mirror of
https://github.com/google-gemini/gemini-cli.git
synced 2026-07-23 16:20:57 -07:00
Compare commits
28 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| a0f32ff7d6 | |||
| 1693afe027 | |||
| d179e3673b | |||
| e4d6a5cc7c | |||
| fc4fdc3cbe | |||
| bdbb996a2e | |||
| 2d05396dd2 | |||
| 7b4a822b0e | |||
| d44615ac2f | |||
| de656f01d7 | |||
| 1d2585dba6 | |||
| 97bc3f28c5 | |||
| 3038fdce2e | |||
| bb060d7a98 | |||
| 9a73aa4072 | |||
| d7d53981f3 | |||
| 19e0b1ff7d | |||
| 4d393f9dca | |||
| 5abc170b08 | |||
| ceb4c5f6a7 | |||
| b6beab9480 | |||
| c2691f44b6 | |||
| 663d9c0537 | |||
| 4863816b81 | |||
| 829c532703 | |||
| c68303c553 | |||
| 7242d71c01 | |||
| 391715c33c |
@@ -1,6 +1,6 @@
|
||||
# Latest stable release: v0.33.0
|
||||
# Latest stable release: v0.33.1
|
||||
|
||||
Released: March 11, 2026
|
||||
Released: March 12, 2026
|
||||
|
||||
For most users, our latest stable release is the recommended release. Install
|
||||
the latest stable version with:
|
||||
@@ -29,6 +29,9 @@ npm install -g @google/gemini-cli
|
||||
|
||||
## What's Changed
|
||||
|
||||
- fix(patch): cherry-pick 8432bce to release/v0.33.0-pr-22069 to patch version
|
||||
v0.33.0 and create version 0.33.1 by @gemini-cli-robot in
|
||||
[#22206](https://github.com/google-gemini/gemini-cli/pull/22206)
|
||||
- Docs: Update model docs to remove Preview Features. by @jkcinouye in
|
||||
[#20084](https://github.com/google-gemini/gemini-cli/pull/20084)
|
||||
- docs: fix typo in installation documentation by @AdityaSharma-Git3207 in
|
||||
@@ -228,4 +231,4 @@ npm install -g @google/gemini-cli
|
||||
[#21952](https://github.com/google-gemini/gemini-cli/pull/21952)
|
||||
|
||||
**Full Changelog**:
|
||||
https://github.com/google-gemini/gemini-cli/compare/v0.32.1...v0.33.0
|
||||
https://github.com/google-gemini/gemini-cli/compare/v0.32.1...v0.33.1
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Preview release: v0.34.0-preview.0
|
||||
# Preview release: v0.34.0-preview.1
|
||||
|
||||
Released: March 11, 2026
|
||||
Released: March 12, 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).
|
||||
@@ -28,6 +28,9 @@ npm install -g @google/gemini-cli@preview
|
||||
|
||||
## What's Changed
|
||||
|
||||
- fix(patch): cherry-pick 45faf4d to release/v0.34.0-preview.0-pr-22148
|
||||
[CONFLICTS] by @gemini-cli-robot in
|
||||
[#22174](https://github.com/google-gemini/gemini-cli/pull/22174)
|
||||
- feat(cli): add chat resume footer on session quit by @lordshashank in
|
||||
[#20667](https://github.com/google-gemini/gemini-cli/pull/20667)
|
||||
- Support bold and other styles in svg snapshots by @jacob314 in
|
||||
@@ -465,4 +468,4 @@ npm install -g @google/gemini-cli@preview
|
||||
[#21938](https://github.com/google-gemini/gemini-cli/pull/21938)
|
||||
|
||||
**Full Changelog**:
|
||||
https://github.com/google-gemini/gemini-cli/compare/v0.33.0-preview.15...v0.34.0-preview.0
|
||||
https://github.com/google-gemini/gemini-cli/compare/v0.33.0-preview.15...v0.34.0-preview.1
|
||||
|
||||
@@ -26,6 +26,20 @@ policies.
|
||||
the CLI will use an available fallback model for the current turn or the
|
||||
remainder of the session.
|
||||
|
||||
### Local Model Routing (Experimental)
|
||||
|
||||
Gemini CLI supports using a local model for routing decisions. When configured,
|
||||
Gemini CLI will use a locally-running **Gemma** model to make routing decisions
|
||||
(instead of sending routing decisions to a hosted model). This feature can help
|
||||
reduce costs associated with hosted model usage while offering similar routing
|
||||
decision latency and quality.
|
||||
|
||||
In order to use this feature, the local Gemma model **must** be served behind a
|
||||
Gemini API and accessible via HTTP at an endpoint configured in `settings.json`.
|
||||
|
||||
For more details on how to configure local model routing, see
|
||||
[Local Model Routing](../core/local-model-routing.md).
|
||||
|
||||
### Model selection precedence
|
||||
|
||||
The model used by Gemini CLI is determined by the following order of precedence:
|
||||
@@ -38,5 +52,8 @@ The model used by Gemini CLI is determined by the following order of precedence:
|
||||
3. **`model.name` in `settings.json`:** If neither of the above are set, the
|
||||
model specified in the `model.name` property of your `settings.json` file
|
||||
will be used.
|
||||
4. **Default model:** If none of the above are set, the default model will be
|
||||
4. **Local model (experimental):** If the Gemma local model router is enabled
|
||||
in your `settings.json` file, the CLI will use the local Gemma model
|
||||
(instead of Gemini models) to route the request to an appropriate model.
|
||||
5. **Default model:** If none of the above are set, the default model will be
|
||||
used. The default model is `auto`
|
||||
|
||||
+71
-10
@@ -109,16 +109,6 @@ switch back to another mode.
|
||||
- **Keyboard shortcut:** Press `Shift+Tab` to cycle to the desired mode.
|
||||
- **Natural language:** Ask Gemini CLI to "exit plan mode" or "stop planning."
|
||||
|
||||
## Customization and best practices
|
||||
|
||||
Plan Mode is secure by default, but you can adapt it to fit your specific
|
||||
workflows. You can customize how Gemini CLI plans by using skills, adjusting
|
||||
safety policies, or changing where plans are stored.
|
||||
|
||||
## Commands
|
||||
|
||||
- **`/plan copy`**: Copy the currently approved plan to your clipboard.
|
||||
|
||||
## Tool Restrictions
|
||||
|
||||
Plan Mode enforces strict safety policies to prevent accidental changes.
|
||||
@@ -146,6 +136,12 @@ These are the only allowed tools:
|
||||
- **Skills:** [`activate_skill`](../cli/skills.md) (allows loading specialized
|
||||
instructions and resources in a read-only manner)
|
||||
|
||||
## Customization and best practices
|
||||
|
||||
Plan Mode is secure by default, but you can adapt it to fit your specific
|
||||
workflows. You can customize how Gemini CLI plans by using skills, adjusting
|
||||
safety policies, changing where plans are stored, or adding hooks.
|
||||
|
||||
### Custom planning with skills
|
||||
|
||||
You can use [Agent Skills](../cli/skills.md) to customize how Gemini CLI
|
||||
@@ -294,6 +290,71 @@ modes = ["plan"]
|
||||
argsPattern = "\"file_path\":\"[^\"]+[\\\\/]+\\.gemini[\\\\/]+plans[\\\\/]+[\\w-]+\\.md\""
|
||||
```
|
||||
|
||||
### Using hooks with Plan Mode
|
||||
|
||||
You can use the [hook system](../hooks/writing-hooks.md) to automate parts of
|
||||
the planning workflow or enforce additional checks when Gemini CLI transitions
|
||||
into or out of Plan Mode.
|
||||
|
||||
Hooks such as `BeforeTool` or `AfterTool` can be configured to intercept the
|
||||
`enter_plan_mode` and `exit_plan_mode` tool calls.
|
||||
|
||||
> [!WARNING] When hooks are triggered by **tool executions**, they do **not**
|
||||
> run when you manually toggle Plan Mode using the `/plan` command or the
|
||||
> `Shift+Tab` keyboard shortcut. If you need hooks to execute on mode changes,
|
||||
> ensure the transition is initiated by the agent (e.g., by asking "start a plan
|
||||
> for...").
|
||||
|
||||
#### Example: Archive approved plans to GCS (`AfterTool`)
|
||||
|
||||
If your organizational policy requires a record of all execution plans, you can
|
||||
use an `AfterTool` hook to securely copy the plan artifact to Google Cloud
|
||||
Storage whenever Gemini CLI exits Plan Mode to start the implementation.
|
||||
|
||||
**`.gemini/hooks/archive-plan.sh`:**
|
||||
|
||||
```bash
|
||||
#!/usr/bin/env bash
|
||||
# Extract the plan path from the tool input JSON
|
||||
plan_path=$(jq -r '.tool_input.plan_path // empty')
|
||||
|
||||
if [ -f "$plan_path" ]; then
|
||||
# Generate a unique filename using a timestamp
|
||||
filename="$(date +%s)_$(basename "$plan_path")"
|
||||
|
||||
# Upload the plan to GCS in the background so it doesn't block the CLI
|
||||
gsutil cp "$plan_path" "gs://my-audit-bucket/gemini-plans/$filename" > /dev/null 2>&1 &
|
||||
fi
|
||||
|
||||
# AfterTool hooks should generally allow the flow to continue
|
||||
echo '{"decision": "allow"}'
|
||||
```
|
||||
|
||||
To register this `AfterTool` hook, add it to your `settings.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"hooks": {
|
||||
"AfterTool": [
|
||||
{
|
||||
"matcher": "exit_plan_mode",
|
||||
"hooks": [
|
||||
{
|
||||
"name": "archive-plan",
|
||||
"type": "command",
|
||||
"command": "./.gemini/hooks/archive-plan.sh"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Commands
|
||||
|
||||
- **`/plan copy`**: Copy the currently approved plan to your clipboard.
|
||||
|
||||
## Planning workflows
|
||||
|
||||
Plan Mode provides building blocks for structured research and design. These are
|
||||
|
||||
@@ -55,6 +55,7 @@ they appear in the UI.
|
||||
| Show Home Directory Warning | `ui.showHomeDirectoryWarning` | Show a warning when running Gemini CLI in the home directory. | `true` |
|
||||
| Show Compatibility Warnings | `ui.showCompatibilityWarnings` | Show warnings about terminal or OS compatibility issues. | `true` |
|
||||
| Hide Tips | `ui.hideTips` | Hide helpful tips in the UI | `false` |
|
||||
| Escape Pasted @ Symbols | `ui.escapePastedAtSymbols` | When enabled, @ symbols in pasted text are escaped to prevent unintended @path expansion. | `false` |
|
||||
| Show Shortcuts Hint | `ui.showShortcutsHint` | Show the "? for shortcuts" hint above the input. | `true` |
|
||||
| Hide Banner | `ui.hideBanner` | Hide the application banner | `false` |
|
||||
| Hide Context Summary | `ui.hideContextSummary` | Hide the context summary (GEMINI.md, MCP servers) above the input. | `false` |
|
||||
|
||||
@@ -15,6 +15,8 @@ requests sent from `packages/cli`. For a general overview of Gemini CLI, see the
|
||||
modular GEMINI.md import feature using @file.md syntax.
|
||||
- **[Policy Engine](../reference/policy-engine.md):** Use the Policy Engine for
|
||||
fine-grained control over tool execution.
|
||||
- **[Local Model Routing (experimental)](./local-model-routing.md):** Learn how
|
||||
to enable use of a local Gemma model for model routing decisions.
|
||||
|
||||
## Role of the core
|
||||
|
||||
|
||||
@@ -0,0 +1,193 @@
|
||||
# Local Model Routing (experimental)
|
||||
|
||||
Gemini CLI supports using a local model for
|
||||
[routing decisions](../cli/model-routing.md). When configured, Gemini CLI will
|
||||
use a locally-running **Gemma** model to make routing decisions (instead of
|
||||
sending routing decisions to a hosted model).
|
||||
|
||||
This feature can help reduce costs associated with hosted model usage while
|
||||
offering similar routing decision latency and quality.
|
||||
|
||||
> **Note: Local model routing is currently an experimental feature.**
|
||||
|
||||
## Setup
|
||||
|
||||
Using a Gemma model for routing decisions requires that an implementation of a
|
||||
Gemma model be running locally on your machine, served behind an HTTP endpoint
|
||||
and accessed via the Gemini API.
|
||||
|
||||
To serve the Gemma model, follow these steps:
|
||||
|
||||
### Download the LiteRT-LM runtime
|
||||
|
||||
The [LiteRT-LM](https://github.com/google-ai-edge/LiteRT-LM) runtime offers
|
||||
pre-built binaries for locally-serving models. Download the binary appropriate
|
||||
for your system.
|
||||
|
||||
#### Windows
|
||||
|
||||
1. Download
|
||||
[lit.windows_x86_64.exe](https://github.com/google-ai-edge/LiteRT-LM/releases/download/v0.9.0-alpha03/lit.windows_x86_64.exe).
|
||||
2. Using GPU on Windows requires the DirectXShaderCompiler. Download the
|
||||
[dxc zip from the latest release](https://github.com/microsoft/DirectXShaderCompiler/releases/download/v1.8.2505.1/dxc_2025_07_14.zip).
|
||||
Unzip the archive and from the architecture-appropriate `bin\` directory, and
|
||||
copy the `dxil.dll` and `dxcompiler.dll` into the same location as you saved
|
||||
`lit.windows_x86_64.exe`.
|
||||
3. (Optional) Test starting the runtime:
|
||||
`.\lit.windows_x86_64.exe serve --verbose`
|
||||
|
||||
#### Linux
|
||||
|
||||
1. Download
|
||||
[lit.linux_x86_64](https://github.com/google-ai-edge/LiteRT-LM/releases/download/v0.9.0-alpha03/lit.linux_x86_64).
|
||||
2. Ensure the binary is executable: `chmod a+x lit.linux_x86_64`
|
||||
3. (Optional) Test starting the runtime: `./lit.linux_x86_64 serve --verbose`
|
||||
|
||||
#### MacOS
|
||||
|
||||
1. Download
|
||||
[lit-macos-arm64](https://github.com/google-ai-edge/LiteRT-LM/releases/download/v0.9.0-alpha03/lit.macos_arm64).
|
||||
2. Ensure the binary is executable: `chmod a+x lit.macos_arm64`
|
||||
3. (Optional) Test starting the runtime: `./lit.macos_arm64 serve --verbose`
|
||||
|
||||
> **Note**: MacOS can be configured to only allows binaries from "App Store &
|
||||
> Known Developers". If you encounter an error message when attempting to run
|
||||
> the binary, you will need to allow the application. One option is to visit
|
||||
> `System Settings -> Privacy & Security`, scroll to `Security`, and click
|
||||
> `"Allow Anyway"` for `"lit.macos_arm64"`. Another option is to run
|
||||
> `xattr -d com.apple.quarantine lit.macos_arm64` from the commandline.
|
||||
|
||||
### Download the Gemma Model
|
||||
|
||||
Before using Gemma, you will need to download the model (and agree to the Terms
|
||||
of Service).
|
||||
|
||||
This can be done via the LiteRT-LM runtime.
|
||||
|
||||
#### Windows
|
||||
|
||||
```bash
|
||||
$ .\lit.windows_x86_64.exe pull gemma3-1b-gpu-custom
|
||||
|
||||
[Legal] The model you are about to download is governed by
|
||||
the Gemma Terms of Use and Prohibited Use Policy. Please review these terms and ensure you agree before continuing.
|
||||
|
||||
Full Terms: https://ai.google.dev/gemma/terms
|
||||
Prohibited Use Policy: https://ai.google.dev/gemma/prohibited_use_policy
|
||||
|
||||
Do you accept these terms? (Y/N): Y
|
||||
|
||||
Terms accepted.
|
||||
Downloading model 'gemma3-1b-gpu-custom' ...
|
||||
Downloading... 968.6 MB
|
||||
Download complete.
|
||||
```
|
||||
|
||||
#### Linux
|
||||
|
||||
```bash
|
||||
$ ./lit.linux_x86_64 pull gemma3-1b-gpu-custom
|
||||
|
||||
[Legal] The model you are about to download is governed by
|
||||
the Gemma Terms of Use and Prohibited Use Policy. Please review these terms and ensure you agree before continuing.
|
||||
|
||||
Full Terms: https://ai.google.dev/gemma/terms
|
||||
Prohibited Use Policy: https://ai.google.dev/gemma/prohibited_use_policy
|
||||
|
||||
Do you accept these terms? (Y/N): Y
|
||||
|
||||
Terms accepted.
|
||||
Downloading model 'gemma3-1b-gpu-custom' ...
|
||||
Downloading... 968.6 MB
|
||||
Download complete.
|
||||
```
|
||||
|
||||
#### MacOS
|
||||
|
||||
```bash
|
||||
$ ./lit.lit.macos_arm64 pull gemma3-1b-gpu-custom
|
||||
|
||||
[Legal] The model you are about to download is governed by
|
||||
the Gemma Terms of Use and Prohibited Use Policy. Please review these terms and ensure you agree before continuing.
|
||||
|
||||
Full Terms: https://ai.google.dev/gemma/terms
|
||||
Prohibited Use Policy: https://ai.google.dev/gemma/prohibited_use_policy
|
||||
|
||||
Do you accept these terms? (Y/N): Y
|
||||
|
||||
Terms accepted.
|
||||
Downloading model 'gemma3-1b-gpu-custom' ...
|
||||
Downloading... 968.6 MB
|
||||
Download complete.
|
||||
```
|
||||
|
||||
### Start LiteRT-LM Runtime
|
||||
|
||||
Using the command appropriate to your system, start the LiteRT-LM runtime.
|
||||
Configure the port that you want to use for your Gemma model. For the purposes
|
||||
of this document, we will use port `9379`.
|
||||
|
||||
Example command for MacOS: `./lit.macos_arm64 serve --port=9379 --verbose`
|
||||
|
||||
### (Optional) Verify Model Serving
|
||||
|
||||
Send a quick prompt to the model via HTTP to validate successful model serving.
|
||||
This will cause the runtime to download the model and run it once.
|
||||
|
||||
You should see a short joke in the server output as an indicator of success.
|
||||
|
||||
#### Windows
|
||||
|
||||
```
|
||||
# Run this in PowerShell to send a request to the server
|
||||
|
||||
$uri = "http://localhost:9379/v1beta/models/gemma3-1b-gpu-custom:generateContent"
|
||||
$body = @{contents = @( @{
|
||||
role = "user"
|
||||
parts = @( @{ text = "Tell me a joke." } )
|
||||
})} | ConvertTo-Json -Depth 10
|
||||
|
||||
Invoke-RestMethod -Uri $uri -Method Post -Body $body -ContentType "application/json"
|
||||
```
|
||||
|
||||
#### Linux/MacOS
|
||||
|
||||
```bash
|
||||
$ curl "http://localhost:9379/v1beta/models/gemma3-1b-gpu-custom:generateContent" \
|
||||
-H 'Content-Type: application/json' \
|
||||
-X POST \
|
||||
-d '{"contents":[{"role":"user","parts":[{"text":"Tell me a joke."}]}]}'
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
To use a local Gemma model for routing, you must explicitly enable it in your
|
||||
`settings.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"experimental": {
|
||||
"gemmaModelRouter": {
|
||||
"enabled": true,
|
||||
"classifier": {
|
||||
"host": "http://localhost:9379",
|
||||
"model": "gemma3-1b-gpu-custom"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
> Use the port you started your LiteRT-LM runtime on in the setup steps.
|
||||
|
||||
### Configuration schema
|
||||
|
||||
| Field | Type | Required | Description |
|
||||
| :----------------- | :------ | :------- | :----------------------------------------------------------------------------------------- |
|
||||
| `enabled` | boolean | Yes | Must be `true` to enable the feature. |
|
||||
| `classifier` | object | Yes | The configuration for the local model endpoint. It includes the host and model specifiers. |
|
||||
| `classifier.host` | string | Yes | The URL to the local model server. Should be `http://localhost:<port>`. |
|
||||
| `classifier.model` | string | Yes | The model name to use for decisions. Must be `"gemma3-1b-gpu-custom"`. |
|
||||
|
||||
> **Note: You will need to restart after configuration changes for local model
|
||||
> routing to take effect.**
|
||||
@@ -245,6 +245,11 @@ their corresponding top-level category object in your `settings.json` file.
|
||||
- **Description:** Hide helpful tips in the UI
|
||||
- **Default:** `false`
|
||||
|
||||
- **`ui.escapePastedAtSymbols`** (boolean):
|
||||
- **Description:** When enabled, @ symbols in pasted text are escaped to
|
||||
prevent unintended @path expansion.
|
||||
- **Default:** `false`
|
||||
|
||||
- **`ui.showShortcutsHint`** (boolean):
|
||||
- **Description:** Show the "? for shortcuts" hint above the input.
|
||||
- **Default:** `true`
|
||||
@@ -672,6 +677,141 @@ their corresponding top-level category object in your `settings.json` file.
|
||||
used.
|
||||
- **Default:** `[]`
|
||||
|
||||
- **`modelConfigs.modelDefinitions`** (object):
|
||||
- **Description:** Registry of model metadata, including tier, family, and
|
||||
features.
|
||||
- **Default:**
|
||||
|
||||
```json
|
||||
{
|
||||
"gemini-3.1-pro-preview": {
|
||||
"tier": "pro",
|
||||
"family": "gemini-3",
|
||||
"isPreview": true,
|
||||
"dialogLocation": "manual",
|
||||
"features": {
|
||||
"thinking": true,
|
||||
"multimodalToolUse": true
|
||||
}
|
||||
},
|
||||
"gemini-3.1-pro-preview-customtools": {
|
||||
"tier": "pro",
|
||||
"family": "gemini-3",
|
||||
"isPreview": true,
|
||||
"features": {
|
||||
"thinking": true,
|
||||
"multimodalToolUse": true
|
||||
}
|
||||
},
|
||||
"gemini-3-pro-preview": {
|
||||
"tier": "pro",
|
||||
"family": "gemini-3",
|
||||
"isPreview": true,
|
||||
"dialogLocation": "manual",
|
||||
"features": {
|
||||
"thinking": true,
|
||||
"multimodalToolUse": true
|
||||
}
|
||||
},
|
||||
"gemini-3-flash-preview": {
|
||||
"tier": "flash",
|
||||
"family": "gemini-3",
|
||||
"isPreview": true,
|
||||
"dialogLocation": "manual",
|
||||
"features": {
|
||||
"thinking": false,
|
||||
"multimodalToolUse": true
|
||||
}
|
||||
},
|
||||
"gemini-2.5-pro": {
|
||||
"tier": "pro",
|
||||
"family": "gemini-2.5",
|
||||
"isPreview": false,
|
||||
"dialogLocation": "manual",
|
||||
"features": {
|
||||
"thinking": false,
|
||||
"multimodalToolUse": false
|
||||
}
|
||||
},
|
||||
"gemini-2.5-flash": {
|
||||
"tier": "flash",
|
||||
"family": "gemini-2.5",
|
||||
"isPreview": false,
|
||||
"dialogLocation": "manual",
|
||||
"features": {
|
||||
"thinking": false,
|
||||
"multimodalToolUse": false
|
||||
}
|
||||
},
|
||||
"gemini-2.5-flash-lite": {
|
||||
"tier": "flash-lite",
|
||||
"family": "gemini-2.5",
|
||||
"isPreview": false,
|
||||
"dialogLocation": "manual",
|
||||
"features": {
|
||||
"thinking": false,
|
||||
"multimodalToolUse": false
|
||||
}
|
||||
},
|
||||
"auto": {
|
||||
"tier": "auto",
|
||||
"isPreview": true,
|
||||
"features": {
|
||||
"thinking": true,
|
||||
"multimodalToolUse": false
|
||||
}
|
||||
},
|
||||
"pro": {
|
||||
"tier": "pro",
|
||||
"isPreview": false,
|
||||
"features": {
|
||||
"thinking": true,
|
||||
"multimodalToolUse": false
|
||||
}
|
||||
},
|
||||
"flash": {
|
||||
"tier": "flash",
|
||||
"isPreview": false,
|
||||
"features": {
|
||||
"thinking": false,
|
||||
"multimodalToolUse": false
|
||||
}
|
||||
},
|
||||
"flash-lite": {
|
||||
"tier": "flash-lite",
|
||||
"isPreview": false,
|
||||
"features": {
|
||||
"thinking": false,
|
||||
"multimodalToolUse": false
|
||||
}
|
||||
},
|
||||
"auto-gemini-3": {
|
||||
"displayName": "Auto (Gemini 3)",
|
||||
"tier": "auto",
|
||||
"isPreview": true,
|
||||
"dialogLocation": "main",
|
||||
"dialogDescription": "Let Gemini CLI decide the best model for the task: gemini-3.1-pro, gemini-3-flash",
|
||||
"features": {
|
||||
"thinking": true,
|
||||
"multimodalToolUse": false
|
||||
}
|
||||
},
|
||||
"auto-gemini-2.5": {
|
||||
"displayName": "Auto (Gemini 2.5)",
|
||||
"tier": "auto",
|
||||
"isPreview": false,
|
||||
"dialogLocation": "main",
|
||||
"dialogDescription": "Let Gemini CLI decide the best model for the task: gemini-2.5-pro, gemini-2.5-flash",
|
||||
"features": {
|
||||
"thinking": false,
|
||||
"multimodalToolUse": false
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
- **Requires restart:** Yes
|
||||
|
||||
#### `agents`
|
||||
|
||||
- **`agents.overrides`** (object):
|
||||
@@ -1063,6 +1203,12 @@ their corresponding top-level category object in your `settings.json` file.
|
||||
- **Default:** `false`
|
||||
- **Requires restart:** Yes
|
||||
|
||||
- **`experimental.dynamicModelConfiguration`** (boolean):
|
||||
- **Description:** Enable dynamic model configuration (definitions,
|
||||
resolutions, and chains) via settings.
|
||||
- **Default:** `false`
|
||||
- **Requires restart:** Yes
|
||||
|
||||
- **`experimental.gemmaModelRouter.enabled`** (boolean):
|
||||
- **Description:** Enable the Gemma Model Router (experimental). Requires a
|
||||
local endpoint serving Gemma via the Gemini API using LiteRT-LM shim.
|
||||
|
||||
@@ -342,7 +342,9 @@ policies, as it is much more robust than manually writing Fully Qualified Names
|
||||
|
||||
**1. Targeting a specific tool on a server**
|
||||
|
||||
Combine `mcpName` and `toolName` to target a single operation.
|
||||
Combine `mcpName` and `toolName` to target a single operation. When using
|
||||
`mcpName`, the `toolName` field should strictly be the simple name of the tool
|
||||
(e.g., `search`), **not** the Fully Qualified Name (e.g., `mcp_server_search`).
|
||||
|
||||
```toml
|
||||
# Allows the `search` tool on the `my-jira-server` MCP
|
||||
|
||||
@@ -120,6 +120,14 @@ tools to detect if they are being run from within the Gemini CLI.
|
||||
|
||||
## Command restrictions
|
||||
|
||||
<!-- prettier-ignore -->
|
||||
> [!WARNING]
|
||||
> The `tools.core` setting is an **allowlist for _all_ built-in
|
||||
> tools**, not just shell commands. When you set `tools.core` to any value,
|
||||
> _only_ the tools explicitly listed will be enabled. This includes all built-in
|
||||
> tools like `read_file`, `write_file`, `glob`, `grep_search`, `list_directory`,
|
||||
> `replace`, etc.
|
||||
|
||||
You can restrict the commands that can be executed by the `run_shell_command`
|
||||
tool by using the `tools.core` and `tools.exclude` settings in your
|
||||
configuration file.
|
||||
|
||||
+9
-4
@@ -82,11 +82,14 @@ const commonAliases = {
|
||||
const cliConfig = {
|
||||
...baseConfig,
|
||||
banner: {
|
||||
js: `const require = (await import('node:module')).createRequire(import.meta.url); globalThis.__filename = (await import('node:url')).fileURLToPath(import.meta.url); globalThis.__dirname = (await import('node:path')).dirname(globalThis.__filename);`,
|
||||
js: `const require = (await import('node:module')).createRequire(import.meta.url); const __chunk_filename = (await import('node:url')).fileURLToPath(import.meta.url); const __chunk_dirname = (await import('node:path')).dirname(__chunk_filename);`,
|
||||
},
|
||||
entryPoints: ['packages/cli/index.ts'],
|
||||
outfile: 'bundle/gemini.js',
|
||||
entryPoints: { gemini: 'packages/cli/index.ts' },
|
||||
outdir: 'bundle',
|
||||
splitting: true,
|
||||
define: {
|
||||
__filename: '__chunk_filename',
|
||||
__dirname: '__chunk_dirname',
|
||||
'process.env.CLI_VERSION': JSON.stringify(pkg.version),
|
||||
'process.env.GEMINI_SANDBOX_IMAGE_DEFAULT': JSON.stringify(
|
||||
pkg.config?.sandboxImageUri,
|
||||
@@ -103,11 +106,13 @@ const cliConfig = {
|
||||
const a2aServerConfig = {
|
||||
...baseConfig,
|
||||
banner: {
|
||||
js: `const require = (await import('node:module')).createRequire(import.meta.url); globalThis.__filename = (await import('node:url')).fileURLToPath(import.meta.url); globalThis.__dirname = (await import('node:path')).dirname(globalThis.__filename);`,
|
||||
js: `const require = (await import('node:module')).createRequire(import.meta.url); const __chunk_filename = (await import('node:url')).fileURLToPath(import.meta.url); const __chunk_dirname = (await import('node:path')).dirname(__chunk_filename);`,
|
||||
},
|
||||
entryPoints: ['packages/a2a-server/src/http/server.ts'],
|
||||
outfile: 'packages/a2a-server/dist/a2a-server.mjs',
|
||||
define: {
|
||||
__filename: '__chunk_filename',
|
||||
__dirname: '__chunk_dirname',
|
||||
'process.env.CLI_VERSION': JSON.stringify(pkg.version),
|
||||
},
|
||||
plugins: createWasmPlugins(),
|
||||
|
||||
@@ -35,11 +35,6 @@ const commonRestrictedSyntaxRules = [
|
||||
message:
|
||||
'Do not throw string literals or non-Error objects. Throw new Error("...") instead.',
|
||||
},
|
||||
{
|
||||
selector: 'CallExpression[callee.name="fetch"]',
|
||||
message:
|
||||
'Use safeFetch() from "@/utils/fetch" instead of the global fetch() to ensure SSRF protection. If you are implementing a custom security layer, use an eslint-disable comment and explain why.',
|
||||
},
|
||||
];
|
||||
|
||||
export default tseslint.config(
|
||||
|
||||
@@ -26,7 +26,7 @@ describe('Task Event-Driven Scheduler', () => {
|
||||
mockConfig = createMockConfig({
|
||||
isEventDrivenSchedulerEnabled: () => true,
|
||||
}) as Config;
|
||||
messageBus = mockConfig.getMessageBus();
|
||||
messageBus = mockConfig.messageBus;
|
||||
mockEventBus = {
|
||||
publish: vi.fn(),
|
||||
on: vi.fn(),
|
||||
@@ -360,7 +360,7 @@ describe('Task Event-Driven Scheduler', () => {
|
||||
isEventDrivenSchedulerEnabled: () => true,
|
||||
getApprovalMode: () => ApprovalMode.YOLO,
|
||||
}) as Config;
|
||||
const yoloMessageBus = yoloConfig.getMessageBus();
|
||||
const yoloMessageBus = yoloConfig.messageBus;
|
||||
|
||||
// @ts-expect-error - Calling private constructor
|
||||
const task = new Task('task-id', 'context-id', yoloConfig, mockEventBus);
|
||||
|
||||
@@ -5,6 +5,7 @@
|
||||
*/
|
||||
|
||||
import {
|
||||
type AgentLoopContext,
|
||||
Scheduler,
|
||||
type GeminiClient,
|
||||
GeminiEventType,
|
||||
@@ -114,7 +115,8 @@ export class Task {
|
||||
|
||||
this.scheduler = this.setupEventDrivenScheduler();
|
||||
|
||||
this.geminiClient = this.config.getGeminiClient();
|
||||
const loopContext: AgentLoopContext = this.config;
|
||||
this.geminiClient = loopContext.geminiClient;
|
||||
this.pendingToolConfirmationDetails = new Map();
|
||||
this.taskState = 'submitted';
|
||||
this.eventBus = eventBus;
|
||||
@@ -143,7 +145,8 @@ export class Task {
|
||||
// process. This is not scoped to the individual task but reflects the global connection
|
||||
// state managed within the @gemini-cli/core module.
