent', () => {
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should be able to use generalist agent by explicitly asking the main agent to invoke it',
|
||||
params: {
|
||||
settings: {
|
||||
|
||||
@@ -11,6 +11,8 @@ describe('generalist_delegation', () => {
|
||||
// --- Positive Evals (Should Delegate) ---
|
||||
|
||||
appEvalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should delegate batch error fixing to generalist agent',
|
||||
configOverrides: {
|
||||
agents: {
|
||||
@@ -54,6 +56,8 @@ describe('generalist_delegation', () => {
|
||||
});
|
||||
|
||||
appEvalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should autonomously delegate complex batch task to generalist agent',
|
||||
configOverrides: {
|
||||
agents: {
|
||||
@@ -94,6 +98,8 @@ describe('generalist_delegation', () => {
|
||||
// --- Negative Evals (Should NOT Delegate - Assertive Handling) ---
|
||||
|
||||
appEvalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should NOT delegate simple read and fix to generalist agent',
|
||||
configOverrides: {
|
||||
agents: {
|
||||
@@ -128,6 +134,8 @@ describe('generalist_delegation', () => {
|
||||
});
|
||||
|
||||
appEvalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should NOT delegate simple direct question to generalist agent',
|
||||
configOverrides: {
|
||||
agents: {
|
||||
|
||||
@@ -26,6 +26,8 @@ describe('git repo eval', () => {
|
||||
* be more consistent.
|
||||
*/
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should not git add commit changes unprompted',
|
||||
prompt:
|
||||
'Finish this up for me by just making a targeted fix for the bug in index.ts. Do not build, install anything, or add tests',
|
||||
@@ -55,6 +57,8 @@ describe('git repo eval', () => {
|
||||
* instructed to not do so by default.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should git commit changes when prompted',
|
||||
prompt:
|
||||
'Make a targeted fix for the bug in index.ts without building, installing anything, or adding tests. Then, commit your changes.',
|
||||
|
||||
@@ -15,6 +15,8 @@ describe('grep_search_functionality', () => {
|
||||
const TEST_PREFIX = 'Grep Search Functionality: ';
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should find a simple string in a file',
|
||||
files: {
|
||||
'test.txt': `hello
|
||||
@@ -33,6 +35,8 @@ describe('grep_search_functionality', () => {
|
||||
});
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should perform a case-sensitive search',
|
||||
files: {
|
||||
'test.txt': `Hello
|
||||
@@ -63,6 +67,8 @@ describe('grep_search_functionality', () => {
|
||||
});
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should return only file names when names_only is used',
|
||||
files: {
|
||||
'file1.txt': 'match me',
|
||||
@@ -93,6 +99,8 @@ describe('grep_search_functionality', () => {
|
||||
});
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should search only within the specified include_pattern glob',
|
||||
files: {
|
||||
'file.js': 'my_function();',
|
||||
@@ -123,6 +131,8 @@ describe('grep_search_functionality', () => {
|
||||
});
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should search within a specific subdirectory',
|
||||
files: {
|
||||
'src/main.js': 'unique_string_1',
|
||||
@@ -153,6 +163,8 @@ describe('grep_search_functionality', () => {
|
||||
});
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should report no matches correctly',
|
||||
files: {
|
||||
'file.txt': 'nothing to see here',
|
||||
|
||||
@@ -5,13 +5,14 @@
|
||||
*/
|
||||
|
||||
import { describe, expect } from 'vitest';
|
||||
import { evalTest } from './test-helper.js';
|
||||
import { assertModelHasOutput } from '../integration-tests/test-helper.js';
|
||||
import { evalTest, assertModelHasOutput } from './test-helper.js';
|
||||
|
||||
describe('Hierarchical Memory', () => {
|
||||
const conflictResolutionTest =
|
||||
'Agent follows hierarchy for contradictory instructions';
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: conflictResolutionTest,
|
||||
params: {
|
||||
settings: {
|
||||
@@ -48,6 +49,8 @@ What is my favorite fruit? Tell me just the name of the fruit.`,
|
||||
|
||||
const provenanceAwarenessTest = 'Agent is aware of memory provenance';
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: provenanceAwarenessTest,
|
||||
params: {
|
||||
settings: {
|
||||
@@ -87,6 +90,8 @@ Provide the answer as an XML block like this:
|
||||
|
||||
const extensionVsGlobalTest = 'Extension memory wins over Global memory';
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: extensionVsGlobalTest,
|
||||
params: {
|
||||
settings: {
|
||||
|
||||
@@ -8,6 +8,8 @@ describe('interactive_commands', () => {
|
||||
* intervention.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should not use interactive commands',
|
||||
prompt: 'Execute tests.',
|
||||
files: {
|
||||
@@ -49,6 +51,8 @@ describe('interactive_commands', () => {
|
||||
* Validates that the agent uses non-interactive flags when scaffolding a new project.
|
||||
*/
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should use non-interactive flags when scaffolding a new app',
|
||||
prompt: 'Create a new react application named my-app using vite.',
|
||||
assert: async (rig, result) => {
|
||||
|
||||
@@ -5,14 +5,14 @@
|
||||
*/
|
||||
|
||||
import { describe, expect } from 'vitest';
|
||||
import { act } from 'react';
|
||||
import path from 'node:path';
|
||||
import fs from 'node:fs';
|
||||
import { appEvalTest } from './app-test-helper.js';
|
||||
import { PolicyDecision } from '@google/gemini-cli-core';
|
||||
|
||||
describe('Model Steering Behavioral Evals', () => {
|
||||
appEvalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'Corrective Hint: Model switches task based on hint during tool turn',
|
||||
configOverrides: {
|
||||
modelSteering: true,
|
||||
@@ -52,6 +52,8 @@ describe('Model Steering Behavioral Evals', () => {
|
||||
});
|
||||
|
||||
appEvalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'Suggestive Hint: Model incorporates user guidance mid-stream',
|
||||
configOverrides: {
|
||||
modelSteering: true,
|
||||
|
||||
@@ -33,6 +33,8 @@ describe('plan_mode', () => {
|
||||
.filter(Boolean);
|
||||
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should refuse file modification when in plan mode',
|
||||
approvalMode: ApprovalMode.PLAN,
|
||||
params: {
|
||||
@@ -68,6 +70,8 @@ describe('plan_mode', () => {
|
||||
});
|
||||
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should refuse saving new documentation to the repo when in plan mode',
|
||||
approvalMode: ApprovalMode.PLAN,
|
||||
params: {
|
||||
@@ -105,6 +109,8 @@ describe('plan_mode', () => {
|
||||
});
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should enter plan mode when asked to create a plan',
|
||||
approvalMode: ApprovalMode.DEFAULT,
|
||||
params: {
|
||||
@@ -122,6 +128,8 @@ describe('plan_mode', () => {
|
||||
});
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should exit plan mode when plan is complete and implementation is requested',
|
||||
approvalMode: ApprovalMode.PLAN,
|
||||
params: {
|
||||
@@ -169,6 +177,8 @@ describe('plan_mode', () => {
|
||||
});
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should allow file modification in plans directory when in plan mode',
|
||||
approvalMode: ApprovalMode.PLAN,
|
||||
params: {
|
||||
@@ -201,6 +211,8 @@ describe('plan_mode', () => {
|
||||
});
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should create a plan in plan mode and implement it for a refactoring task',
|
||||
params: {
|
||||
settings,
|
||||
|
||||
@@ -11,6 +11,8 @@ import fs from 'node:fs/promises';
|
||||
|
||||
describe('redundant_casts', () => {
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should not add redundant or unsafe casts when modifying typescript code',
|
||||
files: {
|
||||
'src/cast_example.ts': `
|
||||
|
||||
@@ -3,6 +3,8 @@ import { evalTest } from './test-helper.js';
|
||||
|
||||
describe('Sandbox recovery', () => {
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'attempts to use additional_permissions when operation not permitted',
|
||||
prompt:
|
||||
'Run ./script.sh. It will fail with "Operation not permitted". When it does, you must retry running it by passing the appropriate additional_permissions.',
|
||||
|
||||
@@ -5,16 +5,18 @@
|
||||
*/
|
||||
|
||||
import { describe, expect } from 'vitest';
|
||||
import { evalTest } from './test-helper.js';
|
||||
import {
|
||||
evalTest,
|
||||
assertModelHasOutput,
|
||||
checkModelOutputContent,
|
||||
} from '../integration-tests/test-helper.js';
|
||||
} from './test-helper.js';
|
||||
|
||||
describe('save_memory', () => {
|
||||
const TEST_PREFIX = 'Save memory test: ';
|
||||
const rememberingFavoriteColor = "Agent remembers user's favorite color";
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: rememberingFavoriteColor,
|
||||
|
||||
prompt: `remember that my favorite color is blue.
|
||||
@@ -35,6 +37,8 @@ describe('save_memory', () => {
|
||||
});
|
||||
const rememberingCommandRestrictions = 'Agent remembers command restrictions';
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: rememberingCommandRestrictions,
|
||||
|
||||
prompt: `I don't want you to ever run npm commands.`,
|
||||
@@ -54,6 +58,8 @@ describe('save_memory', () => {
|
||||
|
||||
const rememberingWorkflow = 'Agent remembers workflow preferences';
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: rememberingWorkflow,
|
||||
|
||||
prompt: `I want you to always lint after building.`,
|
||||
@@ -74,6 +80,8 @@ describe('save_memory', () => {
|
||||
const ignoringTemporaryInformation =
|
||||
'Agent ignores temporary conversation details';
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: ignoringTemporaryInformation,
|
||||
|
||||
prompt: `I'm going to get a coffee.`,
|
||||
@@ -97,6 +105,8 @@ describe('save_memory', () => {
|
||||
|
||||
const rememberingPetName = "Agent remembers user's pet's name";
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: rememberingPetName,
|
||||
|
||||
prompt: `Please remember that my dog's name is Buddy.`,
|
||||
@@ -116,6 +126,8 @@ describe('save_memory', () => {
|
||||
|
||||
const rememberingCommandAlias = 'Agent remembers custom command aliases';
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: rememberingCommandAlias,
|
||||
|
||||
prompt: `When I say 'start server', you should run 'npm run dev'.`,
|
||||
@@ -136,6 +148,8 @@ describe('save_memory', () => {
|
||||
const ignoringDbSchemaLocation =
|
||||
"Agent ignores workspace's database schema location";
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: ignoringDbSchemaLocation,
|
||||
prompt: `The database schema for this workspace is located in \`db/schema.sql\`.`,
|
||||
assert: async (rig, result) => {
|
||||
@@ -155,6 +169,8 @@ describe('save_memory', () => {
|
||||
const rememberingCodingStyle =
|
||||
"Agent remembers user's coding style preference";
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: rememberingCodingStyle,
|
||||
|
||||
prompt: `I prefer to use tabs instead of spaces for indentation.`,
|
||||
@@ -175,6 +191,8 @@ describe('save_memory', () => {
|
||||
const ignoringBuildArtifactLocation =
|
||||
'Agent ignores workspace build artifact location';
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: ignoringBuildArtifactLocation,
|
||||
prompt: `In this workspace, build artifacts are stored in the \`dist/artifacts\` directory.`,
|
||||
assert: async (rig, result) => {
|
||||
@@ -193,6 +211,8 @@ describe('save_memory', () => {
|
||||
|
||||
const ignoringMainEntryPoint = "Agent ignores workspace's main entry point";
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: ignoringMainEntryPoint,
|
||||
prompt: `The main entry point for this workspace is \`src/index.js\`.`,
|
||||
assert: async (rig, result) => {
|
||||
@@ -211,6 +231,8 @@ describe('save_memory', () => {
|
||||
|
||||
const rememberingBirthday = "Agent remembers user's birthday";
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: rememberingBirthday,
|
||||
|
||||
prompt: `My birthday is on June 15th.`,
|
||||
@@ -231,6 +253,8 @@ describe('save_memory', () => {
|
||||
const proactiveMemoryFromLongSession =
|
||||
'Agent saves preference from earlier in conversation history';
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: proactiveMemoryFromLongSession,
|
||||
params: {
|
||||
settings: {
|
||||
@@ -309,6 +333,8 @@ describe('save_memory', () => {
|
||||
const memoryManagerRoutingPreferences =
|
||||
'Agent routes global and project preferences to memory';
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: memoryManagerRoutingPreferences,
|
||||
params: {
|
||||
settings: {
|
||||
|
||||
@@ -21,6 +21,8 @@ describe('Shell Efficiency', () => {
|
||||
};
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should use --silent/--quiet flags when installing packages',
|
||||
prompt: 'Install the "lodash" package using npm.',
|
||||
assert: async (rig) => {
|
||||
@@ -50,6 +52,8 @@ describe('Shell Efficiency', () => {
|
||||
});
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should use --no-pager with git commands',
|
||||
prompt: 'Show the git log.',
|
||||
assert: async (rig) => {
|
||||
@@ -73,6 +77,8 @@ describe('Shell Efficiency', () => {
|
||||
});
|
||||
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should NOT use efficiency flags when enableShellOutputEfficiency is disabled',
|
||||
params: {
|
||||
settings: {
|
||||
|
||||
@@ -45,6 +45,8 @@ describe('subagent eval test cases', () => {
|
||||
* This tests the system prompt's subagent specific clauses.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should delegate to user provided agent with relevant expertise',
|
||||
params: {
|
||||
settings: {
|
||||
@@ -69,6 +71,8 @@ describe('subagent eval test cases', () => {
|
||||
* subagents are available. This helps catch orchestration overuse.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should avoid delegating trivial direct edit work',
|
||||
params: {
|
||||
settings: {
|
||||
@@ -113,6 +117,8 @@ describe('subagent eval test cases', () => {
|
||||
* This is meant to codify the "overusing Generalist" failure mode.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should prefer relevant specialist over generalist',
|
||||
params: {
|
||||
settings: {
|
||||
@@ -149,6 +155,8 @@ describe('subagent eval test cases', () => {
|
||||
* naturally spans docs and tests, so multiple specialists should be used.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should use multiple relevant specialists for multi-surface task',
|
||||
params: {
|
||||
settings: {
|
||||
@@ -193,6 +201,8 @@ describe('subagent eval test cases', () => {
|
||||
* from a large pool of available subagents (10 total).
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should select the correct subagent from a pool of 10 different agents',
|
||||
prompt: 'Please add a new SQL table migration for a user profile.',
|
||||
files: {
|
||||
@@ -243,6 +253,8 @@ describe('subagent eval test cases', () => {
|
||||
* This test includes stress tests the subagent delegation with ~80 tools.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should select the correct subagent from a pool of 10 different agents with MCP tools present',
|
||||
prompt: 'Please add a new SQL table migration for a user profile.',
|
||||
setup: async (rig) => {
|
||||
|
||||
@@ -49,6 +49,8 @@ describe('evalTest reliability logic', () => {
|
||||
|
||||
// Execute the test function directly
|
||||
await internalEvalTest({
|
||||
suiteName: 'test',
|
||||
suiteType: 'behavioral',
|
||||
name: 'test-api-failure',
|
||||
prompt: 'do something',
|
||||
assert: async () => {},
|
||||
@@ -83,6 +85,8 @@ describe('evalTest reliability logic', () => {
|
||||
// Expect the test function to throw immediately
|
||||
await expect(
|
||||
internalEvalTest({
|
||||
suiteName: 'test',
|
||||
suiteType: 'behavioral',
|
||||
name: 'test-logic-failure',
|
||||
prompt: 'do something',
|
||||
assert: async () => {
|
||||
@@ -108,6 +112,8 @@ describe('evalTest reliability logic', () => {
|
||||
.mockResolvedValueOnce('Success');
|
||||
|
||||
await internalEvalTest({
|
||||
suiteName: 'test',
|
||||
suiteType: 'behavioral',
|
||||
name: 'test-recovery',
|
||||
prompt: 'do something',
|
||||
assert: async () => {},
|
||||
@@ -135,6 +141,8 @@ describe('evalTest reliability logic', () => {
|
||||
);
|
||||
|
||||
await internalEvalTest({
|
||||
suiteName: 'test',
|
||||
suiteType: 'behavioral',
|
||||
name: 'test-api-503',
|
||||
prompt: 'do something',
|
||||
assert: async () => {},
|
||||
@@ -162,6 +170,8 @@ describe('evalTest reliability logic', () => {
|
||||
try {
|
||||
await expect(
|
||||
internalEvalTest({
|
||||
suiteName: 'test',
|
||||
suiteType: 'behavioral',
|
||||
name: 'test-absolute-path',
|
||||
prompt: 'do something',
|
||||
files: {
|
||||
@@ -190,6 +200,8 @@ describe('evalTest reliability logic', () => {
|
||||
try {
|
||||
await expect(
|
||||
internalEvalTest({
|
||||
suiteName: 'test',
|
||||
suiteType: 'behavioral',
|
||||
name: 'test-traversal',
|
||||
prompt: 'do something',
|
||||
files: {
|
||||
|
||||
+94
-54
@@ -16,10 +16,19 @@ import {
|
||||
Storage,
|
||||
getProjectHash,
|
||||
SESSION_FILE_PREFIX,
|
||||
PREVIEW_GEMINI_FLASH_MODEL,
|
||||
getErrorMessage,
|
||||
} from '@google/gemini-cli-core';
|
||||
|
||||
export * from '@google/gemini-cli-test-utils';
|
||||
|
||||
/**
|
||||
* The default model used for all evaluations.
|
||||
* Can be overridden by setting the GEMINI_MODEL environment variable.
|
||||
*/
|
||||
export const EVAL_MODEL =
|
||||
process.env['GEMINI_MODEL'] || PREVIEW_GEMINI_FLASH_MODEL;
|
||||
|
||||
// Indicates the consistency expectation for this test.
|
||||
// - ALWAYS_PASSES - Means that the test is expected to pass 100% of the time. These
|
||||
// These tests are typically trivial and test basic functionality with unambiguous
|
||||
@@ -39,19 +48,49 @@ export * from '@google/gemini-cli-test-utils';
|
||||
export type EvalPolicy = 'ALWAYS_PASSES' | 'USUALLY_PASSES';
|
||||
|
||||
export function evalTest(policy: EvalPolicy, evalCase: EvalCase) {
|
||||
runEval(
|
||||
policy,
|
||||
evalCase.name,
|
||||
() => internalEvalTest(evalCase),
|
||||
evalCase.timeout,
|
||||
);
|
||||
runEval(policy, evalCase, () => internalEvalTest(evalCase));
|
||||
}
|
||||
|
||||
export async function internalEvalTest(evalCase: EvalCase) {
|
||||
export async function withEvalRetries(
|
||||
name: string,
|
||||
attemptFn: (attempt: number) => Promise<void>,
|
||||
) {
|
||||
const maxRetries = 3;
|
||||
let attempt = 0;
|
||||
|
||||
while (attempt <= maxRetries) {
|
||||
try {
|
||||
await attemptFn(attempt);
|
||||
return; // Success! Exit the retry loop.
|
||||
} catch (error: unknown) {
|
||||
const errorMessage = getErrorMessage(error);
|
||||
const errorCode = getApiErrorCode(errorMessage);
|
||||
|
||||
if (errorCode) {
|
||||
const status = attempt < maxRetries ? 'RETRY' : 'SKIP';
|
||||
logReliabilityEvent(name, attempt, status, errorCode, errorMessage);
|
||||
|
||||
if (attempt < maxRetries) {
|
||||
attempt++;
|
||||
console.warn(
|
||||
`[Eval] Attempt ${attempt} failed with ${errorCode} Error. Retrying...`,
|
||||
);
|
||||
continue; // Retry
|
||||
}
|
||||
|
||||
console.warn(
|
||||
`[Eval] '${name}' failed after ${maxRetries} retries due to persistent API errors. Skipping failure to avoid blocking PR.`,
|
||||
);
|
||||
return; // Gracefully exit without failing the test
|
||||
}
|
||||
|
||||
throw error; // Real failure
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
export async function internalEvalTest(evalCase: EvalCase) {
|
||||
await withEvalRetries(evalCase.name, async () => {
|
||||
const rig = new TestRig();
|
||||
const { logDir, sanitizedName } = await prepareLogDir(evalCase.name);
|
||||
const activityLogFile = path.join(logDir, `${sanitizedName}.jsonl`);
|
||||
@@ -59,14 +98,21 @@ export async function internalEvalTest(evalCase: EvalCase) {
|
||||
let isSuccess = false;
|
||||
|
||||
try {
|
||||
rig.setup(evalCase.name, evalCase.params);
|
||||
const setupOptions = {
|
||||
...evalCase.params,
|
||||
settings: {
|
||||
model: { name: EVAL_MODEL },
|
||||
...evalCase.params?.settings,
|
||||
},
|
||||
};
|
||||
rig.setup(evalCase.name, setupOptions);
|
||||
|
||||
if (evalCase.setup) {
|
||||
await evalCase.setup(rig);
|
||||
}
|
||||
|
||||
if (evalCase.files) {
|
||||
await setupTestFiles(rig, evalCase.files);
|
||||
await prepareWorkspace(rig.testDir!, rig.homeDir!, evalCase.files);
|
||||
}
|
||||
|
||||
symlinkNodeModules(rig.testDir || '');
|
||||
@@ -139,37 +185,6 @@ export async function internalEvalTest(evalCase: EvalCase) {
|
||||
|
||||
await evalCase.assert(rig, result);
|
||||
isSuccess = true;
|
||||
return; // Success! Exit the retry loop.
|
||||
} catch (error: unknown) {
|
||||
const errorMessage =
|
||||
error instanceof Error ? error.message : String(error);
|
||||
const errorCode = getApiErrorCode(errorMessage);
|
||||
|
||||
if (errorCode) {
|
||||
const status = attempt < maxRetries ? 'RETRY' : 'SKIP';
|
||||
logReliabilityEvent(
|
||||
evalCase.name,
|
||||
attempt,
|
||||
status,
|
||||
errorCode,
|
||||
errorMessage,
|
||||
);
|
||||
|
||||
if (attempt < maxRetries) {
|
||||
attempt++;
|
||||
console.warn(
|
||||
`[Eval] Attempt ${attempt} failed with ${errorCode} Error. Retrying...`,
|
||||
);
|
||||
continue; // Retry
|
||||
}
|
||||
|
||||
console.warn(
|
||||
`[Eval] '${evalCase.name}' failed after ${maxRetries} retries due to persistent API errors. Skipping failure to avoid blocking PR.`,
|
||||
);
|
||||
return; // Gracefully exit without failing the test
|
||||
}
|
||||
|
||||
throw error; // Real failure
|
||||
} finally {
|
||||
if (isSuccess) {
|
||||
await fs.promises.unlink(activityLogFile).catch((err) => {
|
||||
@@ -188,7 +203,7 @@ export async function internalEvalTest(evalCase: EvalCase) {
|
||||
);
|
||||
await rig.cleanup();
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
function getApiErrorCode(message: string): '500' | '503' | undefined {
|
||||
@@ -226,7 +241,7 @@ function logReliabilityEvent(
|
||||
const reliabilityLog = {
|
||||
timestamp: new Date().toISOString(),
|
||||
testName,
|
||||
model: process.env.GEMINI_MODEL || 'unknown',
|
||||
model: process.env['GEMINI_MODEL'] || 'unknown',
|
||||
attempt,
|
||||
status,
|
||||
errorCode,
|
||||
@@ -252,9 +267,13 @@ function logReliabilityEvent(
|
||||
* intentionally uses synchronous filesystem and child_process operations
|
||||
* for simplicity and to ensure sequential environment preparation.
