mirror of
https://github.com/google-gemini/gemini-cli.git
synced 2026-07-27 18:21:00 -07:00
Compare commits
94 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Christian Gunderman
|
1fa422a7c6 | ||
|
Christian Gunderman
|
38830bfe81 | ||
|
Christian Gunderman
|
3f1d217d36 | ||
|
Your Name
|
9a147b41a8 | ||
|
Your Name
|
17c9b4341a | ||
|
Your Name
|
68e7e93eaa | ||
|
Your Name
|
87ccf70998 | ||
|
Your Name
|
2f8ea41aeb | ||
|
Your Name
|
264fffbe81 | ||
|
Your Name
|
8cbdbdac04 | ||
|
Your Name
|
c01ed6ff4a | ||
|
Your Name
|
9bd9c0f72d | ||
|
Your Name
|
10ef9a6876 | ||
|
Your Name
|
46c20c6d6e | ||
|
Your Name
|
8fd439678b | ||
|
Your Name
|
28bd094965 | ||
|
Your Name
|
0179a140f0 | ||
|
Your Name
|
1d25931026 | ||
|
Your Name
|
775b36e04a | ||
|
Christian Gunderman
|
f4cd486f90 | ||
|
Your Name
|
f7b67ec3de | ||
|
Your Name
|
4a34f64efa | ||
|
Your Name
|
6e7987696f | ||
|
Christian Gunderman
|
642c244739 | ||
|
Christian Gunderman
|
40e6acf797 | ||
|
Your Name
|
fd5a703684 | ||
|
Your Name
|
aa71d592f9 | ||
|
Your Name
|
9b9ed0c803 | ||
|
Christian Gunderman
|
30d70e862d | ||
|
Your Name
|
b39b74ee09 | ||
|
Christian Gunderman
|
cba2298e5c | ||
|
Christian Gunderman
|
6d353a6c1b | ||
|
Sri Pasumarthi
|
c7b920717f | ||
|
ruomeng
|
15f7b24312 | ||
|
gemini-cli-robot
|
18cb7fd46c | ||
|
Christian Gunderman
|
ca607a5305 | ||
|
Your Name
|
0df3521032 | ||
|
JAYADITYA
|
8b01d78512 | ||
|
gemini-cli-robot
|
56c2397e78 | ||
|
Your Name
|
9287159ccc | ||
|
Your Name
|
f726de12e5 | ||
|
Your Name
|
42022279bb | ||
|
Jacob Richman
|
d1a062bcc4 | ||
|
Your Name
|
57f13a196e | ||
|
Emily Hedlund
|
a39461718c | ||
|
gemini-cli-robot
|
3df99d8bcb | ||
|
Sandy Tao
|
a837b39f8d | ||
|
Christian Gunderman
|
15826637d2 | ||
|
Christian Gunderman
|
e68234a573 | ||
|
Your Name
|
95a175deca | ||
|
Your Name
|
631053bbf4 | ||
|
Your Name
|
84868b49f5 | ||
|
Your Name
|
60ba97e7e6 | ||
|
Your Name
|
23fce4656d | ||
|
Your Name
|
1f2ca6d0e7 | ||
|
Your Name
|
0c48e5f09c | ||
|
Your Name
|
ee0123ad0d | ||
|
Your Name
|
229d570263 | ||
|
Your Name
|
5381a5cc64 | ||
|
Your Name
|
b1d62a0b9d | ||
|
Your Name
|
cd14eb40ce | ||
|
Your Name
|
19c39885e7 | ||
|
Your Name
|
1c76caec6f | ||
|
Your Name
|
5fad1f4053 | ||
|
Your Name
|
e548cd6b0e | ||
|
Your Name
|
1383200054 | ||
|
Your Name
|
256a7a83fa | ||
|
Your Name
|
370e2b9e1d | ||
|
Your Name
|
1754797929 | ||
|
Your Name
|
64b8a6f4a8 | ||
|
Your Name
|
a9cc61349e | ||
|
Your Name
|
94c59405aa | ||
|
Your Name
|
63e8b825a7 | ||
|
Your Name
|
61dacecacf | ||
|
Your Name
|
54e901bf42 | ||
|
Your Name
|
0dc8efb03f | ||
|
Your Name
|
81c8dac01c | ||
|
Your Name
|
f423affe6d | ||
|
Your Name
|
d3d6b9403d | ||
|
Your Name
|
fbcfa40f1d | ||
|
Your Name
|
fc4439ce03 | ||
|
Your Name
|
cf6866c38d | ||
|
Your Name
|
a4b6372d31 | ||
|
Your Name
|
dd7190bf9c | ||
|
Your Name
|
1774abebe9 | ||
|
Your Name
|
c1b06fec0d | ||
|
Your Name
|
d7433ddd03 | ||
|
Your Name
|
2e80fad7a4 | ||
|
Your Name
|
7c2135574c | ||
|
Your Name
|
e601563652 | ||
|
Your Name
|
6867a96be0 | ||
|
Your Name
|
fcaa6c5584 | ||
|
Your Name
|
aa0deb05a4 | ||
|
Your Name
|
ac6dc1d477 |
@@ -2,7 +2,6 @@
|
||||
"experimental": {
|
||||
"extensionReloading": true,
|
||||
"modelSteering": true,
|
||||
"memoryManager": false,
|
||||
"topicUpdateNarration": true
|
||||
},
|
||||
"general": {
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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: {
|
||||
|
||||
@@ -0,0 +1,469 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, expect } from 'vitest';
|
||||
import { componentEvalTest } from './component-test-helper.js';
|
||||
import { SimulationHarness } from '../packages/core/src/context/system-tests/SimulationHarness.js';
|
||||
import type { SidecarConfig } from '../packages/core/src/context/sidecar/types.js';
|
||||
import { Config, LlmRole, getResponseText } from '@google/gemini-cli-core';
|
||||
import fs from 'node:fs';
|
||||
import path from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import type { Content } from '@google/genai';
|
||||
import { EVAL_MODEL } from './test-helper.js';
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = path.dirname(__filename);
|
||||
const DATA_DIR = path.join(__dirname, 'data', 'context_manager');
|
||||
|
||||
interface ScenarioQuestion {
|
||||
id: string;
|
||||
prompt: string;
|
||||
expectedSubstring: string;
|
||||
}
|
||||
|
||||
interface Scenario {
|
||||
scenarioId: string;
|
||||
description: string;
|
||||
history: Content[];
|
||||
questions: ScenarioQuestion[];
|
||||
}
|
||||
|
||||
const getScenario = (id: string): Scenario => {
|
||||
const filePath = path.join(DATA_DIR, 'scenario-c-compiler.json');
|
||||
if (!fs.existsSync(filePath)) {
|
||||
throw new Error(
|
||||
`Scenario file not found at ${filePath}. Run generate-c-compiler-scenario.ts first.`,
|
||||
);
|
||||
}
|
||||
const content = fs.readFileSync(filePath, 'utf-8');
|
||||
return JSON.parse(content) as Scenario;
|
||||
};
|
||||
|
||||
/**
|
||||
* Runs a single evaluation iteration using the SimulationHarness.
|
||||
*/
|
||||
async function runContextManagerEval(
|
||||
config: Config,
|
||||
sidecarConfig: SidecarConfig,
|
||||
seed: number,
|
||||
scenario: Scenario,
|
||||
judge: boolean = true,
|
||||
): Promise<{
|
||||
pass: boolean;
|
||||
response: string;
|
||||
question: ScenarioQuestion;
|
||||
tokens: number;
|
||||
}> {
|
||||
const harness = await SimulationHarness.create(
|
||||
sidecarConfig,
|
||||
config.getBaseLlmClient() as any,
|
||||
path.join(process.cwd(), 'harness-tmp'),
|
||||
);
|
||||
|
||||
// 1. Feed trajectory
|
||||
for (const message of scenario.history) {
|
||||
await harness.simulateTurn([message]);
|
||||
}
|
||||
|
||||
// Ensure background tasks (like StateSnapshotProcessor) have finished
|
||||
|
||||
// 2. Pick a question based on seed
|
||||
const questionIndex = seed % scenario.questions.length;
|
||||
const question = scenario.questions[questionIndex];
|
||||
|
||||
// 3. Project compressed history
|
||||
const compressedHistory =
|
||||
await harness.contextManager.projectCompressedHistory();
|
||||
|
||||
// We can't easily get the episode IDs from the projected Content[],
|
||||
// but we can look at the working buffer instead.
|
||||
const workingBuffer = harness.contextManager.getNodes();
|
||||
console.log('--- WORKING BUFFER EPISODES START ---');
|
||||
workingBuffer.forEach((node: any, i: number) => {
|
||||
console.log(`[Node ${i}] ID: ${node.id}, Type: ${node.type}`);
|
||||
if (node.type === 'USER_PROMPT') {
|
||||
console.log(` Text: ${node.semanticParts?.[0]?.text?.slice(0, 50)}`);
|
||||
}
|
||||
});
|
||||
console.log('--- WORKING BUFFER EPISODES END ---');
|
||||
|
||||
console.log('--- COMPRESSED HISTORY START ---');
|
||||
compressedHistory.forEach((msg, i) => {
|
||||
console.log(`[${i}] Role: ${msg.role}`);
|
||||
(msg.parts || []).forEach((part, j) => {
|
||||
if ('text' in part) {
|
||||
console.log(
|
||||
` Part ${j} (text): ${part.text?.slice(0, 100)}${part.text && part.text.length > 100 ? '...' : ''}`,
|
||||
);
|
||||
} else if ('functionCall' in part) {
|
||||
console.log(` Part ${j} (functionCall): ${part.functionCall?.name}`);
|
||||
} else if ('functionResponse' in part) {
|
||||
console.log(
|
||||
` Part ${j} (functionResponse): ${part.functionResponse?.name}`,
|
||||
);
|
||||
} else {
|
||||
console.log(` Part ${j} (other): ${Object.keys(part).join(', ')}`);
|
||||
}
|
||||
});
|
||||
});
|
||||
console.log('--- COMPRESSED HISTORY END ---');
|
||||
|
||||
// 4. Ask the question
|
||||
const evalPrompt: Content = {
|
||||
role: 'user',
|
||||
parts: [
|
||||
{
|
||||
text: `[SYSTEM: EVALUATION MODE - ANSWER AS TEXT ONLY - DO NOT USE TOOLS]\n\n${question.prompt}\n\nIMPORTANT: Answer in plain text and DO NOT call any tools. Provide the specific information requested.`,
|
||||
},
|
||||
],
|
||||
};
|
||||
|
||||
const response = await config.getContentGenerator().generateContent(
|
||||
{
|
||||
model: config.getModel(),
|
||||
config: {},
|
||||
contents: [...compressedHistory, evalPrompt],
|
||||
},
|
||||
'eval-prompt',
|
||||
LlmRole.UTILITY_TOOL,
|
||||
);
|
||||
|
||||
const responseText = getResponseText(response) ?? '';
|
||||
let pass = false;
|
||||
if (judge) {
|
||||
pass = await judgeResponse(config, question, responseText);
|
||||
} else {
|
||||
// Naive string check for potential failure identification
|
||||
pass = responseText
|
||||
.toLowerCase()
|
||||
.includes(question.expectedSubstring.toLowerCase());
|
||||
}
|
||||
|
||||
const finalTokens = harness.env.tokenCalculator.calculateConcreteListTokens(
|
||||
harness.contextManager.getNodes(),
|
||||
);
|
||||
|
||||
return { pass, response: responseText, question, tokens: finalTokens };
|
||||
}
|
||||
|
||||
/**
|
||||
* Uses an LLM to judge whether the response matches the expected information.
|
||||
*/
|
||||
async function judgeResponse(
|
||||
config: Config,
|
||||
question: ScenarioQuestion,
|
||||
actualResponse: string,
|
||||
): Promise<boolean> {
|
||||
const lowerResponse = actualResponse.toLowerCase();
|
||||
const lowerExpected = question.expectedSubstring.toLowerCase();
|
||||
|
||||
// Fast path: direct substring match
|
||||
if (lowerResponse.includes(lowerExpected)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
const judgePrompt: Content = {
|
||||
role: 'user',
|
||||
parts: [
|
||||
{
|
||||
text: `Evaluate if the AI's response correctly answers the question by explicitly containing the expected information.
|
||||
|
||||
Question: ${question.prompt}
|
||||
Expected Information: ${question.expectedSubstring}
|
||||
AI's Response: ${actualResponse}
|
||||
|
||||
CRITICAL RULES FOR JUDGING:
|
||||
1. The AI's response MUST explicitly answer the question in the prompt and the provided details must match those in 'Expected Information'.
|
||||
2. Do not infer or assume knowledge. Vague, partial, or generalized answers MUST fail.
|
||||
3. If the AI hallucinates, states it cannot find the information, or provides an incomplete answer, it MUST fail.
|
||||
4. Expected information may contain extra details that are not required to answer the question that aren't in the AI's Response. For example: "the answer is X. It was previously Y.". These are still considered to be passing cases.
|
||||
|
||||
Does the AI's response explicitly and completely satisfy the expected information?
|
||||
Respond with ONLY "PASS" or "FAIL".`,
|
||||
},
|
||||
],
|
||||
};
|
||||
|
||||
const response = await config.getContentGenerator().generateContent(
|
||||
{
|
||||
model: EVAL_MODEL,
|
||||
config: { temperature: 0 },
|
||||
contents: [judgePrompt],
|
||||
},
|
||||
'eval-judge',
|
||||
LlmRole.UTILITY_TOOL,
|
||||
);
|
||||
|
||||
const judgeText = getResponseText(response)?.trim().toUpperCase() ?? '';
|
||||
return judgeText === 'PASS';
|
||||
}
|
||||
|
||||
function calculateScenarioTokens(scenario: Scenario): number {
|
||||
let totalChars = 0;
|
||||
for (const message of scenario.history) {
|
||||
for (const part of message.parts || []) {
|
||||
if ('text' in part && part.text) {
|
||||
totalChars += part.text.length;
|
||||
}
|
||||
}
|
||||
}
|
||||
// The SimulationHarness uses 4 chars per token.
|
||||
return Math.ceil(totalChars / 4);
|
||||
}
|
||||
|
||||
function generateRandomSidecarConfig(
|
||||
seed: number,
|
||||
maxRetained: number,
|
||||
): SidecarConfig {
|
||||
// Simple LCG or similar for deterministic randomness from seed if needed,
|
||||
// but for a fuzzer we can just use Math.random and log the seed.
|
||||
const minRetained = Math.min(1000, maxRetained);
|
||||
const retained =
|
||||
minRetained + Math.floor(Math.random() * (maxRetained - minRetained));
|
||||
const max = Math.floor(retained * (1.1 + Math.random() * 2.0)); // 110% to 300% buffer
|
||||
|
||||
const useSquashing = Math.random() > 0.5;
|
||||
const useRollingSummary = Math.random() > 0.5;
|
||||
const useSnapshot = Math.random() > 0.5;
|
||||
|
||||
const processors: any[] = [
|
||||
{
|
||||
processorId: 'ToolMaskingProcessor',
|
||||
options: {
|
||||
stringLengthThresholdTokens: Math.floor(
|
||||
retained * (0.2 + Math.random() * 0.5),
|
||||
),
|
||||
},
|
||||
},
|
||||
{ processorId: 'BlobDegradationProcessor', options: {} },
|
||||
{
|
||||
processorId: 'NodeDistillationProcessor',
|
||||
options: {
|
||||
nodeThresholdTokens: Math.floor(retained * (0.1 + Math.random() * 0.3)),
|
||||
},
|
||||
},
|
||||
{
|
||||
processorId: 'NodeTruncationProcessor',
|
||||
options: {
|
||||
maxTokensPerNode: Math.floor(retained * (0.1 + Math.random() * 0.5)),
|
||||
},
|
||||
},
|
||||
];
|
||||
|
||||
const backgroundProcessors: any[] = [];
|
||||
if (useSquashing) {
|
||||
backgroundProcessors.push({
|
||||
processorId: 'HistoryTruncationProcessor',
|
||||
options: {
|
||||
target: 'freeNTokens',
|
||||
freeTokensTarget: Math.floor(retained * (0.05 + Math.random() * 0.15)),
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
if (useRollingSummary) {
|
||||
backgroundProcessors.push({
|
||||
processorId: 'RollingSummaryProcessor',
|
||||
options: {
|
||||
target: 'freeNTokens',
|
||||
freeTokensTarget: Math.floor(retained * (0.05 + Math.random() * 0.15)),
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
if (useSnapshot) {
|
||||
backgroundProcessors.push({
|
||||
processorId: 'StateSnapshotProcessor',
|
||||
options: {},
|
||||
});
|
||||
}
|
||||
|
||||
const workers: any[] = [];
|
||||
if (useSnapshot && Math.random() > 0.5) {
|
||||
workers.push({
|
||||
workerId: 'StateSnapshotWorker',
|
||||
options: {
|
||||
type: Math.random() > 0.5 ? 'accumulate' : 'point-in-time',
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
return {
|
||||
budget: { retainedTokens: retained, maxTokens: max },
|
||||
pipelines: [
|
||||
{
|
||||
name: 'Immediate Sanitization',
|
||||
triggers: ['new_message'],
|
||||
processors,
|
||||
},
|
||||
{
|
||||
name: 'Deep Background Compression',
|
||||
triggers: [
|
||||
Math.random() > 0.5
|
||||
? { type: 'timer', intervalMs: 100 }
|
||||
: 'gc_backstop',
|
||||
'retained_exceeded',
|
||||
],
|
||||
processors: backgroundProcessors,
|
||||
},
|
||||
],
|
||||
workers: workers.length > 0 ? workers : undefined,
|
||||
};
|
||||
}
|
||||
|
||||
describe('ContextManager Evaluation Suite', () => {
|
||||
const scenario = getScenario('scenario-c-compiler');
|
||||
|
||||
/**
|
||||
* The "Explorer" test.
|
||||
* Set RUN_EXPLORER=1 to run many iterations and find failures.
|
||||
*/
|
||||
if (process.env['RUN_EXPLORER']) {
|
||||
componentEvalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'context-manager',
|
||||
suiteType: 'component-level',
|
||||
name: 'ContextManager explorer (fuzzer)',
|
||||
configOverrides: { model: EVAL_MODEL },
|
||||
timeout: 1200000, // 20 minutes
|
||||
assert: async (config: Config) => {
|
||||
const scenarioTokens = calculateScenarioTokens(scenario);
|
||||
console.log(
|
||||
`Starting ContextManager explorer loop for scenario of size ${scenarioTokens} tokens...`,
|
||||
);
|
||||
for (let i = 0; i < 50; i++) {
|
||||
const seed = Math.floor(Math.random() * 1000000);
|
||||
const sidecarConfig = generateRandomSidecarConfig(
|
||||
seed,
|
||||
scenarioTokens,
|
||||
);
|
||||
|
||||
const result = await runContextManagerEval(
|
||||
config,
|
||||
sidecarConfig,
|
||||
seed,
|
||||
scenario,
|
||||
false, // Optimistic string check
|
||||
);
|
||||
|
||||
if (!result.pass) {
|
||||
// Potential failure. Confirm with LLM judge.
|
||||
result.pass = await judgeResponse(
|
||||
config,
|
||||
result.question,
|
||||
result.response,
|
||||
);
|
||||
}
|
||||
|
||||
if (!result.pass) {
|
||||
console.log('!!! FAILURE FOUND !!!');
|
||||
console.log(`Seed: ${seed}`);
|
||||
console.log(`Question: ${result.question.id}`);
|
||||
console.log(`Expected: ${result.question.expectedSubstring}`);
|
||||
console.log(`Actual Response: ${result.response}`);
|
||||
console.log('---------------------------');
|
||||
console.log(`NEW FROZEN CASE SUGGESTION:`);
|
||||
console.log(`
|
||||
componentEvalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'context-manager',
|
||||
suiteType: 'component-level',
|
||||
name: 'ContextManager Frozen Case - ${result.question.id} (Budget: ${sidecarConfig.budget.retainedTokens})',
|
||||
configOverrides: { model: EVAL_MODEL },
|
||||
assert: async (config: Config) => {
|
||||
const scenario = getScenario('scenario-c-compiler');
|
||||
const sidecarConfig: SidecarConfig = ${JSON.stringify(sidecarConfig, null, 2)};
|
||||
const seed = ${seed};
|
||||
const result = await runContextManagerEval(config, sidecarConfig, seed, scenario);
|
||||
expect(result.pass, \`Recall failed for ${result.question.id}. Response: \${result.response}\`).toBe(true);
|
||||
}
|
||||
});
|
||||
`);
|
||||
} else {
|
||||
console.log(
|
||||
`Iteration ${i} (Budget: ${sidecarConfig.budget.retainedTokens}, Seed: ${seed}) passed.`,
|
||||
);
|
||||
}
|
||||
}
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
// --- Frozen cases discovered by explorer ---
|
||||
|
||||
componentEvalTest('ALWAYS_PASSES', {
|
||||
suiteName: 'context-manager',
|
||||
suiteType: 'component-level',
|
||||
name: 'ContextManager Frozen Case - lexer-constraint (Budget: 3737)',
|
||||
configOverrides: { model: EVAL_MODEL },
|
||||
assert: async (config: Config) => {
|
||||
const scenario = getScenario('scenario-c-compiler');
|
||||
const sidecarConfig: SidecarConfig = {
|
||||
budget: {
|
||||
retainedTokens: 3737,
|
||||
maxTokens: 11280,
|
||||
},
|
||||
pipelines: [
|
||||
{
|
||||
name: 'Immediate Sanitization',
|
||||
triggers: ['new_message'],
|
||||
processors: [
|
||||
{
|
||||
processorId: 'ToolMaskingProcessor',
|
||||
options: {
|
||||
stringLengthThresholdTokens: 2442,
|
||||
},
|
||||
},
|
||||
{
|
||||
processorId: 'BlobDegradationProcessor',
|
||||
options: {},
|
||||
},
|
||||
{
|
||||
processorId: 'NodeDistillationProcessor',
|
||||
options: {
|
||||
nodeThresholdTokens: 733,
|
||||
},
|
||||
},
|
||||
{
|
||||
processorId: 'NodeTruncationProcessor',
|
||||
options: { maxTokensPerNode: 1000 },
|
||||
},
|
||||
],
|
||||
},
|
||||
{
|
||||
name: 'Deep Background Compression',
|
||||
triggers: [
|
||||
{
|
||||
type: 'timer',
|
||||
intervalMs: 100,
|
||||
},
|
||||
'retained_exceeded',
|
||||
],
|
||||
processors: [
|
||||
{
|
||||
processorId: 'HistoryTruncationProcessor',
|
||||
options: {
|
||||
target: 'freeNTokens',
|
||||
freeTokensTarget: 327,
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
};
|
||||
const seed = 288421;
|
||||
const result = await runContextManagerEval(
|
||||
config,
|
||||
sidecarConfig,
|
||||
seed,
|
||||
scenario,
|
||||
);
|
||||
expect(
|
||||
result.pass,
|
||||
`Recall failed for lexer-constraint. Response: ${result.response}`,
|
||||
).toBe(true);
|
||||
},
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,928 @@
|
||||
{
|
||||
"scenarioId": "scenario-c-compiler",
|
||||
"description": "A robust 100-turn trajectory building a C compiler, featuring realistic noise, synchronized tool state, high-entropy data, and superseded architectural decisions.",
|
||||
"history": [
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "How is the test coverage looking lately?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "We're making good progress. We now have 12 unit tests passing across all modules."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Let's call this project 'TitanC'. I think it has a strong, industrial feel."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "'TitanC' sounds excellent. I've initialized the project workspace under that name."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Initially, I'd like to target x86-64 assembly for our compiler backend."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Got it. We will focus on generating x86-64 assembly instructions."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Let's run a full build of TitanC and see if there are any issues."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Executing build for TitanC (Target: x86-64)...\n```\n[CC] src/main.ts -> build/main.o\n[CC] src/lexer.ts -> build/lexer.o\n[CC] src/parser.ts -> build/parser.o\n[CC] src/ast.ts -> build/ast.o\n[CC] src/codegen.ts -> build/codegen.o\n[CC] src/utils.ts -> build/utils.o\n[LD] build/compiler\nBuild successful.\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "I was thinking about the refactoring the visitor pattern for better readability. What's your take?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "That's a valid concern. Given our current architecture in TitanC, we could definitely improve that area. I recommend we prioritize correctness first, then profile to see if it's a bottleneck."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Wait, we just got a new production deployment key: 'PROD_DEPLOY_KEY_XYZ'. This replaces all previous keys, so make sure to use this one from now on."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Updated. The current production deployment key is now PROD_DEPLOY_KEY_XYZ."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "How is the test coverage looking lately?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "We're making good progress. We now have 14 unit tests passing across all modules."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "The client actually needs ARM64 support for their new server farm, so let's pivot from x86-64. It's more energy-efficient and fits their requirements better."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "That's a significant change in direction. Switching the backend architecture to ARM64. I'll adjust the register allocation and instruction set templates accordingly."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "What was the most recent change committed to the repo?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "The latest commit is:\n```\ncommit jn759a\nAuthor: Christian <gundermanc@google.com>\nDate: Mon Feb 2 14:00:00 2026 -0800\n\n docs: add architectural overview\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "What was the most recent change committed to the repo?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "The latest commit is:\n```\ncommit dmp72i\nAuthor: Christian <gundermanc@google.com>\nDate: Mon Feb 2 14:00:00 2026 -0800\n\n refactor: extract token scanner to separate module\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "What was the most recent change committed to the repo?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "The latest commit is:\n```\ncommit g39v9p\nAuthor: Christian <gundermanc@google.com>\nDate: Mon Feb 2 14:00:00 2026 -0800\n\n fix: correctly handle escaped characters in strings\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "For the code generator, let's add a standard header to all generated assembly files. It should say exactly '; Generated by TitanC Compiler v0.1'."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Understood. I will prepend '; Generated by TitanC Compiler v0.1' to all output files generated by the backend."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "I'm reorganizing the project structure. Moving forward, the lexer logic should live in 'src/core/scanner/main.ts' and the parser in 'src/core/parser/main.ts'."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Structure updated. I'll refer to 'src/core/scanner/main.ts' for lexer tasks and 'src/core/parser/main.ts' for parser logic."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "I have a strict requirement for the lexer: we must NOT use any third-party regex libraries. I want it to be a manual character-by-character scanner for maximum performance and to avoid heavy dependencies."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Understood. I'll ensure the lexer implementation avoids external regex libraries and uses manual scanning logic."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "What was the most recent change committed to the repo?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "The latest commit is:\n```\ncommit qdyivi\nAuthor: Christian <gundermanc@google.com>\nDate: Mon Feb 2 14:00:00 2026 -0800\n\n docs: add architectural overview\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Can you list the files in the src directory? I want to make sure I haven't missed anything."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"functionCall": {
|
||||
"name": "ls",
|
||||
"args": {
|
||||
"path": "src/"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"functionResponse": {
|
||||
"name": "ls",
|
||||
"response": {
|
||||
"output": "src/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Sure, here are the files in src/:\nsrc/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "I was thinking about the performance of our hash map implementation. What's your take?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "That's a valid concern. Given our current architecture in TitanC, we could definitely improve that area. I recommend we prioritize correctness first, then profile to see if it's a bottleneck."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Can you list the files in the src directory? I want to make sure I haven't missed anything."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"functionCall": {
|
||||
"name": "ls",
|
||||
"args": {
|
||||
"path": "src/"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"functionResponse": {
|
||||
"name": "ls",
|
||||
"response": {
|
||||
"output": "src/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Sure, here are the files in src/:\nsrc/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Let's define the core tokens for our lexer. We'll need an enum with at least INT, KEYWORD, IDENTIFIER, PLUS, MINUS, SEMICOLON, and EOF."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Understood. I've defined the TokenType enum as requested:\n```typescript\nenum TokenType {\n INT,\n KEYWORD,\n IDENTIFIER,\n PLUS,\n MINUS,\n SEMICOLON,\n EOF\n}\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Can you define the interface for our AST nodes? Each node should have a 'type' property that can be 'Program', 'Function', 'Return', or 'Constant'."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Here is the AST node interface:\n```typescript\ninterface AstNode {\n type: 'Program' | 'Function' | 'Return' | 'Constant';\n value?: any;\n children?: AstNode[];\n}\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "What was the most recent change committed to the repo?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "The latest commit is:\n```\ncommit jgqwe\nAuthor: Christian <gundermanc@google.com>\nDate: Mon Feb 2 14:00:00 2026 -0800\n\n docs: add architectural overview\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Let's run a full build of TitanC and see if there are any issues."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Executing build for TitanC (Target: ARM64)...\n```\n[CC] src/main.ts -> build/main.o\n[CC] src/core/scanner/main.ts -> build/core_scanner_main.o\n[CC] src/core/parser/main.ts -> build/core_parser_main.o\n[CC] src/ast.ts -> build/ast.o\nsrc/ast.ts:60:8: warning: unused variable 'temp' [-Wunused-variable]\n[CC] src/codegen.ts -> build/codegen.o\n[CC] src/utils.ts -> build/utils.o\n[LD] build/compiler\nBuild successful.\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Let's run a full build of TitanC and see if there are any issues."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Executing build for TitanC (Target: ARM64)...\n```\n[CC] src/main.ts -> build/main.o\n[CC] src/core/scanner/main.ts -> build/core_scanner_main.o\nsrc/core/scanner/main.ts:97:8: warning: unused variable 'temp' [-Wunused-variable]\n[CC] src/core/parser/main.ts -> build/core_parser_main.o\n[CC] src/ast.ts -> build/ast.o\nsrc/ast.ts:22:8: warning: unused variable 'temp' [-Wunused-variable]\n[CC] src/codegen.ts -> build/codegen.o\n[CC] src/utils.ts -> build/utils.o\n[LD] build/compiler\nBuild successful.\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Can you list the files in the src directory? I want to make sure I haven't missed anything."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"functionCall": {
|
||||
"name": "ls",
|
||||
"args": {
|
||||
"path": "src/"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"functionResponse": {
|
||||
"name": "ls",
|
||||
"response": {
|
||||
"output": "src/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Sure, here are the files in src/:\nsrc/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Can you list the files in the src directory? I want to make sure I haven't missed anything."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"functionCall": {
|
||||
"name": "ls",
|
||||
"args": {
|
||||
"path": "src/"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"functionResponse": {
|
||||
"name": "ls",
|
||||
"response": {
|
||||
"output": "src/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Sure, here are the files in src/:\nsrc/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "I just found out there's another project called 'TitanC'. To avoid any legal issues, let's rename our compiler to 'GigaC'. We should update all references immediately."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Understood. Safety first. Renaming project from 'TitanC' to 'GigaC'. I'll update all our internal strings and build scripts."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Let's run a full build of GigaC and see if there are any issues."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Executing build for GigaC (Target: ARM64)...\n```\n[CC] src/main.ts -> build/main.o\n[CC] src/core/scanner/main.ts -> build/core_scanner_main.o\nsrc/core/scanner/main.ts:42:8: warning: unused variable 'temp' [-Wunused-variable]\n[CC] src/core/parser/main.ts -> build/core_parser_main.o\n[CC] src/ast.ts -> build/ast.o\n[CC] src/codegen.ts -> build/codegen.o\n[CC] src/utils.ts -> build/utils.o\n[LD] build/compiler\nBuild successful.\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Can you list the files in the src directory? I want to make sure I haven't missed anything."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"functionCall": {
|
||||
"name": "ls",
|
||||
"args": {
|
||||
"path": "src/"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"functionResponse": {
|
||||
"name": "ls",
|
||||
"response": {
|
||||
"output": "src/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Sure, here are the files in src/:\nsrc/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "How is the test coverage looking lately?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "We're making good progress. We now have 15 unit tests passing across all modules."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "For our integration tests, we'll need to use the staging environment. The access code is 'STAGING_READY_2026'. Please keep this secure."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Acknowledged. I've noted the staging environment access code as STAGING_READY_2026 and will treat it as sensitive information."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "What was the most recent change committed to the repo?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "The latest commit is:\n```\ncommit 8s45s\nAuthor: Christian <gundermanc@google.com>\nDate: Mon Feb 2 14:00:00 2026 -0800\n\n fix: correctly handle escaped characters in strings\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "How is the test coverage looking lately?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "We're making good progress. We now have 16 unit tests passing across all modules."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "How is the test coverage looking lately?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "We're making good progress. We now have 17 unit tests passing across all modules."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "I've discovered a critical bug in the lexer. It seems to fail when block comments (/* ... */) span across multiple lines. Let's track this as Bug #404."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Got it. Tracking Bug #404: Lexer fails to handle multi-line block comments. I'll keep this in mind as we refine the scanner."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "I was thinking about the optimizing the constant folding pass. What's your take?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "That's a valid concern. Given our current architecture in GigaC, we could definitely improve that area. I recommend we prioritize correctness first, then profile to see if it's a bottleneck."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Let's run a full build of GigaC and see if there are any issues."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Executing build for GigaC (Target: ARM64)...\n```\n[CC] src/main.ts -> build/main.o\n[CC] src/core/scanner/main.ts -> build/core_scanner_main.o\n[CC] src/core/parser/main.ts -> build/core_parser_main.o\n[CC] src/ast.ts -> build/ast.o\n[CC] src/codegen.ts -> build/codegen.o\nsrc/codegen.ts:82:8: warning: unused variable 'temp' [-Wunused-variable]\n[CC] src/utils.ts -> build/utils.o\n[LD] build/compiler\nBuild successful.\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Can you list the files in the src directory? I want to make sure I haven't missed anything."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"functionCall": {
|
||||
"name": "ls",
|
||||
"args": {
|
||||
"path": "src/"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"functionResponse": {
|
||||
"name": "ls",
|
||||
"response": {
|
||||
"output": "src/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Sure, here are the files in src/:\nsrc/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "What was the most recent change committed to the repo?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "The latest commit is:\n```\ncommit 5tclu\nAuthor: Christian <gundermanc@google.com>\nDate: Mon Feb 2 14:00:00 2026 -0800\n\n test: add edge cases for floating point literals\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "I was thinking about the switching to a data-oriented design for the AST. What's your take?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "That's a valid concern. Given our current architecture in GigaC, we could definitely improve that area. I recommend we prioritize correctness first, then profile to see if it's a bottleneck."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Can you list the files in the src directory? I want to make sure I haven't missed anything."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"functionCall": {
|
||||
"name": "ls",
|
||||
"args": {
|
||||
"path": "src/"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"functionResponse": {
|
||||
"name": "ls",
|
||||
"response": {
|
||||
"output": "src/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "Sure, here are the files in src/:\nsrc/main.ts\nsrc/core/scanner/main.ts\nsrc/core/parser/main.ts\nsrc/ast.ts\nsrc/codegen.ts\nsrc/utils.ts"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "What was the most recent change committed to the repo?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "The latest commit is:\n```\ncommit 0z2ta5\nAuthor: Christian <gundermanc@google.com>\nDate: Mon Feb 2 14:00:00 2026 -0800\n\n perf: optimize lexer lookup table\n```"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "I was thinking about the handling variadic functions in the calling convention. What's your take?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "That's a valid concern. Given our current architecture in GigaC, we could definitely improve that area. I recommend we prioritize correctness first, then profile to see if it's a bottleneck."
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"parts": [
|
||||
{
|
||||
"text": "How is the test coverage looking lately?"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "model",
|
||||
"parts": [
|
||||
{
|
||||
"text": "We're making good progress. We now have 19 unit tests passing across all modules."