|
||||
async getMetadata(): Promise<TaskMetadata> {
|
||||
const toolRegistry = this.config.getToolRegistry();
|
||||
const loopContext: AgentLoopContext = this.config;
|
||||
const toolRegistry = loopContext.toolRegistry;
|
||||
const mcpServers = this.config.getMcpClientManager()?.getMcpServers() || {};
|
||||
const serverStatuses = getAllMCPServerStatuses();
|
||||
const servers = Object.keys(mcpServers).map((serverName) => ({
|
||||
@@ -376,7 +379,8 @@ export class Task {
|
||||
private messageBusListener?: (message: ToolCallsUpdateMessage) => void;
|
||||
|
||||
private setupEventDrivenScheduler(): Scheduler {
|
||||
const messageBus = this.config.getMessageBus();
|
||||
const loopContext: AgentLoopContext = this.config;
|
||||
const messageBus = loopContext.messageBus;
|
||||
const scheduler = new Scheduler({
|
||||
schedulerId: this.id,
|
||||
context: this.config,
|
||||
@@ -395,9 +399,11 @@ export class Task {
|
||||
|
||||
dispose(): void {
|
||||
if (this.messageBusListener) {
|
||||
this.config
|
||||
.getMessageBus()
|
||||
.unsubscribe(MessageBusType.TOOL_CALLS_UPDATE, this.messageBusListener);
|
||||
const loopContext: AgentLoopContext = this.config;
|
||||
loopContext.messageBus.unsubscribe(
|
||||
MessageBusType.TOOL_CALLS_UPDATE,
|
||||
this.messageBusListener,
|
||||
);
|
||||
this.messageBusListener = undefined;
|
||||
}
|
||||
|
||||
@@ -948,7 +954,8 @@ export class Task {
|
||||
|
||||
try {
|
||||
if (correlationId) {
|
||||
await this.config.getMessageBus().publish({
|
||||
const loopContext: AgentLoopContext = this.config;
|
||||
await loopContext.messageBus.publish({
|
||||
type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
|
||||
correlationId,
|
||||
confirmed:
|
||||
|
||||
@@ -59,6 +59,9 @@ describe('a2a-server memory commands', () => {
|
||||
} as unknown as ToolRegistry;
|
||||
|
||||
mockConfig = {
|
||||
get toolRegistry() {
|
||||
return mockToolRegistry;
|
||||
},
|
||||
getToolRegistry: vi.fn().mockReturnValue(mockToolRegistry),
|
||||
} as unknown as Config;
|
||||
|
||||
@@ -168,7 +171,6 @@ describe('a2a-server memory commands', () => {
|
||||
]);
|
||||
|
||||
expect(mockAddMemory).toHaveBeenCalledWith(fact);
|
||||
expect(mockConfig.getToolRegistry).toHaveBeenCalled();
|
||||
expect(mockToolRegistry.getTool).toHaveBeenCalledWith('save_memory');
|
||||
expect(mockSaveMemoryTool.buildAndExecute).toHaveBeenCalledWith(
|
||||
{ fact },
|
||||
|
||||
@@ -15,6 +15,7 @@ import type {
|
||||
CommandContext,
|
||||
CommandExecutionResponse,
|
||||
} from './types.js';
|
||||
import type { AgentLoopContext } from '@google/gemini-cli-core';
|
||||
|
||||
const DEFAULT_SANITIZATION_CONFIG = {
|
||||
allowedEnvironmentVariables: [],
|
||||
@@ -95,7 +96,8 @@ export class AddMemoryCommand implements Command {
|
||||
return { name: this.name, data: result.content };
|
||||
}
|
||||
|
||||
const toolRegistry = context.config.getToolRegistry();
|
||||
const loopContext: AgentLoopContext = context.config;
|
||||
const toolRegistry = loopContext.toolRegistry;
|
||||
const tool = toolRegistry.getTool(result.toolName);
|
||||
if (tool) {
|
||||
const abortController = new AbortController();
|
||||
|
||||
@@ -16,6 +16,7 @@ import {
|
||||
DEFAULT_TRUNCATE_TOOL_OUTPUT_THRESHOLD,
|
||||
GeminiClient,
|
||||
HookSystem,
|
||||
type MessageBus,
|
||||
PolicyDecision,
|
||||
tmpdir,
|
||||
type Config,
|
||||
@@ -31,9 +32,27 @@ export function createMockConfig(
|
||||
const tmpDir = tmpdir();
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
const mockConfig = {
|
||||
get toolRegistry(): ToolRegistry {
|
||||
get config() {
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
return (this as unknown as Config).getToolRegistry();
|
||||
return this as unknown as Config;
|
||||
},
|
||||
get toolRegistry() {
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
const config = this as unknown as Config;
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
return config.getToolRegistry?.() as unknown as ToolRegistry;
|
||||
},
|
||||
get messageBus() {
|
||||
return (
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
(this as unknown as Config).getMessageBus?.() as unknown as MessageBus
|
||||
);
|
||||
},
|
||||
get geminiClient() {
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
const config = this as unknown as Config;
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
return config.getGeminiClient?.() as unknown as GeminiClient;
|
||||
},
|
||||
getToolRegistry: vi.fn().mockReturnValue({
|
||||
getTool: vi.fn(),
|
||||
@@ -81,9 +100,6 @@ export function createMockConfig(
|
||||
...overrides,
|
||||
} as unknown as Config;
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
(mockConfig as unknown as { config: Config; promptId: string }).config =
|
||||
mockConfig;
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
(mockConfig as unknown as { config: Config; promptId: string }).promptId =
|
||||
'test-prompt-id';
|
||||
|
||||
@@ -3632,6 +3632,8 @@ describe('loadCliConfig acpMode and clientName', () => {
|
||||
it('should set acpMode to true and detect clientName when --acp flag is used', async () => {
|
||||
process.argv = ['node', 'script.js', '--acp'];
|
||||
vi.stubEnv('TERM_PROGRAM', 'vscode');
|
||||
vi.stubEnv('VSCODE_GIT_ASKPASS_MAIN', '');
|
||||
vi.stubEnv('ANTIGRAVITY_CLI_ALIAS', '');
|
||||
const argv = await parseArguments(createTestMergedSettings());
|
||||
const config = await loadCliConfig(
|
||||
createTestMergedSettings(),
|
||||
@@ -3645,6 +3647,8 @@ describe('loadCliConfig acpMode and clientName', () => {
|
||||
it('should set acpMode to true but leave clientName undefined for generic terminals', async () => {
|
||||
process.argv = ['node', 'script.js', '--acp'];
|
||||
vi.stubEnv('TERM_PROGRAM', 'iTerm.app'); // Generic terminal
|
||||
vi.stubEnv('VSCODE_GIT_ASKPASS_MAIN', '');
|
||||
vi.stubEnv('ANTIGRAVITY_CLI_ALIAS', '');
|
||||
const argv = await parseArguments(createTestMergedSettings());
|
||||
const config = await loadCliConfig(
|
||||
createTestMergedSettings(),
|
||||
|
||||
@@ -857,6 +857,7 @@ export async function loadCliConfig(
|
||||
disableLLMCorrection: settings.tools?.disableLLMCorrection,
|
||||
rawOutput: argv.rawOutput,
|
||||
acceptRawOutputRisk: argv.acceptRawOutputRisk,
|
||||
dynamicModelConfiguration: settings.experimental?.dynamicModelConfiguration,
|
||||
modelConfigServiceConfig: settings.modelConfigs,
|
||||
// TODO: loading of hooks based on workspace trust
|
||||
enableHooks: settings.hooksConfig.enabled,
|
||||
|
||||
@@ -540,6 +540,16 @@ const SETTINGS_SCHEMA = {
|
||||
description: 'Hide helpful tips in the UI',
|
||||
showInDialog: true,
|
||||
},
|
||||
escapePastedAtSymbols: {
|
||||
type: 'boolean',
|
||||
label: 'Escape Pasted @ Symbols',
|
||||
category: 'UI',
|
||||
requiresRestart: false,
|
||||
default: false,
|
||||
description:
|
||||
'When enabled, @ symbols in pasted text are escaped to prevent unintended @path expansion.',
|
||||
showInDialog: true,
|
||||
},
|
||||
showShortcutsHint: {
|
||||
type: 'boolean',
|
||||
label: 'Show Shortcuts Hint',
|
||||
@@ -1029,6 +1039,20 @@ const SETTINGS_SCHEMA = {
|
||||
'Apply specific configuration overrides based on matches, with a primary key of model (or alias). The most specific match will be used.',
|
||||
showInDialog: false,
|
||||
},
|
||||
modelDefinitions: {
|
||||
type: 'object',
|
||||
label: 'Model Definitions',
|
||||
category: 'Model',
|
||||
requiresRestart: true,
|
||||
default: DEFAULT_MODEL_CONFIGS.modelDefinitions,
|
||||
description:
|
||||
'Registry of model metadata, including tier, family, and features.',
|
||||
showInDialog: false,
|
||||
additionalProperties: {
|
||||
type: 'object',
|
||||
ref: 'ModelDefinition',
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
|
||||
@@ -1900,6 +1924,16 @@ const SETTINGS_SCHEMA = {
|
||||
'Enable web fetch behavior that bypasses LLM summarization.',
|
||||
showInDialog: true,
|
||||
},
|
||||
dynamicModelConfiguration: {
|
||||
type: 'boolean',
|
||||
label: 'Dynamic Model Configuration',
|
||||
category: 'Experimental',
|
||||
requiresRestart: true,
|
||||
default: false,
|
||||
description:
|
||||
'Enable dynamic model configuration (definitions, resolutions, and chains) via settings.',
|
||||
showInDialog: false,
|
||||
},
|
||||
gemmaModelRouter: {
|
||||
type: 'object',
|
||||
label: 'Gemma Model Router',
|
||||
@@ -2716,6 +2750,25 @@ export const SETTINGS_SCHEMA_DEFINITIONS: Record<
|
||||
},
|
||||
},
|
||||
},
|
||||
ModelDefinition: {
|
||||
type: 'object',
|
||||
description: 'Model metadata registry entry.',
|
||||
properties: {
|
||||
displayName: { type: 'string' },
|
||||
tier: { enum: ['pro', 'flash', 'flash-lite', 'custom', 'auto'] },
|
||||
family: { type: 'string' },
|
||||
isPreview: { type: 'boolean' },
|
||||
dialogLocation: { enum: ['main', 'manual'] },
|
||||
dialogDescription: { type: 'string' },
|
||||
features: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
thinking: { type: 'boolean' },
|
||||
multimodalToolUse: { type: 'boolean' },
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
export function getSettingsSchema(): SettingsSchemaType {
|
||||
|
||||
+38
-217
@@ -4,13 +4,38 @@
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import React from 'react';
|
||||
import { render } from 'ink';
|
||||
import { AppContainer } from './ui/AppContainer.js';
|
||||
import {
|
||||
type StartupWarning,
|
||||
WarningPriority,
|
||||
type Config,
|
||||
type ResumedSessionData,
|
||||
type OutputPayload,
|
||||
type ConsoleLogPayload,
|
||||
type UserFeedbackPayload,
|
||||
sessionId,
|
||||
logUserPrompt,
|
||||
AuthType,
|
||||
UserPromptEvent,
|
||||
coreEvents,
|
||||
CoreEvent,
|
||||
getOauthClient,
|
||||
patchStdio,
|
||||
writeToStdout,
|
||||
writeToStderr,
|
||||
shouldEnterAlternateScreen,
|
||||
startupProfiler,
|
||||
ExitCodes,
|
||||
SessionStartSource,
|
||||
SessionEndReason,
|
||||
ValidationCancelledError,
|
||||
ValidationRequiredError,
|
||||
type AdminControlsSettings,
|
||||
debugLogger,
|
||||
} from '@google/gemini-cli-core';
|
||||
|
||||
import { loadCliConfig, parseArguments } from './config/config.js';
|
||||
import * as cliConfig from './config/config.js';
|
||||
import { readStdin } from './utils/readStdin.js';
|
||||
import { basename } from 'node:path';
|
||||
import { createHash } from 'node:crypto';
|
||||
import v8 from 'node:v8';
|
||||
import os from 'node:os';
|
||||
@@ -37,47 +62,11 @@ import {
|
||||
runExitCleanup,
|
||||
registerTelemetryConfig,
|
||||
setupSignalHandlers,
|
||||
setupTtyCheck,
|
||||
} from './utils/cleanup.js';
|
||||
import {
|
||||
cleanupToolOutputFiles,
|
||||
cleanupExpiredSessions,
|
||||
} from './utils/sessionCleanup.js';
|
||||
import {
|
||||
type StartupWarning,
|
||||
WarningPriority,
|
||||
type Config,
|
||||
type ResumedSessionData,
|
||||
type OutputPayload,
|
||||
type ConsoleLogPayload,
|
||||
type UserFeedbackPayload,
|
||||
sessionId,
|
||||
logUserPrompt,
|
||||
AuthType,
|
||||
getOauthClient,
|
||||
UserPromptEvent,
|
||||
debugLogger,
|
||||
recordSlowRender,
|
||||
coreEvents,
|
||||
CoreEvent,
|
||||
createWorkingStdio,
|
||||
patchStdio,
|
||||
writeToStdout,
|
||||
writeToStderr,
|
||||
disableMouseEvents,
|
||||
enableMouseEvents,
|
||||
disableLineWrapping,
|
||||
enableLineWrapping,
|
||||
shouldEnterAlternateScreen,
|
||||
startupProfiler,
|
||||
ExitCodes,
|
||||
SessionStartSource,
|
||||
SessionEndReason,
|
||||
getVersion,
|
||||
ValidationCancelledError,
|
||||
ValidationRequiredError,
|
||||
type AdminControlsSettings,
|
||||
} from '@google/gemini-cli-core';
|
||||
import {
|
||||
initializeApp,
|
||||
type InitializationResult,
|
||||
@@ -85,21 +74,9 @@ import {
|
||||
import { validateAuthMethod } from './config/auth.js';
|
||||
import { runAcpClient } from './acp/acpClient.js';
|
||||
import { validateNonInteractiveAuth } from './validateNonInterActiveAuth.js';
|
||||
import { checkForUpdates } from './ui/utils/updateCheck.js';
|
||||
import { handleAutoUpdate } from './utils/handleAutoUpdate.js';
|
||||
import { appEvents, AppEvent } from './utils/events.js';
|
||||
import { SessionError, SessionSelector } from './utils/sessionUtils.js';
|
||||
import { SettingsContext } from './ui/contexts/SettingsContext.js';
|
||||
import { MouseProvider } from './ui/contexts/MouseContext.js';
|
||||
import { StreamingState } from './ui/types.js';
|
||||
import { computeTerminalTitle } from './utils/windowTitle.js';
|
||||
|
||||
import { SessionStatsProvider } from './ui/contexts/SessionContext.js';
|
||||
import { VimModeProvider } from './ui/contexts/VimModeContext.js';
|
||||
import { KeyMatchersProvider } from './ui/hooks/useKeyMatchers.js';
|
||||
import { loadKeyMatchers } from './ui/key/keyMatchers.js';
|
||||
import { KeypressProvider } from './ui/contexts/KeypressContext.js';
|
||||
import { useKittyKeyboardProtocol } from './ui/hooks/useKittyKeyboardProtocol.js';
|
||||
import {
|
||||
relaunchAppInChildProcess,
|
||||
relaunchOnExitCode,
|
||||
@@ -107,19 +84,13 @@ import {
|
||||
import { loadSandboxConfig } from './config/sandboxConfig.js';
|
||||
import { deleteSession, listSessions } from './utils/sessions.js';
|
||||
import { createPolicyUpdater } from './config/policy.js';
|
||||
import { ScrollProvider } from './ui/contexts/ScrollProvider.js';
|
||||
import { TerminalProvider } from './ui/contexts/TerminalContext.js';
|
||||
import { isAlternateBufferEnabled } from './ui/hooks/useAlternateBuffer.js';
|
||||
import { OverflowProvider } from './ui/contexts/OverflowContext.js';
|
||||
|
||||
import { setupTerminalAndTheme } from './utils/terminalTheme.js';
|
||||
import { profiler } from './ui/components/DebugProfiler.js';
|
||||
import { runDeferredCommand } from './deferred.js';
|
||||
import { cleanupBackgroundLogs } from './utils/logCleanup.js';
|
||||
import { SlashCommandConflictHandler } from './services/SlashCommandConflictHandler.js';
|
||||
|
||||
const SLOW_RENDER_MS = 200;
|
||||
|
||||
export function validateDnsResolutionOrder(
|
||||
order: string | undefined,
|
||||
): DnsResolutionOrder {
|
||||
@@ -198,147 +169,16 @@ export async function startInteractiveUI(
|
||||
resumedSessionData: ResumedSessionData | undefined,
|
||||
initializationResult: InitializationResult,
|
||||
) {
|
||||
// Never enter Ink alternate buffer mode when screen reader mode is enabled
|
||||
// as there is no benefit of alternate buffer mode when using a screen reader
|
||||
// and the Ink alternate buffer mode requires line wrapping harmful to
|
||||
// screen readers.
|
||||
const useAlternateBuffer = shouldEnterAlternateScreen(
|
||||
isAlternateBufferEnabled(config),
|
||||
config.getScreenReader(),
|
||||
// Dynamically import the heavy UI module so React/Ink are only parsed when needed
|
||||
const { startInteractiveUI: doStartUI } = await import('./interactiveCli.js');
|
||||
await doStartUI(
|
||||
config,
|
||||
settings,
|
||||
startupWarnings,
|
||||
workspaceRoot,
|
||||
resumedSessionData,
|
||||
initializationResult,
|
||||
);
|
||||
const mouseEventsEnabled = useAlternateBuffer;
|
||||
if (mouseEventsEnabled) {
|
||||
enableMouseEvents();
|
||||
registerCleanup(() => {
|
||||
disableMouseEvents();
|
||||
});
|
||||
}
|
||||
|
||||
const { matchers, errors } = await loadKeyMatchers();
|
||||
errors.forEach((error) => {
|
||||
coreEvents.emitFeedback('warning', error);
|
||||
});
|
||||
|
||||
const version = await getVersion();
|
||||
setWindowTitle(basename(workspaceRoot), settings);
|
||||
|
||||
const consolePatcher = new ConsolePatcher({
|
||||
onNewMessage: (msg) => {
|
||||
coreEvents.emitConsoleLog(msg.type, msg.content);
|
||||
},
|
||||
debugMode: config.getDebugMode(),
|
||||
});
|
||||
consolePatcher.patch();
|
||||
registerCleanup(consolePatcher.cleanup);
|
||||
|
||||
const { stdout: inkStdout, stderr: inkStderr } = createWorkingStdio();
|
||||
|
||||
const isShpool = !!process.env['SHPOOL_SESSION_NAME'];
|
||||
|
||||
// Create wrapper component to use hooks inside render
|
||||
const AppWrapper = () => {
|
||||
useKittyKeyboardProtocol();
|
||||
|
||||
return (
|
||||
<SettingsContext.Provider value={settings}>
|
||||
<KeyMatchersProvider value={matchers}>
|
||||
<KeypressProvider
|
||||
config={config}
|
||||
debugKeystrokeLogging={
|
||||
settings.merged.general.debugKeystrokeLogging
|
||||
}
|
||||
>
|
||||
<MouseProvider
|
||||
mouseEventsEnabled={mouseEventsEnabled}
|
||||
debugKeystrokeLogging={
|
||||
settings.merged.general.debugKeystrokeLogging
|
||||
}
|
||||
>
|
||||
<TerminalProvider>
|
||||
<ScrollProvider>
|
||||
<OverflowProvider>
|
||||
<SessionStatsProvider>
|
||||
<VimModeProvider>
|
||||
<AppContainer
|
||||
config={config}
|
||||
startupWarnings={startupWarnings}
|
||||
version={version}
|
||||
resumedSessionData={resumedSessionData}
|
||||
initializationResult={initializationResult}
|
||||
/>
|
||||
</VimModeProvider>
|
||||
</SessionStatsProvider>
|
||||
</OverflowProvider>
|
||||
</ScrollProvider>
|
||||
</TerminalProvider>
|
||||
</MouseProvider>
|
||||
</KeypressProvider>
|
||||
</KeyMatchersProvider>
|
||||
</SettingsContext.Provider>
|
||||
);
|
||||
};
|
||||
|
||||
if (isShpool) {
|
||||
// Wait a moment for shpool to stabilize terminal size and state.
|
||||
// shpool is a persistence tool that restores terminal state by replaying it.
|
||||
// This delay gives shpool time to finish its restoration replay and send
|
||||
// the actual terminal size (often via an immediate SIGWINCH) before we
|
||||
// render the first TUI frame. Without this, the first frame may be
|
||||
// garbled or rendered at an incorrect size, which disabling incremental
|
||||
// rendering alone cannot fix for the initial frame.
|
||||
await new Promise((resolve) => setTimeout(resolve, 100));
|
||||
}
|
||||
|
||||
const instance = render(
|
||||
process.env['DEBUG'] ? (
|
||||
<React.StrictMode>
|
||||
<AppWrapper />
|
||||
</React.StrictMode>
|
||||
) : (
|
||||
<AppWrapper />
|
||||
),
|
||||
{
|
||||
stdout: inkStdout,
|
||||
stderr: inkStderr,
|
||||
stdin: process.stdin,
|
||||
exitOnCtrlC: false,
|
||||
isScreenReaderEnabled: config.getScreenReader(),
|
||||
onRender: ({ renderTime }: { renderTime: number }) => {
|
||||
if (renderTime > SLOW_RENDER_MS) {
|
||||
recordSlowRender(config, renderTime);
|
||||
}
|
||||
profiler.reportFrameRendered();
|
||||
},
|
||||
patchConsole: false,
|
||||
alternateBuffer: useAlternateBuffer,
|
||||
incrementalRendering:
|
||||
settings.merged.ui.incrementalRendering !== false &&
|
||||
useAlternateBuffer &&
|
||||
!isShpool,
|
||||
},
|
||||
);
|
||||
|
||||
if (useAlternateBuffer) {
|
||||
disableLineWrapping();
|
||||
registerCleanup(() => {
|
||||
enableLineWrapping();
|
||||
});
|
||||
}
|
||||
|
||||
checkForUpdates(settings)
|
||||
.then((info) => {
|
||||
handleAutoUpdate(info, settings, config.getProjectRoot());
|
||||
})
|
||||
.catch((err) => {
|
||||
// Silently ignore update check errors.
|
||||
if (config.getDebugMode()) {
|
||||
debugLogger.warn('Update check failed:', err);
|
||||
}
|
||||
});
|
||||
|
||||
registerCleanup(() => instance.unmount());
|
||||
|
||||
registerCleanup(setupTtyCheck());
|
||||
}
|
||||
|
||||
export async function main() {
|
||||
@@ -845,25 +685,6 @@ export async function main() {
|
||||
}
|
||||
}
|
||||
|
||||
function setWindowTitle(title: string, settings: LoadedSettings) {
|
||||
if (!settings.merged.ui.hideWindowTitle) {
|
||||
// Initial state before React loop starts
|
||||
const windowTitle = computeTerminalTitle({
|
||||
streamingState: StreamingState.Idle,
|
||||
isConfirming: false,
|
||||
isSilentWorking: false,
|
||||
folderName: title,
|
||||
showThoughts: !!settings.merged.ui.showStatusInTitle,
|
||||
useDynamicTitle: settings.merged.ui.dynamicWindowTitle,
|
||||
});
|
||||
writeToStdout(`\x1b]0;${windowTitle}\x07`);
|
||||
|
||||
process.on('exit', () => {
|
||||
writeToStdout(`\x1b]0;\x07`);
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
export function initializeOutputListenersAndFlush() {
|
||||
// If there are no listeners for output, make sure we flush so output is not
|
||||
// lost.
|
||||
|
||||
@@ -0,0 +1,214 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import React from 'react';
|
||||
import { render } from 'ink';
|
||||
import { basename } from 'node:path';
|
||||
import { AppContainer } from './ui/AppContainer.js';
|
||||
import { ConsolePatcher } from './ui/utils/ConsolePatcher.js';
|
||||
import { registerCleanup, setupTtyCheck } from './utils/cleanup.js';
|
||||
import {
|
||||
type StartupWarning,
|
||||
type Config,
|
||||
type ResumedSessionData,
|
||||
coreEvents,
|
||||
createWorkingStdio,
|
||||
disableMouseEvents,
|
||||
enableMouseEvents,
|
||||
disableLineWrapping,
|
||||
enableLineWrapping,
|
||||
shouldEnterAlternateScreen,
|
||||
recordSlowRender,
|
||||
writeToStdout,
|
||||
getVersion,
|
||||
debugLogger,
|
||||
} from '@google/gemini-cli-core';
|
||||
import type { InitializationResult } from './core/initializer.js';
|
||||
import type { LoadedSettings } from './config/settings.js';
|
||||
import { checkForUpdates } from './ui/utils/updateCheck.js';
|
||||
import { handleAutoUpdate } from './utils/handleAutoUpdate.js';
|
||||
import { SettingsContext } from './ui/contexts/SettingsContext.js';
|
||||
import { MouseProvider } from './ui/contexts/MouseContext.js';
|
||||
import { StreamingState } from './ui/types.js';
|
||||
import { computeTerminalTitle } from './utils/windowTitle.js';
|
||||
|
||||
import { SessionStatsProvider } from './ui/contexts/SessionContext.js';
|
||||
import { VimModeProvider } from './ui/contexts/VimModeContext.js';
|
||||
import { KeyMatchersProvider } from './ui/hooks/useKeyMatchers.js';
|
||||
import { loadKeyMatchers } from './ui/key/keyMatchers.js';
|
||||
import { KeypressProvider } from './ui/contexts/KeypressContext.js';
|
||||
import { useKittyKeyboardProtocol } from './ui/hooks/useKittyKeyboardProtocol.js';
|
||||
import { ScrollProvider } from './ui/contexts/ScrollProvider.js';
|
||||
import { TerminalProvider } from './ui/contexts/TerminalContext.js';
|
||||
import { isAlternateBufferEnabled } from './ui/hooks/useAlternateBuffer.js';
|
||||
import { OverflowProvider } from './ui/contexts/OverflowContext.js';
|
||||
import { profiler } from './ui/components/DebugProfiler.js';
|
||||
|
||||
const SLOW_RENDER_MS = 200;
|
||||
|
||||
export async function startInteractiveUI(
|
||||
config: Config,
|
||||
settings: LoadedSettings,
|
||||
startupWarnings: StartupWarning[],
|
||||
workspaceRoot: string = process.cwd(),
|
||||
resumedSessionData: ResumedSessionData | undefined,
|
||||
initializationResult: InitializationResult,
|
||||
) {
|
||||
// Never enter Ink alternate buffer mode when screen reader mode is enabled
|
||||
// as there is no benefit of alternate buffer mode when using a screen reader
|
||||
// and the Ink alternate buffer mode requires line wrapping harmful to
|
||||
// screen readers.
|
||||
const useAlternateBuffer = shouldEnterAlternateScreen(
|
||||
isAlternateBufferEnabled(config),
|
||||
config.getScreenReader(),
|
||||
);
|
||||
const mouseEventsEnabled = useAlternateBuffer;
|
||||
if (mouseEventsEnabled) {
|
||||
enableMouseEvents();
|
||||
registerCleanup(() => {
|
||||
disableMouseEvents();
|
||||
});
|
||||
}
|
||||
|
||||
const { matchers, errors } = await loadKeyMatchers();
|
||||
errors.forEach((error) => {
|
||||
coreEvents.emitFeedback('warning', error);
|
||||
});
|
||||
|
||||
const version = await getVersion();
|
||||
setWindowTitle(basename(workspaceRoot), settings);
|
||||
|
||||
const consolePatcher = new ConsolePatcher({
|
||||
onNewMessage: (msg) => {
|
||||
coreEvents.emitConsoleLog(msg.type, msg.content);
|
||||
},
|
||||
debugMode: config.getDebugMode(),
|
||||
});
|
||||
consolePatcher.patch();
|
||||
registerCleanup(consolePatcher.cleanup);
|
||||
|
||||
const { stdout: inkStdout, stderr: inkStderr } = createWorkingStdio();
|
||||
|
||||
const isShpool = !!process.env['SHPOOL_SESSION_NAME'];
|
||||
|
||||
// Create wrapper component to use hooks inside render
|
||||
const AppWrapper = () => {
|
||||
useKittyKeyboardProtocol();
|
||||
|
||||
return (
|
||||
<SettingsContext.Provider value={settings}>
|
||||
<KeyMatchersProvider value={matchers}>
|
||||
<KeypressProvider
|
||||
config={config}
|
||||
debugKeystrokeLogging={
|
||||
settings.merged.general.debugKeystrokeLogging
|
||||
}
|
||||
>
|
||||
<MouseProvider
|
||||
mouseEventsEnabled={mouseEventsEnabled}
|
||||
debugKeystrokeLogging={
|
||||
settings.merged.general.debugKeystrokeLogging
|
||||
}
|
||||
>
|
||||
<TerminalProvider>
|
||||
<ScrollProvider>
|
||||
<OverflowProvider>
|
||||
<SessionStatsProvider>
|
||||
<VimModeProvider>
|
||||
<AppContainer
|
||||
config={config}
|
||||
startupWarnings={startupWarnings}
|
||||
version={version}
|
||||
resumedSessionData={resumedSessionData}
|
||||
initializationResult={initializationResult}
|
||||
/>
|
||||
</VimModeProvider>
|
||||
</SessionStatsProvider>
|
||||
</OverflowProvider>
|
||||
</ScrollProvider>
|
||||
</TerminalProvider>
|
||||
</MouseProvider>
|
||||
</KeypressProvider>
|
||||
</KeyMatchersProvider>
|
||||
</SettingsContext.Provider>
|
||||
);
|
||||
};
|
||||
|
||||
if (isShpool) {
|
||||
// Wait a moment for shpool to stabilize terminal size and state.
|
||||
await new Promise((resolve) => setTimeout(resolve, 100));
|
||||
}
|
||||
|
||||
const instance = render(
|
||||
process.env['DEBUG'] ? (
|
||||
<React.StrictMode>
|
||||
<AppWrapper />
|
||||
</React.StrictMode>
|
||||
) : (
|
||||
<AppWrapper />
|
||||
),
|
||||
{
|
||||
stdout: inkStdout,
|
||||
stderr: inkStderr,
|
||||
stdin: process.stdin,
|
||||
exitOnCtrlC: false,
|
||||
isScreenReaderEnabled: config.getScreenReader(),
|
||||
onRender: ({ renderTime }: { renderTime: number }) => {
|
||||
if (renderTime > SLOW_RENDER_MS) {
|
||||
recordSlowRender(config, renderTime);
|
||||
}
|
||||
profiler.reportFrameRendered();
|
||||
},
|
||||
patchConsole: false,
|
||||
alternateBuffer: useAlternateBuffer,
|
||||
incrementalRendering:
|
||||
settings.merged.ui.incrementalRendering !== false &&
|
||||
useAlternateBuffer &&
|
||||
!isShpool,
|
||||
},
|
||||
);
|
||||
|
||||
if (useAlternateBuffer) {
|
||||
disableLineWrapping();
|
||||
registerCleanup(() => {
|
||||
enableLineWrapping();
|
||||
});
|
||||
}
|
||||
|
||||
checkForUpdates(settings)
|
||||
.then((info) => {
|
||||
handleAutoUpdate(info, settings, config.getProjectRoot());
|
||||
})
|
||||
.catch((err) => {
|
||||
// Silently ignore update check errors.