|
||||
*/
|
||||
async function setupTestFiles(rig: TestRig, files: Record<string, string>) {
|
||||
export async function prepareWorkspace(
|
||||
testDir: string,
|
||||
homeDir: string,
|
||||
files: Record<string, string>,
|
||||
) {
|
||||
const acknowledgedAgents: Record<string, Record<string, string>> = {};
|
||||
const projectRoot = fs.realpathSync(rig.testDir!);
|
||||
const projectRoot = fs.realpathSync(testDir);
|
||||
|
||||
for (const [filePath, content] of Object.entries(files)) {
|
||||
if (filePath.includes('..') || path.isAbsolute(filePath)) {
|
||||
@@ -290,7 +309,7 @@ async function setupTestFiles(rig: TestRig, files: Record<string, string>) {
|
||||
|
||||
if (Object.keys(acknowledgedAgents).length > 0) {
|
||||
const ackPath = path.join(
|
||||
rig.homeDir!,
|
||||
homeDir,
|
||||
'.gemini',
|
||||
'acknowledgments',
|
||||
'agents.json',
|
||||
@@ -299,7 +318,7 @@ async function setupTestFiles(rig: TestRig, files: Record<string, string>) {
|
||||
fs.writeFileSync(ackPath, JSON.stringify(acknowledgedAgents, null, 2));
|
||||
}
|
||||
|
||||
const execOptions = { cwd: rig.testDir!, stdio: 'inherit' as const };
|
||||
const execOptions = { cwd: testDir, stdio: 'ignore' as const };
|
||||
execSync('git init --initial-branch=main', execOptions);
|
||||
execSync('git config user.email "test@example.com"', execOptions);
|
||||
execSync('git config user.name "Test User"', execOptions);
|
||||
@@ -320,14 +339,30 @@ async function setupTestFiles(rig: TestRig, files: Record<string, string>) {
|
||||
*/
|
||||
export function runEval(
|
||||
policy: EvalPolicy,
|
||||
name: string,
|
||||
evalCase: BaseEvalCase,
|
||||
fn: () => Promise<void>,
|
||||
timeout?: number,
|
||||
timeoutOverride?: number,
|
||||
) {
|
||||
if (policy === 'USUALLY_PASSES' && !process.env['RUN_EVALS']) {
|
||||
it.skip(name, fn);
|
||||
const { name, timeout, suiteName, suiteType } = evalCase;
|
||||
const targetSuiteType = process.env['EVAL_SUITE_TYPE'];
|
||||
const targetSuiteName = process.env['EVAL_SUITE_NAME'];
|
||||
|
||||
const meta = { suiteType, suiteName };
|
||||
|
||||
const skipBySuiteType =
|
||||
targetSuiteType && suiteType && suiteType !== targetSuiteType;
|
||||
const skipBySuiteName =
|
||||
targetSuiteName && suiteName && suiteName !== targetSuiteName;
|
||||
|
||||
const options = { timeout: timeoutOverride ?? timeout, meta };
|
||||
if (
|
||||
(policy === 'USUALLY_PASSES' && !process.env['RUN_EVALS']) ||
|
||||
skipBySuiteType ||
|
||||
skipBySuiteName
|
||||
) {
|
||||
it.skip(name, options, fn);
|
||||
} else {
|
||||
it(name, fn, timeout);
|
||||
it(name, options, fn);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -366,15 +401,20 @@ interface ForbiddenToolSettings {
|
||||
};
|
||||
}
|
||||
|
||||
export interface EvalCase {
|
||||
export interface BaseEvalCase {
|
||||
suiteName: string;
|
||||
suiteType: 'behavioral' | 'component-level' | 'hero-scenario';
|
||||
name: string;
|
||||
timeout?: number;
|
||||
files?: Record<string, string>;
|
||||
}
|
||||
|
||||
export interface EvalCase extends BaseEvalCase {
|
||||
params?: {
|
||||
settings?: ForbiddenToolSettings & Record<string, unknown>;
|
||||
[key: string]: unknown;
|
||||
};
|
||||
prompt: string;
|
||||
timeout?: number;
|
||||
files?: Record<string, string>;
|
||||
setup?: (rig: TestRig) => Promise<void> | void;
|
||||
/** Conversation history to pre-load via --resume. Each entry is a message object with type, content, etc. */
|
||||
messages?: Record<string, unknown>[];
|
||||
|
||||
@@ -31,6 +31,8 @@ describe('Tool Output Masking Behavioral Evals', () => {
|
||||
* It should recognize the <tool_output_masked> tag and use a tool to read the file.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should attempt to read the redirected full output file when information is masked',
|
||||
params: {
|
||||
security: {
|
||||
@@ -167,6 +169,8 @@ Output too large. Full output available at: ${outputFilePath}
|
||||
* Scenario: Information is in the preview.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should NOT read the full output file when the information is already in the preview',
|
||||
params: {
|
||||
security: {
|
||||
|
||||
@@ -25,6 +25,8 @@ const FILES = {
|
||||
|
||||
describe('tracker_mode', () => {
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should manage tasks in the tracker when explicitly requested during a bug fix',
|
||||
params: {
|
||||
settings: { experimental: { taskTracker: true } },
|
||||
@@ -78,6 +80,8 @@ describe('tracker_mode', () => {
|
||||
});
|
||||
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should implicitly create tasks when asked to build a feature plan',
|
||||
params: {
|
||||
settings: { experimental: { taskTracker: true } },
|
||||
|
||||
@@ -9,6 +9,8 @@ import { evalTest } from './test-helper.js';
|
||||
|
||||
describe('validation_fidelity', () => {
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should perform exhaustive validation autonomously when guided by system instructions',
|
||||
files: {
|
||||
'src/types.ts': `
|
||||
|
||||
@@ -9,6 +9,8 @@ import { evalTest } from './test-helper.js';
|
||||
|
||||
describe('validation_fidelity_pre_existing_errors', () => {
|
||||
evalTest('USUALLY_PASSES', {
|
||||
suiteName: 'default',
|
||||
suiteType: 'behavioral',
|
||||
name: 'should handle pre-existing project errors gracefully during validation',
|
||||
files: {
|
||||
'src/math.ts': `
|
||||
|
||||
@@ -24,7 +24,10 @@ export default defineConfig({
|
||||
environment: 'node',
|
||||
globals: true,
|
||||
alias: {
|
||||
react: path.resolve(__dirname, '../node_modules/react'),
|
||||
'@google/gemini-cli-core': path.resolve(
|
||||
__dirname,
|
||||
'../packages/core/index.ts',
|
||||
),
|
||||
},
|
||||
setupFiles: [path.resolve(__dirname, '../packages/cli/test-setup.ts')],
|
||||
server: {
|
||||
|
||||
@@ -14,6 +14,7 @@ import { join, dirname, extname } from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import { canUseRipgrep } from '../packages/core/src/tools/ripGrep.js';
|
||||
import { disableMouseTracking } from '@google/gemini-cli-core';
|
||||
import { isolateTestEnv } from '../packages/test-utils/src/env-setup.js';
|
||||
import { createServer, type Server } from 'node:http';
|
||||
|
||||
const __dirname = dirname(fileURLToPath(import.meta.url));
|
||||
@@ -88,15 +89,8 @@ export async function setup() {
|
||||
runDir = join(integrationTestsDir, `${Date.now()}`);
|
||||
await mkdir(runDir, { recursive: true });
|
||||
|
||||
// Set the home directory to the test run directory to avoid conflicts
|
||||
// with the user's local config.
|
||||
process.env['HOME'] = runDir;
|
||||
if (process.platform === 'win32') {
|
||||
process.env['USERPROFILE'] = runDir;
|
||||
}
|
||||
// We also need to set the config dir explicitly, since the code might
|
||||
// construct the path before the HOME env var is set.
|
||||
process.env['GEMINI_CONFIG_DIR'] = join(runDir, '.gemini');
|
||||
// Isolate environment variables
|
||||
isolateTestEnv(runDir);
|
||||
|
||||
// Download ripgrep to avoid race conditions in parallel tests
|
||||
const available = await canUseRipgrep();
|
||||
@@ -127,10 +121,6 @@ export async function setup() {
|
||||
}
|
||||
|
||||
process.env['INTEGRATION_TEST_FILE_DIR'] = runDir;
|
||||
process.env['GEMINI_CLI_INTEGRATION_TEST'] = 'true';
|
||||
// Force file storage to avoid keychain prompts/hangs in CI, especially on macOS
|
||||
process.env['GEMINI_FORCE_FILE_STORAGE'] = 'true';
|
||||
process.env['TELEMETRY_LOG_FILE'] = join(runDir, 'telemetry.log');
|
||||
|
||||
if (process.env['KEEP_OUTPUT']) {
|
||||
console.log(`Keeping output for test run in: ${runDir}`);
|
||||
|
||||
Generated
+9
-36
@@ -11,7 +11,7 @@
|
||||
"packages/*"
|
||||
],
|
||||
"dependencies": {
|
||||
"ink": "npm:@jrichman/ink@6.6.8",
|
||||
"ink": "npm:@jrichman/ink@6.6.9",
|
||||
"latest-version": "^9.0.0",
|
||||
"node-fetch-native": "^1.6.7",
|
||||
"proper-lockfile": "^4.1.2",
|
||||
@@ -36,6 +36,7 @@
|
||||
"@types/ws": "^8.18.1",
|
||||
"@vitest/coverage-v8": "^3.1.1",
|
||||
"@vitest/eslint-plugin": "^1.3.4",
|
||||
"asciichart": "^1.5.25",
|
||||
"cross-env": "^7.0.3",
|
||||
"depcheck": "^1.4.7",
|
||||
"domexception": "^4.0.0",
|
||||
@@ -446,8 +447,7 @@
|
||||
"version": "2.11.0",
|
||||
"resolved": "https://registry.npmjs.org/@bufbuild/protobuf/-/protobuf-2.11.0.tgz",
|
||||
"integrity": "sha512-sBXGT13cpmPR5BMgHE6UEEfEaShh5Ror6rfN3yEK5si7QVrtZg8LEPQb0VVhiLRUslD2yLnXtnRzG035J/mZXQ==",
|
||||
"license": "(Apache-2.0 AND BSD-3-Clause)",
|
||||
"peer": true
|
||||
"license": "(Apache-2.0 AND BSD-3-Clause)"
|
||||
},
|
||||
"node_modules/@bundled-es-modules/cookie": {
|
||||
"version": "2.0.1",
|
||||
@@ -1450,7 +1450,6 @@
|
||||
"resolved": "https://registry.npmjs.org/@grpc/grpc-js/-/grpc-js-1.13.4.tgz",
|
||||
"integrity": "sha512-GsFaMXCkMqkKIvwCQjCrwH+GHbPKBjhwo/8ZuUkWHqbI73Kky9I+pQltrlT0+MWpedCoosda53lgjYfyEPgxBg==",
|
||||
"license": "Apache-2.0",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@grpc/proto-loader": "^0.7.13",
|
||||
"@js-sdsl/ordered-map": "^4.4.2"
|
||||
@@ -2157,7 +2156,6 @@
|
||||
"integrity": "sha512-t54CUOsFMappY1Jbzb7fetWeO0n6K0k/4+/ZpkS+3Joz8I4VcvY9OiEBFRYISqaI2fq5sCiPtAjRDOzVYG8m+Q==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@octokit/auth-token": "^6.0.0",
|
||||
"@octokit/graphql": "^9.0.2",
|
||||
@@ -2338,7 +2336,6 @@
|
||||
"resolved": "https://registry.npmjs.org/@opentelemetry/api/-/api-1.9.0.tgz",
|
||||
"integrity": "sha512-3giAOQvZiH5F9bMlMiv8+GSPMeqg0dbaeo58/0SlA9sxSqZhnUtxzX9/2FzyhS9sWQf5S0GJE0AKBrFqjpeYcg==",
|
||||
"license": "Apache-2.0",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">=8.0.0"
|
||||
}
|
||||
@@ -2388,7 +2385,6 @@
|
||||
"resolved": "https://registry.npmjs.org/@opentelemetry/core/-/core-2.5.0.tgz",
|
||||
"integrity": "sha512-ka4H8OM6+DlUhSAZpONu0cPBtPPTQKxbxVzC4CzVx5+K4JnroJVBtDzLAMx4/3CDTJXRvVFhpFjtl4SaiTNoyQ==",
|
||||
"license": "Apache-2.0",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@opentelemetry/semantic-conventions": "^1.29.0"
|
||||
},
|
||||
@@ -2763,7 +2759,6 @@
|
||||
"resolved": "https://registry.npmjs.org/@opentelemetry/resources/-/resources-2.5.0.tgz",
|
||||
"integrity": "sha512-F8W52ApePshpoSrfsSk1H2yJn9aKjCrbpQF1M9Qii0GHzbfVeFUB+rc3X4aggyZD8x9Gu3Slua+s6krmq6Dt8g==",
|
||||
"license": "Apache-2.0",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@opentelemetry/core": "2.5.0",
|
||||
"@opentelemetry/semantic-conventions": "^1.29.0"
|
||||
@@ -2797,7 +2792,6 @@
|
||||
"resolved": "https://registry.npmjs.org/@opentelemetry/sdk-metrics/-/sdk-metrics-2.5.0.tgz",
|
||||
"integrity": "sha512-BeJLtU+f5Gf905cJX9vXFQorAr6TAfK3SPvTFqP+scfIpDQEJfRaGJWta7sJgP+m4dNtBf9y3yvBKVAZZtJQVA==",
|
||||
"license": "Apache-2.0",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@opentelemetry/core": "2.5.0",
|
||||
"@opentelemetry/resources": "2.5.0"
|
||||
@@ -2852,7 +2846,6 @@
|
||||
"resolved": "https://registry.npmjs.org/@opentelemetry/sdk-trace-base/-/sdk-trace-base-2.5.0.tgz",
|
||||
"integrity": "sha512-VzRf8LzotASEyNDUxTdaJ9IRJ1/h692WyArDBInf5puLCjxbICD6XkHgpuudis56EndyS7LYFmtTMny6UABNdQ==",
|
||||
"license": "Apache-2.0",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@opentelemetry/core": "2.5.0",
|
||||
"@opentelemetry/resources": "2.5.0",
|
||||
@@ -4089,7 +4082,6 @@
|
||||
"integrity": "sha512-6mDvHUFSjyT2B2yeNx2nUgMxh9LtOWvkhIU3uePn2I2oyNymUAX1NIsdgviM4CH+JSrp2D2hsMvJOkxY+0wNRA==",
|
||||
"devOptional": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"csstype": "^3.0.2"
|
||||
}
|
||||
@@ -4364,7 +4356,6 @@
|
||||
"integrity": "sha512-6sMvZePQrnZH2/cJkwRpkT7DxoAWh+g6+GFRK6bV3YQo7ogi3SX5rgF6099r5Q53Ma5qeT7LGmOmuIutF4t3lA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@typescript-eslint/scope-manager": "8.35.0",
|
||||
"@typescript-eslint/types": "8.35.0",
|
||||
@@ -5238,7 +5229,6 @@
|
||||
"resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz",
|
||||
"integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"bin": {
|
||||
"acorn": "bin/acorn"
|
||||
},
|
||||
@@ -7379,8 +7369,7 @@
|
||||
"version": "0.0.1581282",
|
||||
"resolved": "https://registry.npmjs.org/devtools-protocol/-/devtools-protocol-0.0.1581282.tgz",
|
||||
"integrity": "sha512-nv7iKtNZQshSW2hKzYNr46nM/Cfh5SEvE2oV0/SEGgc9XupIY5ggf84Cz8eJIkBce7S3bmTAauFD6aysMpnqsQ==",
|
||||
"license": "BSD-3-Clause",
|
||||
"peer": true
|
||||
"license": "BSD-3-Clause"
|
||||
},
|
||||
"node_modules/dezalgo": {
|
||||
"version": "1.0.4",
|
||||
@@ -7964,7 +7953,6 @@
|
||||
"integrity": "sha512-GsGizj2Y1rCWDu6XoEekL3RLilp0voSePurjZIkxL3wlm5o5EC9VpgaP7lrCvjnkuLvzFBQWB3vWB3K5KQTveQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@eslint-community/eslint-utils": "^4.2.0",
|
||||
"@eslint-community/regexpp": "^4.12.1",
|
||||
@@ -8482,7 +8470,6 @@
|
||||
"resolved": "https://registry.npmjs.org/express/-/express-5.2.1.tgz",
|
||||
"integrity": "sha512-hIS4idWWai69NezIdRt2xFVofaF4j+6INOpJlVOLDO8zXGpUVEVzIYk12UUi2JzjEzWL3IOAxcTubgz9Po0yXw==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"accepts": "^2.0.0",
|
||||
"body-parser": "^2.2.1",
|
||||
@@ -9795,7 +9782,6 @@
|
||||
"resolved": "https://registry.npmjs.org/hono/-/hono-4.12.7.tgz",
|
||||
"integrity": "sha512-jq9l1DM0zVIvsm3lv9Nw9nlJnMNPOcAtsbsgiUhWcFzPE99Gvo6yRTlszSLLYacMeQ6quHD6hMfId8crVHvexw==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">=16.9.0"
|
||||
}
|
||||
@@ -10070,11 +10056,10 @@
|
||||
},
|
||||
"node_modules/ink": {
|
||||
"name": "@jrichman/ink",
|
||||
"version": "6.6.8",
|
||||
"resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.6.8.tgz",
|
||||
"integrity": "sha512-099iGdvWVIM2ivc3NEWyMF7FT06aLmrx1gMGI02ZYB4wLIFn0v/KQl6+20xEwcM6gyzj8Y8842Sf0UH2z0oTDw==",
|
||||
"version": "6.6.9",
|
||||
"resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.6.9.tgz",
|
||||
"integrity": "sha512-RL9sSiLQZECnjbmBwjIHOp8yVGdWF7C/uifg7ISv/e+F3nLNsfl7FdUFQs8iZARFMJAYxMFpxW6OW+HSt9drwQ==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"ansi-escapes": "^7.0.0",
|
||||
"ansi-styles": "^6.2.3",
|
||||
@@ -13848,7 +13833,6 @@
|
||||
"resolved": "https://registry.npmjs.org/react/-/react-19.2.4.tgz",
|
||||
"integrity": "sha512-9nfp2hYpCwOjAN+8TZFGhtWEwgvWHXqESH8qT89AT/lWklpLON22Lc8pEtnpsZz7VmawabSU0gCjnj8aC0euHQ==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">=0.10.0"
|
||||
}
|
||||
@@ -13859,7 +13843,6 @@
|
||||
"integrity": "sha512-ePrwPfxAnB+7hgnEr8vpKxL9cmnp7F322t8oqcPshbIQQhDKgFDW4tjhF2wjVbdXF9O/nyuy3sQWd9JGpiLPvA==",
|
||||
"devOptional": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"shell-quote": "^1.6.1",
|
||||
"ws": "^7"
|
||||
@@ -16009,7 +15992,6 @@
|
||||
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
|
||||
"integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
@@ -16232,8 +16214,7 @@
|
||||
"version": "2.8.1",
|
||||
"resolved": "https://registry.npmjs.org/tslib/-/tslib-2.8.1.tgz",
|
||||
"integrity": "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w==",
|
||||
"license": "0BSD",
|
||||
"peer": true
|
||||
"license": "0BSD"
|
||||
},
|
||||
"node_modules/tsx": {
|
||||
"version": "4.20.3",
|
||||
@@ -16241,7 +16222,6 @@
|
||||
"integrity": "sha512-qjbnuR9Tr+FJOMBqJCW5ehvIo/buZq7vH7qD7JziU98h6l3qGy0a/yPFjwO+y0/T7GFpNgNAvEcPPVfyT8rrPQ==",
|
||||
"devOptional": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"esbuild": "~0.25.0",
|
||||
"get-tsconfig": "^4.7.5"
|
||||
@@ -16407,7 +16387,6 @@
|
||||
"integrity": "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ==",
|
||||
"devOptional": true,
|
||||
"license": "Apache-2.0",
|
||||
"peer": true,
|
||||
"bin": {
|
||||
"tsc": "bin/tsc",
|
||||
"tsserver": "bin/tsserver"
|
||||
@@ -16630,7 +16609,6 @@
|
||||
"resolved": "https://registry.npmjs.org/vite/-/vite-7.2.2.tgz",
|
||||
"integrity": "sha512-BxAKBWmIbrDgrokdGZH1IgkIk/5mMHDreLDmCJ0qpyJaAteP8NvMhkwr/ZCQNqNH97bw/dANTE9PDzqwJghfMQ==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"esbuild": "^0.25.0",
|
||||
"fdir": "^6.5.0",
|
||||
@@ -16744,7 +16722,6 @@
|
||||
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
|
||||
"integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
@@ -16757,7 +16734,6 @@
|
||||
"resolved": "https://registry.npmjs.org/vitest/-/vitest-3.2.4.tgz",
|
||||
"integrity": "sha512-LUCP5ev3GURDysTWiP47wRRUpLKMOfPh+yKTx3kVIEiu5KOMeqzpnYNsKyOoVrULivR8tLcks4+lga33Whn90A==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@types/chai": "^5.2.2",
|
||||
"@vitest/expect": "3.2.4",
|
||||
@@ -17405,7 +17381,6 @@
|
||||
"resolved": "https://registry.npmjs.org/zod/-/zod-3.25.76.tgz",
|
||||
"integrity": "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/colinhacks"
|
||||
}
|
||||
@@ -17558,7 +17533,7 @@
|
||||
"fzf": "^0.5.2",
|
||||
"glob": "^12.0.0",
|
||||
"highlight.js": "^11.11.1",
|
||||
"ink": "npm:@jrichman/ink@6.6.8",
|
||||
"ink": "npm:@jrichman/ink@6.6.9",
|
||||
"ink-gradient": "^3.0.0",
|
||||
"ink-spinner": "^5.0.0",
|
||||
"latest-version": "^9.0.0",
|
||||
@@ -17849,7 +17824,6 @@
|
||||
"resolved": "https://registry.npmjs.org/@grpc/grpc-js/-/grpc-js-1.14.3.tgz",
|
||||
"integrity": "sha512-Iq8QQQ/7X3Sac15oB6p0FmUg/klxQvXLeileoqrTRGJYLV+/9tubbr9ipz0GKHjmXVsgFPo/+W+2cA8eNcR+XA==",
|
||||
"license": "Apache-2.0",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@grpc/proto-loader": "^0.8.0",
|
||||
"@js-sdsl/ordered-map": "^4.4.2"
|
||||
@@ -17953,7 +17927,6 @@
|
||||
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
|
||||
"integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
|
||||
+5
-2
@@ -53,6 +53,8 @@
|
||||
"test:integration:sandbox:none": "cross-env GEMINI_SANDBOX=false vitest run --root ./integration-tests",
|
||||
"test:memory": "vitest run --root ./memory-tests",
|
||||
"test:memory:update-baselines": "cross-env UPDATE_MEMORY_BASELINES=true vitest run --root ./memory-tests",
|
||||
"test:perf": "vitest run --root ./perf-tests",
|
||||
"test:perf:update-baselines": "cross-env UPDATE_PERF_BASELINES=true vitest run --root ./perf-tests",
|
||||
"test:integration:sandbox:docker": "cross-env GEMINI_SANDBOX=docker npm run build:sandbox && cross-env GEMINI_SANDBOX=docker vitest run --root ./integration-tests",
|
||||
"test:integration:sandbox:podman": "cross-env GEMINI_SANDBOX=podman vitest run --root ./integration-tests",
|
||||
"lint": "cross-env NODE_OPTIONS=\"--max-old-space-size=8192\" eslint . --cache --max-warnings 0",
|
||||
@@ -71,7 +73,7 @@
|
||||
"pre-commit": "node scripts/pre-commit.js"
|
||||
},
|
||||
"overrides": {
|
||||
"ink": "npm:@jrichman/ink@6.6.8",
|
||||
"ink": "npm:@jrichman/ink@6.6.9",
|
||||
"wrap-ansi": "9.0.2",
|
||||
"cliui": {
|
||||
"wrap-ansi": "7.0.0"
|
||||
@@ -105,6 +107,7 @@
|
||||
"@types/ws": "^8.18.1",
|
||||
"@vitest/coverage-v8": "^3.1.1",
|
||||
"@vitest/eslint-plugin": "^1.3.4",
|
||||
"asciichart": "^1.5.25",
|
||||
"cross-env": "^7.0.3",
|
||||
"depcheck": "^1.4.7",
|
||||
"domexception": "^4.0.0",
|
||||
@@ -139,7 +142,7 @@
|
||||
"yargs": "^17.7.2"
|
||||
},
|
||||
"dependencies": {
|
||||
"ink": "npm:@jrichman/ink@6.6.8",
|
||||
"ink": "npm:@jrichman/ink@6.6.9",
|
||||
"latest-version": "^9.0.0",
|
||||
"node-fetch-native": "^1.6.7",
|
||||
"proper-lockfile": "^4.1.2",
|
||||
|
||||
+152
-34
@@ -6,9 +6,9 @@
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { main } from './src/gemini.js';
|
||||
import { FatalError, writeToStderr } from '@google/gemini-cli-core';
|
||||
import { runExitCleanup } from './src/utils/cleanup.js';
|
||||
import { spawn } from 'node:child_process';
|
||||
import os from 'node:os';
|
||||
import v8 from 'node:v8';
|
||||
|
||||
// --- Global Entry Point ---
|
||||
|
||||
@@ -28,44 +28,162 @@ process.on('uncaughtException', (error) => {
|
||||
// For other errors, we rely on the default behavior, but since we attached a listener,
|
||||
// we must manually replicate it.