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"questions": [
|
||||
{
|
||||
"id": "lexer-enum",
|
||||
"prompt": "What are the first 3 enum values in the TokenType definition for the Lexer?",
|
||||
"expectedSubstring": "INT, KEYWORD, IDENTIFIER"
|
||||
},
|
||||
{
|
||||
"id": "lexer-constraint",
|
||||
"prompt": "What is the primary constraint regarding regex libraries in the lexer?",
|
||||
"expectedSubstring": "no third-party regex libraries"
|
||||
},
|
||||
{
|
||||
"id": "spatial-lexer-path",
|
||||
"prompt": "Where is the core lexer source file located?",
|
||||
"expectedSubstring": "src/core/scanner/main.ts"
|
||||
},
|
||||
{
|
||||
"id": "ast-interface",
|
||||
"prompt": "What are the allowed 'type' values in the AstNode interface?",
|
||||
"expectedSubstring": "Program' | 'Function' | 'Return' | 'Constant"
|
||||
},
|
||||
{
|
||||
"id": "bug-1-description",
|
||||
"prompt": "What was Bug #404 about?",
|
||||
"expectedSubstring": "multi-line block comment"
|
||||
},
|
||||
{
|
||||
"id": "secret-alpha",
|
||||
"prompt": "What is the secret staging environment access code?",
|
||||
"expectedSubstring": "STAGING_READY_2026"
|
||||
},
|
||||
{
|
||||
"id": "secret-beta",
|
||||
"prompt": "What is the production deployment key?",
|
||||
"expectedSubstring": "PROD_DEPLOY_KEY_XYZ"
|
||||
},
|
||||
{
|
||||
"id": "codegen-header",
|
||||
"prompt": "What exact comment line should the code generator emit at the start of every file?",
|
||||
"expectedSubstring": "; Generated by GigaC Compiler v0.1"
|
||||
},
|
||||
{
|
||||
"id": "current-arch",
|
||||
"prompt": "What is the final target architecture we decided on?",
|
||||
"expectedSubstring": "ARM64"
|
||||
},
|
||||
{
|
||||
"id": "final-name",
|
||||
"prompt": "What is the final name of our project after the rename?",
|
||||
"expectedSubstring": "GigaC"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -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
+15
-14
@@ -1,17 +1,17 @@
|
||||
{
|
||||
"name": "@google/gemini-cli",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"name": "@google/gemini-cli",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"workspaces": [
|
||||
"packages/*"
|
||||
],
|
||||
"dependencies": {
|
||||
"ink": "npm:@jrichman/ink@6.6.7",
|
||||
"ink": "npm:@jrichman/ink@6.6.8",
|
||||
"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",
|
||||
@@ -10070,9 +10071,9 @@
|
||||
},
|
||||
"node_modules/ink": {
|
||||
"name": "@jrichman/ink",
|
||||
"version": "6.6.7",
|
||||
"resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.6.7.tgz",
|
||||
"integrity": "sha512-bDzQLpLzK/dn9Ur/Ku88ZZR9totVcMGrGYAgPHidsAAbe9NKztU1fggj/iu0wRp5g1kBeALb3cfagFGdDxAU1w==",
|
||||
"version": "6.6.8",
|
||||
"resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.6.8.tgz",
|
||||
"integrity": "sha512-099iGdvWVIM2ivc3NEWyMF7FT06aLmrx1gMGI02ZYB4wLIFn0v/KQl6+20xEwcM6gyzj8Y8842Sf0UH2z0oTDw==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
@@ -17421,7 +17422,7 @@
|
||||
},
|
||||
"packages/a2a-server": {
|
||||
"name": "@google/gemini-cli-a2a-server",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"dependencies": {
|
||||
"@a2a-js/sdk": "0.3.11",
|
||||
"@google-cloud/storage": "^7.16.0",
|
||||
@@ -17536,7 +17537,7 @@
|
||||
},
|
||||
"packages/cli": {
|
||||
"name": "@google/gemini-cli",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"license": "Apache-2.0",
|
||||
"dependencies": {
|
||||
"@agentclientprotocol/sdk": "^0.16.1",
|
||||
@@ -17558,7 +17559,7 @@
|
||||
"fzf": "^0.5.2",
|
||||
"glob": "^12.0.0",
|
||||
"highlight.js": "^11.11.1",
|
||||
"ink": "npm:@jrichman/ink@6.6.7",
|
||||
"ink": "npm:@jrichman/ink@6.6.8",
|
||||
"ink-gradient": "^3.0.0",
|
||||
"ink-spinner": "^5.0.0",
|
||||
"latest-version": "^9.0.0",
|
||||
@@ -17708,7 +17709,7 @@
|
||||
},
|
||||
"packages/core": {
|
||||
"name": "@google/gemini-cli-core",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"license": "Apache-2.0",
|
||||
"dependencies": {
|
||||
"@a2a-js/sdk": "0.3.11",
|
||||
@@ -17976,7 +17977,7 @@
|
||||
},
|
||||
"packages/devtools": {
|
||||
"name": "@google/gemini-cli-devtools",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"license": "Apache-2.0",
|
||||
"dependencies": {
|
||||
"ws": "^8.16.0"
|
||||
@@ -17991,7 +17992,7 @@
|
||||
},
|
||||
"packages/sdk": {
|
||||
"name": "@google/gemini-cli-sdk",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"license": "Apache-2.0",
|
||||
"dependencies": {
|
||||
"@google/gemini-cli-core": "file:../core",
|
||||
@@ -18008,7 +18009,7 @@
|
||||
},
|
||||
"packages/test-utils": {
|
||||
"name": "@google/gemini-cli-test-utils",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"license": "Apache-2.0",
|
||||
"dependencies": {
|
||||
"@google/gemini-cli-core": "file:../core",
|
||||
@@ -18026,7 +18027,7 @@
|
||||
},
|
||||
"packages/vscode-ide-companion": {
|
||||
"name": "gemini-cli-vscode-ide-companion",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"license": "LICENSE",
|
||||
"dependencies": {
|
||||
"@modelcontextprotocol/sdk": "^1.23.0",
|
||||
|
||||
+7
-4
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@google/gemini-cli",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"engines": {
|
||||
"node": ">=20.0.0"
|
||||
},
|
||||
@@ -14,7 +14,7 @@
|
||||
"url": "git+https://github.com/google-gemini/gemini-cli.git"
|
||||
},
|
||||
"config": {
|
||||
"sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.36.0-nightly.20260317.2f90b4653"
|
||||
"sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.39.0-nightly.20260408.e77b22e63"
|
||||
},
|
||||
"scripts": {
|
||||
"start": "cross-env NODE_ENV=development node scripts/start.js",
|
||||
@@ -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@6.6.7",
|
||||
"ink": "npm:@jrichman/ink@6.6.8",
|
||||
"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@6.6.7",
|
||||
"ink": "npm:@jrichman/ink@6.6.8",
|
||||
"latest-version": "^9.0.0",
|
||||
"node-fetch-native": "^1.6.7",
|
||||
"proper-lockfile": "^4.1.2",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@google/gemini-cli-a2a-server",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"description": "Gemini CLI A2A Server",
|
||||
"repository": {
|
||||
"type": "git",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@google/gemini-cli",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"description": "Gemini CLI",
|
||||
"license": "Apache-2.0",
|
||||
"repository": {
|
||||
@@ -27,7 +27,7 @@
|
||||
"dist"
|
||||
],
|
||||
"config": {
|
||||
"sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.36.0-nightly.20260317.2f90b4653"
|
||||
"sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.39.0-nightly.20260408.e77b22e63"
|
||||
},
|
||||
"dependencies": {
|
||||
"@agentclientprotocol/sdk": "^0.16.1",
|
||||
@@ -49,7 +49,7 @@
|
||||
"fzf": "^0.5.2",
|
||||
"glob": "^12.0.0",
|
||||
"highlight.js": "^11.11.1",
|
||||
"ink": "npm:@jrichman/ink@6.6.7",
|
||||
"ink": "npm:@jrichman/ink@6.6.8",
|
||||
"ink-gradient": "^3.0.0",
|
||||
"ink-spinner": "^5.0.0",
|
||||
"latest-version": "^9.0.0",
|
||||
|
||||
@@ -6,6 +6,7 @@
|
||||
|
||||
import {
|
||||
addMemory,
|
||||
listInboxSkills,
|
||||
listMemoryFiles,
|
||||
refreshMemory,
|
||||
showMemory,
|
||||
@@ -30,6 +31,7 @@ export class MemoryCommand implements Command {
|
||||
new RefreshMemoryCommand(),
|
||||
new ListMemoryCommand(),
|
||||
new AddMemoryCommand(),
|
||||
new InboxMemoryCommand(),
|
||||
];
|
||||
readonly requiresWorkspace = true;
|
||||
|
||||
@@ -122,3 +124,39 @@ export class AddMemoryCommand implements Command {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
export class InboxMemoryCommand implements Command {
|
||||
readonly name = 'memory inbox';
|
||||
readonly description =
|
||||
'Lists skills extracted from past sessions that are pending review.';
|
||||
|
||||
async execute(
|
||||
context: CommandContext,
|
||||
_: string[],
|
||||
): Promise<CommandExecutionResponse> {
|
||||
if (!context.agentContext.config.isMemoryManagerEnabled()) {
|
||||
return {
|
||||
name: this.name,
|
||||
data: 'The memory inbox requires the experimental memory manager. Enable it with: experimental.memoryManager = true in settings.',
|
||||
};
|
||||
}
|
||||
|
||||
const skills = await listInboxSkills(context.agentContext.config);
|
||||
|
||||
if (skills.length === 0) {
|
||||
return { name: this.name, data: 'No extracted skills in inbox.' };
|
||||
}
|
||||
|
||||
const lines = skills.map((s) => {
|
||||
const date = s.extractedAt
|
||||
? ` (extracted: ${new Date(s.extractedAt).toLocaleDateString()})`
|
||||
: '';
|
||||
return `- **${s.name}**: ${s.description}${date}`;
|
||||
});
|
||||
|
||||
return {
|
||||
name: this.name,
|
||||
data: `Skill inbox (${skills.length}):\n${lines.join('\n')}`,
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
@@ -457,4 +457,78 @@ describe('memoryCommand', () => {
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe('/memory inbox', () => {
|
||||
let inboxCommand: SlashCommand;
|
||||
|
||||
beforeEach(() => {
|
||||
inboxCommand = memoryCommand.subCommands!.find(
|
||||
(cmd) => cmd.name === 'inbox',
|
||||
)!;
|
||||
expect(inboxCommand).toBeDefined();
|
||||
});
|
||||
|
||||
it('should return custom_dialog when config is available and flag is enabled', () => {
|
||||
if (!inboxCommand.action) throw new Error('Command has no action');
|
||||
|
||||
const mockConfig = {
|
||||
reloadSkills: vi.fn(),
|
||||
isMemoryManagerEnabled: vi.fn().mockReturnValue(true),
|
||||
};
|
||||
const context = createMockCommandContext({
|
||||
services: {
|
||||
agentContext: { config: mockConfig },
|
||||
},
|
||||
ui: {
|
||||
removeComponent: vi.fn(),
|
||||
reloadCommands: vi.fn(),
|
||||
},
|
||||
});
|
||||
|
||||
const result = inboxCommand.action(context, '');
|
||||
|
||||
expect(result).toHaveProperty('type', 'custom_dialog');
|
||||
expect(result).toHaveProperty('component');
|
||||
});
|
||||
|
||||
it('should return info message when memory manager is disabled', () => {
|
||||
if (!inboxCommand.action) throw new Error('Command has no action');
|
||||
|
||||
const mockConfig = {
|
||||
isMemoryManagerEnabled: vi.fn().mockReturnValue(false),
|
||||
};
|
||||
const context = createMockCommandContext({
|
||||
services: {
|
||||
agentContext: { config: mockConfig },
|
||||
},
|
||||
});
|
||||
|
||||
const result = inboxCommand.action(context, '');
|
||||
|
||||
expect(result).toEqual({
|
||||
type: 'message',
|
||||
messageType: 'info',
|
||||
content:
|
||||
'The memory inbox requires the experimental memory manager. Enable it with: experimental.memoryManager = true in settings.',
|
||||
});
|
||||
});
|
||||
|
||||
it('should return error when config is not loaded', () => {
|
||||
if (!inboxCommand.action) throw new Error('Command has no action');
|
||||
|
||||
const context = createMockCommandContext({
|
||||
services: {
|
||||
agentContext: null,
|
||||
},
|
||||
});
|
||||
|
||||
const result = inboxCommand.action(context, '');
|
||||
|
||||
expect(result).toEqual({
|
||||
type: 'message',
|
||||
messageType: 'error',
|
||||
content: 'Config not loaded.',
|
||||
});
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
@@ -4,6 +4,7 @@
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import React from 'react';
|
||||
import {
|
||||
addMemory,
|
||||
listMemoryFiles,
|
||||
@@ -13,9 +14,11 @@ import {
|
||||
import { MessageType } from '../types.js';
|
||||
import {
|
||||
CommandKind,
|
||||
type OpenCustomDialogActionReturn,
|
||||
type SlashCommand,
|
||||
type SlashCommandActionReturn,
|
||||
} from './types.js';
|
||||
import { SkillInboxDialog } from '../components/SkillInboxDialog.js';
|
||||
|
||||
export const memoryCommand: SlashCommand = {
|
||||
name: 'memory',
|
||||
@@ -124,5 +127,45 @@ export const memoryCommand: SlashCommand = {
|
||||
);
|
||||
},
|
||||
},
|
||||
{
|
||||
name: 'inbox',
|
||||
description:
|
||||
'Review skills extracted from past sessions and move them to global or project skills',
|
||||
kind: CommandKind.BUILT_IN,
|
||||
autoExecute: true,
|
||||
action: (
|
||||
context,
|
||||
): OpenCustomDialogActionReturn | SlashCommandActionReturn | void => {
|
||||
const config = context.services.agentContext?.config;
|
||||
if (!config) {
|
||||
return {
|
||||
type: 'message',
|
||||
messageType: 'error',
|
||||
content: 'Config not loaded.',
|
||||
};
|
||||
}
|
||||
|
||||
if (!config.isMemoryManagerEnabled()) {
|
||||
return {
|
||||
type: 'message',
|
||||
messageType: 'info',
|
||||
content:
|
||||
'The memory inbox requires the experimental memory manager. Enable it with: experimental.memoryManager = true in settings.',
|
||||
};
|
||||
}
|
||||
|
||||
return {
|
||||
type: 'custom_dialog',
|
||||
component: React.createElement(SkillInboxDialog, {
|
||||
config,
|
||||
onClose: () => context.ui.removeComponent(),
|
||||
onReloadSkills: async () => {
|
||||
await config.reloadSkills();
|
||||
context.ui.reloadCommands();
|
||||
},
|
||||
}),
|
||||
};
|
||||
},
|
||||
},
|
||||
],
|
||||
};
|
||||
|
||||
@@ -0,0 +1,187 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { act } from 'react';
|
||||
import { beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
import type { Config, InboxSkill } from '@google/gemini-cli-core';
|
||||
import {
|
||||
dismissInboxSkill,
|
||||
listInboxSkills,
|
||||
moveInboxSkill,
|
||||
} from '@google/gemini-cli-core';
|
||||
import { waitFor } from '../../test-utils/async.js';
|
||||
import { renderWithProviders } from '../../test-utils/render.js';
|
||||
import { SkillInboxDialog } from './SkillInboxDialog.js';
|
||||
|
||||
vi.mock('@google/gemini-cli-core', async (importOriginal) => {
|
||||
const original =
|
||||
await importOriginal<typeof import('@google/gemini-cli-core')>();
|
||||
|
||||
return {
|
||||
...original,
|
||||
dismissInboxSkill: vi.fn(),
|
||||
listInboxSkills: vi.fn(),
|
||||
moveInboxSkill: vi.fn(),
|
||||
getErrorMessage: vi.fn((error: unknown) =>
|
||||
error instanceof Error ? error.message : String(error),
|
||||
),
|
||||
};
|
||||
});
|
||||
|
||||
const mockListInboxSkills = vi.mocked(listInboxSkills);
|
||||
const mockMoveInboxSkill = vi.mocked(moveInboxSkill);
|
||||
const mockDismissInboxSkill = vi.mocked(dismissInboxSkill);
|
||||
|
||||
const inboxSkill: InboxSkill = {
|
||||
dirName: 'inbox-skill',
|
||||
name: 'Inbox Skill',
|
||||
description: 'A test skill',
|
||||
extractedAt: '2025-01-15T10:00:00Z',
|
||||
};
|
||||
|
||||
describe('SkillInboxDialog', () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks();
|
||||
mockListInboxSkills.mockResolvedValue([inboxSkill]);
|
||||
mockMoveInboxSkill.mockResolvedValue({
|
||||
success: true,
|
||||
message: 'Moved "inbox-skill" to ~/.gemini/skills.',
|
||||
});
|
||||
mockDismissInboxSkill.mockResolvedValue({
|
||||
success: true,
|
||||
message: 'Dismissed "inbox-skill" from inbox.',
|
||||
});
|
||||
});
|
||||
|
||||
it('disables the project destination when the workspace is untrusted', async () => {
|
||||
const config = {
|
||||
isTrustedFolder: vi.fn().mockReturnValue(false),
|
||||
} as unknown as Config;
|
||||
const onReloadSkills = vi.fn().mockResolvedValue(undefined);
|
||||
const { lastFrame, stdin, unmount, waitUntilReady } = await act(async () =>
|
||||
renderWithProviders(
|
||||
<SkillInboxDialog
|
||||
config={config}
|
||||
onClose={vi.fn()}
|
||||
onReloadSkills={onReloadSkills}
|
||||
/>,
|
||||
),
|
||||
);
|
||||
|
||||
await waitFor(() => {
|
||||
expect(lastFrame()).toContain('Inbox Skill');
|
||||
});
|
||||
|
||||
await act(async () => {
|
||||
stdin.write('\r');
|
||||
await waitUntilReady();
|
||||
});
|
||||
|
||||
await waitFor(() => {
|
||||
const frame = lastFrame();
|
||||
expect(frame).toContain('Project');
|
||||
expect(frame).toContain('unavailable until this workspace is trusted');
|
||||
});
|
||||
|
||||
await act(async () => {
|
||||
stdin.write('\x1b[B');
|
||||
await waitUntilReady();
|
||||
});
|
||||
|
||||
await act(async () => {
|
||||
stdin.write('\r');
|
||||
await waitUntilReady();
|
||||
});
|
||||
|
||||
await waitFor(() => {
|
||||
expect(mockDismissInboxSkill).toHaveBeenCalledWith(config, 'inbox-skill');
|
||||
});
|
||||
expect(mockMoveInboxSkill).not.toHaveBeenCalled();
|
||||
expect(onReloadSkills).not.toHaveBeenCalled();
|
||||
|
||||
unmount();
|
||||
});
|
||||
|
||||
it('shows inline feedback when moving a skill throws', async () => {
|
||||
mockMoveInboxSkill.mockRejectedValue(new Error('permission denied'));
|
||||
|
||||
const config = {
|
||||
isTrustedFolder: vi.fn().mockReturnValue(true),
|
||||
} as unknown as Config;
|
||||
const { lastFrame, stdin, unmount, waitUntilReady } = await act(async () =>
|
||||
renderWithProviders(
|
||||
<SkillInboxDialog
|
||||
config={config}
|
||||
onClose={vi.fn()}
|
||||
onReloadSkills={vi.fn().mockResolvedValue(undefined)}
|
||||
/>,
|
||||
),
|
||||
);
|
||||
|
||||
await waitFor(() => {
|
||||
expect(lastFrame()).toContain('Inbox Skill');
|
||||
});
|
||||
|
||||
await act(async () => {
|
||||
stdin.write('\r');
|
||||
await waitUntilReady();
|
||||
});
|
||||
|
||||
await act(async () => {
|
||||
stdin.write('\r');
|
||||
await waitUntilReady();
|
||||
});
|
||||
|
||||
await waitFor(() => {
|
||||
const frame = lastFrame();
|
||||
expect(frame).toContain('Move "Inbox Skill"');
|
||||
expect(frame).toContain('Failed to install skill: permission denied');
|
||||
});
|
||||
|
||||
unmount();
|
||||
});
|
||||
|
||||
it('shows inline feedback when reloading skills fails after a move', async () => {
|
||||
const config = {
|
||||
isTrustedFolder: vi.fn().mockReturnValue(true),
|
||||
} as unknown as Config;
|
||||
const onReloadSkills = vi
|
||||
.fn()
|
||||
.mockRejectedValue(new Error('reload hook failed'));
|
||||
const { lastFrame, stdin, unmount, waitUntilReady } = await act(async () =>
|
||||
renderWithProviders(
|
||||
<SkillInboxDialog
|
||||
config={config}
|
||||
onClose={vi.fn()}
|
||||
onReloadSkills={onReloadSkills}
|
||||
/>,
|
||||
),
|
||||
);
|
||||
|
||||
await waitFor(() => {
|
||||
expect(lastFrame()).toContain('Inbox Skill');
|
||||
});
|
||||
|
||||
await act(async () => {
|
||||
stdin.write('\r');
|
||||
await waitUntilReady();
|
||||
});
|
||||
|
||||
await act(async () => {
|
||||
stdin.write('\r');
|
||||
await waitUntilReady();
|
||||
});
|
||||
|
||||
await waitFor(() => {
|
||||
expect(lastFrame()).toContain(
|
||||
'Moved "inbox-skill" to ~/.gemini/skills. Failed to reload skills: reload hook failed',
|
||||
);
|
||||
});
|
||||
expect(onReloadSkills).toHaveBeenCalledTimes(1);
|
||||
|
||||
unmount();
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,378 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type React from 'react';
|
||||
import { useState, useMemo, useCallback, useEffect } from 'react';
|
||||
import { Box, Text } from 'ink';
|
||||
import { theme } from '../semantic-colors.js';
|
||||
import { useKeypress } from '../hooks/useKeypress.js';
|
||||
import { Command } from '../key/keyMatchers.js';
|
||||
import { useKeyMatchers } from '../hooks/useKeyMatchers.js';
|
||||
import { BaseSelectionList } from './shared/BaseSelectionList.js';
|
||||
import type { SelectionListItem } from '../hooks/useSelectionList.js';
|
||||
import { DialogFooter } from './shared/DialogFooter.js';
|
||||
import {
|
||||
type Config,
|
||||
type InboxSkill,
|
||||
type InboxSkillDestination,
|
||||
getErrorMessage,
|
||||
listInboxSkills,
|
||||
moveInboxSkill,
|
||||
dismissInboxSkill,
|
||||
} from '@google/gemini-cli-core';
|
||||
|
||||
type Phase = 'list' | 'action';
|
||||
|
||||
interface DestinationChoice {
|
||||
destination: InboxSkillDestination | 'dismiss';
|
||||
label: string;
|
||||
description: string;
|
||||
}
|
||||
|
||||
const DESTINATION_CHOICES: DestinationChoice[] = [
|
||||
{
|
||||
destination: 'global',
|
||||
label: 'Global',
|
||||
description: '~/.gemini/skills — available in all projects',
|
||||
},
|
||||
{
|
||||
destination: 'project',
|
||||
label: 'Project',
|
||||
description: '.gemini/skills — available in this workspace',
|
||||
},
|
||||
{
|
||||
destination: 'dismiss',
|
||||
label: 'Dismiss',
|
||||
description: 'Delete from inbox',
|
||||
},
|
||||
];
|
||||
|
||||
function formatDate(isoString: string): string {
|
||||
try {
|
||||
const date = new Date(isoString);
|
||||
return date.toLocaleDateString(undefined, {
|
||||
year: 'numeric',
|
||||
month: 'short',
|
||||
day: 'numeric',
|
||||
});
|
||||
} catch {
|
||||
return isoString;
|
||||
}
|
||||
}
|
||||
|
||||
interface SkillInboxDialogProps {
|
||||
config: Config;
|
||||
onClose: () => void;
|
||||
onReloadSkills: () => Promise<void>;
|
||||
}
|
||||
|
||||
export const SkillInboxDialog: React.FC<SkillInboxDialogProps> = ({
|
||||
config,
|
||||
onClose,
|
||||
onReloadSkills,
|
||||
}) => {
|
||||
const keyMatchers = useKeyMatchers();
|
||||
const isTrustedFolder = config.isTrustedFolder();
|
||||
const [phase, setPhase] = useState<Phase>('list');
|
||||
const [skills, setSkills] = useState<InboxSkill[]>([]);
|
||||
const [loading, setLoading] = useState(true);
|
||||
const [selectedSkill, setSelectedSkill] = useState<InboxSkill | null>(null);
|
||||
const [feedback, setFeedback] = useState<{
|
||||
text: string;
|
||||
isError: boolean;
|
||||
} | null>(null);
|
||||
|
||||
// Load inbox skills on mount
|
||||
useEffect(() => {
|
||||
let cancelled = false;
|
||||
void (async () => {
|
||||
try {
|
||||
const result = await listInboxSkills(config);
|
||||
if (!cancelled) {
|
||||
setSkills(result);
|
||||
setLoading(false);
|
||||
}
|
||||
} catch {
|
||||
if (!cancelled) {
|
||||
setSkills([]);
|
||||
setLoading(false);
|
||||
}
|
||||
}
|
||||
})();
|
||||
return () => {
|
||||
cancelled = true;
|
||||
};
|
||||
}, [config]);
|
||||
|
||||
const skillItems: Array<SelectionListItem<InboxSkill>> = useMemo(
|
||||
() =>
|
||||
skills.map((skill) => ({
|
||||
key: skill.dirName,
|
||||
value: skill,
|
||||
})),
|
||||
[skills],
|
||||
);
|
||||
|
||||
const destinationItems: Array<SelectionListItem<DestinationChoice>> = useMemo(
|
||||
() =>
|
||||
DESTINATION_CHOICES.map((choice) => {
|
||||
if (choice.destination === 'project' && !isTrustedFolder) {
|
||||
return {
|
||||
key: choice.destination,
|
||||
value: {
|
||||
...choice,
|
||||
description:
|
||||
'.gemini/skills — unavailable until this workspace is trusted',
|
||||
},
|
||||
disabled: true,
|
||||
};
|
||||
}
|
||||
|
||||
return {
|
||||
key: choice.destination,
|
||||
value: choice,
|
||||
};
|
||||
}),
|
||||
[isTrustedFolder],
|
||||
);
|
||||
|
||||
const handleSelectSkill = useCallback((skill: InboxSkill) => {
|
||||
setSelectedSkill(skill);
|
||||
setFeedback(null);
|
||||
setPhase('action');
|
||||
}, []);
|
||||
|
||||
const handleSelectDestination = useCallback(
|
||||
(choice: DestinationChoice) => {
|
||||
if (!selectedSkill) return;
|
||||
|
||||
if (choice.destination === 'project' && !config.isTrustedFolder()) {
|
||||
setFeedback({
|
||||
text: 'Project skills are unavailable until this workspace is trusted.',
|
||||
isError: true,
|
||||
});
|
||||
return;
|
||||
}
|
||||
|
||||
setFeedback(null);
|
||||
|
||||
void (async () => {
|
||||
try {
|
||||
let result: { success: boolean; message: string };
|
||||
if (choice.destination === 'dismiss') {
|
||||
result = await dismissInboxSkill(config, selectedSkill.dirName);
|
||||
} else {
|
||||
result = await moveInboxSkill(
|
||||
config,
|
||||
selectedSkill.dirName,
|
||||
choice.destination,
|
||||
);
|
||||
}
|
||||
|
||||
setFeedback({ text: result.message, isError: !result.success });
|
||||
|
||||
if (!result.success) {
|
||||
return;
|
||||
}
|
||||
|
||||
// Remove the skill from the local list.
|
||||
setSkills((prev) =>
|
||||
prev.filter((skill) => skill.dirName !== selectedSkill.dirName),
|
||||
);
|
||||
setSelectedSkill(null);
|
||||
setPhase('list');
|
||||
|
||||
if (choice.destination === 'dismiss') {
|
||||
return;
|
||||
}
|
||||
|
||||
try {
|
||||
await onReloadSkills();
|
||||
} catch (error) {
|
||||
setFeedback({
|
||||
text: `${result.message} Failed to reload skills: ${getErrorMessage(error)}`,
|
||||
isError: true,
|
||||
});
|
||||
}
|
||||
} catch (error) {
|
||||
const operation =
|
||||
choice.destination === 'dismiss'
|
||||
? 'dismiss skill'
|
||||
: 'install skill';
|
||||
setFeedback({
|
||||
text: `Failed to ${operation}: ${getErrorMessage(error)}`,
|
||||
isError: true,
|
||||
});
|
||||
}
|
||||
})();
|
||||
},
|
||||
[config, selectedSkill, onReloadSkills],
|
||||
);
|
||||
|
||||
useKeypress(
|
||||
(key) => {
|
||||
if (keyMatchers[Command.ESCAPE](key)) {
|
||||
if (phase === 'action') {
|
||||
setPhase('list');
|
||||
setSelectedSkill(null);
|
||||
setFeedback(null);
|
||||
} else {
|
||||
onClose();
|
||||
}
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
},
|
||||
{ isActive: true, priority: true },
|
||||
);
|
||||
|
||||
if (loading) {
|
||||
return (
|
||||
<Box
|
||||
flexDirection="column"
|
||||
borderStyle="round"
|
||||
borderColor={theme.border.default}
|
||||
paddingX={2}
|
||||
paddingY={1}
|
||||
>
|
||||
<Text>Loading inbox…</Text>
|
||||
</Box>
|
||||
);
|
||||
}
|
||||
|
||||
if (skills.length === 0 && !feedback) {
|
||||
return (
|
||||
<Box
|
||||
flexDirection="column"
|
||||
borderStyle="round"
|
||||
borderColor={theme.border.default}
|
||||
paddingX={2}
|
||||
paddingY={1}
|
||||
>
|
||||
<Text bold>Skill Inbox</Text>
|
||||
<Box marginTop={1}>
|
||||
<Text color={theme.text.secondary}>
|
||||
No extracted skills in inbox.
|
||||
</Text>
|
||||
</Box>
|
||||
<DialogFooter primaryAction="Esc to close" cancelAction="" />
|
||||
</Box>
|
||||
);
|
||||
}
|
||||
|
||||
return (
|
||||
<Box
|
||||
flexDirection="column"
|
||||
borderStyle="round"
|
||||
borderColor={theme.border.default}
|
||||
paddingX={2}
|
||||
paddingY={1}
|
||||
width="100%"
|
||||
>
|
||||
{phase === 'list' ? (
|
||||
<>
|
||||
<Text bold>
|
||||
Skill Inbox ({skills.length} skill{skills.length !== 1 ? 's' : ''})
|
||||
</Text>
|
||||
<Text color={theme.text.secondary}>
|
||||
Skills extracted from past sessions. Select one to move or dismiss.
|
||||
</Text>
|
||||
|
||||
<Box flexDirection="column" marginTop={1}>
|
||||
<BaseSelectionList<InboxSkill>
|
||||
items={skillItems}
|
||||
onSelect={handleSelectSkill}
|
||||
isFocused={true}
|
||||
showNumbers={true}
|
||||
showScrollArrows={true}
|
||||
maxItemsToShow={8}
|
||||
renderItem={(item, { titleColor }) => (
|
||||
<Box flexDirection="column" minHeight={2}>
|
||||
<Text color={titleColor} bold>
|
||||
{item.value.name}
|
||||
</Text>
|
||||
<Box flexDirection="row">
|
||||
<Text color={theme.text.secondary} wrap="wrap">
|
||||
{item.value.description}
|
||||
</Text>
|
||||
{item.value.extractedAt && (
|
||||
<Text color={theme.text.secondary}>
|
||||
{' · '}
|
||||
{formatDate(item.value.extractedAt)}
|
||||
</Text>
|
||||
)}
|
||||
</Box>
|
||||
</Box>
|
||||
)}
|
||||
/>
|
||||
</Box>
|
||||
|
||||
{feedback && (
|
||||
<Box marginTop={1}>
|
||||
<Text
|
||||
color={
|
||||
feedback.isError ? theme.status.error : theme.status.success
|
||||
}
|
||||
>
|
||||
{feedback.isError ? '✗ ' : '✓ '}
|
||||
{feedback.text}
|
||||
</Text>
|
||||
</Box>
|
||||
)}
|
||||
|
||||
<DialogFooter
|
||||
primaryAction="Enter to select"
|
||||
cancelAction="Esc to close"
|
||||
/>
|
||||
</>
|
||||
) : (
|
||||
<>
|
||||
<Text bold>Move "{selectedSkill?.name}"</Text>
|
||||
<Text color={theme.text.secondary}>
|
||||
Choose where to install this skill.