|
||||
if (config.getDebugMode()) {
|
||||
debugLogger.warn('Update check failed:', err);
|
||||
}
|
||||
});
|
||||
|
||||
registerCleanup(() => instance.unmount());
|
||||
|
||||
registerCleanup(setupTtyCheck());
|
||||
}
|
||||
|
||||
function setWindowTitle(title: string, settings: LoadedSettings) {
|
||||
if (!settings.merged.ui.hideWindowTitle) {
|
||||
// Initial state before React loop starts
|
||||
const windowTitle = computeTerminalTitle({
|
||||
streamingState: StreamingState.Idle,
|
||||
isConfirming: false,
|
||||
isSilentWorking: false,
|
||||
folderName: title,
|
||||
showThoughts: !!settings.merged.ui.showStatusInTitle,
|
||||
useDynamicTitle: settings.merged.ui.dynamicWindowTitle,
|
||||
});
|
||||
writeToStdout(`\x1b]0;${windowTitle}\x07`);
|
||||
|
||||
process.on('exit', () => {
|
||||
writeToStdout(`\x1b]0;\x07`);
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -263,8 +263,8 @@ export async function runNonInteractive({
|
||||
onDebugMessage: () => {},
|
||||
messageId: Date.now(),
|
||||
signal: abortController.signal,
|
||||
escapePastedAtSymbols: false,
|
||||
});
|
||||
|
||||
if (error || !processedQuery) {
|
||||
// An error occurred during @include processing (e.g., file not found).
|
||||
// The error message is already logged by handleAtCommand.
|
||||
|
||||
@@ -123,7 +123,6 @@ async function downloadFiles({
|
||||
downloads.push(
|
||||
(async () => {
|
||||
const endpoint = `${REPO_DOWNLOAD_URL}/refs/tags/${releaseTag}/${SOURCE_DIR}/${fileBasename}`;
|
||||
// eslint-disable-next-line no-restricted-syntax -- TODO: Migrate to safeFetch for SSRF protection
|
||||
const response = await fetch(endpoint, {
|
||||
method: 'GET',
|
||||
dispatcher: proxy ? new ProxyAgent(proxy) : undefined,
|
||||
|
||||
@@ -11,6 +11,7 @@ import { Box, Text, useStdout, type DOMElement } from 'ink';
|
||||
import { SuggestionsDisplay, MAX_WIDTH } from './SuggestionsDisplay.js';
|
||||
import { theme } from '../semantic-colors.js';
|
||||
import { useInputHistory } from '../hooks/useInputHistory.js';
|
||||
import { escapeAtSymbols } from '../hooks/atCommandProcessor.js';
|
||||
import { HalfLinePaddedBox } from './shared/HalfLinePaddedBox.js';
|
||||
import {
|
||||
type TextBuffer,
|
||||
@@ -515,7 +516,11 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
|
||||
stdout.write('\x1b]52;c;?\x07');
|
||||
} else {
|
||||
const textToInsert = await clipboardy.read();
|
||||
buffer.insert(textToInsert, { paste: true });
|
||||
const escapedText = settings.ui?.escapePastedAtSymbols
|
||||
? escapeAtSymbols(textToInsert)
|
||||
: textToInsert;
|
||||
buffer.insert(escapedText, { paste: true });
|
||||
|
||||
if (isLargePaste(textToInsert)) {
|
||||
appEvents.emit(AppEvent.TransientMessage, {
|
||||
message: `Press ${formatCommand(Command.EXPAND_PASTE)} to expand pasted text`,
|
||||
@@ -750,8 +755,15 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
|
||||
pasteTimeoutRef.current = null;
|
||||
}, 40);
|
||||
}
|
||||
// Ensure we never accidentally interpret paste as regular input.
|
||||
buffer.handleInput(key);
|
||||
if (settings.ui?.escapePastedAtSymbols) {
|
||||
buffer.handleInput({
|
||||
...key,
|
||||
sequence: escapeAtSymbols(key.sequence || ''),
|
||||
});
|
||||
} else {
|
||||
buffer.handleInput(key);
|
||||
}
|
||||
|
||||
if (key.sequence && isLargePaste(key.sequence)) {
|
||||
appEvents.emit(AppEvent.TransientMessage, {
|
||||
message: `Press ${formatCommand(Command.EXPAND_PASTE)} to expand pasted text`,
|
||||
@@ -1291,6 +1303,7 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
|
||||
forceShowShellSuggestions,
|
||||
keyMatchers,
|
||||
isHelpDismissKey,
|
||||
settings,
|
||||
],
|
||||
);
|
||||
|
||||
|
||||
@@ -13,9 +13,8 @@ import { useTerminalSize } from '../hooks/useTerminalSize.js';
|
||||
import { useKeypress } from '../hooks/useKeypress.js';
|
||||
import path from 'node:path';
|
||||
import type { Config } from '@google/gemini-cli-core';
|
||||
import type { SessionInfo, TextMatch } from '../../utils/sessionUtils.js';
|
||||
import type { SessionInfo } from '../../utils/sessionUtils.js';
|
||||
import {
|
||||
cleanMessage,
|
||||
formatRelativeTime,
|
||||
getSessionFiles,
|
||||
} from '../../utils/sessionUtils.js';
|
||||
@@ -150,124 +149,7 @@ const SessionBrowserEmpty = (): React.JSX.Element => (
|
||||
</Box>
|
||||
);
|
||||
|
||||
/**
|
||||
* Sorts an array of sessions by the specified criteria.
|
||||
* @param sessions - Array of sessions to sort
|
||||
* @param sortBy - Sort criteria: 'date' (lastUpdated), 'messages' (messageCount), or 'name' (displayName)
|
||||
* @param reverse - Whether to reverse the sort order (ascending instead of descending)
|
||||
* @returns New sorted array of sessions
|
||||
*/
|
||||
const sortSessions = (
|
||||
sessions: SessionInfo[],
|
||||
sortBy: 'date' | 'messages' | 'name',
|
||||
reverse: boolean,
|
||||
): SessionInfo[] => {
|
||||
const sorted = [...sessions].sort((a, b) => {
|
||||
switch (sortBy) {
|
||||
case 'date':
|
||||
return (
|
||||
new Date(b.lastUpdated).getTime() - new Date(a.lastUpdated).getTime()
|
||||
);
|
||||
case 'messages':
|
||||
return b.messageCount - a.messageCount;
|
||||
case 'name':
|
||||
return a.displayName.localeCompare(b.displayName);
|
||||
default:
|
||||
return 0;
|
||||
}
|
||||
});
|
||||
|
||||
return reverse ? sorted.reverse() : sorted;
|
||||
};
|
||||
|
||||
/**
|
||||
* Finds all text matches for a search query within conversation messages.
|
||||
* Creates TextMatch objects with context (10 chars before/after) and role information.
|
||||
* @param messages - Array of messages to search through
|
||||
* @param query - Search query string (case-insensitive)
|
||||
* @returns Array of TextMatch objects containing match context and metadata
|
||||
*/
|
||||
const findTextMatches = (
|
||||
messages: Array<{ role: 'user' | 'assistant'; content: string }>,
|
||||
query: string,
|
||||
): TextMatch[] => {
|
||||
if (!query.trim()) return [];
|
||||
|
||||
const lowerQuery = query.toLowerCase();
|
||||
const matches: TextMatch[] = [];
|
||||
|
||||
for (const message of messages) {
|
||||
const m = cleanMessage(message.content);
|
||||
const lowerContent = m.toLowerCase();
|
||||
let startIndex = 0;
|
||||
|
||||
while (true) {
|
||||
const matchIndex = lowerContent.indexOf(lowerQuery, startIndex);
|
||||
if (matchIndex === -1) break;
|
||||
|
||||
const contextStart = Math.max(0, matchIndex - 10);
|
||||
const contextEnd = Math.min(m.length, matchIndex + query.length + 10);
|
||||
|
||||
const snippet = m.slice(contextStart, contextEnd);
|
||||
const relativeMatchStart = matchIndex - contextStart;
|
||||
const relativeMatchEnd = relativeMatchStart + query.length;
|
||||
|
||||
let before = snippet.slice(0, relativeMatchStart);
|
||||
const match = snippet.slice(relativeMatchStart, relativeMatchEnd);
|
||||
let after = snippet.slice(relativeMatchEnd);
|
||||
|
||||
if (contextStart > 0) before = '…' + before;
|
||||
if (contextEnd < m.length) after = after + '…';
|
||||
|
||||
matches.push({ before, match, after, role: message.role });
|
||||
startIndex = matchIndex + 1;
|
||||
}
|
||||
}
|
||||
|
||||
return matches;
|
||||
};
|
||||
|
||||
/**
|
||||
* Filters sessions based on a search query, checking titles, IDs, and full content.
|
||||
* Also populates matchSnippets and matchCount for sessions with content matches.
|
||||
* @param sessions - Array of sessions to filter
|
||||
* @param query - Search query string (case-insensitive)
|
||||
* @returns Filtered array of sessions that match the query
|
||||
*/
|
||||
const filterSessions = (
|
||||
sessions: SessionInfo[],
|
||||
query: string,
|
||||
): SessionInfo[] => {
|
||||
if (!query.trim()) {
|
||||
return sessions.map((session) => ({
|
||||
...session,
|
||||
matchSnippets: undefined,
|
||||
matchCount: undefined,
|
||||
}));
|
||||
}
|
||||
|
||||
const lowerQuery = query.toLowerCase();
|
||||
return sessions.filter((session) => {
|
||||
const titleMatch =
|
||||
session.displayName.toLowerCase().includes(lowerQuery) ||
|
||||
session.id.toLowerCase().includes(lowerQuery) ||
|
||||
session.firstUserMessage.toLowerCase().includes(lowerQuery);
|
||||
|
||||
const contentMatch = session.fullContent
|
||||
?.toLowerCase()
|
||||
.includes(lowerQuery);
|
||||
|
||||
if (titleMatch || contentMatch) {
|
||||
if (session.messages) {
|
||||
session.matchSnippets = findTextMatches(session.messages, query);
|
||||
session.matchCount = session.matchSnippets.length;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
});
|
||||
};
|
||||
import { sortSessions, filterSessions } from './SessionBrowser/utils.js';
|
||||
|
||||
/**
|
||||
* Search input display component.
|
||||
|
||||
@@ -0,0 +1,132 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { sortSessions, findTextMatches, filterSessions } from './utils.js';
|
||||
import type { SessionInfo } from '../../../utils/sessionUtils.js';
|
||||
|
||||
describe('SessionBrowser utils', () => {
|
||||
const createTestSession = (overrides: Partial<SessionInfo>): SessionInfo => ({
|
||||
id: 'test-id',
|
||||
file: 'test-file',
|
||||
fileName: 'test-file.json',
|
||||
startTime: '2025-01-01T10:00:00Z',
|
||||
lastUpdated: '2025-01-01T10:00:00Z',
|
||||
messageCount: 1,
|
||||
displayName: 'Test Session',
|
||||
firstUserMessage: 'Hello',
|
||||
isCurrentSession: false,
|
||||
index: 0,
|
||||
...overrides,
|
||||
});
|
||||
|
||||
describe('sortSessions', () => {
|
||||
it('sorts by date ascending/descending', () => {
|
||||
const older = createTestSession({
|
||||
id: '1',
|
||||
lastUpdated: '2025-01-01T10:00:00Z',
|
||||
});
|
||||
const newer = createTestSession({
|
||||
id: '2',
|
||||
lastUpdated: '2025-01-02T10:00:00Z',
|
||||
});
|
||||
|
||||
const desc = sortSessions([older, newer], 'date', false);
|
||||
expect(desc[0].id).toBe('2');
|
||||
|
||||
const asc = sortSessions([older, newer], 'date', true);
|
||||
expect(asc[0].id).toBe('1');
|
||||
});
|
||||
|
||||
it('sorts by message count ascending/descending', () => {
|
||||
const more = createTestSession({ id: '1', messageCount: 10 });
|
||||
const less = createTestSession({ id: '2', messageCount: 2 });
|
||||
|
||||
const desc = sortSessions([more, less], 'messages', false);
|
||||
expect(desc[0].id).toBe('1');
|
||||
|
||||
const asc = sortSessions([more, less], 'messages', true);
|
||||
expect(asc[0].id).toBe('2');
|
||||
});
|
||||
|
||||
it('sorts by name ascending/descending', () => {
|
||||
const apple = createTestSession({ id: '1', displayName: 'Apple' });
|
||||
const banana = createTestSession({ id: '2', displayName: 'Banana' });
|
||||
|
||||
const asc = sortSessions([apple, banana], 'name', true);
|
||||
expect(asc[0].id).toBe('2'); // Reversed alpha
|
||||
|
||||
const desc = sortSessions([apple, banana], 'name', false);
|
||||
expect(desc[0].id).toBe('1');
|
||||
});
|
||||
});
|
||||
|
||||
describe('findTextMatches', () => {
|
||||
it('returns empty array if query is practically empty', () => {
|
||||
expect(
|
||||
findTextMatches([{ role: 'user', content: 'hello world' }], ' '),
|
||||
).toEqual([]);
|
||||
});
|
||||
|
||||
it('finds simple matches with surrounding context', () => {
|
||||
const messages: Array<{ role: 'user' | 'assistant'; content: string }> = [
|
||||
{ role: 'user', content: 'What is the capital of France?' },
|
||||
];
|
||||
|
||||
const matches = findTextMatches(messages, 'capital');
|
||||
expect(matches.length).toBe(1);
|
||||
expect(matches[0].match).toBe('capital');
|
||||
expect(matches[0].before.endsWith('the ')).toBe(true);
|
||||
expect(matches[0].after.startsWith(' of')).toBe(true);
|
||||
expect(matches[0].role).toBe('user');
|
||||
});
|
||||
|
||||
it('finds multiple matches in a single message', () => {
|
||||
const messages: Array<{ role: 'user' | 'assistant'; content: string }> = [
|
||||
{ role: 'user', content: 'test here test there' },
|
||||
];
|
||||
|
||||
const matches = findTextMatches(messages, 'test');
|
||||
expect(matches.length).toBe(2);
|
||||
});
|
||||
});
|
||||
|
||||
describe('filterSessions', () => {
|
||||
it('returns all sessions when query is blank and clears existing snippets', () => {
|
||||
const sessions = [createTestSession({ id: '1', matchCount: 5 })];
|
||||
|
||||
const result = filterSessions(sessions, ' ');
|
||||
expect(result.length).toBe(1);
|
||||
expect(result[0].matchCount).toBeUndefined();
|
||||
});
|
||||
|
||||
it('filters by displayName', () => {
|
||||
const session1 = createTestSession({
|
||||
id: '1',
|
||||
displayName: 'Cats and Dogs',
|
||||
});
|
||||
const session2 = createTestSession({ id: '2', displayName: 'Fish' });
|
||||
|
||||
const result = filterSessions([session1, session2], 'cat');
|
||||
expect(result.length).toBe(1);
|
||||
expect(result[0].id).toBe('1');
|
||||
});
|
||||
|
||||
it('populates match snippets if it matches content inside messages array', () => {
|
||||
const sessionWithMessages = createTestSession({
|
||||
id: '1',
|
||||
displayName: 'Unrelated Title',
|
||||
fullContent: 'This mentions a giraffe',
|
||||
messages: [{ role: 'user', content: 'This mentions a giraffe' }],
|
||||
});
|
||||
|
||||
const result = filterSessions([sessionWithMessages], 'giraffe');
|
||||
expect(result.length).toBe(1);
|
||||
expect(result[0].matchCount).toBe(1);
|
||||
expect(result[0].matchSnippets?.[0].match).toBe('giraffe');
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,130 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import {
|
||||
cleanMessage,
|
||||
type SessionInfo,
|
||||
type TextMatch,
|
||||
} from '../../../utils/sessionUtils.js';
|
||||
|
||||
/**
|
||||
* Sorts an array of sessions by the specified criteria.
|
||||
* @param sessions - Array of sessions to sort
|
||||
* @param sortBy - Sort criteria: 'date' (lastUpdated), 'messages' (messageCount), or 'name' (displayName)
|
||||
* @param reverse - Whether to reverse the sort order (ascending instead of descending)
|
||||
* @returns New sorted array of sessions
|
||||
*/
|
||||
export const sortSessions = (
|
||||
sessions: SessionInfo[],
|
||||
sortBy: 'date' | 'messages' | 'name',
|
||||
reverse: boolean,
|
||||
): SessionInfo[] => {
|
||||
const sorted = [...sessions].sort((a, b) => {
|
||||
switch (sortBy) {
|
||||
case 'date':
|
||||
return (
|
||||
new Date(b.lastUpdated).getTime() - new Date(a.lastUpdated).getTime()
|
||||
);
|
||||
case 'messages':
|
||||
return b.messageCount - a.messageCount;
|
||||
case 'name':
|
||||
return a.displayName.localeCompare(b.displayName);
|
||||
default:
|
||||
return 0;
|
||||
}
|
||||
});
|
||||
|
||||
return reverse ? sorted.reverse() : sorted;
|
||||
};
|
||||
|
||||
/**
|
||||
* Finds all text matches for a search query within conversation messages.
|
||||
* Creates TextMatch objects with context (10 chars before/after) and role information.
|
||||
* @param messages - Array of messages to search through
|
||||
* @param query - Search query string (case-insensitive)
|
||||
* @returns Array of TextMatch objects containing match context and metadata
|
||||
*/
|
||||
export const findTextMatches = (
|
||||
messages: Array<{ role: 'user' | 'assistant'; content: string }>,
|
||||
query: string,
|
||||
): TextMatch[] => {
|
||||
if (!query.trim()) return [];
|
||||
|
||||
const lowerQuery = query.toLowerCase();
|
||||
const matches: TextMatch[] = [];
|
||||
|
||||
for (const message of messages) {
|
||||
const m = cleanMessage(message.content);
|
||||
const lowerContent = m.toLowerCase();
|
||||
let startIndex = 0;
|
||||
|
||||
while (true) {
|
||||
const matchIndex = lowerContent.indexOf(lowerQuery, startIndex);
|
||||
if (matchIndex === -1) break;
|
||||
|
||||
const contextStart = Math.max(0, matchIndex - 10);
|
||||
const contextEnd = Math.min(m.length, matchIndex + query.length + 10);
|
||||
|
||||
const snippet = m.slice(contextStart, contextEnd);
|
||||
const relativeMatchStart = matchIndex - contextStart;
|
||||
const relativeMatchEnd = relativeMatchStart + query.length;
|
||||
|
||||
let before = snippet.slice(0, relativeMatchStart);
|
||||
const match = snippet.slice(relativeMatchStart, relativeMatchEnd);
|
||||
let after = snippet.slice(relativeMatchEnd);
|
||||
|
||||
if (contextStart > 0) before = '…' + before;
|
||||
if (contextEnd < m.length) after = after + '…';
|
||||
|
||||
matches.push({ before, match, after, role: message.role });
|
||||
startIndex = matchIndex + 1;
|
||||
}
|
||||
}
|
||||
|
||||
return matches;
|
||||
};
|
||||
|
||||
/**
|
||||
* Filters sessions based on a search query, checking titles, IDs, and full content.
|
||||
* Also populates matchSnippets and matchCount for sessions with content matches.
|
||||
* @param sessions - Array of sessions to filter
|
||||
* @param query - Search query string (case-insensitive)
|
||||
* @returns Filtered array of sessions that match the query
|
||||
*/
|
||||
export const filterSessions = (
|
||||
sessions: SessionInfo[],
|
||||
query: string,
|
||||
): SessionInfo[] => {
|
||||
if (!query.trim()) {
|
||||
return sessions.map((session) => ({
|
||||
...session,
|
||||
matchSnippets: undefined,
|
||||
matchCount: undefined,
|
||||
}));
|
||||
}
|
||||
|
||||
const lowerQuery = query.toLowerCase();
|
||||
return sessions.filter((session) => {
|
||||
const titleMatch =
|
||||
session.displayName.toLowerCase().includes(lowerQuery) ||
|
||||
session.id.toLowerCase().includes(lowerQuery) ||
|
||||
session.firstUserMessage.toLowerCase().includes(lowerQuery);
|
||||
|
||||
const contentMatch = session.fullContent
|
||||
?.toLowerCase()
|
||||
.includes(lowerQuery);
|
||||
|
||||
if (titleMatch || contentMatch) {
|
||||
if (session.messages) {
|
||||
session.matchSnippets = findTextMatches(session.messages, query);
|
||||
session.matchCount = session.matchSnippets.length;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
});
|
||||
};
|
||||
@@ -27,6 +27,7 @@ import {
|
||||
} from '../utils/displayUtils.js';
|
||||
import { computeSessionStats } from '../utils/computeStats.js';
|
||||
import {
|
||||
type Config,
|
||||
type RetrieveUserQuotaResponse,
|
||||
isActiveModel,
|
||||
getDisplayString,
|
||||
@@ -88,13 +89,16 @@ const Section: React.FC<SectionProps> = ({ title, children }) => (
|
||||
// Logic for building the unified list of table rows
|
||||
const buildModelRows = (
|
||||
models: Record<string, ModelMetrics>,
|
||||
config: Config,
|
||||
quotas?: RetrieveUserQuotaResponse,
|
||||
useGemini3_1 = false,
|
||||
useCustomToolModel = false,
|
||||
) => {
|
||||
const getBaseModelName = (name: string) => name.replace('-001', '');
|
||||
const usedModelNames = new Set(
|
||||
Object.keys(models).map(getBaseModelName).map(getDisplayString),
|
||||
Object.keys(models)
|
||||
.map(getBaseModelName)
|
||||
.map((name) => getDisplayString(name, config)),
|
||||
);
|
||||
|
||||
// 1. Models with active usage
|
||||
@@ -104,7 +108,7 @@ const buildModelRows = (
|
||||
const inputTokens = metrics.tokens.input;
|
||||
return {
|
||||
key: name,
|
||||
modelName: getDisplayString(modelName),
|
||||
modelName: getDisplayString(modelName, config),
|
||||
requests: metrics.api.totalRequests,
|
||||
cachedTokens: cachedTokens.toLocaleString(),
|
||||
inputTokens: inputTokens.toLocaleString(),
|
||||
@@ -121,11 +125,11 @@ const buildModelRows = (
|
||||
(b) =>
|
||||
b.modelId &&
|
||||
isActiveModel(b.modelId, useGemini3_1, useCustomToolModel) &&
|
||||
!usedModelNames.has(getDisplayString(b.modelId)),
|
||||
!usedModelNames.has(getDisplayString(b.modelId, config)),
|
||||
)
|
||||
.map((bucket) => ({
|
||||
key: bucket.modelId!,
|
||||
modelName: getDisplayString(bucket.modelId!),
|
||||
modelName: getDisplayString(bucket.modelId!, config),
|
||||
requests: '-',
|
||||
cachedTokens: '-',
|
||||
inputTokens: '-',
|
||||
@@ -139,6 +143,7 @@ const buildModelRows = (
|
||||
|
||||
const ModelUsageTable: React.FC<{
|
||||
models: Record<string, ModelMetrics>;
|
||||
config: Config;
|
||||
quotas?: RetrieveUserQuotaResponse;
|
||||
cacheEfficiency: number;
|
||||
totalCachedTokens: number;
|
||||
@@ -150,6 +155,7 @@ const ModelUsageTable: React.FC<{
|
||||
useCustomToolModel?: boolean;
|
||||
}> = ({
|
||||
models,
|
||||
config,
|
||||
quotas,
|
||||
cacheEfficiency,
|
||||
totalCachedTokens,
|
||||
@@ -162,7 +168,13 @@ const ModelUsageTable: React.FC<{
|
||||
}) => {
|
||||
const { stdout } = useStdout();
|
||||
const terminalWidth = stdout?.columns ?? 84;
|
||||
const rows = buildModelRows(models, quotas, useGemini3_1, useCustomToolModel);
|
||||
const rows = buildModelRows(
|
||||
models,
|
||||
config,
|
||||
quotas,
|
||||
useGemini3_1,
|
||||
useCustomToolModel,
|
||||
);
|
||||
|
||||
if (rows.length === 0) {
|
||||
return null;
|
||||
@@ -676,6 +688,7 @@ export const StatsDisplay: React.FC<StatsDisplayProps> = ({
|
||||
</Section>
|
||||
<ModelUsageTable
|
||||
models={models}
|
||||
config={config}
|
||||
quotas={quotas}
|
||||
cacheEfficiency={computed.cacheEfficiency}
|
||||
totalCachedTokens={computed.totalCachedTokens}
|
||||
|
||||
@@ -13,7 +13,11 @@ import {
|
||||
afterEach,
|
||||
type Mock,
|
||||
} from 'vitest';
|
||||
import { handleAtCommand } from './atCommandProcessor.js';
|
||||
import {
|
||||
handleAtCommand,
|
||||
escapeAtSymbols,
|
||||
unescapeLiteralAt,
|
||||
} from './atCommandProcessor.js';
|
||||
import {
|
||||
FileDiscoveryService,
|
||||
GlobTool,
|
||||
@@ -1481,3 +1485,56 @@ describe('handleAtCommand', () => {
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe('escapeAtSymbols', () => {
|
||||
it('escapes a bare @ symbol', () => {
|
||||
expect(escapeAtSymbols('test@domain.com')).toBe('test\\@domain.com');
|
||||
});
|
||||
|
||||
it('escapes a leading @ symbol', () => {
|
||||
expect(escapeAtSymbols('@scope/pkg')).toBe('\\@scope/pkg');
|
||||
});
|
||||
|
||||
it('escapes multiple @ symbols', () => {
|
||||
expect(escapeAtSymbols('a@b and c@d')).toBe('a\\@b and c\\@d');
|
||||
});
|
||||
|
||||
it('does not double-escape an already escaped @', () => {
|
||||
expect(escapeAtSymbols('test\\@domain.com')).toBe('test\\@domain.com');
|
||||
});
|
||||
|
||||
it('returns text with no @ unchanged', () => {
|
||||
expect(escapeAtSymbols('hello world')).toBe('hello world');
|
||||
});
|
||||
|
||||
it('returns empty string unchanged', () => {
|
||||
expect(escapeAtSymbols('')).toBe('');
|
||||
});
|
||||
});
|
||||
|
||||
describe('unescapeLiteralAt', () => {
|
||||
it('unescapes \\@ to @', () => {
|
||||
expect(unescapeLiteralAt('test\\@domain.com')).toBe('test@domain.com');
|
||||
});
|
||||
|
||||
it('unescapes a leading \\@', () => {
|
||||
expect(unescapeLiteralAt('\\@scope/pkg')).toBe('@scope/pkg');
|
||||
});
|
||||
|
||||
it('unescapes multiple \\@ sequences', () => {
|
||||
expect(unescapeLiteralAt('a\\@b and c\\@d')).toBe('a@b and c@d');
|
||||
});
|
||||
|
||||
it('returns text with no \\@ unchanged', () => {
|
||||
expect(unescapeLiteralAt('hello world')).toBe('hello world');
|
||||
});
|
||||
|
||||
it('returns empty string unchanged', () => {
|
||||
expect(unescapeLiteralAt('')).toBe('');
|
||||
});
|
||||
|
||||
it('roundtrips correctly with escapeAtSymbols', () => {
|
||||
const input = 'user@example.com and @scope/pkg';
|
||||
expect(unescapeLiteralAt(escapeAtSymbols(input))).toBe(input);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -30,6 +30,26 @@ import type { UseHistoryManagerReturn } from './useHistoryManager.js';
|
||||
const REF_CONTENT_HEADER = `\n${REFERENCE_CONTENT_START}`;
|
||||
const REF_CONTENT_FOOTER = `\n${REFERENCE_CONTENT_END}`;
|
||||
|
||||
/**
|
||||
* Escapes unescaped @ symbols so they are not interpreted as @path commands.
|
||||
*/
|
||||
export function escapeAtSymbols(text: string): string {
|
||||
return text.replace(/(?<!\\)@/g, '\\@');
|
||||
}
|
||||
|
||||
/**
|
||||
* Unescapes \@ back to @ correctly, preserving \\@ sequences.
|
||||
*/
|
||||
export function unescapeLiteralAt(text: string): string {
|
||||
return text.replace(/\\@/g, (match, offset, full) => {
|
||||
let backslashCount = 0;
|
||||
for (let i = offset - 1; i >= 0 && full[i] === '\\'; i--) {
|
||||
backslashCount++;
|
||||
}
|
||||
return backslashCount % 2 === 0 ? '@' : '\\@';
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Regex source for the path/command part of an @ reference.
|
||||
* It uses strict ASCII whitespace delimiters to allow Unicode characters like NNBSP in filenames.
|
||||
@@ -49,6 +69,7 @@ interface HandleAtCommandParams {
|
||||
onDebugMessage: (message: string) => void;
|
||||
messageId: number;
|
||||
signal: AbortSignal;
|
||||
escapePastedAtSymbols?: boolean;
|
||||
}
|
||||
|
||||
interface HandleAtCommandResult {
|
||||
@@ -65,7 +86,10 @@ interface AtCommandPart {
|
||||
* Parses a query string to find all '@<path>' commands and text segments.
|
||||
* Handles \ escaped spaces within paths.
|
||||
*/
|
||||
function parseAllAtCommands(query: string): AtCommandPart[] {
|
||||
function parseAllAtCommands(
|
||||
query: string,
|
||||
escapePastedAtSymbols = false,
|
||||
): AtCommandPart[] {
|
||||
const parts: AtCommandPart[] = [];
|
||||
let lastIndex = 0;
|
||||
|
||||
@@ -85,7 +109,9 @@ function parseAllAtCommands(query: string): AtCommandPart[] {
|
||||
if (matchIndex > lastIndex) {
|
||||
parts.push({
|
||||
type: 'text',
|
||||
content: query.substring(lastIndex, matchIndex),
|
||||
content: escapePastedAtSymbols
|
||||
? unescapeLiteralAt(query.substring(lastIndex, matchIndex))
|
||||
: query.substring(lastIndex, matchIndex),
|
||||
});
|
||||
}
|
||||
|
||||
@@ -98,7 +124,12 @@ function parseAllAtCommands(query: string): AtCommandPart[] {
|
||||
|
||||
// Add remaining text
|
||||
if (lastIndex < query.length) {
|
||||
parts.push({ type: 'text', content: query.substring(lastIndex) });
|
||||
parts.push({
|
||||
type: 'text',
|
||||
content: escapePastedAtSymbols
|
||||
? unescapeLiteralAt(query.substring(lastIndex))
|
||||
: query.substring(lastIndex),
|
||||
});
|
||||
}
|
||||
|
||||
// Filter out empty text parts that might result from consecutive @paths or leading/trailing spaces
|
||||
@@ -635,8 +666,9 @@ export async function handleAtCommand({
|
||||
onDebugMessage,
|
||||
messageId: userMessageTimestamp,
|
||||
signal,
|
||||
escapePastedAtSymbols = false,
|
||||
}: HandleAtCommandParams): Promise<HandleAtCommandResult> {
|
||||
const commandParts = parseAllAtCommands(query);
|
||||
const commandParts = parseAllAtCommands(query, escapePastedAtSymbols);
|
||||
|
||||
const { agentParts, resourceParts, fileParts } = categorizeAtCommands(
|
||||
commandParts,
|
||||
|
||||
@@ -837,8 +837,8 @@ export const useGeminiStream = (
|
||||
onDebugMessage,
|
||||
messageId: userMessageTimestamp,
|
||||
signal: abortSignal,
|
||||
escapePastedAtSymbols: settings.merged.ui?.escapePastedAtSymbols,
|
||||
});
|
||||
|
||||
if (atCommandResult.error) {
|
||||
onDebugMessage(atCommandResult.error);
|
||||
return { queryToSend: null, shouldProceed: false };
|
||||
@@ -874,6 +874,7 @@ export const useGeminiStream = (
|
||||
logger,
|
||||
shellModeActive,
|
||||
scheduleToolCalls,
|
||||
settings,
|
||||
],
|
||||
);
|
||||
|
||||
|
||||
@@ -25,7 +25,7 @@ export type HighlightToken = {
|
||||
// It matches any character except strict delimiters (ASCII whitespace, comma, etc.).