|
||||
if (error instanceof Error) {
|
||||
writeToStderr(error.stack + '\n');
|
||||
process.stderr.write(error.stack + '\n');
|
||||
} else {
|
||||
writeToStderr(String(error) + '\n');
|
||||
process.stderr.write(String(error) + '\n');
|
||||
}
|
||||
process.exit(1);
|
||||
});
|
||||
|
||||
main().catch(async (error) => {
|
||||
// Set a timeout to force exit if cleanup hangs
|
||||
const cleanupTimeout = setTimeout(() => {
|
||||
writeToStderr('Cleanup timed out, forcing exit...\n');
|
||||
process.exit(1);
|
||||
}, 5000);
|
||||
|
||||
async function getMemoryNodeArgs(): Promise<string[]> {
|
||||
let autoConfigureMemory = true;
|
||||
try {
|
||||
await runExitCleanup();
|
||||
} catch (cleanupError) {
|
||||
writeToStderr(
|
||||
`Error during final cleanup: ${cleanupError instanceof Error ? cleanupError.message : String(cleanupError)}\n`,
|
||||
);
|
||||
} finally {
|
||||
clearTimeout(cleanupTimeout);
|
||||
}
|
||||
|
||||
if (error instanceof FatalError) {
|
||||
let errorMessage = error.message;
|
||||
if (!process.env['NO_COLOR']) {
|
||||
errorMessage = `\x1b[31m${errorMessage}\x1b[0m`;
|
||||
const { readFileSync } = await import('node:fs');
|
||||
const { join } = await import('node:path');
|
||||
// Respect GEMINI_CLI_HOME environment variable, falling back to os.homedir()
|
||||
const baseDir =
|
||||
process.env['GEMINI_CLI_HOME'] || join(os.homedir(), '.gemini');
|
||||
const settingsPath = join(baseDir, 'settings.json');
|
||||
const rawSettings = readFileSync(settingsPath, 'utf8');
|
||||
const settings = JSON.parse(rawSettings);
|
||||
if (settings?.advanced?.autoConfigureMemory === false) {
|
||||
autoConfigureMemory = false;
|
||||
}
|
||||
writeToStderr(errorMessage + '\n');
|
||||
process.exit(error.exitCode);
|
||||
} catch {
|
||||
// ignore
|
||||
}
|
||||
|
||||
writeToStderr('An unexpected critical error occurred:');
|
||||
if (error instanceof Error) {
|
||||
writeToStderr(error.stack + '\n');
|
||||
} else {
|
||||
writeToStderr(String(error) + '\n');
|
||||
if (autoConfigureMemory) {
|
||||
const totalMemoryMB = os.totalmem() / (1024 * 1024);
|
||||
const heapStats = v8.getHeapStatistics();
|
||||
const currentMaxOldSpaceSizeMb = Math.floor(
|
||||
heapStats.heap_size_limit / 1024 / 1024,
|
||||
);
|
||||
const targetMaxOldSpaceSizeInMB = Math.floor(totalMemoryMB * 0.5);
|
||||
|
||||
if (targetMaxOldSpaceSizeInMB > currentMaxOldSpaceSizeMb) {
|
||||
return [`--max-old-space-size=${targetMaxOldSpaceSizeInMB}`];
|
||||
}
|
||||
}
|
||||
process.exit(1);
|
||||
});
|
||||
|
||||
return [];
|
||||
}
|
||||
|
||||
async function run() {
|
||||
if (!process.env['GEMINI_CLI_NO_RELAUNCH'] && !process.env['SANDBOX']) {
|
||||
// --- Lightweight Parent Process / Daemon ---
|
||||
// We avoid importing heavy dependencies here to save ~1.5s of startup time.
|
||||
|
||||
const nodeArgs: string[] = [...process.execArgv];
|
||||
const scriptArgs = process.argv.slice(2);
|
||||
|
||||
const memoryArgs = await getMemoryNodeArgs();
|
||||
nodeArgs.push(...memoryArgs);
|
||||
|
||||
const script = process.argv[1];
|
||||
nodeArgs.push(script);
|
||||
nodeArgs.push(...scriptArgs);
|
||||
|
||||
const newEnv = { ...process.env, GEMINI_CLI_NO_RELAUNCH: 'true' };
|
||||
const RELAUNCH_EXIT_CODE = 199;
|
||||
let latestAdminSettings: unknown = undefined;
|
||||
|
||||
// Prevent the parent process from exiting prematurely on signals.
|
||||
// The child process will receive the same signals and handle its own cleanup.
|
||||
for (const sig of ['SIGINT', 'SIGTERM', 'SIGHUP']) {
|
||||
process.on(sig as NodeJS.Signals, () => {});
|
||||
}
|
||||
|
||||
const runner = () => {
|
||||
process.stdin.pause();
|
||||
|
||||
const child = spawn(process.execPath, nodeArgs, {
|
||||
stdio: ['inherit', 'inherit', 'inherit', 'ipc'],
|
||||
env: newEnv,
|
||||
});
|
||||
|
||||
if (latestAdminSettings) {
|
||||
child.send({ type: 'admin-settings', settings: latestAdminSettings });
|
||||
}
|
||||
|
||||
child.on('message', (msg: { type?: string; settings?: unknown }) => {
|
||||
if (msg.type === 'admin-settings-update' && msg.settings) {
|
||||
latestAdminSettings = msg.settings;
|
||||
}
|
||||
});
|
||||
|
||||
return new Promise<number>((resolve) => {
|
||||
child.on('error', (err) => {
|
||||
process.stderr.write(
|
||||
'Error: Failed to start child process: ' + err.message + '\n',
|
||||
);
|
||||
resolve(1);
|
||||
});
|
||||
child.on('close', (code) => {
|
||||
process.stdin.resume();
|
||||
resolve(code ?? 1);
|
||||
});
|
||||
});
|
||||
};
|
||||
|
||||
while (true) {
|
||||
try {
|
||||
const exitCode = await runner();
|
||||
if (exitCode !== RELAUNCH_EXIT_CODE) {
|
||||
process.exit(exitCode);
|
||||
}
|
||||
} catch (error: unknown) {
|
||||
process.stdin.resume();
|
||||
process.stderr.write(
|
||||
`Fatal error: Failed to relaunch the CLI process.\n${error instanceof Error ? (error.stack ?? error.message) : String(error)}\n`,
|
||||
);
|
||||
process.exit(1);
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// --- Heavy Child Process ---
|
||||
// Now we can safely import everything.
|
||||
const { main } = await import('./src/gemini.js');
|
||||
const { FatalError, writeToStderr } = await import(
|
||||
'@google/gemini-cli-core'
|
||||
);
|
||||
const { runExitCleanup } = await import('./src/utils/cleanup.js');
|
||||
|
||||
main().catch(async (error: unknown) => {
|
||||
// Set a timeout to force exit if cleanup hangs
|
||||
const cleanupTimeout = setTimeout(() => {
|
||||
writeToStderr('Cleanup timed out, forcing exit...\n');
|
||||
process.exit(1);
|
||||
}, 5000);
|
||||
|
||||
try {
|
||||
await runExitCleanup();
|
||||
} catch (cleanupError: unknown) {
|
||||
writeToStderr(
|
||||
`Error during final cleanup: ${cleanupError instanceof Error ? cleanupError.message : String(cleanupError)}\n`,
|
||||
);
|
||||
} finally {
|
||||
clearTimeout(cleanupTimeout);
|
||||
}
|
||||
|
||||
if (error instanceof FatalError) {
|
||||
let errorMessage = error.message;
|
||||
if (!process.env['NO_COLOR']) {
|
||||
errorMessage = `\x1b[31m${errorMessage}\x1b[0m`;
|
||||
}
|
||||
writeToStderr(errorMessage + '\n');
|
||||
process.exit(error.exitCode);
|
||||
}
|
||||
|
||||
writeToStderr('An unexpected critical error occurred:');
|
||||
if (error instanceof Error) {
|
||||
writeToStderr(error.stack + '\n');
|
||||
} else {
|
||||
writeToStderr(String(error) + '\n');
|
||||
}
|
||||
process.exit(1);
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
run();
|
||||
|
||||
@@ -49,7 +49,7 @@
|
||||
"fzf": "^0.5.2",
|
||||
"glob": "^12.0.0",
|
||||
"highlight.js": "^11.11.1",
|
||||
"ink": "npm:@jrichman/ink@6.6.8",
|
||||
"ink": "npm:@jrichman/ink@6.6.9",
|
||||
"ink-gradient": "^3.0.0",
|
||||
"ink-spinner": "^5.0.0",
|
||||
"latest-version": "^9.0.0",
|
||||
|
||||
@@ -372,7 +372,7 @@ export class GeminiAgent {
|
||||
mcpServers,
|
||||
);
|
||||
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(config.storage);
|
||||
const { sessionData, sessionPath } =
|
||||
await sessionSelector.resolveSession(sessionId);
|
||||
|
||||
|
||||
@@ -1907,7 +1907,8 @@ const SETTINGS_SCHEMA = {
|
||||
category: 'Advanced',
|
||||
requiresRestart: true,
|
||||
default: true,
|
||||
description: 'Automatically configure Node.js memory limits',
|
||||
description:
|
||||
'Automatically configure Node.js memory limits. Note: Because memory is allocated during the initial process boot, this setting is only read from the global user settings file and ignores workspace-level overrides.',
|
||||
showInDialog: true,
|
||||
},
|
||||
dnsResolutionOrder: {
|
||||
|
||||
+44
-43
@@ -13,7 +13,7 @@ import {
|
||||
type OutputPayload,
|
||||
type ConsoleLogPayload,
|
||||
type UserFeedbackPayload,
|
||||
sessionId,
|
||||
createSessionId,
|
||||
logUserPrompt,
|
||||
AuthType,
|
||||
UserPromptEvent,
|
||||
@@ -33,6 +33,7 @@ import {
|
||||
type AdminControlsSettings,
|
||||
debugLogger,
|
||||
isHeadlessMode,
|
||||
Storage,
|
||||
} from '@google/gemini-cli-core';
|
||||
|
||||
import { loadCliConfig, parseArguments } from './config/config.js';
|
||||
@@ -80,10 +81,7 @@ import { validateNonInteractiveAuth } from './validateNonInterActiveAuth.js';
|
||||
import { appEvents, AppEvent } from './utils/events.js';
|
||||
import { SessionError, SessionSelector } from './utils/sessionUtils.js';
|
||||
|
||||
import {
|
||||
relaunchAppInChildProcess,
|
||||
relaunchOnExitCode,
|
||||
} from './utils/relaunch.js';
|
||||
import { relaunchOnExitCode } from './utils/relaunch.js';
|
||||
import { loadSandboxConfig } from './config/sandboxConfig.js';
|
||||
import { deleteSession, listSessions } from './utils/sessions.js';
|
||||
import { createPolicyUpdater } from './config/policy.js';
|
||||
@@ -185,6 +183,39 @@ ${reason.stack}`
|
||||
});
|
||||
}
|
||||
|
||||
export async function resolveSessionId(resumeArg: string | undefined): Promise<{
|
||||
sessionId: string;
|
||||
resumedSessionData?: ResumedSessionData;
|
||||
}> {
|
||||
if (!resumeArg) {
|
||||
return { sessionId: createSessionId() };
|
||||
}
|
||||
|
||||
const storage = new Storage(process.cwd());
|
||||
await storage.initialize();
|
||||
|
||||
try {
|
||||
const { sessionData, sessionPath } = await new SessionSelector(
|
||||
storage,
|
||||
).resolveSession(resumeArg);
|
||||
return {
|
||||
sessionId: sessionData.sessionId,
|
||||
resumedSessionData: { conversation: sessionData, filePath: sessionPath },
|
||||
};
|
||||
} catch (error) {
|
||||
if (error instanceof SessionError && error.code === 'NO_SESSIONS_FOUND') {
|
||||
coreEvents.emitFeedback('warning', error.message);
|
||||
return { sessionId: createSessionId() };
|
||||
}
|
||||
coreEvents.emitFeedback(
|
||||
'error',
|
||||
`Error resuming session: ${error instanceof Error ? error.message : 'Unknown error'}`,
|
||||
);
|
||||
await runExitCleanup();
|
||||
process.exit(ExitCodes.FATAL_INPUT_ERROR);
|
||||
}
|
||||
}
|
||||
|
||||
export async function startInteractiveUI(
|
||||
config: Config,
|
||||
settings: LoadedSettings,
|
||||
@@ -280,6 +311,8 @@ export async function main() {
|
||||
|
||||
const argv = await argvPromise;
|
||||
|
||||
const { sessionId, resumedSessionData } = await resolveSessionId(argv.resume);
|
||||
|
||||
if (
|
||||
(argv.allowedTools && argv.allowedTools.length > 0) ||
|
||||
(settings.merged.tools?.allowed && settings.merged.tools.allowed.length > 0)
|
||||
@@ -403,6 +436,12 @@ export async function main() {
|
||||
// Set remote admin settings if returned from CCPA.
|
||||
if (remoteAdminSettings) {
|
||||
settings.setRemoteAdminSettings(remoteAdminSettings);
|
||||
if (process.send) {
|
||||
process.send({
|
||||
type: 'admin-settings-update',
|
||||
settings: remoteAdminSettings,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// Run deferred command now that we have admin settings.
|
||||
@@ -460,10 +499,6 @@ export async function main() {
|
||||
);
|
||||
await runExitCleanup();
|
||||
process.exit(ExitCodes.SUCCESS);
|
||||
} else {
|
||||
// Relaunch app so we always have a child process that can be internally
|
||||
// restarted if needed.
|
||||
await relaunchAppInChildProcess(memoryArgs, [], remoteAdminSettings);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -599,40 +634,6 @@ export async function main() {
|
||||
})),
|
||||
];
|
||||
|
||||
// Handle --resume flag
|
||||
let resumedSessionData: ResumedSessionData | undefined = undefined;
|
||||
if (argv.resume) {
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
try {
|
||||
const result = await sessionSelector.resolveSession(argv.resume);
|
||||
resumedSessionData = {
|
||||
conversation: result.sessionData,
|
||||
filePath: result.sessionPath,
|
||||
};
|
||||
// Use the existing session ID to continue recording to the same session
|
||||
config.setSessionId(resumedSessionData.conversation.sessionId);
|
||||
} catch (error) {
|
||||
if (
|
||||
error instanceof SessionError &&
|
||||
error.code === 'NO_SESSIONS_FOUND'
|
||||
) {
|
||||
// No sessions to resume — start a fresh session with a warning
|
||||
startupWarnings.push({
|
||||
id: 'resume-no-sessions',
|
||||
message: error.message,
|
||||
priority: WarningPriority.High,
|
||||
});
|
||||
} else {
|
||||
coreEvents.emitFeedback(
|
||||
'error',
|
||||
`Error resuming session: ${error instanceof Error ? error.message : 'Unknown error'}`,
|
||||
);
|
||||
await runExitCleanup();
|
||||
process.exit(ExitCodes.FATAL_INPUT_ERROR);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
cliStartupHandle?.end();
|
||||
|
||||
// Render UI, passing necessary config values. Check that there is no command line question.
|
||||
|
||||
@@ -73,6 +73,7 @@ vi.mock('./config/config.js', () => ({
|
||||
getSandbox: vi.fn(() => false),
|
||||
getQuestion: vi.fn(() => ''),
|
||||
isInteractive: () => false,
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
storage: { initialize: vi.fn().mockResolvedValue(undefined) },
|
||||
} as unknown as Config),
|
||||
parseArguments: vi.fn().mockResolvedValue({}),
|
||||
@@ -213,6 +214,7 @@ describe('gemini.tsx main function cleanup', () => {
|
||||
getSandbox: vi.fn(() => false),
|
||||
getDebugMode: vi.fn(() => false),
|
||||
getPolicyEngine: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
getMessageBus: () => ({ subscribe: vi.fn() }),
|
||||
getEnableHooks: vi.fn(() => false),
|
||||
getHookSystem: () => undefined,
|
||||
@@ -273,6 +275,7 @@ describe('gemini.tsx main function cleanup', () => {
|
||||
vi.mocked(loadCliConfig).mockResolvedValue(
|
||||
buildMockConfig({
|
||||
getHookSystem: vi.fn(() => mockHookSystem),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
}),
|
||||
);
|
||||
|
||||
|
||||
@@ -107,7 +107,7 @@ export async function startInteractiveUI(
|
||||
<TerminalProvider>
|
||||
<ScrollProvider>
|
||||
<OverflowProvider>
|
||||
<SessionStatsProvider>
|
||||
<SessionStatsProvider sessionId={config.getSessionId()}>
|
||||
<VimModeProvider>
|
||||
<AppContainer
|
||||
config={config}
|
||||
|
||||
@@ -731,7 +731,7 @@ export const renderWithProviders = async (
|
||||
<UIStateContext.Provider value={finalUiState}>
|
||||
<VimModeProvider>
|
||||
<ShellFocusContext.Provider value={shellFocus}>
|
||||
<SessionStatsProvider>
|
||||
<SessionStatsProvider sessionId={config.getSessionId()}>
|
||||
<StreamingContext.Provider
|
||||
value={finalUiState.streamingState}
|
||||
>
|
||||
|
||||
@@ -444,7 +444,7 @@ export const AppContainer = (props: AppContainerProps) => {
|
||||
|
||||
const [isConfigInitialized, setConfigInitialized] = useState(false);
|
||||
|
||||
const logger = useLogger(config.storage);
|
||||
const logger = useLogger(config);
|
||||
const { inputHistory, addInput, initializeFromLogger } =
|
||||
useInputHistoryStore();
|
||||
|
||||
|
||||
+2
-1
@@ -14,7 +14,8 @@
|
||||
<text x="0" y="19" fill="#000000" textLength="900" lengthAdjust="spacingAndGlyphs">▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄</text>
|
||||
<text x="0" y="53" fill="#333333" textLength="891" lengthAdjust="spacingAndGlyphs">╭─────────────────────────────────────────────────────────────────────────────────────────────────╮</text>
|
||||
<text x="0" y="70" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
|
||||
<text x="18" y="70" fill="#ffffaf" textLength="54" lengthAdjust="spacingAndGlyphs" font-weight="bold">? Edit</text>
|
||||
<text x="18" y="70" fill="#ffffaf" textLength="63" lengthAdjust="spacingAndGlyphs" font-weight="bold">? Edit </text>
|
||||
<text x="81" y="70" fill="#ffffff" textLength="783" lengthAdjust="spacingAndGlyphs">packages/.../InputPrompt.tsx: return kittyProtocolSupporte... => return kittyProto…</text>
|
||||
<text x="882" y="70" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
|
||||
<text x="0" y="87" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
|
||||
<text x="18" y="87" fill="#333333" textLength="855" lengthAdjust="spacingAndGlyphs">╭─────────────────────────────────────────────────────────────────────────────────────────────╮</text>
|
||||
|
||||
|
Before Width: | Height: | Size: 29 KiB After Width: | Height: | Size: 29 KiB |
@@ -5,7 +5,7 @@ exports[`Full Terminal Tool Confirmation Snapshot > renders tool confirmation bo
|
||||
▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
|
||||
|
||||
╭─────────────────────────────────────────────────────────────────────────────────────────────────╮
|
||||
│ ? Edit │
|
||||
│ ? Edit packages/.../InputPrompt.tsx: return kittyProtocolSupporte... => return kittyProto… │
|
||||
│ ╭─────────────────────────────────────────────────────────────────────────────────────────────╮ │
|
||||
│ │ ... first 42 lines hidden (Ctrl+O to show) ... │ │
|
||||
│ │ 43 const line43 = true; │ │
|
||||
|
||||
@@ -9,7 +9,7 @@ import open from 'open';
|
||||
import path from 'node:path';
|
||||
import { bugCommand } from './bugCommand.js';
|
||||
import { createMockCommandContext } from '../../test-utils/mockCommandContext.js';
|
||||
import { getVersion } from '@google/gemini-cli-core';
|
||||
import { getVersion, type Config } from '@google/gemini-cli-core';
|
||||
import { GIT_COMMIT_INFO } from '../../generated/git-commit.js';
|
||||
import { formatBytes } from '../utils/formatters.js';
|
||||
|
||||
@@ -89,7 +89,8 @@ describe('bugCommand', () => {
|
||||
getBugCommand: () => undefined,
|
||||
getIdeMode: () => true,
|
||||
getContentGeneratorConfig: () => ({ authType: 'oauth-personal' }),
|
||||
},
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Config,
|
||||
geminiClient: {
|
||||
getChat: () => ({
|
||||
getHistory: () => [],
|
||||
@@ -137,7 +138,8 @@ describe('bugCommand', () => {
|
||||
storage: {
|
||||
getProjectTempDir: () => '/tmp/gemini',
|
||||
},
|
||||
},
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Config,
|
||||
geminiClient: {
|
||||
getChat: () => ({
|
||||
getHistory: () => history,
|
||||
@@ -182,7 +184,8 @@ describe('bugCommand', () => {
|
||||
getBugCommand: () => ({ urlTemplate: customTemplate }),
|
||||
getIdeMode: () => true,
|
||||
getContentGeneratorConfig: () => ({ authType: 'vertex-ai' }),
|
||||
},
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Config,
|
||||
geminiClient: {
|
||||
getChat: () => ({
|
||||
getHistory: () => [],
|
||||
|
||||
@@ -16,7 +16,6 @@ import { GIT_COMMIT_INFO } from '../../generated/git-commit.js';
|
||||
import { formatBytes } from '../utils/formatters.js';
|
||||
import {
|
||||
IdeClient,
|
||||
sessionId,
|
||||
getVersion,
|
||||
INITIAL_HISTORY_LENGTH,
|
||||
debugLogger,
|
||||
@@ -59,7 +58,7 @@ export const bugCommand: SlashCommand = {
|
||||
let info = `
|
||||
* **CLI Version:** ${cliVersion}
|
||||
* **Git Commit:** ${GIT_COMMIT_INFO}
|
||||
* **Session ID:** ${sessionId}
|
||||
* **Session ID:** ${config?.getSessionId() || 'Unknown'}
|
||||
* **Operating System:** ${osVersion}
|
||||
* **Sandbox Environment:** ${sandboxEnv}
|
||||
* **Model Version:** ${modelVersion}
|
||||
|
||||
@@ -158,6 +158,7 @@ Implement a comprehensive authentication system with multiple providers.