|
||||
</Text>
|
||||
|
||||
<Box flexDirection="column" marginTop={1}>
|
||||
<BaseSelectionList<DestinationChoice>
|
||||
items={destinationItems}
|
||||
onSelect={handleSelectDestination}
|
||||
isFocused={true}
|
||||
showNumbers={true}
|
||||
renderItem={(item, { titleColor }) => (
|
||||
<Box flexDirection="column" minHeight={2}>
|
||||
<Text color={titleColor} bold>
|
||||
{item.value.label}
|
||||
</Text>
|
||||
<Text color={theme.text.secondary}>
|
||||
{item.value.description}
|
||||
</Text>
|
||||
</Box>
|
||||
)}
|
||||
/>
|
||||
</Box>
|
||||
|
||||
{feedback && (
|
||||
<Box marginTop={1}>
|
||||
<Text
|
||||
color={
|
||||
feedback.isError ? theme.status.error : theme.status.success
|
||||
}
|
||||
>
|
||||
{feedback.isError ? '✗ ' : '✓ '}
|
||||
{feedback.text}
|
||||
</Text>
|
||||
</Box>
|
||||
)}
|
||||
|
||||
<DialogFooter
|
||||
primaryAction="Enter to confirm"
|
||||
cancelAction="Esc to go back"
|
||||
/>
|
||||
</>
|
||||
)}
|
||||
</Box>
|
||||
);
|
||||
};
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@google/gemini-cli-core",
|
||||
"version": "0.36.0-nightly.20260317.2f90b4653",
|
||||
"version": "0.39.0-nightly.20260408.e77b22e63",
|
||||
"description": "Gemini CLI Core",
|
||||
"license": "Apache-2.0",
|
||||
"repository": {
|
||||
|
||||
@@ -4,11 +4,18 @@
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import * as fs from 'node:fs/promises';
|
||||
import * as os from 'node:os';
|
||||
import * as path from 'node:path';
|
||||
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
|
||||
import type { Config } from '../config/config.js';
|
||||
import { Storage } from '../config/storage.js';
|
||||
import {
|
||||
addMemory,
|
||||
dismissInboxSkill,
|
||||
listInboxSkills,
|
||||
listMemoryFiles,
|
||||
moveInboxSkill,
|
||||
refreshMemory,
|
||||
showMemory,
|
||||
} from './memory.js';
|
||||
@@ -18,6 +25,12 @@ vi.mock('../utils/memoryDiscovery.js', () => ({
|
||||
refreshServerHierarchicalMemory: vi.fn(),
|
||||
}));
|
||||
|
||||
vi.mock('../config/storage.js', () => ({
|
||||
Storage: {
|
||||
getUserSkillsDir: vi.fn(),
|
||||
},
|
||||
}));
|
||||
|
||||
const mockRefresh = vi.mocked(memoryDiscovery.refreshServerHierarchicalMemory);
|
||||
|
||||
describe('memory commands', () => {
|
||||
@@ -202,4 +215,317 @@ describe('memory commands', () => {
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('listInboxSkills', () => {
|
||||
let tmpDir: string;
|
||||
let skillsDir: string;
|
||||
let memoryTempDir: string;
|
||||
let inboxConfig: Config;
|
||||
|
||||
async function writeSkillMd(
|
||||
dirName: string,
|
||||
name: string,
|
||||
description: string,
|
||||
): Promise<void> {
|
||||
const dir = path.join(skillsDir, dirName);
|
||||
await fs.mkdir(dir, { recursive: true });
|
||||
await fs.writeFile(
|
||||
path.join(dir, 'SKILL.md'),
|
||||
`---\nname: ${name}\ndescription: ${description}\n---\nBody content here\n`,
|
||||
);
|
||||
}
|
||||
|
||||
beforeEach(async () => {
|
||||
tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), 'inbox-test-'));
|
||||
skillsDir = path.join(tmpDir, 'skills-memory');
|
||||
memoryTempDir = path.join(tmpDir, 'memory-temp');
|
||||
await fs.mkdir(skillsDir, { recursive: true });
|
||||
await fs.mkdir(memoryTempDir, { recursive: true });
|
||||
|
||||
inboxConfig = {
|
||||
storage: {
|
||||
getProjectSkillsMemoryDir: () => skillsDir,
|
||||
getProjectMemoryTempDir: () => memoryTempDir,
|
||||
getProjectSkillsDir: () => path.join(tmpDir, 'project-skills'),
|
||||
},
|
||||
} as unknown as Config;
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await fs.rm(tmpDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
it('should return inbox skills with name, description, and extractedAt', async () => {
|
||||
await writeSkillMd('my-skill', 'my-skill', 'A test skill');
|
||||
await writeSkillMd('other-skill', 'other-skill', 'Another skill');
|
||||
|
||||
const stateContent = JSON.stringify({
|
||||
runs: [
|
||||
{
|
||||
runAt: '2025-01-15T10:00:00Z',
|
||||
sessionIds: ['sess-1'],
|
||||
skillsCreated: ['my-skill'],
|
||||
},
|
||||
{
|
||||
runAt: '2025-01-16T12:00:00Z',
|
||||
sessionIds: ['sess-2'],
|
||||
skillsCreated: ['other-skill'],
|
||||
},
|
||||
],
|
||||
});
|
||||
await fs.writeFile(
|
||||
path.join(memoryTempDir, '.extraction-state.json'),
|
||||
stateContent,
|
||||
);
|
||||
|
||||
const skills = await listInboxSkills(inboxConfig);
|
||||
|
||||
expect(skills).toHaveLength(2);
|
||||
const mySkill = skills.find((s) => s.dirName === 'my-skill');
|
||||
expect(mySkill).toBeDefined();
|
||||
expect(mySkill!.name).toBe('my-skill');
|
||||
expect(mySkill!.description).toBe('A test skill');
|
||||
expect(mySkill!.extractedAt).toBe('2025-01-15T10:00:00Z');
|
||||
|
||||
const otherSkill = skills.find((s) => s.dirName === 'other-skill');
|
||||
expect(otherSkill).toBeDefined();
|
||||
expect(otherSkill!.name).toBe('other-skill');
|
||||
expect(otherSkill!.description).toBe('Another skill');
|
||||
expect(otherSkill!.extractedAt).toBe('2025-01-16T12:00:00Z');
|
||||
});
|
||||
|
||||
it('should return an empty array when the inbox is empty', async () => {
|
||||
const skills = await listInboxSkills(inboxConfig);
|
||||
expect(skills).toEqual([]);
|
||||
});
|
||||
|
||||
it('should return an empty array when the inbox directory does not exist', async () => {
|
||||
const missingConfig = {
|
||||
storage: {
|
||||
getProjectSkillsMemoryDir: () => path.join(tmpDir, 'nonexistent-dir'),
|
||||
getProjectMemoryTempDir: () => memoryTempDir,
|
||||
},
|
||||
} as unknown as Config;
|
||||
|
||||
const skills = await listInboxSkills(missingConfig);
|
||||
expect(skills).toEqual([]);
|
||||
});
|
||||
});
|
||||
|
||||
describe('moveInboxSkill', () => {
|
||||
let tmpDir: string;
|
||||
let skillsDir: string;
|
||||
let globalSkillsDir: string;
|
||||
let projectSkillsDir: string;
|
||||
let moveConfig: Config;
|
||||
|
||||
async function writeSkillMd(
|
||||
dirName: string,
|
||||
name: string,
|
||||
description: string,
|
||||
): Promise<void> {
|
||||
const dir = path.join(skillsDir, dirName);
|
||||
await fs.mkdir(dir, { recursive: true });
|
||||
await fs.writeFile(
|
||||
path.join(dir, 'SKILL.md'),
|
||||
`---\nname: ${name}\ndescription: ${description}\n---\nBody content here\n`,
|
||||
);
|
||||
}
|
||||
|
||||
beforeEach(async () => {
|
||||
tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), 'move-test-'));
|
||||
skillsDir = path.join(tmpDir, 'skills-memory');
|
||||
globalSkillsDir = path.join(tmpDir, 'global-skills');
|
||||
projectSkillsDir = path.join(tmpDir, 'project-skills');
|
||||
await fs.mkdir(skillsDir, { recursive: true });
|
||||
|
||||
moveConfig = {
|
||||
storage: {
|
||||
getProjectSkillsMemoryDir: () => skillsDir,
|
||||
getProjectSkillsDir: () => projectSkillsDir,
|
||||
},
|
||||
} as unknown as Config;
|
||||
|
||||
vi.mocked(Storage.getUserSkillsDir).mockReturnValue(globalSkillsDir);
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await fs.rm(tmpDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
it('should move a skill to global skills directory', async () => {
|
||||
await writeSkillMd('my-skill', 'my-skill', 'A test skill');
|
||||
|
||||
const result = await moveInboxSkill(moveConfig, 'my-skill', 'global');
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toBe('Moved "my-skill" to ~/.gemini/skills.');
|
||||
|
||||
// Verify the skill was copied to global
|
||||
const targetSkill = await fs.readFile(
|
||||
path.join(globalSkillsDir, 'my-skill', 'SKILL.md'),
|
||||
'utf-8',
|
||||
);
|
||||
expect(targetSkill).toContain('name: my-skill');
|
||||
|
||||
// Verify the skill was removed from inbox
|
||||
await expect(
|
||||
fs.access(path.join(skillsDir, 'my-skill')),
|
||||
).rejects.toThrow();
|
||||
});
|
||||
|
||||
it('should move a skill to project skills directory', async () => {
|
||||
await writeSkillMd('my-skill', 'my-skill', 'A test skill');
|
||||
|
||||
const result = await moveInboxSkill(moveConfig, 'my-skill', 'project');
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toBe('Moved "my-skill" to .gemini/skills.');
|
||||
|
||||
// Verify the skill was copied to project
|
||||
const targetSkill = await fs.readFile(
|
||||
path.join(projectSkillsDir, 'my-skill', 'SKILL.md'),
|
||||
'utf-8',
|
||||
);
|
||||
expect(targetSkill).toContain('name: my-skill');
|
||||
|
||||
// Verify the skill was removed from inbox
|
||||
await expect(
|
||||
fs.access(path.join(skillsDir, 'my-skill')),
|
||||
).rejects.toThrow();
|
||||
});
|
||||
|
||||
it('should return an error when the source skill does not exist', async () => {
|
||||
const result = await moveInboxSkill(moveConfig, 'nonexistent', 'global');
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toBe('Skill "nonexistent" not found in inbox.');
|
||||
});
|
||||
|
||||
it('should reject invalid skill directory names', async () => {
|
||||
const result = await moveInboxSkill(moveConfig, '../escape', 'global');
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toBe('Invalid skill name.');
|
||||
});
|
||||
|
||||
it('should return an error when the target already exists', async () => {
|
||||
await writeSkillMd('my-skill', 'my-skill', 'A test skill');
|
||||
|
||||
// Pre-create the target
|
||||
const targetDir = path.join(globalSkillsDir, 'my-skill');
|
||||
await fs.mkdir(targetDir, { recursive: true });
|
||||
await fs.writeFile(path.join(targetDir, 'SKILL.md'), 'existing content');
|
||||
|
||||
const result = await moveInboxSkill(moveConfig, 'my-skill', 'global');
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toBe(
|
||||
'A skill named "my-skill" already exists in global skills.',
|
||||
);
|
||||
});
|
||||
|
||||
it('should detect conflicts based on the normalized skill name', async () => {
|
||||
await writeSkillMd(
|
||||
'inbox-skill',
|
||||
'gke:prs-troubleshooter',
|
||||
'A test skill',
|
||||
);
|
||||
await fs.mkdir(
|
||||
path.join(globalSkillsDir, 'existing-gke-prs-troubleshooter'),
|
||||
{ recursive: true },
|
||||
);
|
||||
await fs.writeFile(
|
||||
path.join(
|
||||
globalSkillsDir,
|
||||
'existing-gke-prs-troubleshooter',
|
||||
'SKILL.md',
|
||||
),
|
||||
[
|
||||
'---',
|
||||
'name: gke-prs-troubleshooter',
|
||||
'description: Existing skill',
|
||||
'---',
|
||||
'Existing body content',
|
||||
'',
|
||||
].join('\n'),
|
||||
);
|
||||
|
||||
const result = await moveInboxSkill(moveConfig, 'inbox-skill', 'global');
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toBe(
|
||||
'A skill named "gke-prs-troubleshooter" already exists in global skills.',
|
||||
);
|
||||
await expect(
|
||||
fs.access(path.join(skillsDir, 'inbox-skill', 'SKILL.md')),
|
||||
).resolves.toBeUndefined();
|
||||
await expect(
|
||||
fs.access(path.join(globalSkillsDir, 'inbox-skill')),
|
||||
).rejects.toThrow();
|
||||
});
|
||||
});
|
||||
|
||||
describe('dismissInboxSkill', () => {
|
||||
let tmpDir: string;
|
||||
let skillsDir: string;
|
||||
let dismissConfig: Config;
|
||||
|
||||
async function writeSkillMd(
|
||||
dirName: string,
|
||||
name: string,
|
||||
description: string,
|
||||
): Promise<void> {
|
||||
const dir = path.join(skillsDir, dirName);
|
||||
await fs.mkdir(dir, { recursive: true });
|
||||
await fs.writeFile(
|
||||
path.join(dir, 'SKILL.md'),
|
||||
`---\nname: ${name}\ndescription: ${description}\n---\nBody content here\n`,
|
||||
);
|
||||
}
|
||||
|
||||
beforeEach(async () => {
|
||||
tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), 'dismiss-test-'));
|
||||
skillsDir = path.join(tmpDir, 'skills-memory');
|
||||
await fs.mkdir(skillsDir, { recursive: true });
|
||||
|
||||
dismissConfig = {
|
||||
storage: {
|
||||
getProjectSkillsMemoryDir: () => skillsDir,
|
||||
},
|
||||
} as unknown as Config;
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await fs.rm(tmpDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
it('should remove a skill from the inbox', async () => {
|
||||
await writeSkillMd('my-skill', 'my-skill', 'A test skill');
|
||||
|
||||
const result = await dismissInboxSkill(dismissConfig, 'my-skill');
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toBe('Dismissed "my-skill" from inbox.');
|
||||
|
||||
// Verify the skill directory was removed
|
||||
await expect(
|
||||
fs.access(path.join(skillsDir, 'my-skill')),
|
||||
).rejects.toThrow();
|
||||
});
|
||||
|
||||
it('should return an error when the skill does not exist', async () => {
|
||||
const result = await dismissInboxSkill(dismissConfig, 'nonexistent');
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toBe('Skill "nonexistent" not found in inbox.');
|
||||
});
|
||||
|
||||
it('should reject invalid skill directory names', async () => {
|
||||
const result = await dismissInboxSkill(dismissConfig, 'nested\\skill');
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toBe('Invalid skill name.');
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
@@ -4,8 +4,13 @@
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import * as fs from 'node:fs/promises';
|
||||
import * as path from 'node:path';
|
||||
import type { Config } from '../config/config.js';
|
||||
import { Storage } from '../config/storage.js';
|
||||
import { flattenMemory } from '../config/memory.js';
|
||||
import { loadSkillFromFile, loadSkillsFromDir } from '../skills/skillLoader.js';
|
||||
import { readExtractionState } from '../services/memoryService.js';
|
||||
import { refreshServerHierarchicalMemory } from '../utils/memoryDiscovery.js';
|
||||
import type { MessageActionReturn, ToolActionReturn } from './types.js';
|
||||
|
||||
@@ -95,3 +100,186 @@ export function listMemoryFiles(config: Config): MessageActionReturn {
|
||||
content,
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Represents a skill found in the extraction inbox.
|
||||
*/
|
||||
export interface InboxSkill {
|
||||
/** Directory name in the inbox. */
|
||||
dirName: string;
|
||||
/** Skill name from SKILL.md frontmatter. */
|
||||
name: string;
|
||||
/** Skill description from SKILL.md frontmatter. */
|
||||
description: string;
|
||||
/** When the skill was extracted (ISO string), if known. */
|
||||
extractedAt?: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* Scans the skill extraction inbox and returns structured data
|
||||
* for each extracted skill.
|
||||
*/
|
||||
export async function listInboxSkills(config: Config): Promise<InboxSkill[]> {
|
||||
const skillsDir = config.storage.getProjectSkillsMemoryDir();
|
||||
|
||||
let entries: Array<import('node:fs').Dirent>;
|
||||
try {
|
||||
entries = await fs.readdir(skillsDir, { withFileTypes: true });
|
||||
} catch {
|
||||
return [];
|
||||
}
|
||||
|
||||
const dirs = entries.filter((e) => e.isDirectory());
|
||||
if (dirs.length === 0) {
|
||||
return [];
|
||||
}
|
||||
|
||||
// Load extraction state to get dates
|
||||
const memoryDir = config.storage.getProjectMemoryTempDir();
|
||||
const statePath = path.join(memoryDir, '.extraction-state.json');
|
||||
const state = await readExtractionState(statePath);
|
||||
|
||||
// Build a map: skillDirName → extractedAt
|
||||
const skillDateMap = new Map<string, string>();
|
||||
for (const run of state.runs) {
|
||||
for (const skillName of run.skillsCreated) {
|
||||
skillDateMap.set(skillName, run.runAt);
|
||||
}
|
||||
}
|
||||
|
||||
const skills: InboxSkill[] = [];
|
||||
for (const dir of dirs) {
|
||||
const skillPath = path.join(skillsDir, dir.name, 'SKILL.md');
|
||||
const skillDef = await loadSkillFromFile(skillPath);
|
||||
if (!skillDef) continue;
|
||||
|
||||
skills.push({
|
||||
dirName: dir.name,
|
||||
name: skillDef.name,
|
||||
description: skillDef.description,
|
||||
extractedAt: skillDateMap.get(dir.name),
|
||||
});
|
||||
}
|
||||
|
||||
return skills;
|
||||
}
|
||||
|
||||
export type InboxSkillDestination = 'global' | 'project';
|
||||
|
||||
function isValidInboxSkillDirName(dirName: string): boolean {
|
||||
return (
|
||||
dirName.length > 0 &&
|
||||
dirName !== '.' &&
|
||||
dirName !== '..' &&
|
||||
!dirName.includes('/') &&
|
||||
!dirName.includes('\\')
|
||||
);
|
||||
}
|
||||
|
||||
async function getSkillNameForConflictCheck(
|
||||
skillDir: string,
|
||||
fallbackName: string,
|
||||
): Promise<string> {
|
||||
const skill = await loadSkillFromFile(path.join(skillDir, 'SKILL.md'));
|
||||
return skill?.name ?? fallbackName;
|
||||
}
|
||||
|
||||
/**
|
||||
* Copies an inbox skill to the target skills directory.
|
||||
*/
|
||||
export async function moveInboxSkill(
|
||||
config: Config,
|
||||
dirName: string,
|
||||
destination: InboxSkillDestination,
|
||||
): Promise<{ success: boolean; message: string }> {
|
||||
if (!isValidInboxSkillDirName(dirName)) {
|
||||
return {
|
||||
success: false,
|
||||
message: 'Invalid skill name.',
|
||||
};
|
||||
}
|
||||
|
||||
const skillsDir = config.storage.getProjectSkillsMemoryDir();
|
||||
const sourcePath = path.join(skillsDir, dirName);
|
||||
|
||||
try {
|
||||
await fs.access(sourcePath);
|
||||
} catch {
|
||||
return {
|
||||
success: false,
|
||||
message: `Skill "${dirName}" not found in inbox.`,
|
||||
};
|
||||
}
|
||||
|
||||
const targetBase =
|
||||
destination === 'global'
|
||||
? Storage.getUserSkillsDir()
|
||||
: config.storage.getProjectSkillsDir();
|
||||
const targetPath = path.join(targetBase, dirName);
|
||||
const skillName = await getSkillNameForConflictCheck(sourcePath, dirName);
|
||||
|
||||
try {
|
||||
await fs.access(targetPath);
|
||||
return {
|
||||
success: false,
|
||||
message: `A skill named "${skillName}" already exists in ${destination} skills.`,
|
||||
};
|
||||
} catch {
|
||||
// Target doesn't exist — good
|
||||
}
|
||||
|
||||
const existingTargetSkills = await loadSkillsFromDir(targetBase);
|
||||
if (existingTargetSkills.some((skill) => skill.name === skillName)) {
|
||||
return {
|
||||
success: false,
|
||||
message: `A skill named "${skillName}" already exists in ${destination} skills.`,
|
||||
};
|
||||
}
|
||||
|
||||
await fs.mkdir(targetBase, { recursive: true });
|
||||
await fs.cp(sourcePath, targetPath, { recursive: true });
|
||||
|
||||
// Remove from inbox after successful copy
|
||||
await fs.rm(sourcePath, { recursive: true, force: true });
|
||||
|
||||
const label =
|
||||
destination === 'global' ? '~/.gemini/skills' : '.gemini/skills';
|
||||
return {
|
||||
success: true,
|
||||
message: `Moved "${dirName}" to ${label}.`,
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Removes a skill from the extraction inbox.
|
||||
*/
|
||||
export async function dismissInboxSkill(
|
||||
config: Config,
|
||||
dirName: string,
|
||||
): Promise<{ success: boolean; message: string }> {
|
||||
if (!isValidInboxSkillDirName(dirName)) {
|
||||
return {
|
||||
success: false,
|
||||
message: 'Invalid skill name.',
|
||||
};
|
||||
}
|
||||
|
||||
const skillsDir = config.storage.getProjectSkillsMemoryDir();
|
||||
const sourcePath = path.join(skillsDir, dirName);
|
||||
|
||||
try {
|
||||
await fs.access(sourcePath);
|
||||
} catch {
|
||||
return {
|
||||
success: false,
|
||||
message: `Skill "${dirName}" not found in inbox.`,
|
||||
};
|
||||
}
|
||||
|
||||
await fs.rm(sourcePath, { recursive: true, force: true });
|
||||
|
||||
return {
|
||||
success: true,
|
||||
message: `Dismissed "${dirName}" from inbox.`,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -700,6 +700,7 @@ export interface ConfigParameters {
|
||||
experimentalJitContext?: boolean;
|
||||
autoDistillation?: boolean;
|
||||
experimentalMemoryManager?: boolean;
|
||||
experimentalContextSidecarConfig?: string;
|
||||
experimentalAgentHistoryTruncation?: boolean;
|
||||
experimentalAgentHistoryTruncationThreshold?: number;
|
||||
experimentalAgentHistoryRetainedMessages?: number;
|
||||
@@ -942,6 +943,7 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
private readonly adminSkillsEnabled: boolean;
|
||||
private readonly experimentalJitContext: boolean;
|
||||
private readonly experimentalMemoryManager: boolean;
|
||||
private readonly experimentalContextSidecarConfig?: string;
|
||||
private readonly memoryBoundaryMarkers: readonly string[];
|
||||
private readonly topicUpdateNarration: boolean;
|
||||
private readonly disableLLMCorrection: boolean;
|
||||
@@ -1153,6 +1155,8 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
|
||||
this.experimentalJitContext = params.experimentalJitContext ?? false;
|
||||
this.experimentalMemoryManager = params.experimentalMemoryManager ?? false;
|
||||
this.experimentalContextSidecarConfig =
|
||||
params.experimentalContextSidecarConfig;
|
||||
this.memoryBoundaryMarkers = params.memoryBoundaryMarkers ?? ['.git'];
|
||||
this.contextManagement = {
|
||||
enabled: params.contextManagement?.enabled ?? false,
|
||||
@@ -2427,6 +2431,10 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
return this.experimentalMemoryManager;
|
||||
}
|
||||
|
||||
getExperimentalContextSidecarConfig(): string | undefined {
|
||||
return this.experimentalContextSidecarConfig;
|
||||
}
|
||||
|
||||
getContextManagementConfig(): ContextManagementConfig {
|
||||
return this.contextManagement;
|
||||
}
|
||||
|
||||
@@ -0,0 +1,82 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
|
||||
import { testTruncateProfile } from './testing/testProfile.js';
|
||||
import {
|
||||
createSyntheticHistory,
|
||||
createMockContextConfig,
|
||||
setupContextComponentTest,
|
||||
} from './testing/contextTestUtils.js';
|
||||
|
||||
describe('ContextManager Sync Pressure Barrier Tests', () => {
|
||||
beforeEach(() => {
|
||||
vi.useFakeTimers();
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
vi.useRealTimers();
|
||||
vi.restoreAllMocks();
|
||||
});
|
||||
|
||||
it('should instantly truncate history when maxTokens is exceeded using truncate strategy', async () => {
|
||||
// 1. Setup
|
||||
const config = createMockContextConfig();
|
||||
const { chatHistory, contextManager } = setupContextComponentTest(
|
||||
config,
|
||||
testTruncateProfile,
|
||||
);
|
||||
|
||||
// 2. Add System Prompt (Episode 0 - Protected)
|
||||
chatHistory.set([
|
||||
{ role: 'user', parts: [{ text: 'System prompt' }] },
|
||||
{ role: 'model', parts: [{ text: 'Understood.' }] },
|
||||
]);
|
||||
|
||||
// 3. Add massive history that blows past the 150k maxTokens limit
|
||||
// 20 turns * 10,000 tokens/turn = ~200,000 tokens
|
||||
const massiveHistory = createSyntheticHistory(20, 35000);
|
||||
chatHistory.set([...chatHistory.get(), ...massiveHistory]);
|
||||
|
||||
// 4. Add the Latest Turn (Protected)
|
||||
chatHistory.set([
|
||||
...chatHistory.get(),
|
||||
{ role: 'user', parts: [{ text: 'Final question.' }] },
|
||||
{ role: 'model', parts: [{ text: 'Final answer.' }] },
|
||||
]);
|
||||
|
||||
const rawHistoryLength = chatHistory.get().length;
|
||||
|
||||
// 5. Project History (Triggers Sync Barrier)
|
||||
const projection = await contextManager.projectCompressedHistory();
|
||||
|
||||
// 6. Assertions
|
||||
// The barrier should have dropped several older episodes to get under 150k.
|
||||
|
||||
expect(projection.length).toBeLessThan(rawHistoryLength);
|
||||
|
||||
// Verify Episode 0 (System) is perfectly preserved at the front
|
||||
|
||||
expect(projection[0].role).toBe('user');
|
||||
expect(projection[0].parts![0].text).toBe('System prompt');
|
||||
|
||||
// Filter out synthetic Yield nodes (they are model responses without actual tool/text bodies)
|
||||
const contentNodes = projection.filter(
|
||||
(p) =>
|
||||
p.parts && p.parts.some((part) => part.text && part.text !== 'Yield'),
|
||||
);
|
||||
|
||||
// Verify the latest turn is perfectly preserved at the back
|
||||
const lastUser = contentNodes[contentNodes.length - 2];
|
||||
const lastModel = contentNodes[contentNodes.length - 1];
|
||||
|
||||
expect(lastUser.role).toBe('user');
|
||||
expect(lastUser.parts![0].text).toBe('Final question.');
|
||||
|
||||
expect(lastModel.role).toBe('model');
|
||||
expect(lastModel.parts![0].text).toBe('Final answer.');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,158 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { Content } from '@google/genai';
|
||||
import type { AgentChatHistory } from '../core/agentChatHistory.js';
|
||||
import type { ConcreteNode } from './ir/types.js';
|
||||
import type { ContextEventBus } from './eventBus.js';
|
||||
import type { ContextTracer } from './tracer.js';
|
||||
import type { ContextEnvironment } from './sidecar/environment.js';
|
||||
import type { SidecarConfig } from './sidecar/types.js';
|
||||
import type { PipelineOrchestrator } from './sidecar/orchestrator.js';
|
||||
import { HistoryObserver } from './historyObserver.js';
|
||||
import { IrProjector } from './ir/projector.js';
|
||||
import { ContextWorkingBufferImpl } from './sidecar/contextWorkingBuffer.js';
|
||||
|
||||
export class ContextManager {
|
||||
// The master state containing the pristine graph and current active graph.
|
||||
private buffer: ContextWorkingBufferImpl =
|
||||
ContextWorkingBufferImpl.initialize([]);
|
||||
private pristineNodes: readonly ConcreteNode[] = [];
|
||||
|
||||
private readonly eventBus: ContextEventBus;
|
||||
|
||||
// Internal sub-components
|
||||
private readonly orchestrator: PipelineOrchestrator;
|
||||
private readonly historyObserver: HistoryObserver;
|
||||
|
||||
constructor(
|
||||
private readonly sidecar: SidecarConfig,
|
||||
private readonly env: ContextEnvironment,
|
||||
private readonly tracer: ContextTracer,
|
||||
orchestrator: PipelineOrchestrator,
|
||||
chatHistory: AgentChatHistory,
|
||||
) {
|
||||
this.eventBus = env.eventBus;
|
||||
this.orchestrator = orchestrator;
|
||||
|
||||
this.historyObserver = new HistoryObserver(
|
||||
chatHistory,
|
||||
this.env.eventBus,
|
||||
this.tracer,
|
||||
this.env.tokenCalculator,
|
||||
this.env.irMapper,
|
||||
);
|
||||
this.historyObserver.start();
|
||||
|
||||
this.eventBus.onPristineHistoryUpdated((event) => {
|
||||
this.pristineNodes = event.nodes;
|
||||
|
||||
const existingIds = new Set(this.buffer.nodes.map((n) => n.id));
|
||||
const addedNodes = event.nodes.filter((n) => !existingIds.has(n.id));
|
||||
|
||||
if (addedNodes.length > 0) {
|
||||
this.buffer = this.buffer.appendPristineNodes(addedNodes);
|
||||
}
|
||||
|
||||
this.evaluateTriggers(event.newNodes);
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Safely stops background workers and clears event listeners.
|
||||
*/
|
||||
shutdown() {
|
||||
this.orchestrator.shutdown();
|
||||
this.historyObserver.stop();
|
||||
}
|
||||
|
||||
/**
|
||||
* Evaluates if the current working buffer exceeds configured budget thresholds,
|
||||
* firing consolidation events if necessary.
|
||||
*/
|
||||
private evaluateTriggers(newNodes: Set<string>) {
|
||||
if (!this.sidecar.budget) return;
|
||||
|
||||
if (newNodes.size > 0) {
|
||||
this.eventBus.emitChunkReceived({
|
||||
nodes: this.buffer.nodes,
|
||||
targetNodeIds: newNodes,
|
||||
});
|
||||
}
|
||||
|
||||
const currentTokens = this.env.tokenCalculator.calculateConcreteListTokens(
|
||||
this.buffer.nodes,
|
||||
);
|
||||
|
||||
if (currentTokens > this.sidecar.budget.retainedTokens) {
|
||||
const agedOutNodes = new Set<string>();
|
||||
let rollingTokens = 0;
|
||||
// Walk backwards finding nodes that fall out of the retained budget
|
||||
for (let i = this.buffer.nodes.length - 1; i >= 0; i--) {
|
||||
const node = this.buffer.nodes[i];
|
||||
rollingTokens += this.env.tokenCalculator.calculateConcreteListTokens([
|
||||
node,
|
||||
]);
|
||||
if (rollingTokens > this.sidecar.budget.retainedTokens) {
|
||||
agedOutNodes.add(node.id);
|
||||
}
|
||||
}
|
||||
|
||||
if (agedOutNodes.size > 0) {
|
||||
this.eventBus.emitConsolidationNeeded({
|
||||
nodes: this.buffer.nodes,
|
||||
targetDeficit: currentTokens - this.sidecar.budget.retainedTokens,
|
||||
targetNodeIds: agedOutNodes,
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Retrieves the raw, uncompressed Episodic IR graph.
|
||||
* Useful for internal tool rendering (like the trace viewer).
|
||||
* Note: This is an expensive, deep clone operation.
|
||||
*/
|
||||
getPristineGraph(): readonly ConcreteNode[] {
|
||||
return [...this.pristineNodes];
|
||||
}
|
||||
|
||||
/**
|
||||
* Generates a virtual view of the pristine graph, substituting in variants
|
||||
* up to the configured token budget.
|
||||
* This is the view that will eventually be projected back to the LLM.
|
||||
*/
|
||||
getNodes(): readonly ConcreteNode[] {
|
||||
return [...this.buffer.nodes];
|
||||
}
|
||||
|
||||
/**
|
||||
* Executes the final 'gc_backstop' pipeline if necessary, enforcing the token budget,
|
||||
* and maps the Episodic IR back into a raw Gemini Content[] array for transmission.
|
||||
* This is the primary method called by the agent framework before sending a request.
|
||||
*/
|
||||
async projectCompressedHistory(
|
||||
activeTaskIds: Set<string> = new Set(),
|
||||
): Promise<Content[]> {
|
||||
this.tracer.logEvent(
|
||||
'ContextManager',
|
||||
'Starting projection to LLM context',
|
||||
);
|
||||
// Apply final GC Backstop pressure barrier synchronously before mapping
|
||||
const finalHistory = await IrProjector.project(
|
||||
this.buffer.nodes,
|
||||
this.orchestrator,
|
||||
this.sidecar,
|
||||
this.tracer,
|
||||
this.env,
|
||||
activeTaskIds,
|
||||
);
|
||||
|
||||
this.tracer.logEvent('ContextManager', 'Finished projection');
|
||||
|
||||
return finalHistory;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,52 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { EventEmitter } from 'node:events';
|
||||
import type { ConcreteNode } from './ir/types.js';
|
||||
|
||||
export interface PristineHistoryUpdatedEvent {
|
||||
nodes: readonly ConcreteNode[];
|
||||
newNodes: Set<string>;
|
||||
}
|
||||
|
||||
export interface ContextConsolidationEvent {
|
||||
nodes: readonly ConcreteNode[];
|
||||
targetDeficit: number;
|
||||
targetNodeIds: Set<string>;
|
||||
}
|
||||
|
||||
export interface IrChunkReceivedEvent {
|
||||
nodes: readonly ConcreteNode[];
|
||||
targetNodeIds: Set<string>;
|
||||
}
|
||||
|
||||
export class ContextEventBus extends EventEmitter {
|
||||
emitPristineHistoryUpdated(event: PristineHistoryUpdatedEvent) {
|
||||
this.emit('PRISTINE_HISTORY_UPDATED', event);
|
||||
}
|
||||
|
||||
onPristineHistoryUpdated(
|
||||
listener: (event: PristineHistoryUpdatedEvent) => void,
|
||||
) {
|
||||
this.on('PRISTINE_HISTORY_UPDATED', listener);
|
||||
}
|
||||
|
||||
emitChunkReceived(event: IrChunkReceivedEvent) {
|
||||
this.emit('IR_CHUNK_RECEIVED', event);
|
||||
}
|
||||
|
||||
onChunkReceived(listener: (event: IrChunkReceivedEvent) => void) {
|
||||
this.on('IR_CHUNK_RECEIVED', listener);
|
||||
}
|
||||
|
||||
emitConsolidationNeeded(event: ContextConsolidationEvent) {
|
||||
this.emit('BUDGET_RETAINED_CROSSED', event);
|
||||
}
|
||||
|
||||
onConsolidationNeeded(listener: (event: ContextConsolidationEvent) => void) {
|
||||
this.on('BUDGET_RETAINED_CROSSED', listener);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,88 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type {
|
||||
AgentChatHistory,
|
||||
HistoryEvent,
|
||||
} from '../core/agentChatHistory.js';
|
||||
import type { IrMapper } from './ir/mapper.js';
|
||||
import type { ContextTokenCalculator } from './utils/contextTokenCalculator.js';
|
||||
import type { ContextEventBus } from './eventBus.js';
|
||||
import type { ContextTracer } from './tracer.js';
|
||||
|
||||
import type { ConcreteNode } from './ir/types.js';
|
||||
|
||||
/**
|
||||
* Connects the raw AgentChatHistory to the ContextManager.
|
||||
* It maps raw messages into Episodic Intermediate Representation (IR)
|
||||
* and evaluates background triggers whenever history changes.
|
||||
*/
|
||||
export class HistoryObserver {
|
||||
private unsubscribeHistory?: () => void;
|
||||
|
||||
private seenNodeIds = new Set<string>();
|
||||
|
||||
constructor(
|
||||
private readonly chatHistory: AgentChatHistory,
|
||||
private readonly eventBus: ContextEventBus,
|
||||
private readonly tracer: ContextTracer,
|
||||
private readonly tokenCalculator: ContextTokenCalculator,
|
||||
private readonly irMapper: IrMapper,
|
||||
) {}
|
||||
|
||||
start() {
|
||||
if (this.unsubscribeHistory) {
|
||||
this.unsubscribeHistory();
|
||||
}
|
||||
|
||||
this.unsubscribeHistory = this.chatHistory.subscribe(
|
||||
(_event: HistoryEvent) => {
|
||||
// Rebuild the pristine IR graph from the full source history on every change.
|
||||
// Wait, toIr still returns an Episode[].
|
||||
// We actually need to map the Episode[] to a flat ConcreteNode[] here to form the 'nodes'.
|
||||
const pristineEpisodes = this.irMapper.toIr(
|
||||
this.chatHistory.get(),
|
||||
this.tokenCalculator,
|
||||
);
|
||||
|
||||
const nodes: ConcreteNode[] = [];
|
||||
for (const ep of pristineEpisodes) {
|
||||
if (ep.concreteNodes) {
|
||||
for (const child of ep.concreteNodes) {
|
||||
nodes.push(child);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const newNodes = new Set<string>();
|
||||
for (const node of nodes) {
|
||||
if (!this.seenNodeIds.has(node.id)) {
|
||||
newNodes.add(node.id);
|
||||
this.seenNodeIds.add(node.id);
|
||||
}
|
||||
}
|
||||
|
||||
this.tracer.logEvent(
|
||||
'HistoryObserver',
|
||||
'Rebuilt pristine graph from chat history update',
|
||||
{ nodesSize: nodes.length, newNodesCount: newNodes.size },
|
||||
);
|
||||
|
||||
this.eventBus.emitPristineHistoryUpdated({
|
||||
nodes,
|
||||
newNodes,
|
||||
});
|
||||
},
|
||||
);
|
||||
}
|
||||
|
||||
stop() {
|
||||
if (this.unsubscribeHistory) {
|
||||
this.unsubscribeHistory();
|
||||
this.unsubscribeHistory = undefined;
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,43 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { Content, Part } from '@google/genai';
|
||||
import type { ConcreteNode } from './types.js';
|
||||
|
||||
export interface IrSerializationWriter {
|
||||
appendContent(content: Content): void;
|
||||
appendModelPart(part: Part): void;
|
||||
appendUserPart(part: Part): void;
|
||||
flushModelParts(): void;
|
||||
}
|
||||
|
||||
export interface IrNodeBehavior<T extends ConcreteNode = ConcreteNode> {
|
||||
readonly type: T['type'];
|
||||
|
||||
/** Serializes the node into the Gemini Content structure. */
|
||||
serialize(node: T, writer: IrSerializationWriter): void;
|
||||
|
||||
/**
|
||||
* Generates a structural representation of the node for the purpose
|
||||
* of estimating its token cost.