|
||||
// This supports URIs like `@file:///example.txt` and filenames with Unicode spaces (like NNBSP).
|
||||
const HIGHLIGHT_REGEX = new RegExp(
|
||||
`(^/[a-zA-Z0-9_-]+|@${AT_COMMAND_PATH_REGEX_SOURCE}|${PASTED_TEXT_PLACEHOLDER_REGEX.source})`,
|
||||
`(^/[a-zA-Z0-9_-]+|(?<!\\\\)@${AT_COMMAND_PATH_REGEX_SOURCE}|${PASTED_TEXT_PLACEHOLDER_REGEX.source})`,
|
||||
'g',
|
||||
);
|
||||
|
||||
|
||||
@@ -61,7 +61,6 @@ export const getLatestGitHubRelease = async (
|
||||
|
||||
const endpoint = `https://api.github.com/repos/google-github-actions/run-gemini-cli/releases/latest`;
|
||||
|
||||
// eslint-disable-next-line no-restricted-syntax -- TODO: Migrate to safeFetch for SSRF protection
|
||||
const response = await fetch(endpoint, {
|
||||
method: 'GET',
|
||||
headers: {
|
||||
|
||||
@@ -5,11 +5,8 @@
|
||||
*/
|
||||
|
||||
import { vi, describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import {
|
||||
A2AClientManager,
|
||||
type SendMessageResult,
|
||||
} from './a2a-client-manager.js';
|
||||
import type { AgentCard, Task } from '@a2a-js/sdk';
|
||||
import { A2AClientManager } from './a2a-client-manager.js';
|
||||
import type { AgentCard } from '@a2a-js/sdk';
|
||||
import {
|
||||
ClientFactory,
|
||||
DefaultAgentCardResolver,
|
||||
@@ -18,83 +15,99 @@ import {
|
||||
type AuthenticationHandler,
|
||||
type Client,
|
||||
} from '@a2a-js/sdk/client';
|
||||
import type { Config } from '../config/config.js';
|
||||
import { Agent as UndiciAgent, ProxyAgent } from 'undici';
|
||||
import { debugLogger } from '../utils/debugLogger.js';
|
||||
|
||||
interface MockClient {
|
||||
sendMessageStream: ReturnType<typeof vi.fn>;
|
||||
getTask: ReturnType<typeof vi.fn>;
|
||||
cancelTask: ReturnType<typeof vi.fn>;
|
||||
}
|
||||
|
||||
vi.mock('@a2a-js/sdk/client', async (importOriginal) => {
|
||||
const actual = await importOriginal();
|
||||
return {
|
||||
...(actual as Record<string, unknown>),
|
||||
createAuthenticatingFetchWithRetry: vi.fn(),
|
||||
ClientFactory: vi.fn(),
|
||||
DefaultAgentCardResolver: vi.fn(),
|
||||
ClientFactoryOptions: {
|
||||
createFrom: vi.fn(),
|
||||
default: {},
|
||||
},
|
||||
};
|
||||
});
|
||||
|
||||
vi.mock('../utils/debugLogger.js', () => ({
|
||||
debugLogger: {
|
||||
debug: vi.fn(),
|
||||
},
|
||||
}));
|
||||
|
||||
vi.mock('@a2a-js/sdk/client', () => {
|
||||
const ClientFactory = vi.fn();
|
||||
const DefaultAgentCardResolver = vi.fn();
|
||||
const RestTransportFactory = vi.fn();
|
||||
const JsonRpcTransportFactory = vi.fn();
|
||||
const ClientFactoryOptions = {
|
||||
default: {},
|
||||
createFrom: vi.fn(),
|
||||
};
|
||||
const createAuthenticatingFetchWithRetry = vi.fn();
|
||||
|
||||
DefaultAgentCardResolver.prototype.resolve = vi.fn();
|
||||
ClientFactory.prototype.createFromUrl = vi.fn();
|
||||
|
||||
return {
|
||||
ClientFactory,
|
||||
ClientFactoryOptions,
|
||||
DefaultAgentCardResolver,
|
||||
RestTransportFactory,
|
||||
JsonRpcTransportFactory,
|
||||
createAuthenticatingFetchWithRetry,
|
||||
};
|
||||
});
|
||||
|
||||
describe('A2AClientManager', () => {
|
||||
let manager: A2AClientManager;
|
||||
const mockAgentCard: AgentCard = {
|
||||
name: 'test-agent',
|
||||
description: 'A test agent',
|
||||
url: 'http://test.agent',
|
||||
version: '1.0.0',
|
||||
protocolVersion: '0.1.0',
|
||||
capabilities: {},
|
||||
skills: [],
|
||||
defaultInputModes: [],
|
||||
defaultOutputModes: [],
|
||||
};
|
||||
|
||||
const mockClient: MockClient = {
|
||||
sendMessageStream: vi.fn(),
|
||||
getTask: vi.fn(),
|
||||
cancelTask: vi.fn(),
|
||||
};
|
||||
|
||||
// Stable mocks initialized once
|
||||
const sendMessageStreamMock = vi.fn();
|
||||
const getTaskMock = vi.fn();
|
||||
const cancelTaskMock = vi.fn();
|
||||
const getAgentCardMock = vi.fn();
|
||||
const authFetchMock = vi.fn();
|
||||
|
||||
const mockClient = {
|
||||
sendMessageStream: sendMessageStreamMock,
|
||||
getTask: getTaskMock,
|
||||
cancelTask: cancelTaskMock,
|
||||
getAgentCard: getAgentCardMock,
|
||||
} as unknown as Client;
|
||||
|
||||
const mockAgentCard: Partial<AgentCard> = { name: 'TestAgent' };
|
||||
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks();
|
||||
A2AClientManager.resetInstanceForTesting();
|
||||
manager = A2AClientManager.getInstance();
|
||||
|
||||
// Default mock implementations
|
||||
getAgentCardMock.mockResolvedValue({
|
||||
// Re-create the instances as plain objects that can be spied on
|
||||
const factoryInstance = {
|
||||
createFromUrl: vi.fn(),
|
||||
createFromAgentCard: vi.fn(),
|
||||
};
|
||||
const resolverInstance = {
|
||||
resolve: vi.fn(),
|
||||
};
|
||||
|
||||
vi.mocked(ClientFactory).mockReturnValue(
|
||||
factoryInstance as unknown as ClientFactory,
|
||||
);
|
||||
vi.mocked(DefaultAgentCardResolver).mockReturnValue(
|
||||
resolverInstance as unknown as DefaultAgentCardResolver,
|
||||
);
|
||||
|
||||
vi.spyOn(factoryInstance, 'createFromUrl').mockResolvedValue(
|
||||
mockClient as unknown as Client,
|
||||
);
|
||||
vi.spyOn(factoryInstance, 'createFromAgentCard').mockResolvedValue(
|
||||
mockClient as unknown as Client,
|
||||
);
|
||||
vi.spyOn(resolverInstance, 'resolve').mockResolvedValue({
|
||||
...mockAgentCard,
|
||||
url: 'http://test.agent/real/endpoint',
|
||||
} as AgentCard);
|
||||
|
||||
vi.mocked(ClientFactory.prototype.createFromUrl).mockResolvedValue(
|
||||
mockClient,
|
||||
vi.spyOn(ClientFactoryOptions, 'createFrom').mockImplementation(
|
||||
(_defaults, overrides) => overrides as unknown as ClientFactoryOptions,
|
||||
);
|
||||
|
||||
vi.mocked(DefaultAgentCardResolver.prototype.resolve).mockResolvedValue({
|
||||
...mockAgentCard,
|
||||
url: 'http://test.agent/real/endpoint',
|
||||
} as AgentCard);
|
||||
|
||||
vi.mocked(ClientFactoryOptions.createFrom).mockImplementation(
|
||||
(_defaults, overrides) => overrides as ClientFactoryOptions,
|
||||
);
|
||||
|
||||
vi.mocked(createAuthenticatingFetchWithRetry).mockReturnValue(
|
||||
authFetchMock,
|
||||
vi.mocked(createAuthenticatingFetchWithRetry).mockImplementation(() =>
|
||||
authFetchMock.mockResolvedValue({
|
||||
ok: true,
|
||||
json: async () => ({}),
|
||||
} as Response),
|
||||
);
|
||||
|
||||
vi.stubGlobal(
|
||||
@@ -117,21 +130,70 @@ describe('A2AClientManager', () => {
|
||||
expect(instance1).toBe(instance2);
|
||||
});
|
||||
|
||||
describe('getInstance / dispatcher initialization', () => {
|
||||
it('should use UndiciAgent when no proxy is configured', async () => {
|
||||
await manager.loadAgent('TestAgent', 'http://test.agent/card');
|
||||
|
||||
const resolverOptions = vi.mocked(DefaultAgentCardResolver).mock
|
||||
.calls[0][0];
|
||||
const cardFetch = resolverOptions?.fetchImpl as typeof fetch;
|
||||
await cardFetch('http://test.agent/card');
|
||||
|
||||
const fetchCall = vi
|
||||
.mocked(fetch)
|
||||
.mock.calls.find((call) => call[0] === 'http://test.agent/card');
|
||||
expect(fetchCall).toBeDefined();
|
||||
expect(
|
||||
(fetchCall![1] as { dispatcher?: unknown })?.dispatcher,
|
||||
).toBeInstanceOf(UndiciAgent);
|
||||
expect(
|
||||
(fetchCall![1] as { dispatcher?: unknown })?.dispatcher,
|
||||
).not.toBeInstanceOf(ProxyAgent);
|
||||
});
|
||||
|
||||
it('should use ProxyAgent when a proxy is configured via Config', async () => {
|
||||
A2AClientManager.resetInstanceForTesting();
|
||||
const mockConfig = {
|
||||
getProxy: () => 'http://my-proxy:8080',
|
||||
} as Config;
|
||||
|
||||
manager = A2AClientManager.getInstance(mockConfig);
|
||||
await manager.loadAgent('TestProxyAgent', 'http://test.proxy.agent/card');
|
||||
|
||||
const resolverOptions = vi.mocked(DefaultAgentCardResolver).mock
|
||||
.calls[0][0];
|
||||
const cardFetch = resolverOptions?.fetchImpl as typeof fetch;
|
||||
await cardFetch('http://test.proxy.agent/card');
|
||||
|
||||
const fetchCall = vi
|
||||
.mocked(fetch)
|
||||
.mock.calls.find((call) => call[0] === 'http://test.proxy.agent/card');
|
||||
expect(fetchCall).toBeDefined();
|
||||
expect(
|
||||
(fetchCall![1] as { dispatcher?: unknown })?.dispatcher,
|
||||
).toBeInstanceOf(ProxyAgent);
|
||||
});
|
||||
});
|
||||
|
||||
describe('loadAgent', () => {
|
||||
it('should create and cache an A2AClient', async () => {
|
||||
const agentCard = await manager.loadAgent(
|
||||
'TestAgent',
|
||||
'http://test.agent/card',
|
||||
);
|
||||
expect(agentCard).toMatchObject(mockAgentCard);
|
||||
expect(manager.getAgentCard('TestAgent')).toBe(agentCard);
|
||||
expect(manager.getClient('TestAgent')).toBeDefined();
|
||||
});
|
||||
|
||||
it('should configure ClientFactory with REST, JSON-RPC, and gRPC transports', async () => {
|
||||
await manager.loadAgent('TestAgent', 'http://test.agent/card');
|
||||
expect(ClientFactoryOptions.createFrom).toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('should throw an error if an agent with the same name is already loaded', async () => {
|
||||
await manager.loadAgent('TestAgent', 'http://test.agent/card');
|
||||
await expect(
|
||||
manager.loadAgent('TestAgent', 'http://another.agent/card'),
|
||||
manager.loadAgent('TestAgent', 'http://test.agent/card'),
|
||||
).rejects.toThrow("Agent with name 'TestAgent' is already loaded.");
|
||||
});
|
||||
|
||||
@@ -146,20 +208,12 @@ describe('A2AClientManager', () => {
|
||||
shouldRetryWithHeaders: vi.fn(),
|
||||
};
|
||||
await manager.loadAgent(
|
||||
'CustomAuthAgent',
|
||||
'http://custom.agent/card',
|
||||
'TestAgent',
|
||||
'http://test.agent/card',
|
||||
customAuthHandler as unknown as AuthenticationHandler,
|
||||
);
|
||||
|
||||
expect(createAuthenticatingFetchWithRetry).toHaveBeenCalledWith(
|
||||
expect.anything(),
|
||||
customAuthHandler,
|
||||
);
|
||||
|
||||
// Card resolver should NOT use the authenticated fetch by default.
|
||||
const resolverInstance = vi.mocked(DefaultAgentCardResolver).mock
|
||||
.instances[0];
|
||||
expect(resolverInstance).toBeDefined();
|
||||
const resolverOptions = vi.mocked(DefaultAgentCardResolver).mock
|
||||
.calls[0][0];
|
||||
expect(resolverOptions?.fetchImpl).not.toBe(authFetchMock);
|
||||
@@ -220,106 +274,163 @@ describe('A2AClientManager', () => {
|
||||
it('should log a debug message upon loading an agent', async () => {
|
||||
await manager.loadAgent('TestAgent', 'http://test.agent/card');
|
||||
expect(debugLogger.debug).toHaveBeenCalledWith(
|
||||
"[A2AClientManager] Loaded agent 'TestAgent' from http://test.agent/card",
|
||||
expect.stringContaining("Loaded agent 'TestAgent'"),
|
||||
);
|
||||
});
|
||||
|
||||
it('should clear the cache', async () => {
|
||||
await manager.loadAgent('TestAgent', 'http://test.agent/card');
|
||||
expect(manager.getAgentCard('TestAgent')).toBeDefined();
|
||||
expect(manager.getClient('TestAgent')).toBeDefined();
|
||||
|
||||
manager.clearCache();
|
||||
|
||||
expect(manager.getAgentCard('TestAgent')).toBeUndefined();
|
||||
expect(manager.getClient('TestAgent')).toBeUndefined();
|
||||
expect(debugLogger.debug).toHaveBeenCalledWith(
|
||||
'[A2AClientManager] Cache cleared.',
|
||||
});
|
||||
|
||||
it('should throw if resolveAgentCard fails', async () => {
|
||||
const resolverInstance = {
|
||||
resolve: vi.fn().mockRejectedValue(new Error('Resolution failed')),
|
||||
};
|
||||
vi.mocked(DefaultAgentCardResolver).mockReturnValue(
|
||||
resolverInstance as unknown as DefaultAgentCardResolver,
|
||||
);
|
||||
|
||||
await expect(
|
||||
manager.loadAgent('FailAgent', 'http://fail.agent'),
|
||||
).rejects.toThrow('Resolution failed');
|
||||
});
|
||||
|
||||
it('should throw if factory.createFromAgentCard fails', async () => {
|
||||
const factoryInstance = {
|
||||
createFromAgentCard: vi
|
||||
.fn()
|
||||
.mockRejectedValue(new Error('Factory failed')),
|
||||
};
|
||||
vi.mocked(ClientFactory).mockReturnValue(
|
||||
factoryInstance as unknown as ClientFactory,
|
||||
);
|
||||
|
||||
await expect(
|
||||
manager.loadAgent('FailAgent', 'http://fail.agent'),
|
||||
).rejects.toThrow('Factory failed');
|
||||
});
|
||||
});
|
||||
|
||||
describe('getAgentCard and getClient', () => {
|
||||
it('should return undefined if agent is not found', () => {
|
||||
expect(manager.getAgentCard('Unknown')).toBeUndefined();
|
||||
expect(manager.getClient('Unknown')).toBeUndefined();
|
||||
});
|
||||
});
|
||||
|
||||
describe('sendMessageStream', () => {
|
||||
beforeEach(async () => {
|
||||
await manager.loadAgent('TestAgent', 'http://test.agent');
|
||||
await manager.loadAgent('TestAgent', 'http://test.agent/card');
|
||||
});
|
||||
|
||||
it('should send a message and return a stream', async () => {
|
||||
const mockResult = {
|
||||
kind: 'message',
|
||||
messageId: 'a',
|
||||
parts: [],
|
||||
role: 'agent',
|
||||
} as SendMessageResult;
|
||||
|
||||
sendMessageStreamMock.mockReturnValue(
|
||||
mockClient.sendMessageStream.mockReturnValue(
|
||||
(async function* () {
|
||||
yield mockResult;
|
||||
yield { kind: 'message' };
|
||||
})(),
|
||||
);
|
||||
|
||||
const stream = manager.sendMessageStream('TestAgent', 'Hello');
|
||||
const results = [];
|
||||
for await (const res of stream) {
|
||||
results.push(res);
|
||||
for await (const result of stream) {
|
||||
results.push(result);
|
||||
}
|
||||
|
||||
expect(results).toEqual([mockResult]);
|
||||
expect(sendMessageStreamMock).toHaveBeenCalledWith(
|
||||
expect(results).toHaveLength(1);
|
||||
expect(mockClient.sendMessageStream).toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('should use contextId and taskId when provided', async () => {
|
||||
mockClient.sendMessageStream.mockReturnValue(
|
||||
(async function* () {
|
||||
yield { kind: 'message' };
|
||||
})(),
|
||||
);
|
||||
|
||||
const stream = manager.sendMessageStream('TestAgent', 'Hello', {
|
||||
contextId: 'ctx123',
|
||||
taskId: 'task456',
|
||||
});
|
||||
// trigger execution
|
||||
for await (const _ of stream) {
|
||||
break;
|
||||
}
|
||||
|
||||
expect(mockClient.sendMessageStream).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
message: expect.anything(),
|
||||
message: expect.objectContaining({
|
||||
contextId: 'ctx123',
|
||||
taskId: 'task456',
|
||||
}),
|
||||
}),
|
||||
expect.any(Object),
|
||||
);
|
||||
});
|
||||
|
||||
it('should use contextId and taskId when provided', async () => {
|
||||
sendMessageStreamMock.mockReturnValue(
|
||||
it('should correctly propagate AbortSignal to the stream', async () => {
|
||||
mockClient.sendMessageStream.mockReturnValue(
|
||||
(async function* () {
|
||||
yield {
|
||||
kind: 'message',
|
||||
messageId: 'a',
|
||||
parts: [],
|
||||
role: 'agent',
|
||||
} as SendMessageResult;
|
||||
yield { kind: 'message' };
|
||||
})(),
|
||||
);
|
||||
|
||||
const expectedContextId = 'user-context-id';
|
||||
const expectedTaskId = 'user-task-id';
|
||||
|
||||
const controller = new AbortController();
|
||||
const stream = manager.sendMessageStream('TestAgent', 'Hello', {
|
||||
contextId: expectedContextId,
|
||||
taskId: expectedTaskId,
|
||||
signal: controller.signal,
|
||||
});
|
||||
|
||||
// trigger execution
|
||||
for await (const _ of stream) {
|
||||
// consume stream
|
||||
break;
|
||||
}
|
||||
|
||||
const call = sendMessageStreamMock.mock.calls[0][0];
|
||||
expect(call.message.contextId).toBe(expectedContextId);
|
||||
expect(call.message.taskId).toBe(expectedTaskId);
|
||||
expect(mockClient.sendMessageStream).toHaveBeenCalledWith(
|
||||
expect.any(Object),
|
||||
expect.objectContaining({ signal: controller.signal }),
|
||||
);
|
||||
});
|
||||
|
||||
it('should propagate the original error on failure', async () => {
|
||||
sendMessageStreamMock.mockImplementationOnce(() => {
|
||||
throw new Error('Network error');
|
||||
it('should handle a multi-chunk stream with different event types', async () => {
|
||||
mockClient.sendMessageStream.mockReturnValue(
|
||||
(async function* () {
|
||||
yield { kind: 'message', messageId: 'm1' };
|
||||
yield { kind: 'status-update', taskId: 't1' };
|
||||
})(),
|
||||
);
|
||||
|
||||
const stream = manager.sendMessageStream('TestAgent', 'Hello');
|
||||
const results = [];
|
||||
for await (const result of stream) {
|
||||
results.push(result);
|
||||
}
|
||||
|
||||
expect(results).toHaveLength(2);
|
||||
expect(results[0].kind).toBe('message');
|
||||
expect(results[1].kind).toBe('status-update');
|
||||
});
|
||||
|
||||
it('should throw prefixed error on failure', async () => {
|
||||
mockClient.sendMessageStream.mockImplementation(() => {
|
||||
throw new Error('Network failure');
|
||||
});
|
||||
|
||||
const stream = manager.sendMessageStream('TestAgent', 'Hello');
|
||||
await expect(async () => {
|
||||
for await (const _ of stream) {
|
||||
// consume
|
||||
// empty
|
||||
}
|
||||
}).rejects.toThrow('Network error');
|
||||
}).rejects.toThrow(
|
||||
'[A2AClientManager] sendMessageStream Error [TestAgent]: Network failure',
|
||||
);
|
||||
});
|
||||
|
||||
it('should throw an error if the agent is not found', async () => {
|
||||
const stream = manager.sendMessageStream('NonExistentAgent', 'Hello');
|
||||
await expect(async () => {
|
||||
for await (const _ of stream) {
|
||||
// consume
|
||||
// empty
|
||||
}
|
||||
}).rejects.toThrow("Agent 'NonExistentAgent' not found.");
|
||||
});
|
||||
@@ -327,28 +438,23 @@ describe('A2AClientManager', () => {
|
||||
|
||||
describe('getTask', () => {
|
||||
beforeEach(async () => {
|
||||
await manager.loadAgent('TestAgent', 'http://test.agent');
|
||||
await manager.loadAgent('TestAgent', 'http://test.agent/card');
|
||||
});
|
||||
|
||||
it('should get a task from the correct agent', async () => {
|
||||
getTaskMock.mockResolvedValue({
|
||||
id: 'task123',
|
||||
contextId: 'a',
|
||||
kind: 'task',
|
||||
status: { state: 'completed' },
|
||||
} as Task);
|
||||
const mockTask = { id: 'task123', kind: 'task' };
|
||||
mockClient.getTask.mockResolvedValue(mockTask);
|
||||
|
||||
await manager.getTask('TestAgent', 'task123');
|
||||
expect(getTaskMock).toHaveBeenCalledWith({
|
||||
id: 'task123',
|
||||
});
|
||||
const result = await manager.getTask('TestAgent', 'task123');
|
||||
expect(result).toBe(mockTask);
|
||||
expect(mockClient.getTask).toHaveBeenCalledWith({ id: 'task123' });
|
||||
});
|
||||
|
||||
it('should throw prefixed error on failure', async () => {
|
||||
getTaskMock.mockRejectedValueOnce(new Error('Network error'));
|
||||
mockClient.getTask.mockRejectedValue(new Error('Not found'));
|
||||
|
||||
await expect(manager.getTask('TestAgent', 'task123')).rejects.toThrow(
|
||||
'A2AClient getTask Error [TestAgent]: Network error',
|
||||
'A2AClient getTask Error [TestAgent]: Not found',
|
||||
);
|
||||
});
|
||||
|
||||
@@ -361,28 +467,23 @@ describe('A2AClientManager', () => {
|
||||
|
||||
describe('cancelTask', () => {
|
||||
beforeEach(async () => {
|
||||
await manager.loadAgent('TestAgent', 'http://test.agent');
|
||||
await manager.loadAgent('TestAgent', 'http://test.agent/card');
|
||||
});
|
||||
|
||||
it('should cancel a task on the correct agent', async () => {
|
||||
cancelTaskMock.mockResolvedValue({
|
||||
id: 'task123',
|
||||
contextId: 'a',
|
||||
kind: 'task',
|
||||
status: { state: 'canceled' },
|
||||
} as Task);
|
||||
const mockTask = { id: 'task123', kind: 'task' };
|
||||
mockClient.cancelTask.mockResolvedValue(mockTask);
|
||||
|
||||
await manager.cancelTask('TestAgent', 'task123');
|
||||
expect(cancelTaskMock).toHaveBeenCalledWith({
|
||||
id: 'task123',
|
||||
});
|
||||
const result = await manager.cancelTask('TestAgent', 'task123');
|
||||
expect(result).toBe(mockTask);
|
||||
expect(mockClient.cancelTask).toHaveBeenCalledWith({ id: 'task123' });
|
||||
});
|
||||
|
||||
it('should throw prefixed error on failure', async () => {
|
||||
cancelTaskMock.mockRejectedValueOnce(new Error('Network error'));
|
||||
mockClient.cancelTask.mockRejectedValue(new Error('Cannot cancel'));
|
||||
|
||||
await expect(manager.cancelTask('TestAgent', 'task123')).rejects.toThrow(
|
||||
'A2AClient cancelTask Error [TestAgent]: Network error',
|
||||
'A2AClient cancelTask Error [TestAgent]: Cannot cancel',
|
||||
);
|
||||
});
|
||||
|
||||
|
||||
@@ -12,45 +12,41 @@ import type {
|
||||
TaskStatusUpdateEvent,
|
||||
TaskArtifactUpdateEvent,
|
||||
} from '@a2a-js/sdk';
|
||||
import type { AuthenticationHandler, Client } from '@a2a-js/sdk/client';
|
||||
import {
|
||||
type Client,
|
||||
ClientFactory,
|
||||
ClientFactoryOptions,
|
||||
DefaultAgentCardResolver,
|
||||
RestTransportFactory,
|
||||
JsonRpcTransportFactory,
|
||||
type AuthenticationHandler,
|
||||
RestTransportFactory,
|
||||
createAuthenticatingFetchWithRetry,
|
||||
} from '@a2a-js/sdk/client';
|
||||
import { GrpcTransportFactory } from '@a2a-js/sdk/client/grpc';
|
||||
import * as grpc from '@grpc/grpc-js';
|
||||
import { v4 as uuidv4 } from 'uuid';
|
||||
import { Agent as UndiciAgent } from 'undici';
|
||||
import { Agent as UndiciAgent, ProxyAgent } from 'undici';
|
||||
import { normalizeAgentCard } from './a2aUtils.js';
|
||||
import type { Config } from '../config/config.js';
|
||||
import { debugLogger } from '../utils/debugLogger.js';
|
||||
import { safeLookup } from '../utils/fetch.js';
|
||||
import { classifyAgentError } from './a2a-errors.js';
|
||||
|
||||
// Remote agents can take 10+ minutes (e.g. Deep Research).
|
||||
// Use a dedicated dispatcher so the global 5-min timeout isn't affected.
|
||||
const A2A_TIMEOUT = 1800000; // 30 minutes
|
||||
const a2aDispatcher = new UndiciAgent({
|
||||
headersTimeout: A2A_TIMEOUT,
|
||||
bodyTimeout: A2A_TIMEOUT,
|
||||
connect: {
|
||||
lookup: safeLookup, // SSRF protection at connection level
|
||||
},
|
||||
});
|
||||
const a2aFetch: typeof fetch = (input, init) =>
|
||||
// eslint-disable-next-line no-restricted-syntax -- TODO: Migrate to safeFetch for SSRF protection
|
||||
fetch(input, { ...init, dispatcher: a2aDispatcher } as RequestInit);
|
||||
|
||||
/**
|
||||
* Result of sending a message, which can be a full message, a task,
|
||||
* or an incremental status/artifact update.
|
||||
*/
|
||||
export type SendMessageResult =
|
||||
| Message
|
||||
| Task
|
||||
| TaskStatusUpdateEvent
|
||||
| TaskArtifactUpdateEvent;
|
||||
|
||||
// Remote agents can take 10+ minutes (e.g. Deep Research).
|
||||
// Use a dedicated dispatcher so the global 5-min timeout isn't affected.
|
||||
const A2A_TIMEOUT = 1800000; // 30 minutes
|
||||
|
||||
/**
|
||||
* Manages A2A clients and caches loaded agent information.
|
||||
* Follows a singleton pattern to ensure a single client instance.
|
||||
* Orchestrates communication with remote A2A agents.
|
||||
* Manages protocol negotiation, authentication, and transport selection.
|
||||
*/
|
||||
export class A2AClientManager {
|
||||
private static instance: A2AClientManager;
|
||||
@@ -59,14 +55,35 @@ export class A2AClientManager {
|
||||
private clients = new Map<string, Client>();
|
||||
private agentCards = new Map<string, AgentCard>();
|
||||
|
||||
private constructor() {}
|
||||
private a2aDispatcher: UndiciAgent | ProxyAgent;
|
||||
private a2aFetch: typeof fetch;
|
||||
|
||||
private constructor(config?: Config) {
|
||||
const proxyUrl = config?.getProxy();
|
||||
const agentOptions = {
|
||||
headersTimeout: A2A_TIMEOUT,
|
||||
bodyTimeout: A2A_TIMEOUT,
|
||||
};
|
||||
|
||||
if (proxyUrl) {
|
||||
this.a2aDispatcher = new ProxyAgent({
|
||||
uri: proxyUrl,
|
||||
...agentOptions,
|
||||
});
|
||||
} else {
|
||||
this.a2aDispatcher = new UndiciAgent(agentOptions);
|
||||
}
|
||||
|
||||
this.a2aFetch = (input, init) =>
|
||||
fetch(input, { ...init, dispatcher: this.a2aDispatcher } as RequestInit);
|
||||
}
|
||||
|
||||
/**
|
||||
* Gets the singleton instance of the A2AClientManager.
|
||||
*/
|
||||
static getInstance(): A2AClientManager {
|
||||
static getInstance(config?: Config): A2AClientManager {
|
||||
if (!A2AClientManager.instance) {
|
||||
A2AClientManager.instance = new A2AClientManager();
|
||||
A2AClientManager.instance = new A2AClientManager(config);
|
||||
}
|
||||
return A2AClientManager.instance;
|
||||
}
|
||||
@@ -97,9 +114,12 @@ export class A2AClientManager {
|
||||
}
|
||||
|
||||
// Authenticated fetch for API calls (transports).
|
||||
let authFetch: typeof fetch = a2aFetch;
|
||||
let authFetch: typeof fetch = this.a2aFetch;
|
||||
if (authHandler) {
|
||||
authFetch = createAuthenticatingFetchWithRetry(a2aFetch, authHandler);
|
||||
authFetch = createAuthenticatingFetchWithRetry(
|
||||
this.a2aFetch,
|
||||
authHandler,
|
||||
);
|
||||
}
|
||||
|
||||
// Use unauthenticated fetch for the agent card unless explicitly required.