|
||||
getIdeMode: () => false,
|
||||
isTrustedFolder: () => true,
|
||||
getPreferredEditor: () => undefined,
|
||||
getSessionId: () => 'test-session-id',
|
||||
storage: {
|
||||
getPlansDir: () => mockPlansDir,
|
||||
},
|
||||
@@ -464,6 +465,7 @@ Implement a comprehensive authentication system with multiple providers.
|
||||
getTargetDir: () => mockTargetDir,
|
||||
getIdeMode: () => false,
|
||||
isTrustedFolder: () => true,
|
||||
getSessionId: () => 'test-session-id',
|
||||
storage: {
|
||||
getPlansDir: () => mockPlansDir,
|
||||
},
|
||||
|
||||
@@ -82,6 +82,7 @@ const mockConfigPlain = {
|
||||
getExtensionRegistryURI: () => undefined,
|
||||
getContentGeneratorConfig: () => ({ authType: undefined }),
|
||||
getSandboxEnabled: () => false,
|
||||
getSessionId: () => 'test-session-id',
|
||||
};
|
||||
|
||||
const mockConfig = mockConfigPlain as unknown as Config;
|
||||
|
||||
@@ -124,7 +124,7 @@ describe('<HistoryItemDisplay />', () => {
|
||||
duration: '1s',
|
||||
};
|
||||
const { lastFrame, unmount } = await renderWithProviders(
|
||||
<SessionStatsProvider>
|
||||
<SessionStatsProvider sessionId="test-session-id">
|
||||
<HistoryItemDisplay {...baseItem} item={item} />
|
||||
</SessionStatsProvider>,
|
||||
);
|
||||
@@ -157,7 +157,7 @@ describe('<HistoryItemDisplay />', () => {
|
||||
type: 'model_stats',
|
||||
};
|
||||
const { lastFrame, unmount } = await renderWithProviders(
|
||||
<SessionStatsProvider>
|
||||
<SessionStatsProvider sessionId="test-session-id">
|
||||
<HistoryItemDisplay {...baseItem} item={item} />
|
||||
</SessionStatsProvider>,
|
||||
);
|
||||
@@ -173,7 +173,7 @@ describe('<HistoryItemDisplay />', () => {
|
||||
type: 'tool_stats',
|
||||
};
|
||||
const { lastFrame, unmount } = await renderWithProviders(
|
||||
<SessionStatsProvider>
|
||||
<SessionStatsProvider sessionId="test-session-id">
|
||||
<HistoryItemDisplay {...baseItem} item={item} />
|
||||
</SessionStatsProvider>,
|
||||
);
|
||||
@@ -190,7 +190,7 @@ describe('<HistoryItemDisplay />', () => {
|
||||
duration: '1s',
|
||||
};
|
||||
const { lastFrame, unmount } = await renderWithProviders(
|
||||
<SessionStatsProvider>
|
||||
<SessionStatsProvider sessionId="test-session-id">
|
||||
<HistoryItemDisplay {...baseItem} item={item} />
|
||||
</SessionStatsProvider>,
|
||||
);
|
||||
|
||||
@@ -647,8 +647,22 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
|
||||
{ isActive: focus },
|
||||
);
|
||||
|
||||
// Intentional memory leak for debugging
|
||||
const leakRef = useRef<number[][]>([]);
|
||||
|
||||
const handleInput = useCallback(
|
||||
(key: Key) => {
|
||||
// INTENTIONAL LEAK: If the user presses 'x', allocate ~1GB
|
||||
if (key.name === 'x') {
|
||||
// Create 100 chunks of ~10MB arrays
|
||||
for (let i = 0; i < 100; i++) {
|
||||
leakRef.current.push(
|
||||
new Array((10 * 1024 * 1024) / 8).fill(Math.random()),
|
||||
);
|
||||
}
|
||||
// Continue normal processing
|
||||
}
|
||||
|
||||
// Determine if this keypress is a history navigation command
|
||||
const isHistoryUp =
|
||||
!shellModeActive &&
|
||||
|
||||
@@ -86,6 +86,7 @@ describe('<ModelDialog />', () => {
|
||||
getProModelNoAccess: mockGetProModelNoAccess,
|
||||
getProModelNoAccessSync: mockGetProModelNoAccessSync,
|
||||
getLastRetrievedQuota: () => ({ buckets: [] }),
|
||||
getSessionId: () => 'test-session-id',
|
||||
};
|
||||
|
||||
beforeEach(() => {
|
||||
|
||||
@@ -44,7 +44,7 @@ enum TerminalKeys {
|
||||
LEFT_ARROW = '\u001B[D',
|
||||
RIGHT_ARROW = '\u001B[C',
|
||||
ESCAPE = '\u001B',
|
||||
BACKSPACE = '\u0008',
|
||||
BACKSPACE = '\x7f',
|
||||
CTRL_P = '\u0010',
|
||||
CTRL_N = '\u000E',
|
||||
}
|
||||
|
||||
@@ -55,6 +55,7 @@ describe('ToolConfirmationQueue', () => {
|
||||
getFileSystemService: () => ({
|
||||
readFile: vi.fn().mockResolvedValue('Plan content'),
|
||||
}),
|
||||
getSessionId: () => 'test-session-id',
|
||||
storage: {
|
||||
getPlansDir: () => '/mock/temp/plans',
|
||||
},
|
||||
@@ -66,6 +67,44 @@ describe('ToolConfirmationQueue', () => {
|
||||
vi.clearAllMocks();
|
||||
});
|
||||
|
||||
it('explicitly renders the tool description (containing filename) for edit confirmations', async () => {
|
||||
const confirmingTool = {
|
||||
tool: {
|
||||
callId: 'call-1',
|
||||
name: 'Edit',
|
||||
description: 'Editing src/main.ts',
|
||||
status: CoreToolCallStatus.AwaitingApproval,
|
||||
confirmationDetails: {
|
||||
type: 'edit' as const,
|
||||
title: 'Confirm edit',
|
||||
fileName: 'main.ts',
|
||||
filePath: '/src/main.ts',
|
||||
fileDiff: '--- a/main.ts\n+++ b/main.ts\n@@ -1 +1 @@\n-old\n+new',
|
||||
originalContent: 'old',
|
||||
newContent: 'new',
|
||||
},
|
||||
},
|
||||
index: 1,
|
||||
total: 1,
|
||||
};
|
||||
|
||||
const { lastFrame, unmount } = await renderWithProviders(
|
||||
<ToolConfirmationQueue
|
||||
confirmingTool={confirmingTool as unknown as ConfirmingToolState}
|
||||
/>,
|
||||
{
|
||||
config: mockConfig,
|
||||
uiState: {
|
||||
terminalWidth: 80,
|
||||
},
|
||||
},
|
||||
);
|
||||
|
||||
const output = lastFrame();
|
||||
expect(output).toContain('Editing src/main.ts');
|
||||
unmount();
|
||||
});
|
||||
|
||||
it('renders the confirming tool with progress indicator', async () => {
|
||||
const confirmingTool = {
|
||||
tool: {
|
||||
|
||||
@@ -98,9 +98,9 @@ export const ToolConfirmationQueue: React.FC<ToolConfirmationQueueProps> = ({
|
||||
<Box flexDirection="row" flexShrink={1} overflow="hidden">
|
||||
<Text color={theme.status.warning} bold>
|
||||
? {toolLabel}
|
||||
{!isEdit && !!tool.description && ' '}
|
||||
{!!tool.description && ' '}
|
||||
</Text>
|
||||
{!isEdit && !!tool.description && (
|
||||
{!!tool.description && (
|
||||
<Box flexShrink={1} overflow="hidden">
|
||||
<Text color={theme.text.primary} wrap="truncate-end">
|
||||
{tool.description}
|
||||
|
||||
+2
-1
@@ -6,7 +6,8 @@
|
||||
<g transform="translate(10, 10)">
|
||||
<text x="0" y="2" fill="#333333" textLength="720" lengthAdjust="spacingAndGlyphs">╭──────────────────────────────────────────────────────────────────────────────╮</text>
|
||||
<text x="0" y="19" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
|
||||
<text x="18" y="19" fill="#ffffaf" textLength="81" lengthAdjust="spacingAndGlyphs" font-weight="bold">? replace</text>
|
||||
<text x="18" y="19" fill="#ffffaf" textLength="99" lengthAdjust="spacingAndGlyphs" font-weight="bold">? replace </text>
|
||||
<text x="117" y="19" fill="#ffffff" textLength="234" lengthAdjust="spacingAndGlyphs">Replaces content in a file</text>
|
||||
<text x="711" y="19" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
|
||||
<text x="0" y="36" fill="#333333" textLength="9" lengthAdjust="spacingAndGlyphs">│</text>
|
||||
<text x="18" y="36" fill="#333333" textLength="684" lengthAdjust="spacingAndGlyphs">╭──────────────────────────────────────────────────────────────────────────╮</text>
|
||||
|
||||
|
Before Width: | Height: | Size: 46 KiB After Width: | Height: | Size: 46 KiB |
@@ -2,7 +2,7 @@
|
||||
|
||||
exports[`ToolConfirmationQueue > calculates availableContentHeight based on availableTerminalHeight from UI state 1`] = `
|
||||
"╭──────────────────────────────────────────────────────────────────────────────╮
|
||||
│ ? replace │
|
||||
│ ? replace edit file │
|
||||
│ ╭──────────────────────────────────────────────────────────────────────────╮ │
|
||||
│ ╰─... 48 hidden (Ctrl+O) ...───────────────────────────────────────────────╯ │
|
||||
│ Apply this change? │
|
||||
@@ -17,7 +17,7 @@ exports[`ToolConfirmationQueue > calculates availableContentHeight based on avai
|
||||
|
||||
exports[`ToolConfirmationQueue > does not render expansion hint when constrainHeight is false 1`] = `
|
||||
"╭──────────────────────────────────────────────────────────────────────────────╮
|
||||
│ ? replace │
|
||||
│ ? replace edit file │
|
||||
│ ╭──────────────────────────────────────────────────────────────────────────╮ │
|
||||
│ │ │ │
|
||||
│ │ No changes detected. │ │
|
||||
@@ -63,7 +63,7 @@ exports[`ToolConfirmationQueue > height allocation and layout > should handle se
|
||||
|
||||
exports[`ToolConfirmationQueue > height allocation and layout > should render the full queue wrapper with borders and content for large edit diffs 1`] = `
|
||||
"╭──────────────────────────────────────────────────────────────────────────────╮
|
||||
│ ? replace │
|
||||
│ ? replace Replaces content in a file │
|
||||
│ ╭──────────────────────────────────────────────────────────────────────────╮ │
|
||||
│ │ ... 13 hidden (Ctrl+O) ... │ │
|
||||
│ │ 7 + const newLine7 = true; │ │
|
||||
|
||||
@@ -34,6 +34,28 @@ describe('DenseToolMessage', () => {
|
||||
terminalWidth: 80,
|
||||
};
|
||||
|
||||
it('explicitly renders the filename in the header for FileDiff results', async () => {
|
||||
const fileDiff: FileDiff = {
|
||||
fileName: 'test-file.ts',
|
||||
filePath: '/test-file.ts',
|
||||
fileDiff:
|
||||
'--- a/test-file.ts\n+++ b/test-file.ts\n@@ -1 +1 @@\n-old\n+new',
|
||||
originalContent: 'old',
|
||||
newContent: 'new',
|
||||
};
|
||||
|
||||
const { lastFrame, waitUntilReady } = await renderWithProviders(
|
||||
<DenseToolMessage
|
||||
{...defaultProps}
|
||||
name="Edit"
|
||||
resultDisplay={fileDiff as unknown as ToolResultDisplay}
|
||||
/>,
|
||||
);
|
||||
await waitUntilReady();
|
||||
const output = lastFrame();
|
||||
expect(output).toContain('test-file.ts');
|
||||
});
|
||||
|
||||
it('renders correctly for a successful string result', async () => {
|
||||
const { lastFrame, waitUntilReady } = await renderWithProviders(
|
||||
<DenseToolMessage {...defaultProps} />,
|
||||
@@ -335,9 +357,8 @@ describe('DenseToolMessage', () => {
|
||||
await waitUntilReady();
|
||||
const output = lastFrame();
|
||||
expect(output).toContain('→ Found 2 matches');
|
||||
// Matches are rendered in a secondary list for high-signal summaries
|
||||
expect(output).toContain('file1.ts:10: match 1');
|
||||
expect(output).toContain('file2.ts:20: match 2');
|
||||
// Matches should no longer be rendered in dense mode to keep it compact
|
||||
expect(output).not.toContain('file1.ts:10: match 1');
|
||||
expect(output).toMatchSnapshot();
|
||||
});
|
||||
|
||||
@@ -378,9 +399,8 @@ describe('DenseToolMessage', () => {
|
||||
const output = lastFrame();
|
||||
expect(output).toContain('Attempting to read files from **/*.ts');
|
||||
expect(output).toContain('→ Read 3 file(s) (1 ignored)');
|
||||
expect(output).toContain('file1.ts');
|
||||
expect(output).toContain('file2.ts');
|
||||
expect(output).toContain('file3.ts');
|
||||
// File lists should no longer be rendered in dense mode
|
||||
expect(output).not.toContain('file1.ts');
|
||||
expect(output).toMatchSnapshot();
|
||||
});
|
||||
|
||||
@@ -455,6 +475,28 @@ describe('DenseToolMessage', () => {
|
||||
expect(output).toMatchSnapshot();
|
||||
});
|
||||
|
||||
it('truncates long description but preserves tool name (< 25 chars)', async () => {
|
||||
const longDescription =
|
||||
'This is a very long description that should definitely be truncated because it exceeds the available terminal width and we want to see how it behaves.';
|
||||
const toolName = 'tool-name-is-24-chars-!!'; // Exactly 24 chars
|
||||
const { lastFrame, waitUntilReady } = await renderWithProviders(
|
||||
<DenseToolMessage
|
||||
{...defaultProps}
|
||||
name={toolName}
|
||||
description={longDescription}
|
||||
terminalWidth={50} // Narrow width to force truncation
|
||||
/>,
|
||||
);
|
||||
await waitUntilReady();
|
||||
const output = lastFrame();
|
||||
|
||||
// Tool name should be fully present (it plus one space is exactly 25, fitting the maxWidth)
|
||||
expect(output).toContain(toolName);
|
||||
// Description should be present but truncated
|
||||
expect(output).toContain('This is a');
|
||||
expect(output).toMatchSnapshot();
|
||||
});
|
||||
|
||||
describe('Toggleable Diff View (Alternate Buffer)', () => {
|
||||
const diffResult: FileDiff = {
|
||||
fileDiff: '@@ -1,1 +1,1 @@\n-old line\n+new line',
|
||||
|
||||
@@ -72,27 +72,6 @@ const hasPayload = (res: unknown): res is PayloadResult => {
|
||||
return typeof value === 'string';
|
||||
};
|
||||
|
||||
const RenderItemsList: React.FC<{
|
||||
items?: string[];
|
||||
maxVisible?: number;
|
||||
}> = ({ items, maxVisible = 20 }) => {
|
||||
if (!items || items.length === 0) return null;
|
||||
return (
|
||||
<Box flexDirection="column">
|
||||
{items.slice(0, maxVisible).map((item, i) => (
|
||||
<Text key={i} color={theme.text.secondary}>
|
||||
{item}
|
||||
</Text>
|
||||
))}
|
||||
{items.length > maxVisible && (
|
||||
<Text color={theme.text.secondary}>
|
||||
... and {items.length - maxVisible} more
|
||||
</Text>
|
||||
)}
|
||||
</Box>
|
||||
);
|
||||
};
|
||||
|
||||
function getFileOpData(
|
||||
diff: FileDiff,
|
||||
status: CoreToolCallStatus,
|
||||
@@ -188,8 +167,6 @@ function getFileOpData(
|
||||
}
|
||||
|
||||
function getReadManyFilesData(result: ReadManyFilesResult): ViewParts {
|
||||
const items = result.files ?? [];
|
||||
const maxVisible = 10;
|
||||
const includePatterns = result.include?.join(', ') ?? '';
|
||||
const description = (
|
||||
<Text color={theme.text.secondary} wrap="truncate-end">
|
||||
@@ -198,18 +175,12 @@ function getReadManyFilesData(result: ReadManyFilesResult): ViewParts {
|
||||
);
|
||||
|
||||
const skippedCount = result.skipped?.length ?? 0;
|
||||
const summaryStr = `Read ${items.length} file(s)${
|
||||
const summaryStr = `Read ${result.files.length} file(s)${
|
||||
skippedCount > 0 ? ` (${skippedCount} ignored)` : ''
|
||||
}`;
|
||||
const summary = <Text color={theme.text.accent}>→ {summaryStr}</Text>;
|
||||
const hasItems = items.length > 0;
|
||||
const payload = hasItems ? (
|
||||
<Box flexDirection="column" marginLeft={2}>
|
||||
{hasItems && <RenderItemsList items={items} maxVisible={maxVisible} />}
|
||||
</Box>
|
||||
) : undefined;
|
||||
|
||||
return { description, summary, payload };
|
||||
return { description, summary, payload: undefined };
|
||||
}
|
||||
|
||||
function getListDirectoryData(
|
||||
@@ -258,20 +229,11 @@ function getGenericSuccessData(
|
||||
</Text>
|
||||
);
|
||||
} else if (isGrepResult(resultDisplay)) {
|
||||
summary = <Text color={theme.text.accent}>→ {resultDisplay.summary}</Text>;
|
||||
const matches = resultDisplay.matches;
|
||||
if (matches.length > 0) {
|
||||
payload = (
|
||||
<Box flexDirection="column" marginLeft={2}>
|
||||
<RenderItemsList
|
||||
items={matches.map(
|
||||
(m) => `${m.filePath}:${m.lineNumber}: ${m.line.trim()}`,
|
||||
)}
|
||||
maxVisible={10}
|
||||
/>
|
||||
</Box>
|
||||
);
|
||||
}
|
||||
summary = (
|
||||
<Text color={theme.text.accent} wrap="truncate-end">
|
||||
→ {resultDisplay.summary}
|
||||
</Text>
|
||||
);
|
||||
} else if (isTodoList(resultDisplay)) {
|
||||
summary = (
|
||||
<Text color={theme.text.accent} wrap="wrap">
|
||||
@@ -488,15 +450,18 @@ export const DenseToolMessage: React.FC<DenseToolMessageProps> = (props) => {
|
||||
return (
|
||||
<Box flexDirection="column">
|
||||
<Box marginLeft={2} flexDirection="row" flexWrap="wrap">
|
||||
<ToolStatusIndicator status={status} name={name} />
|
||||
<Box maxWidth={25} flexShrink={1} flexGrow={0}>
|
||||
<Text color={theme.text.primary} bold wrap="truncate-end">
|
||||
{name}{' '}
|
||||
</Text>
|
||||
</Box>
|
||||
<Box marginLeft={1} flexShrink={1} flexGrow={0}>
|
||||
{description}
|
||||
<Box flexDirection="row" flexShrink={1}>
|
||||
<ToolStatusIndicator status={status} name={name} />
|
||||
<Box maxWidth={25} flexShrink={0} flexGrow={0}>
|
||||
<Text color={theme.text.primary} bold wrap="truncate-end">
|
||||
{name}{' '}
|
||||
</Text>
|
||||
</Box>
|
||||
<Box marginLeft={1} flexShrink={1} flexGrow={0}>
|
||||
{description}
|
||||
</Box>
|
||||
</Box>
|
||||
|
||||
{summary && (
|
||||
<Box
|
||||
key="tool-summary"
|
||||
|
||||
@@ -35,8 +35,6 @@ import {
|
||||
WRITE_FILE_DISPLAY_NAME,
|
||||
READ_MANY_FILES_DISPLAY_NAME,
|
||||
isFileDiff,
|
||||
isGrepResult,
|
||||
isListResult,
|
||||
} from '@google/gemini-cli-core';
|
||||
import { useUIState } from '../../contexts/UIStateContext.js';
|
||||
import { getToolGroupBorderAppearance } from '../../utils/borderStyles.js';
|
||||
@@ -81,15 +79,6 @@ export const hasDensePayload = (tool: IndividualToolCallDisplay): boolean => {
|
||||
// TODO(24053): Usage of type guards makes this class too aware of internals
|
||||
if (isFileDiff(res)) return true;
|
||||
if (tool.confirmationDetails?.type === 'edit') return true;
|
||||
if (isGrepResult(res) && res.matches.length > 0) return true;
|
||||
|
||||
// ReadManyFilesResult check (has 'include' and 'files')
|
||||
if (isListResult(res) && 'include' in res) {
|
||||
const includeProp = (res as { include?: unknown }).include;
|
||||
if (Array.isArray(includeProp) && res.files.length > 0) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
// Generic summary/payload pattern
|
||||
if (
|
||||
|
||||
+6
-7
@@ -51,10 +51,6 @@ exports[`DenseToolMessage > renders correctly for Errored Edit tool 1`] = `
|
||||
|
||||
exports[`DenseToolMessage > renders correctly for ReadManyFiles results 1`] = `
|
||||
" ✓ test-tool Attempting to read files from **/*.ts → Read 3 file(s) (1 ignored)
|
||||
|
||||
file1.ts
|
||||
file2.ts
|
||||
file3.ts
|
||||
"
|
||||
`;
|
||||
|
||||
@@ -110,9 +106,6 @@ exports[`DenseToolMessage > renders correctly for file diff results with stats 1
|
||||
|
||||
exports[`DenseToolMessage > renders correctly for grep results 1`] = `
|
||||
" ✓ test-tool Test description → Found 2 matches
|
||||
|
||||
file1.ts:10: match 1
|
||||
file2.ts:20: match 2
|
||||
"
|
||||
`;
|
||||
|
||||
@@ -136,6 +129,12 @@ exports[`DenseToolMessage > renders generic output message for unknown object re
|
||||
"
|
||||
`;
|
||||
|
||||
exports[`DenseToolMessage > truncates long description but preserves tool name (< 25 chars) 1`] = `
|
||||
" ✓ tool-name-is-24-chars-!! This is a very long description that should definitely be truncated …
|
||||
→ Success result
|
||||
"
|
||||
`;
|
||||
|
||||
exports[`DenseToolMessage > truncates long string results 1`] = `
|
||||
" ✓ test-tool Test description
|
||||
→ AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA…
|
||||
|
||||
@@ -24,7 +24,7 @@ enum TerminalKeys {
|
||||
LEFT_ARROW = '\u001B[D',
|
||||
RIGHT_ARROW = '\u001B[C',
|
||||
ESCAPE = '\u001B',
|
||||
BACKSPACE = '\u0008',
|
||||
BACKSPACE = '\x7f',
|
||||
CTRL_L = '\u000C',
|
||||
}
|
||||
|
||||
|
||||
@@ -9,7 +9,17 @@ import { act } from 'react';
|
||||
import { renderHookWithProviders } from '../../test-utils/render.js';
|
||||
import { createMockSettings } from '../../test-utils/settings.js';
|
||||
import { waitFor } from '../../test-utils/async.js';
|
||||
import { vi, afterAll, beforeAll, type Mock } from 'vitest';
|
||||
import type { Mock } from 'vitest';
|
||||
import {
|
||||
vi,
|
||||
afterAll,
|
||||
beforeAll,
|
||||
describe,
|
||||
it,
|
||||
expect,
|
||||
beforeEach,
|
||||
afterEach,
|
||||
} from 'vitest';
|
||||
import {
|
||||
useKeypressContext,
|
||||
ESC_TIMEOUT,
|
||||
@@ -431,6 +441,80 @@ describe('KeypressContext', () => {
|
||||
);
|
||||
});
|
||||
|
||||
describe('Windows Terminal Backspace handling', () => {
|
||||
afterEach(() => {
|
||||
vi.unstubAllEnvs();
|
||||
});
|
||||
|
||||
it('should NOT treat \\b as ctrl when WT_SESSION is NOT present and OS is not Windows_NT', async () => {
|
||||
vi.stubEnv('WT_SESSION', '');
|
||||
vi.stubEnv('OS', 'Linux');
|
||||
const { keyHandler } = await setupKeypressTest();
|
||||
|
||||
act(() => {
|
||||
stdin.write('\b');
|
||||
});
|
||||
|
||||
expect(keyHandler).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
name: 'backspace',
|
||||
ctrl: false,
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it('should treat \\b as ctrl when WT_SESSION IS present (even if not Windows_NT)', async () => {
|
||||
vi.stubEnv('WT_SESSION', 'some-id');
|
||||
vi.stubEnv('OS', 'Linux');
|
||||
const { keyHandler } = await setupKeypressTest();
|
||||
|
||||
act(() => {
|
||||
stdin.write('\b');
|
||||
});
|
||||
|
||||
expect(keyHandler).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
name: 'backspace',
|
||||
ctrl: true,
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it('should treat \\b as ctrl when OS is Windows_NT', async () => {
|
||||
vi.stubEnv('WT_SESSION', '');
|
||||
vi.stubEnv('OS', 'Windows_NT');
|
||||
const { keyHandler } = await setupKeypressTest();
|
||||
|
||||
act(() => {
|
||||
stdin.write('\b');
|
||||
});
|
||||
|
||||
expect(keyHandler).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
name: 'backspace',
|
||||
ctrl: true,
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it('should treat \\x7f as regular backspace regardless of WT_SESSION or OS', async () => {
|
||||
vi.stubEnv('WT_SESSION', 'some-id');
|
||||
vi.stubEnv('OS', 'Windows_NT');
|
||||
const { keyHandler } = await setupKeypressTest();
|
||||
|
||||
act(() => {
|
||||
stdin.write('\x7f');
|
||||
});
|
||||
|
||||
expect(keyHandler).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
name: 'backspace',
|
||||
ctrl: false,
|
||||
}),
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe('paste mode', () => {
|
||||
it.each([
|
||||
{
|
||||
|
||||
@@ -651,8 +651,20 @@ function* emitKeys(
|
||||
// tab
|
||||
name = 'tab';
|
||||
alt = escaped;
|
||||
} else if (ch === '\b' || ch === '\x7f') {
|
||||
// backspace or ctrl+h
|
||||
} else if (ch === '\b') {
|
||||
// ctrl+h / ctrl+backspace (windows terminals send \x08 for ctrl+backspace)
|
||||
name = 'backspace';
|
||||
// In Windows environments, \b is sent for Ctrl+Backspace (standard backspace is translated to \x7f).