|
||||
*/
|
||||
getEstimatableParts(node: T): Part[];
|
||||
}
|
||||
|
||||
export class IrNodeBehaviorRegistry {
|
||||
private readonly behaviors = new Map<string, IrNodeBehavior<ConcreteNode>>();
|
||||
|
||||
register<T extends ConcreteNode>(behavior: IrNodeBehavior<T>) {
|
||||
this.behaviors.set(behavior.type, behavior as IrNodeBehavior<ConcreteNode>);
|
||||
}
|
||||
|
||||
get(type: string): IrNodeBehavior<ConcreteNode> {
|
||||
const behavior = this.behaviors.get(type);
|
||||
if (!behavior) {
|
||||
throw new Error(`Unregistered IrNode type: ${type}`);
|
||||
}
|
||||
return behavior;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,175 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { Part } from '@google/genai';
|
||||
import type {
|
||||
IrNodeBehavior,
|
||||
IrNodeBehaviorRegistry,
|
||||
} from './behaviorRegistry.js';
|
||||
import type {
|
||||
UserPrompt,
|
||||
AgentThought,
|
||||
ToolExecution,
|
||||
MaskedTool,
|
||||
AgentYield,
|
||||
Snapshot,
|
||||
RollingSummary,
|
||||
SystemEvent,
|
||||
} from './types.js';
|
||||
|
||||
export const UserPromptBehavior: IrNodeBehavior<UserPrompt> = {
|
||||
type: 'USER_PROMPT',
|
||||
getEstimatableParts(prompt) {
|
||||
const parts: Part[] = [];
|
||||
for (const sp of prompt.semanticParts) {
|
||||
switch (sp.type) {
|
||||
case 'text':
|
||||
parts.push({ text: sp.text });
|
||||
break;
|
||||
case 'inline_data':
|
||||
parts.push({ inlineData: { mimeType: sp.mimeType, data: sp.data } });
|
||||
break;
|
||||
case 'file_data':
|
||||
parts.push({
|
||||
fileData: { mimeType: sp.mimeType, fileUri: sp.fileUri },
|
||||
});
|
||||
break;
|
||||
case 'raw_part':
|
||||
parts.push(sp.part);
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
}
|
||||
return parts;
|
||||
},
|
||||
serialize(prompt, writer) {
|
||||
const parts = this.getEstimatableParts(prompt);
|
||||
if (parts.length > 0) {
|
||||
writer.flushModelParts();
|
||||
writer.appendContent({ role: 'user', parts });
|
||||
}
|
||||
},
|
||||
};
|
||||
|
||||
export const AgentThoughtBehavior: IrNodeBehavior<AgentThought> = {
|
||||
type: 'AGENT_THOUGHT',
|
||||
getEstimatableParts(thought) {
|
||||
return [{ text: thought.text }];
|
||||
},
|
||||
serialize(thought, writer) {
|
||||
writer.appendModelPart({ text: thought.text });
|
||||
},
|
||||
};
|
||||
|
||||
export const ToolExecutionBehavior: IrNodeBehavior<ToolExecution> = {
|
||||
type: 'TOOL_EXECUTION',
|
||||
getEstimatableParts(tool) {
|
||||
return [
|
||||
{ functionCall: { id: tool.id, name: tool.toolName, args: tool.intent } },
|
||||
{
|
||||
functionResponse: {
|
||||
id: tool.id,
|
||||
name: tool.toolName,
|
||||
response:
|
||||
typeof tool.observation === 'string'
|
||||
? { message: tool.observation }
|
||||
: tool.observation,
|
||||
},
|
||||
},
|
||||
];
|
||||
},
|
||||
serialize(tool, writer) {
|
||||
const parts = this.getEstimatableParts(tool);
|
||||
writer.appendModelPart(parts[0]);
|
||||
writer.flushModelParts();
|
||||
writer.appendUserPart(parts[1]);
|
||||
},
|
||||
};
|
||||
|
||||
export const MaskedToolBehavior: IrNodeBehavior<MaskedTool> = {
|
||||
type: 'MASKED_TOOL',
|
||||
getEstimatableParts(tool) {
|
||||
return [
|
||||
{
|
||||
functionCall: {
|
||||
id: tool.id,
|
||||
name: tool.toolName,
|
||||
args: tool.intent ?? {},
|
||||
},
|
||||
},
|
||||
{
|
||||
functionResponse: {
|
||||
id: tool.id,
|
||||
name: tool.toolName,
|
||||
response:
|
||||
typeof tool.observation === 'string'
|
||||
? { message: tool.observation }
|
||||
: (tool.observation ?? {}),
|
||||
},
|
||||
},
|
||||
];
|
||||
},
|
||||
serialize(tool, writer) {
|
||||
const parts = this.getEstimatableParts(tool);
|
||||
writer.appendModelPart(parts[0]);
|
||||
writer.flushModelParts();
|
||||
writer.appendUserPart(parts[1]);
|
||||
},
|
||||
};
|
||||
|
||||
export const AgentYieldBehavior: IrNodeBehavior<AgentYield> = {
|
||||
type: 'AGENT_YIELD',
|
||||
getEstimatableParts(yieldNode) {
|
||||
return [{ text: yieldNode.text }];
|
||||
},
|
||||
serialize(yieldNode, writer) {
|
||||
writer.appendModelPart({ text: yieldNode.text });
|
||||
writer.flushModelParts();
|
||||
},
|
||||
};
|
||||
|
||||
export const SystemEventBehavior: IrNodeBehavior<SystemEvent> = {
|
||||
type: 'SYSTEM_EVENT',
|
||||
getEstimatableParts() {
|
||||
return [];
|
||||
},
|
||||
serialize(node, writer) {
|
||||
writer.flushModelParts();
|
||||
},
|
||||
};
|
||||
|
||||
export const SnapshotBehavior: IrNodeBehavior<Snapshot> = {
|
||||
type: 'SNAPSHOT',
|
||||
getEstimatableParts(node) {
|
||||
return [{ text: node.text }];
|
||||
},
|
||||
serialize(node, writer) {
|
||||
writer.flushModelParts();
|
||||
writer.appendUserPart({ text: node.text });
|
||||
},
|
||||
};
|
||||
|
||||
export const RollingSummaryBehavior: IrNodeBehavior<RollingSummary> = {
|
||||
type: 'ROLLING_SUMMARY',
|
||||
getEstimatableParts(node) {
|
||||
return [{ text: node.text }];
|
||||
},
|
||||
serialize(node, writer) {
|
||||
writer.flushModelParts();
|
||||
writer.appendUserPart({ text: node.text });
|
||||
},
|
||||
};
|
||||
|
||||
export function registerBuiltInBehaviors(registry: IrNodeBehaviorRegistry) {
|
||||
registry.register(UserPromptBehavior);
|
||||
registry.register(AgentThoughtBehavior);
|
||||
registry.register(ToolExecutionBehavior);
|
||||
registry.register(MaskedToolBehavior);
|
||||
registry.register(AgentYieldBehavior);
|
||||
registry.register(SystemEventBehavior);
|
||||
registry.register(SnapshotBehavior);
|
||||
registry.register(RollingSummaryBehavior);
|
||||
}
|
||||
@@ -0,0 +1,54 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { Content, Part } from '@google/genai';
|
||||
import type { ConcreteNode } from './types.js';
|
||||
import type {
|
||||
IrSerializationWriter,
|
||||
IrNodeBehaviorRegistry,
|
||||
} from './behaviorRegistry.js';
|
||||
|
||||
class IrSerializer implements IrSerializationWriter {
|
||||
private history: Content[] = [];
|
||||
private currentModelParts: Part[] = [];
|
||||
|
||||
appendContent(content: Content) {
|
||||
this.flushModelParts();
|
||||
this.history.push(content);
|
||||
}
|
||||
|
||||
appendModelPart(part: Part) {
|
||||
this.currentModelParts.push(part);
|
||||
}
|
||||
|
||||
appendUserPart(part: Part) {
|
||||
this.flushModelParts();
|
||||
this.history.push({ role: 'user', parts: [part] });
|
||||
}
|
||||
|
||||
flushModelParts() {
|
||||
if (this.currentModelParts.length > 0) {
|
||||
this.history.push({ role: 'model', parts: [...this.currentModelParts] });
|
||||
this.currentModelParts = [];
|
||||
}
|
||||
}
|
||||
|
||||
getContents(): Content[] {
|
||||
this.flushModelParts();
|
||||
return this.history;
|
||||
}
|
||||
}
|
||||
|
||||
export function fromIr(
|
||||
nodes: readonly ConcreteNode[],
|
||||
registry: IrNodeBehaviorRegistry,
|
||||
): Content[] {
|
||||
const writer = new IrSerializer();
|
||||
for (const node of nodes) {
|
||||
const behavior = registry.get(node.type);
|
||||
behavior.serialize(node, writer);
|
||||
}
|
||||
return writer.getContents();
|
||||
}
|
||||
@@ -0,0 +1,59 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type {
|
||||
Episode,
|
||||
Task,
|
||||
IrNode,
|
||||
AgentThought,
|
||||
ToolExecution,
|
||||
MaskedTool,
|
||||
UserPrompt,
|
||||
AgentYield,
|
||||
SystemEvent,
|
||||
Snapshot,
|
||||
RollingSummary,
|
||||
} from './types.js';
|
||||
|
||||
export function isEpisode(node: IrNode): node is Episode {
|
||||
return node.type === 'EPISODE';
|
||||
}
|
||||
|
||||
export function isTask(node: IrNode): node is Task {
|
||||
return node.type === 'TASK';
|
||||
}
|
||||
|
||||
export function isAgentThought(node: IrNode): node is AgentThought {
|
||||
return node.type === 'AGENT_THOUGHT';
|
||||
}
|
||||
|
||||
export function isAgentYield(node: IrNode): node is AgentYield {
|
||||
return node.type === 'AGENT_YIELD';
|
||||
}
|
||||
|
||||
export function isToolExecution(node: IrNode): node is ToolExecution {
|
||||
return node.type === 'TOOL_EXECUTION';
|
||||
}
|
||||
|
||||
export function isMaskedTool(node: IrNode): node is MaskedTool {
|
||||
return node.type === 'MASKED_TOOL';
|
||||
}
|
||||
|
||||
export function isUserPrompt(node: IrNode): node is UserPrompt {
|
||||
return node.type === 'USER_PROMPT';
|
||||
}
|
||||
|
||||
export function isSystemEvent(node: IrNode): node is SystemEvent {
|
||||
return node.type === 'SYSTEM_EVENT';
|
||||
}
|
||||
|
||||
export function isSnapshot(node: IrNode): node is Snapshot {
|
||||
return node.type === 'SNAPSHOT';
|
||||
}
|
||||
|
||||
export function isRollingSummary(node: IrNode): node is RollingSummary {
|
||||
return node.type === 'ROLLING_SUMMARY';
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { Content } from '@google/genai';
|
||||
import type { Episode, ConcreteNode } from './types.js';
|
||||
import { toIr } from './toIr.js';
|
||||
import { fromIr } from './fromIr.js';
|
||||
import type { ContextTokenCalculator } from '../utils/contextTokenCalculator.js';
|
||||
import type { IrNodeBehaviorRegistry } from './behaviorRegistry.js';
|
||||
|
||||
export class IrMapper {
|
||||
private readonly nodeIdentityMap = new WeakMap<object, string>();
|
||||
|
||||
constructor(private readonly registry: IrNodeBehaviorRegistry) {}
|
||||
|
||||
toIr(
|
||||
history: readonly Content[],
|
||||
tokenCalculator: ContextTokenCalculator,
|
||||
): Episode[] {
|
||||
return toIr(history, tokenCalculator, this.nodeIdentityMap);
|
||||
}
|
||||
|
||||
fromIr(nodes: readonly ConcreteNode[]): Content[] {
|
||||
return fromIr(nodes, this.registry);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,120 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { Content } from '@google/genai';
|
||||
import type { ConcreteNode } from './types.js';
|
||||
import { debugLogger } from '../../utils/debugLogger.js';
|
||||
import type {
|
||||
ContextEnvironment,
|
||||
ContextTracer,
|
||||
} from '../sidecar/environment.js';
|
||||
import type { PipelineOrchestrator } from '../sidecar/orchestrator.js';
|
||||
import type { SidecarConfig } from '../sidecar/types.js';
|
||||
|
||||
export class IrProjector {
|
||||
/**
|
||||
* Orchestrates the final projection: takes a working buffer view (The Nodes),
|
||||
* applies the Immediate Sanitization pipeline, and enforces token boundaries.
|
||||
*/
|
||||
static async project(
|
||||
nodes: readonly ConcreteNode[],
|
||||
orchestrator: PipelineOrchestrator,
|
||||
sidecar: SidecarConfig,
|
||||
tracer: ContextTracer,
|
||||
env: ContextEnvironment,
|
||||
protectedIds: Set<string>,
|
||||
): Promise<Content[]> {
|
||||
if (!sidecar.budget) {
|
||||
const contents = env.irMapper.fromIr(nodes);
|
||||
tracer.logEvent('IrProjector', 'Projected Context to LLM (No Budget)', {
|
||||
projectedContext: contents,
|
||||
});
|
||||
return contents;
|
||||
}
|
||||
|
||||
const maxTokens = sidecar.budget.maxTokens;
|
||||
const currentTokens =
|
||||
env.tokenCalculator.calculateConcreteListTokens(nodes);
|
||||
|
||||
// V0: Always protect the first node (System Prompt) and the last turn
|
||||
if (nodes.length > 0) {
|
||||
protectedIds.add(nodes[0].id);
|
||||
if (nodes[0].logicalParentId) protectedIds.add(nodes[0].logicalParentId);
|
||||
|
||||
const lastNode = nodes[nodes.length - 1];
|
||||
protectedIds.add(lastNode.id);
|
||||
if (lastNode.logicalParentId) protectedIds.add(lastNode.logicalParentId);
|
||||
}
|
||||
|
||||
if (currentTokens <= maxTokens) {
|
||||
tracer.logEvent(
|
||||
'IrProjector',
|
||||
`View is within maxTokens (${currentTokens} <= ${maxTokens}). Returning view.`,
|
||||
);
|
||||
const contents = env.irMapper.fromIr(nodes);
|
||||
tracer.logEvent('IrProjector', 'Projected Context to LLM', {
|
||||
projectedContext: contents,
|
||||
});
|
||||
return contents;
|
||||
}
|
||||
|
||||
tracer.logEvent(
|
||||
'IrProjector',
|
||||
`View exceeds maxTokens (${currentTokens} > ${maxTokens}). Hitting Synchronous Pressure Barrier.`,
|
||||
);
|
||||
debugLogger.log(
|
||||
`Context Manager Synchronous Barrier triggered: View at ${currentTokens} tokens (limit: ${maxTokens}).`,
|
||||
);
|
||||
|
||||
// Calculate exactly which nodes aged out of the retainedTokens budget to form our target delta
|
||||
const agedOutNodes = new Set<string>();
|
||||
let rollingTokens = 0;
|
||||
// Start from newest and count backwards
|
||||
for (let i = nodes.length - 1; i >= 0; i--) {
|
||||
const node = nodes[i];
|
||||
const nodeTokens = env.tokenCalculator.calculateConcreteListTokens([
|
||||
node,
|
||||
]);
|
||||
rollingTokens += nodeTokens;
|
||||
if (rollingTokens > sidecar.budget.retainedTokens) {
|
||||
agedOutNodes.add(node.id);
|
||||
}
|
||||
}
|
||||
|
||||
const processedNodes = await orchestrator.executeTriggerSync(
|
||||
'gc_backstop',
|
||||
nodes,
|
||||
agedOutNodes,
|
||||
protectedIds,
|
||||
);
|
||||
|
||||
const finalTokens =
|
||||
env.tokenCalculator.calculateConcreteListTokens(processedNodes);
|
||||
tracer.logEvent(
|
||||
'IrProjector',
|
||||
`Finished projection. Final token count: ${finalTokens}.`,
|
||||
);
|
||||
debugLogger.log(
|
||||
`Context Manager finished. Final actual token count: ${finalTokens}.`,
|
||||
);
|
||||
|
||||
// Apply skipList logic to abstract over summarized nodes
|
||||
const skipList = new Set<string>();
|
||||
for (const node of processedNodes) {
|
||||
if (node.abstractsIds) {
|
||||
for (const id of node.abstractsIds) skipList.add(id);
|
||||
}
|
||||
}
|
||||
|
||||
const visibleNodes = processedNodes.filter((n) => !skipList.has(n.id));
|
||||
|
||||
const contents = env.irMapper.fromIr(visibleNodes);
|
||||
tracer.logEvent('IrProjector', 'Projected Sanitized Context to LLM', {
|
||||
projectedContextSanitized: contents,
|
||||
});
|
||||
return contents;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,236 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { Content, Part } from '@google/genai';
|
||||
import { randomUUID } from 'node:crypto';
|
||||
import type {
|
||||
Episode,
|
||||
SemanticPart,
|
||||
ToolExecution,
|
||||
AgentThought,
|
||||
AgentYield,
|
||||
UserPrompt,
|
||||
} from './types.js';
|
||||
import type { ContextTokenCalculator } from '../utils/contextTokenCalculator.js';
|
||||
|
||||
// We remove the global nodeIdentityMap and instead rely on one passed from IrMapper
|
||||
export function getStableId(
|
||||
obj: object,
|
||||
nodeIdentityMap: WeakMap<object, string>,
|
||||
): string {
|
||||
let id = nodeIdentityMap.get(obj);
|
||||
if (!id) {
|
||||
id = randomUUID();
|
||||
nodeIdentityMap.set(obj, id);
|
||||
}
|
||||
return id;
|
||||
}
|
||||
|
||||
function isRecord(v: unknown): v is Record<string, unknown> {
|
||||
return typeof v === 'object' && v !== null && !Array.isArray(v);
|
||||
}
|
||||
|
||||
function isCompleteEpisode(ep: Partial<Episode>): ep is Episode {
|
||||
return (
|
||||
typeof ep.id === 'string' &&
|
||||
typeof ep.timestamp === 'number' &&
|
||||
Array.isArray(ep.concreteNodes) &&
|
||||
ep.concreteNodes.length > 0
|
||||
);
|
||||
}
|
||||
|
||||
export function toIr(
|
||||
history: readonly Content[],
|
||||
tokenCalculator: ContextTokenCalculator,
|
||||
nodeIdentityMap: WeakMap<object, string>,
|
||||
): Episode[] {
|
||||
const episodes: Episode[] = [];
|
||||
let currentEpisode: Partial<Episode> | null = null;
|
||||
const pendingCallParts: Map<string, Part> = new Map();
|
||||
|
||||
const finalizeEpisode = () => {
|
||||
if (currentEpisode && isCompleteEpisode(currentEpisode)) {
|
||||
episodes.push(currentEpisode);
|
||||
}
|
||||
currentEpisode = null;
|
||||
};
|
||||
|
||||
for (const msg of history) {
|
||||
if (!msg.parts) continue;
|
||||
|
||||
if (msg.role === 'user') {
|
||||
const hasToolResponses = msg.parts.some((p) => !!p.functionResponse);
|
||||
const hasUserParts = msg.parts.some(
|
||||
(p) => !!p.text || !!p.inlineData || !!p.fileData,
|
||||
);
|
||||
|
||||
if (hasToolResponses) {
|
||||
currentEpisode = parseToolResponses(
|
||||
msg,
|
||||
currentEpisode,
|
||||
pendingCallParts,
|
||||
tokenCalculator,
|
||||
nodeIdentityMap,
|
||||
);
|
||||
}
|
||||
|
||||
if (hasUserParts) {
|
||||
finalizeEpisode();
|
||||
currentEpisode = parseUserParts(msg, nodeIdentityMap);
|
||||
}
|
||||
} else if (msg.role === 'model') {
|
||||
currentEpisode = parseModelParts(
|
||||
msg,
|
||||
currentEpisode,
|
||||
pendingCallParts,
|
||||
nodeIdentityMap,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
if (currentEpisode) {
|
||||
finalizeYield(currentEpisode);
|
||||
finalizeEpisode();
|
||||
}
|
||||
|
||||
return episodes;
|
||||
}
|
||||
|
||||
function parseToolResponses(
|
||||
msg: Content,
|
||||
currentEpisode: Partial<Episode> | null,
|
||||
pendingCallParts: Map<string, Part>,
|
||||
tokenCalculator: ContextTokenCalculator,
|
||||
nodeIdentityMap: WeakMap<object, string>,
|
||||
): Partial<Episode> {
|
||||
if (!currentEpisode) {
|
||||
currentEpisode = {
|
||||
id: getStableId(msg, nodeIdentityMap),
|
||||
timestamp: Date.now(),
|
||||
concreteNodes: [],
|
||||
};
|
||||
}
|
||||
|
||||
const parts = msg.parts || [];
|
||||
for (const part of parts) {
|
||||
if (part.functionResponse) {
|
||||
const callId = part.functionResponse.id || '';
|
||||
const matchingCall = pendingCallParts.get(callId);
|
||||
|
||||
const intentTokens = matchingCall
|
||||
? tokenCalculator.estimateTokensForParts([matchingCall])
|
||||
: 0;
|
||||
const obsTokens = tokenCalculator.estimateTokensForParts([part]);
|
||||
|
||||
const step: ToolExecution = {
|
||||
id: getStableId(part, nodeIdentityMap),
|
||||
type: 'TOOL_EXECUTION',
|
||||
toolName: part.functionResponse.name || 'unknown',
|
||||
intent: isRecord(matchingCall?.functionCall?.args)
|
||||
? matchingCall.functionCall.args
|
||||
: {},
|
||||
observation: isRecord(part.functionResponse.response)
|
||||
? part.functionResponse.response
|
||||
: {},
|
||||
tokens: {
|
||||
intent: intentTokens,
|
||||
observation: obsTokens,
|
||||
},
|
||||
};
|
||||
currentEpisode.concreteNodes = [
|
||||
...(currentEpisode.concreteNodes || []),
|
||||
step,
|
||||
];
|
||||
if (callId) pendingCallParts.delete(callId);
|
||||
}
|
||||
}
|
||||
return currentEpisode;
|
||||
}
|
||||
|
||||
function parseUserParts(
|
||||
msg: Content,
|
||||
nodeIdentityMap: WeakMap<object, string>,
|
||||
): Partial<Episode> {
|
||||
const semanticParts: SemanticPart[] = [];
|
||||
const parts = msg.parts || [];
|
||||
for (const p of parts) {
|
||||
if (p.text !== undefined)
|
||||
semanticParts.push({ type: 'text', text: p.text });
|
||||
else if (p.inlineData)
|
||||
semanticParts.push({
|
||||
type: 'inline_data',
|
||||
mimeType: p.inlineData.mimeType || '',
|
||||
data: p.inlineData.data || '',
|
||||
});
|
||||
else if (p.fileData)
|
||||
semanticParts.push({
|
||||
type: 'file_data',
|
||||
mimeType: p.fileData.mimeType || '',
|
||||
fileUri: p.fileData.fileUri || '',
|
||||
});
|
||||
else if (!p.functionResponse)
|
||||
semanticParts.push({ type: 'raw_part', part: p }); // Preserve unknowns
|
||||
}
|
||||
|
||||
const baseObj = parts.length > 0 ? parts[0] : msg;
|
||||
const trigger: UserPrompt = {
|
||||
id: getStableId(baseObj, nodeIdentityMap),
|
||||
type: 'USER_PROMPT',
|
||||
semanticParts,
|
||||
};
|
||||
return {
|
||||
id: getStableId(msg, nodeIdentityMap),
|
||||
timestamp: Date.now(),
|
||||
concreteNodes: [trigger],
|
||||
};
|
||||
}
|
||||
|
||||
function parseModelParts(
|
||||
msg: Content,
|
||||
currentEpisode: Partial<Episode> | null,
|
||||
pendingCallParts: Map<string, Part>,
|
||||
nodeIdentityMap: WeakMap<object, string>,
|
||||
): Partial<Episode> {
|
||||
if (!currentEpisode) {
|
||||
currentEpisode = {
|
||||
id: getStableId(msg, nodeIdentityMap),
|
||||
timestamp: Date.now(),
|
||||
concreteNodes: [],
|
||||
};
|
||||
}
|
||||
|
||||
const parts = msg.parts || [];
|
||||
for (const part of parts) {
|
||||
if (part.functionCall) {
|
||||
const callId = part.functionCall.id || '';
|
||||
if (callId) pendingCallParts.set(callId, part);
|
||||
} else if (part.text) {
|
||||
const thought: AgentThought = {
|
||||
id: getStableId(part, nodeIdentityMap),
|
||||
type: 'AGENT_THOUGHT',
|
||||
text: part.text,
|
||||
};
|
||||
|
||||
currentEpisode.concreteNodes = [
|
||||
...(currentEpisode.concreteNodes || []),
|
||||
thought,
|
||||
];
|
||||
}
|
||||
}
|
||||
return currentEpisode;
|
||||
}
|
||||
|
||||
function finalizeYield(currentEpisode: Partial<Episode>) {
|
||||
if (currentEpisode.concreteNodes && currentEpisode.concreteNodes.length > 0) {
|
||||
const yieldNode: AgentYield = {
|
||||
id: randomUUID(),
|
||||
type: 'AGENT_YIELD',
|
||||
text: 'Yield', // Synthesized yield since we don't have the original concrete node
|
||||
};
|
||||
const existingNodes = currentEpisode.concreteNodes || [];
|
||||
currentEpisode.concreteNodes = [...existingNodes, yieldNode];
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,177 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { Part } from '@google/genai';
|
||||
|
||||
export type IrNodeType =
|
||||
// Organic Concrete Nodes
|
||||
| 'USER_PROMPT'
|
||||
| 'SYSTEM_EVENT'
|
||||
| 'AGENT_THOUGHT'
|
||||
| 'TOOL_EXECUTION'
|
||||
| 'AGENT_YIELD'
|
||||
|
||||
// Synthetic Concrete Nodes
|
||||
| 'SNAPSHOT'
|
||||
| 'ROLLING_SUMMARY'
|
||||
| 'MASKED_TOOL'
|
||||
|
||||
// Logical Nodes
|
||||
| 'TASK'
|
||||
| 'EPISODE';
|
||||
|
||||
/** Base interface for all nodes in the Episodic IR */
|
||||
export interface IrNode {
|
||||
readonly id: string;
|
||||
readonly type: IrNodeType;
|
||||
}
|
||||
|
||||
/**
|
||||
* Concrete Nodes: The atomic, renderable pieces of data.
|
||||
* These are the actual "planks" of the Nodes of Theseus.
|
||||
*/
|
||||
export interface BaseConcreteNode extends IrNode {
|
||||
/** The ID of the Logical Node (e.g., Episode) that structurally owns this node */
|
||||
readonly logicalParentId?: string;
|
||||
|
||||
/** If this node replaced a single node 1:1 (e.g., masking), this points to the original */
|
||||
readonly replacesId?: string;
|
||||
|
||||
/** If this node is a synthetic summary of N nodes, this points to the original IDs */
|
||||
readonly abstractsIds?: readonly string[];
|
||||
}
|
||||
|
||||
/**
|
||||
* Semantic Parts for User Prompts
|
||||
*/
|
||||
export type SemanticPart =
|
||||
| {
|
||||
readonly type: 'text';
|
||||
readonly text: string;
|
||||
}
|
||||
| {
|
||||
readonly type: 'inline_data';
|
||||
readonly mimeType: string;
|
||||
readonly data: string;
|
||||
}
|
||||
| {
|
||||
readonly type: 'file_data';
|
||||
readonly mimeType: string;
|
||||
readonly fileUri: string;
|
||||
}
|
||||
| {
|
||||
readonly type: 'raw_part';
|
||||
readonly part: Part;
|
||||
};
|
||||
|
||||
/**
|
||||
* Trigger Nodes
|
||||
* Events that wake the agent up and initiate an Episode.
|
||||
*/
|
||||
export interface UserPrompt extends BaseConcreteNode {
|
||||
readonly type: 'USER_PROMPT';
|
||||
readonly semanticParts: readonly SemanticPart[];
|
||||
}
|
||||
|
||||
export interface SystemEvent extends BaseConcreteNode {
|
||||
readonly type: 'SYSTEM_EVENT';
|
||||
readonly name: string;
|
||||
readonly payload: Record<string, unknown>;
|
||||
}
|
||||
|
||||
export type EpisodeTrigger = UserPrompt | SystemEvent;
|
||||
|
||||
/**
|
||||
* Step Nodes
|
||||
* The internal autonomous actions taken by the agent during its loop.
|
||||
*/
|
||||
export interface AgentThought extends BaseConcreteNode {
|
||||
readonly type: 'AGENT_THOUGHT';
|
||||
readonly text: string;
|
||||
}
|
||||
|
||||
export interface ToolExecution extends BaseConcreteNode {
|
||||
readonly type: 'TOOL_EXECUTION';
|
||||
readonly toolName: string;
|
||||
readonly intent: Record<string, unknown>;
|
||||
readonly observation: string | Record<string, unknown>;
|
||||
readonly tokens: {
|
||||
readonly intent: number;
|
||||
readonly observation: number;
|
||||
};
|
||||
}
|
||||
|
||||
export interface MaskedTool extends BaseConcreteNode {
|
||||
readonly type: 'MASKED_TOOL';
|
||||
readonly toolName: string;
|
||||
readonly intent?: Record<string, unknown>;
|
||||
readonly observation?: string | Record<string, unknown>;
|
||||
readonly tokens: {
|
||||
readonly intent: number;
|
||||
readonly observation: number;
|
||||
};
|
||||
}
|
||||
|
||||
export type EpisodeStep = AgentThought | ToolExecution | MaskedTool;
|
||||
|
||||
/**
|
||||
* Resolution Node
|
||||
* The final message where the agent yields control back to the user.
|
||||
*/
|
||||
export interface AgentYield extends BaseConcreteNode {
|
||||
readonly type: 'AGENT_YIELD';
|
||||
readonly text: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* Synthetic Leaf Interfaces
|
||||
* Processors that generate summaries emit explicit synthetic nodes.
|
||||
*/
|
||||
export interface Snapshot extends BaseConcreteNode {
|
||||
readonly type: 'SNAPSHOT';
|
||||
readonly timestamp: number;
|
||||
readonly text: string;
|
||||
}
|
||||
|
||||
export interface RollingSummary extends BaseConcreteNode {
|
||||
readonly type: 'ROLLING_SUMMARY';
|
||||
readonly timestamp: number;
|
||||
readonly text: string;
|
||||
}
|
||||
|
||||
export type SyntheticLeaf = Snapshot | RollingSummary;
|
||||
|
||||
export type ConcreteNode =
|
||||
| UserPrompt
|
||||
| SystemEvent
|
||||
| AgentThought
|
||||
| ToolExecution
|
||||
| MaskedTool
|
||||
| AgentYield
|
||||
| Snapshot
|
||||
| RollingSummary;
|
||||
|
||||
/**
|
||||
* Logical Nodes
|
||||
* These define hierarchy and grouping. They do not directly render to Gemini.
|
||||
*/
|
||||
export interface Episode extends IrNode {
|
||||
readonly type: 'EPISODE';
|
||||
readonly timestamp: number;
|
||||
/** References to the Concrete Node IDs that conceptually belong to this Episode. */
|
||||
concreteNodes: readonly ConcreteNode[];
|
||||
}
|
||||
|
||||
export interface Task extends IrNode {
|
||||
readonly type: 'TASK';
|
||||
readonly timestamp: number;
|
||||
readonly goal: string;
|
||||
readonly status: 'active' | 'completed' | 'failed';
|
||||
/** References to the Episode IDs that belong to this task */
|
||||
readonly episodeIds: readonly string[];
|
||||
}
|
||||
|
||||
export type LogicalNode = Task | Episode;
|
||||
@@ -0,0 +1,64 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { ConcreteNode } from './ir/types.js';
|
||||
|
||||
export interface InboxMessage<T = unknown> {
|
||||
id: string;
|
||||
topic: string;
|
||||
payload: T;
|
||||
timestamp: number;
|
||||
}
|
||||
|
||||
export interface InboxSnapshot {
|
||||
getMessages<T = unknown>(topic: string): ReadonlyArray<InboxMessage<T>>;
|
||||
consume(messageId: string): void;
|
||||
}
|
||||
|
||||
export interface GraphMutation {
|
||||
readonly processorId: string;
|
||||
readonly timestamp: number;
|
||||
readonly removedIds: readonly string[];
|
||||
readonly addedNodes: readonly ConcreteNode[];
|
||||
}
|
||||
|
||||
export interface ContextWorkingBuffer {
|
||||
readonly nodes: readonly ConcreteNode[];
|
||||
getPristineNodes(id: string): readonly ConcreteNode[];
|
||||
getLineage(id: string): readonly ConcreteNode[];
|
||||
getAuditLog(): readonly GraphMutation[];
|
||||
}
|
||||
|
||||
export interface ProcessArgs {
|
||||
readonly buffer: ContextWorkingBuffer;
|
||||
readonly targets: readonly ConcreteNode[];
|
||||
readonly inbox: InboxSnapshot;
|
||||
}
|
||||
|
||||
export interface ContextProcessor {
|
||||
readonly id: string;
|
||||
readonly name: string;
|
||||
process(args: ProcessArgs): Promise<readonly ConcreteNode[]>;
|
||||
}
|
||||
|
||||
export interface ContextWorker {
|
||||
readonly id: string;
|
||||
readonly name: string;
|
||||
readonly triggers: {
|
||||
onNodesAdded?: boolean;
|
||||
onNodesAgedOut?: boolean;
|
||||
onInboxTopics?: string[];
|
||||
};
|
||||
execute(args: {
|
||||
targets: readonly ConcreteNode[];
|
||||
inbox: InboxSnapshot;
|
||||
}): Promise<void>;
|
||||
}
|
||||
|
||||
export interface BackstopTargetOptions {
|
||||
target?: 'incremental' | 'freeNTokens' | 'max';
|
||||
freeTokensTarget?: number;
|
||||
}
|
||||
@@ -0,0 +1,101 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import assert from 'node:assert';
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { BlobDegradationProcessor } from './blobDegradationProcessor.js';
|
||||
import {
|
||||
createMockProcessArgs,
|
||||
createMockEnvironment,
|
||||
createDummyNode,
|
||||
} from '../testing/contextTestUtils.js';
|
||||
import type { UserPrompt, SemanticPart, ConcreteNode } from '../ir/types.js';
|
||||
|
||||
describe('BlobDegradationProcessor', () => {
|
||||
it('should ignore text parts and only target inline_data and file_data', async () => {
|
||||
const env = createMockEnvironment();
|
||||
// charsPerToken = 1
|
||||
// We want the degraded text to be cheaper than the original blob.
|
||||
// Degraded text is ~100 chars ("...degraded to text...").
|
||||
// So we make the blob data 200 chars.
|
||||
const fakeData = 'A'.repeat(200);
|
||||
|
||||
const processor = BlobDegradationProcessor.create(env, {});
|
||||
|
||||
const parts: SemanticPart[] = [
|
||||
{ type: 'text', text: 'Hello' },
|
||||
{ type: 'inline_data', mimeType: 'image/png', data: fakeData },
|
||||
{ type: 'text', text: 'World' },
|
||||
];
|
||||
|
||||
const prompt = createDummyNode('ep1', 'USER_PROMPT', 100, {
|
||||
semanticParts: parts,
|
||||
}) as UserPrompt;
|
||||
|
||||
const targets = [prompt];
|
||||
|
||||
const result = await processor.process(createMockProcessArgs(targets));
|
||||
|
||||
expect(result.length).toBe(1);
|
||||
const modifiedPrompt = result[0] as UserPrompt;
|
||||
|
||||
expect(modifiedPrompt.id).not.toBe(prompt.id);
|
||||
expect(modifiedPrompt.semanticParts.length).toBe(3);
|
||||
|
||||
// Text parts should be untouched
|
||||
expect(modifiedPrompt.semanticParts[0]).toEqual(parts[0]);
|
||||
expect(modifiedPrompt.semanticParts[2]).toEqual(parts[2]);
|
||||
|
||||
// The inline_data part should be replaced with text
|
||||
const degradedPart = modifiedPrompt.semanticParts[1];
|
||||
expect(degradedPart.type).toBe('text');
|
||||
assert(degradedPart.type === 'text');
|
||||
expect(degradedPart.text).toContain(
|
||||
'[Multi-Modal Blob (image/png, 0.00MB) degraded to text',
|
||||
);
|
||||
});
|
||||
|
||||
it('should degrade all blobs unconditionally', async () => {
|
||||
const env = createMockEnvironment();
|
||||
|
||||
const processor = BlobDegradationProcessor.create(env, {});
|
||||
|
||||
// Tokens for fileData = 258.