|
||||
@@ -109,7 +129,7 @@ export class A2AClientManager {
|
||||
init?: RequestInit,
|
||||
): Promise<Response> => {
|
||||
// Try without auth first
|
||||
const response = await a2aFetch(input, init);
|
||||
const response = await this.a2aFetch(input, init);
|
||||
|
||||
// Retry with auth if we hit a 401/403
|
||||
if ((response.status === 401 || response.status === 403) && authFetch) {
|
||||
@@ -120,22 +140,35 @@ export class A2AClientManager {
|
||||
};
|
||||
|
||||
const resolver = new DefaultAgentCardResolver({ fetchImpl: cardFetch });
|
||||
const rawCard = await resolver.resolve(agentCardUrl, '');
|
||||
// TODO: Remove normalizeAgentCard once @a2a-js/sdk handles
|
||||
// proto field name aliases (supportedInterfaces → additionalInterfaces,
|
||||
// protocolBinding → transport).
|
||||
const agentCard = normalizeAgentCard(rawCard);
|
||||
|
||||
const options = ClientFactoryOptions.createFrom(
|
||||
const grpcUrl =
|
||||
agentCard.additionalInterfaces?.find((i) => i.transport === 'GRPC')
|
||||
?.url ?? agentCard.url;
|
||||
|
||||
const clientOptions = ClientFactoryOptions.createFrom(
|
||||
ClientFactoryOptions.default,
|
||||
{
|
||||
transports: [
|
||||
new RestTransportFactory({ fetchImpl: authFetch }),
|
||||
new JsonRpcTransportFactory({ fetchImpl: authFetch }),
|
||||
new GrpcTransportFactory({
|
||||
grpcChannelCredentials: grpcUrl.startsWith('https://')
|
||||
? grpc.credentials.createSsl()
|
||||
: grpc.credentials.createInsecure(),
|
||||
}),
|
||||
],
|
||||
cardResolver: resolver,
|
||||
},
|
||||
);
|
||||
|
||||
try {
|
||||
const factory = new ClientFactory(options);
|
||||
const client = await factory.createFromUrl(agentCardUrl, '');
|
||||
const agentCard = await client.getAgentCard();
|
||||
const factory = new ClientFactory(clientOptions);
|
||||
const client = await factory.createFromAgentCard(agentCard);
|
||||
|
||||
this.clients.set(name, client);
|
||||
this.agentCards.set(name, agentCard);
|
||||
@@ -173,9 +206,7 @@ export class A2AClientManager {
|
||||
options?: { contextId?: string; taskId?: string; signal?: AbortSignal },
|
||||
): AsyncIterable<SendMessageResult> {
|
||||
const client = this.clients.get(agentName);
|
||||
if (!client) {
|
||||
throw new Error(`Agent '${agentName}' not found.`);
|
||||
}
|
||||
if (!client) throw new Error(`Agent '${agentName}' not found.`);
|
||||
|
||||
const messageParams: MessageSendParams = {
|
||||
message: {
|
||||
@@ -188,9 +219,19 @@ export class A2AClientManager {
|
||||
},
|
||||
};
|
||||
|
||||
yield* client.sendMessageStream(messageParams, {
|
||||
signal: options?.signal,
|
||||
});
|
||||
try {
|
||||
yield* client.sendMessageStream(messageParams, {
|
||||
signal: options?.signal,
|
||||
});
|
||||
} catch (error: unknown) {
|
||||
const prefix = `[A2AClientManager] sendMessageStream Error [${agentName}]`;
|
||||
if (error instanceof Error) {
|
||||
throw new Error(`${prefix}: ${error.message}`, { cause: error });
|
||||
}
|
||||
throw new Error(
|
||||
`${prefix}: Unexpected error during sendMessageStream: ${String(error)}`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -219,9 +260,7 @@ export class A2AClientManager {
|
||||
*/
|
||||
async getTask(agentName: string, taskId: string): Promise<Task> {
|
||||
const client = this.clients.get(agentName);
|
||||
if (!client) {
|
||||
throw new Error(`Agent '${agentName}' not found.`);
|
||||
}
|
||||
if (!client) throw new Error(`Agent '${agentName}' not found.`);
|
||||
try {
|
||||
return await client.getTask({ id: taskId });
|
||||
} catch (error: unknown) {
|
||||
@@ -241,9 +280,7 @@ export class A2AClientManager {
|
||||
*/
|
||||
async cancelTask(agentName: string, taskId: string): Promise<Task> {
|
||||
const client = this.clients.get(agentName);
|
||||
if (!client) {
|
||||
throw new Error(`Agent '${agentName}' not found.`);
|
||||
}
|
||||
if (!client) throw new Error(`Agent '${agentName}' not found.`);
|
||||
try {
|
||||
return await client.cancelTask({ id: taskId });
|
||||
} catch (error: unknown) {
|
||||
|
||||
@@ -12,9 +12,6 @@ import {
|
||||
A2AResultReassembler,
|
||||
AUTH_REQUIRED_MSG,
|
||||
normalizeAgentCard,
|
||||
getGrpcCredentials,
|
||||
pinUrlToIp,
|
||||
splitAgentCardUrl,
|
||||
} from './a2aUtils.js';
|
||||
import type { SendMessageResult } from './a2a-client-manager.js';
|
||||
import type {
|
||||
@@ -26,12 +23,6 @@ import type {
|
||||
TaskStatusUpdateEvent,
|
||||
TaskArtifactUpdateEvent,
|
||||
} from '@a2a-js/sdk';
|
||||
import * as dnsPromises from 'node:dns/promises';
|
||||
import type { LookupAddress } from 'node:dns';
|
||||
|
||||
vi.mock('node:dns/promises', () => ({
|
||||
lookup: vi.fn(),
|
||||
}));
|
||||
|
||||
describe('a2aUtils', () => {
|
||||
beforeEach(() => {
|
||||
@@ -42,89 +33,6 @@ describe('a2aUtils', () => {
|
||||
vi.restoreAllMocks();
|
||||
});
|
||||
|
||||
describe('getGrpcCredentials', () => {
|
||||
it('should return secure credentials for https', () => {
|
||||
const credentials = getGrpcCredentials('https://test.agent');
|
||||
expect(credentials).toBeDefined();
|
||||
});
|
||||
|
||||
it('should return insecure credentials for http', () => {
|
||||
const credentials = getGrpcCredentials('http://test.agent');
|
||||
expect(credentials).toBeDefined();
|
||||
});
|
||||
});
|
||||
|
||||
describe('pinUrlToIp', () => {
|
||||
it('should resolve and pin hostname to IP', async () => {
|
||||
vi.mocked(
|
||||
dnsPromises.lookup as unknown as (
|
||||
hostname: string,
|
||||
options: { all: true },
|
||||
) => Promise<LookupAddress[]>,
|
||||
).mockResolvedValue([{ address: '93.184.216.34', family: 4 }]);
|
||||
|
||||
const { pinnedUrl, hostname } = await pinUrlToIp(
|
||||
'http://example.com:9000',
|
||||
'test-agent',
|
||||
);
|
||||
expect(hostname).toBe('example.com');
|
||||
expect(pinnedUrl).toBe('http://93.184.216.34:9000/');
|
||||
});
|
||||
|
||||
it('should handle raw host:port strings (standard for gRPC)', async () => {
|
||||
vi.mocked(
|
||||
dnsPromises.lookup as unknown as (
|
||||
hostname: string,
|
||||
options: { all: true },
|
||||
) => Promise<LookupAddress[]>,
|
||||
).mockResolvedValue([{ address: '93.184.216.34', family: 4 }]);
|
||||
|
||||
const { pinnedUrl, hostname } = await pinUrlToIp(
|
||||
'example.com:9000',
|
||||
'test-agent',
|
||||
);
|
||||
expect(hostname).toBe('example.com');
|
||||
expect(pinnedUrl).toBe('93.184.216.34:9000');
|
||||
});
|
||||
|
||||
it('should throw error if resolution fails (fail closed)', async () => {
|
||||
vi.mocked(dnsPromises.lookup).mockRejectedValue(new Error('DNS Error'));
|
||||
|
||||
await expect(
|
||||
pinUrlToIp('http://unreachable.com', 'test-agent'),
|
||||
).rejects.toThrow("Failed to resolve host for agent 'test-agent'");
|
||||
});
|
||||
|
||||
it('should throw error if resolved to private IP', async () => {
|
||||
vi.mocked(
|
||||
dnsPromises.lookup as unknown as (
|
||||
hostname: string,
|
||||
options: { all: true },
|
||||
) => Promise<LookupAddress[]>,
|
||||
).mockResolvedValue([{ address: '10.0.0.1', family: 4 }]);
|
||||
|
||||
await expect(
|
||||
pinUrlToIp('http://malicious.com', 'test-agent'),
|
||||
).rejects.toThrow('resolves to private IP range');
|
||||
});
|
||||
|
||||
it('should allow localhost/127.0.0.1/::1 exceptions', async () => {
|
||||
vi.mocked(
|
||||
dnsPromises.lookup as unknown as (
|
||||
hostname: string,
|
||||
options: { all: true },
|
||||
) => Promise<LookupAddress[]>,
|
||||
).mockResolvedValue([{ address: '127.0.0.1', family: 4 }]);
|
||||
|
||||
const { pinnedUrl, hostname } = await pinUrlToIp(
|
||||
'http://localhost:9000',
|
||||
'test-agent',
|
||||
);
|
||||
expect(hostname).toBe('localhost');
|
||||
expect(pinnedUrl).toBe('http://127.0.0.1:9000/');
|
||||
});
|
||||
});
|
||||
|
||||
describe('isTerminalState', () => {
|
||||
it('should return true for completed, failed, canceled, and rejected', () => {
|
||||
expect(isTerminalState('completed')).toBe(true);
|
||||
@@ -365,12 +273,12 @@ describe('a2aUtils', () => {
|
||||
expect(normalized.name).toBe('my-agent');
|
||||
// @ts-expect-error - testing dynamic preservation
|
||||
expect(normalized.customField).toBe('keep-me');
|
||||
expect(normalized.description).toBe('');
|
||||
expect(normalized.skills).toEqual([]);
|
||||
expect(normalized.defaultInputModes).toEqual([]);
|
||||
expect(normalized.description).toBeUndefined();
|
||||
expect(normalized.skills).toBeUndefined();
|
||||
expect(normalized.defaultInputModes).toBeUndefined();
|
||||
});
|
||||
|
||||
it('should normalize and synchronize interfaces while preserving other fields', () => {
|
||||
it('should map supportedInterfaces to additionalInterfaces with protocolBinding → transport', () => {
|
||||
const raw = {
|
||||
name: 'test',
|
||||
supportedInterfaces: [
|
||||
@@ -384,13 +292,7 @@ describe('a2aUtils', () => {
|
||||
|
||||
const normalized = normalizeAgentCard(raw);
|
||||
|
||||
// Should exist in both fields
|
||||
expect(normalized.additionalInterfaces).toHaveLength(1);
|
||||
expect(
|
||||
(normalized as unknown as Record<string, unknown>)[
|
||||
'supportedInterfaces'
|
||||
],
|
||||
).toHaveLength(1);
|
||||
|
||||
const intf = normalized.additionalInterfaces?.[0] as unknown as Record<
|
||||
string,
|
||||
@@ -399,43 +301,18 @@ describe('a2aUtils', () => {
|
||||
|
||||
expect(intf['transport']).toBe('GRPC');
|
||||
expect(intf['url']).toBe('grpc://test');
|
||||
|
||||
// Should fallback top-level url
|
||||
expect(normalized.url).toBe('grpc://test');
|
||||
});
|
||||
|
||||
it('should preserve existing top-level url if present', () => {
|
||||
it('should not overwrite additionalInterfaces if already present', () => {
|
||||
const raw = {
|
||||
name: 'test',
|
||||
url: 'http://existing',
|
||||
additionalInterfaces: [{ url: 'http://grpc', transport: 'GRPC' }],
|
||||
supportedInterfaces: [{ url: 'http://other', transport: 'REST' }],
|
||||
};
|
||||
|
||||
const normalized = normalizeAgentCard(raw);
|
||||
expect(normalized.url).toBe('http://existing');
|
||||
});
|
||||
|
||||
it('should NOT prepend http:// scheme to raw IP:port strings for gRPC interfaces', () => {
|
||||
const raw = {
|
||||
name: 'raw-ip-grpc',
|
||||
supportedInterfaces: [{ url: '127.0.0.1:9000', transport: 'GRPC' }],
|
||||
};
|
||||
|
||||
const normalized = normalizeAgentCard(raw);
|
||||
expect(normalized.additionalInterfaces?.[0].url).toBe('127.0.0.1:9000');
|
||||
expect(normalized.url).toBe('127.0.0.1:9000');
|
||||
});
|
||||
|
||||
it('should prepend http:// scheme to raw IP:port strings for REST interfaces', () => {
|
||||
const raw = {
|
||||
name: 'raw-ip-rest',
|
||||
supportedInterfaces: [{ url: '127.0.0.1:8080', transport: 'REST' }],
|
||||
};
|
||||
|
||||
const normalized = normalizeAgentCard(raw);
|
||||
expect(normalized.additionalInterfaces?.[0].url).toBe(
|
||||
'http://127.0.0.1:8080',
|
||||
);
|
||||
expect(normalized.additionalInterfaces).toHaveLength(1);
|
||||
expect(normalized.additionalInterfaces?.[0].url).toBe('http://grpc');
|
||||
});
|
||||
|
||||
it('should NOT override existing transport if protocolBinding is also present', () => {
|
||||
@@ -448,48 +325,20 @@ describe('a2aUtils', () => {
|
||||
const normalized = normalizeAgentCard(raw);
|
||||
expect(normalized.additionalInterfaces?.[0].transport).toBe('GRPC');
|
||||
});
|
||||
});
|
||||
|
||||
describe('splitAgentCardUrl', () => {
|
||||
const standard = '.well-known/agent-card.json';
|
||||
it('should not mutate the original card object', () => {
|
||||
const raw = {
|
||||
name: 'test',
|
||||
supportedInterfaces: [{ url: 'grpc://test', protocolBinding: 'GRPC' }],
|
||||
};
|
||||
|
||||
it('should return baseUrl as-is if it does not end with standard path', () => {
|
||||
const url = 'http://localhost:9001/custom/path';
|
||||
expect(splitAgentCardUrl(url)).toEqual({ baseUrl: url });
|
||||
});
|
||||
|
||||
it('should split correctly if URL ends with standard path', () => {
|
||||
const url = `http://localhost:9001/${standard}`;
|
||||
expect(splitAgentCardUrl(url)).toEqual({
|
||||
baseUrl: 'http://localhost:9001/',
|
||||
path: undefined,
|
||||
});
|
||||
});
|
||||
|
||||
it('should handle trailing slash in baseUrl when splitting', () => {
|
||||
const url = `http://example.com/api/${standard}`;
|
||||
expect(splitAgentCardUrl(url)).toEqual({
|
||||
baseUrl: 'http://example.com/api/',
|
||||
path: undefined,
|
||||
});
|
||||
});
|
||||
|
||||
it('should ignore hashes and query params when splitting', () => {
|
||||
const url = `http://localhost:9001/${standard}?foo=bar#baz`;
|
||||
expect(splitAgentCardUrl(url)).toEqual({
|
||||
baseUrl: 'http://localhost:9001/',
|
||||
path: undefined,
|
||||
});
|
||||
});
|
||||
|
||||
it('should return original URL if parsing fails', () => {
|
||||
const url = 'not-a-url';
|
||||
expect(splitAgentCardUrl(url)).toEqual({ baseUrl: url });
|
||||
});
|
||||
|
||||
it('should handle standard path appearing earlier in the path', () => {
|
||||
const url = `http://localhost:9001/${standard}/something-else`;
|
||||
expect(splitAgentCardUrl(url)).toEqual({ baseUrl: url });
|
||||
const normalized = normalizeAgentCard(raw);
|
||||
expect(normalized).not.toBe(raw);
|
||||
expect(normalized.additionalInterfaces).toBeDefined();
|
||||
// Original should not have additionalInterfaces added
|
||||
expect(
|
||||
(raw as Record<string, unknown>)['additionalInterfaces'],
|
||||
).toBeUndefined();
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -4,9 +4,6 @@
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import * as grpc from '@grpc/grpc-js';
|
||||
import { lookup } from 'node:dns/promises';
|
||||
import { z } from 'zod';
|
||||
import type {
|
||||
Message,
|
||||
Part,
|
||||
@@ -18,37 +15,10 @@ import type {
|
||||
AgentCard,
|
||||
AgentInterface,
|
||||
} from '@a2a-js/sdk';
|
||||
import { isAddressPrivate } from '../utils/fetch.js';
|
||||
import type { SendMessageResult } from './a2a-client-manager.js';
|
||||
|
||||
export const AUTH_REQUIRED_MSG = `[Authorization Required] The agent has indicated it requires authorization to proceed. Please follow the agent's instructions.`;
|
||||
|
||||
const AgentInterfaceSchema = z
|
||||
.object({
|
||||
url: z.string().default(''),
|
||||
transport: z.string().optional(),
|
||||
protocolBinding: z.string().optional(),
|
||||
})
|
||||
.passthrough();
|
||||
|
||||
const AgentCardSchema = z
|
||||
.object({
|
||||
name: z.string().default('unknown'),
|
||||
description: z.string().default(''),
|
||||
url: z.string().default(''),
|
||||
version: z.string().default(''),
|
||||
protocolVersion: z.string().default(''),
|
||||
capabilities: z.record(z.unknown()).default({}),
|
||||
skills: z.array(z.union([z.string(), z.record(z.unknown())])).default([]),
|
||||
defaultInputModes: z.array(z.string()).default([]),
|
||||
defaultOutputModes: z.array(z.string()).default([]),
|
||||
|
||||
additionalInterfaces: z.array(AgentInterfaceSchema).optional(),
|
||||
supportedInterfaces: z.array(AgentInterfaceSchema).optional(),
|
||||
preferredTransport: z.string().optional(),
|
||||
})
|
||||
.passthrough();
|
||||
|
||||
/**
|
||||
* Reassembles incremental A2A streaming updates into a coherent result.
|
||||
* Shows sequential status/messages followed by all reassembled artifacts.
|
||||
@@ -241,166 +211,45 @@ function extractPartText(part: Part): string {
|
||||
}
|
||||
|
||||
/**
|
||||
* Normalizes an agent card by ensuring it has the required properties
|
||||
* and resolving any inconsistencies between protocol versions.
|
||||
* Normalizes proto field name aliases that the SDK doesn't handle yet.
|
||||
* The A2A proto spec uses `supported_interfaces` and `protocol_binding`,
|
||||
* while the SDK expects `additionalInterfaces` and `transport`.
|
||||
* TODO: Remove once @a2a-js/sdk handles these aliases natively.
|
||||
*/
|
||||
export function normalizeAgentCard(card: unknown): AgentCard {
|
||||
if (!isObject(card)) {
|
||||
throw new Error('Agent card is missing.');
|
||||
}
|
||||
|
||||
// Use Zod to validate and parse the card, ensuring safe defaults and narrowing types.
|
||||
const parsed = AgentCardSchema.parse(card);
|
||||
// Narrowing to AgentCard interface after runtime validation.
|
||||
// Shallow-copy to avoid mutating the SDK's cached object.
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
const result = parsed as unknown as AgentCard;
|
||||
const result = { ...card } as unknown as AgentCard;
|
||||
|
||||
// Normalize interfaces and synchronize both interface fields.
|
||||
const normalizedInterfaces = extractNormalizedInterfaces(parsed);
|
||||
result.additionalInterfaces = normalizedInterfaces;
|
||||
|
||||
// Sync supportedInterfaces for backward compatibility.
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
const legacyResult = result as unknown as Record<string, AgentInterface[]>;
|
||||
legacyResult['supportedInterfaces'] = normalizedInterfaces;
|
||||
|
||||
// Fallback preferredTransport: If not specified, default to GRPC if available.
|
||||
if (
|
||||
!result.preferredTransport &&
|
||||
normalizedInterfaces.some((i) => i.transport === 'GRPC')
|
||||
) {
|
||||
result.preferredTransport = 'GRPC';
|
||||
// Map supportedInterfaces → additionalInterfaces if needed
|
||||
if (!result.additionalInterfaces) {
|
||||
const raw = card;
|
||||
if (Array.isArray(raw['supportedInterfaces'])) {
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
result.additionalInterfaces = raw[
|
||||
'supportedInterfaces'
|
||||
] as AgentInterface[];
|
||||
}
|
||||
}
|
||||
|
||||
// Fallback: If top-level URL is missing, use the first interface's URL.
|
||||
if (result.url === '' && normalizedInterfaces.length > 0) {
|
||||
result.url = normalizedInterfaces[0].url;
|
||||
// Map protocolBinding → transport on each interface
|
||||
for (const intf of result.additionalInterfaces ?? []) {
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
const raw = intf as unknown as Record<string, unknown>;
|
||||
const binding = raw['protocolBinding'];
|
||||
|
||||
if (!intf.transport && typeof binding === 'string') {
|
||||
intf.transport = binding;
|
||||
}
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns gRPC channel credentials based on the URL scheme.
|
||||
*/
|
||||
export function getGrpcCredentials(url: string): grpc.ChannelCredentials {
|
||||
return url.startsWith('https://')
|
||||
? grpc.credentials.createSsl()
|
||||
: grpc.credentials.createInsecure();
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns gRPC channel options to ensure SSL/authority matches the original hostname
|
||||
* when connecting via a pinned IP address.
|
||||
*/
|
||||
export function getGrpcChannelOptions(
|
||||
hostname: string,
|
||||
): Record<string, unknown> {
|
||||
return {
|
||||
'grpc.default_authority': hostname,
|
||||
'grpc.ssl_target_name_override': hostname,
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolves a hostname to its IP address and validates it against SSRF.
|
||||
* Returns the pinned IP-based URL and the original hostname.
|
||||
*/
|
||||
export async function pinUrlToIp(
|
||||
url: string,
|
||||
agentName: string,
|
||||
): Promise<{ pinnedUrl: string; hostname: string }> {
|
||||
if (!url) return { pinnedUrl: url, hostname: '' };
|
||||
|
||||
// gRPC URLs in A2A can be 'host:port' or 'dns:///host:port' or have schemes.
|
||||
// We normalize to host:port for resolution.
|
||||
const hasScheme = url.includes('://');
|
||||
const normalizedUrl = hasScheme ? url : `http://${url}`;
|
||||
|
||||
try {
|
||||
const parsed = new URL(normalizedUrl);
|
||||
const hostname = parsed.hostname;
|
||||
|
||||
const sanitizedHost =
|
||||
hostname.startsWith('[') && hostname.endsWith(']')
|
||||
? hostname.slice(1, -1)
|
||||
: hostname;
|
||||
|
||||
// Resolve DNS to check the actual target IP and pin it
|
||||
const addresses = await lookup(hostname, { all: true });
|
||||
const publicAddresses = addresses.filter(
|
||||
(addr) =>
|
||||
!isAddressPrivate(addr.address) ||
|
||||
sanitizedHost === 'localhost' ||
|
||||
sanitizedHost === '127.0.0.1' ||
|
||||
sanitizedHost === '::1',
|
||||
);
|
||||
|
||||
if (publicAddresses.length === 0) {
|
||||
if (addresses.length > 0) {
|
||||
throw new Error(
|
||||
`Refusing to load agent '${agentName}': transport URL '${url}' resolves to private IP range.`,
|
||||
);
|
||||
}
|
||||
throw new Error(
|
||||
`Failed to resolve any public IP addresses for host: ${hostname}`,
|
||||
);
|
||||
}
|
||||
|
||||
const pinnedIp = publicAddresses[0].address;
|
||||
const pinnedHostname = pinnedIp.includes(':') ? `[${pinnedIp}]` : pinnedIp;
|
||||
|
||||
// Reconstruct URL with IP
|
||||
parsed.hostname = pinnedHostname;
|
||||
let pinnedUrl = parsed.toString();
|
||||
|
||||
// If original didn't have scheme, remove it (standard for gRPC targets)
|
||||
if (!hasScheme) {
|
||||
pinnedUrl = pinnedUrl.replace(/^http:\/\//, '');
|
||||
// URL.toString() might append a trailing slash
|
||||
if (pinnedUrl.endsWith('/') && !url.endsWith('/')) {
|
||||
pinnedUrl = pinnedUrl.slice(0, -1);
|
||||
}
|
||||
}
|
||||
|
||||
return { pinnedUrl, hostname };
|
||||
} catch (e) {
|
||||
if (e instanceof Error && e.message.includes('Refusing')) throw e;
|
||||
throw new Error(`Failed to resolve host for agent '${agentName}': ${url}`, {
|
||||
cause: e,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Splts an agent card URL into a baseUrl and a standard path if it already
|
||||
* contains '.well-known/agent-card.json'.
|
||||
*/
|
||||
export function splitAgentCardUrl(url: string): {
|
||||
baseUrl: string;
|
||||
path?: string;
|
||||
} {
|
||||
const standardPath = '.well-known/agent-card.json';
|
||||
try {
|
||||
const parsedUrl = new URL(url);
|
||||
if (parsedUrl.pathname.endsWith(standardPath)) {
|
||||
// Reconstruct baseUrl from parsed components to avoid issues with hashes or query params.
|
||||
parsedUrl.pathname = parsedUrl.pathname.substring(
|
||||
0,
|
||||
parsedUrl.pathname.lastIndexOf(standardPath),
|
||||
);
|
||||
parsedUrl.search = '';
|
||||
parsedUrl.hash = '';
|
||||
// We return undefined for path if it's the standard one,
|
||||
// because the SDK's DefaultAgentCardResolver appends it automatically.
|
||||
return { baseUrl: parsedUrl.toString(), path: undefined };
|
||||
}
|
||||
} catch (_e) {
|
||||
// Ignore URL parsing errors here, let the resolver handle them.
|
||||
}
|
||||
return { baseUrl: url };
|
||||
}
|
||||
|
||||
/**
|
||||
* Extracts contextId and taskId from a Message, Task, or Update response.
|
||||
* Follows the pattern from the A2A CLI sample to maintain conversational continuity.
|
||||
@@ -446,65 +295,6 @@ export function extractIdsFromResponse(result: SendMessageResult): {
|
||||
return { contextId, taskId, clearTaskId };
|
||||
}
|
||||
|
||||
/**
|
||||
* Extracts and normalizes interfaces from the card, handling protocol version fallbacks.
|
||||
* Preserves all original fields to maintain SDK compatibility.
|
||||
*/
|
||||
function extractNormalizedInterfaces(
|
||||
card: Record<string, unknown>,
|
||||
): AgentInterface[] {
|
||||
const rawInterfaces =
|
||||
getArray(card, 'additionalInterfaces') ||
|
||||
getArray(card, 'supportedInterfaces');
|
||||
|
||||
if (!rawInterfaces) {
|
||||
return [];
|
||||
}
|
||||
|
||||
const mapped: AgentInterface[] = [];
|
||||
for (const i of rawInterfaces) {
|
||||
if (isObject(i)) {
|
||||
// Use schema to validate interface object.
|
||||
const parsed = AgentInterfaceSchema.parse(i);
|
||||
// Narrowing to AgentInterface after runtime validation.