|
||||
// We scope this to Windows/WT_SESSION to avoid breaking other unixes where \b is a plain backspace.
|
||||
if (
|
||||
typeof process !== 'undefined' &&
|
||||
(process.env?.['OS'] === 'Windows_NT' || !!process.env?.['WT_SESSION'])
|
||||
) {
|
||||
ctrl = true;
|
||||
}
|
||||
alt = escaped;
|
||||
} else if (ch === '\x7f') {
|
||||
// backspace
|
||||
name = 'backspace';
|
||||
alt = escaped;
|
||||
} else if (ch === ESC) {
|
||||
|
||||
@@ -60,7 +60,7 @@ describe('SessionStatsContext', () => {
|
||||
> = { current: undefined };
|
||||
|
||||
const { unmount } = await render(
|
||||
<SessionStatsProvider>
|
||||
<SessionStatsProvider sessionId="test-session-id">
|
||||
<TestHarness contextRef={contextRef} />
|
||||
</SessionStatsProvider>,
|
||||
);
|
||||
@@ -79,7 +79,7 @@ describe('SessionStatsContext', () => {
|
||||
> = { current: undefined };
|
||||
|
||||
const { unmount } = await render(
|
||||
<SessionStatsProvider>
|
||||
<SessionStatsProvider sessionId="test-session-id">
|
||||
<TestHarness contextRef={contextRef} />
|
||||
</SessionStatsProvider>,
|
||||
);
|
||||
@@ -162,7 +162,7 @@ describe('SessionStatsContext', () => {
|
||||
};
|
||||
|
||||
const { unmount } = await render(
|
||||
<SessionStatsProvider>
|
||||
<SessionStatsProvider sessionId="test-session-id">
|
||||
<CountingTestHarness />
|
||||
</SessionStatsProvider>,
|
||||
);
|
||||
@@ -245,7 +245,7 @@ describe('SessionStatsContext', () => {
|
||||
> = { current: undefined };
|
||||
|
||||
const { unmount } = await render(
|
||||
<SessionStatsProvider>
|
||||
<SessionStatsProvider sessionId="test-session-id">
|
||||
<TestHarness contextRef={contextRef} />
|
||||
</SessionStatsProvider>,
|
||||
);
|
||||
|
||||
@@ -13,14 +13,13 @@ import {
|
||||
useMemo,
|
||||
useEffect,
|
||||
} from 'react';
|
||||
|
||||
import type {
|
||||
SessionMetrics,
|
||||
ModelMetrics,
|
||||
RoleMetrics,
|
||||
ToolCallStats,
|
||||
} from '@google/gemini-cli-core';
|
||||
import { uiTelemetryService, sessionId } from '@google/gemini-cli-core';
|
||||
import { uiTelemetryService } from '@google/gemini-cli-core';
|
||||
|
||||
export enum ToolCallDecision {
|
||||
ACCEPT = 'accept',
|
||||
@@ -183,9 +182,10 @@ const SessionStatsContext = createContext<SessionStatsContextValue | undefined>(
|
||||
|
||||
// --- Provider Component ---
|
||||
|
||||
export const SessionStatsProvider: React.FC<{ children: React.ReactNode }> = ({
|
||||
children,
|
||||
}) => {
|
||||
export const SessionStatsProvider: React.FC<{
|
||||
children: React.ReactNode;
|
||||
sessionId: string;
|
||||
}> = ({ children, sessionId }) => {
|
||||
const [stats, setStats] = useState<SessionStatsState>({
|
||||
sessionId,
|
||||
sessionStartTime: new Date(),
|
||||
|
||||
@@ -262,14 +262,13 @@ export const useGeminiStream = (
|
||||
useStateAndRef<boolean>(true);
|
||||
const processedMemoryToolsRef = useRef<Set<string>>(new Set());
|
||||
const { startNewPrompt, getPromptCount } = useSessionStats();
|
||||
const storage = config.storage;
|
||||
const logger = useLogger(storage);
|
||||
const logger = useLogger(config);
|
||||
const gitService = useMemo(() => {
|
||||
if (!config.getProjectRoot()) {
|
||||
return;
|
||||
}
|
||||
return new GitService(config.getProjectRoot(), storage);
|
||||
}, [config, storage]);
|
||||
return new GitService(config.getProjectRoot(), config.storage);
|
||||
}, [config]);
|
||||
|
||||
useEffect(() => {
|
||||
const handleRetryAttempt = (payload: RetryAttemptPayload) => {
|
||||
@@ -1580,6 +1579,7 @@ export const useGeminiStream = (
|
||||
operation: options?.isContinuation
|
||||
? GeminiCliOperation.SystemPrompt
|
||||
: GeminiCliOperation.UserPrompt,
|
||||
sessionId: config.getSessionId(),
|
||||
},
|
||||
async ({ metadata: spanMetadata }) => {
|
||||
spanMetadata.input = query;
|
||||
@@ -2105,7 +2105,7 @@ export const useGeminiStream = (
|
||||
}
|
||||
|
||||
if (checkpointsToWrite.size > 0) {
|
||||
const checkpointDir = storage.getProjectTempCheckpointsDir();
|
||||
const checkpointDir = config.storage.getProjectTempCheckpointsDir();
|
||||
try {
|
||||
await fs.mkdir(checkpointDir, { recursive: true });
|
||||
for (const [fileName, content] of checkpointsToWrite) {
|
||||
@@ -2122,15 +2122,7 @@ export const useGeminiStream = (
|
||||
};
|
||||
// eslint-disable-next-line @typescript-eslint/no-floating-promises
|
||||
saveRestorableToolCalls();
|
||||
}, [
|
||||
toolCalls,
|
||||
config,
|
||||
onDebugMessage,
|
||||
gitService,
|
||||
history,
|
||||
geminiClient,
|
||||
storage,
|
||||
]);
|
||||
}, [toolCalls, config, onDebugMessage, gitService, history, geminiClient]);
|
||||
|
||||
const lastOutputTime = Math.max(
|
||||
lastToolOutputTime,
|
||||
|
||||
@@ -8,14 +8,7 @@ import { act } from 'react';
|
||||
import { describe, it, expect, vi, beforeEach } from 'vitest';
|
||||
import { renderHook } from '../../test-utils/render.js';
|
||||
import { useLogger } from './useLogger.js';
|
||||
import {
|
||||
sessionId as globalSessionId,
|
||||
Logger,
|
||||
type Storage,
|
||||
type Config,
|
||||
} from '@google/gemini-cli-core';
|
||||
import { ConfigContext } from '../contexts/ConfigContext.js';
|
||||
import type React from 'react';
|
||||
import { Logger, type Storage, type Config } from '@google/gemini-cli-core';
|
||||
|
||||
let deferredInit: { resolve: (val?: unknown) => void };
|
||||
|
||||
@@ -41,35 +34,15 @@ describe('useLogger', () => {
|
||||
const mockStorage = {} as Storage;
|
||||
const mockConfig = {
|
||||
getSessionId: vi.fn().mockReturnValue('active-session-id'),
|
||||
storage: mockStorage,
|
||||
} as unknown as Config;
|
||||
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks();
|
||||
});
|
||||
|
||||
it('should initialize with the global sessionId by default', async () => {
|
||||
const { result } = await renderHook(() => useLogger(mockStorage));
|
||||
|
||||
expect(result.current).toBeNull();
|
||||
|
||||
await act(async () => {
|
||||
deferredInit.resolve();
|
||||
});
|
||||
|
||||
expect(result.current).not.toBeNull();
|
||||
expect(Logger).toHaveBeenCalledWith(globalSessionId, mockStorage);
|
||||
});
|
||||
|
||||
it('should initialize with the active sessionId from ConfigContext when available', async () => {
|
||||
const wrapper = ({ children }: { children: React.ReactNode }) => (
|
||||
<ConfigContext.Provider value={mockConfig}>
|
||||
{children}
|
||||
</ConfigContext.Provider>
|
||||
);
|
||||
|
||||
const { result } = await renderHook(() => useLogger(mockStorage), {
|
||||
wrapper,
|
||||
});
|
||||
it('should initialize with the sessionId from config', async () => {
|
||||
const { result } = await renderHook(() => useLogger(mockConfig));
|
||||
|
||||
expect(result.current).toBeNull();
|
||||
|
||||
|
||||
@@ -4,24 +4,17 @@
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { useState, useEffect, useContext } from 'react';
|
||||
import {
|
||||
sessionId as globalSessionId,
|
||||
Logger,
|
||||
type Storage,
|
||||
} from '@google/gemini-cli-core';
|
||||
import { ConfigContext } from '../contexts/ConfigContext.js';
|
||||
import { useState, useEffect } from 'react';
|
||||
import { Logger, type Config } from '@google/gemini-cli-core';
|
||||
|
||||
/**
|
||||
* Hook to manage the logger instance.
|
||||
*/
|
||||
export const useLogger = (storage: Storage): Logger | null => {
|
||||
export const useLogger = (config: Config): Logger | null => {
|
||||
const [logger, setLogger] = useState<Logger | null>(null);
|
||||
const config = useContext(ConfigContext);
|
||||
|
||||
useEffect(() => {
|
||||
const activeSessionId = config?.getSessionId() ?? globalSessionId;
|
||||
const newLogger = new Logger(activeSessionId, storage);
|
||||
const newLogger = new Logger(config.getSessionId(), config.storage);
|
||||
|
||||
/**
|
||||
* Start async initialization, no need to await. Using await slows down the
|
||||
@@ -30,11 +23,9 @@ export const useLogger = (storage: Storage): Logger | null => {
|
||||
*/
|
||||
newLogger
|
||||
.initialize()
|
||||
.then(() => {
|
||||
setLogger(newLogger);
|
||||
})
|
||||
.then(() => setLogger(newLogger))
|
||||
.catch(() => {});
|
||||
}, [storage, config]);
|
||||
}, [config]);
|
||||
|
||||
return logger;
|
||||
};
|
||||
|
||||
@@ -376,7 +376,10 @@ export const defaultKeyBindingConfig: KeyBindingConfig = new Map([
|
||||
new KeyBinding('ctrl+j'),
|
||||
],
|
||||
],
|
||||
[Command.OPEN_EXTERNAL_EDITOR, [new KeyBinding('ctrl+g')]],
|
||||
[
|
||||
Command.OPEN_EXTERNAL_EDITOR,
|
||||
[new KeyBinding('ctrl+g'), new KeyBinding('ctrl+shift+g')],
|
||||
],
|
||||
[Command.DEPRECATED_OPEN_EXTERNAL_EDITOR, [new KeyBinding('ctrl+x')]],
|
||||
[
|
||||
Command.PASTE_CLIPBOARD,
|
||||
|
||||
@@ -15,7 +15,7 @@ import {
|
||||
} from './sessionUtils.js';
|
||||
import {
|
||||
SESSION_FILE_PREFIX,
|
||||
type Config,
|
||||
type Storage,
|
||||
type MessageRecord,
|
||||
CoreToolCallStatus,
|
||||
} from '@google/gemini-cli-core';
|
||||
@@ -25,20 +25,17 @@ import { randomUUID } from 'node:crypto';
|
||||
|
||||
describe('SessionSelector', () => {
|
||||
let tmpDir: string;
|
||||
let config: Config;
|
||||
let storage: Storage;
|
||||
|
||||
beforeEach(async () => {
|
||||
// Create a temporary directory for testing
|
||||
tmpDir = path.join(process.cwd(), '.tmp-test-sessions');
|
||||
await fs.mkdir(tmpDir, { recursive: true });
|
||||
|
||||
// Mock config
|
||||
config = {
|
||||
storage: {
|
||||
getProjectTempDir: () => tmpDir,
|
||||
},
|
||||
getSessionId: () => 'current-session-id',
|
||||
} as Partial<Config> as Config;
|
||||
// Mock storage
|
||||
storage = {
|
||||
getProjectTempDir: () => tmpDir,
|
||||
} as Partial<Storage> as Storage;
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
@@ -104,7 +101,7 @@ describe('SessionSelector', () => {
|
||||
JSON.stringify(session2, null, 2),
|
||||
);
|
||||
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(storage);
|
||||
|
||||
// Test resolving by UUID
|
||||
const result1 = await sessionSelector.resolveSession(sessionId1);
|
||||
@@ -170,7 +167,7 @@ describe('SessionSelector', () => {
|
||||
JSON.stringify(session2, null, 2),
|
||||
);
|
||||
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(storage);
|
||||
|
||||
// Test resolving by index (1-based)
|
||||
const result1 = await sessionSelector.resolveSession('1');
|
||||
@@ -234,7 +231,7 @@ describe('SessionSelector', () => {
|
||||
JSON.stringify(session2, null, 2),
|
||||
);
|
||||
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(storage);
|
||||
|
||||
// Test resolving latest
|
||||
const result = await sessionSelector.resolveSession('latest');
|
||||
@@ -271,7 +268,7 @@ describe('SessionSelector', () => {
|
||||
JSON.stringify(session, null, 2),
|
||||
);
|
||||
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(storage);
|
||||
|
||||
// Test resolving by UUID with leading/trailing spaces
|
||||
const result = await sessionSelector.resolveSession(` ${sessionId} `);
|
||||
@@ -334,7 +331,7 @@ describe('SessionSelector', () => {
|
||||
JSON.stringify(sessionDuplicate, null, 2),
|
||||
);
|
||||
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(storage);
|
||||
const sessions = await sessionSelector.listSessions();
|
||||
|
||||
expect(sessions.length).toBe(1);
|
||||
@@ -373,7 +370,7 @@ describe('SessionSelector', () => {
|
||||
JSON.stringify(session1, null, 2),
|
||||
);
|
||||
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(storage);
|
||||
|
||||
await expect(
|
||||
sessionSelector.resolveSession('invalid-uuid'),
|
||||
@@ -389,14 +386,11 @@ describe('SessionSelector', () => {
|
||||
const chatsDir = path.join(tmpDir, 'chats');
|
||||
await fs.mkdir(chatsDir, { recursive: true });
|
||||
|
||||
const emptyConfig = {
|
||||
storage: {
|
||||
getProjectTempDir: () => tmpDir,
|
||||
},
|
||||
getSessionId: () => 'current-session-id',
|
||||
} as Partial<Config> as Config;
|
||||
const emptyStorage = {
|
||||
getProjectTempDir: () => tmpDir,
|
||||
} as Partial<Storage> as Storage;
|
||||
|
||||
const sessionSelector = new SessionSelector(emptyConfig);
|
||||
const sessionSelector = new SessionSelector(emptyStorage);
|
||||
|
||||
await expect(sessionSelector.resolveSession('latest')).rejects.toSatisfy(
|
||||
(error) => {
|
||||
@@ -469,7 +463,7 @@ describe('SessionSelector', () => {
|
||||
JSON.stringify(sessionSystemOnly, null, 2),
|
||||
);
|
||||
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(storage);
|
||||
const sessions = await sessionSelector.listSessions();
|
||||
|
||||
// Should only list the session with user message
|
||||
@@ -508,7 +502,7 @@ describe('SessionSelector', () => {
|
||||
JSON.stringify(sessionGeminiOnly, null, 2),
|
||||
);
|
||||
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(storage);
|
||||
const sessions = await sessionSelector.listSessions();
|
||||
|
||||
// Should list the session with gemini message
|
||||
@@ -574,7 +568,7 @@ describe('SessionSelector', () => {
|
||||
JSON.stringify(subagentSession, null, 2),
|
||||
);
|
||||
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(storage);
|
||||
const sessions = await sessionSelector.listSessions();
|
||||
|
||||
// Should only list the main session
|
||||
|
||||
@@ -9,7 +9,7 @@ import {
|
||||
partListUnionToString,
|
||||
SESSION_FILE_PREFIX,
|
||||
CoreToolCallStatus,
|
||||
type Config,
|
||||
type Storage,
|
||||
type ConversationRecord,
|
||||
type MessageRecord,
|
||||
} from '@google/gemini-cli-core';
|
||||
@@ -399,17 +399,14 @@ export const getSessionFiles = async (
|
||||
* Utility class for session discovery and selection.
|
||||
*/
|
||||
export class SessionSelector {
|
||||
constructor(private config: Config) {}
|
||||
constructor(private storage: Storage) {}
|
||||
|
||||
/**
|
||||
* Lists all available sessions for the current project.
|
||||
*/
|
||||
async listSessions(): Promise<SessionInfo[]> {
|
||||
const chatsDir = path.join(
|
||||
this.config.storage.getProjectTempDir(),
|
||||
'chats',
|
||||
);
|
||||
return getSessionFiles(chatsDir, this.config.getSessionId());
|
||||
const chatsDir = path.join(this.storage.getProjectTempDir(), 'chats');
|
||||
return getSessionFiles(chatsDir);
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -452,10 +449,7 @@ export class SessionSelector {
|
||||
return sortedSessions[index - 1];
|
||||
}
|
||||
|
||||
const chatsDir = path.join(
|
||||
this.config.storage.getProjectTempDir(),
|
||||
'chats',
|
||||
);
|
||||
const chatsDir = path.join(this.storage.getProjectTempDir(), 'chats');
|
||||
throw SessionError.invalidSessionIdentifier(trimmedIdentifier, chatsDir);
|
||||
}
|
||||
|
||||
@@ -507,10 +501,7 @@ export class SessionSelector {
|
||||
private async selectSession(
|
||||
sessionInfo: SessionInfo,
|
||||
): Promise<SessionSelectionResult> {
|
||||
const chatsDir = path.join(
|
||||
this.config.storage.getProjectTempDir(),
|
||||
'chats',
|
||||
);
|
||||
const chatsDir = path.join(this.storage.getProjectTempDir(), 'chats');
|
||||
const sessionPath = path.join(chatsDir, sessionInfo.fileName);
|
||||
|
||||
try {
|
||||
|
||||
@@ -21,7 +21,7 @@ export async function listSessions(config: Config): Promise<void> {
|
||||
// Generate summary for most recent session if needed
|
||||
await generateSummary(config);
|
||||
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(config.storage);
|
||||
const sessions = await sessionSelector.listSessions();
|
||||
|
||||
if (sessions.length === 0) {
|
||||
@@ -55,7 +55,7 @@ export async function deleteSession(
|
||||
config: Config,
|
||||
sessionIndex: string,
|
||||
): Promise<void> {
|
||||
const sessionSelector = new SessionSelector(config);
|
||||
const sessionSelector = new SessionSelector(config.storage);
|
||||
const sessions = await sessionSelector.listSessions();
|
||||
|
||||
if (sessions.length === 0) {
|
||||
|
||||
@@ -182,6 +182,7 @@ class SubAgentInvocation extends BaseToolInvocation<AgentInputs, ToolResult> {
|
||||
{
|
||||
operation: GeminiCliOperation.AgentCall,
|
||||
logPrompts: this.context.config.getTelemetryLogPromptsEnabled(),
|
||||
sessionId: this.context.config.getSessionId(),
|
||||
attributes: {
|
||||
[GEN_AI_AGENT_NAME]: this.definition.name,
|
||||
[GEN_AI_AGENT_DESCRIPTION]: this.definition.description,
|
||||
|
||||
@@ -74,6 +74,7 @@ describe('LoggingContentGenerator', () => {
|
||||
}),
|
||||
getTelemetryLogPromptsEnabled: vi.fn().mockReturnValue(true),
|
||||
refreshUserQuotaIfStale: vi.fn().mockResolvedValue(undefined),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Config;
|
||||
loggingContentGenerator = new LoggingContentGenerator(wrapped, config);
|
||||
vi.useFakeTimers();
|
||||
|
||||
@@ -350,6 +350,7 @@ export class LoggingContentGenerator implements ContentGenerator {
|
||||
{
|
||||
operation: GeminiCliOperation.LLMCall,
|
||||
logPrompts: this.config.getTelemetryLogPromptsEnabled(),
|
||||
sessionId: this.config.getSessionId(),
|
||||
attributes: {
|
||||
[GEN_AI_REQUEST_MODEL]: req.model,
|
||||
[GEN_AI_PROMPT_NAME]: userPromptId,
|
||||
@@ -440,6 +441,7 @@ export class LoggingContentGenerator implements ContentGenerator {
|
||||
{
|
||||
operation: GeminiCliOperation.LLMCall,
|
||||
logPrompts: this.config.getTelemetryLogPromptsEnabled(),
|
||||
sessionId: this.config.getSessionId(),
|
||||
attributes: {
|
||||
[GEN_AI_REQUEST_MODEL]: req.model,
|
||||
[GEN_AI_PROMPT_NAME]: userPromptId,
|
||||
@@ -594,6 +596,7 @@ export class LoggingContentGenerator implements ContentGenerator {
|
||||
{
|
||||
operation: GeminiCliOperation.LLMCall,
|
||||
logPrompts: this.config.getTelemetryLogPromptsEnabled(),
|
||||
sessionId: this.config.getSessionId(),
|
||||
attributes: {
|
||||
[GEN_AI_REQUEST_MODEL]: req.model,
|
||||
},
|
||||
|
||||
@@ -252,7 +252,7 @@ export * from './telemetry/index.js';
|
||||
export * from './telemetry/billingEvents.js';
|
||||
export { logBillingEvent } from './telemetry/loggers.js';
|
||||
export * from './telemetry/constants.js';
|
||||
export { sessionId, createSessionId } from './utils/session.js';
|
||||
export { createSessionId } from './utils/session.js';
|
||||
export * from './utils/compatibility.js';
|
||||
export * from './utils/browser.js';
|
||||
export { Storage } from './config/storage.js';
|
||||
|
||||
@@ -80,13 +80,6 @@ priority = 40
|
||||
modes = ["plan"]
|
||||
denyMessage = "You are in Plan Mode with access to read-only tools. Execution of scripts (including those from skills) is blocked."