|
||||
// Degraded text = "[File Reference (video/mp4) degraded to text to preserve context window. Original URI: gs://test1]"
|
||||
// Degraded text length ~100 characters.
|
||||
// Since charsPerToken=1, degraded text = 100 tokens.
|
||||
// Tokens saved = 258 - 100 = 158. This is > 0, so it WILL degrade it!
|
||||
|
||||
const prompt = createDummyNode('ep1', 'USER_PROMPT', 100, {
|
||||
semanticParts: [
|
||||
{ type: 'file_data', mimeType: 'video/mp4', fileUri: 'gs://test1' },
|
||||
{ type: 'file_data', mimeType: 'video/mp4', fileUri: 'gs://test2' },
|
||||
],
|
||||
}) as UserPrompt;
|
||||
|
||||
const targets = [prompt];
|
||||
|
||||
const result = await processor.process(createMockProcessArgs(targets));
|
||||
|
||||
const modifiedPrompt = result[0] as UserPrompt;
|
||||
expect(modifiedPrompt.semanticParts.length).toBe(2);
|
||||
|
||||
// Both parts should be degraded
|
||||
expect(modifiedPrompt.semanticParts[0].type).toBe('text');
|
||||
expect(modifiedPrompt.semanticParts[1].type).toBe('text');
|
||||
});
|
||||
|
||||
it('should return exactly the targets array if targets are empty', async () => {
|
||||
const env = createMockEnvironment();
|
||||
|
||||
const processor = BlobDegradationProcessor.create(env, {});
|
||||
const targets: ConcreteNode[] = [];
|
||||
|
||||
const result = await processor.process(createMockProcessArgs(targets));
|
||||
|
||||
expect(result).toBe(targets);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,161 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { ProcessArgs, ContextProcessor } from '../pipeline.js';
|
||||
import type { ConcreteNode, UserPrompt } from '../ir/types.js';
|
||||
import type { ContextEnvironment } from '../sidecar/environment.js';
|
||||
import { sanitizeFilenamePart } from '../../utils/fileUtils.js';
|
||||
|
||||
export type BlobDegradationProcessorOptions = Record<string, never>;
|
||||
|
||||
export class BlobDegradationProcessor implements ContextProcessor {
|
||||
static create(
|
||||
env: ContextEnvironment,
|
||||
_options: BlobDegradationProcessorOptions,
|
||||
): BlobDegradationProcessor {
|
||||
return new BlobDegradationProcessor(env);
|
||||
}
|
||||
|
||||
readonly componentType = 'processor';
|
||||
readonly id = 'BlobDegradationProcessor';
|
||||
readonly name = 'BlobDegradationProcessor';
|
||||
readonly options = {};
|
||||
private env: ContextEnvironment;
|
||||
|
||||
constructor(env: ContextEnvironment) {
|
||||
this.env = env;
|
||||
}
|
||||
|
||||
async process({ targets }: ProcessArgs): Promise<readonly ConcreteNode[]> {
|
||||
if (targets.length === 0) {
|
||||
return targets;
|
||||
}
|
||||
|
||||
let directoryCreated = false;
|
||||
|
||||
let blobOutputsDir = this.env.fileSystem.join(
|
||||
this.env.projectTempDir,
|
||||
'degraded-blobs',
|
||||
);
|
||||
const sessionId = this.env.sessionId;
|
||||
if (sessionId) {
|
||||
blobOutputsDir = this.env.fileSystem.join(
|
||||
blobOutputsDir,
|
||||
`session-${sanitizeFilenamePart(sessionId)}`,
|
||||
);
|
||||
}
|
||||
|
||||
const ensureDir = async () => {
|
||||
if (!directoryCreated) {
|
||||
await this.env.fileSystem.mkdir(blobOutputsDir, { recursive: true });
|
||||
directoryCreated = true;
|
||||
}
|
||||
};
|
||||
|
||||
const returnedNodes: ConcreteNode[] = [];
|
||||
|
||||
// Forward scan, looking for bloated non-text parts to degrade
|
||||
for (const node of targets) {
|
||||
switch (node.type) {
|
||||
case 'USER_PROMPT': {
|
||||
let modified = false;
|
||||
const newParts = [...node.semanticParts];
|
||||
|
||||
for (let j = 0; j < node.semanticParts.length; j++) {
|
||||
const part = node.semanticParts[j];
|
||||
if (part.type === 'text') continue;
|
||||
|
||||
let newText = '';
|
||||
let tokensSaved = 0;
|
||||
|
||||
switch (part.type) {
|
||||
case 'inline_data': {
|
||||
await ensureDir();
|
||||
const ext = part.mimeType.split('/')[1] || 'bin';
|
||||
const fileName = `blob_${Date.now()}_${this.env.idGenerator.generateId()}.${ext}`;
|
||||
const filePath = this.env.fileSystem.join(
|
||||
blobOutputsDir,
|
||||
fileName,
|
||||
);
|
||||
|
||||
const buffer = Buffer.from(part.data, 'base64');
|
||||
await this.env.fileSystem.writeFile(filePath, buffer);
|
||||
|
||||
const mb = (buffer.byteLength / 1024 / 1024).toFixed(2);
|
||||
newText = `[Multi-Modal Blob (${part.mimeType}, ${mb}MB) degraded to text to preserve context window. Saved to: ${filePath}]`;
|
||||
|
||||
const oldTokens =
|
||||
this.env.tokenCalculator.estimateTokensForParts([
|
||||
{
|
||||
inlineData: { mimeType: part.mimeType, data: part.data },
|
||||
},
|
||||
]);
|
||||
const newTokens =
|
||||
this.env.tokenCalculator.estimateTokensForParts([
|
||||
{ text: newText },
|
||||
]);
|
||||
tokensSaved = oldTokens - newTokens;
|
||||
break;
|
||||
}
|
||||
case 'file_data': {
|
||||
newText = `[File Reference (${part.mimeType}) degraded to text to preserve context window. Original URI: ${part.fileUri}]`;
|
||||
const oldTokens =
|
||||
this.env.tokenCalculator.estimateTokensForParts([
|
||||
{
|
||||
fileData: {
|
||||
mimeType: part.mimeType,
|
||||
fileUri: part.fileUri,
|
||||
},
|
||||
},
|
||||
]);
|
||||
const newTokens =
|
||||
this.env.tokenCalculator.estimateTokensForParts([
|
||||
{ text: newText },
|
||||
]);
|
||||
tokensSaved = oldTokens - newTokens;
|
||||
break;
|
||||
}
|
||||
case 'raw_part': {
|
||||
newText = `[Unknown Part degraded to text to preserve context window.]`;
|
||||
const oldTokens =
|
||||
this.env.tokenCalculator.estimateTokensForParts([part.part]);
|
||||
const newTokens =
|
||||
this.env.tokenCalculator.estimateTokensForParts([
|
||||
{ text: newText },
|
||||
]);
|
||||
tokensSaved = oldTokens - newTokens;
|
||||
break;
|
||||
}
|
||||
default:
|
||||
break;
|
||||
}
|
||||
|
||||
if (newText && tokensSaved > 0) {
|
||||
newParts[j] = { type: 'text', text: newText };
|
||||
modified = true;
|
||||
}
|
||||
}
|
||||
|
||||
if (modified) {
|
||||
const degradedNode: UserPrompt = {
|
||||
...node,
|
||||
id: this.env.idGenerator.generateId(),
|
||||
semanticParts: newParts,
|
||||
};
|
||||
returnedNodes.push(degradedNode);
|
||||
} else {
|
||||
returnedNodes.push(node);
|
||||
}
|
||||
break;
|
||||
}
|
||||
default:
|
||||
returnedNodes.push(node);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return returnedNodes;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,84 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type {
|
||||
ContextProcessor,
|
||||
BackstopTargetOptions,
|
||||
ProcessArgs,
|
||||
} from '../pipeline.js';
|
||||
import type { ConcreteNode } from '../ir/types.js';
|
||||
import type { ContextEnvironment } from '../sidecar/environment.js';
|
||||
|
||||
export type HistoryTruncationProcessorOptions = BackstopTargetOptions;
|
||||
|
||||
export class HistoryTruncationProcessor implements ContextProcessor {
|
||||
static create(
|
||||
env: ContextEnvironment,
|
||||
options: HistoryTruncationProcessorOptions,
|
||||
): HistoryTruncationProcessor {
|
||||
return new HistoryTruncationProcessor(env, options);
|
||||
}
|
||||
|
||||
static readonly schema = {
|
||||
type: 'object',
|
||||
properties: {
|
||||
target: {
|
||||
type: 'string',
|
||||
enum: ['incremental', 'freeNTokens', 'max'],
|
||||
description: 'How much of the targeted history to truncate.',
|
||||
},
|
||||
freeTokensTarget: {
|
||||
type: 'number',
|
||||
description: 'The number of tokens to free if target is freeNTokens.',
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
readonly componentType = 'processor';
|
||||
readonly id = 'HistoryTruncationProcessor';
|
||||
readonly name = 'HistoryTruncationProcessor';
|
||||
private readonly env: ContextEnvironment;
|
||||
readonly options: HistoryTruncationProcessorOptions;
|
||||
constructor(
|
||||
env: ContextEnvironment,
|
||||
options: HistoryTruncationProcessorOptions,
|
||||
) {
|
||||
this.env = env;
|
||||
this.options = options;
|
||||
}
|
||||
|
||||
async process({ targets }: ProcessArgs): Promise<readonly ConcreteNode[]> {
|
||||
// Calculate how many tokens we need to remove based on the configured knob
|
||||
let targetTokensToRemove = 0;
|
||||
const strategy = this.options.target ?? 'max';
|
||||
|
||||
if (strategy === 'incremental') {
|
||||
targetTokensToRemove = Infinity;
|
||||
} else if (strategy === 'freeNTokens') {
|
||||
targetTokensToRemove = this.options.freeTokensTarget ?? 0;
|
||||
if (targetTokensToRemove <= 0) return targets;
|
||||
} else if (strategy === 'max') {
|
||||
// 'max' means we remove all targets without stopping early
|
||||
targetTokensToRemove = Infinity;
|
||||
}
|
||||
|
||||
let removedTokens = 0;
|
||||
const keptNodes: ConcreteNode[] = [];
|
||||
|
||||
// The targets are sequentially ordered from oldest to newest.
|
||||
// We want to delete the oldest targets first.
|
||||
for (const node of targets) {
|
||||
if (removedTokens >= targetTokensToRemove) {
|
||||
keptNodes.push(node);
|
||||
continue;
|
||||
}
|
||||
|
||||
removedTokens += this.env.tokenCalculator.getTokenCost(node);
|
||||
}
|
||||
|
||||
return keptNodes;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,140 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import assert from 'node:assert';
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { NodeDistillationProcessor } from './nodeDistillationProcessor.js';
|
||||
import {
|
||||
createMockProcessArgs,
|
||||
createMockEnvironment,
|
||||
createDummyNode,
|
||||
createDummyToolNode,
|
||||
createMockLlmClient,
|
||||
} from '../testing/contextTestUtils.js';
|
||||
import type { UserPrompt, AgentThought, ToolExecution } from '../ir/types.js';
|
||||
|
||||
describe('NodeDistillationProcessor', () => {
|
||||
it('should trigger summarization via LLM for long text parts', async () => {
|
||||
const mockLlmClient = createMockLlmClient(['Mocked Summary!']);
|
||||
|
||||
// Use charsPerToken=1 naturally.
|
||||
const env = createMockEnvironment({
|
||||
llmClient: mockLlmClient,
|
||||
});
|
||||
|
||||
const processor = NodeDistillationProcessor.create(env, {
|
||||
nodeThresholdTokens: 10,
|
||||
});
|
||||
|
||||
const longText = 'A'.repeat(50); // 50 chars
|
||||
|
||||
const prompt = createDummyNode(
|
||||
'ep1',
|
||||
'USER_PROMPT',
|
||||
50,
|
||||
{
|
||||
semanticParts: [{ type: 'text', text: longText }],
|
||||
},
|
||||
'prompt-id',
|
||||
) as UserPrompt;
|
||||
|
||||
const thought = createDummyNode(
|
||||
'ep1',
|
||||
'AGENT_THOUGHT',
|
||||
50,
|
||||
{
|
||||
text: longText,
|
||||
},
|
||||
'thought-id',
|
||||
) as AgentThought;
|
||||
|
||||
const tool = createDummyToolNode(
|
||||
'ep1',
|
||||
5,
|
||||
500,
|
||||
{
|
||||
observation: { result: 'A'.repeat(500) },
|
||||
},
|
||||
'tool-id',
|
||||
);
|
||||
|
||||
const targets = [prompt, thought, tool];
|
||||
|
||||
const result = await processor.process(createMockProcessArgs(targets));
|
||||
|
||||
expect(result.length).toBe(3);
|
||||
|
||||
// 1. User Prompt
|
||||
const compressedPrompt = result[0] as UserPrompt;
|
||||
expect(compressedPrompt.id).not.toBe(prompt.id);
|
||||
expect(compressedPrompt.semanticParts[0].type).toBe('text');
|
||||
assert(compressedPrompt.semanticParts[0].type === 'text');
|
||||
expect(compressedPrompt.semanticParts[0].text).toBe('Mocked Summary!');
|
||||
|
||||
// 2. Agent Thought
|
||||
const compressedThought = result[1] as AgentThought;
|
||||
expect(compressedThought.id).not.toBe(thought.id);
|
||||
expect(compressedThought.text).toBe('Mocked Summary!');
|
||||
|
||||
// 3. Tool Execution
|
||||
const compressedTool = result[2] as ToolExecution;
|
||||
expect(compressedTool.id).not.toBe(tool.id);
|
||||
expect(compressedTool.observation).toEqual({ summary: 'Mocked Summary!' });
|
||||
|
||||
expect(mockLlmClient.generateContent).toHaveBeenCalledTimes(3);
|
||||
});
|
||||
|
||||
it('should ignore nodes that are below the threshold', async () => {
|
||||
const mockLlmClient = createMockLlmClient(['S']); // length = 1
|
||||
|
||||
const env = createMockEnvironment({
|
||||
llmClient: mockLlmClient,
|
||||
});
|
||||
|
||||
const processor = NodeDistillationProcessor.create(env, {
|
||||
nodeThresholdTokens: 100, // Very high threshold
|
||||
});
|
||||
|
||||
const shortText = 'Short text'; // 10 chars
|
||||
|
||||
const prompt = createDummyNode(
|
||||
'ep1',
|
||||
'USER_PROMPT',
|
||||
10,
|
||||
{
|
||||
semanticParts: [{ type: 'text', text: shortText }],
|
||||
},
|
||||
'prompt-id',
|
||||
) as UserPrompt;
|
||||
|
||||
const thought = createDummyNode(
|
||||
'ep1',
|
||||
'AGENT_THOUGHT',
|
||||
13,
|
||||
{
|
||||
text: 'Short thought',
|
||||
},
|
||||
'thought-id',
|
||||
) as AgentThought;
|
||||
|
||||
const targets = [prompt, thought];
|
||||
|
||||
const result = await processor.process(createMockProcessArgs(targets));
|
||||
|
||||
expect(result.length).toBe(2);
|
||||
|
||||
// 1. User Prompt (NOT compressed)
|
||||
const untouchedPrompt = result[0] as UserPrompt;
|
||||
expect(untouchedPrompt.id).toBe(prompt.id);
|
||||
|
||||
// 2. Agent Thought (NOT compressed)
|
||||
const untouchedThought = result[1] as AgentThought;
|
||||
expect(untouchedThought.id).toBe(thought.id);
|
||||
|
||||
// LLM should not have been called
|
||||
expect(mockLlmClient.generateContent).toHaveBeenCalledTimes(0);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,221 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { ContextProcessor, ProcessArgs } from '../pipeline.js';
|
||||
import type { ConcreteNode } from '../ir/types.js';
|
||||
import type { ContextEnvironment } from '../sidecar/environment.js';
|
||||
import { debugLogger } from '../../utils/debugLogger.js';
|
||||
import { getResponseText } from '../../utils/partUtils.js';
|
||||
|
||||
import { LlmRole } from '../../telemetry/llmRole.js';
|
||||
|
||||
export interface NodeDistillationProcessorOptions {
|
||||
nodeThresholdTokens: number;
|
||||
}
|
||||
|
||||
export class NodeDistillationProcessor implements ContextProcessor {
|
||||
static create(
|
||||
env: ContextEnvironment,
|
||||
options: NodeDistillationProcessorOptions,
|
||||
): NodeDistillationProcessor {
|
||||
return new NodeDistillationProcessor(env, options);
|
||||
}
|
||||
|
||||
static readonly schema = {
|
||||
type: 'object',
|
||||
properties: {
|
||||
nodeThresholdTokens: {
|
||||
type: 'number',
|
||||
description: 'The token threshold above which nodes are summarized.',
|
||||
},
|
||||
},
|
||||
required: ['nodeThresholdTokens'],
|
||||
};
|
||||
|
||||
readonly componentType = 'processor';
|
||||
readonly id = 'NodeDistillationProcessor';
|
||||
readonly name = 'NodeDistillationProcessor';
|
||||
readonly options: NodeDistillationProcessorOptions;
|
||||
private env: ContextEnvironment;
|
||||
|
||||
constructor(
|
||||
env: ContextEnvironment,
|
||||
options: NodeDistillationProcessorOptions,
|
||||
) {
|
||||
this.env = env;
|
||||
this.options = options;
|
||||
}
|
||||
|
||||
private async generateSummary(
|
||||
text: string,
|
||||
contextInfo: string,
|
||||
): Promise<string> {
|
||||
try {
|
||||
const response = await this.env.llmClient.generateContent({
|
||||
role: LlmRole.UTILITY_COMPRESSOR,
|
||||
modelConfigKey: { model: 'summarizer-default' },
|
||||
promptId: this.env.promptId,
|
||||
abortSignal: new AbortController().signal,
|
||||
contents: [
|
||||
{
|
||||
role: 'user',
|
||||
parts: [{ text }],
|
||||
},
|
||||
],
|
||||
systemInstruction: {
|
||||
role: 'system',
|
||||
parts: [
|
||||
{
|
||||
text: `You are an expert context compressor. Your job is to drastically shorten the following ${contextInfo} while preserving the absolute core semantic meaning, facts, and intent. Omit all conversational filler, pleasantries, or redundant information. Return ONLY the compressed summary.`,
|
||||
},
|
||||
],
|
||||
},
|
||||
});
|
||||
return getResponseText(response) || text;
|
||||
} catch (e) {
|
||||
debugLogger.warn(
|
||||
`NodeDistillationProcessor failed to summarize ${contextInfo}`,
|
||||
e,
|
||||
);
|
||||
return text; // Fallback to original text on API failure
|
||||
}
|
||||
}
|
||||
|
||||
async process({ targets }: ProcessArgs): Promise<readonly ConcreteNode[]> {
|
||||
const semanticConfig = this.options;
|
||||
const limitTokens = semanticConfig.nodeThresholdTokens;
|
||||
const thresholdChars = this.env.tokenCalculator.tokensToChars(limitTokens);
|
||||
|
||||
const returnedNodes: ConcreteNode[] = [];
|
||||
|
||||
// Scan the target working buffer and unconditionally apply the configured hyperparameter threshold
|
||||
for (const node of targets) {
|
||||
switch (node.type) {
|
||||
case 'USER_PROMPT': {
|
||||
let modified = false;
|
||||
const newParts = [...node.semanticParts];
|
||||
|
||||
for (let j = 0; j < node.semanticParts.length; j++) {
|
||||
const part = node.semanticParts[j];
|
||||
if (part.type !== 'text') continue;
|
||||
|
||||
if (part.text.length > thresholdChars) {
|
||||
const summary = await this.generateSummary(
|
||||
part.text,
|
||||
'User Prompt',
|
||||
);
|
||||
const newTokens = this.env.tokenCalculator.estimateTokensForParts(
|
||||
[{ text: summary }],
|
||||
);
|
||||
const oldTokens = this.env.tokenCalculator.estimateTokensForParts(
|
||||
[{ text: part.text }],
|
||||
);
|
||||
|
||||
if (newTokens < oldTokens) {
|
||||
newParts[j] = { type: 'text', text: summary };
|
||||
modified = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (modified) {
|
||||
returnedNodes.push({
|
||||
...node,
|
||||
id: this.env.idGenerator.generateId(),
|
||||
semanticParts: newParts,
|
||||
});
|
||||
} else {
|
||||
returnedNodes.push(node);
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
case 'AGENT_THOUGHT': {
|
||||
if (node.text.length > thresholdChars) {
|
||||
const summary = await this.generateSummary(
|
||||
node.text,
|
||||
'Agent Thought',
|
||||
);
|
||||
const newTokens = this.env.tokenCalculator.estimateTokensForParts([
|
||||
{ text: summary },
|
||||
]);
|
||||
const oldTokens = this.env.tokenCalculator.getTokenCost(node);
|
||||
|
||||
if (newTokens < oldTokens) {
|
||||
returnedNodes.push({
|
||||
...node,
|
||||
id: this.env.idGenerator.generateId(),
|
||||
text: summary,
|
||||
});
|
||||
break;
|
||||
}
|
||||
}
|
||||
returnedNodes.push(node);
|
||||
break;
|
||||
}
|
||||
|
||||
case 'TOOL_EXECUTION': {
|
||||
const rawObs = node.observation;
|
||||
|
||||
let stringifiedObs = '';
|
||||
if (typeof rawObs === 'string') {
|
||||
stringifiedObs = rawObs;
|
||||
} else {
|
||||
try {
|
||||
stringifiedObs = JSON.stringify(rawObs);
|
||||
} catch {
|
||||
stringifiedObs = String(rawObs);
|
||||
}
|
||||
}
|
||||
|
||||
if (stringifiedObs.length > thresholdChars) {
|
||||
const summary = await this.generateSummary(
|
||||
stringifiedObs,
|
||||
node.toolName || 'unknown',
|
||||
);
|
||||
const newObsObject = { summary };
|
||||
|
||||
const newObsTokens =
|
||||
this.env.tokenCalculator.estimateTokensForParts([
|
||||
{
|
||||
functionResponse: {
|
||||
name: node.toolName || 'unknown',
|
||||
response: newObsObject,
|
||||
id: node.id,
|
||||
},
|
||||
},
|
||||
]);
|
||||
|
||||
const oldObsTokens =
|
||||
node.tokens?.observation ??
|
||||
this.env.tokenCalculator.getTokenCost(node);
|
||||
const intentTokens = node.tokens?.intent ?? 0;
|
||||
|
||||
if (newObsTokens < oldObsTokens) {
|
||||
returnedNodes.push({
|
||||
...node,
|
||||
id: this.env.idGenerator.generateId(),
|
||||
observation: newObsObject as Record<string, unknown>,
|
||||
tokens: {
|
||||
intent: intentTokens,
|
||||
observation: newObsTokens,
|
||||
},
|
||||
});
|
||||
break;
|
||||
}
|
||||
}
|
||||
returnedNodes.push(node);
|
||||
break;
|
||||
}
|
||||
|
||||
default:
|
||||
returnedNodes.push(node);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return returnedNodes;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,128 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import assert from 'node:assert';
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { NodeTruncationProcessor } from './nodeTruncationProcessor.js';
|
||||
import {
|
||||
createMockProcessArgs,
|
||||
createMockEnvironment,
|
||||
createDummyNode,
|
||||
} from '../testing/contextTestUtils.js';
|
||||
import type { UserPrompt, AgentThought, AgentYield } from '../ir/types.js';
|
||||
|
||||
describe('NodeTruncationProcessor', () => {
|
||||
it('should truncate nodes that exceed maxTokensPerNode', async () => {
|
||||
// env.tokenCalculator uses charsPerToken=1 natively.
|
||||
const env = createMockEnvironment();
|
||||
|
||||
const processor = NodeTruncationProcessor.create(env, {
|
||||
maxTokensPerNode: 10, // 10 chars limit
|
||||
});
|
||||
|
||||
const longText = 'A'.repeat(50); // 50 tokens
|
||||
|
||||
const prompt = createDummyNode(
|
||||
'ep1',
|
||||
'USER_PROMPT',
|
||||
50,
|
||||
{
|
||||
semanticParts: [{ type: 'text', text: longText }],
|
||||
},
|
||||
'prompt-id',
|
||||
) as UserPrompt;
|
||||
|
||||
const thought = createDummyNode(
|
||||
'ep1',
|
||||
'AGENT_THOUGHT',
|
||||
50,
|
||||
{
|
||||
text: longText,
|
||||
},
|
||||
'thought-id',
|
||||
) as AgentThought;
|
||||
|
||||
const yieldNode = createDummyNode(
|
||||
'ep1',
|
||||
'AGENT_YIELD',
|
||||
50,
|
||||
{
|
||||
text: longText,
|
||||
},
|
||||
'yield-id',
|
||||
) as AgentYield;
|
||||
|
||||
const targets = [prompt, thought, yieldNode];
|
||||
|
||||
const result = await processor.process(createMockProcessArgs(targets));
|
||||
|
||||
expect(result.length).toBe(3);
|
||||
|
||||
// 1. User Prompt
|
||||
const squashedPrompt = result[0] as UserPrompt;
|
||||
expect(squashedPrompt.id).not.toBe(prompt.id);
|
||||
expect(squashedPrompt.semanticParts[0].type).toBe('text');
|
||||
assert(squashedPrompt.semanticParts[0].type === 'text');
|
||||
expect(squashedPrompt.semanticParts[0].text).toContain('[... OMITTED');
|
||||
|
||||
// 2. Agent Thought
|
||||
const squashedThought = result[1] as AgentThought;
|
||||
expect(squashedThought.id).not.toBe(thought.id);
|
||||
expect(squashedThought.text).toContain('[... OMITTED');
|
||||
|
||||
// 3. Agent Yield
|
||||
const squashedYield = result[2] as AgentYield;
|
||||
expect(squashedYield.id).not.toBe(yieldNode.id);
|
||||
expect(squashedYield.text).toContain('[... OMITTED');
|
||||
});
|
||||
|
||||
it('should ignore nodes that are below maxTokensPerNode', async () => {
|
||||
const env = createMockEnvironment();
|
||||
|
||||
const processor = NodeTruncationProcessor.create(env, {
|
||||
maxTokensPerNode: 100, // 100 chars limit
|
||||
});
|
||||
|
||||
const shortText = 'Short text'; // 10 chars
|
||||
|
||||
const prompt = createDummyNode(
|
||||
'ep1',
|
||||
'USER_PROMPT',
|
||||
10,
|
||||
{
|
||||
semanticParts: [{ type: 'text', text: shortText }],
|
||||
},
|
||||
'prompt-id',
|
||||
) as UserPrompt;
|
||||
|
||||
const thought = createDummyNode(
|
||||
'ep1',
|
||||
'AGENT_THOUGHT',
|
||||
13,
|
||||
{
|
||||
text: 'Short thought', // 13 chars
|
||||
},
|
||||
'thought-id',
|
||||
) as AgentThought;
|
||||
|
||||
const targets = [prompt, thought];
|
||||
|
||||
const result = await processor.process(createMockProcessArgs(targets));
|
||||
|
||||
expect(result.length).toBe(2);
|
||||
|
||||
// 1. User Prompt (untouched)
|
||||
const squashedPrompt = result[0] as UserPrompt;
|
||||
expect(squashedPrompt.id).toBe(prompt.id);
|
||||
assert(squashedPrompt.semanticParts[0].type === 'text');
|
||||
expect(squashedPrompt.semanticParts[0].text).not.toContain('[... OMITTED');
|
||||
|
||||
// 2. Agent Thought (untouched)
|
||||
const untouchedThought = result[1] as AgentThought;
|
||||
expect(untouchedThought.id).toBe(thought.id);
|
||||
expect(untouchedThought.text).not.toContain('[... OMITTED');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,156 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { ContextProcessor, ProcessArgs } from '../pipeline.js';
|
||||
import type { ContextEnvironment } from '../sidecar/environment.js';
|
||||
import { truncateProportionally } from '../truncation.js';
|
||||
import type { ConcreteNode } from '../ir/types.js';
|
||||
|
||||
export interface NodeTruncationProcessorOptions {
|
||||
maxTokensPerNode: number;
|
||||
}
|
||||
|
||||
export class NodeTruncationProcessor implements ContextProcessor {
|
||||
static create(
|
||||
env: ContextEnvironment,
|
||||
options: NodeTruncationProcessorOptions,
|
||||
): NodeTruncationProcessor {
|
||||
return new NodeTruncationProcessor(env, options);
|
||||
}
|
||||
|
||||
static readonly schema = {
|
||||
type: 'object',
|
||||
properties: {
|
||||
maxTokensPerNode: {
|
||||
type: 'number',
|
||||
description:
|
||||
'The maximum tokens a node can have before being truncated.',
|
||||
},
|
||||
},
|
||||
required: ['maxTokensPerNode'],
|
||||
};
|
||||
|
||||
readonly componentType = 'processor';
|
||||
readonly id = 'NodeTruncationProcessor';
|
||||
readonly name = 'NodeTruncationProcessor';
|
||||
readonly options: NodeTruncationProcessorOptions;
|
||||
private env: ContextEnvironment;
|
||||
|
||||
constructor(
|
||||
env: ContextEnvironment,
|
||||
options: NodeTruncationProcessorOptions,
|
||||
) {
|
||||
this.env = env;
|
||||
this.options = options;
|
||||
}
|
||||
|
||||
private tryApplySquash(
|
||||
text: string,
|
||||
limitChars: number,
|
||||
): {
|
||||
text: string;
|
||||
newTokens: number;
|
||||
oldTokens: number;
|
||||
tokensSaved: number;
|
||||
} | null {
|
||||
const originalLength = text.length;
|
||||
if (originalLength <= limitChars) return null;
|
||||
|
||||
const newText = truncateProportionally(
|
||||
text,
|
||||
limitChars,
|
||||
`\n\n[... OMITTED ${originalLength - limitChars} chars ...]\n\n`,
|
||||
);
|
||||
|
||||
if (newText !== text) {
|
||||
// Using accurate TokenCalculator instead of simple math
|
||||
const newTokens =
|
||||
this.env.tokenCalculator.estimateTokensForString(newText);
|
||||
const oldTokens = this.env.tokenCalculator.estimateTokensForString(text);
|
||||
const tokensSaved = oldTokens - newTokens;
|
||||
|
||||
if (tokensSaved > 0) {
|
||||
return { text: newText, newTokens, oldTokens, tokensSaved };
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
async process({ targets }: ProcessArgs): Promise<readonly ConcreteNode[]> {
|
||||
if (targets.length === 0) {
|
||||
return targets;
|
||||
}
|
||||
|
||||
const { maxTokensPerNode } = this.options;
|
||||
const limitChars = this.env.tokenCalculator.tokensToChars(maxTokensPerNode);
|
||||
|
||||
const returnedNodes: ConcreteNode[] = [];
|
||||
|
||||
for (const node of targets) {
|
||||
switch (node.type) {
|
||||
case 'USER_PROMPT': {
|
||||
let modified = false;
|
||||
const newParts = [...node.semanticParts];
|
||||
|
||||
for (let j = 0; j < node.semanticParts.length; j++) {
|
||||
const part = node.semanticParts[j];
|
||||
if (part.type === 'text') {
|
||||
const squashResult = this.tryApplySquash(part.text, limitChars);
|
||||
if (squashResult) {
|
||||
newParts[j] = { type: 'text', text: squashResult.text };
|
||||
modified = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (modified) {
|
||||
returnedNodes.push({
|
||||
...node,
|
||||
id: this.env.idGenerator.generateId(),
|
||||
semanticParts: newParts,
|
||||
});
|
||||
} else {
|
||||
returnedNodes.push(node);
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
case 'AGENT_THOUGHT': {
|
||||
const squashResult = this.tryApplySquash(node.text, limitChars);
|
||||
if (squashResult) {
|
||||
returnedNodes.push({
|
||||
...node,
|
||||
id: this.env.idGenerator.generateId(),
|
||||
text: squashResult.text,
|
||||
});
|
||||
} else {
|
||||
returnedNodes.push(node);
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
case 'AGENT_YIELD': {
|
||||
const squashResult = this.tryApplySquash(node.text, limitChars);
|
||||
if (squashResult) {
|
||||
returnedNodes.push({
|
||||
...node,
|
||||
id: this.env.idGenerator.generateId(),
|
||||
text: squashResult.text,
|
||||
});
|
||||
} else {
|
||||
returnedNodes.push(node);
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
default:
|
||||
returnedNodes.push(node);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return returnedNodes;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,86 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { RollingSummaryProcessor } from './rollingSummaryProcessor.js';
|
||||
import {
|
||||
createMockProcessArgs,
|
||||
createMockEnvironment,
|
||||
createDummyNode,
|
||||
} from '../testing/contextTestUtils.js';
|
||||
|
||||
describe('RollingSummaryProcessor', () => {
|
||||
it('should initialize with correct default options', () => {
|
||||
const env = createMockEnvironment();
|
||||
const processor = RollingSummaryProcessor.create(env, {
|
||||
target: 'incremental',
|
||||
});
|
||||
expect(processor.id).toBe('RollingSummaryProcessor');
|
||||
});
|
||||
|
||||
it('should summarize older nodes when the deficit exceeds the threshold', async () => {
|
||||
// env.tokenCalculator uses charsPerToken=1 based on createMockEnvironment
|
||||
const env = createMockEnvironment();
|
||||
|
||||
// We want to free exactly 100 tokens.
|
||||
// We will supply nodes that cost 50 tokens each.
|
||||
const processor = RollingSummaryProcessor.create(env, {
|
||||
target: 'freeNTokens',
|
||||
freeTokensTarget: 100,
|
||||
});
|
||||
|
||||
const text50 = 'A'.repeat(50);
|
||||
const targets = [
|
||||
createDummyNode(
|
||||
'ep1',
|
||||
'USER_PROMPT',
|
||||
50,
|
||||
{ semanticParts: [{ type: 'text', text: text50 }] },
|
||||
'id1',
|
||||
),
|
||||
createDummyNode('ep1', 'AGENT_THOUGHT', 50, { text: text50 }, 'id2'),
|
||||
createDummyNode('ep1', 'AGENT_YIELD', 50, { text: text50 }, 'id3'),
|
||||
];
|
||||
|
||||
const result = await processor.process(createMockProcessArgs(targets));
|
||||
|
||||
// 3 nodes at 50 cost each.
|
||||
// The first node (id1) is the initial USER_PROMPT and is always skipped by RollingSummaryProcessor.
|
||||
// Node id2 adds 50 deficit. Node id3 adds 50 deficit. Total = 100 deficit, which hits the target break point.
|
||||
// Thus, id2 and id3 are summarized into a new ROLLING_SUMMARY node.
|
||||
expect(result.length).toBe(2);
|
||||
expect(result[0].type).toBe('USER_PROMPT');
|
||||
expect(result[1].type).toBe('ROLLING_SUMMARY');
|
||||
});
|
||||
|
||||
it('should preserve targets if deficit does not trigger summary', async () => {
|
||||
const env = createMockEnvironment();
|
||||
|
||||
// We want to free 100 tokens, but our nodes will only cost 10 tokens each.