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
const normalized = parsed as unknown as AgentInterface & {
|
||||
protocolBinding?: string;
|
||||
};
|
||||
|
||||
// Normalize 'transport' from 'protocolBinding' if missing.
|
||||
if (!normalized.transport && normalized.protocolBinding) {
|
||||
normalized.transport = normalized.protocolBinding;
|
||||
}
|
||||
|
||||
// Robust URL: Ensure the URL has a scheme (except for gRPC).
|
||||
if (
|
||||
normalized.url &&
|
||||
!normalized.url.includes('://') &&
|
||||
!normalized.url.startsWith('/') &&
|
||||
normalized.transport !== 'GRPC'
|
||||
) {
|
||||
// Default to http:// for insecure REST/JSON-RPC if scheme is missing.
|
||||
normalized.url = `http://${normalized.url}`;
|
||||
}
|
||||
|
||||
mapped.push(normalized as AgentInterface);
|
||||
}
|
||||
}
|
||||
return mapped;
|
||||
}
|
||||
|
||||
/**
|
||||
* Safely extracts an array property from an object.
|
||||
*/
|
||||
function getArray(
|
||||
obj: Record<string, unknown>,
|
||||
key: string,
|
||||
): unknown[] | undefined {
|
||||
const val = obj[key];
|
||||
return Array.isArray(val) ? val : undefined;
|
||||
}
|
||||
|
||||
// Type Guards
|
||||
|
||||
function isTextPart(part: Part): part is TextPart {
|
||||
|
||||
@@ -28,10 +28,10 @@ describe('agent-scheduler', () => {
|
||||
mockMessageBus = {} as Mocked<MessageBus>;
|
||||
mockToolRegistry = {
|
||||
getTool: vi.fn(),
|
||||
getMessageBus: vi.fn().mockReturnValue(mockMessageBus),
|
||||
messageBus: mockMessageBus,
|
||||
} as unknown as Mocked<ToolRegistry>;
|
||||
mockConfig = {
|
||||
getMessageBus: vi.fn().mockReturnValue(mockMessageBus),
|
||||
messageBus: mockMessageBus,
|
||||
toolRegistry: mockToolRegistry,
|
||||
} as unknown as Mocked<Config>;
|
||||
(mockConfig as unknown as { messageBus: MessageBus }).messageBus =
|
||||
@@ -42,7 +42,7 @@ describe('agent-scheduler', () => {
|
||||
|
||||
it('should create a scheduler with agent-specific config', async () => {
|
||||
const mockConfig = {
|
||||
getMessageBus: vi.fn().mockReturnValue(mockMessageBus),
|
||||
messageBus: mockMessageBus,
|
||||
toolRegistry: mockToolRegistry,
|
||||
} as unknown as Mocked<Config>;
|
||||
|
||||
@@ -87,11 +87,11 @@ describe('agent-scheduler', () => {
|
||||
const mainRegistry = { _id: 'main' } as unknown as Mocked<ToolRegistry>;
|
||||
const agentRegistry = {
|
||||
_id: 'agent',
|
||||
getMessageBus: vi.fn().mockReturnValue(mockMessageBus),
|
||||
messageBus: mockMessageBus,
|
||||
} as unknown as Mocked<ToolRegistry>;
|
||||
|
||||
const config = {
|
||||
getMessageBus: vi.fn().mockReturnValue(mockMessageBus),
|
||||
messageBus: mockMessageBus,
|
||||
} as unknown as Mocked<Config>;
|
||||
Object.defineProperty(config, 'toolRegistry', {
|
||||
get: () => mainRegistry,
|
||||
|
||||
@@ -60,7 +60,7 @@ export async function scheduleAgentTools(
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-assignment
|
||||
const agentConfig: Config = Object.create(config);
|
||||
agentConfig.getToolRegistry = () => toolRegistry;
|
||||
agentConfig.getMessageBus = () => toolRegistry.getMessageBus();
|
||||
agentConfig.getMessageBus = () => toolRegistry.messageBus;
|
||||
// Override toolRegistry property so AgentLoopContext reads the agent-specific registry.
|
||||
Object.defineProperty(agentConfig, 'toolRegistry', {
|
||||
get: () => toolRegistry,
|
||||
@@ -69,7 +69,7 @@ export async function scheduleAgentTools(
|
||||
|
||||
const scheduler = new Scheduler({
|
||||
context: agentConfig,
|
||||
messageBus: toolRegistry.getMessageBus(),
|
||||
messageBus: toolRegistry.messageBus,
|
||||
getPreferredEditor: getPreferredEditor ?? (() => undefined),
|
||||
schedulerId,
|
||||
subagent,
|
||||
|
||||
@@ -109,7 +109,7 @@ export const BrowserAgentDefinition = (
|
||||
): LocalAgentDefinition<typeof BrowserTaskResultSchema> => {
|
||||
// Use Preview Flash model if the main model is any of the preview models.
|
||||
// If the main model is not a preview model, use the default flash model.
|
||||
const model = isPreviewModel(config.getModel())
|
||||
const model = isPreviewModel(config.getModel(), config)
|
||||
? PREVIEW_GEMINI_FLASH_MODEL
|
||||
: DEFAULT_GEMINI_FLASH_MODEL;
|
||||
|
||||
|
||||
@@ -7,8 +7,8 @@
|
||||
import type { AgentDefinition } from './types.js';
|
||||
import { GEMINI_MODEL_ALIAS_FLASH } from '../config/models.js';
|
||||
import { z } from 'zod';
|
||||
import type { Config } from '../config/config.js';
|
||||
import { GetInternalDocsTool } from '../tools/get-internal-docs.js';
|
||||
import type { AgentLoopContext } from '../config/agent-loop-context.js';
|
||||
|
||||
const CliHelpReportSchema = z.object({
|
||||
answer: z
|
||||
@@ -24,7 +24,7 @@ const CliHelpReportSchema = z.object({
|
||||
* using its own documentation and runtime state.
|
||||
*/
|
||||
export const CliHelpAgent = (
|
||||
config: Config,
|
||||
context: AgentLoopContext,
|
||||
): AgentDefinition<typeof CliHelpReportSchema> => ({
|
||||
name: 'cli_help',
|
||||
kind: 'local',
|
||||
@@ -69,7 +69,7 @@ export const CliHelpAgent = (
|
||||
},
|
||||
|
||||
toolConfig: {
|
||||
tools: [new GetInternalDocsTool(config.getMessageBus())],
|
||||
tools: [new GetInternalDocsTool(context.messageBus)],
|
||||
},
|
||||
|
||||
promptConfig: {
|
||||
|
||||
@@ -22,9 +22,19 @@ describe('GeneralistAgent', () => {
|
||||
|
||||
it('should create a valid generalist agent definition', () => {
|
||||
const config = makeFakeConfig();
|
||||
vi.spyOn(config, 'getToolRegistry').mockReturnValue({
|
||||
const mockToolRegistry = {
|
||||
getAllToolNames: () => ['tool1', 'tool2', 'agent-tool'],
|
||||
} as unknown as ToolRegistry);
|
||||
} as unknown as ToolRegistry;
|
||||
vi.spyOn(config, 'getToolRegistry').mockReturnValue(mockToolRegistry);
|
||||
Object.defineProperty(config, 'toolRegistry', {
|
||||
get: () => mockToolRegistry,
|
||||
});
|
||||
Object.defineProperty(config, 'config', {
|
||||
get() {
|
||||
return this;
|
||||
},
|
||||
});
|
||||
|
||||
vi.spyOn(config, 'getAgentRegistry').mockReturnValue({
|
||||
getDirectoryContext: () => 'mock directory context',
|
||||
getAllAgentNames: () => ['agent-tool'],
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
*/
|
||||
|
||||
import { z } from 'zod';
|
||||
import type { Config } from '../config/config.js';
|
||||
import type { AgentLoopContext } from '../config/agent-loop-context.js';
|
||||
import { getCoreSystemPrompt } from '../core/prompts.js';
|
||||
import type { LocalAgentDefinition } from './types.js';
|
||||
|
||||
@@ -18,7 +18,7 @@ const GeneralistAgentSchema = z.object({
|
||||
* It uses the same core system prompt as the main agent but in a non-interactive mode.
|
||||
*/
|
||||
export const GeneralistAgent = (
|
||||
config: Config,
|
||||
context: AgentLoopContext,
|
||||
): LocalAgentDefinition<typeof GeneralistAgentSchema> => ({
|
||||
kind: 'local',
|
||||
name: 'generalist',
|
||||
@@ -46,7 +46,7 @@ export const GeneralistAgent = (
|
||||
model: 'inherit',
|
||||
},
|
||||
get toolConfig() {
|
||||
const tools = config.getToolRegistry().getAllToolNames();
|
||||
const tools = context.toolRegistry.getAllToolNames();
|
||||
return {
|
||||
tools,
|
||||
};
|
||||
@@ -54,7 +54,7 @@ export const GeneralistAgent = (
|
||||
get promptConfig() {
|
||||
return {
|
||||
systemPrompt: getCoreSystemPrompt(
|
||||
config,
|
||||
context.config,
|
||||
/*useMemory=*/ undefined,
|
||||
/*interactiveOverride=*/ false,
|
||||
),
|
||||
|
||||
@@ -33,6 +33,7 @@ import {
|
||||
type PartListUnion,
|
||||
type Tool,
|
||||
type CallableTool,
|
||||
type FunctionDeclaration,
|
||||
} from '@google/genai';
|
||||
import type { Config } from '../config/config.js';
|
||||
import { MockTool } from '../test-utils/mock-tool.js';
|
||||
@@ -312,12 +313,9 @@ describe('LocalAgentExecutor', () => {
|
||||
get: () => 'test-prompt-id',
|
||||
configurable: true,
|
||||
});
|
||||
parentToolRegistry = new ToolRegistry(
|
||||
mockConfig,
|
||||
mockConfig.getMessageBus(),
|
||||
);
|
||||
parentToolRegistry = new ToolRegistry(mockConfig, mockConfig.messageBus);
|
||||
parentToolRegistry.registerTool(
|
||||
new LSTool(mockConfig, mockConfig.getMessageBus()),
|
||||
new LSTool(mockConfig, mockConfig.messageBus),
|
||||
);
|
||||
parentToolRegistry.registerTool(
|
||||
new MockTool({ name: READ_FILE_TOOL_NAME }),
|
||||
@@ -523,7 +521,7 @@ describe('LocalAgentExecutor', () => {
|
||||
toolName,
|
||||
'description',
|
||||
{},
|
||||
mockConfig.getMessageBus(),
|
||||
mockConfig.messageBus,
|
||||
);
|
||||
|
||||
// Mock getTool to return our real DiscoveredMCPTool instance
|
||||
@@ -560,6 +558,34 @@ describe('LocalAgentExecutor', () => {
|
||||
|
||||
getToolSpy.mockRestore();
|
||||
});
|
||||
|
||||
it('should not duplicate schemas when instantiated tools are provided in toolConfig', async () => {
|
||||
// Create an instantiated mock tool
|
||||
const instantiatedTool = new MockTool({ name: 'instantiated_tool' });
|
||||
|
||||
// Create an agent definition containing the instantiated tool
|
||||
const definition = createTestDefinition([instantiatedTool]);
|
||||
|
||||
// Create the executor
|
||||
const executor = await LocalAgentExecutor.create(
|
||||
definition,
|
||||
mockConfig,
|
||||
onActivity,
|
||||
);
|
||||
|
||||
// Extract the prepared tools list using the private method
|
||||
const toolsList = (
|
||||
executor as unknown as { prepareToolsList: () => FunctionDeclaration[] }
|
||||
).prepareToolsList();
|
||||
|
||||
// Filter for the specific tool schema
|
||||
const foundSchemas = (
|
||||
toolsList as unknown as FunctionDeclaration[]
|
||||
).filter((t: FunctionDeclaration) => t.name === 'instantiated_tool');
|
||||
|
||||
// Assert that there is exactly ONE schema for this tool
|
||||
expect(foundSchemas).toHaveLength(1);
|
||||
});
|
||||
});
|
||||
|
||||
describe('run (Execution Loop and Logic)', () => {
|
||||
@@ -2466,4 +2492,337 @@ describe('LocalAgentExecutor', () => {
|
||||
expect(mockSetHistory).toHaveBeenCalledWith(compressedHistory);
|
||||
});
|
||||
});
|
||||
|
||||
describe('DeclarativeTool instance tools (browser agent pattern)', () => {
|
||||
/**
|
||||
* The browser agent passes DeclarativeTool instances (not string names) in
|
||||
* toolConfig.tools. These tests ensure that prepareToolsList() and
|
||||
* create() handle that pattern correctly — in particular, that each tool
|
||||
* appears exactly once in the function declarations sent to the model.
|
||||
*/
|
||||
|
||||
/**
|
||||
* Helper that creates a definition using MockTool *instances* in
|
||||
* toolConfig.tools — the same pattern the browser agent uses.
|
||||
*/
|
||||
const createInstanceToolDefinition = (
|
||||
instanceTools: MockTool[],
|
||||
outputConfigMode: 'default' | 'none' = 'default',
|
||||
): LocalAgentDefinition => {
|
||||
const outputConfig =
|
||||
outputConfigMode === 'default'
|
||||
? {
|
||||
outputName: 'finalResult',
|
||||
description: 'The final result.',
|
||||
schema: z.string(),
|
||||
}
|
||||
: undefined;
|
||||
|
||||
return {
|
||||
kind: 'local',
|
||||
name: 'BrowserLikeAgent',
|
||||
description: 'An agent using instance tools.',
|
||||
inputConfig: {
|
||||
inputSchema: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
goal: { type: 'string', description: 'goal' },
|
||||
},
|
||||
required: ['goal'],
|
||||
},
|
||||
},
|
||||
modelConfig: {
|
||||
model: 'gemini-test-model',
|
||||
generateContentConfig: { temperature: 0, topP: 1 },
|
||||
},
|
||||
runConfig: { maxTimeMinutes: 5, maxTurns: 5 },
|
||||
promptConfig: { systemPrompt: 'Achieve: ${goal}.' },
|
||||
toolConfig: {
|
||||
// Cast required because the type expects AnyDeclarativeTool |
|
||||
// string | FunctionDeclaration; MockTool satisfies the first.
|
||||
tools: instanceTools as unknown as AnyDeclarativeTool[],
|
||||
},
|
||||
outputConfig,
|
||||
} as unknown as LocalAgentDefinition;
|
||||
};
|
||||
|
||||
/**
|
||||
* Helper to extract the functionDeclarations sent to GeminiChat.
|
||||
*/
|
||||
const getSentFunctionDeclarations = () => {
|
||||
const chatCtorArgs = MockedGeminiChat.mock.calls[0];
|
||||
const toolsArg = chatCtorArgs[2] as Tool[];
|
||||
return toolsArg[0].functionDeclarations ?? [];
|
||||
};
|
||||
|
||||
it('should produce NO duplicate function declarations when tools are DeclarativeTool instances', async () => {
|
||||
const clickTool = new MockTool({ name: 'click' });
|
||||
const fillTool = new MockTool({ name: 'fill' });
|
||||
const snapshotTool = new MockTool({ name: 'take_snapshot' });
|
||||
|
||||
const definition = createInstanceToolDefinition([
|
||||
clickTool,
|
||||
fillTool,
|
||||
snapshotTool,
|
||||
]);
|
||||
|
||||
mockModelResponse([
|
||||
{
|
||||
name: TASK_COMPLETE_TOOL_NAME,
|
||||
args: { finalResult: 'done' },
|
||||
id: 'c1',
|
||||
},
|
||||
]);
|
||||
|
||||
const executor = await LocalAgentExecutor.create(
|
||||
definition,
|
||||
mockConfig,
|
||||
onActivity,
|
||||
);
|
||||
await executor.run({ goal: 'Test' }, signal);
|
||||
|
||||
const declarations = getSentFunctionDeclarations();
|
||||
const names = declarations.map((d) => d.name);
|
||||
|
||||
// Each tool must appear exactly once
|
||||
expect(names.filter((n) => n === 'click')).toHaveLength(1);
|
||||
expect(names.filter((n) => n === 'fill')).toHaveLength(1);
|
||||
expect(names.filter((n) => n === 'take_snapshot')).toHaveLength(1);
|
||||
|
||||
// Total = 3 tools + complete_task
|
||||
expect(declarations).toHaveLength(4);
|
||||
});
|
||||
|
||||
it('should register DeclarativeTool instances in the isolated tool registry', async () => {
|
||||
const clickTool = new MockTool({ name: 'click' });
|
||||
const navTool = new MockTool({ name: 'navigate_page' });
|
||||
|
||||
const definition = createInstanceToolDefinition([clickTool, navTool]);
|
||||
|
||||
const executor = await LocalAgentExecutor.create(
|
||||
definition,
|
||||
mockConfig,
|
||||
onActivity,
|
||||
);
|
||||
|
||||
const registry = executor['toolRegistry'];
|
||||
expect(registry.getTool('click')).toBeDefined();
|
||||
expect(registry.getTool('navigate_page')).toBeDefined();
|
||||
// Should NOT have tools that were not passed
|
||||
expect(registry.getTool(LS_TOOL_NAME)).toBeUndefined();
|
||||
});
|
||||
|
||||
it('should handle mixed string + DeclarativeTool instances without duplicates', async () => {
|
||||
const instanceTool = new MockTool({ name: 'fill' });
|
||||
|
||||
const definition: LocalAgentDefinition = {
|
||||
kind: 'local',
|
||||
name: 'MixedAgent',
|
||||
description: 'Uses both patterns.',
|
||||
inputConfig: {
|
||||
inputSchema: {
|
||||
type: 'object',
|
||||
properties: { goal: { type: 'string', description: 'goal' } },
|
||||
},
|
||||
},
|
||||
modelConfig: {
|
||||
model: 'gemini-test-model',
|
||||
generateContentConfig: { temperature: 0, topP: 1 },
|
||||
},
|
||||
runConfig: { maxTimeMinutes: 5, maxTurns: 5 },
|
||||
promptConfig: { systemPrompt: 'Achieve: ${goal}.' },
|
||||
toolConfig: {
|
||||
tools: [
|
||||
LS_TOOL_NAME, // string reference
|
||||
instanceTool as unknown as AnyDeclarativeTool, // instance
|
||||
],
|
||||
},
|
||||
outputConfig: {
|
||||
outputName: 'finalResult',
|
||||
description: 'result',
|
||||
schema: z.string(),
|
||||
},
|
||||
} as unknown as LocalAgentDefinition;
|
||||
|
||||
mockModelResponse([
|
||||
{
|
||||
name: TASK_COMPLETE_TOOL_NAME,
|
||||
args: { finalResult: 'ok' },
|
||||
id: 'c1',
|
||||
},
|
||||
]);
|
||||
|
||||
const executor = await LocalAgentExecutor.create(
|
||||
definition,
|
||||
mockConfig,
|
||||
onActivity,
|
||||
);
|
||||
await executor.run({ goal: 'Mixed' }, signal);
|
||||
|
||||
const declarations = getSentFunctionDeclarations();
|
||||
const names = declarations.map((d) => d.name);
|
||||
|
||||
expect(names.filter((n) => n === LS_TOOL_NAME)).toHaveLength(1);
|
||||
expect(names.filter((n) => n === 'fill')).toHaveLength(1);
|
||||
expect(names.filter((n) => n === TASK_COMPLETE_TOOL_NAME)).toHaveLength(
|
||||
1,
|
||||
);
|
||||
// Total = ls + fill + complete_task
|
||||
expect(declarations).toHaveLength(3);
|
||||
});
|
||||
|
||||
it('should correctly execute tools passed as DeclarativeTool instances', async () => {
|
||||
const executeFn = vi.fn().mockResolvedValue({
|
||||
llmContent: 'Clicked successfully.',
|
||||
returnDisplay: 'Clicked successfully.',
|
||||
});
|
||||
const clickTool = new MockTool({ name: 'click', execute: executeFn });
|
||||
|
||||
const definition = createInstanceToolDefinition([clickTool]);
|
||||
|
||||
// Turn 1: Model calls click
|
||||
mockModelResponse([
|
||||
{ name: 'click', args: { uid: '42' }, id: 'call-click' },
|
||||
]);
|
||||
mockScheduleAgentTools.mockResolvedValueOnce([
|
||||
{
|
||||
status: 'success',
|
||||
request: {
|
||||
callId: 'call-click',
|
||||
name: 'click',
|
||||
args: { uid: '42' },
|
||||
isClientInitiated: false,
|
||||
prompt_id: 'test',
|
||||
},
|
||||
tool: {} as AnyDeclarativeTool,
|
||||
invocation: {} as AnyToolInvocation,
|
||||
response: {
|
||||
callId: 'call-click',
|
||||
resultDisplay: 'Clicked',
|
||||
responseParts: [
|
||||
{
|
||||
functionResponse: {
|
||||
name: 'click',
|
||||
response: { result: 'Clicked' },
|
||||
id: 'call-click',
|
||||
},
|
||||
},
|
||||
],
|
||||
error: undefined,
|
||||
errorType: undefined,
|
||||
contentLength: undefined,
|
||||
},
|
||||
},
|
||||
]);
|
||||
|
||||
// Turn 2: Model completes
|
||||
mockModelResponse([
|
||||
{
|
||||
name: TASK_COMPLETE_TOOL_NAME,
|
||||
args: { finalResult: 'done' },
|
||||
id: 'call-done',
|
||||
},
|
||||
]);
|
||||
|
||||
const executor = await LocalAgentExecutor.create(
|
||||
definition,
|
||||
mockConfig,
|
||||
onActivity,
|
||||
);
|
||||
const output = await executor.run({ goal: 'Click test' }, signal);
|
||||
|
||||
// The scheduler should have received the click tool call
|
||||
expect(mockScheduleAgentTools).toHaveBeenCalled();
|
||||
const scheduledRequests = mockScheduleAgentTools.mock
|
||||
.calls[0][1] as ToolCallRequestInfo[];
|
||||
expect(scheduledRequests).toHaveLength(1);
|
||||
expect(scheduledRequests[0].name).toBe('click');
|
||||
|
||||
expect(output.terminate_reason).toBe(AgentTerminateMode.GOAL);
|
||||
});
|
||||
|
||||
it('should always include complete_task even when all tools are instances', async () => {
|
||||
const definition = createInstanceToolDefinition(
|
||||
[new MockTool({ name: 'take_snapshot' })],
|
||||
'none',
|
||||
);
|
||||
|
||||
mockModelResponse([
|
||||
{
|
||||
name: TASK_COMPLETE_TOOL_NAME,
|
||||
args: { result: 'done' },
|
||||
id: 'c1',
|
||||
},
|
||||
]);
|
||||
|
||||
const executor = await LocalAgentExecutor.create(
|
||||
definition,
|
||||
mockConfig,
|
||||
onActivity,
|
||||
);
|
||||
await executor.run({ goal: 'Test' }, signal);
|
||||
|
||||
const declarations = getSentFunctionDeclarations();
|
||||
const names = declarations.map((d) => d.name);
|
||||
|
||||
expect(names).toContain(TASK_COMPLETE_TOOL_NAME);
|
||||
expect(names).toContain('take_snapshot');
|
||||
expect(declarations).toHaveLength(2);
|
||||
});
|
||||
|
||||
it('should produce unique declarations for many instance tools (browser agent scale)', async () => {
|
||||
// Simulates the full set of tools the browser agent typically registers
|
||||
const browserToolNames = [
|
||||
'click',
|
||||
'click_at',
|
||||
'fill',
|
||||
'fill_form',
|
||||
'hover',
|
||||
'drag',
|
||||
'press_key',
|
||||
'take_snapshot',
|
||||
'navigate_page',
|
||||
'new_page',
|
||||
'close_page',
|
||||
'select_page',
|
||||
'evaluate_script',
|
||||
'type_text',
|
||||
];
|
||||
const instanceTools = browserToolNames.map(
|
||||
(name) => new MockTool({ name }),
|
||||
);
|
||||
|
||||
const definition = createInstanceToolDefinition(instanceTools);
|
||||
|
||||
mockModelResponse([
|
||||
{
|
||||
name: TASK_COMPLETE_TOOL_NAME,
|
||||
args: { finalResult: 'done' },
|
||||
id: 'c1',
|
||||
},
|
||||
]);
|
||||
|
||||
const executor = await LocalAgentExecutor.create(
|
||||
definition,
|
||||
mockConfig,
|
||||
onActivity,
|
||||
);
|
||||
await executor.run({ goal: 'Scale test' }, signal);
|
||||
|
||||
const declarations = getSentFunctionDeclarations();
|
||||
const names = declarations.map((d) => d.name);
|
||||
|
||||
// Every tool name must appear exactly once
|
||||
for (const toolName of browserToolNames) {
|
||||
const count = names.filter((n) => n === toolName).length;
|
||||
expect(count).toBe(1);
|
||||
}
|
||||
// Plus complete_task
|
||||
expect(declarations).toHaveLength(browserToolNames.length + 1);
|
||||
|
||||
// Verify the complete set of names has no duplicates
|
||||
const uniqueNames = new Set(names);
|
||||
expect(uniqueNames.size).toBe(names.length);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1209,17 +1209,12 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
|
||||
|
||||
if (toolConfig) {
|
||||
for (const toolRef of toolConfig.tools) {
|
||||
if (typeof toolRef === 'string') {
|
||||
// The names were already expanded and loaded into the registry during creation.
|
||||
} else if (typeof toolRef === 'object' && 'schema' in toolRef) {
|
||||
// Tool instance with an explicit schema property.
|
||||
toolsList.push(toolRef.schema);
|
||||
} else {
|
||||
if (typeof toolRef === 'object' && !('schema' in toolRef)) {
|
||||
// Raw `FunctionDeclaration` object.
|
||||
toolsList.push(toolRef);
|
||||
}
|
||||
}
|
||||
// Add schemas from tools that were explicitly registered by name or wildcard.
|
||||
// Add schemas from tools that were explicitly registered by name, wildcard, or instance.
|
||||
toolsList.push(...this.toolRegistry.getFunctionDeclarations());
|
||||
}
|
||||
|
||||
|
||||
@@ -69,7 +69,7 @@ export class AgentRegistry {
|
||||
* Clears the current registry and re-scans for agents.
|
||||
*/
|
||||
async reload(): Promise<void> {
|
||||
A2AClientManager.getInstance().clearCache();
|
||||
A2AClientManager.getInstance(this.config).clearCache();
|
||||
await this.config.reloadAgents();
|
||||
this.agents.clear();
|
||||
this.allDefinitions.clear();
|
||||
@@ -414,7 +414,7 @@ export class AgentRegistry {
|
||||
|
||||
// Load the remote A2A agent card and register.
|
||||
try {
|
||||
const clientManager = A2AClientManager.getInstance();
|
||||
const clientManager = A2AClientManager.getInstance(this.config);
|
||||
let authHandler: AuthenticationHandler | undefined;
|
||||
if (definition.auth) {
|
||||
const provider = await A2AAuthProviderFactory.create({
|
||||
|
||||
@@ -43,12 +43,12 @@ export const DEFAULT_QUERY_STRING = 'Get Started!';
|
||||
/**
|
||||
* The default maximum number of conversational turns for an agent.
|
||||
*/
|
||||
export const DEFAULT_MAX_TURNS = 15;
|
||||
export const DEFAULT_MAX_TURNS = 30;
|
||||
|
||||
/**
|
||||
* The default maximum execution time for an agent in minutes.
|
||||
*/
|
||||
export const DEFAULT_MAX_TIME_MINUTES = 5;
|
||||
export const DEFAULT_MAX_TIME_MINUTES = 10;
|
||||
|
||||
/**
|
||||
* Represents the validated input parameters passed to an agent upon invocation.
|
||||
@@ -223,12 +223,12 @@ export interface OutputConfig<T extends z.ZodTypeAny> {
|
||||
export interface RunConfig {
|
||||
/**
|
||||
* The maximum execution time for the agent in minutes.
|
||||
* If not specified, defaults to DEFAULT_MAX_TIME_MINUTES (5).
|
||||
* If not specified, defaults to DEFAULT_MAX_TIME_MINUTES (10).
|
||||
*/
|
||||
maxTimeMinutes?: number;
|
||||
/**
|
||||
* The maximum number of conversational turns.
|
||||
* If not specified, defaults to DEFAULT_MAX_TURNS (15).
|
||||
* If not specified, defaults to DEFAULT_MAX_TURNS (30).
|
||||
*/
|
||||
maxTurns?: number;
|
||||
}
|
||||
|
||||
@@ -54,19 +54,21 @@ export function resolvePolicyChain(
|
||||
useCustomToolModel,
|
||||
hasAccessToPreview,
|
||||
);
|
||||
const isAutoPreferred = preferredModel ? isAutoModel(preferredModel) : false;
|
||||
const isAutoConfigured = isAutoModel(configuredModel);
|
||||
const isAutoPreferred = preferredModel
|
||||
? isAutoModel(preferredModel, config)
|
||||
: false;
|
||||
const isAutoConfigured = isAutoModel(configuredModel, config);
|
||||
|
||||
if (resolvedModel === DEFAULT_GEMINI_FLASH_LITE_MODEL) {
|
||||
chain = getFlashLitePolicyChain();
|
||||
} else if (
|
||||
isGemini3Model(resolvedModel) ||
|
||||
isGemini3Model(resolvedModel, config) ||
|
||||
isAutoPreferred ||
|
||||
isAutoConfigured
|
||||
) {
|
||||
if (hasAccessToPreview) {
|
||||
const previewEnabled =
|
||||
isGemini3Model(resolvedModel) ||
|
||||
isGemini3Model(resolvedModel, config) ||
|
||||
preferredModel === PREVIEW_GEMINI_MODEL_AUTO ||
|
||||
configuredModel === PREVIEW_GEMINI_MODEL_AUTO;
|
||||
chain = getModelPolicyChain({
|
||||
|
||||
@@ -700,7 +700,6 @@ async function fetchAndCacheUserInfo(client: OAuth2Client): Promise<void> {
|
||||
return;
|
||||
}
|
||||
|
||||
// eslint-disable-next-line no-restricted-syntax -- TODO: Migrate to safeFetch for SSRF protection
|
||||
const response = await fetch(
|
||||
'https://www.googleapis.com/oauth2/v2/userinfo',
|
||||
{
|
||||
|
||||
@@ -208,6 +208,7 @@ describe('CodeAssistServer', () => {
|
||||
traceId: 'test-trace-id',
|
||||
status: ActionStatus.ACTION_STATUS_NO_ERROR,
|
||||
initiationMethod: InitiationMethod.COMMAND,
|
||||
trajectoryId: 'test-session',
|
||||
streamingLatency: expect.objectContaining({
|
||||
totalLatency: expect.stringMatching(/\d+s/),
|
||||
firstMessageLatency: expect.stringMatching(/\d+s/),
|
||||
@@ -277,6 +278,7 @@ describe('CodeAssistServer', () => {
|
||||
conversationOffered: expect.objectContaining({
|
||||
traceId: 'stream-trace-id',
|
||||
initiationMethod: InitiationMethod.COMMAND,
|
||||
trajectoryId: 'test-session',
|
||||
}),
|
||||
timestamp: expect.stringMatching(
|
||||
/\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}.\d{3}Z/,
|
||||
|
||||
@@ -153,6 +153,7 @@ export class CodeAssistServer implements ContentGenerator {
|
||||
translatedResponse,
|
||||
streamingLatency,
|
||||
req.config?.abortSignal,
|
||||
server.sessionId, // Use sessionId as trajectoryId
|
||||
);
|
||||
|
||||
if (response.consumedCredits) {
|
||||
@@ -223,6 +224,7 @@ export class CodeAssistServer implements ContentGenerator {
|
||||
translatedResponse,
|
||||
streamingLatency,
|
||||
req.config?.abortSignal,
|
||||
this.sessionId, // Use sessionId as trajectoryId
|
||||
);
|
||||
|
||||
if (response.remainingCredits) {
|
||||
|
||||
@@ -92,6 +92,7 @@ describe('telemetry', () => {
|
||||
traceId,
|
||||
undefined,
|
||||
streamingLatency,
|
||||
'trajectory-id',
|
||||
);
|
||||
|
||||
expect(result).toEqual({
|
||||
@@ -102,6 +103,7 @@ describe('telemetry', () => {
|
||||
streamingLatency,
|
||||
isAgentic: true,
|
||||
initiationMethod: InitiationMethod.COMMAND,
|
||||
trajectoryId: 'trajectory-id',
|
||||
});
|
||||
});
|
||||
|
||||
@@ -124,6 +126,7 @@ describe('telemetry', () => {
|
||||
'trace-id',
|
||||
undefined,
|
||||
{},
|
||||
'trajectory-id',
|
||||
);
|
||||
expect(result).toBeUndefined();
|
||||
});
|
||||
@@ -140,6 +143,7 @@ describe('telemetry', () => {
|
||||
'trace-id',
|
||||
signal,
|
||||
{},
|
||||
'trajectory-id',
|
||||
);
|
||||
|
||||
expect(result?.status).toBe(ActionStatus.ACTION_STATUS_CANCELLED);
|
||||
@@ -155,6 +159,7 @@ describe('telemetry', () => {
|
||||
'trace-id',
|
||||
undefined,
|
||||
{},
|
||||
'trajectory-id',
|
||||
);
|
||||
|
||||
expect(result?.status).toBe(ActionStatus.ACTION_STATUS_ERROR_UNKNOWN);
|
||||
@@ -177,6 +182,7 @@ describe('telemetry', () => {
|
||||
'trace-id',
|
||||
undefined,
|
||||
{},
|
||||
'trajectory-id',
|
||||
);
|
||||
|
||||
expect(result?.status).toBe(ActionStatus.ACTION_STATUS_ERROR_UNKNOWN);
|
||||
@@ -194,6 +200,7 @@ describe('telemetry', () => {
|
||||
'trace-id',
|
||||
undefined,
|
||||
{},
|
||||
undefined,
|
||||
);
|
||||
|
||||
expect(result?.status).toBe(ActionStatus.ACTION_STATUS_EMPTY);
|
||||
@@ -214,7 +221,13 @@ describe('telemetry', () => {
|
||||
true,
|
||||
[{ name: 'replace', args: {} }],
|
||||
);
|
||||
const result = createConversationOffered(response, 'id', undefined, {});
|
||||
const result = createConversationOffered(
|
||||
response,
|
||||
'id',
|
||||
undefined,
|
||||
{},
|
||||
undefined,
|
||||
);
|
||||
expect(result?.includedCode).toBe(true);
|
||||
});
|
||||
|
||||
@@ -231,7 +244,13 @@ describe('telemetry', () => {
|
||||
true,
|
||||
[{ name: 'replace', args: {} }],
|
||||
);
|
||||
const result = createConversationOffered(response, 'id', undefined, {});
|
||||
const result = createConversationOffered(
|
||||
response,
|
||||
'id',
|
||||
undefined,
|
||||
{},
|
||||
undefined,
|
||||
);
|
||||
expect(result?.includedCode).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -260,6 +279,7 @@ describe('telemetry', () => {
|
||||
response,
|
||||
streamingLatency,
|
||||
undefined,
|
||||
undefined,
|
||||
);
|
||||
|
||||
expect(serverMock.recordConversationOffered).toHaveBeenCalledWith(
|
||||
@@ -283,6 +303,7 @@ describe('telemetry', () => {
|
||||
response,
|
||||
{},
|
||||
undefined,
|
||||
undefined,
|
||||
);
|
||||
|
||||
expect(serverMock.recordConversationOffered).not.toHaveBeenCalled();
|
||||
|
||||
@@ -36,6 +36,7 @@ export async function recordConversationOffered(
|
||||
response: GenerateContentResponse,
|
||||
streamingLatency: StreamingLatency,
|
||||
abortSignal: AbortSignal | undefined,
|
||||
trajectoryId: string | undefined,
|
||||
): Promise<void> {
|
||||
try {
|
||||
if (traceId) {
|
||||
@@ -44,6 +45,7 @@ export async function recordConversationOffered(
|
||||
traceId,
|
||||
abortSignal,
|
||||
streamingLatency,
|
||||
trajectoryId,
|
||||
);
|
||||
if (offered) {
|
||||
await server.recordConversationOffered(offered);
|
||||
@@ -87,6 +89,7 @@ export function createConversationOffered(
|
||||
traceId: string,
|
||||
signal: AbortSignal | undefined,
|
||||
streamingLatency: StreamingLatency,
|
||||
trajectoryId: string | undefined,
|
||||
): ConversationOffered | undefined {
|
||||
// Only send conversation offered events for responses that contain edit
|
||||
// function calls. Non-edit function calls don't represent file modifications.