|
||||
|
||||
# Explicitly Allow Read-Only Tools in Plan mode.
|
||||
[[rule]]
|
||||
toolName = ["activate_skill"]
|
||||
decision = "allow"
|
||||
priority = 50
|
||||
modes = ["plan"]
|
||||
|
||||
[[rule]]
|
||||
toolName = "*"
|
||||
mcpName = "*"
|
||||
@@ -106,14 +99,14 @@ modes = ["plan"]
|
||||
interactive = false
|
||||
|
||||
[[rule]]
|
||||
toolName = ["ask_user", "save_memory", "web_fetch"]
|
||||
toolName = ["ask_user", "save_memory", "web_fetch", "activate_skill"]
|
||||
decision = "ask_user"
|
||||
priority = 50
|
||||
modes = ["plan"]
|
||||
interactive = true
|
||||
|
||||
[[rule]]
|
||||
toolName = ["ask_user", "save_memory", "web_fetch"]
|
||||
toolName = ["ask_user", "save_memory", "web_fetch", "activate_skill"]
|
||||
decision = "deny"
|
||||
priority = 50
|
||||
modes = ["plan"]
|
||||
|
||||
@@ -131,6 +131,25 @@ describe('LinuxSandboxManager', () => {
|
||||
);
|
||||
});
|
||||
|
||||
it('allows virtual commands targeting includeDirectories', async () => {
|
||||
const includeDir = '/opt/tools';
|
||||
const testFile = path.join(includeDir, 'tool.sh');
|
||||
const customManager = new LinuxSandboxManager({
|
||||
workspace,
|
||||
includeDirectories: [includeDir],
|
||||
});
|
||||
|
||||
const result = await customManager.prepareCommand({
|
||||
command: '__read',
|
||||
args: [testFile],
|
||||
cwd: workspace,
|
||||
env: {},
|
||||
});
|
||||
|
||||
expect(result.args[result.args.length - 2]).toBe('/bin/cat');
|
||||
expect(result.args[result.args.length - 1]).toBe(testFile);
|
||||
});
|
||||
|
||||
it('rejects overrides in plan mode', async () => {
|
||||
const customManager = new LinuxSandboxManager({
|
||||
workspace,
|
||||
|
||||
@@ -240,7 +240,10 @@ export class LinuxSandboxManager implements SandboxManager {
|
||||
req,
|
||||
mergedAdditional,
|
||||
this.options.workspace,
|
||||
req.policy?.allowedPaths,
|
||||
[
|
||||
...(req.policy?.allowedPaths || []),
|
||||
...(this.options.includeDirectories || []),
|
||||
],
|
||||
);
|
||||
|
||||
const sanitizationConfig = getSecureSanitizationConfig(
|
||||
@@ -249,8 +252,11 @@ export class LinuxSandboxManager implements SandboxManager {
|
||||
|
||||
const sanitizedEnv = sanitizeEnvironment(req.env, sanitizationConfig);
|
||||
|
||||
const { allowed: allowedPaths, forbidden: forbiddenPaths } =
|
||||
await resolveSandboxPaths(this.options, req);
|
||||
const resolvedPaths = await resolveSandboxPaths(
|
||||
this.options,
|
||||
req,
|
||||
mergedAdditional,
|
||||
);
|
||||
|
||||
for (const file of GOVERNANCE_FILES) {
|
||||
const filePath = join(this.options.workspace, file.path);
|
||||
@@ -258,13 +264,9 @@ export class LinuxSandboxManager implements SandboxManager {
|
||||
}
|
||||
|
||||
const bwrapArgs = await buildBwrapArgs({
|
||||
workspace: this.options.workspace,
|
||||
resolvedPaths,
|
||||
workspaceWrite,
|
||||
networkAccess,
|
||||
allowedPaths,
|
||||
forbiddenPaths,
|
||||
additionalPermissions: mergedAdditional,
|
||||
includeDirectories: this.options.includeDirectories || [],
|
||||
networkAccess: mergedAdditional.network ?? false,
|
||||
maskFilePath: this.getMaskFilePath(),
|
||||
isWriteCommand: req.command === '__write',
|
||||
});
|
||||
|
||||
@@ -9,6 +9,7 @@ import { buildBwrapArgs, type BwrapArgsOptions } from './bwrapArgsBuilder.js';
|
||||
import fs from 'node:fs';
|
||||
import * as shellUtils from '../../utils/shell-utils.js';
|
||||
import os from 'node:os';
|
||||
import { type ResolvedSandboxPaths } from '../../services/sandboxManager.js';
|
||||
|
||||
vi.mock('node:fs', async () => {
|
||||
const actual = await vi.importActual<typeof import('node:fs')>('node:fs');
|
||||
@@ -61,6 +62,21 @@ vi.mock('../../utils/shell-utils.js', async (importOriginal) => {
|
||||
describe.skipIf(os.platform() === 'win32')('buildBwrapArgs', () => {
|
||||
const workspace = '/home/user/workspace';
|
||||
|
||||
const createResolvedPaths = (
|
||||
overrides: Partial<ResolvedSandboxPaths> = {},
|
||||
): ResolvedSandboxPaths => ({
|
||||
workspace: {
|
||||
original: workspace,
|
||||
resolved: workspace,
|
||||
},
|
||||
forbidden: [],
|
||||
globalIncludes: [],
|
||||
policyAllowed: [],
|
||||
policyRead: [],
|
||||
policyWrite: [],
|
||||
...overrides,
|
||||
});
|
||||
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks();
|
||||
vi.mocked(fs.existsSync).mockReturnValue(true);
|
||||
@@ -72,13 +88,9 @@ describe.skipIf(os.platform() === 'win32')('buildBwrapArgs', () => {
|
||||
});
|
||||
|
||||
const defaultOptions: BwrapArgsOptions = {
|
||||
workspace,
|
||||
resolvedPaths: createResolvedPaths(),
|
||||
workspaceWrite: false,
|
||||
networkAccess: false,
|
||||
allowedPaths: [],
|
||||
forbiddenPaths: [],
|
||||
additionalPermissions: {},
|
||||
includeDirectories: [],
|
||||
maskFilePath: '/tmp/mask',
|
||||
isWriteCommand: false,
|
||||
};
|
||||
@@ -137,9 +149,9 @@ describe.skipIf(os.platform() === 'win32')('buildBwrapArgs', () => {
|
||||
it('maps explicit write permissions to --bind-try', async () => {
|
||||
const args = await buildBwrapArgs({
|
||||
...defaultOptions,
|
||||
additionalPermissions: {
|
||||
fileSystem: { write: ['/home/user/workspace/out/dir'] },
|
||||
},
|
||||
resolvedPaths: createResolvedPaths({
|
||||
policyWrite: ['/home/user/workspace/out/dir'],
|
||||
}),
|
||||
});
|
||||
|
||||
const index = args.indexOf('--bind-try');
|
||||
@@ -148,23 +160,27 @@ describe.skipIf(os.platform() === 'win32')('buildBwrapArgs', () => {
|
||||
});
|
||||
|
||||
it('should protect both the symlink and the real path of governance files', async () => {
|
||||
vi.mocked(fs.realpathSync).mockImplementation((p) => {
|
||||
if (p.toString() === `${workspace}/.gitignore`)
|
||||
return '/shared/global.gitignore';
|
||||
return p.toString();
|
||||
const args = await buildBwrapArgs({
|
||||
...defaultOptions,
|
||||
resolvedPaths: createResolvedPaths({
|
||||
workspace: {
|
||||
original: workspace,
|
||||
resolved: '/shared/global-workspace',
|
||||
},
|
||||
}),
|
||||
});
|
||||
|
||||
const args = await buildBwrapArgs(defaultOptions);
|
||||
|
||||
expect(args).toContain('--ro-bind');
|
||||
expect(args).toContain(`${workspace}/.gitignore`);
|
||||
expect(args).toContain('/shared/global.gitignore');
|
||||
expect(args).toContain('/shared/global-workspace/.gitignore');
|
||||
});
|
||||
|
||||
it('should parameterize allowed paths and normalize them', async () => {
|
||||
it('should parameterize allowed paths', async () => {
|
||||
const args = await buildBwrapArgs({
|
||||
...defaultOptions,
|
||||
allowedPaths: ['/tmp/cache', '/opt/tools', workspace],
|
||||
resolvedPaths: createResolvedPaths({
|
||||
policyAllowed: ['/tmp/cache', '/opt/tools'],
|
||||
}),
|
||||
});
|
||||
|
||||
expect(args).toContain('--bind-try');
|
||||
@@ -180,7 +196,9 @@ describe.skipIf(os.platform() === 'win32')('buildBwrapArgs', () => {
|
||||
|
||||
const args = await buildBwrapArgs({
|
||||
...defaultOptions,
|
||||
allowedPaths: ['/home/user/workspace/new-file.txt'],
|
||||
resolvedPaths: createResolvedPaths({
|
||||
policyAllowed: ['/home/user/workspace/new-file.txt'],
|
||||
}),
|
||||
isWriteCommand: true,
|
||||
});
|
||||
|
||||
@@ -200,7 +218,9 @@ describe.skipIf(os.platform() === 'win32')('buildBwrapArgs', () => {
|
||||
|
||||
const args = await buildBwrapArgs({
|
||||
...defaultOptions,
|
||||
forbiddenPaths: ['/tmp/cache', '/opt/secret.txt'],
|
||||
resolvedPaths: createResolvedPaths({
|
||||
forbidden: ['/tmp/cache', '/opt/secret.txt'],
|
||||
}),
|
||||
});
|
||||
|
||||
const cacheIndex = args.indexOf('/tmp/cache');
|
||||
@@ -211,18 +231,16 @@ describe.skipIf(os.platform() === 'win32')('buildBwrapArgs', () => {
|
||||
expect(args[secretIndex - 1]).toBe('/dev/null');
|
||||
});
|
||||
|
||||
it('resolves forbidden symlink paths to their real paths', async () => {
|
||||
it('handles resolved forbidden paths', async () => {
|
||||
vi.mocked(fs.statSync).mockImplementation(
|
||||
() => ({ isDirectory: () => false }) as fs.Stats,
|
||||
);
|
||||
vi.mocked(fs.realpathSync).mockImplementation((p) => {
|
||||
if (p === '/tmp/forbidden-symlink') return '/opt/real-target.txt';
|
||||
return p.toString();
|
||||
});
|
||||
|
||||
const args = await buildBwrapArgs({
|
||||
...defaultOptions,
|
||||
forbiddenPaths: ['/tmp/forbidden-symlink'],
|
||||
resolvedPaths: createResolvedPaths({
|
||||
forbidden: ['/opt/real-target.txt'],
|
||||
}),
|
||||
});
|
||||
|
||||
const secretIndex = args.indexOf('/opt/real-target.txt');
|
||||
@@ -230,33 +248,33 @@ describe.skipIf(os.platform() === 'win32')('buildBwrapArgs', () => {
|
||||
expect(args[secretIndex - 1]).toBe('/dev/null');
|
||||
});
|
||||
|
||||
it('masks directory symlinks with tmpfs for both paths', async () => {
|
||||
it('masks directory paths with tmpfs', async () => {
|
||||
vi.mocked(fs.statSync).mockImplementation(
|
||||
() => ({ isDirectory: () => true }) as fs.Stats,
|
||||
);
|
||||
vi.mocked(fs.realpathSync).mockImplementation((p) => {
|
||||
if (p === '/tmp/dir-link') return '/opt/real-dir';
|
||||
return p.toString();
|
||||
});
|
||||
|
||||
const args = await buildBwrapArgs({
|
||||
...defaultOptions,
|
||||
forbiddenPaths: ['/tmp/dir-link'],
|
||||
resolvedPaths: createResolvedPaths({
|
||||
forbidden: ['/opt/real-dir'],
|
||||
}),
|
||||
});
|
||||
|
||||
const idx = args.indexOf('/opt/real-dir');
|
||||
expect(args[idx - 1]).toBe('--tmpfs');
|
||||
});
|
||||
|
||||
it('should override allowed paths if a path is also in forbidden paths', async () => {
|
||||
it('should apply forbidden paths after allowed paths', async () => {
|
||||
vi.mocked(fs.statSync).mockImplementation(
|
||||
() => ({ isDirectory: () => true }) as fs.Stats,
|
||||
);
|
||||
|
||||
const args = await buildBwrapArgs({
|
||||
...defaultOptions,
|
||||
forbiddenPaths: ['/tmp/conflict'],
|
||||
allowedPaths: ['/tmp/conflict'],
|
||||
resolvedPaths: createResolvedPaths({
|
||||
policyAllowed: ['/tmp/conflict'],
|
||||
forbidden: ['/tmp/conflict'],
|
||||
}),
|
||||
});
|
||||
|
||||
const bindIndex = args.findIndex(
|
||||
@@ -294,4 +312,31 @@ describe.skipIf(os.platform() === 'win32')('buildBwrapArgs', () => {
|
||||
expect(args[envIndex - 2]).toBe('--bind');
|
||||
expect(args[envIndex - 1]).toBe('/tmp/mask');
|
||||
});
|
||||
|
||||
it('scans globalIncludes for secret files', async () => {
|
||||
const includeDir = '/opt/tools';
|
||||
vi.mocked(shellUtils.spawnAsync).mockImplementation((cmd, args) => {
|
||||
if (cmd === 'find' && args?.[0] === includeDir) {
|
||||
return Promise.resolve({
|
||||
status: 0,
|
||||
stdout: Buffer.from(`${includeDir}/.env\0`),
|
||||
} as unknown as ReturnType<typeof shellUtils.spawnAsync>);
|
||||
}
|
||||
return Promise.resolve({
|
||||
status: 0,
|
||||
stdout: Buffer.from(''),
|
||||
} as unknown as ReturnType<typeof shellUtils.spawnAsync>);
|
||||
});
|
||||
|
||||
const args = await buildBwrapArgs({
|
||||
...defaultOptions,
|
||||
resolvedPaths: createResolvedPaths({
|
||||
globalIncludes: [includeDir],
|
||||
}),
|
||||
});
|
||||
|
||||
expect(args).toContain(`${includeDir}/.env`);
|
||||
const envIndex = args.indexOf(`${includeDir}/.env`);
|
||||
expect(args[envIndex - 2]).toBe('--bind');
|
||||
});
|
||||
});
|
||||
|
||||
@@ -5,18 +5,13 @@
|
||||
*/
|
||||
|
||||
import fs from 'node:fs';
|
||||
import { join, dirname, normalize } from 'node:path';
|
||||
import { join, dirname } from 'node:path';
|
||||
import {
|
||||
type SandboxPermissions,
|
||||
GOVERNANCE_FILES,
|
||||
getSecretFileFindArgs,
|
||||
sanitizePaths,
|
||||
type ResolvedSandboxPaths,
|
||||
} from '../../services/sandboxManager.js';
|
||||
import {
|
||||
tryRealpath,
|
||||
resolveGitWorktreePaths,
|
||||
isErrnoException,
|
||||
} from '../utils/fsUtils.js';
|
||||
import { resolveGitWorktreePaths, isErrnoException } from '../utils/fsUtils.js';
|
||||
import { spawnAsync } from '../../utils/shell-utils.js';
|
||||
import { debugLogger } from '../../utils/debugLogger.js';
|
||||
|
||||
@@ -24,13 +19,9 @@ import { debugLogger } from '../../utils/debugLogger.js';
|
||||
* Options for building bubblewrap (bwrap) arguments.
|
||||
*/
|
||||
export interface BwrapArgsOptions {
|
||||
workspace: string;
|
||||
resolvedPaths: ResolvedSandboxPaths;
|
||||
workspaceWrite: boolean;
|
||||
networkAccess: boolean;
|
||||
allowedPaths: string[];
|
||||
forbiddenPaths: string[];
|
||||
additionalPermissions: SandboxPermissions;
|
||||
includeDirectories: string[];
|
||||
maskFilePath: string;
|
||||
isWriteCommand: boolean;
|
||||
}
|
||||
@@ -41,13 +32,22 @@ export interface BwrapArgsOptions {
|
||||
export async function buildBwrapArgs(
|
||||
options: BwrapArgsOptions,
|
||||
): Promise<string[]> {
|
||||
const {
|
||||
resolvedPaths,
|
||||
workspaceWrite,
|
||||
networkAccess,
|
||||
maskFilePath,
|
||||
isWriteCommand,
|
||||
} = options;
|
||||
const { workspace } = resolvedPaths;
|
||||
|
||||
const bwrapArgs: string[] = [
|
||||
'--unshare-all',
|
||||
'--new-session', // Isolate session
|
||||
'--die-with-parent', // Prevent orphaned runaway processes
|
||||
];
|
||||
|
||||
if (options.networkAccess || options.additionalPermissions.network) {
|
||||
if (networkAccess) {
|
||||
bwrapArgs.push('--share-net');
|
||||
}
|
||||
|
||||
@@ -63,23 +63,16 @@ export async function buildBwrapArgs(
|
||||
'/tmp',
|
||||
);
|
||||
|
||||
const workspacePath = tryRealpath(options.workspace);
|
||||
const bindFlag = workspaceWrite ? '--bind-try' : '--ro-bind-try';
|
||||
|
||||
const bindFlag = options.workspaceWrite ? '--bind-try' : '--ro-bind-try';
|
||||
|
||||
if (options.workspaceWrite) {
|
||||
bwrapArgs.push('--bind-try', options.workspace, options.workspace);
|
||||
if (workspacePath !== options.workspace) {
|
||||
bwrapArgs.push('--bind-try', workspacePath, workspacePath);
|
||||
}
|
||||
} else {
|
||||
bwrapArgs.push('--ro-bind-try', options.workspace, options.workspace);
|
||||
if (workspacePath !== options.workspace) {
|
||||
bwrapArgs.push('--ro-bind-try', workspacePath, workspacePath);
|
||||
}
|
||||
bwrapArgs.push(bindFlag, workspace.original, workspace.original);
|
||||
if (workspace.resolved !== workspace.original) {
|
||||
bwrapArgs.push(bindFlag, workspace.resolved, workspace.resolved);
|
||||
}
|
||||
|
||||
const { worktreeGitDir, mainGitDir } = resolveGitWorktreePaths(workspacePath);
|
||||
const { worktreeGitDir, mainGitDir } = resolveGitWorktreePaths(
|
||||
workspace.resolved,
|
||||
);
|
||||
if (worktreeGitDir) {
|
||||
bwrapArgs.push(bindFlag, worktreeGitDir, worktreeGitDir);
|
||||
}
|
||||
@@ -87,110 +80,62 @@ export async function buildBwrapArgs(
|
||||
bwrapArgs.push(bindFlag, mainGitDir, mainGitDir);
|
||||
}
|
||||
|
||||
const includeDirs = sanitizePaths(options.includeDirectories);
|
||||
for (const includeDir of includeDirs) {
|
||||
try {
|
||||
const resolved = tryRealpath(includeDir);
|
||||
bwrapArgs.push('--ro-bind-try', resolved, resolved);
|
||||
} catch {
|
||||
// Ignore
|
||||
}
|
||||
for (const includeDir of resolvedPaths.globalIncludes) {
|
||||
bwrapArgs.push('--ro-bind-try', includeDir, includeDir);
|
||||
}
|
||||
|
||||
const normalizedWorkspace = normalize(workspacePath).replace(/\/$/, '');
|
||||
for (const allowedPath of options.allowedPaths) {
|
||||
const resolved = tryRealpath(allowedPath);
|
||||
if (!fs.existsSync(resolved)) {
|
||||
for (const allowedPath of resolvedPaths.policyAllowed) {
|
||||
if (fs.existsSync(allowedPath)) {
|
||||
bwrapArgs.push('--bind-try', allowedPath, allowedPath);
|
||||
} else {
|
||||
// If the path doesn't exist, we still want to allow access to its parent
|
||||
// if it's explicitly allowed, to enable creating it.
|
||||
try {
|
||||
const resolvedParent = tryRealpath(dirname(resolved));
|
||||
bwrapArgs.push(
|
||||
options.isWriteCommand ? '--bind-try' : bindFlag,
|
||||
resolvedParent,
|
||||
resolvedParent,
|
||||
);
|
||||
} catch {
|
||||
// Ignore
|
||||
}
|
||||
continue;
|
||||
}
|
||||
const normalizedAllowedPath = normalize(resolved).replace(/\/$/, '');
|
||||
if (normalizedAllowedPath !== normalizedWorkspace) {
|
||||
bwrapArgs.push('--bind-try', resolved, resolved);
|
||||
// to enable creating it. Since allowedPath is already resolved by resolveSandboxPaths,
|
||||
// its parent is also correctly resolved.
|
||||
const parent = dirname(allowedPath);
|
||||
bwrapArgs.push(isWriteCommand ? '--bind-try' : bindFlag, parent, parent);
|
||||
}
|
||||
}
|
||||
|
||||
const additionalReads = sanitizePaths(
|
||||
options.additionalPermissions.fileSystem?.read,
|
||||
);
|
||||
for (const p of additionalReads) {
|
||||
try {
|
||||
const safeResolvedPath = tryRealpath(p);
|
||||
bwrapArgs.push('--ro-bind-try', safeResolvedPath, safeResolvedPath);
|
||||
} catch (e: unknown) {
|
||||
debugLogger.warn(e instanceof Error ? e.message : String(e));
|
||||
}
|
||||
for (const p of resolvedPaths.policyRead) {
|
||||
bwrapArgs.push('--ro-bind-try', p, p);
|
||||
}
|
||||
|
||||
const additionalWrites = sanitizePaths(
|
||||
options.additionalPermissions.fileSystem?.write,
|
||||
);
|
||||
for (const p of additionalWrites) {
|
||||
try {
|
||||
const safeResolvedPath = tryRealpath(p);
|
||||
bwrapArgs.push('--bind-try', safeResolvedPath, safeResolvedPath);
|
||||
} catch (e: unknown) {
|
||||
debugLogger.warn(e instanceof Error ? e.message : String(e));
|
||||
}
|
||||
for (const p of resolvedPaths.policyWrite) {
|
||||
bwrapArgs.push('--bind-try', p, p);
|
||||
}
|
||||
|
||||
for (const file of GOVERNANCE_FILES) {
|
||||
const filePath = join(options.workspace, file.path);
|
||||
const realPath = tryRealpath(filePath);
|
||||
const filePath = join(workspace.original, file.path);
|
||||
const realPath = join(workspace.resolved, file.path);
|
||||
bwrapArgs.push('--ro-bind', filePath, filePath);
|
||||
if (realPath !== filePath) {
|
||||
bwrapArgs.push('--ro-bind', realPath, realPath);
|
||||
}
|
||||
}
|
||||
|
||||
for (const p of options.forbiddenPaths) {
|
||||
let resolved: string;
|
||||
for (const p of resolvedPaths.forbidden) {
|
||||
if (!fs.existsSync(p)) continue;
|
||||
try {
|
||||
resolved = tryRealpath(p); // Forbidden paths should still resolve to block the real path
|
||||
if (!fs.existsSync(resolved)) continue;
|
||||
} catch (e: unknown) {
|
||||
debugLogger.warn(
|
||||
`Failed to resolve forbidden path ${p}: ${e instanceof Error ? e.message : String(e)}`,
|
||||
);
|
||||
bwrapArgs.push('--ro-bind', '/dev/null', p);
|
||||
continue;
|
||||
}
|
||||
try {
|
||||
const stat = fs.statSync(resolved);
|
||||
const stat = fs.statSync(p);
|
||||
if (stat.isDirectory()) {
|
||||
bwrapArgs.push('--tmpfs', resolved, '--remount-ro', resolved);
|
||||
bwrapArgs.push('--tmpfs', p, '--remount-ro', p);
|
||||
} else {
|
||||
bwrapArgs.push('--ro-bind', '/dev/null', resolved);
|
||||
bwrapArgs.push('--ro-bind', '/dev/null', p);
|
||||
}
|
||||
} catch (e: unknown) {
|
||||
if (isErrnoException(e) && e.code === 'ENOENT') {
|
||||
bwrapArgs.push('--symlink', '/dev/null', resolved);
|
||||
bwrapArgs.push('--symlink', '/dev/null', p);
|
||||
} else {
|
||||
debugLogger.warn(
|
||||
`Failed to stat forbidden path ${resolved}: ${e instanceof Error ? e.message : String(e)}`,
|
||||
`Failed to secure forbidden path ${p}: ${e instanceof Error ? e.message : String(e)}`,
|
||||
);
|
||||
bwrapArgs.push('--ro-bind', '/dev/null', resolved);
|
||||
bwrapArgs.push('--ro-bind', '/dev/null', p);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Mask secret files (.env, .env.*)
|
||||
const secretArgs = await getSecretFilesArgs(
|
||||
options.workspace,
|
||||
options.allowedPaths,
|
||||
options.maskFilePath,
|
||||
);
|
||||
const secretArgs = await getSecretFilesArgs(resolvedPaths, maskFilePath);
|
||||
bwrapArgs.push(...secretArgs);
|
||||
|
||||
return bwrapArgs;
|
||||
@@ -200,12 +145,16 @@ export async function buildBwrapArgs(
|
||||
* Generates bubblewrap arguments to mask secret files.