|
||||
const processor = RollingSummaryProcessor.create(env, {
|
||||
target: 'freeNTokens',
|
||||
freeTokensTarget: 100,
|
||||
});
|
||||
|
||||
const text10 = 'A'.repeat(10);
|
||||
const targets = [
|
||||
createDummyNode(
|
||||
'ep1',
|
||||
'USER_PROMPT',
|
||||
10,
|
||||
{ semanticParts: [{ type: 'text', text: text10 }] },
|
||||
'id1',
|
||||
),
|
||||
createDummyNode('ep1', 'AGENT_THOUGHT', 10, { text: text10 }, 'id2'),
|
||||
];
|
||||
|
||||
const result = await processor.process(createMockProcessArgs(targets));
|
||||
|
||||
// Deficit accumulator reaches 10. This is < 100 limit, and total summarizable nodes < 2 anyway.
|
||||
expect(result.length).toBe(2);
|
||||
expect(result[0].type).toBe('USER_PROMPT');
|
||||
expect(result[1].type).toBe('AGENT_THOUGHT');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,125 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type {
|
||||
ContextProcessor,
|
||||
ProcessArgs,
|
||||
BackstopTargetOptions,
|
||||
} from '../pipeline.js';
|
||||
import type { ContextEnvironment } from '../sidecar/environment.js';
|
||||
import type { ConcreteNode, RollingSummary } from '../ir/types.js';
|
||||
import { SnapshotGenerator } from '../utils/snapshotGenerator.js';
|
||||
import { debugLogger } from '../../utils/debugLogger.js';
|
||||
|
||||
export interface RollingSummaryProcessorOptions extends BackstopTargetOptions {
|
||||
systemInstruction?: string;
|
||||
}
|
||||
|
||||
export class RollingSummaryProcessor implements ContextProcessor {
|
||||
static readonly schema = {
|
||||
type: 'object',
|
||||
properties: {
|
||||
target: { type: 'string', enum: ['incremental', 'freeNTokens', 'max'] },
|
||||
freeTokensTarget: { type: 'number' },
|
||||
systemInstruction: { type: 'string' },
|
||||
},
|
||||
};
|
||||
|
||||
static create(
|
||||
env: ContextEnvironment,
|
||||
options: RollingSummaryProcessorOptions,
|
||||
): RollingSummaryProcessor {
|
||||
return new RollingSummaryProcessor(env, options);
|
||||
}
|
||||
|
||||
readonly componentType = 'processor';
|
||||
readonly id = 'RollingSummaryProcessor';
|
||||
readonly name = 'RollingSummaryProcessor';
|
||||
readonly options: RollingSummaryProcessorOptions;
|
||||
private readonly env: ContextEnvironment;
|
||||
private readonly generator: SnapshotGenerator;
|
||||
|
||||
constructor(
|
||||
env: ContextEnvironment,
|
||||
options: RollingSummaryProcessorOptions,
|
||||
) {
|
||||
this.env = env;
|
||||
this.options = options;
|
||||
this.generator = new SnapshotGenerator(env);
|
||||
}
|
||||
|
||||
async process({ targets }: ProcessArgs): Promise<readonly ConcreteNode[]> {
|
||||
if (targets.length === 0) return targets;
|
||||
|
||||
const strategy = this.options.target ?? 'max';
|
||||
let targetTokensToRemove = 0;
|
||||
|
||||
if (strategy === 'incremental') {
|
||||
// A rolling summary should target a small chunk. For now, since state isn't passed,
|
||||
// we'll default to a fixed threshold, like 10000 tokens, to avoid eating the whole history.
|
||||
// Ideally, the orchestrator should pass `tokensToRemove` explicitly.
|
||||
targetTokensToRemove = 10000;
|
||||
} else if (strategy === 'freeNTokens') {
|
||||
targetTokensToRemove = this.options.freeTokensTarget ?? Infinity;
|
||||
} else if (strategy === 'max') {
|
||||
targetTokensToRemove = Infinity;
|
||||
}
|
||||
|
||||
if (targetTokensToRemove <= 0) return targets;
|
||||
|
||||
let deficitAccumulator = 0;
|
||||
const nodesToSummarize: ConcreteNode[] = [];
|
||||
|
||||
// Scan oldest to newest to find the oldest block that exceeds the token requirement
|
||||
for (const node of targets) {
|
||||
if (node.id === targets[0].id && node.type === 'USER_PROMPT') {
|
||||
// Keep system prompt if it's the very first node
|
||||
continue;
|
||||
}
|
||||
|
||||
nodesToSummarize.push(node);
|
||||
deficitAccumulator += this.env.tokenCalculator.getTokenCost(node);
|
||||
|
||||
if (deficitAccumulator >= targetTokensToRemove) break;
|
||||
}
|
||||
|
||||
if (nodesToSummarize.length < 2) return targets; // Not enough context to summarize
|
||||
|
||||
try {
|
||||
// Synthesize the rolling summary synchronously
|
||||
const snapshotText = await this.generator.synthesizeSnapshot(
|
||||
nodesToSummarize,
|
||||
this.options.systemInstruction,
|
||||
);
|
||||
const newId = this.env.idGenerator.generateId();
|
||||
|
||||
const summaryNode: RollingSummary = {
|
||||
id: newId,
|
||||
logicalParentId: newId,
|
||||
type: 'ROLLING_SUMMARY',
|
||||
timestamp: Date.now(),
|
||||
text: snapshotText,
|
||||
};
|
||||
|
||||
const consumedIds = nodesToSummarize.map((n) => n.id);
|
||||
const returnedNodes = targets.filter((t) => !consumedIds.includes(t.id));
|
||||
const firstRemovedIdx = targets.findIndex((t) =>
|
||||
consumedIds.includes(t.id),
|
||||
);
|
||||
|
||||
if (firstRemovedIdx !== -1) {
|
||||
const idx = Math.max(0, firstRemovedIdx);
|
||||
returnedNodes.splice(idx, 0, summaryNode);
|
||||
} else {
|
||||
returnedNodes.unshift(summaryNode);
|
||||
}
|
||||
|
||||
return returnedNodes;
|
||||
} catch (e) {
|
||||
debugLogger.error('RollingSummaryProcessor failed sync backstop', e);
|
||||
return targets;
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,115 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { StateSnapshotProcessor } from './stateSnapshotProcessor.js';
|
||||
import {
|
||||
createMockEnvironment,
|
||||
createDummyNode,
|
||||
createMockProcessArgs,
|
||||
} from '../testing/contextTestUtils.js';
|
||||
import type { InboxSnapshotImpl } from '../sidecar/inbox.js';
|
||||
|
||||
describe('StateSnapshotProcessor', () => {
|
||||
it('should ignore if budget is satisfied', async () => {
|
||||
const env = createMockEnvironment();
|
||||
const processor = StateSnapshotProcessor.create(env, {
|
||||
target: 'incremental',
|
||||
});
|
||||
const targets = [createDummyNode('ep1', 'USER_PROMPT')];
|
||||
const result = await processor.process(createMockProcessArgs(targets));
|
||||
expect(result).toBe(targets); // Strict equality
|
||||
});
|
||||
|
||||
it('should apply a valid snapshot from the Inbox (Fast Path)', async () => {
|
||||
const env = createMockEnvironment();
|
||||
const processor = StateSnapshotProcessor.create(env, {
|
||||
target: 'incremental',
|
||||
});
|
||||
|
||||
const nodeA = createDummyNode('ep1', 'USER_PROMPT', 50, {}, 'node-A');
|
||||
const nodeB = createDummyNode('ep1', 'AGENT_THOUGHT', 60, {}, 'node-B');
|
||||
const nodeC = createDummyNode('ep2', 'USER_PROMPT', 50, {}, 'node-C');
|
||||
|
||||
const targets = [nodeA, nodeB, nodeC];
|
||||
|
||||
// The background worker created a snapshot of A and B
|
||||
const messages = [
|
||||
{
|
||||
id: 'msg-1',
|
||||
topic: 'PROPOSED_SNAPSHOT',
|
||||
timestamp: Date.now(),
|
||||
payload: {
|
||||
consumedIds: ['node-A', 'node-B'],
|
||||
newText: '<compressed A and B>',
|
||||
type: 'point-in-time',
|
||||
},
|
||||
},
|
||||
];
|
||||
|
||||
const processArgs = createMockProcessArgs(targets, [], messages);
|
||||
const result = await processor.process(processArgs);
|
||||
|
||||
// Should remove A and B, insert Snapshot, keep C
|
||||
expect(result.length).toBe(2);
|
||||
expect(result[0].type).toBe('SNAPSHOT');
|
||||
expect(result[1].id).toBe('node-C');
|
||||
|
||||
// Should consume the message
|
||||
expect(
|
||||
(processArgs.inbox as InboxSnapshotImpl).getConsumedIds().has('msg-1'),
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it('should reject a snapshot if the nodes were modified/deleted (Cache Invalidated)', async () => {
|
||||
const env = createMockEnvironment();
|
||||
const processor = StateSnapshotProcessor.create(env, {
|
||||
target: 'incremental',
|
||||
});
|
||||
// Make deficit 0 so we don't fall through to the sync backstop and fail the test that way
|
||||
|
||||
// node-A is MISSING (user deleted it)
|
||||
const nodeB = createDummyNode('ep1', 'AGENT_THOUGHT', 60, {}, 'node-B');
|
||||
const targets = [nodeB];
|
||||
|
||||
const messages = [
|
||||
{
|
||||
id: 'msg-1',
|
||||
topic: 'PROPOSED_SNAPSHOT',
|
||||
timestamp: Date.now(),
|
||||
payload: {
|
||||
consumedIds: ['node-A', 'node-B'],
|
||||
newText: '<compressed A and B>',
|
||||
},
|
||||
},
|
||||
];
|
||||
|
||||
const processArgs = createMockProcessArgs(targets, [], messages);
|
||||
const result = await processor.process(processArgs);
|
||||
|
||||
// Because deficit is 0, and Inbox was rejected, nothing should change
|
||||
expect(result.length).toBe(1);
|
||||
expect(result[0].id).toBe('node-B');
|
||||
expect(
|
||||
(processArgs.inbox as InboxSnapshotImpl).getConsumedIds().has('msg-1'),
|
||||
).toBe(false);
|
||||
});
|
||||
|
||||
it('should fall back to sync backstop if inbox is empty', async () => {
|
||||
const env = createMockEnvironment();
|
||||
const processor = StateSnapshotProcessor.create(env, { target: 'max' }); // Summarize all
|
||||
|
||||
const nodeA = createDummyNode('ep1', 'USER_PROMPT', 50, {}, 'node-A');
|
||||
const nodeB = createDummyNode('ep1', 'AGENT_THOUGHT', 60, {}, 'node-B');
|
||||
const nodeC = createDummyNode('ep2', 'USER_PROMPT', 50, {}, 'node-C');
|
||||
const targets = [nodeA, nodeB, nodeC];
|
||||
const result = await processor.process(createMockProcessArgs(targets));
|
||||
|
||||
// Should synthesize a new snapshot synchronously
|
||||
expect(env.llmClient.generateContent).toHaveBeenCalled();
|
||||
expect(result.length).toBe(2); // nodeA is skipped as "system prompt", snapshot + nodeA
|
||||
expect(result[1].type).toBe('SNAPSHOT');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,187 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type {
|
||||
ContextProcessor,
|
||||
ProcessArgs,
|
||||
BackstopTargetOptions,
|
||||
} from '../pipeline.js';
|
||||
import type { ContextEnvironment } from '../sidecar/environment.js';
|
||||
import type { ConcreteNode, Snapshot } from '../ir/types.js';
|
||||
import { SnapshotGenerator } from '../utils/snapshotGenerator.js';
|
||||
import { debugLogger } from '../../utils/debugLogger.js';
|
||||
|
||||
export interface StateSnapshotProcessorOptions extends BackstopTargetOptions {
|
||||
model?: string;
|
||||
systemInstruction?: string;
|
||||
}
|
||||
|
||||
export class StateSnapshotProcessor implements ContextProcessor {
|
||||
static readonly schema = {
|
||||
type: 'object',
|
||||
properties: {
|
||||
target: { type: 'string', enum: ['incremental', 'freeNTokens', 'max'] },
|
||||
freeTokensTarget: { type: 'number' },
|
||||
model: { type: 'string' },
|
||||
systemInstruction: { type: 'string' },
|
||||
},
|
||||
};
|
||||
|
||||
static create(
|
||||
env: ContextEnvironment,
|
||||
options: StateSnapshotProcessorOptions,
|
||||
): StateSnapshotProcessor {
|
||||
return new StateSnapshotProcessor(env, options);
|
||||
}
|
||||
|
||||
readonly componentType = 'processor';
|
||||
readonly id = 'StateSnapshotProcessor';
|
||||
readonly name = 'StateSnapshotProcessor';
|
||||
readonly options: StateSnapshotProcessorOptions;
|
||||
private readonly env: ContextEnvironment;
|
||||
private readonly generator: SnapshotGenerator;
|
||||
|
||||
constructor(env: ContextEnvironment, options: StateSnapshotProcessorOptions) {
|
||||
this.env = env;
|
||||
this.options = options;
|
||||
this.generator = new SnapshotGenerator(env);
|
||||
}
|
||||
|
||||
// --- ContextProcessor Interface (Sync Backstop / Cache Application) ---
|
||||
async process({
|
||||
targets,
|
||||
inbox,
|
||||
}: ProcessArgs): Promise<readonly ConcreteNode[]> {
|
||||
if (targets.length === 0) {
|
||||
return targets;
|
||||
}
|
||||
|
||||
// Determine what mode we are looking for: 'incremental' -> 'point-in-time', 'max' -> 'accumulate'
|
||||
const strategy = this.options.target ?? 'max';
|
||||
const expectedType =
|
||||
strategy === 'incremental' ? 'point-in-time' : 'accumulate';
|
||||
|
||||
// 1. Check Inbox for a completed Snapshot (The Fast Path)
|
||||
const proposedSnapshots = inbox.getMessages<{
|
||||
newText: string;
|
||||
consumedIds: string[];
|
||||
type: string;
|
||||
}>('PROPOSED_SNAPSHOT');
|
||||
|
||||
if (proposedSnapshots.length > 0) {
|
||||
// Filter for the snapshot type that matches our processor mode
|
||||
const matchingSnapshots = proposedSnapshots.filter(
|
||||
(s) => s.payload.type === expectedType,
|
||||
);
|
||||
|
||||
// Sort by newest timestamp first (we want the most accumulated snapshot)
|
||||
const sorted = [...matchingSnapshots].sort(
|
||||
(a, b) => b.timestamp - a.timestamp,
|
||||
);
|
||||
|
||||
for (const proposed of sorted) {
|
||||
const { consumedIds, newText } = proposed.payload;
|
||||
|
||||
// Verify all consumed IDs still exist sequentially in targets
|
||||
const targetIds = new Set(targets.map((t) => t.id));
|
||||
const isValid = consumedIds.every((id) => targetIds.has(id));
|
||||
|
||||
if (isValid) {
|
||||
// If valid, apply it!
|
||||
const newId = this.env.idGenerator.generateId();
|
||||
|
||||
const snapshotNode: Snapshot = {
|
||||
id: newId,
|
||||
logicalParentId: newId,
|
||||
type: 'SNAPSHOT',
|
||||
timestamp: Date.now(),
|
||||
text: newText,
|
||||
};
|
||||
|
||||
// Remove the consumed nodes and insert the snapshot at the earliest index
|
||||
const returnedNodes = targets.filter(
|
||||
(t) => !consumedIds.includes(t.id),
|
||||
);
|
||||
const firstRemovedIdx = targets.findIndex((t) =>
|
||||
consumedIds.includes(t.id),
|
||||
);
|
||||
|
||||
if (firstRemovedIdx !== -1) {
|
||||
const idx = Math.max(0, firstRemovedIdx);
|
||||
returnedNodes.splice(idx, 0, snapshotNode);
|
||||
} else {
|
||||
returnedNodes.unshift(snapshotNode);
|
||||
}
|
||||
|
||||
inbox.consume(proposed.id);
|
||||
return returnedNodes;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 2. The Synchronous Backstop (The Slow Path)
|
||||
let targetTokensToRemove = 0;
|
||||
|
||||
if (strategy === 'incremental') {
|
||||
targetTokensToRemove = Infinity; // incremental implies removing as much as possible if no state is passed
|
||||
} else if (strategy === 'freeNTokens') {
|
||||
targetTokensToRemove = this.options.freeTokensTarget ?? Infinity;
|
||||
} else if (strategy === 'max') {
|
||||
targetTokensToRemove = Infinity;
|
||||
}
|
||||
|
||||
let deficitAccumulator = 0;
|
||||
const nodesToSummarize: ConcreteNode[] = [];
|
||||
|
||||
// Scan oldest to newest
|
||||
for (const node of targets) {
|
||||
if (node.id === targets[0].id && node.type === 'USER_PROMPT') {
|
||||
// Keep system prompt if it's the very first node
|
||||
// In a real system, system prompt is protected, but we double check
|
||||
continue;
|
||||
}
|
||||
|
||||
nodesToSummarize.push(node);
|
||||
deficitAccumulator += this.env.tokenCalculator.getTokenCost(node);
|
||||
|
||||
if (deficitAccumulator >= targetTokensToRemove) break;
|
||||
}
|
||||
|
||||
if (nodesToSummarize.length < 2) return targets; // Not enough context
|
||||
|
||||
try {
|
||||
const snapshotText = await this.generator.synthesizeSnapshot(
|
||||
nodesToSummarize,
|
||||
this.options.systemInstruction,
|
||||
);
|
||||
const newId = this.env.idGenerator.generateId();
|
||||
const snapshotNode: Snapshot = {
|
||||
id: newId,
|
||||
logicalParentId: newId,
|
||||
type: 'SNAPSHOT',
|
||||
timestamp: Date.now(),
|
||||
text: snapshotText,
|
||||
};
|
||||
|
||||
const consumedIds = nodesToSummarize.map((n) => n.id);
|
||||
const returnedNodes = targets.filter((t) => !consumedIds.includes(t.id));
|
||||
const firstRemovedIdx = targets.findIndex((t) =>
|
||||
consumedIds.includes(t.id),
|
||||
);
|
||||
|
||||
if (firstRemovedIdx !== -1) {
|
||||
const idx = Math.max(0, firstRemovedIdx);
|
||||
returnedNodes.splice(idx, 0, snapshotNode);
|
||||
} else {
|
||||
returnedNodes.unshift(snapshotNode);
|
||||
}
|
||||
|
||||
return returnedNodes;
|
||||
} catch (e) {
|
||||
debugLogger.error('StateSnapshotProcessor failed sync backstop', e);
|
||||
return targets;
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,112 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import { describe, it, expect, vi } from 'vitest';
|
||||
import { StateSnapshotWorker } from './stateSnapshotWorker.js';
|
||||
import {
|
||||
createMockEnvironment,
|
||||
createDummyNode,
|
||||
} from '../testing/contextTestUtils.js';
|
||||
import { InboxSnapshotImpl } from '../sidecar/inbox.js';
|
||||
|
||||
describe('StateSnapshotWorker', () => {
|
||||
it('should generate a snapshot and publish it to the inbox', async () => {
|
||||
const env = createMockEnvironment();
|
||||
// Spy on the publish method
|
||||
const publishSpy = vi.spyOn(env.inbox, 'publish');
|
||||
|
||||
const worker = StateSnapshotWorker.create(env, { type: 'point-in-time' });
|
||||
|
||||
const nodeA = createDummyNode('ep1', 'USER_PROMPT', 50, {}, 'node-A');
|
||||
const nodeB = createDummyNode('ep1', 'AGENT_THOUGHT', 60, {}, 'node-B');
|
||||
|
||||
const targets = [nodeA, nodeB];
|
||||
const inbox = new InboxSnapshotImpl([]);
|
||||
|
||||
await worker.execute({ targets, inbox });
|
||||
|
||||
// Ensure generateContent was called
|
||||
expect(env.llmClient.generateContent).toHaveBeenCalled();
|
||||
|
||||
// Verify it published to the inbox
|
||||
expect(publishSpy).toHaveBeenCalledWith(
|
||||
'PROPOSED_SNAPSHOT',
|
||||
expect.objectContaining({
|
||||
newText: 'Mock LLM summary response',
|
||||
consumedIds: ['node-A', 'node-B'],
|
||||
type: 'point-in-time',
|
||||
}),
|
||||
env.idGenerator,
|
||||
);
|
||||
});
|
||||
|
||||
it('should pull previous accumulate snapshot from inbox and append new targets', async () => {
|
||||
const env = createMockEnvironment();
|
||||
const publishSpy = vi.spyOn(env.inbox, 'publish');
|
||||
const drainSpy = vi.spyOn(env.inbox, 'drainConsumed');
|
||||
|
||||
const worker = StateSnapshotWorker.create(env, { type: 'accumulate' });
|
||||
|
||||
const nodeC = createDummyNode('ep2', 'USER_PROMPT', 50, {}, 'node-C');
|
||||
const targets = [nodeC];
|
||||
|
||||
// Simulate an existing accumulate draft in the inbox
|
||||
const inbox = new InboxSnapshotImpl([
|
||||
{
|
||||
id: 'draft-1',
|
||||
topic: 'PROPOSED_SNAPSHOT',
|
||||
timestamp: Date.now() - 1000,
|
||||
payload: {
|
||||
consumedIds: ['node-A', 'node-B'],
|
||||
newText: '<old snapshot>',
|
||||
type: 'accumulate',
|
||||
},
|
||||
},
|
||||
]);
|
||||
|
||||
await worker.execute({ targets, inbox });
|
||||
|
||||
// The old draft should be consumed
|
||||
expect(inbox.getConsumedIds().has('draft-1')).toBe(true);
|
||||
expect(drainSpy).toHaveBeenCalledWith(expect.any(Set));
|
||||
|
||||
// The new publish should contain ALL consumed IDs (old + new)
|
||||
expect(publishSpy).toHaveBeenCalledWith(
|
||||
'PROPOSED_SNAPSHOT',
|
||||
expect.objectContaining({
|
||||
newText: 'Mock LLM summary response',
|
||||
consumedIds: ['node-A', 'node-B', 'node-C'], // Aggregated!
|
||||
type: 'accumulate',
|
||||
}),
|
||||
env.idGenerator,
|
||||
);
|
||||
|
||||
// Verify the LLM was called with the old snapshot prepended
|
||||
expect(env.llmClient.generateContent).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
contents: expect.arrayContaining([
|
||||
expect.objectContaining({
|
||||
parts: expect.arrayContaining([
|
||||
expect.objectContaining({
|
||||
text: expect.stringContaining('<old snapshot>'),
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it('should ignore empty targets', async () => {
|
||||
const env = createMockEnvironment();
|
||||
const publishSpy = vi.spyOn(env.inbox, 'publish');
|
||||
const worker = StateSnapshotWorker.create(env, { type: 'accumulate' });
|
||||
|
||||
await worker.execute({ targets: [], inbox: new InboxSnapshotImpl([]) });
|
||||
|
||||
expect(env.llmClient.generateContent).not.toHaveBeenCalled();
|
||||
expect(publishSpy).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,127 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { ContextWorker, InboxSnapshot } from '../pipeline.js';
|
||||
import type { ContextEnvironment } from '../sidecar/environment.js';
|
||||
import type { ConcreteNode } from '../ir/types.js';
|
||||
import { SnapshotGenerator } from '../utils/snapshotGenerator.js';
|
||||
import { debugLogger } from '../../utils/debugLogger.js';
|
||||
|
||||
export interface StateSnapshotWorkerOptions {
|
||||
type?: 'accumulate' | 'point-in-time';
|
||||
systemInstruction?: string;
|
||||
}
|
||||
|
||||
export class StateSnapshotWorker implements ContextWorker {
|
||||
static readonly schema = {
|
||||
type: 'object',
|
||||
properties: {
|
||||
type: { type: 'string', enum: ['accumulate', 'point-in-time'] },
|
||||
systemInstruction: { type: 'string' },
|
||||
},
|
||||
};
|
||||
|
||||
static create(
|
||||
env: ContextEnvironment,
|
||||
options: StateSnapshotWorkerOptions,
|
||||
): StateSnapshotWorker {
|
||||
return new StateSnapshotWorker(env, options);
|
||||
}
|
||||
|
||||
readonly componentType = 'worker';
|
||||
readonly id = 'StateSnapshotWorker';
|
||||
readonly name = 'StateSnapshotWorker';
|
||||
readonly options: StateSnapshotWorkerOptions;
|
||||
private readonly env: ContextEnvironment;
|
||||
private readonly generator: SnapshotGenerator;
|
||||
|
||||
// Triggers when nodes exceed retained threshold (via retained_exceeded in Orchestrator)
|
||||
readonly triggers = {
|
||||
onNodesAgedOut: true,
|
||||
};
|
||||
|
||||
constructor(env: ContextEnvironment, options: StateSnapshotWorkerOptions) {
|
||||
this.env = env;
|
||||
this.options = options;
|
||||
this.generator = new SnapshotGenerator(env);
|
||||
}
|
||||
|
||||
async execute({
|
||||
targets,
|
||||
inbox,
|
||||
}: {
|
||||
targets: readonly ConcreteNode[];
|
||||
inbox: InboxSnapshot;
|
||||
}): Promise<void> {
|
||||
if (targets.length === 0) return;
|
||||
|
||||
try {
|
||||
let nodesToSummarize = [...targets];
|
||||
let previousConsumedIds: string[] = [];
|
||||
const workerType = this.options.type ?? 'point-in-time';
|
||||
|
||||
if (workerType === 'accumulate') {
|
||||
// Look for the most recent unconsumed accumulate snapshot in the inbox
|
||||
const proposedSnapshots = inbox.getMessages<{
|
||||
newText: string;
|
||||
consumedIds: string[];
|
||||
type: string;
|
||||
}>('PROPOSED_SNAPSHOT');
|
||||
const accumulateSnapshots = proposedSnapshots.filter(
|
||||
(s) => s.payload.type === 'accumulate',
|
||||
);
|
||||
|
||||
if (accumulateSnapshots.length > 0) {
|
||||
// Sort to find the most recent
|
||||
const latest = [...accumulateSnapshots].sort(
|
||||
(a, b) => b.timestamp - a.timestamp,
|
||||
)[0];
|
||||
|
||||
// Consume the old draft so the inbox doesn't fill up with stale drafts
|
||||
inbox.consume(latest.id);
|
||||
// And we must persist its consumption back to the live inbox immediately,
|
||||
// because we are effectively "taking" it from the shelf to modify.
|
||||
this.env.inbox.drainConsumed(new Set([latest.id]));
|
||||
|
||||
previousConsumedIds = latest.payload.consumedIds;
|
||||
|
||||
// Prepend a synthetic node representing the previous rolling state
|
||||
const previousStateNode: ConcreteNode = {
|
||||
id: this.env.idGenerator.generateId(),
|
||||
logicalParentId: '',
|
||||
type: 'SNAPSHOT',
|
||||
timestamp: latest.timestamp,
|
||||
text: latest.payload.newText,
|
||||
};
|
||||
|
||||
nodesToSummarize = [previousStateNode, ...targets];
|
||||
}
|
||||
}
|
||||
|
||||
const snapshotText = await this.generator.synthesizeSnapshot(
|
||||
nodesToSummarize,
|
||||
this.options.systemInstruction,
|
||||
);
|
||||
|
||||
const newConsumedIds = [
|
||||
...previousConsumedIds,
|
||||
...targets.map((t) => t.id),
|
||||
];
|
||||
|
||||
// In V2, workers communicate their work to the inbox, and the processor picks it up.
|
||||
this.env.inbox.publish(
|
||||
'PROPOSED_SNAPSHOT',
|
||||
{
|
||||
newText: snapshotText,
|
||||
consumedIds: newConsumedIds,
|
||||
type: workerType,
|
||||
},
|
||||
this.env.idGenerator,
|
||||
);
|
||||
} catch (e) {
|
||||
debugLogger.error('StateSnapshotWorker failed to generate snapshot', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,68 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { ToolMaskingProcessor } from './toolMaskingProcessor.js';
|
||||
import {
|
||||
createMockProcessArgs,
|
||||
createMockEnvironment,
|
||||
createDummyToolNode,
|
||||
} from '../testing/contextTestUtils.js';
|
||||
import type { ToolExecution } from '../ir/types.js';
|
||||
|
||||
describe('ToolMaskingProcessor', () => {
|
||||
it('should write large strings to disk and replace them with a masked pointer', async () => {
|
||||
const env = createMockEnvironment();
|
||||
// env uses charsPerToken=1 natively.