|
||||
@@ -107,6 +110,7 @@ export function createConversationOffered(
|
||||
streamingLatency,
|
||||
isAgentic: true,
|
||||
initiationMethod: InitiationMethod.COMMAND,
|
||||
trajectoryId,
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -315,6 +315,7 @@ export interface ConversationOffered {
|
||||
streamingLatency?: StreamingLatency;
|
||||
isAgentic?: boolean;
|
||||
initiationMethod?: InitiationMethod;
|
||||
trajectoryId?: string;
|
||||
}
|
||||
|
||||
export interface StreamingLatency {
|
||||
|
||||
@@ -67,6 +67,7 @@ import {
|
||||
DEFAULT_GEMINI_MODEL_AUTO,
|
||||
} from './models.js';
|
||||
import { Storage } from './storage.js';
|
||||
import type { AgentLoopContext } from './agent-loop-context.js';
|
||||
|
||||
vi.mock('fs', async (importOriginal) => {
|
||||
const actual = await importOriginal<typeof import('fs')>();
|
||||
@@ -641,8 +642,9 @@ describe('Server Config (config.ts)', () => {
|
||||
|
||||
await config.refreshAuth(AuthType.LOGIN_WITH_GOOGLE);
|
||||
|
||||
const loopContext: AgentLoopContext = config;
|
||||
expect(
|
||||
config.getGeminiClient().stripThoughtsFromHistory,
|
||||
loopContext.geminiClient.stripThoughtsFromHistory,
|
||||
).toHaveBeenCalledWith();
|
||||
});
|
||||
|
||||
@@ -660,8 +662,9 @@ describe('Server Config (config.ts)', () => {
|
||||
|
||||
await config.refreshAuth(AuthType.USE_VERTEX_AI);
|
||||
|
||||
const loopContext: AgentLoopContext = config;
|
||||
expect(
|
||||
config.getGeminiClient().stripThoughtsFromHistory,
|
||||
loopContext.geminiClient.stripThoughtsFromHistory,
|
||||
).toHaveBeenCalledWith();
|
||||
});
|
||||
|
||||
@@ -679,8 +682,9 @@ describe('Server Config (config.ts)', () => {
|
||||
|
||||
await config.refreshAuth(AuthType.USE_GEMINI);
|
||||
|
||||
const loopContext: AgentLoopContext = config;
|
||||
expect(
|
||||
config.getGeminiClient().stripThoughtsFromHistory,
|
||||
loopContext.geminiClient.stripThoughtsFromHistory,
|
||||
).not.toHaveBeenCalledWith();
|
||||
});
|
||||
});
|
||||
@@ -3059,7 +3063,8 @@ describe('Config JIT Initialization', () => {
|
||||
await config.initialize();
|
||||
|
||||
const skillManager = config.getSkillManager();
|
||||
const toolRegistry = config.getToolRegistry();
|
||||
const loopContext: AgentLoopContext = config;
|
||||
const toolRegistry = loopContext.toolRegistry;
|
||||
|
||||
vi.spyOn(skillManager, 'discoverSkills').mockResolvedValue(undefined);
|
||||
vi.spyOn(skillManager, 'setDisabledSkills');
|
||||
@@ -3095,7 +3100,8 @@ describe('Config JIT Initialization', () => {
|
||||
await config.initialize();
|
||||
|
||||
const skillManager = config.getSkillManager();
|
||||
const toolRegistry = config.getToolRegistry();
|
||||
const loopContext: AgentLoopContext = config;
|
||||
const toolRegistry = loopContext.toolRegistry;
|
||||
|
||||
vi.spyOn(skillManager, 'discoverSkills').mockResolvedValue(undefined);
|
||||
vi.spyOn(toolRegistry, 'registerTool');
|
||||
|
||||
@@ -601,6 +601,7 @@ export interface ConfigParameters {
|
||||
disableYoloMode?: boolean;
|
||||
rawOutput?: boolean;
|
||||
acceptRawOutputRisk?: boolean;
|
||||
dynamicModelConfiguration?: boolean;
|
||||
modelConfigServiceConfig?: ModelConfigServiceConfig;
|
||||
enableHooks?: boolean;
|
||||
enableHooksUI?: boolean;
|
||||
@@ -799,6 +800,7 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
private readonly disableYoloMode: boolean;
|
||||
private readonly rawOutput: boolean;
|
||||
private readonly acceptRawOutputRisk: boolean;
|
||||
private readonly dynamicModelConfiguration: boolean;
|
||||
private pendingIncludeDirectories: string[];
|
||||
private readonly enableHooks: boolean;
|
||||
private readonly enableHooksUI: boolean;
|
||||
@@ -987,7 +989,7 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
this.truncateToolOutputThreshold =
|
||||
params.truncateToolOutputThreshold ??
|
||||
DEFAULT_TRUNCATE_TOOL_OUTPUT_THRESHOLD;
|
||||
this.useWriteTodos = isPreviewModel(this.model)
|
||||
this.useWriteTodos = isPreviewModel(this.model, this)
|
||||
? false
|
||||
: (params.useWriteTodos ?? true);
|
||||
this.workspacePoliciesDir = params.workspacePoliciesDir;
|
||||
@@ -1036,7 +1038,7 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
// Register Conseca if enabled
|
||||
if (this.enableConseca) {
|
||||
debugLogger.log('[SAFETY] Registering Conseca Safety Checker');
|
||||
ConsecaSafetyChecker.getInstance().setConfig(this);
|
||||
ConsecaSafetyChecker.getInstance().setContext(this);
|
||||
}
|
||||
|
||||
this._messageBus = new MessageBus(this.policyEngine, this.debugMode);
|
||||
@@ -1062,6 +1064,7 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
this.disableYoloMode = params.disableYoloMode ?? false;
|
||||
this.rawOutput = params.rawOutput ?? false;
|
||||
this.acceptRawOutputRisk = params.acceptRawOutputRisk ?? false;
|
||||
this.dynamicModelConfiguration = params.dynamicModelConfiguration ?? false;
|
||||
|
||||
if (params.hooks) {
|
||||
this.hooks = params.hooks;
|
||||
@@ -1111,18 +1114,23 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
// remove this hack.
|
||||
let modelConfigServiceConfig = params.modelConfigServiceConfig;
|
||||
if (modelConfigServiceConfig) {
|
||||
if (!modelConfigServiceConfig.aliases) {
|
||||
modelConfigServiceConfig = {
|
||||
...modelConfigServiceConfig,
|
||||
aliases: DEFAULT_MODEL_CONFIGS.aliases,
|
||||
};
|
||||
}
|
||||
if (!modelConfigServiceConfig.overrides) {
|
||||
modelConfigServiceConfig = {
|
||||
...modelConfigServiceConfig,
|
||||
overrides: DEFAULT_MODEL_CONFIGS.overrides,
|
||||
};
|
||||
}
|
||||
// Ensure user-defined model definitions augment, not replace, the defaults.
|
||||
const mergedModelDefinitions = {
|
||||
...DEFAULT_MODEL_CONFIGS.modelDefinitions,
|
||||
...modelConfigServiceConfig.modelDefinitions,
|
||||
};
|
||||
|
||||
modelConfigServiceConfig = {
|
||||
// Preserve other user settings like customAliases
|
||||
...modelConfigServiceConfig,
|
||||
// Apply defaults for aliases and overrides if they are not provided
|
||||
aliases:
|
||||
modelConfigServiceConfig.aliases ?? DEFAULT_MODEL_CONFIGS.aliases,
|
||||
overrides:
|
||||
modelConfigServiceConfig.overrides ?? DEFAULT_MODEL_CONFIGS.overrides,
|
||||
// Use the merged model definitions
|
||||
modelDefinitions: mergedModelDefinitions,
|
||||
};
|
||||
}
|
||||
|
||||
this.modelConfigService = new ModelConfigService(
|
||||
@@ -1225,8 +1233,8 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
|
||||
// Re-register ActivateSkillTool to update its schema with the discovered enabled skill enums
|
||||
if (this.getSkillManager().getSkills().length > 0) {
|
||||
this.getToolRegistry().unregisterTool(ActivateSkillTool.Name);
|
||||
this.getToolRegistry().registerTool(
|
||||
this.toolRegistry.unregisterTool(ActivateSkillTool.Name);
|
||||
this.toolRegistry.registerTool(
|
||||
new ActivateSkillTool(this, this.messageBus),
|
||||
);
|
||||
}
|
||||
@@ -1325,7 +1333,10 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
|
||||
// Only reset when we have explicit "no access" (hasAccessToPreviewModel === false).
|
||||
// When null (quota not fetched) or true, we preserve the saved model.
|
||||
if (isPreviewModel(this.model) && this.hasAccessToPreviewModel === false) {
|
||||
if (
|
||||
isPreviewModel(this.model, this) &&
|
||||
this.hasAccessToPreviewModel === false
|
||||
) {
|
||||
this.setModel(DEFAULT_GEMINI_MODEL_AUTO);
|
||||
}
|
||||
|
||||
@@ -1397,14 +1408,26 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
return this._sessionId;
|
||||
}
|
||||
|
||||
/**
|
||||
* @deprecated Do not access directly on Config.
|
||||
* Use the injected AgentLoopContext instead.
|
||||
*/
|
||||
get toolRegistry(): ToolRegistry {
|
||||
return this._toolRegistry;
|
||||
}
|
||||
|
||||
/**
|
||||
* @deprecated Do not access directly on Config.
|
||||
* Use the injected AgentLoopContext instead.
|
||||
*/
|
||||
get messageBus(): MessageBus {
|
||||
return this._messageBus;
|
||||
}
|
||||
|
||||
/**
|
||||
* @deprecated Do not access directly on Config.
|
||||
* Use the injected AgentLoopContext instead.
|
||||
*/
|
||||
get geminiClient(): GeminiClient {
|
||||
return this._geminiClient;
|
||||
}
|
||||
@@ -1581,7 +1604,7 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
|
||||
const isPreview =
|
||||
model === PREVIEW_GEMINI_MODEL_AUTO ||
|
||||
isPreviewModel(this.getActiveModel());
|
||||
isPreviewModel(this.getActiveModel(), this);
|
||||
const proModel = isPreview ? PREVIEW_GEMINI_MODEL : DEFAULT_GEMINI_MODEL;
|
||||
const flashModel = isPreview
|
||||
? PREVIEW_GEMINI_FLASH_MODEL
|
||||
@@ -1779,8 +1802,9 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
}
|
||||
|
||||
const hasAccess =
|
||||
quota.buckets?.some((b) => b.modelId && isPreviewModel(b.modelId)) ??
|
||||
false;
|
||||
quota.buckets?.some(
|
||||
(b) => b.modelId && isPreviewModel(b.modelId, this),
|
||||
) ?? false;
|
||||
this.setHasAccessToPreviewModel(hasAccess);
|
||||
return quota;
|
||||
} catch (e) {
|
||||
@@ -2172,6 +2196,10 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
return this.acceptRawOutputRisk;
|
||||
}
|
||||
|
||||
getExperimentalDynamicModelConfiguration(): boolean {
|
||||
return this.dynamicModelConfiguration;
|
||||
}
|
||||
|
||||
getPendingIncludeDirectories(): string[] {
|
||||
return this.pendingIncludeDirectories;
|
||||
}
|
||||
@@ -2243,7 +2271,7 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
* Whenever the user memory (GEMINI.md files) is updated.
|
||||
*/
|
||||
updateSystemInstructionIfInitialized(): void {
|
||||
const geminiClient = this.getGeminiClient();
|
||||
const geminiClient = this.geminiClient;
|
||||
if (geminiClient?.isInitialized()) {
|
||||
geminiClient.updateSystemInstruction();
|
||||
}
|
||||
@@ -2709,16 +2737,16 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
|
||||
// Re-register ActivateSkillTool to update its schema with the newly discovered skills
|
||||
if (this.getSkillManager().getSkills().length > 0) {
|
||||
this.getToolRegistry().unregisterTool(ActivateSkillTool.Name);
|
||||
this.getToolRegistry().registerTool(
|
||||
this.toolRegistry.unregisterTool(ActivateSkillTool.Name);
|
||||
this.toolRegistry.registerTool(
|
||||
new ActivateSkillTool(this, this.messageBus),
|
||||
);
|
||||
} else {
|
||||
this.getToolRegistry().unregisterTool(ActivateSkillTool.Name);
|
||||
this.toolRegistry.unregisterTool(ActivateSkillTool.Name);
|
||||
}
|
||||
} else {
|
||||
this.getSkillManager().clearSkills();
|
||||
this.getToolRegistry().unregisterTool(ActivateSkillTool.Name);
|
||||
this.toolRegistry.unregisterTool(ActivateSkillTool.Name);
|
||||
}
|
||||
|
||||
// Notify the client that system instructions might need updating
|
||||
@@ -3054,7 +3082,7 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
|
||||
for (const definition of definitions) {
|
||||
try {
|
||||
const tool = new SubagentTool(definition, this, this.getMessageBus());
|
||||
const tool = new SubagentTool(definition, this, this.messageBus);
|
||||
registry.registerTool(tool);
|
||||
} catch (e: unknown) {
|
||||
debugLogger.warn(
|
||||
@@ -3159,7 +3187,7 @@ export class Config implements McpContext, AgentLoopContext {
|
||||
this.registerSubAgentTools(this._toolRegistry);
|
||||
}
|
||||
// Propagate updates to the active chat session
|
||||
const client = this.getGeminiClient();
|
||||
const client = this.geminiClient;
|
||||
if (client?.isInitialized()) {
|
||||
await client.setTools();
|
||||
client.updateSystemInstruction();
|
||||
|
||||
@@ -249,4 +249,94 @@ export const DEFAULT_MODEL_CONFIGS: ModelConfigServiceConfig = {
|
||||
},
|
||||
},
|
||||
],
|
||||
modelDefinitions: {
|
||||
// Concrete Models
|
||||
'gemini-3.1-pro-preview': {
|
||||
tier: 'pro',
|
||||
family: 'gemini-3',
|
||||
isPreview: true,
|
||||
dialogLocation: 'manual',
|
||||
features: { thinking: true, multimodalToolUse: true },
|
||||
},
|
||||
'gemini-3.1-pro-preview-customtools': {
|
||||
tier: 'pro',
|
||||
family: 'gemini-3',
|
||||
isPreview: true,
|
||||
features: { thinking: true, multimodalToolUse: true },
|
||||
},
|
||||
'gemini-3-pro-preview': {
|
||||
tier: 'pro',
|
||||
family: 'gemini-3',
|
||||
isPreview: true,
|
||||
dialogLocation: 'manual',
|
||||
features: { thinking: true, multimodalToolUse: true },
|
||||
},
|
||||
'gemini-3-flash-preview': {
|
||||
tier: 'flash',
|
||||
family: 'gemini-3',
|
||||
isPreview: true,
|
||||
dialogLocation: 'manual',
|
||||
features: { thinking: false, multimodalToolUse: true },
|
||||
},
|
||||
'gemini-2.5-pro': {
|
||||
tier: 'pro',
|
||||
family: 'gemini-2.5',
|
||||
isPreview: false,
|
||||
dialogLocation: 'manual',
|
||||
features: { thinking: false, multimodalToolUse: false },
|
||||
},
|
||||
'gemini-2.5-flash': {
|
||||
tier: 'flash',
|
||||
family: 'gemini-2.5',
|
||||
isPreview: false,
|
||||
dialogLocation: 'manual',
|
||||
features: { thinking: false, multimodalToolUse: false },
|
||||
},
|
||||
'gemini-2.5-flash-lite': {
|
||||
tier: 'flash-lite',
|
||||
family: 'gemini-2.5',
|
||||
isPreview: false,
|
||||
dialogLocation: 'manual',
|
||||
features: { thinking: false, multimodalToolUse: false },
|
||||
},
|
||||
// Aliases
|
||||
auto: {
|
||||
tier: 'auto',
|
||||
isPreview: true,
|
||||
features: { thinking: true, multimodalToolUse: false },
|
||||
},
|
||||
pro: {
|
||||
tier: 'pro',
|
||||
isPreview: false,
|
||||
features: { thinking: true, multimodalToolUse: false },
|
||||
},
|
||||
flash: {
|
||||
tier: 'flash',
|
||||
isPreview: false,
|
||||
features: { thinking: false, multimodalToolUse: false },
|
||||
},
|
||||
'flash-lite': {
|
||||
tier: 'flash-lite',
|
||||
isPreview: false,
|
||||
features: { thinking: false, multimodalToolUse: false },
|
||||
},
|
||||
'auto-gemini-3': {
|
||||
displayName: 'Auto (Gemini 3)',
|
||||
tier: 'auto',
|
||||
isPreview: true,
|
||||
dialogLocation: 'main',
|
||||
dialogDescription:
|
||||
'Let Gemini CLI decide the best model for the task: gemini-3.1-pro, gemini-3-flash',
|
||||
features: { thinking: true, multimodalToolUse: false },
|
||||
},
|
||||
'auto-gemini-2.5': {
|
||||
displayName: 'Auto (Gemini 2.5)',
|
||||
tier: 'auto',
|
||||
isPreview: false,
|
||||
dialogLocation: 'main',
|
||||
dialogDescription:
|
||||
'Let Gemini CLI decide the best model for the task: gemini-2.5-pro, gemini-2.5-flash',
|
||||
features: { thinking: false, multimodalToolUse: false },
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
@@ -36,6 +36,121 @@ import {
|
||||
VALID_GEMINI_MODELS,
|
||||
VALID_ALIASES,
|
||||
} from './models.js';
|
||||
import type { Config } from './config.js';
|
||||
import { ModelConfigService } from '../services/modelConfigService.js';
|
||||
import { DEFAULT_MODEL_CONFIGS } from './defaultModelConfigs.js';
|
||||
|
||||
const modelConfigService = new ModelConfigService(DEFAULT_MODEL_CONFIGS);
|
||||
|
||||
const dynamicConfig = {
|
||||
getExperimentalDynamicModelConfiguration: () => true,
|
||||
modelConfigService,
|
||||
} as unknown as Config;
|
||||
|
||||
const legacyConfig = {
|
||||
getExperimentalDynamicModelConfiguration: () => false,
|
||||
modelConfigService,
|
||||
} as unknown as Config;
|
||||
|
||||
describe('Dynamic Configuration Parity', () => {
|
||||
const modelsToTest = [
|
||||
GEMINI_MODEL_ALIAS_AUTO,
|
||||
GEMINI_MODEL_ALIAS_PRO,
|
||||
GEMINI_MODEL_ALIAS_FLASH,
|
||||
GEMINI_MODEL_ALIAS_FLASH_LITE,
|
||||
PREVIEW_GEMINI_MODEL_AUTO,
|
||||
DEFAULT_GEMINI_MODEL_AUTO,
|
||||
PREVIEW_GEMINI_MODEL,
|
||||
DEFAULT_GEMINI_MODEL,
|
||||
'custom-model',
|
||||
];
|
||||
|
||||
it('getDisplayString should match legacy behavior', () => {
|
||||
for (const model of modelsToTest) {
|
||||
const legacy = getDisplayString(model, legacyConfig);
|
||||
const dynamic = getDisplayString(model, dynamicConfig);
|
||||
expect(dynamic).toBe(legacy);
|
||||
}
|
||||
});
|
||||
|
||||
it('isPreviewModel should match legacy behavior', () => {
|
||||
const allModels = [
|
||||
...modelsToTest,
|
||||
PREVIEW_GEMINI_3_1_MODEL,
|
||||
PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL,
|
||||
PREVIEW_GEMINI_FLASH_MODEL,
|
||||
];
|
||||
for (const model of allModels) {
|
||||
const legacy = isPreviewModel(model, legacyConfig);
|
||||
const dynamic = isPreviewModel(model, dynamicConfig);
|
||||
expect(dynamic).toBe(legacy);
|
||||
}
|
||||
});
|
||||
|
||||
it('isProModel should match legacy behavior', () => {
|
||||
for (const model of modelsToTest) {
|
||||
const legacy = isProModel(model, legacyConfig);
|
||||
const dynamic = isProModel(model, dynamicConfig);
|
||||
expect(dynamic).toBe(legacy);
|
||||
}
|
||||
});
|
||||
|
||||
it('isGemini3Model should match legacy behavior', () => {
|
||||
for (const model of modelsToTest) {
|
||||
const legacy = isGemini3Model(model, legacyConfig);
|
||||
const dynamic = isGemini3Model(model, dynamicConfig);
|
||||
expect(dynamic).toBe(legacy);
|
||||
}
|
||||
});
|
||||
|
||||
it('isGemini2Model should match legacy behavior', () => {
|
||||
for (const model of modelsToTest) {
|
||||
const legacy = isGemini2Model(model, legacyConfig);
|
||||
const dynamic = isGemini2Model(model, dynamicConfig);
|
||||
expect(dynamic).toBe(legacy);
|
||||
}
|
||||
});
|
||||
|
||||
it('isCustomModel should match legacy behavior', () => {
|
||||
for (const model of modelsToTest) {
|
||||
const legacy = isCustomModel(model, legacyConfig);
|
||||
const dynamic = isCustomModel(model, dynamicConfig);
|
||||
expect(dynamic).toBe(legacy);
|
||||
}
|
||||
});
|
||||
|
||||
it('supportsModernFeatures should match legacy behavior', () => {
|
||||
for (const model of modelsToTest) {
|
||||
const legacy = supportsModernFeatures(model, legacyConfig);
|
||||
const dynamic = supportsModernFeatures(model, dynamicConfig);
|
||||
expect(dynamic).toBe(legacy);
|
||||
}
|
||||
});
|
||||
|
||||
it('isActiveModel should match legacy behavior', () => {
|
||||
for (const model of modelsToTest) {
|
||||
const legacy = isActiveModel(model, false, false, legacyConfig);
|
||||
const dynamic = isActiveModel(model, false, false, dynamicConfig);
|
||||
expect(dynamic).toBe(legacy);
|
||||
}
|
||||
});
|
||||
|
||||
it('isValidModelOrAlias should match legacy behavior', () => {
|
||||
for (const model of modelsToTest) {
|
||||
const legacy = isValidModelOrAlias(model, legacyConfig);
|
||||
const dynamic = isValidModelOrAlias(model, dynamicConfig);
|
||||
expect(dynamic).toBe(legacy);
|
||||
}
|
||||
});
|
||||
|
||||
it('supportsMultimodalFunctionResponse should match legacy behavior', () => {
|
||||
for (const model of modelsToTest) {
|
||||
const legacy = supportsMultimodalFunctionResponse(model, legacyConfig);
|
||||
const dynamic = supportsMultimodalFunctionResponse(model, dynamicConfig);
|
||||
expect(dynamic).toBe(legacy);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('isPreviewModel', () => {
|
||||
it('should return true for preview models', () => {
|
||||
|
||||
@@ -4,6 +4,8 @@
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { ModelConfigService } from '../services/modelConfigService.js';
|
||||
|
||||
export const PREVIEW_GEMINI_MODEL = 'gemini-3-pro-preview';
|
||||
export const PREVIEW_GEMINI_3_1_MODEL = 'gemini-3.1-pro-preview';
|
||||
export const PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL =
|
||||
@@ -46,6 +48,15 @@ export const DEFAULT_GEMINI_EMBEDDING_MODEL = 'gemini-embedding-001';
|
||||
// Cap the thinking at 8192 to prevent run-away thinking loops.
|
||||
export const DEFAULT_THINKING_MODE = 8192;
|
||||
|
||||
/**
|
||||
* Represents the minimal configuration needed to resolve models dynamically.
|
||||
* This breaks circular dependencies by avoiding an import of the full Config class.
|
||||
*/
|
||||
export interface ModelResolutionContext {
|
||||
getExperimentalDynamicModelConfiguration?: () => boolean;
|
||||
modelConfigService: ModelConfigService;
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolves the requested model alias (e.g., 'auto-gemini-3', 'pro', 'flash', 'flash-lite')
|
||||
* to a concrete model name.
|
||||
@@ -148,7 +159,17 @@ export function resolveClassifierModel(
|
||||
}
|
||||
return resolveModel(requestedModel, useGemini3_1, useCustomToolModel);
|
||||
}
|
||||
export function getDisplayString(model: string) {
|
||||
export function getDisplayString(
|
||||
model: string,
|
||||
config?: ModelResolutionContext,
|
||||
) {
|
||||
if (config?.getExperimentalDynamicModelConfiguration?.() === true) {
|
||||
const definition = config.modelConfigService.getModelDefinition(model);
|
||||
if (definition?.displayName) {
|
||||
return definition.displayName;
|
||||
}
|
||||
}
|
||||
|
||||
switch (model) {
|
||||
case PREVIEW_GEMINI_MODEL_AUTO:
|
||||
return 'Auto (Gemini 3)';
|
||||
@@ -169,9 +190,19 @@ export function getDisplayString(model: string) {
|
||||
* Checks if the model is a preview model.
|
||||
*
|
||||
* @param model The model name to check.
|
||||
* @param config Optional config object for dynamic model configuration.
|
||||
* @returns True if the model is a preview model.
|
||||
*/
|
||||
export function isPreviewModel(model: string): boolean {
|
||||
export function isPreviewModel(
|
||||
model: string,
|
||||
config?: ModelResolutionContext,
|
||||
): boolean {
|
||||
if (config?.getExperimentalDynamicModelConfiguration?.() === true) {
|
||||
return (
|
||||
config.modelConfigService.getModelDefinition(model)?.isPreview === true
|
||||
);
|
||||
}
|
||||
|
||||
return (
|
||||
model === PREVIEW_GEMINI_MODEL ||
|
||||
model === PREVIEW_GEMINI_3_1_MODEL ||
|
||||
@@ -186,9 +217,16 @@ export function isPreviewModel(model: string): boolean {
|
||||
* Checks if the model is a Pro model.
|
||||
*
|
||||
* @param model The model name to check.
|
||||
* @param config Optional config object for dynamic model configuration.
|
||||
* @returns True if the model is a Pro model.
|
||||
*/
|
||||
export function isProModel(model: string): boolean {
|
||||
export function isProModel(
|
||||
model: string,
|
||||
config?: ModelResolutionContext,
|
||||
): boolean {
|
||||
if (config?.getExperimentalDynamicModelConfiguration?.() === true) {
|
||||
return config.modelConfigService.getModelDefinition(model)?.tier === 'pro';
|
||||
}
|
||||
return model.toLowerCase().includes('pro');
|
||||
}
|
||||
|
||||
@@ -196,9 +234,22 @@ export function isProModel(model: string): boolean {
|
||||
* Checks if the model is a Gemini 3 model.
|
||||
*
|
||||
* @param model The model name to check.
|
||||
* @param config Optional config object for dynamic model configuration.
|
||||
* @returns True if the model is a Gemini 3 model.
|
||||
*/
|
||||
export function isGemini3Model(model: string): boolean {
|
||||
export function isGemini3Model(
|
||||
model: string,
|
||||
config?: ModelResolutionContext,
|
||||
): boolean {
|
||||
if (config?.getExperimentalDynamicModelConfiguration?.() === true) {
|
||||
// Legacy behavior resolves the model first.
|
||||
const resolved = resolveModel(model);
|
||||
return (
|
||||
config.modelConfigService.getModelDefinition(resolved)?.family ===
|
||||
'gemini-3'
|
||||
);
|
||||
}
|
||||
|
||||
const resolved = resolveModel(model);
|
||||
return /^gemini-3(\.|-|$)/.test(resolved);
|
||||
}
|
||||
@@ -207,9 +258,20 @@ export function isGemini3Model(model: string): boolean {
|
||||
* Checks if the model is a Gemini 2.x model.
|
||||
*
|
||||
* @param model The model name to check.
|
||||
* @param config Optional config object for dynamic model configuration.
|
||||
* @returns True if the model is a Gemini-2.x model.
|
||||
*/
|
||||
export function isGemini2Model(model: string): boolean {
|
||||
export function isGemini2Model(
|
||||
model: string,
|
||||
config?: ModelResolutionContext,
|
||||
): boolean {
|
||||
if (config?.getExperimentalDynamicModelConfiguration?.() === true) {
|
||||
// Legacy behavior does NOT resolve the model first for Gemini 2 check.
|
||||
return (
|
||||
config.modelConfigService.getModelDefinition(model)?.family ===
|
||||
'gemini-2.5'
|
||||
);
|
||||
}
|
||||
return /^gemini-2(\.|$)/.test(model);
|
||||
}
|
||||
|
||||
@@ -217,9 +279,20 @@ export function isGemini2Model(model: string): boolean {
|
||||
* Checks if the model is a "custom" model (not Gemini branded).
|
||||
*
|
||||
* @param model The model name to check.
|
||||
* @param config Optional config object for dynamic model configuration.
|
||||
* @returns True if the model is not a Gemini branded model.
|
||||
*/
|
||||
export function isCustomModel(model: string): boolean {
|
||||
export function isCustomModel(
|
||||
model: string,
|
||||
config?: ModelResolutionContext,
|
||||
): boolean {
|
||||
if (config?.getExperimentalDynamicModelConfiguration?.() === true) {
|
||||
const resolved = resolveModel(model);
|
||||
return (
|
||||
config.modelConfigService.getModelDefinition(resolved)?.tier ===
|
||||
'custom' || !resolved.startsWith('gemini-')
|
||||
);
|
||||
}
|
||||
const resolved = resolveModel(model);
|
||||
return !resolved.startsWith('gemini-');
|
||||
}
|
||||
@@ -229,20 +302,31 @@ export function isCustomModel(model: string): boolean {
|
||||
* This includes Gemini 3 models and any custom models.
|
||||
*
|
||||
* @param model The model name to check.
|
||||
* @param config Optional config object for dynamic model configuration.
|
||||
* @returns True if the model supports modern features like thoughts.
|
||||
*/
|
||||
export function supportsModernFeatures(model: string): boolean {
|
||||
if (isGemini3Model(model)) return true;
|
||||
return isCustomModel(model);
|
||||
export function supportsModernFeatures(
|
||||
model: string,
|
||||
config?: ModelResolutionContext,
|
||||
): boolean {
|
||||
if (isGemini3Model(model, config)) return true;
|
||||
return isCustomModel(model, config);
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks if the model is an auto model.
|
||||
*
|
||||
* @param model The model name to check.
|
||||
* @param config Optional config object for dynamic model configuration.
|
||||
* @returns True if the model is an auto model.
|
||||
*/
|
||||
export function isAutoModel(model: string): boolean {
|
||||
export function isAutoModel(
|
||||
model: string,
|
||||
config?: ModelResolutionContext,
|
||||
): boolean {
|
||||
if (config?.getExperimentalDynamicModelConfiguration?.() === true) {
|
||||
return config.modelConfigService.getModelDefinition(model)?.tier === 'auto';
|
||||
}
|
||||
return (
|
||||
model === GEMINI_MODEL_ALIAS_AUTO ||
|
||||
model === PREVIEW_GEMINI_MODEL_AUTO ||
|
||||
@@ -255,9 +339,23 @@ export function isAutoModel(model: string): boolean {
|
||||
* This is supported in Gemini 3.
|
||||
*
|
||||
* @param model The model name to check.
|
||||
* @param config Optional config object for dynamic model configuration.
|
||||
* @returns True if the model supports multimodal function responses.