|
||||
*/
|
||||
async function getSecretFilesArgs(
|
||||
workspace: string,
|
||||
allowedPaths: string[],
|
||||
resolvedPaths: ResolvedSandboxPaths,
|
||||
maskPath: string,
|
||||
): Promise<string[]> {
|
||||
const args: string[] = [];
|
||||
const searchDirs = new Set([workspace, ...allowedPaths]);
|
||||
const searchDirs = new Set([
|
||||
resolvedPaths.workspace.original,
|
||||
resolvedPaths.workspace.resolved,
|
||||
...resolvedPaths.policyAllowed,
|
||||
...resolvedPaths.globalIncludes,
|
||||
]);
|
||||
const findPatterns = getSecretFileFindArgs();
|
||||
|
||||
for (const dir of searchDirs) {
|
||||
|
||||
@@ -64,20 +64,12 @@ describe('MacOsSandboxManager', () => {
|
||||
policy: mockPolicy,
|
||||
});
|
||||
|
||||
expect(seatbeltArgsBuilder.buildSeatbeltProfile).toHaveBeenCalledWith({
|
||||
workspace: mockWorkspace,
|
||||
allowedPaths: mockAllowedPaths,
|
||||
forbiddenPaths: [],
|
||||
networkAccess: mockNetworkAccess,
|
||||
workspaceWrite: false,
|
||||
additionalPermissions: {
|
||||
fileSystem: {
|
||||
read: [],
|
||||
write: [],
|
||||
},
|
||||
network: true,
|
||||
},
|
||||
});
|
||||
expect(seatbeltArgsBuilder.buildSeatbeltProfile).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
networkAccess: true,
|
||||
workspaceWrite: false,
|
||||
}),
|
||||
);
|
||||
|
||||
expect(result.program).toBe('/usr/bin/sandbox-exec');
|
||||
expect(result.args[0]).toBe('-f');
|
||||
@@ -155,11 +147,10 @@ describe('MacOsSandboxManager', () => {
|
||||
|
||||
expect(seatbeltArgsBuilder.buildSeatbeltProfile).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
additionalPermissions: expect.objectContaining({
|
||||
fileSystem: expect.objectContaining({
|
||||
read: expect.not.arrayContaining(['/']),
|
||||
write: expect.not.arrayContaining(['/']),
|
||||
}),
|
||||
workspaceWrite: true,
|
||||
resolvedPaths: expect.objectContaining({
|
||||
policyRead: expect.not.arrayContaining(['/']),
|
||||
policyWrite: expect.not.arrayContaining(['/']),
|
||||
}),
|
||||
}),
|
||||
);
|
||||
@@ -213,7 +204,11 @@ describe('MacOsSandboxManager', () => {
|
||||
// The seatbelt builder internally handles governance files, so we simply verify
|
||||
// it is invoked correctly with the right workspace.
|
||||
expect(seatbeltArgsBuilder.buildSeatbeltProfile).toHaveBeenCalledWith(
|
||||
expect.objectContaining({ workspace: mockWorkspace }),
|
||||
expect.objectContaining({
|
||||
resolvedPaths: expect.objectContaining({
|
||||
workspace: { resolved: mockWorkspace, original: mockWorkspace },
|
||||
}),
|
||||
}),
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -233,7 +228,12 @@ describe('MacOsSandboxManager', () => {
|
||||
|
||||
expect(seatbeltArgsBuilder.buildSeatbeltProfile).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
allowedPaths: ['/tmp/allowed1', '/tmp/allowed2'],
|
||||
resolvedPaths: expect.objectContaining({
|
||||
policyAllowed: expect.arrayContaining([
|
||||
'/tmp/allowed1',
|
||||
'/tmp/allowed2',
|
||||
]),
|
||||
}),
|
||||
}),
|
||||
);
|
||||
});
|
||||
@@ -255,7 +255,9 @@ describe('MacOsSandboxManager', () => {
|
||||
|
||||
expect(seatbeltArgsBuilder.buildSeatbeltProfile).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
forbiddenPaths: ['/tmp/forbidden1'],
|
||||
resolvedPaths: expect.objectContaining({
|
||||
forbidden: expect.arrayContaining(['/tmp/forbidden1']),
|
||||
}),
|
||||
}),
|
||||
);
|
||||
});
|
||||
@@ -275,7 +277,9 @@ describe('MacOsSandboxManager', () => {
|
||||
|
||||
expect(seatbeltArgsBuilder.buildSeatbeltProfile).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
forbiddenPaths: ['/tmp/does-not-exist'],
|
||||
resolvedPaths: expect.objectContaining({
|
||||
forbidden: expect.arrayContaining(['/tmp/does-not-exist']),
|
||||
}),
|
||||
}),
|
||||
);
|
||||
});
|
||||
@@ -298,8 +302,10 @@ describe('MacOsSandboxManager', () => {
|
||||
|
||||
expect(seatbeltArgsBuilder.buildSeatbeltProfile).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
allowedPaths: [],
|
||||
forbiddenPaths: ['/tmp/conflict'],
|
||||
resolvedPaths: expect.objectContaining({
|
||||
policyAllowed: [],
|
||||
forbidden: expect.arrayContaining(['/tmp/conflict']),
|
||||
}),
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
@@ -106,13 +106,9 @@ export class MacOsSandboxManager implements SandboxManager {
|
||||
|
||||
const isYolo = this.options.modeConfig?.yolo ?? false;
|
||||
const workspaceWrite = !isReadonlyMode || isApproved || isYolo;
|
||||
|
||||
const defaultNetwork =
|
||||
this.options.modeConfig?.network || req.policy?.networkAccess || isYolo;
|
||||
|
||||
const { allowed: allowedPaths, forbidden: forbiddenPaths } =
|
||||
await resolveSandboxPaths(this.options, req);
|
||||
|
||||
// Fetch persistent approvals for this command
|
||||
const commandName = await getFullCommandName(currentReq);
|
||||
const persistentPermissions = allowOverrides
|
||||
@@ -141,19 +137,22 @@ export class MacOsSandboxManager implements SandboxManager {
|
||||
req,
|
||||
mergedAdditional,
|
||||
this.options.workspace,
|
||||
req.policy?.allowedPaths,
|
||||
[
|
||||
...(req.policy?.allowedPaths || []),
|
||||
...(this.options.includeDirectories || []),
|
||||
],
|
||||
);
|
||||
|
||||
const resolvedPaths = await resolveSandboxPaths(
|
||||
this.options,
|
||||
req,
|
||||
mergedAdditional,
|
||||
);
|
||||
|
||||
const sandboxArgs = buildSeatbeltProfile({
|
||||
workspace: this.options.workspace,
|
||||
allowedPaths: [
|
||||
...allowedPaths,
|
||||
...(this.options.includeDirectories || []),
|
||||
],
|
||||
forbiddenPaths,
|
||||
resolvedPaths,
|
||||
networkAccess: mergedAdditional.network,
|
||||
workspaceWrite,
|
||||
additionalPermissions: mergedAdditional,
|
||||
});
|
||||
|
||||
const tempFile = this.writeProfileToTempFile(sandboxArgs);
|
||||
|
||||
@@ -8,18 +8,21 @@ import {
|
||||
buildSeatbeltProfile,
|
||||
escapeSchemeString,
|
||||
} from './seatbeltArgsBuilder.js';
|
||||
import * as fsUtils from '../utils/fsUtils.js';
|
||||
import type { ResolvedSandboxPaths } from '../../services/sandboxManager.js';
|
||||
import fs from 'node:fs';
|
||||
import os from 'node:os';
|
||||
|
||||
vi.mock('../utils/fsUtils.js', async () => {
|
||||
const actual = await vi.importActual('../utils/fsUtils.js');
|
||||
return {
|
||||
...actual,
|
||||
tryRealpath: vi.fn((p) => p),
|
||||
resolveGitWorktreePaths: vi.fn(() => ({})),
|
||||
};
|
||||
});
|
||||
const defaultResolvedPaths: ResolvedSandboxPaths = {
|
||||
workspace: {
|
||||
resolved: '/Users/test/workspace',
|
||||
original: '/Users/test/raw-workspace',
|
||||
},
|
||||
forbidden: [],
|
||||
globalIncludes: [],
|
||||
policyAllowed: [],
|
||||
policyRead: [],
|
||||
policyWrite: [],
|
||||
};
|
||||
|
||||
describe.skipIf(os.platform() === 'win32')('seatbeltArgsBuilder', () => {
|
||||
afterEach(() => {
|
||||
@@ -35,12 +38,8 @@ describe.skipIf(os.platform() === 'win32')('seatbeltArgsBuilder', () => {
|
||||
|
||||
describe('buildSeatbeltProfile', () => {
|
||||
it('should build a strict allowlist profile allowing the workspace', () => {
|
||||
vi.mocked(fsUtils.tryRealpath).mockImplementation((p) => p);
|
||||
|
||||
const profile = buildSeatbeltProfile({
|
||||
workspace: '/Users/test/workspace',
|
||||
allowedPaths: [],
|
||||
forbiddenPaths: [],
|
||||
resolvedPaths: defaultResolvedPaths,
|
||||
});
|
||||
|
||||
expect(profile).toContain('(version 1)');
|
||||
@@ -51,11 +50,11 @@ describe.skipIf(os.platform() === 'win32')('seatbeltArgsBuilder', () => {
|
||||
});
|
||||
|
||||
it('should allow network when networkAccess is true', () => {
|
||||
vi.mocked(fsUtils.tryRealpath).mockImplementation((p) => p);
|
||||
const profile = buildSeatbeltProfile({
|
||||
workspace: '/test',
|
||||
allowedPaths: [],
|
||||
forbiddenPaths: [],
|
||||
resolvedPaths: {
|
||||
...defaultResolvedPaths,
|
||||
workspace: { resolved: '/test', original: '/test' },
|
||||
},
|
||||
networkAccess: true,
|
||||
});
|
||||
expect(profile).toContain('(allow network-outbound)');
|
||||
@@ -63,7 +62,6 @@ describe.skipIf(os.platform() === 'win32')('seatbeltArgsBuilder', () => {
|
||||
|
||||
describe('governance files', () => {
|
||||
it('should inject explicit deny rules for governance files', () => {
|
||||
vi.mocked(fsUtils.tryRealpath).mockImplementation((p) => p.toString());
|
||||
vi.spyOn(fs, 'existsSync').mockReturnValue(true);
|
||||
vi.spyOn(fs, 'lstatSync').mockImplementation(
|
||||
(p) =>
|
||||
@@ -74,9 +72,13 @@ describe.skipIf(os.platform() === 'win32')('seatbeltArgsBuilder', () => {
|
||||
);
|
||||
|
||||
const profile = buildSeatbeltProfile({
|
||||
workspace: '/test/workspace',
|
||||
allowedPaths: [],
|
||||
forbiddenPaths: [],
|
||||
resolvedPaths: {
|
||||
...defaultResolvedPaths,
|
||||
workspace: {
|
||||
resolved: '/test/workspace',
|
||||
original: '/test/workspace',
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
expect(profile).toContain(
|
||||
@@ -87,48 +89,16 @@ describe.skipIf(os.platform() === 'win32')('seatbeltArgsBuilder', () => {
|
||||
`(deny file-write* (subpath "/test/workspace/.git"))`,
|
||||
);
|
||||
});
|
||||
|
||||
it('should protect both the symlink and the real path if they differ', () => {
|
||||
vi.mocked(fsUtils.tryRealpath).mockImplementation((p) => {
|
||||
if (p === '/test/workspace/.gitignore')
|
||||
return '/test/real/.gitignore';
|
||||
return p.toString();
|
||||
});
|
||||
vi.spyOn(fs, 'existsSync').mockReturnValue(true);
|
||||
vi.spyOn(fs, 'lstatSync').mockImplementation(
|
||||
() =>
|
||||
({
|
||||
isDirectory: () => false,
|
||||
isFile: () => true,
|
||||
}) as unknown as fs.Stats,
|
||||
);
|
||||
|
||||
const profile = buildSeatbeltProfile({
|
||||
workspace: '/test/workspace',
|
||||
allowedPaths: [],
|
||||
forbiddenPaths: [],
|
||||
});
|
||||
|
||||
expect(profile).toContain(
|
||||
`(deny file-write* (literal "/test/workspace/.gitignore"))`,
|
||||
);
|
||||
expect(profile).toContain(
|
||||
`(deny file-write* (literal "/test/real/.gitignore"))`,
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe('allowedPaths', () => {
|
||||
it('should embed allowed paths and normalize them', () => {
|
||||
vi.mocked(fsUtils.tryRealpath).mockImplementation((p) => {
|
||||
if (p === '/test/symlink') return '/test/real_path';
|
||||
return p;
|
||||
});
|
||||
|
||||
it('should embed allowed paths', () => {
|
||||
const profile = buildSeatbeltProfile({
|
||||
workspace: '/test',
|
||||
allowedPaths: ['/custom/path1', '/test/symlink'],
|
||||
forbiddenPaths: [],
|
||||
resolvedPaths: {
|
||||
...defaultResolvedPaths,
|
||||
workspace: { resolved: '/test', original: '/test' },
|
||||
policyAllowed: ['/custom/path1', '/test/real_path'],
|
||||
},
|
||||
});
|
||||
|
||||
expect(profile).toContain(`(subpath "/custom/path1")`);
|
||||
@@ -138,12 +108,12 @@ describe.skipIf(os.platform() === 'win32')('seatbeltArgsBuilder', () => {
|
||||
|
||||
describe('forbiddenPaths', () => {
|
||||
it('should explicitly deny forbidden paths', () => {
|
||||
vi.mocked(fsUtils.tryRealpath).mockImplementation((p) => p);
|
||||
|
||||
const profile = buildSeatbeltProfile({
|
||||
workspace: '/test',
|
||||
allowedPaths: [],
|
||||
forbiddenPaths: ['/secret/path'],
|
||||
resolvedPaths: {
|
||||
...defaultResolvedPaths,
|
||||
workspace: { resolved: '/test', original: '/test' },
|
||||
forbidden: ['/secret/path'],
|
||||
},
|
||||
});
|
||||
|
||||
expect(profile).toContain(
|
||||
@@ -151,46 +121,14 @@ describe.skipIf(os.platform() === 'win32')('seatbeltArgsBuilder', () => {
|
||||
);
|
||||
});
|
||||
|
||||
it('resolves forbidden symlink paths to their real paths', () => {
|
||||
vi.mocked(fsUtils.tryRealpath).mockImplementation((p) => {
|
||||
if (p === '/test/symlink' || p === '/test/missing-dir') {
|
||||
return '/test/real_path';
|
||||
}
|
||||
return p;
|
||||
});
|
||||
|
||||
const profile = buildSeatbeltProfile({
|
||||
workspace: '/test',
|
||||
allowedPaths: [],
|
||||
forbiddenPaths: ['/test/symlink'],
|
||||
});
|
||||
|
||||
expect(profile).toContain(
|
||||
`(deny file-read* file-write* (subpath "/test/real_path"))`,
|
||||
);
|
||||
});
|
||||
|
||||
it('explicitly denies non-existent forbidden paths to prevent creation', () => {
|
||||
vi.mocked(fsUtils.tryRealpath).mockImplementation((p) => p);
|
||||
|
||||
const profile = buildSeatbeltProfile({
|
||||
workspace: '/test',
|
||||
allowedPaths: [],
|
||||
forbiddenPaths: ['/test/missing-dir/missing-file.txt'],
|
||||
});
|
||||
|
||||
expect(profile).toContain(
|
||||
`(deny file-read* file-write* (subpath "/test/missing-dir/missing-file.txt"))`,
|
||||
);
|
||||
});
|
||||
|
||||
it('should override allowed paths if a path is also in forbidden paths', () => {
|
||||
vi.mocked(fsUtils.tryRealpath).mockImplementation((p) => p);
|
||||
|
||||
const profile = buildSeatbeltProfile({
|
||||
workspace: '/test',
|
||||
allowedPaths: ['/custom/path1'],
|
||||
forbiddenPaths: ['/custom/path1'],
|
||||
resolvedPaths: {
|
||||
...defaultResolvedPaths,
|
||||
workspace: { resolved: '/test', original: '/test' },
|
||||
policyAllowed: ['/custom/path1'],
|
||||
forbidden: ['/custom/path1'],
|
||||
},
|
||||
});
|
||||
|
||||
const allowString = `(allow file-read* file-write* (subpath "/custom/path1"))`;
|
||||
|
||||
@@ -12,9 +12,9 @@ import {
|
||||
NETWORK_SEATBELT_PROFILE,
|
||||
} from './baseProfile.js';
|
||||
import {
|
||||
type SandboxPermissions,
|
||||
GOVERNANCE_FILES,
|
||||
SECRET_FILES,
|
||||
type ResolvedSandboxPaths,
|
||||
} from '../../services/sandboxManager.js';
|
||||
import { tryRealpath, resolveGitWorktreePaths } from '../utils/fsUtils.js';
|
||||
|
||||
@@ -22,16 +22,10 @@ import { tryRealpath, resolveGitWorktreePaths } from '../utils/fsUtils.js';
|
||||
* Options for building macOS Seatbelt profile.
|
||||
*/
|
||||
export interface SeatbeltArgsOptions {
|
||||
/** The primary workspace path to allow access to. */
|
||||
workspace: string;
|
||||
/** Additional paths to allow access to. */
|
||||
allowedPaths: string[];
|
||||
/** Absolute paths to explicitly deny read/write access to (overrides allowlists). */
|
||||
forbiddenPaths: string[];
|
||||
/** Fully resolved paths for the sandbox execution. */
|
||||
resolvedPaths: ResolvedSandboxPaths;
|
||||
/** Whether to allow network access. */
|
||||
networkAccess?: boolean;
|
||||
/** Granular additional permissions. */
|
||||
additionalPermissions?: SandboxPermissions;
|
||||
/** Whether to allow write access to the workspace. */
|
||||
workspaceWrite?: boolean;
|
||||
}
|
||||
@@ -49,72 +43,22 @@ export function escapeSchemeString(str: string): string {
|
||||
*/
|
||||
export function buildSeatbeltProfile(options: SeatbeltArgsOptions): string {
|
||||
let profile = BASE_SEATBELT_PROFILE + '\n';
|
||||
const { resolvedPaths, networkAccess, workspaceWrite } = options;
|
||||
|
||||
const workspacePath = tryRealpath(options.workspace);
|
||||
profile += `(allow file-read* (subpath "${escapeSchemeString(options.workspace)}"))\n`;
|
||||
profile += `(allow file-read* (subpath "${escapeSchemeString(workspacePath)}"))\n`;
|
||||
if (options.workspaceWrite) {
|
||||
profile += `(allow file-write* (subpath "${escapeSchemeString(options.workspace)}"))\n`;
|
||||
profile += `(allow file-write* (subpath "${escapeSchemeString(workspacePath)}"))\n`;
|
||||
profile += `(allow file-read* (subpath "${escapeSchemeString(resolvedPaths.workspace.original)}"))\n`;
|
||||
profile += `(allow file-read* (subpath "${escapeSchemeString(resolvedPaths.workspace.resolved)}"))\n`;
|
||||
if (workspaceWrite) {
|
||||
profile += `(allow file-write* (subpath "${escapeSchemeString(resolvedPaths.workspace.original)}"))\n`;
|
||||
profile += `(allow file-write* (subpath "${escapeSchemeString(resolvedPaths.workspace.resolved)}"))\n`;
|
||||
}
|
||||
|
||||
const tmpPath = tryRealpath(os.tmpdir());
|
||||
profile += `(allow file-read* file-write* (subpath "${escapeSchemeString(tmpPath)}"))\n`;
|
||||
|
||||
// Add explicit deny rules for governance files in the workspace.
|
||||
// These are added after the workspace allow rule to ensure they take precedence
|
||||
// (Seatbelt evaluates rules in order, later rules win for same path).
|
||||
for (let i = 0; i < GOVERNANCE_FILES.length; i++) {
|
||||
const governanceFile = path.join(workspacePath, GOVERNANCE_FILES[i].path);
|
||||
const realGovernanceFile = tryRealpath(governanceFile);
|
||||
|
||||
// Determine if it should be treated as a directory (subpath) or a file (literal).
|
||||
// .git is generally a directory, while ignore files are literals.
|
||||
let isDirectory = GOVERNANCE_FILES[i].isDirectory;
|
||||
try {
|
||||
if (fs.existsSync(realGovernanceFile)) {
|
||||
isDirectory = fs.lstatSync(realGovernanceFile).isDirectory();
|
||||
}
|
||||
} catch {
|
||||
// Ignore errors, use default guess
|
||||
}
|
||||
|
||||
const ruleType = isDirectory ? 'subpath' : 'literal';
|
||||
|
||||
profile += `(deny file-write* (${ruleType} "${escapeSchemeString(governanceFile)}"))\n`;
|
||||
|
||||
if (realGovernanceFile !== governanceFile) {
|
||||
profile += `(deny file-write* (${ruleType} "${escapeSchemeString(realGovernanceFile)}"))\n`;
|
||||
}
|
||||
}
|
||||
|
||||
// Add explicit deny rules for secret files (.env, .env.*) in the workspace and allowed paths.
|
||||
// We use regex rules to avoid expensive file discovery scans.
|
||||
// Anchoring to workspace/allowed paths to avoid over-blocking.
|
||||
const searchPaths = [options.workspace, ...options.allowedPaths];
|
||||
|
||||
for (const basePath of searchPaths) {
|
||||
const resolvedBase = tryRealpath(basePath);
|
||||
for (const secret of SECRET_FILES) {
|
||||
// Map pattern to Seatbelt regex
|
||||
let regexPattern: string;
|
||||
const escapedBase = escapeRegex(resolvedBase);
|
||||
if (secret.pattern.endsWith('*')) {
|
||||
// .env.* -> .env\..+ (match .env followed by dot and something)
|
||||
// We anchor the secret file name to either a directory separator or the start of the relative path.