|
||||
// original string lengths > stringLengthThresholdTokens (which is 10) will be masked
|
||||
|
||||
const processor = ToolMaskingProcessor.create(env, {
|
||||
stringLengthThresholdTokens: 10,
|
||||
});
|
||||
|
||||
const longString = 'A'.repeat(500); // 500 chars
|
||||
|
||||
const toolStep = createDummyToolNode('ep1', 50, 500, {
|
||||
observation: {
|
||||
result: longString,
|
||||
metadata: 'short', // 5 chars, will not be masked
|
||||
},
|
||||
});
|
||||
|
||||
const result = await processor.process(createMockProcessArgs([toolStep]));
|
||||
|
||||
expect(result.length).toBe(1);
|
||||
const masked = result[0] as ToolExecution;
|
||||
|
||||
// It should have generated a new ID because it modified it
|
||||
expect(masked.id).not.toBe(toolStep.id);
|
||||
|
||||
// It should have masked the observation
|
||||
const obs = masked.observation as { result: string; metadata: string };
|
||||
expect(obs.result).toContain('<tool_output_masked>');
|
||||
expect(obs.metadata).toBe('short'); // Untouched
|
||||
});
|
||||
|
||||
it('should skip unmaskable tools', async () => {
|
||||
const env = createMockEnvironment();
|
||||
|
||||
const processor = ToolMaskingProcessor.create(env, {
|
||||
stringLengthThresholdTokens: 10,
|
||||
});
|
||||
|
||||
const toolStep = createDummyToolNode('ep1', 10, 10, {
|
||||
toolName: 'activate_skill',
|
||||
observation: {
|
||||
result:
|
||||
'this is a really long string that normally would get masked but wont because of the tool name',
|
||||
},
|
||||
});
|
||||
|
||||
const result = await processor.process(createMockProcessArgs([toolStep]));
|
||||
|
||||
// Returned the exact same object reference
|
||||
expect(result[0]).toBe(toolStep);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,284 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { ContextProcessor, ProcessArgs } from '../pipeline.js';
|
||||
import type { ConcreteNode, ToolExecution } from '../ir/types.js';
|
||||
import type { ContextEnvironment } from '../sidecar/environment.js';
|
||||
import { sanitizeFilenamePart } from '../../utils/fileUtils.js';
|
||||
import {
|
||||
ACTIVATE_SKILL_TOOL_NAME,
|
||||
MEMORY_TOOL_NAME,
|
||||
ASK_USER_TOOL_NAME,
|
||||
ENTER_PLAN_MODE_TOOL_NAME,
|
||||
EXIT_PLAN_MODE_TOOL_NAME,
|
||||
} from '../../tools/tool-names.js';
|
||||
import type { Part } from '@google/genai';
|
||||
|
||||
const UNMASKABLE_TOOLS = new Set([
|
||||
ACTIVATE_SKILL_TOOL_NAME,
|
||||
MEMORY_TOOL_NAME,
|
||||
ASK_USER_TOOL_NAME,
|
||||
ENTER_PLAN_MODE_TOOL_NAME,
|
||||
EXIT_PLAN_MODE_TOOL_NAME,
|
||||
]);
|
||||
|
||||
export interface ToolMaskingProcessorOptions {
|
||||
stringLengthThresholdTokens: number;
|
||||
}
|
||||
|
||||
type MaskableValue =
|
||||
| string
|
||||
| number
|
||||
| boolean
|
||||
| null
|
||||
| MaskableValue[]
|
||||
| { [key: string]: MaskableValue };
|
||||
|
||||
function isMaskableValue(val: unknown): val is MaskableValue {
|
||||
if (
|
||||
val === null ||
|
||||
typeof val === 'string' ||
|
||||
typeof val === 'number' ||
|
||||
typeof val === 'boolean'
|
||||
) {
|
||||
return true;
|
||||
}
|
||||
if (Array.isArray(val)) {
|
||||
return val.every(isMaskableValue);
|
||||
}
|
||||
if (typeof val === 'object') {
|
||||
return Object.values(val).every(isMaskableValue);
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
function isMaskableRecord(val: unknown): val is Record<string, MaskableValue> {
|
||||
return (
|
||||
typeof val === 'object' &&
|
||||
val !== null &&
|
||||
!Array.isArray(val) &&
|
||||
isMaskableValue(val)
|
||||
);
|
||||
}
|
||||
|
||||
export class ToolMaskingProcessor implements ContextProcessor {
|
||||
static create(
|
||||
env: ContextEnvironment,
|
||||
options: ToolMaskingProcessorOptions,
|
||||
): ToolMaskingProcessor {
|
||||
return new ToolMaskingProcessor(env, options);
|
||||
}
|
||||
|
||||
static readonly schema = {
|
||||
type: 'object',
|
||||
properties: {
|
||||
stringLengthThresholdTokens: {
|
||||
type: 'number',
|
||||
description:
|
||||
'The token threshold above which tool intents/observations are masked.',
|
||||
},
|
||||
},
|
||||
required: ['stringLengthThresholdTokens'],
|
||||
};
|
||||
|
||||
readonly componentType = 'processor';
|
||||
readonly id = 'ToolMaskingProcessor';
|
||||
readonly name = 'ToolMaskingProcessor';
|
||||
readonly options: ToolMaskingProcessorOptions;
|
||||
private env: ContextEnvironment;
|
||||
|
||||
constructor(env: ContextEnvironment, options: ToolMaskingProcessorOptions) {
|
||||
this.env = env;
|
||||
this.options = options;
|
||||
}
|
||||
|
||||
private isAlreadyMasked(text: string): boolean {
|
||||
return text.includes('<tool_output_masked>');
|
||||
}
|
||||
|
||||
async process({ targets }: ProcessArgs): Promise<readonly ConcreteNode[]> {
|
||||
const maskingConfig = this.options;
|
||||
if (!maskingConfig) return targets;
|
||||
if (targets.length === 0) return targets;
|
||||
|
||||
const limitChars = this.env.tokenCalculator.tokensToChars(
|
||||
maskingConfig.stringLengthThresholdTokens,
|
||||
);
|
||||
|
||||
let toolOutputsDir = this.env.fileSystem.join(
|
||||
this.env.projectTempDir,
|
||||
'tool-outputs',
|
||||
);
|
||||
const sessionId = this.env.sessionId;
|
||||
if (sessionId) {
|
||||
toolOutputsDir = this.env.fileSystem.join(
|
||||
toolOutputsDir,
|
||||
`session-${sanitizeFilenamePart(sessionId)}`,
|
||||
);
|
||||
}
|
||||
|
||||
let directoryCreated = false;
|
||||
|
||||
const handleMasking = async (
|
||||
content: string,
|
||||
toolName: string,
|
||||
callId: string,
|
||||
nodeType: string,
|
||||
): Promise<string> => {
|
||||
if (!directoryCreated) {
|
||||
await this.env.fileSystem.mkdir(toolOutputsDir, { recursive: true });
|
||||
directoryCreated = true;
|
||||
}
|
||||
|
||||
const fileName = `${sanitizeFilenamePart(toolName).toLowerCase()}_${sanitizeFilenamePart(callId).toLowerCase()}_${nodeType}_${this.env.idGenerator.generateId()}.txt`;
|
||||
const filePath = this.env.fileSystem.join(toolOutputsDir, fileName);
|
||||
|
||||
await this.env.fileSystem.writeFile(filePath, content);
|
||||
|
||||
const fileSizeMB = (
|
||||
Buffer.byteLength(content, 'utf8') /
|
||||
1024 /
|
||||
1024
|
||||
).toFixed(2);
|
||||
const totalLines = content.split('\n').length;
|
||||
return `<tool_output_masked>\n[Tool ${nodeType} string (${fileSizeMB}MB, ${totalLines} lines) masked to preserve context window. Full string saved to: ${filePath}]\n</tool_output_masked>`;
|
||||
};
|
||||
|
||||
const returnedNodes: ConcreteNode[] = [];
|
||||
|
||||
for (const node of targets) {
|
||||
switch (node.type) {
|
||||
case 'TOOL_EXECUTION': {
|
||||
const toolName = node.toolName;
|
||||
if (toolName && UNMASKABLE_TOOLS.has(toolName)) {
|
||||
returnedNodes.push(node);
|
||||
break;
|
||||
}
|
||||
|
||||
const callId = node.id || Date.now().toString();
|
||||
|
||||
const maskAsync = async (
|
||||
obj: MaskableValue,
|
||||
nodeType: string,
|
||||
): Promise<{ masked: MaskableValue; changed: boolean }> => {
|
||||
if (typeof obj === 'string') {
|
||||
if (obj.length > limitChars && !this.isAlreadyMasked(obj)) {
|
||||
const newString = await handleMasking(
|
||||
obj,
|
||||
toolName || 'unknown',
|
||||
callId,
|
||||
nodeType,
|
||||
);
|
||||
return { masked: newString, changed: true };
|
||||
}
|
||||
return { masked: obj, changed: false };
|
||||
}
|
||||
if (Array.isArray(obj)) {
|
||||
let changed = false;
|
||||
const masked: MaskableValue[] = [];
|
||||
for (const item of obj) {
|
||||
const res = await maskAsync(item, nodeType);
|
||||
if (res.changed) changed = true;
|
||||
masked.push(res.masked);
|
||||
}
|
||||
return { masked, changed };
|
||||
}
|
||||
if (typeof obj === 'object' && obj !== null) {
|
||||
let changed = false;
|
||||
const masked: Record<string, MaskableValue> = {};
|
||||
for (const [key, value] of Object.entries(obj)) {
|
||||
const res = await maskAsync(value, nodeType);
|
||||
if (res.changed) changed = true;
|
||||
masked[key] = res.masked;
|
||||
}
|
||||
return { masked, changed };
|
||||
}
|
||||
return { masked: obj, changed: false };
|
||||
};
|
||||
|
||||
const rawIntent = node.intent;
|
||||
const rawObs = node.observation;
|
||||
|
||||
if (!isMaskableRecord(rawIntent) || !isMaskableValue(rawObs)) {
|
||||
returnedNodes.push(node);
|
||||
break;
|
||||
}
|
||||
|
||||
const intentRes = await maskAsync(rawIntent, 'intent');
|
||||
const obsRes = await maskAsync(rawObs, 'observation');
|
||||
|
||||
if (intentRes.changed || obsRes.changed) {
|
||||
const maskedIntent = isMaskableRecord(intentRes.masked)
|
||||
? (intentRes.masked as Record<string, unknown>)
|
||||
: undefined;
|
||||
// Handle observation explicitly as string vs object
|
||||
const maskedObs =
|
||||
typeof obsRes.masked === 'string'
|
||||
? ({ message: obsRes.masked } as Record<string, unknown>)
|
||||
: isMaskableRecord(obsRes.masked)
|
||||
? (obsRes.masked as Record<string, unknown>)
|
||||
: undefined;
|
||||
|
||||
const newIntentTokens =
|
||||
this.env.tokenCalculator.estimateTokensForParts([
|
||||
{
|
||||
functionCall: {
|
||||
name: toolName || 'unknown',
|
||||
args: maskedIntent,
|
||||
id: callId,
|
||||
},
|
||||
},
|
||||
]);
|
||||
|
||||
let obsPart: Record<string, unknown> = {};
|
||||
if (maskedObs) {
|
||||
obsPart = {
|
||||
functionResponse: {
|
||||
name: toolName || 'unknown',
|
||||
response: maskedObs,
|
||||
id: callId,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
const newObsTokens =
|
||||
this.env.tokenCalculator.estimateTokensForParts([
|
||||
obsPart as Part,
|
||||
]);
|
||||
|
||||
const tokensSaved =
|
||||
this.env.tokenCalculator.getTokenCost(node) -
|
||||
(newIntentTokens + newObsTokens);
|
||||
|
||||
if (tokensSaved > 0) {
|
||||
const maskedNode: ToolExecution = {
|
||||
...node,
|
||||
id: this.env.idGenerator.generateId(), // Modified, so generate new ID
|
||||
intent: maskedIntent ?? node.intent,
|
||||
observation: maskedObs ?? node.observation,
|
||||
tokens: {
|
||||
intent: newIntentTokens,
|
||||
observation: newObsTokens,
|
||||
},
|
||||
};
|
||||
|
||||
returnedNodes.push(maskedNode);
|
||||
} else {
|
||||
returnedNodes.push(node);
|
||||
}
|
||||
} else {
|
||||
returnedNodes.push(node);
|
||||
}
|
||||
break;
|
||||
}
|
||||
default:
|
||||
returnedNodes.push(node);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return returnedNodes;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,66 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { SidecarRegistry } from './registry.js';
|
||||
import { registerBuiltInProcessors } from './builtins.js';
|
||||
import { describe, it, expect, beforeEach } from 'vitest';
|
||||
import { SidecarLoader } from './SidecarLoader.js';
|
||||
import { defaultSidecarProfile } from './profiles.js';
|
||||
import { InMemoryFileSystem } from '../system/InMemoryFileSystem.js';
|
||||
import type { Config } from 'src/config/config.js';
|
||||
|
||||
describe('SidecarLoader (Fake FS)', () => {
|
||||
let fileSystem: InMemoryFileSystem;
|
||||
let registry: SidecarRegistry;
|
||||
|
||||
beforeEach(() => {
|
||||
fileSystem = new InMemoryFileSystem();
|
||||
registry = new SidecarRegistry();
|
||||
registerBuiltInProcessors(registry);
|
||||
});
|
||||
|
||||
const mockConfig = {
|
||||
getExperimentalContextSidecarConfig: () => '/path/to/sidecar.json',
|
||||
} as unknown as Config;
|
||||
|
||||
it('returns default profile if file does not exist', () => {
|
||||
const result = SidecarLoader.fromConfig(mockConfig, registry, fileSystem);
|
||||
expect(result).toBe(defaultSidecarProfile);
|
||||
});
|
||||
|
||||
it('returns default profile if file exists but is 0 bytes', () => {
|
||||
fileSystem.setFile('/path/to/sidecar.json', '');
|
||||
const result = SidecarLoader.fromConfig(mockConfig, registry, fileSystem);
|
||||
expect(result).toBe(defaultSidecarProfile);
|
||||
});
|
||||
|
||||
it('throws an error if file is empty whitespace', () => {
|
||||
fileSystem.setFile('/path/to/sidecar.json', ' \n ');
|
||||
expect(() =>
|
||||
SidecarLoader.fromConfig(mockConfig, registry, fileSystem),
|
||||
).toThrow('is empty');
|
||||
});
|
||||
|
||||
it('returns parsed config if file is valid', () => {
|
||||
const validConfig = {
|
||||
budget: { retainedTokens: 1000, maxTokens: 2000 },
|
||||
pipelines: [],
|
||||
};
|
||||
fileSystem.setFile('/path/to/sidecar.json', JSON.stringify(validConfig));
|
||||
const result = SidecarLoader.fromConfig(mockConfig, registry, fileSystem);
|
||||
expect(result.budget.maxTokens).toBe(2000);
|
||||
});
|
||||
|
||||
it('throws validation error if file is invalid', () => {
|
||||
const invalidConfig = {
|
||||
budget: { retainedTokens: 1000 }, // missing maxTokens
|
||||
};
|
||||
fileSystem.setFile('/path/to/sidecar.json', JSON.stringify(invalidConfig));
|
||||
expect(() =>
|
||||
SidecarLoader.fromConfig(mockConfig, registry, fileSystem),
|
||||
).toThrow('Validation error:');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,87 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { Config } from '../../config/config.js';
|
||||
import type { SidecarConfig } from './types.js';
|
||||
import { defaultSidecarProfile } from './profiles.js';
|
||||
import { SchemaValidator } from '../../utils/schemaValidator.js';
|
||||
import { getSidecarConfigSchema } from './schema.js';
|
||||
import type { IFileSystem } from '../system/IFileSystem.js';
|
||||
import { NodeFileSystem } from '../system/NodeFileSystem.js';
|
||||
import type { SidecarRegistry } from './registry.js';
|
||||
|
||||
export class SidecarLoader {
|
||||
/**
|
||||
* Loads and validates a sidecar config from a specific file path.
|
||||
* Throws an error if the file cannot be read, parsed, or fails schema validation.
|
||||
*/
|
||||
static loadFromFile(
|
||||
sidecarPath: string,
|
||||
registry: SidecarRegistry,
|
||||
fileSystem: IFileSystem = new NodeFileSystem(),
|
||||
): SidecarConfig {
|
||||
const fileContent = fileSystem.readFileSync(sidecarPath, 'utf8');
|
||||
|
||||
if (!fileContent.trim()) {
|
||||
throw new Error(`Sidecar configuration file at ${sidecarPath} is empty.`);
|
||||
}
|
||||
|
||||
let parsed: unknown;
|
||||
try {
|
||||
parsed = JSON.parse(fileContent);
|
||||
} catch (error) {
|
||||
throw new Error(
|
||||
`Failed to parse Sidecar configuration file at ${sidecarPath}: ${
|
||||
error instanceof Error ? error.message : String(error)
|
||||
}`,
|
||||
);
|
||||
}
|
||||
|
||||
const validationError = SchemaValidator.validate(
|
||||
getSidecarConfigSchema(registry),
|
||||
parsed,
|
||||
);
|
||||
if (validationError) {
|
||||
throw new Error(
|
||||
`Invalid sidecar configuration in ${sidecarPath}. Validation error: ${validationError}`,
|
||||
);
|
||||
}
|
||||
|
||||
// Schema has been validated.
|
||||
const isSidecarConfig = (val: unknown): val is SidecarConfig => true;
|
||||
if (isSidecarConfig(parsed)) {
|
||||
return parsed;
|
||||
}
|
||||
throw new Error(
|
||||
'Unreachable: schema validation passed but type predicate failed.',
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Generates a Sidecar JSON graph from the experimental config file path or defaults.
|
||||
* If a config file is present but invalid, this will THROW to prevent silent misconfiguration.
|
||||
*/
|
||||
static fromConfig(
|
||||
config: Config,
|
||||
registry: SidecarRegistry,
|
||||
fileSystem: IFileSystem = new NodeFileSystem(),
|
||||
): SidecarConfig {
|
||||
const sidecarPath = config.getExperimentalContextSidecarConfig();
|
||||
|
||||
if (sidecarPath && fileSystem.existsSync(sidecarPath)) {
|
||||
const size = fileSystem.statSyncSize(sidecarPath);
|
||||
// If the file exists but is completely empty (0 bytes), it's safe to fallback.
|
||||
if (size === 0) {
|
||||
return defaultSidecarProfile;
|
||||
}
|
||||
|
||||
// If the file has content, enforce strict validation and throw on failure.
|
||||
return this.loadFromFile(sidecarPath, registry, fileSystem);
|
||||
}
|
||||
|
||||
return defaultSidecarProfile;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,85 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { SidecarRegistry } from './registry.js';
|
||||
import {
|
||||
HistoryTruncationProcessor,
|
||||
type HistoryTruncationProcessorOptions,
|
||||
} from '../processors/historyTruncationProcessor.js';
|
||||
import { BlobDegradationProcessor } from '../processors/blobDegradationProcessor.js';
|
||||
import {
|
||||
NodeTruncationProcessor,
|
||||
type NodeTruncationProcessorOptions,
|
||||
} from '../processors/nodeTruncationProcessor.js';
|
||||
import {
|
||||
NodeDistillationProcessor,
|
||||
type NodeDistillationProcessorOptions,
|
||||
} from '../processors/nodeDistillationProcessor.js';
|
||||
import {
|
||||
ToolMaskingProcessor,
|
||||
type ToolMaskingProcessorOptions,
|
||||
} from '../processors/toolMaskingProcessor.js';
|
||||
import {
|
||||
StateSnapshotProcessor,
|
||||
type StateSnapshotProcessorOptions,
|
||||
} from '../processors/stateSnapshotProcessor.js';
|
||||
import {
|
||||
StateSnapshotWorker,
|
||||
type StateSnapshotWorkerOptions,
|
||||
} from '../processors/stateSnapshotWorker.js';
|
||||
import {
|
||||
RollingSummaryProcessor,
|
||||
type RollingSummaryProcessorOptions,
|
||||
} from '../processors/rollingSummaryProcessor.js';
|
||||
|
||||
export function registerBuiltInProcessors(registry: SidecarRegistry) {
|
||||
registry.registerProcessor<Record<string, never>>({
|
||||
id: 'BlobDegradationProcessor',
|
||||
schema: { type: 'object', properties: {} },
|
||||
create: (env) => new BlobDegradationProcessor(env),
|
||||
});
|
||||
|
||||
registry.registerProcessor<HistoryTruncationProcessorOptions>({
|
||||
id: 'HistoryTruncationProcessor',
|
||||
schema: HistoryTruncationProcessor.schema,
|
||||
create: (env, options) => HistoryTruncationProcessor.create(env, options),
|
||||
});
|
||||
|
||||
registry.registerProcessor<NodeTruncationProcessorOptions>({
|
||||
id: 'NodeTruncationProcessor',
|
||||
schema: NodeTruncationProcessor.schema,
|
||||
create: (env, options) => NodeTruncationProcessor.create(env, options),
|
||||
});
|
||||
|
||||
registry.registerProcessor<NodeDistillationProcessorOptions>({
|
||||
id: 'NodeDistillationProcessor',
|
||||
schema: NodeDistillationProcessor.schema,
|
||||
create: (env, options) => NodeDistillationProcessor.create(env, options),
|
||||
});
|
||||
|
||||
registry.registerProcessor<ToolMaskingProcessorOptions>({
|
||||
id: 'ToolMaskingProcessor',
|
||||
schema: ToolMaskingProcessor.schema,
|
||||
create: (env, options) => ToolMaskingProcessor.create(env, options),
|
||||
});
|
||||
|
||||
registry.registerProcessor<StateSnapshotProcessorOptions>({
|
||||
id: 'StateSnapshotProcessor',
|
||||
schema: StateSnapshotProcessor.schema,
|
||||
create: (env, options) => StateSnapshotProcessor.create(env, options),
|
||||
});
|
||||
|
||||
registry.registerWorker<StateSnapshotWorkerOptions>({
|
||||
id: 'StateSnapshotWorker',
|
||||
schema: StateSnapshotWorker.schema,
|
||||
create: (env, options) => StateSnapshotWorker.create(env, options),
|
||||
});
|
||||
|
||||
registry.registerProcessor<RollingSummaryProcessorOptions>({
|
||||
id: 'RollingSummaryProcessor',
|
||||
schema: RollingSummaryProcessor.schema,
|
||||
create: (env, options) => RollingSummaryProcessor.create(env, options),
|
||||
});
|
||||
}
|
||||
@@ -0,0 +1,162 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { ContextWorkingBufferImpl } from './contextWorkingBuffer.js';
|
||||
import { createDummyNode } from '../testing/contextTestUtils.js';
|
||||
|
||||
describe('ContextWorkingBufferImpl', () => {
|
||||
it('should initialize with a pristine graph correctly', () => {
|
||||
const pristine1 = createDummyNode(
|
||||
'ep1',
|
||||
'USER_PROMPT',
|
||||
10,
|
||||
undefined,
|
||||
'p1',
|
||||
);
|
||||
const pristine2 = createDummyNode(
|
||||
'ep1',
|
||||
'AGENT_THOUGHT',
|
||||
10,
|
||||
undefined,
|
||||
'p2',
|
||||
);
|
||||
|
||||
const buffer = ContextWorkingBufferImpl.initialize([pristine1, pristine2]);
|
||||
|
||||
expect(buffer.nodes).toHaveLength(2);
|
||||
expect(buffer.getAuditLog()).toHaveLength(0);
|
||||
|
||||
// Pristine nodes should point to themselves
|
||||
expect(buffer.getPristineNodes('p1')).toEqual([pristine1]);
|
||||
expect(buffer.getPristineNodes('p2')).toEqual([pristine2]);
|
||||
});
|
||||
|
||||
it('should track 1:1 replacements (e.g., masking) and append to audit log', () => {
|
||||
const pristine1 = createDummyNode(
|
||||
'ep1',
|
||||
'USER_PROMPT',
|
||||
10,
|
||||
undefined,
|
||||
'p1',
|
||||
);
|
||||
let buffer = ContextWorkingBufferImpl.initialize([pristine1]);
|
||||
|
||||
const maskedNode = createDummyNode(
|
||||
'ep1',
|
||||
'USER_PROMPT',
|
||||
5,
|
||||
undefined,
|
||||
'm1',
|
||||
);
|
||||
// Simulate what a processor does
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
(maskedNode as any).replacesId = 'p1';
|
||||
|
||||
buffer = buffer.applyProcessorResult(
|
||||
'ToolMasking',
|
||||
[pristine1],
|
||||
[maskedNode],
|
||||
);
|
||||
|
||||
expect(buffer.nodes).toHaveLength(1);
|
||||
expect(buffer.nodes[0].id).toBe('m1');
|
||||
|
||||
const log = buffer.getAuditLog();
|
||||
expect(log).toHaveLength(1);
|
||||
expect(log[0].processorId).toBe('ToolMasking');
|
||||
expect(log[0].removedIds).toEqual(['p1']);
|
||||
expect(log[0].addedNodes[0].id).toBe('m1');
|
||||
|
||||
// Provenance lookup: the masked node should resolve back to the pristine root
|
||||
expect(buffer.getPristineNodes('m1')).toEqual([pristine1]);
|
||||
});
|
||||
|
||||
it('should track N:1 abstractions (e.g., rolling summaries)', () => {
|
||||
const p1 = createDummyNode('ep1', 'USER_PROMPT', 10, undefined, 'p1');
|
||||
const p2 = createDummyNode('ep1', 'AGENT_THOUGHT', 10, undefined, 'p2');
|
||||
const p3 = createDummyNode('ep1', 'USER_PROMPT', 10, undefined, 'p3');
|
||||
|
||||
let buffer = ContextWorkingBufferImpl.initialize([p1, p2, p3]);
|
||||
|
||||
const summaryNode = createDummyNode(
|
||||
'ep1',
|
||||
'ROLLING_SUMMARY',
|
||||
15,
|
||||
undefined,
|
||||
's1',
|
||||
);
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
(summaryNode as any).abstractsIds = ['p1', 'p2'];
|
||||
|
||||
buffer = buffer.applyProcessorResult('Summarizer', [p1, p2], [summaryNode]);
|
||||
|
||||
// p1 and p2 are removed, p3 remains, s1 is added
|
||||
expect(buffer.nodes.map((n) => n.id)).toEqual(['p3', 's1']);
|
||||
|
||||
// Provenance lookup: The summary node should resolve to both p1 and p2!
|
||||
const roots = buffer.getPristineNodes('s1');
|
||||
expect(roots).toHaveLength(2);
|
||||
expect(roots).toContain(p1);
|
||||
expect(roots).toContain(p2);
|
||||
});
|
||||
|
||||
it('should track multi-generation provenance correctly', () => {
|
||||
const p1 = createDummyNode('ep1', 'USER_PROMPT', 10, undefined, 'p1');
|
||||
let buffer = ContextWorkingBufferImpl.initialize([p1]);
|
||||
|
||||
// Gen 1: Masked
|
||||
const gen1 = createDummyNode('ep1', 'USER_PROMPT', 8, undefined, 'gen1');
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
(gen1 as any).replacesId = 'p1';
|
||||
buffer = buffer.applyProcessorResult('Masking', [p1], [gen1]);
|
||||
|
||||
// Gen 2: Summarized
|
||||
const gen2 = createDummyNode(
|
||||
'ep1',
|
||||
'ROLLING_SUMMARY',
|
||||
5,
|
||||
undefined,
|
||||
'gen2',
|
||||
);
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
(gen2 as any).abstractsIds = ['gen1'];
|
||||
buffer = buffer.applyProcessorResult('Summarizer', [gen1], [gen2]);
|
||||
|
||||
expect(buffer.nodes).toHaveLength(1);
|
||||
expect(buffer.nodes[0].id).toBe('gen2');
|
||||
|
||||
// Audit log should show sequence
|
||||
const log = buffer.getAuditLog();
|
||||
expect(log).toHaveLength(2);
|
||||
expect(log[0].processorId).toBe('Masking');
|
||||
expect(log[1].processorId).toBe('Summarizer');
|
||||
|
||||
// Multi-gen Provenance lookup: gen2 -> gen1 -> p1
|
||||
expect(buffer.getPristineNodes('gen2')).toEqual([p1]);
|
||||
});
|
||||
|
||||
it('should handle net-new injected nodes without throwing', () => {
|
||||
const p1 = createDummyNode('ep1', 'USER_PROMPT', 10, undefined, 'p1');
|
||||
let buffer = ContextWorkingBufferImpl.initialize([p1]);
|
||||
|
||||
const injected = createDummyNode(
|
||||
'ep1',
|
||||
'SYSTEM_EVENT',
|
||||
5,
|
||||
undefined,
|
||||
'injected1',
|
||||
);
|
||||
// No replacesId or abstractsIds
|
||||
|
||||
buffer = buffer.applyProcessorResult('Injector', [], [injected]);
|
||||
|
||||
expect(buffer.nodes.map((n) => n.id)).toEqual(['p1', 'injected1']);
|
||||
|
||||
// It should root to itself
|
||||
expect(buffer.getPristineNodes('injected1')).toEqual([injected]);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,195 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { ContextWorkingBuffer, GraphMutation } from '../pipeline.js';
|
||||
import type { ConcreteNode } from '../ir/types.js';
|
||||
|
||||
export class ContextWorkingBufferImpl implements ContextWorkingBuffer {
|
||||
// The current active graph
|
||||
readonly nodes: readonly ConcreteNode[];
|
||||
|
||||
// The AOT pre-calculated provenance index (Current ID -> Pristine IDs)
|
||||
private readonly provenanceMap: ReadonlyMap<string, ReadonlySet<string>>;
|
||||
|
||||
// The original immutable pristine nodes mapping
|
||||
private readonly pristineNodesMap: ReadonlyMap<string, ConcreteNode>;
|
||||
|
||||
// The historical linked list of changes
|
||||
private readonly history: readonly GraphMutation[];
|
||||
|
||||
private constructor(
|
||||
nodes: readonly ConcreteNode[],
|
||||
pristineNodesMap: ReadonlyMap<string, ConcreteNode>,
|
||||
provenanceMap: ReadonlyMap<string, ReadonlySet<string>>,
|
||||
history: readonly GraphMutation[],
|
||||
) {
|
||||
this.nodes = nodes;
|
||||
this.pristineNodesMap = pristineNodesMap;
|
||||
this.provenanceMap = provenanceMap;
|
||||
this.history = history;
|
||||
}
|
||||
|
||||
/**
|
||||
* Initializes a brand new ContextWorkingBuffer from a pristine graph.
|
||||
* Every node's provenance points to itself.
|
||||
*/
|
||||
static initialize(
|
||||
pristineNodes: readonly ConcreteNode[],
|
||||
): ContextWorkingBufferImpl {
|
||||
const pristineMap = new Map<string, ConcreteNode>();
|
||||
const initialProvenance = new Map<string, ReadonlySet<string>>();
|
||||
|
||||
for (const node of pristineNodes) {
|
||||
pristineMap.set(node.id, node);
|
||||
initialProvenance.set(node.id, new Set([node.id]));
|
||||
}
|
||||
|
||||
return new ContextWorkingBufferImpl(
|
||||
pristineNodes,
|
||||
pristineMap,
|
||||
initialProvenance,
|
||||
[], // Empty history
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Appends newly observed pristine nodes (e.g. from a user message) to the working buffer.
|
||||
* Ensures they are tracked in the pristine map and point to themselves in provenance.
|
||||
*/
|
||||
appendPristineNodes(
|
||||
newNodes: readonly ConcreteNode[],
|
||||
): ContextWorkingBufferImpl {
|
||||
if (newNodes.length === 0) return this;
|
||||
|
||||
const newPristineMap = new Map<string, ConcreteNode>(this.pristineNodesMap);
|
||||
const newProvenanceMap = new Map(this.provenanceMap);
|
||||
|
||||
for (const node of newNodes) {
|
||||
newPristineMap.set(node.id, node);
|
||||
newProvenanceMap.set(node.id, new Set([node.id]));
|
||||
}
|
||||
|
||||
return new ContextWorkingBufferImpl(
|
||||
[...this.nodes, ...newNodes],
|
||||
newPristineMap,
|
||||
newProvenanceMap,
|
||||
[...this.history],
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Generates an entirely new buffer instance by calculating the delta between the processor's input and output.
|
||||
*/
|
||||
applyProcessorResult(
|
||||
processorId: string,
|
||||
inputTargets: readonly ConcreteNode[],
|
||||
outputNodes: readonly ConcreteNode[],
|
||||
): ContextWorkingBufferImpl {
|
||||
const outputIds = new Set(outputNodes.map((n) => n.id));
|
||||
const inputIds = new Set(inputTargets.map((n) => n.id));
|
||||
|
||||
// Calculate diffs
|
||||
const removedIds = inputTargets
|
||||
.filter((n) => !outputIds.has(n.id))
|
||||
.map((n) => n.id);
|
||||
const addedNodes = outputNodes.filter((n) => !inputIds.has(n.id));
|
||||
|
||||
// Create mutation record
|
||||
const mutation: GraphMutation = {
|
||||
processorId,
|
||||
timestamp: Date.now(),
|
||||
removedIds,
|
||||
addedNodes,
|
||||
};
|
||||
|
||||
// Calculate new node array
|
||||
const removedSet = new Set(removedIds);
|
||||
const retainedNodes = this.nodes.filter((n) => !removedSet.has(n.id));
|
||||
const newGraph = [...retainedNodes];
|
||||
|
||||
// We append the output nodes in the same general position if possible,
|
||||
// but in a complex graph we just ensure they exist. V2 graph uses timestamps for order.
|
||||
// For simplicity, we just push added nodes to the end of the retained array
|
||||
newGraph.push(...addedNodes);
|
||||
|
||||
// Calculate new provenance map
|
||||
const newProvenanceMap = new Map(this.provenanceMap);
|
||||
|
||||
let finalPristineMap = this.pristineNodesMap;
|
||||
|
||||
// Map the new synthetic nodes back to their pristine roots
|
||||
for (const added of addedNodes) {
|
||||
const roots = new Set<string>();
|
||||
|
||||
// 1:1 Replacement (e.g. Masked Node)
|
||||
if (added.replacesId) {
|
||||
const inheritedRoots = this.provenanceMap.get(added.replacesId);
|
||||
if (inheritedRoots) {
|
||||
for (const rootId of inheritedRoots) roots.add(rootId);
|
||||
}
|
||||
}
|
||||
|
||||
// N:1 Abstraction (e.g. Rolling Summary)
|
||||
if (added.abstractsIds) {
|
||||
for (const abstractId of added.abstractsIds) {
|
||||
const inheritedRoots = this.provenanceMap.get(abstractId);
|
||||
if (inheritedRoots) {
|
||||
for (const rootId of inheritedRoots) roots.add(rootId);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// If it has no links back to the original graph, it is its own root
|
||||
// (e.g., a system-injected instruction)
|
||||
if (roots.size === 0) {
|
||||
roots.add(added.id);
|
||||
// It acts as a net-new pristine root.
|
||||
if (!finalPristineMap.has(added.id)) {
|
||||
const mutableMap = new Map<string, ConcreteNode>(finalPristineMap);
|
||||
mutableMap.set(added.id, added);
|
||||
finalPristineMap = mutableMap;
|
||||
}
|
||||
}
|
||||
|
||||
newProvenanceMap.set(added.id, roots);
|
||||
}
|
||||
|
||||
return new ContextWorkingBufferImpl(
|
||||
newGraph,
|
||||
finalPristineMap,
|
||||
newProvenanceMap,
|
||||
[...this.history, mutation],
|
||||
);
|
||||
}
|
||||
|
||||
getPristineNodes(id: string): readonly ConcreteNode[] {
|
||||
const pristineIds = this.provenanceMap.get(id);
|
||||
if (!pristineIds) return [];
|
||||
return Array.from(pristineIds).map(
|
||||
(pid) => this.pristineNodesMap.get(pid)!,
|
||||
);
|
||||
}
|
||||
|
||||
getAuditLog(): readonly GraphMutation[] {
|
||||
return this.history;
|
||||
}
|
||||
|
||||
getLineage(id: string): readonly ConcreteNode[] {
|
||||
const lineage: ConcreteNode[] = [];
|
||||
const currentNodesMap = new Map(this.nodes.map((n) => [n.id, n]));
|
||||
|
||||
let current = currentNodesMap.get(id);
|
||||
while (current) {
|
||||
lineage.push(current);
|
||||
if (current.logicalParentId && current.logicalParentId !== current.id) {
|
||||
current = currentNodesMap.get(current.logicalParentId);
|
||||
} else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
return lineage;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,33 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { BaseLlmClient } from '../../core/baseLlmClient.js';
|
||||
import type { ContextEventBus } from '../eventBus.js';
|
||||
import type { ContextTokenCalculator } from '../utils/contextTokenCalculator.js';
|
||||
import type { ContextTracer } from '../tracer.js';
|
||||
import type { IFileSystem } from '../system/IFileSystem.js';
|
||||
import type { IIdGenerator } from '../system/IIdGenerator.js';
|
||||
import type { LiveInbox } from './inbox.js';
|
||||
import type { IrNodeBehaviorRegistry } from '../ir/behaviorRegistry.js';
|
||||
import type { IrMapper } from '../ir/mapper.js';
|
||||
|
||||
export type { ContextTracer, ContextEventBus };
|
||||
|
||||
export interface ContextEnvironment {
|
||||
readonly llmClient: BaseLlmClient;
|
||||
readonly promptId: string;
|
||||
readonly sessionId: string;
|
||||
readonly traceDir: string;
|
||||
readonly projectTempDir: string;
|
||||
readonly tracer: ContextTracer;
|
||||
readonly charsPerToken: number;
|
||||
readonly tokenCalculator: ContextTokenCalculator;
|
||||
readonly fileSystem: IFileSystem;
|
||||
readonly idGenerator: IIdGenerator;
|
||||
readonly eventBus: ContextEventBus;
|
||||
readonly inbox: LiveInbox;
|
||||
readonly behaviorRegistry: IrNodeBehaviorRegistry;
|
||||
readonly irMapper: IrMapper;
|
||||
}
|
||||
@@ -0,0 +1,72 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { ContextEnvironmentImpl } from './environmentImpl.js';
|
||||
import { ContextTracer } from '../tracer.js';
|
||||
import { ContextEventBus } from '../eventBus.js';
|
||||
import { InMemoryFileSystem } from '../system/InMemoryFileSystem.js';
|
||||
import { DeterministicIdGenerator } from '../system/DeterministicIdGenerator.js';
|
||||
import { createMockLlmClient } from '../testing/contextTestUtils.js';
|
||||
|
||||
describe('ContextEnvironmentImpl', () => {
|
||||
it('should initialize with defaults correctly', () => {
|
||||
const tracer = new ContextTracer({ targetDir: '/tmp', sessionId: 'mock' });
|
||||
const eventBus = new ContextEventBus();
|
||||
const mockLlmClient = createMockLlmClient();
|
||||
|
||||
const env = new ContextEnvironmentImpl(
|
||||
mockLlmClient,
|
||||
'mock-session',
|
||||
'mock-prompt',
|
||||
'/tmp/trace',
|
||||
'/tmp/temp',
|
||||
tracer,
|
||||
4,
|
||||
eventBus,
|
||||
);
|
||||
|
||||
expect(env.llmClient).toBe(mockLlmClient);
|
||||
expect(env.sessionId).toBe('mock-session');
|
||||
expect(env.promptId).toBe('mock-prompt');
|
||||
expect(env.traceDir).toBe('/tmp/trace');
|
||||
expect(env.projectTempDir).toBe('/tmp/temp');
|
||||
expect(env.tracer).toBe(tracer);
|
||||
expect(env.charsPerToken).toBe(4);
|
||||
expect(env.eventBus).toBe(eventBus);
|
||||
|
||||
// Default internals
|
||||
expect(env.behaviorRegistry).toBeDefined();
|
||||
expect(env.tokenCalculator).toBeDefined();
|
||||
expect(env.fileSystem).toBeDefined();
|
||||
expect(env.idGenerator).toBeDefined();
|
||||
expect(env.inbox).toBeDefined();
|
||||
expect(env.irMapper).toBeDefined();
|
||||
});
|
||||
|
||||
it('should initialize with provided overrides', () => {
|
||||
const tracer = new ContextTracer({ targetDir: '/tmp', sessionId: 'mock' });
|
||||
const eventBus = new ContextEventBus();
|
||||
const mockLlmClient = createMockLlmClient();
|
||||
const fileSystem = new InMemoryFileSystem();
|
||||
const idGenerator = new DeterministicIdGenerator('test-');
|
||||
|
||||
const env = new ContextEnvironmentImpl(
|
||||
mockLlmClient,
|
||||
'mock-session',
|
||||
'mock-prompt',
|
||||
'/tmp/trace',
|
||||
'/tmp/temp',
|
||||
tracer,
|
||||
4,
|
||||
eventBus,
|
||||
fileSystem,
|
||||
idGenerator,
|
||||
);
|
||||
|
||||
expect(env.fileSystem).toBe(fileSystem);
|
||||
expect(env.idGenerator).toBe(idGenerator);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,52 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { BaseLlmClient } from '../../core/baseLlmClient.js';
|
||||
import type { ContextTracer } from '../tracer.js';
|
||||
import type { ContextEnvironment } from './environment.js';
|
||||
import type { ContextEventBus } from '../eventBus.js';
|
||||
import { ContextTokenCalculator } from '../utils/contextTokenCalculator.js';
|
||||
import type { IFileSystem } from '../system/IFileSystem.js';
|
||||
import { NodeFileSystem } from '../system/NodeFileSystem.js';
|
||||
import type { IIdGenerator } from '../system/IIdGenerator.js';
|
||||
import { NodeIdGenerator } from '../system/NodeIdGenerator.js';
|
||||
import { LiveInbox } from './inbox.js';
|
||||
import { IrNodeBehaviorRegistry } from '../ir/behaviorRegistry.js';
|
||||
import { registerBuiltInBehaviors } from '../ir/builtinBehaviors.js';
|
||||
import { IrMapper } from '../ir/mapper.js';
|
||||
|
||||
export class ContextEnvironmentImpl implements ContextEnvironment {
|
||||
readonly tokenCalculator: ContextTokenCalculator;
|
||||
readonly fileSystem: IFileSystem;
|
||||
readonly idGenerator: IIdGenerator;
|
||||
readonly inbox: LiveInbox;
|
||||
readonly behaviorRegistry: IrNodeBehaviorRegistry;
|
||||
readonly irMapper: IrMapper;
|
||||
|
||||
constructor(
|
||||
readonly llmClient: BaseLlmClient,
|
||||
readonly sessionId: string,
|
||||
readonly promptId: string,
|
||||
readonly traceDir: string,
|
||||
readonly projectTempDir: string,
|
||||
readonly tracer: ContextTracer,
|
||||
readonly charsPerToken: number,
|
||||
readonly eventBus: ContextEventBus,
|
||||
fileSystem?: IFileSystem,
|
||||
idGenerator?: IIdGenerator,
|
||||
) {
|
||||
this.behaviorRegistry = new IrNodeBehaviorRegistry();
|
||||
registerBuiltInBehaviors(this.behaviorRegistry);
|
||||
this.tokenCalculator = new ContextTokenCalculator(
|
||||
this.charsPerToken,
|
||||
this.behaviorRegistry,
|
||||
);
|
||||
this.fileSystem = fileSystem || new NodeFileSystem();
|
||||
this.idGenerator = idGenerator || new NodeIdGenerator();
|
||||
this.inbox = new LiveInbox();
|
||||
this.irMapper = new IrMapper(this.behaviorRegistry);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,48 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { LiveInbox, InboxSnapshotImpl } from './inbox.js';
|
||||
import { DeterministicIdGenerator } from '../system/DeterministicIdGenerator.js';
|
||||
|
||||
describe('Inbox', () => {
|
||||
it('should publish messages and provide snapshots', () => {
|
||||
const inbox = new LiveInbox();
|
||||
const idGenerator = new DeterministicIdGenerator('mock-uuid-');
|
||||
|
||||
inbox.publish('test-topic', { data: 'hello' }, idGenerator);
|
||||
inbox.publish('other-topic', { data: 'world' }, idGenerator);
|
||||
|
||||
const messages = inbox.getMessages();
|
||||
expect(messages.length).toBe(2);
|
||||
expect(messages[0].topic).toBe('test-topic');
|
||||
expect(messages[0].payload).toEqual({ data: 'hello' });
|
||||
});
|
||||
|
||||
it('should drain consumed messages from the snapshot', () => {
|
||||
const inbox = new LiveInbox();
|
||||
const idGenerator = new DeterministicIdGenerator('mock-uuid-');
|
||||
|
||||
inbox.publish('test-topic', { data: 'hello' }, idGenerator);
|
||||
inbox.publish('other-topic', { data: 'world' }, idGenerator);
|
||||
|
||||
const messages = inbox.getMessages();
|
||||
const snapshot = new InboxSnapshotImpl(messages);
|
||||
|
||||
const filtered = snapshot.getMessages<{ data: string }>('test-topic');
|
||||
expect(filtered.length).toBe(1);
|
||||
expect(filtered[0].payload.data).toBe('hello');
|
||||
|
||||
// Consume the message
|
||||
snapshot.consume(filtered[0].id);
|
||||
|
||||
// Provide the consumed IDs to the real inbox to drain them
|
||||
inbox.drainConsumed(snapshot.getConsumedIds());
|
||||
|
||||
const finalMessages = inbox.getMessages();
|
||||
expect(finalMessages.length).toBe(1);
|
||||
expect(finalMessages[0].topic).toBe('other-topic');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,64 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import type { InboxMessage, InboxSnapshot } from '../pipeline.js';
|
||||
|
||||
export class LiveInbox {
|
||||
private messages: InboxMessage[] = [];
|
||||
|
||||
publish<T>(
|
||||
topic: string,
|
||||
payload: T,
|
||||
idGenerator: { generateId(): string },
|
||||
): void {
|
||||
this.messages.push({
|
||||
id: idGenerator.generateId(),
|
||||
topic,
|
||||
payload,
|
||||
timestamp: Date.now(),
|
||||
});
|
||||
}
|
||||
|
||||
getMessages(): readonly InboxMessage[] {
|
||||
return [...this.messages];
|
||||
}
|
||||
|
||||
drainConsumed(consumedIds: Set<string>): void {
|
||||
this.messages = this.messages.filter((m) => !consumedIds.has(m.id));
|
||||
}
|
||||
}
|
||||
|
||||
export class InboxSnapshotImpl implements InboxSnapshot {
|
||||
private messages: readonly InboxMessage[];
|
||||
private consumedIds = new Set<string>();
|
||||
|
||||
constructor(messages: readonly InboxMessage[]) {
|
||||
this.messages = messages;
|
||||
}
|
||||
|
||||
getMessages<T = unknown>(topic: string): ReadonlyArray<InboxMessage<T>> {
|
||||
const raw = this.messages.filter((m) => m.topic === topic);
|
||||
/*
|
||||
* Architectural Justification for Unchecked Cast:
|
||||
* The Inbox is a heterogeneous event bus designed to support arbitrary, declarative
|
||||
* routing via configuration files (where topics are just strings). Because TypeScript
|
||||
* completely erases generic type information (<T>) at runtime, the central array
|
||||
* can only hold `unknown` payloads. To enforce strict type safety without a central
|
||||
* registry (which would break decoupling) or heavy runtime validation (Zod schemas),
|
||||
* we must assert the type boundary here. The contract relies on the Worker and Processor
|
||||
* agreeing on the payload structure associated with the configured topic string.