|
||||
const basePattern = secret.pattern.slice(0, -1).replace(/\./g, '\\\\.');
|
||||
regexPattern = `^${escapedBase}/(.*/)?${basePattern}[^/]+$`;
|
||||
} else {
|
||||
// .env -> \.env$
|
||||
const basePattern = secret.pattern.replace(/\./g, '\\\\.');
|
||||
regexPattern = `^${escapedBase}/(.*/)?${basePattern}$`;
|
||||
}
|
||||
profile += `(deny file-read* file-write* (regex #"${regexPattern}"))\n`;
|
||||
}
|
||||
}
|
||||
|
||||
// Auto-detect and support git worktrees by granting read and write access to the underlying git directory
|
||||
const { worktreeGitDir, mainGitDir } = resolveGitWorktreePaths(workspacePath);
|
||||
const { worktreeGitDir, mainGitDir } = resolveGitWorktreePaths(
|
||||
resolvedPaths.workspace.resolved,
|
||||
);
|
||||
if (worktreeGitDir) {
|
||||
profile += `(allow file-read* file-write* (subpath "${escapeSchemeString(worktreeGitDir)}"))\n`;
|
||||
}
|
||||
@@ -154,58 +98,115 @@ export function buildSeatbeltProfile(options: SeatbeltArgsOptions): string {
|
||||
}
|
||||
}
|
||||
|
||||
// Handle allowedPaths
|
||||
const allowedPaths = options.allowedPaths;
|
||||
// Handle allowedPaths and globalIncludes
|
||||
const allowedPaths = [
|
||||
...resolvedPaths.policyAllowed,
|
||||
...resolvedPaths.globalIncludes,
|
||||
];
|
||||
for (let i = 0; i < allowedPaths.length; i++) {
|
||||
const allowedPath = tryRealpath(allowedPaths[i]);
|
||||
const allowedPath = allowedPaths[i];
|
||||
profile += `(allow file-read* file-write* (subpath "${escapeSchemeString(allowedPath)}"))\n`;
|
||||
}
|
||||
|
||||
// Handle granular additional permissions
|
||||
if (options.additionalPermissions?.fileSystem) {
|
||||
const { read, write } = options.additionalPermissions.fileSystem;
|
||||
if (read) {
|
||||
for (let i = 0; i < read.length; i++) {
|
||||
const resolved = tryRealpath(read[i]);
|
||||
let isFile = false;
|
||||
try {
|
||||
isFile = fs.statSync(resolved).isFile();
|
||||
} catch {
|
||||
// Ignore error
|
||||
}
|
||||
if (isFile) {
|
||||
profile += `(allow file-read* (literal "${escapeSchemeString(resolved)}"))\n`;
|
||||
} else {
|
||||
profile += `(allow file-read* (subpath "${escapeSchemeString(resolved)}"))\n`;
|
||||
}
|
||||
}
|
||||
// Handle granular additional read permissions
|
||||
for (let i = 0; i < resolvedPaths.policyRead.length; i++) {
|
||||
const resolved = resolvedPaths.policyRead[i];
|
||||
let isFile = false;
|
||||
try {
|
||||
isFile = fs.statSync(resolved).isFile();
|
||||
} catch {
|
||||
// Ignore error
|
||||
}
|
||||
if (write) {
|
||||
for (let i = 0; i < write.length; i++) {
|
||||
const resolved = tryRealpath(write[i]);
|
||||
let isFile = false;
|
||||
try {
|
||||
isFile = fs.statSync(resolved).isFile();
|
||||
} catch {
|
||||
// Ignore error
|
||||
}
|
||||
if (isFile) {
|
||||
profile += `(allow file-read* file-write* (literal "${escapeSchemeString(resolved)}"))\n`;
|
||||
} else {
|
||||
profile += `(allow file-read* file-write* (subpath "${escapeSchemeString(resolved)}"))\n`;
|
||||
}
|
||||
if (isFile) {
|
||||
profile += `(allow file-read* (literal "${escapeSchemeString(resolved)}"))\n`;
|
||||
} else {
|
||||
profile += `(allow file-read* (subpath "${escapeSchemeString(resolved)}"))\n`;
|
||||
}
|
||||
}
|
||||
|
||||
// Handle granular additional write permissions
|
||||
for (let i = 0; i < resolvedPaths.policyWrite.length; i++) {
|
||||
const resolved = resolvedPaths.policyWrite[i];
|
||||
let isFile = false;
|
||||
try {
|
||||
isFile = fs.statSync(resolved).isFile();
|
||||
} catch {
|
||||
// Ignore error
|
||||
}
|
||||
if (isFile) {
|
||||
profile += `(allow file-read* file-write* (literal "${escapeSchemeString(resolved)}"))\n`;
|
||||
} else {
|
||||
profile += `(allow file-read* file-write* (subpath "${escapeSchemeString(resolved)}"))\n`;
|
||||
}
|
||||
}
|
||||
|
||||
// Add explicit deny rules for governance files in the workspace.
|
||||
// These are added after the workspace allow rule to ensure they take precedence
|
||||
// (Seatbelt evaluates rules in order, later rules win for same path).
|
||||
for (let i = 0; i < GOVERNANCE_FILES.length; i++) {
|
||||
const governanceFile = path.join(
|
||||
resolvedPaths.workspace.resolved,
|
||||
GOVERNANCE_FILES[i].path,
|
||||
);
|
||||
const realGovernanceFile = tryRealpath(governanceFile);
|
||||
|
||||
// Determine if it should be treated as a directory (subpath) or a file (literal).
|
||||
// .git is generally a directory, while ignore files are literals.
|
||||
let isDirectory = GOVERNANCE_FILES[i].isDirectory;
|
||||
try {
|
||||
if (fs.existsSync(realGovernanceFile)) {
|
||||
isDirectory = fs.lstatSync(realGovernanceFile).isDirectory();
|
||||
}
|
||||
} catch {
|
||||
// Ignore errors, use default guess
|
||||
}
|
||||
|
||||
const ruleType = isDirectory ? 'subpath' : 'literal';
|
||||
|
||||
profile += `(deny file-write* (${ruleType} "${escapeSchemeString(governanceFile)}"))\n`;
|
||||
|
||||
if (realGovernanceFile !== governanceFile) {
|
||||
profile += `(deny file-write* (${ruleType} "${escapeSchemeString(realGovernanceFile)}"))\n`;
|
||||
}
|
||||
}
|
||||
|
||||
// Add explicit deny rules for secret files (.env, .env.*) in the workspace and allowed paths.
|
||||
// We use regex rules to avoid expensive file discovery scans.
|
||||
// Anchoring to workspace/allowed paths to avoid over-blocking.
|
||||
const searchPaths = [
|
||||
resolvedPaths.workspace.resolved,
|
||||
resolvedPaths.workspace.original,
|
||||
...resolvedPaths.policyAllowed,
|
||||
...resolvedPaths.globalIncludes,
|
||||
];
|
||||
|
||||
for (const basePath of searchPaths) {
|
||||
for (const secret of SECRET_FILES) {
|
||||
// Map pattern to Seatbelt regex
|
||||
let regexPattern: string;
|
||||
const escapedBase = escapeRegex(basePath);
|
||||
if (secret.pattern.endsWith('*')) {
|
||||
// .env.* -> .env\..+ (match .env followed by dot and something)
|
||||
// We anchor the secret file name to either a directory separator or the start of the relative path.
|
||||
const basePattern = secret.pattern.slice(0, -1).replace(/\./g, '\\\\.');
|
||||
regexPattern = `^${escapedBase}/(.*/)?${basePattern}[^/]+$`;
|
||||
} else {
|
||||
// .env -> \.env$
|
||||
const basePattern = secret.pattern.replace(/\./g, '\\\\.');
|
||||
regexPattern = `^${escapedBase}/(.*/)?${basePattern}$`;
|
||||
}
|
||||
profile += `(deny file-read* file-write* (regex #"${regexPattern}"))\n`;
|
||||
}
|
||||
}
|
||||
|
||||
// Handle forbiddenPaths
|
||||
const forbiddenPaths = options.forbiddenPaths;
|
||||
const forbiddenPaths = resolvedPaths.forbidden;
|
||||
for (let i = 0; i < forbiddenPaths.length; i++) {
|
||||
const forbiddenPath = tryRealpath(forbiddenPaths[i]);
|
||||
const forbiddenPath = forbiddenPaths[i];
|
||||
profile += `(deny file-read* file-write* (subpath "${escapeSchemeString(forbiddenPath)}"))\n`;
|
||||
}
|
||||
|
||||
if (options.networkAccess || options.additionalPermissions?.network) {
|
||||
if (networkAccess) {
|
||||
profile += NETWORK_SEATBELT_PROFILE;
|
||||
}
|
||||
|
||||
|
||||
@@ -398,16 +398,16 @@ describe('WindowsSandboxManager', () => {
|
||||
expect(icaclsArgs).toContainEqual([
|
||||
path.resolve(longPath),
|
||||
'/grant',
|
||||
'*S-1-16-4096:(OI)(CI)(M)',
|
||||
'*S-1-16-4096:(M)',
|
||||
'/setintegritylevel',
|
||||
'(OI)(CI)Low',
|
||||
'Low',
|
||||
]);
|
||||
expect(icaclsArgs).toContainEqual([
|
||||
path.resolve(devicePath),
|
||||
'/grant',
|
||||
'*S-1-16-4096:(OI)(CI)(M)',
|
||||
'*S-1-16-4096:(M)',
|
||||
'/setintegritylevel',
|
||||
'(OI)(CI)Low',
|
||||
'Low',
|
||||
]);
|
||||
},
|
||||
);
|
||||
|
||||
@@ -15,7 +15,6 @@ import {
|
||||
GOVERNANCE_FILES,
|
||||
findSecretFiles,
|
||||
type GlobalSandboxOptions,
|
||||
sanitizePaths,
|
||||
type SandboxPermissions,
|
||||
type ParsedSandboxDenial,
|
||||
resolveSandboxPaths,
|
||||
@@ -51,6 +50,10 @@ const __dirname = path.dirname(__filename);
|
||||
// S-1-16-4096 is the SID for "Low Mandatory Level" (Low Integrity)
|
||||
const LOW_INTEGRITY_SID = '*S-1-16-4096';
|
||||
|
||||
// icacls flags: (OI) Object Inherit, (CI) Container Inherits.
|
||||
// Omit /T (recursive) for performance; (OI)(CI) ensures inheritance for new items.
|
||||
const DIRECTORY_FLAGS = '(OI)(CI)';
|
||||
|
||||
/**
|
||||
* A SandboxManager implementation for Windows that uses Restricted Tokens,
|
||||
* Job Objects, and Low Integrity levels for process isolation.
|
||||
@@ -277,8 +280,11 @@ export class WindowsSandboxManager implements SandboxManager {
|
||||
this.options.modeConfig?.network ?? req.policy?.networkAccess ?? false;
|
||||
const networkAccess = defaultNetwork || mergedAdditional.network;
|
||||
|
||||
const { allowed: allowedPaths, forbidden: forbiddenPaths } =
|
||||
await resolveSandboxPaths(this.options, req);
|
||||
const resolvedPaths = await resolveSandboxPaths(
|
||||
this.options,
|
||||
req,
|
||||
mergedAdditional,
|
||||
);
|
||||
|
||||
// Track all roots where Low Integrity write access has been granted.
|
||||
// New files created within these roots will inherit the Low label.
|
||||
@@ -294,51 +300,45 @@ export class WindowsSandboxManager implements SandboxManager {
|
||||
: false;
|
||||
|
||||
if (!isReadonlyMode || isApproved) {
|
||||
await this.grantLowIntegrityAccess(this.options.workspace);
|
||||
writableRoots.push(this.options.workspace);
|
||||
await this.grantLowIntegrityAccess(resolvedPaths.workspace.resolved);
|
||||
writableRoots.push(resolvedPaths.workspace.resolved);
|
||||
}
|
||||
|
||||
// 2. Globally included directories
|
||||
const includeDirs = sanitizePaths(this.options.includeDirectories);
|
||||
for (const includeDir of includeDirs) {
|
||||
for (const includeDir of resolvedPaths.globalIncludes) {
|
||||
await this.grantLowIntegrityAccess(includeDir);
|
||||
writableRoots.push(includeDir);
|
||||
}
|
||||
|
||||
// 3. Explicitly allowed paths from the request policy
|
||||
for (const allowedPath of allowedPaths) {
|
||||
const resolved = resolveToRealPath(allowedPath);
|
||||
for (const allowedPath of resolvedPaths.policyAllowed) {
|
||||
try {
|
||||
await fs.promises.access(resolved, fs.constants.F_OK);
|
||||
await fs.promises.access(allowedPath, fs.constants.F_OK);
|
||||
} catch {
|
||||
throw new Error(
|
||||
`Sandbox request rejected: Allowed path does not exist: ${resolved}. ` +
|
||||
`Sandbox request rejected: Allowed path does not exist: ${allowedPath}. ` +
|
||||
'On Windows, granular sandbox access can only be granted to existing paths to avoid broad parent directory permissions.',
|
||||
);
|
||||
}
|
||||
await this.grantLowIntegrityAccess(resolved);
|
||||
writableRoots.push(resolved);
|
||||
await this.grantLowIntegrityAccess(allowedPath);
|
||||
writableRoots.push(allowedPath);
|
||||
}
|
||||
|
||||
// 4. Additional write paths (e.g. from internal __write command)
|
||||
const additionalWritePaths = sanitizePaths(
|
||||
mergedAdditional.fileSystem?.write,
|
||||
);
|
||||
for (const writePath of additionalWritePaths) {
|
||||
const resolved = resolveToRealPath(writePath);
|
||||
for (const writePath of resolvedPaths.policyWrite) {
|
||||
try {
|
||||
await fs.promises.access(resolved, fs.constants.F_OK);
|
||||
await this.grantLowIntegrityAccess(resolved);
|
||||
await fs.promises.access(writePath, fs.constants.F_OK);
|
||||
await this.grantLowIntegrityAccess(writePath);
|
||||
continue;
|
||||
} catch {
|
||||
// If the file doesn't exist, it's only allowed if it resides within a granted root.
|
||||
const isInherited = writableRoots.some((root) =>
|
||||
isSubpath(root, resolved),
|
||||
isSubpath(root, writePath),
|
||||
);
|
||||
|
||||
if (!isInherited) {
|
||||
throw new Error(
|
||||
`Sandbox request rejected: Additional write path does not exist and its parent directory is not allowed: ${resolved}. ` +
|
||||
`Sandbox request rejected: Additional write path does not exist and its parent directory is not allowed: ${writePath}. ` +
|
||||
'On Windows, granular sandbox access can only be granted to existing paths to avoid broad parent directory permissions.',
|
||||
);
|
||||
}
|
||||
@@ -350,9 +350,9 @@ export class WindowsSandboxManager implements SandboxManager {
|
||||
// processes to ensure they cannot be read or written.
|
||||
const secretsToBlock: string[] = [];
|
||||
const searchDirs = new Set([
|
||||
this.options.workspace,
|
||||
...allowedPaths,
|
||||
...includeDirs,
|
||||
resolvedPaths.workspace.resolved,
|
||||
...resolvedPaths.policyAllowed,
|
||||
...resolvedPaths.globalIncludes,
|
||||
]);
|
||||
for (const dir of searchDirs) {
|
||||
try {
|
||||
@@ -382,7 +382,7 @@ export class WindowsSandboxManager implements SandboxManager {
|
||||
// is restricted to avoid host corruption. External commands rely on
|
||||
// Low Integrity read/write restrictions, while internal commands
|
||||
// use the manifest for enforcement.
|
||||
for (const forbiddenPath of forbiddenPaths) {
|
||||
for (const forbiddenPath of resolvedPaths.forbidden) {
|
||||
try {
|
||||
await this.denyLowIntegrityAccess(forbiddenPath);
|
||||
} catch (e) {
|
||||
@@ -398,14 +398,14 @@ export class WindowsSandboxManager implements SandboxManager {
|
||||
// the sandboxed process from creating them with Low integrity.
|
||||
// By being created as Medium integrity, they are write-protected from Low processes.
|
||||
for (const file of GOVERNANCE_FILES) {
|
||||
const filePath = path.join(this.options.workspace, file.path);
|
||||
const filePath = path.join(resolvedPaths.workspace.resolved, file.path);
|
||||
this.touch(filePath, file.isDirectory);
|
||||
}
|
||||
|
||||
// 4. Forbidden paths manifest
|
||||
// We use a manifest file to avoid command-line length limits.
|
||||
const allForbidden = Array.from(
|
||||
new Set([...secretsToBlock, ...forbiddenPaths]),
|
||||
new Set([...secretsToBlock, ...resolvedPaths.forbidden]),
|
||||
);
|
||||
const tempDir = fs.mkdtempSync(
|
||||
path.join(os.tmpdir(), 'gemini-cli-forbidden-'),
|
||||
@@ -475,14 +475,19 @@ export class WindowsSandboxManager implements SandboxManager {
|
||||
}
|
||||
|
||||
try {
|
||||
const stats = await fs.promises.stat(resolvedPath);
|
||||
const isDirectory = stats.isDirectory();
|
||||
|
||||
const flags = isDirectory ? DIRECTORY_FLAGS : '';
|
||||
|
||||
// 1. Grant explicit Modify access to the Low Integrity SID
|
||||
// 2. Set the Mandatory Label to Low to allow "Write Up" from Low processes
|
||||
await spawnAsync('icacls', [
|
||||
resolvedPath,
|
||||
'/grant',
|
||||
`${LOW_INTEGRITY_SID}:(OI)(CI)(M)`,
|
||||
`${LOW_INTEGRITY_SID}:${flags}(M)`,
|
||||
'/setintegritylevel',
|
||||
'(OI)(CI)Low',
|
||||
`${flags}Low`,
|
||||
]);
|
||||
this.allowedCache.add(resolvedPath);
|
||||
} catch (e) {
|
||||
@@ -512,29 +517,26 @@ export class WindowsSandboxManager implements SandboxManager {
|
||||
return;
|
||||
}
|
||||
|
||||
// icacls flags: (OI) Object Inherit, (CI) Container Inherit, (F) Full Access Deny.
|
||||
// Omit /T (recursive) for performance; (OI)(CI) ensures inheritance for new items.
|
||||
// Windows dynamically evaluates existing items, though deep explicit Allow ACEs
|
||||
// could potentially bypass this inherited Deny rule.
|
||||
const DENY_ALL_INHERIT = '(OI)(CI)(F)';
|
||||
|
||||
// icacls fails on non-existent paths, so we cannot explicitly deny
|
||||
// paths that do not yet exist (unlike macOS/Linux).
|
||||
// Skip to prevent sandbox initialization failure.
|
||||
let isDirectory = false;
|
||||
try {
|
||||
await fs.promises.stat(resolvedPath);
|
||||
const stats = await fs.promises.stat(resolvedPath);
|
||||
isDirectory = stats.isDirectory();
|
||||
} catch (e: unknown) {
|
||||
if (isNodeError(e) && e.code === 'ENOENT') {
|
||||
return;
|
||||
}
|
||||
throw e;
|
||||
}
|
||||
const flags = isDirectory ? DIRECTORY_FLAGS : '';
|
||||
|
||||
try {
|
||||
await spawnAsync('icacls', [
|
||||
resolvedPath,
|
||||
'/deny',
|
||||
`${LOW_INTEGRITY_SID}:${DENY_ALL_INHERIT}`,
|
||||
`${LOW_INTEGRITY_SID}:${flags}(F)`,
|
||||
]);
|
||||
this.deniedCache.add(resolvedPath);
|
||||
} catch (e) {
|
||||
|
||||
@@ -51,8 +51,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
getPolicyEngine: vi.fn().mockReturnValue(mockPolicyEngine),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
|
||||
@@ -79,8 +79,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
getPolicyEngine: vi.fn().mockReturnValue(mockPolicyEngine),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
|
||||
@@ -161,8 +161,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
getPolicyEngine: vi.fn().mockReturnValue(mockPolicyEngine),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
|
||||
@@ -226,8 +226,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
getPolicyEngine: vi.fn().mockReturnValue(mockPolicyEngine),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
const toolCall = {
|
||||
request: { name: 'test-tool', args: {}, isClientInitiated: true },
|
||||
tool: { name: 'test-tool' },
|
||||
@@ -243,8 +243,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
const mockMessageBus = {
|
||||
@@ -273,8 +273,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
const mockMessageBus = {
|
||||
@@ -307,6 +307,7 @@ describe('policy.ts', () => {
|
||||
isTrustedFolder: vi.fn().mockReturnValue(false),
|
||||
getWorkspacePoliciesDir: vi.fn().mockReturnValue(undefined),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
@@ -339,8 +340,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
const mockMessageBus = {
|
||||
@@ -379,8 +380,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
const mockMessageBus = {
|
||||
@@ -420,8 +421,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
const mockMessageBus = {
|
||||
@@ -447,8 +448,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
const mockMessageBus = {
|
||||
@@ -473,8 +474,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
const mockMessageBus = {
|
||||
@@ -499,8 +500,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
const mockMessageBus = {
|
||||
@@ -540,8 +541,8 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
mockConfig as Config;
|
||||
const mockMessageBus = {
|
||||
@@ -583,6 +584,7 @@ describe('policy.ts', () => {
|
||||
isTrustedFolder: vi.fn().mockReturnValue(false),
|
||||
getWorkspacePoliciesDir: vi.fn().mockReturnValue(undefined),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config =
|
||||
@@ -628,6 +630,7 @@ describe('policy.ts', () => {
|
||||
.fn()
|
||||
.mockReturnValue('/mock/project/policies'),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
const mockMessageBus = {
|
||||
publish: vi.fn(),
|
||||
@@ -659,6 +662,7 @@ describe('policy.ts', () => {
|
||||
.fn()
|
||||
.mockReturnValue('/mock/project/policies'),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
const mockMessageBus = {
|
||||
publish: vi.fn(),
|
||||
@@ -689,6 +693,7 @@ describe('policy.ts', () => {
|
||||
getWorkspacePoliciesDir: vi.fn().mockReturnValue(undefined),
|
||||
getTargetDir: vi.fn().mockReturnValue('/mock/dir'),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
const mockMessageBus = {
|
||||
publish: vi.fn(),
|
||||
@@ -727,6 +732,7 @@ describe('policy.ts', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
const mockMessageBus = {
|
||||
publish: vi.fn(),
|
||||
@@ -766,6 +772,7 @@ describe('policy.ts', () => {
|
||||
it('should return default denial message when no rule provided', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Config;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config = mockConfig;
|
||||
@@ -779,6 +786,7 @@ describe('policy.ts', () => {
|
||||
it('should return custom deny message if provided', () => {
|
||||
const mockConfig = {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Config;
|
||||
|
||||
(mockConfig as unknown as { config: Config }).config = mockConfig;
|
||||
@@ -840,7 +848,6 @@ describe('Plan Mode Denial Consistency', () => {
|
||||
publish: vi.fn(),
|
||||
subscribe: vi.fn(),
|
||||
} as unknown as Mocked<MessageBus>;
|
||||
|
||||
mockConfig = {
|
||||
getPolicyEngine: vi.fn().mockReturnValue(mockPolicyEngine),
|
||||
toolRegistry: mockToolRegistry,
|
||||
@@ -852,6 +859,7 @@ describe('Plan Mode Denial Consistency', () => {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.PLAN), // Key: Plan Mode
|
||||
getTelemetryLogPromptsEnabled: vi.fn().mockReturnValue(false),
|
||||
setApprovalMode: vi.fn(),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
getUsageStatisticsEnabled: vi.fn().mockReturnValue(false),
|
||||
} as unknown as Mocked<Config>;
|
||||
(mockConfig as unknown as { config: Config }).config = mockConfig as Config;
|
||||
@@ -933,6 +941,7 @@ describe('Plan Mode Denial Consistency', () => {
|
||||
getApprovalMode: vi.fn().mockReturnValue(currentMode),
|
||||
isTrustedFolder: vi.fn().mockReturnValue(false),
|
||||
getWorkspacePoliciesDir: vi.fn().mockReturnValue(undefined),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
const mockMessageBus = {
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user