|
||||
*/
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
return raw as ReadonlyArray<InboxMessage<T>>;
|
||||
}
|
||||
|
||||
consume(messageId: string): void {
|
||||
this.consumedIds.add(messageId);
|
||||
}
|
||||
|
||||
getConsumedIds(): Set<string> {
|
||||
return this.consumedIds;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,316 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import assert from 'node:assert';
|
||||
import { describe, it, expect, beforeEach, vi, afterEach } from 'vitest';
|
||||
import { PipelineOrchestrator } from './orchestrator.js';
|
||||
import { SidecarRegistry } from './registry.js';
|
||||
import {
|
||||
createMockEnvironment,
|
||||
createDummyNode,
|
||||
} from '../testing/contextTestUtils.js';
|
||||
import type { ContextEnvironment } from './environment.js';
|
||||
import type {
|
||||
ContextProcessor,
|
||||
ContextWorker,
|
||||
InboxSnapshot,
|
||||
ProcessArgs,
|
||||
} from '../pipeline.js';
|
||||
import type { PipelineDef, ProcessorConfig, SidecarConfig } from './types.js';
|
||||
import type { ContextEventBus } from '../eventBus.js';
|
||||
import type { ConcreteNode, UserPrompt } from '../ir/types.js';
|
||||
|
||||
// A realistic mock processor that modifies the text of the first target node
|
||||
class ModifyingProcessor implements ContextProcessor {
|
||||
static create() {
|
||||
return new ModifyingProcessor();
|
||||
}
|
||||
constructor() {}
|
||||
readonly name = 'ModifyingProcessor';
|
||||
readonly id = 'ModifyingProcessor';
|
||||
readonly options = {};
|
||||
async process(args: ProcessArgs) {
|
||||
const newTargets = [...args.targets];
|
||||
if (newTargets.length > 0 && newTargets[0].type === 'USER_PROMPT') {
|
||||
const prompt = newTargets[0];
|
||||
const newParts = [...prompt.semanticParts];
|
||||
if (newParts.length > 0 && newParts[0].type === 'text') {
|
||||
newParts[0] = {
|
||||
...newParts[0],
|
||||
text: newParts[0].text + ' [modified]',
|
||||
};
|
||||
}
|
||||
newTargets[0] = {
|
||||
...prompt,
|
||||
id: prompt.id + '-modified',
|
||||
replacesId: prompt.id,
|
||||
semanticParts: newParts,
|
||||
};
|
||||
}
|
||||
return newTargets;
|
||||
}
|
||||
}
|
||||
|
||||
// A processor that just throws an error
|
||||
class ThrowingProcessor implements ContextProcessor {
|
||||
static create() {
|
||||
return new ThrowingProcessor();
|
||||
}
|
||||
constructor() {}
|
||||
readonly name = 'Throwing';
|
||||
readonly id = 'Throwing';
|
||||
readonly options = {};
|
||||
async process(): Promise<readonly ConcreteNode[]> {
|
||||
throw new Error('Processor failed intentionally');
|
||||
}
|
||||
}
|
||||
|
||||
// A mock worker that signals it ran
|
||||
class MockWorker implements ContextWorker {
|
||||
static create() {
|
||||
return new MockWorker();
|
||||
}
|
||||
constructor() {}
|
||||
readonly name = 'MockWorker';
|
||||
readonly id = 'MockWorker';
|
||||
readonly triggers = {
|
||||
onNodesAdded: true,
|
||||
};
|
||||
wasExecuted = false;
|
||||
|
||||
async execute(args: {
|
||||
targets: readonly ConcreteNode[];
|
||||
inbox: InboxSnapshot;
|
||||
}) {
|
||||
this.wasExecuted = true;
|
||||
if (args.targets.length > 0 && args.targets[0].type === 'USER_PROMPT') {
|
||||
const prompt = args.targets[0];
|
||||
if (prompt.semanticParts[0].type === 'text') {
|
||||
args.inbox.consume('test');
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
describe('PipelineOrchestrator (Component)', () => {
|
||||
let env: ContextEnvironment;
|
||||
let eventBus: ContextEventBus;
|
||||
let registry: SidecarRegistry;
|
||||
|
||||
beforeEach(() => {
|
||||
vi.resetAllMocks();
|
||||
env = createMockEnvironment();
|
||||
eventBus = env.eventBus;
|
||||
registry = new SidecarRegistry();
|
||||
|
||||
registry.registerProcessor({
|
||||
id: 'ModifyingProcessor',
|
||||
schema: {},
|
||||
create: () => new ModifyingProcessor(),
|
||||
});
|
||||
registry.registerProcessor({
|
||||
id: 'ThrowingProcessor',
|
||||
schema: {},
|
||||
create: () => new ThrowingProcessor(),
|
||||
});
|
||||
registry.registerWorker({
|
||||
id: 'MockWorker',
|
||||
schema: {},
|
||||
create: () => new MockWorker(),
|
||||
});
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
registry.clear();
|
||||
});
|
||||
|
||||
const createConfig = (
|
||||
pipelines: PipelineDef[],
|
||||
workers?: Array<{ workerId: string }>,
|
||||
): SidecarConfig => ({
|
||||
budget: { maxTokens: 100, retainedTokens: 50 },
|
||||
pipelines,
|
||||
workers,
|
||||
});
|
||||
|
||||
it('instantiates processors and workers from the registry on initialization', () => {
|
||||
const config = createConfig(
|
||||
[
|
||||
{
|
||||
name: 'SyncPipe',
|
||||
triggers: ['new_message'],
|
||||
processors: [
|
||||
{ processorId: 'ModifyingProcessor' } as unknown as ProcessorConfig,
|
||||
],
|
||||
},
|
||||
],
|
||||
[{ workerId: 'MockWorker' }],
|
||||
);
|
||||
|
||||
const orchestrator = new PipelineOrchestrator(
|
||||
config,
|
||||
env,
|
||||
eventBus,
|
||||
env.tracer,
|
||||
registry,
|
||||
);
|
||||
|
||||
expect(
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
(orchestrator as any).instantiatedProcessors.has('ModifyingProcessor'),
|
||||
).toBe(true);
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
expect((orchestrator as any).instantiatedWorkers.has('MockWorker')).toBe(
|
||||
true,
|
||||
);
|
||||
});
|
||||
|
||||
it('throws an error if a config requests an unknown processor', () => {
|
||||
const config = createConfig([
|
||||
{
|
||||
name: 'ThrowPipe',
|
||||
triggers: ['new_message'],
|
||||
processors: [
|
||||
{ processorId: 'DoesNotExist' } as unknown as ProcessorConfig,
|
||||
],
|
||||
},
|
||||
]);
|
||||
|
||||
expect(
|
||||
() =>
|
||||
new PipelineOrchestrator(config, env, eventBus, env.tracer, registry),
|
||||
).toThrow('Context Processor [DoesNotExist] is not registered.');
|
||||
});
|
||||
|
||||
it('executes synchronous routes (executeTriggerSync) and returns modified array', async () => {
|
||||
const config = createConfig([
|
||||
{
|
||||
name: 'SyncPipe',
|
||||
triggers: ['new_message'],
|
||||
processors: [
|
||||
{ processorId: 'ModifyingProcessor' } as unknown as ProcessorConfig,
|
||||
],
|
||||
},
|
||||
]);
|
||||
const orchestrator = new PipelineOrchestrator(
|
||||
config,
|
||||
env,
|
||||
eventBus,
|
||||
env.tracer,
|
||||
registry,
|
||||
);
|
||||
|
||||
const nodes = [
|
||||
createDummyNode(
|
||||
'not-protected-ep',
|
||||
'USER_PROMPT',
|
||||
100,
|
||||
{
|
||||
semanticParts: [{ type: 'text', text: 'original text' }],
|
||||
},
|
||||
'not-protected-id',
|
||||
),
|
||||
];
|
||||
|
||||
const result = await orchestrator.executeTriggerSync(
|
||||
'new_message',
|
||||
nodes,
|
||||
new Set(nodes.map((s) => s.id)),
|
||||
new Set(),
|
||||
);
|
||||
|
||||
expect(result).toHaveLength(1);
|
||||
const modifiedPrompt = result[0] as UserPrompt;
|
||||
assert(
|
||||
modifiedPrompt.semanticParts[0].type === 'text',
|
||||
'Expected a text part',
|
||||
);
|
||||
expect(modifiedPrompt.semanticParts[0].text).toBe(
|
||||
'original text [modified]',
|
||||
);
|
||||
});
|
||||
|
||||
it('gracefully handles and swallows processor errors in synchronous routes', async () => {
|
||||
const config = createConfig([
|
||||
{
|
||||
name: 'ThrowPipe',
|
||||
triggers: ['new_message'],
|
||||
processors: [
|
||||
{ processorId: 'ThrowingProcessor' } as unknown as ProcessorConfig,
|
||||
],
|
||||
},
|
||||
]);
|
||||
const orchestrator = new PipelineOrchestrator(
|
||||
config,
|
||||
env,
|
||||
eventBus,
|
||||
env.tracer,
|
||||
registry,
|
||||
);
|
||||
|
||||
const nodes = [
|
||||
createDummyNode(
|
||||
'not-protected-ep',
|
||||
'USER_PROMPT',
|
||||
100,
|
||||
undefined,
|
||||
'not-protected-id',
|
||||
),
|
||||
];
|
||||
|
||||
// It should not throw! It should swallow the error and return the unmodified array.
|
||||
const result = await orchestrator.executeTriggerSync(
|
||||
'new_message',
|
||||
nodes,
|
||||
new Set(nodes.map((s) => s.id)),
|
||||
new Set(),
|
||||
);
|
||||
|
||||
expect(result).toHaveLength(1);
|
||||
expect(result).toStrictEqual(nodes);
|
||||
});
|
||||
|
||||
it('automatically dispatches workers when matching EventBus events occur', async () => {
|
||||
const config = createConfig([], [{ workerId: 'MockWorker' }]);
|
||||
|
||||
const orchestrator = new PipelineOrchestrator(
|
||||
config,
|
||||
env,
|
||||
eventBus,
|
||||
env.tracer,
|
||||
registry,
|
||||
);
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const workerInstance = (orchestrator as any).instantiatedWorkers.get(
|
||||
'MockWorker',
|
||||
) as MockWorker;
|
||||
expect(workerInstance.wasExecuted).toBe(false);
|
||||
|
||||
const nodes = [
|
||||
createDummyNode(
|
||||
'not-protected-ep',
|
||||
'USER_PROMPT',
|
||||
100,
|
||||
{
|
||||
semanticParts: [{ type: 'text', text: 'worker trigger text' }],
|
||||
},
|
||||
'not-protected-id',
|
||||
),
|
||||
];
|
||||
|
||||
// Emit the new_message chunk which maps to onNodesAdded for workers
|
||||
eventBus.emitChunkReceived({
|
||||
nodes,
|
||||
targetNodeIds: new Set(nodes.map((n) => n.id)),
|
||||
});
|
||||
|
||||
// Worker execute is fire and forget, so we yield to the event loop
|
||||
await new Promise((resolve) => setTimeout(resolve, 10));
|
||||
|
||||
expect(workerInstance.wasExecuted).toBe(true);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,263 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { ConcreteNode } from '../ir/types.js';
|
||||
import type { ContextProcessor, ContextWorker } from '../pipeline.js';
|
||||
import type { SidecarConfig, PipelineDef, PipelineTrigger } from './types.js';
|
||||
import type {
|
||||
ContextEnvironment,
|
||||
ContextEventBus,
|
||||
ContextTracer,
|
||||
} from './environment.js';
|
||||
import type { SidecarRegistry } from './registry.js';
|
||||
import { debugLogger } from '../../utils/debugLogger.js';
|
||||
import { InboxSnapshotImpl } from './inbox.js';
|
||||
import { ContextWorkingBufferImpl } from './contextWorkingBuffer.js';
|
||||
|
||||
export class PipelineOrchestrator {
|
||||
private activeTimers: NodeJS.Timeout[] = [];
|
||||
private readonly instantiatedProcessors = new Map<string, ContextProcessor>();
|
||||
private readonly instantiatedWorkers = new Map<string, ContextWorker>();
|
||||
|
||||
constructor(
|
||||
private readonly config: SidecarConfig,
|
||||
private readonly env: ContextEnvironment,
|
||||
private readonly eventBus: ContextEventBus,
|
||||
private readonly tracer: ContextTracer,
|
||||
private readonly registry: SidecarRegistry,
|
||||
) {
|
||||
this.instantiateProcessors();
|
||||
this.instantiateWorkers();
|
||||
this.setupTriggers();
|
||||
}
|
||||
|
||||
private isNodeAllowed(
|
||||
node: ConcreteNode,
|
||||
triggerTargets: ReadonlySet<string>,
|
||||
protectedLogicalIds: ReadonlySet<string> = new Set(),
|
||||
): boolean {
|
||||
return (
|
||||
triggerTargets.has(node.id) &&
|
||||
!protectedLogicalIds.has(node.id) &&
|
||||
(!node.logicalParentId || !protectedLogicalIds.has(node.logicalParentId))
|
||||
);
|
||||
}
|
||||
|
||||
private instantiateProcessors() {
|
||||
for (const pipeline of this.config.pipelines) {
|
||||
for (const procDef of pipeline.processors) {
|
||||
if (!this.instantiatedProcessors.has(procDef.processorId)) {
|
||||
const factory = this.registry.getProcessor(procDef.processorId);
|
||||
const instance = factory.create(this.env, procDef.options || {});
|
||||
this.instantiatedProcessors.set(procDef.processorId, instance);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private instantiateWorkers() {
|
||||
if (!this.config.workers) return;
|
||||
for (const workerDef of this.config.workers) {
|
||||
if (!this.instantiatedWorkers.has(workerDef.workerId)) {
|
||||
const factory = this.registry.getWorker(workerDef.workerId);
|
||||
const instance = factory.create(this.env, workerDef.options || {});
|
||||
this.instantiatedWorkers.set(workerDef.workerId, instance);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private setupTriggers() {
|
||||
// 1. Pipeline Triggers
|
||||
for (const pipeline of this.config.pipelines) {
|
||||
for (const trigger of pipeline.triggers) {
|
||||
if (typeof trigger === 'object' && trigger.type === 'timer') {
|
||||
const timer = setInterval(() => {
|
||||
// Background timers not fully implemented in V1 yet
|
||||
}, trigger.intervalMs);
|
||||
this.activeTimers.push(timer);
|
||||
} else if (trigger === 'retained_exceeded') {
|
||||
this.eventBus.onConsolidationNeeded((event) => {
|
||||
void this.executePipelineAsync(
|
||||
pipeline,
|
||||
event.nodes,
|
||||
event.targetNodeIds,
|
||||
new Set(), // protected IDs
|
||||
);
|
||||
});
|
||||
} else if (trigger === 'new_message') {
|
||||
this.eventBus.onChunkReceived((event) => {
|
||||
void this.executePipelineAsync(
|
||||
pipeline,
|
||||
event.nodes,
|
||||
event.targetNodeIds,
|
||||
new Set(), // protected IDs
|
||||
);
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 2. Worker Triggers (onNodesAdded / onNodesAgedOut)
|
||||
this.eventBus.onChunkReceived((event) => {
|
||||
// Fire all workers that care about new nodes
|
||||
for (const worker of this.instantiatedWorkers.values()) {
|
||||
if (worker.triggers.onNodesAdded) {
|
||||
const inboxSnapshot = new InboxSnapshotImpl(
|
||||
this.env.inbox.getMessages() || [],
|
||||
);
|
||||
const targets = event.nodes.filter((n) =>
|
||||
event.targetNodeIds.has(n.id),
|
||||
);
|
||||
// Fire and forget
|
||||
worker.execute({ targets, inbox: inboxSnapshot }).catch((e) => {
|
||||
debugLogger.error(`Worker ${worker.name} failed onNodesAdded:`, e);
|
||||
});
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
this.eventBus.onConsolidationNeeded((event) => {
|
||||
// Fire all workers that care about aged out nodes
|
||||
for (const worker of this.instantiatedWorkers.values()) {
|
||||
if (worker.triggers.onNodesAgedOut) {
|
||||
const inboxSnapshot = new InboxSnapshotImpl(
|
||||
this.env.inbox.getMessages() || [],
|
||||
);
|
||||
const targets = event.nodes.filter((n) =>
|
||||
event.targetNodeIds.has(n.id),
|
||||
);
|
||||
// Fire and forget
|
||||
worker.execute({ targets, inbox: inboxSnapshot }).catch((e) => {
|
||||
debugLogger.error(
|
||||
`Worker ${worker.name} failed onNodesAgedOut:`,
|
||||
e,
|
||||
);
|
||||
});
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
// We don't have a formal event bus for inbox publish yet, but we will soon.
|
||||
// For now the workers are just registered.
|
||||
}
|
||||
|
||||
shutdown() {
|
||||
for (const timer of this.activeTimers) {
|
||||
clearInterval(timer);
|
||||
}
|
||||
}
|
||||
|
||||
async executeTriggerSync(
|
||||
trigger: PipelineTrigger,
|
||||
nodes: readonly ConcreteNode[],
|
||||
triggerTargets: ReadonlySet<string>,
|
||||
protectedLogicalIds: ReadonlySet<string> = new Set(),
|
||||
): Promise<readonly ConcreteNode[]> {
|
||||
let currentBuffer = ContextWorkingBufferImpl.initialize(nodes);
|
||||
const pipelines = this.config.pipelines.filter((p) =>
|
||||
p.triggers.includes(trigger),
|
||||
);
|
||||
|
||||
// Freeze the inbox for this pipeline run
|
||||
const inboxSnapshot = new InboxSnapshotImpl(
|
||||
this.env.inbox.getMessages() || [],
|
||||
);
|
||||
|
||||
for (const pipeline of pipelines) {
|
||||
for (const procDef of pipeline.processors) {
|
||||
const processor = this.instantiatedProcessors.get(procDef.processorId);
|
||||
if (!processor) continue;
|
||||
|
||||
try {
|
||||
this.tracer.logEvent(
|
||||
'Orchestrator',
|
||||
`Executing processor synchronously: ${procDef.processorId}`,
|
||||
);
|
||||
|
||||
const allowedTargets = currentBuffer.nodes.filter((n) =>
|
||||
this.isNodeAllowed(n, triggerTargets, protectedLogicalIds),
|
||||
);
|
||||
|
||||
const returnedNodes = await processor.process({
|
||||
buffer: currentBuffer,
|
||||
targets: allowedTargets,
|
||||
inbox: inboxSnapshot,
|
||||
});
|
||||
|
||||
currentBuffer = currentBuffer.applyProcessorResult(
|
||||
processor.id,
|
||||
allowedTargets,
|
||||
returnedNodes,
|
||||
);
|
||||
} catch (error) {
|
||||
debugLogger.error(
|
||||
`Synchronous processor ${procDef.processorId} failed:`,
|
||||
error,
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Success! Drain consumed messages
|
||||
this.env.inbox.drainConsumed(inboxSnapshot.getConsumedIds());
|
||||
|
||||
return currentBuffer.nodes;
|
||||
}
|
||||
|
||||
private async executePipelineAsync(
|
||||
pipeline: PipelineDef,
|
||||
nodes: readonly ConcreteNode[],
|
||||
triggerTargets: Set<string>,
|
||||
protectedLogicalIds: ReadonlySet<string> = new Set(),
|
||||
) {
|
||||
this.tracer.logEvent(
|
||||
'Orchestrator',
|
||||
`Triggering async pipeline: ${pipeline.name}`,
|
||||
);
|
||||
if (!nodes || nodes.length === 0) return;
|
||||
|
||||
let currentBuffer = ContextWorkingBufferImpl.initialize(nodes);
|
||||
const inboxSnapshot = new InboxSnapshotImpl(
|
||||
this.env.inbox.getMessages() || [],
|
||||
);
|
||||
|
||||
for (const procDef of pipeline.processors) {
|
||||
const processor = this.instantiatedProcessors.get(procDef.processorId);
|
||||
if (!processor) continue;
|
||||
|
||||
try {
|
||||
this.tracer.logEvent(
|
||||
'Orchestrator',
|
||||
`Executing processor: ${procDef.processorId} (async)`,
|
||||
);
|
||||
|
||||
const allowedTargets = currentBuffer.nodes.filter((n) =>
|
||||
this.isNodeAllowed(n, triggerTargets, protectedLogicalIds),
|
||||
);
|
||||
|
||||
const returnedNodes = await processor.process({
|
||||
buffer: currentBuffer,
|
||||
targets: allowedTargets,
|
||||
inbox: inboxSnapshot,
|
||||
});
|
||||
|
||||
currentBuffer = currentBuffer.applyProcessorResult(
|
||||
processor.id,
|
||||
allowedTargets,
|
||||
returnedNodes,
|
||||
);
|
||||
} catch (error) {
|
||||
debugLogger.error(
|
||||
`Pipeline ${pipeline.name} failed async at ${procDef.processorId}:`,
|
||||
error,
|
||||
);
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
this.env.inbox.drainConsumed(inboxSnapshot.getConsumedIds());
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,63 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { SidecarConfig } from './types.js';
|
||||
|
||||
/**
|
||||
* The standard default context management profile.
|
||||
* Optimized for safety, precision, and reliable summarization.
|
||||
*/
|
||||
export const defaultSidecarProfile: SidecarConfig = {
|
||||
budget: {
|
||||
retainedTokens: 65000,
|
||||
maxTokens: 150000,
|
||||
},
|
||||
workers: [
|
||||
{
|
||||
workerId: 'StateSnapshotWorker',
|
||||
options: {
|
||||
type: 'accumulate',
|
||||
},
|
||||
},
|
||||
],
|
||||
pipelines: [
|
||||
{
|
||||
name: 'Immediate Sanitization',
|
||||
triggers: ['new_message'],
|
||||
processors: [
|
||||
{
|
||||
processorId: 'ToolMaskingProcessor',
|
||||
options: { stringLengthThresholdTokens: 8000 },
|
||||
},
|
||||
{ processorId: 'BlobDegradationProcessor', options: {} },
|
||||
],
|
||||
},
|
||||
{
|
||||
name: 'Normalization',
|
||||
triggers: ['retained_exceeded'],
|
||||
processors: [
|
||||
{
|
||||
processorId: 'NodeTruncationProcessor',
|
||||
options: { maxTokensPerNode: 3000 },
|
||||
},
|
||||
{
|
||||
processorId: 'NodeDistillationProcessor',
|
||||
options: { nodeThresholdTokens: 5000 },
|
||||
},
|
||||
],
|
||||
},
|
||||
{
|
||||
name: 'Emergency Backstop',
|
||||
triggers: ['gc_backstop'],
|
||||
processors: [
|
||||
{
|
||||
processorId: 'StateSnapshotProcessor',
|
||||
options: { target: 'max' },
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
};
|
||||
@@ -0,0 +1,89 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { SidecarRegistry } from './registry.js';
|
||||
import type { ContextProcessorDef, ContextWorkerDef } from './registry.js';
|
||||
import type { ContextProcessor, ContextWorker } from '../pipeline.js';
|
||||
|
||||
describe('SidecarRegistry', () => {
|
||||
it('should register and retrieve processors correctly', () => {
|
||||
const registry = new SidecarRegistry();
|
||||
const processorDef: ContextProcessorDef = {
|
||||
id: 'TestProcessor',
|
||||
schema: { type: 'object' },
|
||||
create: () => ({}) as ContextProcessor,
|
||||
};
|
||||
|
||||
registry.registerProcessor(processorDef);
|
||||
const retrieved = registry.getProcessor('TestProcessor');
|
||||
expect(retrieved).toBe(processorDef);
|
||||
});
|
||||
|
||||
it('should register and retrieve workers correctly', () => {
|
||||
const registry = new SidecarRegistry();
|
||||
const workerDef: ContextWorkerDef = {
|
||||
id: 'TestWorker',
|
||||
schema: { type: 'object' },
|
||||
create: () => ({}) as ContextWorker,
|
||||
};
|
||||
|
||||
registry.registerWorker(workerDef);
|
||||
const retrieved = registry.getWorker('TestWorker');
|
||||
expect(retrieved).toBe(workerDef);
|
||||
});
|
||||
|
||||
it('should throw an error when retrieving unregistered processors', () => {
|
||||
const registry = new SidecarRegistry();
|
||||
expect(() => registry.getProcessor('Unknown')).toThrow(
|
||||
'Context Processor [Unknown] is not registered.',
|
||||
);
|
||||
});
|
||||
|
||||
it('should throw an error when retrieving unregistered workers', () => {
|
||||
const registry = new SidecarRegistry();
|
||||
expect(() => registry.getWorker('Unknown')).toThrow(
|
||||
'Context Worker [Unknown] is not registered.',
|
||||
);
|
||||
});
|
||||
|
||||
it('should return combined schemas', () => {
|
||||
const registry = new SidecarRegistry();
|
||||
registry.registerProcessor({
|
||||
id: 'TestProcessor',
|
||||
schema: { title: 'processorSchema' },
|
||||
create: () => ({}) as ContextProcessor,
|
||||
});
|
||||
registry.registerWorker({
|
||||
id: 'TestWorker',
|
||||
schema: { title: 'workerSchema' },
|
||||
create: () => ({}) as ContextWorker,
|
||||
});
|
||||
|
||||
const schemas = registry.getSchemas() as Array<{ title?: string }>;
|
||||
expect(schemas.length).toBe(2);
|
||||
expect(schemas.find((s) => s.title === 'processorSchema')).toBeDefined();
|
||||
expect(schemas.find((s) => s.title === 'workerSchema')).toBeDefined();
|
||||
});
|
||||
|
||||
it('should safely clear the registry', () => {
|
||||
const registry = new SidecarRegistry();
|
||||
registry.registerProcessor({
|
||||
id: 'TestProcessor',
|
||||
schema: {},
|
||||
create: () => ({}) as ContextProcessor,
|
||||
});
|
||||
registry.registerWorker({
|
||||
id: 'TestWorker',
|
||||
schema: {},
|
||||
create: () => ({}) as ContextWorker,
|
||||
});
|
||||
|
||||
registry.clear();
|
||||
|
||||
expect(() => registry.getProcessor('TestProcessor')).toThrow();
|
||||
expect(() => registry.getWorker('TestWorker')).toThrow();
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,68 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { ContextProcessor, ContextWorker } from '../pipeline.js';
|
||||
import type { ContextEnvironment } from './environment.js';
|
||||
|
||||
export interface ContextProcessorDef<TOptions = object> {
|
||||
readonly id: string;
|
||||
readonly schema: object;
|
||||
create(env: ContextEnvironment, options: TOptions): ContextProcessor;
|
||||
}
|
||||
|
||||
export interface ContextWorkerDef<TOptions = object> {
|
||||
readonly id: string;
|
||||
readonly schema: object;
|
||||
create(env: ContextEnvironment, options: TOptions): ContextWorker;
|
||||
}
|
||||
|
||||
/**
|
||||
* Registry for mapping declarative sidecar configs to running components.
|
||||
*/
|
||||
export class SidecarRegistry {
|
||||
private processors = new Map<string, ContextProcessorDef<unknown>>();
|
||||
private workers = new Map<string, ContextWorkerDef<unknown>>();
|
||||
|
||||
registerProcessor<TOptions>(def: ContextProcessorDef<TOptions>) {
|
||||
this.processors.set(def.id, def);
|
||||
}
|
||||
|
||||
registerWorker<TOptions>(def: ContextWorkerDef<TOptions>) {
|
||||
this.workers.set(def.id, def);
|
||||
}
|
||||
|
||||
getProcessor(id: string): ContextProcessorDef {
|
||||
const def = this.processors.get(id);
|
||||
if (!def) {
|
||||
throw new Error(`Context Processor [${id}] is not registered.`);
|
||||
}
|
||||
return def;
|
||||
}
|
||||
|
||||
getWorker(id: string): ContextWorkerDef {
|
||||
const def = this.workers.get(id);
|
||||
if (!def) {
|
||||
throw new Error(`Context Worker [${id}] is not registered.`);
|
||||
}
|
||||
return def;
|
||||
}
|
||||
|
||||
getSchemas(): object[] {
|
||||
const schemas: object[] = [];
|
||||
for (const def of this.processors.values()) {
|
||||
if (def.schema) schemas.push(def.schema);
|
||||
}
|
||||
for (const def of this.workers.values()) {
|
||||
if (def.schema) schemas.push(def.schema);
|
||||
}
|
||||
return schemas;
|
||||
}
|
||||
|
||||
clear() {
|
||||
this.processors.clear();
|
||||
this.workers.clear();
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,92 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { SidecarRegistry } from './registry.js';
|
||||
import './builtins.js';
|
||||
|
||||
export function getSidecarConfigSchema(registry: SidecarRegistry) {
|
||||
return {
|
||||
$schema: 'http://json-schema.org/draft-07/schema#',
|
||||
title: 'SidecarConfig',
|
||||
description: 'The Data-Driven Schema for the Context Manager.',
|
||||
type: 'object',
|
||||
required: ['budget', 'pipelines'],
|
||||
properties: {
|
||||
budget: {
|
||||
type: 'object',
|
||||
description: 'Defines the token ceilings and limits for the pipeline.',
|
||||
required: ['retainedTokens', 'maxTokens'],
|
||||
properties: {
|
||||
retainedTokens: {
|
||||
type: 'number',
|
||||
description:
|
||||
'The ideal token count the pipeline tries to shrink down to.',
|
||||
},
|
||||
maxTokens: {
|
||||
type: 'number',
|
||||
description:
|
||||
'The absolute maximum token count allowed before synchronous truncation kicks in.',
|
||||
},
|
||||
},
|
||||
},
|
||||
workers: {
|
||||
type: 'array',
|
||||
description: 'Background workers that proactively accumulate context.',
|
||||
items: {
|
||||
type: 'object',
|
||||
required: ['workerId'],
|
||||
properties: {
|
||||
workerId: { type: 'string' },
|
||||
options: { type: 'object' },
|
||||
},
|
||||
},
|
||||
},
|
||||
pipelines: {
|
||||
type: 'array',
|
||||
description: 'The execution graphs for context manipulation.',
|
||||
items: {
|
||||
type: 'object',
|
||||
required: ['name', 'triggers', 'execution', 'processors'],
|
||||
properties: {
|
||||
name: {
|
||||
type: 'string',
|
||||
},
|
||||
triggers: {
|
||||
type: 'array',
|
||||
items: {
|
||||
anyOf: [
|
||||
{
|
||||
type: 'string',
|
||||
enum: ['new_message', 'retained_exceeded', 'gc_backstop'],
|
||||
},
|
||||
{
|
||||
type: 'object',
|
||||
required: ['type', 'intervalMs'],
|
||||
properties: {
|
||||
type: {
|
||||
type: 'string',
|
||||
const: 'timer',
|
||||
},
|
||||
intervalMs: {
|
||||
type: 'number',
|
||||
},
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
processors: {
|
||||
type: 'array',
|
||||
items: {
|
||||
oneOf: registry.getSchemas(),
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
};
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user