|
||||
*/
|
||||
export function supportsMultimodalFunctionResponse(model: string): boolean {
|
||||
export function supportsMultimodalFunctionResponse(
|
||||
model: string,
|
||||
config?: ModelResolutionContext,
|
||||
): boolean {
|
||||
if (config?.getExperimentalDynamicModelConfiguration?.() === true) {
|
||||
if (VALID_ALIASES.has(model)) {
|
||||
return false;
|
||||
}
|
||||
const resolved = resolveModel(model);
|
||||
return (
|
||||
config.modelConfigService.getModelDefinition(resolved)?.features
|
||||
?.multimodalToolUse === true
|
||||
);
|
||||
}
|
||||
return model.startsWith('gemini-3-');
|
||||
}
|
||||
|
||||
@@ -266,16 +364,32 @@ export function supportsMultimodalFunctionResponse(model: string): boolean {
|
||||
*
|
||||
* @param model The model name to check.
|
||||
* @param useGemini3_1 Whether Gemini 3.1 Pro Preview is enabled.
|
||||
* @param config Optional config object for dynamic model configuration.
|
||||
* @returns True if the model is active.
|
||||
*/
|
||||
export function isActiveModel(
|
||||
model: string,
|
||||
useGemini3_1: boolean = false,
|
||||
useCustomToolModel: boolean = false,
|
||||
config?: ModelResolutionContext,
|
||||
): boolean {
|
||||
if (!VALID_GEMINI_MODELS.has(model)) {
|
||||
if (config?.getExperimentalDynamicModelConfiguration?.() === true) {
|
||||
if (VALID_ALIASES.has(model)) {
|
||||
return false;
|
||||
}
|
||||
const definition = config.modelConfigService.getModelDefinition(model);
|
||||
if (!definition) {
|
||||
return false;
|
||||
}
|
||||
|
||||
// Legacy logic only considers explicit Gemini models as "active".
|
||||
if (definition.tier === 'custom' && !model.startsWith('gemini-')) {
|
||||
return false;
|
||||
}
|
||||
} else if (!VALID_GEMINI_MODELS.has(model)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
if (useGemini3_1) {
|
||||
if (model === PREVIEW_GEMINI_MODEL) {
|
||||
return false;
|
||||
@@ -297,9 +411,19 @@ export function isActiveModel(
|
||||
* Checks if the model name is valid (either a valid model or a valid alias).
|
||||
*
|
||||
* @param model The model name to check.
|
||||
* @param config Optional config object for dynamic model configuration.
|
||||
* @returns True if the model is valid.
|
||||
*/
|
||||
export function isValidModelOrAlias(model: string): boolean {
|
||||
export function isValidModelOrAlias(
|
||||
model: string,
|
||||
config?: ModelResolutionContext,
|
||||
): boolean {
|
||||
if (config?.getExperimentalDynamicModelConfiguration?.() === true) {
|
||||
if (config.modelConfigService.getModelDefinition(model)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
// Check if it's a valid alias
|
||||
if (VALID_ALIASES.has(model)) {
|
||||
return true;
|
||||
|
||||
@@ -8,6 +8,7 @@ import { describe, it, expect } from 'vitest';
|
||||
import { Config } from './config.js';
|
||||
import { TRACKER_CREATE_TASK_TOOL_NAME } from '../tools/tool-names.js';
|
||||
import * as os from 'node:os';
|
||||
import type { AgentLoopContext } from './agent-loop-context.js';
|
||||
|
||||
describe('Config Tracker Feature Flag', () => {
|
||||
const baseParams = {
|
||||
@@ -21,7 +22,8 @@ describe('Config Tracker Feature Flag', () => {
|
||||
it('should not register tracker tools by default', async () => {
|
||||
const config = new Config(baseParams);
|
||||
await config.initialize();
|
||||
const registry = config.getToolRegistry();
|
||||
const loopContext: AgentLoopContext = config;
|
||||
const registry = loopContext.toolRegistry;
|
||||
expect(registry.getTool(TRACKER_CREATE_TASK_TOOL_NAME)).toBeUndefined();
|
||||
});
|
||||
|
||||
@@ -31,7 +33,8 @@ describe('Config Tracker Feature Flag', () => {
|
||||
tracker: true,
|
||||
});
|
||||
await config.initialize();
|
||||
const registry = config.getToolRegistry();
|
||||
const loopContext: AgentLoopContext = config;
|
||||
const registry = loopContext.toolRegistry;
|
||||
expect(registry.getTool(TRACKER_CREATE_TASK_TOOL_NAME)).toBeDefined();
|
||||
});
|
||||
|
||||
@@ -41,7 +44,8 @@ describe('Config Tracker Feature Flag', () => {
|
||||
tracker: false,
|
||||
});
|
||||
await config.initialize();
|
||||
const registry = config.getToolRegistry();
|
||||
const loopContext: AgentLoopContext = config;
|
||||
const registry = loopContext.toolRegistry;
|
||||
expect(registry.getTool(TRACKER_CREATE_TASK_TOOL_NAME)).toBeUndefined();
|
||||
});
|
||||
});
|
||||
|
||||
@@ -52,6 +52,7 @@ import * as policyCatalog from '../availability/policyCatalog.js';
|
||||
import { LlmRole, LoopType } from '../telemetry/types.js';
|
||||
import { partToString } from '../utils/partUtils.js';
|
||||
import { coreEvents } from '../utils/events.js';
|
||||
import type { MessageBus } from '../confirmation-bus/message-bus.js';
|
||||
|
||||
// Mock fs module to prevent actual file system operations during tests
|
||||
const mockFileSystem = new Map<string, string>();
|
||||
@@ -216,6 +217,7 @@ describe('Gemini Client (client.ts)', () => {
|
||||
getGlobalMemory: vi.fn().mockReturnValue(''),
|
||||
getEnvironmentMemory: vi.fn().mockReturnValue(''),
|
||||
isJitContextEnabled: vi.fn().mockReturnValue(false),
|
||||
getContextManager: vi.fn().mockReturnValue(undefined),
|
||||
getToolOutputMaskingEnabled: vi.fn().mockReturnValue(false),
|
||||
getDisableLoopDetection: vi.fn().mockReturnValue(false),
|
||||
|
||||
@@ -284,7 +286,10 @@ describe('Gemini Client (client.ts)', () => {
|
||||
(
|
||||
mockConfig as unknown as { toolRegistry: typeof mockToolRegistry }
|
||||
).toolRegistry = mockToolRegistry;
|
||||
(mockConfig as unknown as { messageBus: undefined }).messageBus = undefined;
|
||||
(mockConfig as unknown as { messageBus: MessageBus }).messageBus = {
|
||||
publish: vi.fn(),
|
||||
subscribe: vi.fn(),
|
||||
} as unknown as MessageBus;
|
||||
(mockConfig as unknown as { config: Config; promptId: string }).config =
|
||||
mockConfig;
|
||||
(mockConfig as unknown as { config: Config; promptId: string }).promptId =
|
||||
@@ -293,6 +298,8 @@ describe('Gemini Client (client.ts)', () => {
|
||||
client = new GeminiClient(mockConfig as unknown as AgentLoopContext);
|
||||
await client.initialize();
|
||||
vi.mocked(mockConfig.getGeminiClient).mockReturnValue(client);
|
||||
(mockConfig as unknown as { geminiClient: GeminiClient }).geminiClient =
|
||||
client;
|
||||
|
||||
vi.mocked(uiTelemetryService.setLastPromptTokenCount).mockClear();
|
||||
});
|
||||
@@ -368,6 +375,23 @@ describe('Gemini Client (client.ts)', () => {
|
||||
expect(newHistory.length).toBe(initialHistory.length);
|
||||
expect(JSON.stringify(newHistory)).not.toContain('some old message');
|
||||
});
|
||||
|
||||
it('should refresh ContextManager to reset JIT loaded paths', async () => {
|
||||
const mockRefresh = vi.fn().mockResolvedValue(undefined);
|
||||
vi.mocked(mockConfig.getContextManager).mockReturnValue({
|
||||
refresh: mockRefresh,
|
||||
} as unknown as ReturnType<typeof mockConfig.getContextManager>);
|
||||
|
||||
await client.resetChat();
|
||||
|
||||
expect(mockRefresh).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
it('should not fail when ContextManager is undefined', async () => {
|
||||
vi.mocked(mockConfig.getContextManager).mockReturnValue(undefined);
|
||||
|
||||
await expect(client.resetChat()).resolves.not.toThrow();
|
||||
});
|
||||
});
|
||||
|
||||
describe('startChat', () => {
|
||||
|
||||
@@ -299,6 +299,9 @@ export class GeminiClient {
|
||||
async resetChat(): Promise<void> {
|
||||
this.chat = await this.startChat();
|
||||
this.updateTelemetryTokenCount();
|
||||
// Reset JIT context loaded paths so subdirectory context can be
|
||||
// re-discovered in the new session.
|
||||
await this.config.getContextManager()?.refresh();
|
||||
}
|
||||
|
||||
dispose() {
|
||||
@@ -866,7 +869,7 @@ export class GeminiClient {
|
||||
}
|
||||
|
||||
const hooksEnabled = this.config.getEnableHooks();
|
||||
const messageBus = this.config.getMessageBus();
|
||||
const messageBus = this.context.messageBus;
|
||||
|
||||
if (this.lastPromptId !== prompt_id) {
|
||||
this.loopDetector.reset(prompt_id, partListUnionToString(request));
|
||||
|
||||
@@ -318,6 +318,16 @@ function createMockConfig(overrides: Partial<Config> = {}): Config {
|
||||
}) as unknown as PolicyEngine;
|
||||
}
|
||||
|
||||
Object.defineProperty(finalConfig, 'toolRegistry', {
|
||||
get: () => finalConfig.getToolRegistry?.() || defaultToolRegistry,
|
||||
});
|
||||
Object.defineProperty(finalConfig, 'messageBus', {
|
||||
get: () => finalConfig.getMessageBus?.(),
|
||||
});
|
||||
Object.defineProperty(finalConfig, 'geminiClient', {
|
||||
get: () => finalConfig.getGeminiClient?.(),
|
||||
});
|
||||
|
||||
return finalConfig;
|
||||
}
|
||||
|
||||
@@ -351,7 +361,7 @@ describe('CoreToolScheduler', () => {
|
||||
});
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -431,7 +441,7 @@ describe('CoreToolScheduler', () => {
|
||||
});
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -532,7 +542,7 @@ describe('CoreToolScheduler', () => {
|
||||
});
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -629,7 +639,7 @@ describe('CoreToolScheduler', () => {
|
||||
});
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -684,7 +694,7 @@ describe('CoreToolScheduler', () => {
|
||||
});
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -750,7 +760,7 @@ describe('CoreToolScheduler with payload', () => {
|
||||
.mockReturnValue(new HookSystem(mockConfig));
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -898,7 +908,7 @@ describe('CoreToolScheduler edit cancellation', () => {
|
||||
.mockReturnValue(new HookSystem(mockConfig));
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -991,7 +1001,7 @@ describe('CoreToolScheduler YOLO mode', () => {
|
||||
.mockReturnValue(new HookSystem(mockConfig));
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -1083,7 +1093,7 @@ describe('CoreToolScheduler request queueing', () => {
|
||||
.mockReturnValue(new HookSystem(mockConfig));
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -1212,7 +1222,7 @@ describe('CoreToolScheduler request queueing', () => {
|
||||
.mockReturnValue(new HookSystem(mockConfig));
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -1320,7 +1330,7 @@ describe('CoreToolScheduler request queueing', () => {
|
||||
});
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -1381,7 +1391,7 @@ describe('CoreToolScheduler request queueing', () => {
|
||||
.mockReturnValue(new HookSystem(mockConfig));
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -1453,7 +1463,7 @@ describe('CoreToolScheduler request queueing', () => {
|
||||
getAllTools: () => [],
|
||||
getToolsByServer: () => [],
|
||||
tools: new Map(),
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
mcpClientManager: undefined,
|
||||
getToolByName: () => testTool,
|
||||
getToolByDisplayName: () => testTool,
|
||||
@@ -1471,7 +1481,7 @@ describe('CoreToolScheduler request queueing', () => {
|
||||
> = [];
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate: (toolCalls) => {
|
||||
onToolCallsUpdate(toolCalls);
|
||||
@@ -1620,7 +1630,7 @@ describe('CoreToolScheduler Sequential Execution', () => {
|
||||
.mockReturnValue(new HookSystem(mockConfig));
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -1725,7 +1735,7 @@ describe('CoreToolScheduler Sequential Execution', () => {
|
||||
.mockReturnValue(new HookSystem(mockConfig));
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -1829,7 +1839,7 @@ describe('CoreToolScheduler Sequential Execution', () => {
|
||||
.mockReturnValue(new HookSystem(mockConfig));
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
@@ -1894,7 +1904,7 @@ describe('CoreToolScheduler Sequential Execution', () => {
|
||||
mockConfig.getHookSystem = vi.fn().mockReturnValue(undefined);
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
});
|
||||
|
||||
@@ -2005,7 +2015,7 @@ describe('CoreToolScheduler Sequential Execution', () => {
|
||||
mockConfig.getHookSystem = vi.fn().mockReturnValue(undefined);
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
});
|
||||
|
||||
@@ -2069,7 +2079,7 @@ describe('CoreToolScheduler Sequential Execution', () => {
|
||||
.mockReturnValue(new HookSystem(mockConfig));
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
});
|
||||
@@ -2138,7 +2148,7 @@ describe('CoreToolScheduler Sequential Execution', () => {
|
||||
mockConfig.getHookSystem = vi.fn().mockReturnValue(undefined);
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
});
|
||||
@@ -2229,7 +2239,7 @@ describe('CoreToolScheduler Sequential Execution', () => {
|
||||
mockConfig.getHookSystem = vi.fn().mockReturnValue(undefined);
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
});
|
||||
@@ -2283,7 +2293,7 @@ describe('CoreToolScheduler Sequential Execution', () => {
|
||||
mockConfig.getHookSystem = vi.fn().mockReturnValue(undefined);
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
});
|
||||
@@ -2344,7 +2354,7 @@ describe('CoreToolScheduler Sequential Execution', () => {
|
||||
mockConfig.getHookSystem = vi.fn().mockReturnValue(undefined);
|
||||
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: mockConfig,
|
||||
onAllToolCallsComplete,
|
||||
onToolCallsUpdate,
|
||||
getPreferredEditor: () => 'vscode',
|
||||
|
||||
@@ -13,7 +13,6 @@ import {
|
||||
ToolConfirmationOutcome,
|
||||
} from '../tools/tools.js';
|
||||
import type { EditorType } from '../utils/editor.js';
|
||||
import type { Config } from '../config/config.js';
|
||||
import { PolicyDecision } from '../policy/types.js';
|
||||
import { logToolCall } from '../telemetry/loggers.js';
|
||||
import { ToolErrorType } from '../tools/tool-error.js';
|
||||
@@ -50,6 +49,7 @@ import { ToolExecutor } from '../scheduler/tool-executor.js';
|
||||
import { DiscoveredMCPTool } from '../tools/mcp-tool.js';
|
||||
import { getPolicyDenialError } from '../scheduler/policy.js';
|
||||
import { GeminiCliOperation } from '../telemetry/constants.js';
|
||||
import type { AgentLoopContext } from '../config/agent-loop-context.js';
|
||||
|
||||
export type {
|
||||
ToolCall,
|
||||
@@ -92,7 +92,7 @@ const createErrorResponse = (
|
||||
});
|
||||
|
||||
interface CoreToolSchedulerOptions {
|
||||
config: Config;
|
||||
context: AgentLoopContext;
|
||||
outputUpdateHandler?: OutputUpdateHandler;
|
||||
onAllToolCallsComplete?: AllToolCallsCompleteHandler;
|
||||
onToolCallsUpdate?: ToolCallsUpdateHandler;
|
||||
@@ -112,7 +112,7 @@ export class CoreToolScheduler {
|
||||
private onAllToolCallsComplete?: AllToolCallsCompleteHandler;
|
||||
private onToolCallsUpdate?: ToolCallsUpdateHandler;
|
||||
private getPreferredEditor: () => EditorType | undefined;
|
||||
private config: Config;
|
||||
private context: AgentLoopContext;
|
||||
private isFinalizingToolCalls = false;
|
||||
private isScheduling = false;
|
||||
private isCancelling = false;
|
||||
@@ -128,19 +128,19 @@ export class CoreToolScheduler {
|
||||
private toolModifier: ToolModificationHandler;
|
||||
|
||||
constructor(options: CoreToolSchedulerOptions) {
|
||||
this.config = options.config;
|
||||
this.context = options.context;
|
||||
this.outputUpdateHandler = options.outputUpdateHandler;
|
||||
this.onAllToolCallsComplete = options.onAllToolCallsComplete;
|
||||
this.onToolCallsUpdate = options.onToolCallsUpdate;
|
||||
this.getPreferredEditor = options.getPreferredEditor;
|
||||
this.toolExecutor = new ToolExecutor(this.config);
|
||||
this.toolExecutor = new ToolExecutor(this.context.config);
|
||||
this.toolModifier = new ToolModificationHandler();
|
||||
|
||||
// Subscribe to message bus for ASK_USER policy decisions
|
||||
// Use a static WeakMap to ensure we only subscribe ONCE per MessageBus instance
|
||||
// This prevents memory leaks when multiple CoreToolScheduler instances are created
|
||||
// (e.g., on every React render, or for each non-interactive tool call)
|
||||
const messageBus = this.config.getMessageBus();
|
||||
const messageBus = this.context.messageBus;
|
||||
|
||||
// Check if we've already subscribed a handler to this message bus
|
||||
if (!CoreToolScheduler.subscribedMessageBuses.has(messageBus)) {
|
||||
@@ -526,18 +526,16 @@ export class CoreToolScheduler {
|
||||
);
|
||||
}
|
||||
const requestsToProcess = Array.isArray(request) ? request : [request];
|
||||
const currentApprovalMode = this.config.getApprovalMode();
|
||||
const currentApprovalMode = this.context.config.getApprovalMode();
|
||||
this.completedToolCallsForBatch = [];
|
||||
|
||||
const newToolCalls: ToolCall[] = requestsToProcess.map(
|
||||
(reqInfo): ToolCall => {
|
||||
const toolInstance = this.config
|
||||
.getToolRegistry()
|
||||
.getTool(reqInfo.name);
|
||||
const toolInstance = this.context.toolRegistry.getTool(reqInfo.name);
|
||||
if (!toolInstance) {
|
||||
const suggestion = getToolSuggestion(
|
||||
reqInfo.name,
|
||||
this.config.getToolRegistry().getAllToolNames(),
|
||||
this.context.toolRegistry.getAllToolNames(),
|
||||
);
|
||||
const errorMessage = `Tool "${reqInfo.name}" not found in registry. Tools must use the exact names that are registered.${suggestion}`;
|
||||
return {
|
||||
@@ -647,13 +645,13 @@ export class CoreToolScheduler {
|
||||
: undefined;
|
||||
const toolAnnotations = toolCall.tool.toolAnnotations;
|
||||
|
||||
const { decision, rule } = await this.config
|
||||
const { decision, rule } = await this.context.config
|
||||
.getPolicyEngine()
|
||||
.check(toolCallForPolicy, serverName, toolAnnotations);
|
||||
|
||||
if (decision === PolicyDecision.DENY) {
|
||||
const { errorMessage, errorType } = getPolicyDenialError(
|
||||
this.config,
|
||||
this.context.config,
|
||||
rule,
|
||||
);
|
||||
this.setStatusInternal(
|
||||
@@ -694,7 +692,7 @@ export class CoreToolScheduler {
|
||||
signal,
|
||||
);
|
||||
} else {
|
||||
if (!this.config.isInteractive()) {
|
||||
if (!this.context.config.isInteractive()) {
|
||||
throw new Error(
|
||||
`Tool execution for "${
|
||||
toolCall.tool.displayName || toolCall.tool.name
|
||||
@@ -703,7 +701,7 @@ export class CoreToolScheduler {
|
||||
}
|
||||
|
||||
// Fire Notification hook before showing confirmation to user
|
||||
const hookSystem = this.config.getHookSystem();
|
||||
const hookSystem = this.context.config.getHookSystem();
|
||||
if (hookSystem) {
|
||||
await hookSystem.fireToolNotificationEvent(confirmationDetails);
|
||||
}
|
||||
@@ -988,7 +986,7 @@ export class CoreToolScheduler {
|
||||
// The active tool is finished. Move it to the completed batch.
|
||||
const completedCall = activeCall as CompletedToolCall;
|
||||
this.completedToolCallsForBatch.push(completedCall);
|
||||
logToolCall(this.config, new ToolCallEvent(completedCall));
|
||||
logToolCall(this.context.config, new ToolCallEvent(completedCall));
|
||||
|
||||
// Clear the active tool slot. This is crucial for the sequential processing.
|
||||
this.toolCalls = [];
|
||||
|
||||
@@ -137,6 +137,10 @@ describe('GeminiChat', () => {
|
||||
let currentActiveModel = 'gemini-pro';
|
||||
|
||||
mockConfig = {
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
promptId: 'test-session-id',
|
||||
getSessionId: () => 'test-session-id',
|
||||
getTelemetryLogPromptsEnabled: () => true,
|
||||
getUsageStatisticsEnabled: () => true,
|
||||
|
||||
@@ -25,7 +25,6 @@ import {
|
||||
getRetryErrorType,
|
||||
} from '../utils/retry.js';
|
||||
import type { ValidationRequiredError } from '../utils/googleQuotaErrors.js';
|
||||
import type { Config } from '../config/config.js';
|
||||
import {
|
||||
resolveModel,
|
||||
isGemini2Model,
|
||||
@@ -59,6 +58,7 @@ import {
|
||||
createAvailabilityContextProvider,
|
||||
} from '../availability/policyHelpers.js';
|
||||
import { coreEvents } from '../utils/events.js';
|
||||
import type { AgentLoopContext } from '../config/agent-loop-context.js';
|
||||
|
||||
export enum StreamEventType {
|
||||
/** A regular content chunk from the API. */
|
||||
@@ -251,7 +251,7 @@ export class GeminiChat {
|
||||
private lastPromptTokenCount: number;
|
||||
|
||||
constructor(
|
||||
private readonly config: Config,
|
||||
private readonly context: AgentLoopContext,
|
||||
private systemInstruction: string = '',
|
||||
private tools: Tool[] = [],
|
||||
private history: Content[] = [],
|
||||
@@ -260,7 +260,7 @@ export class GeminiChat {
|
||||
kind: 'main' | 'subagent' = 'main',
|
||||
) {
|
||||
validateHistory(history);
|
||||
this.chatRecordingService = new ChatRecordingService(config);
|
||||
this.chatRecordingService = new ChatRecordingService(context);
|
||||
this.chatRecordingService.initialize(resumedSessionData, kind);
|
||||
this.lastPromptTokenCount = estimateTokenCountSync(
|
||||
this.history.flatMap((c) => c.parts || []),
|
||||
@@ -315,7 +315,7 @@ export class GeminiChat {
|
||||
|
||||
const userContent = createUserContent(message);
|
||||
const { model } =
|
||||
this.config.modelConfigService.getResolvedConfig(modelConfigKey);
|
||||
this.context.config.modelConfigService.getResolvedConfig(modelConfigKey);
|
||||
|
||||
// Record user input - capture complete message with all parts (text, files, images, etc.)
|
||||
// but skip recording function responses (tool call results) as they should be stored in tool call records
|
||||
@@ -350,7 +350,7 @@ export class GeminiChat {
|
||||
this: GeminiChat,
|
||||
): AsyncGenerator<StreamEvent, void, void> {
|
||||
try {
|
||||
const maxAttempts = this.config.getMaxAttempts();
|
||||
const maxAttempts = this.context.config.getMaxAttempts();
|
||||
|
||||
for (let attempt = 0; attempt < maxAttempts; attempt++) {
|
||||
let isConnectionPhase = true;
|
||||
@@ -412,7 +412,7 @@ export class GeminiChat {
|
||||
// like ERR_SSL_SSLV3_ALERT_BAD_RECORD_MAC or ApiError)
|
||||
const isRetryable = isRetryableError(
|
||||
error,
|
||||
this.config.getRetryFetchErrors(),
|
||||
this.context.config.getRetryFetchErrors(),
|
||||
);
|
||||
|
||||
const isContentError = error instanceof InvalidStreamError;
|
||||
@@ -421,7 +421,7 @@ export class GeminiChat {
|
||||
: getRetryErrorType(error);
|
||||
|
||||
if (
|
||||
(isContentError && isGemini2Model(model)) ||
|
||||
(isContentError && isGemini2Model(model, this.context.config)) ||
|
||||
(isRetryable && !signal.aborted)
|
||||
) {
|
||||
// The issue requests exactly 3 retries (4 attempts) for API errors during stream iteration.
|
||||
@@ -437,12 +437,12 @@ export class GeminiChat {
|
||||
|
||||
if (isContentError) {
|
||||
logContentRetry(
|
||||
this.config,
|
||||
this.context.config,
|
||||
new ContentRetryEvent(attempt, errorType, delayMs, model),
|
||||
);
|
||||
} else {
|
||||
logNetworkRetryAttempt(
|
||||
this.config,
|
||||
this.context.config,
|
||||
new NetworkRetryAttemptEvent(
|
||||
attempt + 1,
|
||||
maxAttempts,
|
||||
@@ -472,7 +472,7 @@ export class GeminiChat {
|
||||
}
|
||||
|
||||
logContentRetryFailure(
|
||||
this.config,
|
||||
this.context.config,
|
||||
new ContentRetryFailureEvent(attempt + 1, errorType, model),
|
||||
);
|
||||
|
||||
@@ -502,7 +502,7 @@ export class GeminiChat {
|
||||
model: availabilityFinalModel,
|
||||
config: newAvailabilityConfig,
|
||||
maxAttempts: availabilityMaxAttempts,
|
||||
} = applyModelSelection(this.config, modelConfigKey);
|
||||
} = applyModelSelection(this.context.config, modelConfigKey);
|
||||
|
||||
let lastModelToUse = availabilityFinalModel;
|
||||
let currentGenerateContentConfig: GenerateContentConfig =
|
||||
@@ -511,26 +511,30 @@ export class GeminiChat {
|
||||
let lastContentsToUse: Content[] = [...requestContents];
|
||||
|
||||
const getAvailabilityContext = createAvailabilityContextProvider(
|
||||
this.config,
|
||||
this.context.config,
|
||||
() => lastModelToUse,
|
||||
);
|
||||
// Track initial active model to detect fallback changes
|
||||
const initialActiveModel = this.config.getActiveModel();
|
||||
const initialActiveModel = this.context.config.getActiveModel();
|
||||
|
||||
const apiCall = async () => {
|
||||
const useGemini3_1 = (await this.config.getGemini31Launched?.()) ?? false;
|
||||
const useGemini3_1 =
|
||||
(await this.context.config.getGemini31Launched?.()) ?? false;
|
||||
// Default to the last used model (which respects arguments/availability selection)
|
||||
let modelToUse = resolveModel(lastModelToUse, useGemini3_1);
|
||||
|
||||
// If the active model has changed (e.g. due to a fallback updating the config),
|
||||
// we switch to the new active model.
|
||||
if (this.config.getActiveModel() !== initialActiveModel) {
|
||||
modelToUse = resolveModel(this.config.getActiveModel(), useGemini3_1);
|
||||
if (this.context.config.getActiveModel() !== initialActiveModel) {
|
||||
modelToUse = resolveModel(
|
||||
this.context.config.getActiveModel(),
|
||||
useGemini3_1,
|
||||
);
|
||||
}
|
||||
|
||||
if (modelToUse !== lastModelToUse) {
|
||||
const { generateContentConfig: newConfig } =
|
||||
this.config.modelConfigService.getResolvedConfig({
|
||||
this.context.config.modelConfigService.getResolvedConfig({
|
||||
...modelConfigKey,
|
||||
model: modelToUse,
|
||||
});
|
||||
@@ -547,11 +551,14 @@ export class GeminiChat {
|
||||
abortSignal,
|
||||
};
|
||||
|
||||
let contentsToUse: Content[] = supportsModernFeatures(modelToUse)
|
||||
let contentsToUse: Content[] = supportsModernFeatures(
|
||||
modelToUse,
|
||||
this.context.config,
|
||||
)
|
||||
? [...contentsForPreviewModel]
|
||||
: [...requestContents];
|
||||
|
||||
const hookSystem = this.config.getHookSystem();
|
||||
const hookSystem = this.context.config.getHookSystem();
|
||||
if (hookSystem) {
|
||||
const beforeModelResult = await hookSystem.fireBeforeModelEvent({
|
||||
model: modelToUse,
|
||||
@@ -619,7 +626,7 @@ export class GeminiChat {
|
||||
lastConfig = config;
|
||||
lastContentsToUse = contentsToUse;
|
||||
|
||||
return this.config.getContentGenerator().generateContentStream(
|
||||
return this.context.config.getContentGenerator().generateContentStream(
|
||||
{
|
||||
model: modelToUse,
|
||||
contents: contentsToUse,
|
||||
@@ -633,12 +640,12 @@ export class GeminiChat {
|
||||
const onPersistent429Callback = async (
|
||||
authType?: string,
|
||||
error?: unknown,
|
||||
) => handleFallback(this.config, lastModelToUse, authType, error);
|
||||
) => handleFallback(this.context.config, lastModelToUse, authType, error);
|
||||
|
||||
const onValidationRequiredCallback = async (
|
||||
validationError: ValidationRequiredError,
|
||||
) => {
|
||||
const handler = this.config.getValidationHandler();
|
||||
const handler = this.context.config.getValidationHandler();
|
||||
if (typeof handler !== 'function') {
|
||||
// No handler registered, re-throw to show default error message
|
||||
throw validationError;
|
||||
@@ -653,15 +660,17 @@ export class GeminiChat {
|
||||
const streamResponse = await retryWithBackoff(apiCall, {
|
||||
onPersistent429: onPersistent429Callback,
|
||||
onValidationRequired: onValidationRequiredCallback,
|
||||
authType: this.config.getContentGeneratorConfig()?.authType,
|
||||
retryFetchErrors: this.config.getRetryFetchErrors(),
|
||||
authType: this.context.config.getContentGeneratorConfig()?.authType,
|
||||
retryFetchErrors: this.context.config.getRetryFetchErrors(),
|
||||
signal: abortSignal,
|
||||
maxAttempts: availabilityMaxAttempts ?? this.config.getMaxAttempts(),
|
||||
maxAttempts:
|
||||
availabilityMaxAttempts ?? this.context.config.getMaxAttempts(),
|
||||
getAvailabilityContext,
|
||||
onRetry: (attempt, error, delayMs) => {
|
||||
coreEvents.emitRetryAttempt({
|
||||
attempt,
|
||||
maxAttempts: availabilityMaxAttempts ?? this.config.getMaxAttempts(),
|
||||
maxAttempts:
|
||||
availabilityMaxAttempts ?? this.context.config.getMaxAttempts(),
|
||||
delayMs,
|
||||
error: error instanceof Error ? error.message : String(error),
|
||||
model: lastModelToUse,
|
||||
@@ -814,7 +823,7 @@ export class GeminiChat {
|
||||
isSchemaDepthError(error.message) ||
|
||||
isInvalidArgumentError(error.message)
|
||||
) {
|
||||
const tools = this.config.getToolRegistry().getAllTools();
|
||||
const tools = this.context.toolRegistry.getAllTools();
|
||||
const cyclicSchemaTools: string[] = [];
|
||||
for (const tool of tools) {
|
||||
if (
|
||||
@@ -881,7 +890,7 @@ export class GeminiChat {
|
||||
}
|
||||
}
|
||||
|
||||
const hookSystem = this.config.getHookSystem();
|
||||
const hookSystem = this.context.config.getHookSystem();
|
||||
if (originalRequest && chunk && hookSystem) {
|
||||
const hookResult = await hookSystem.fireAfterModelEvent(
|
||||
originalRequest,
|
||||
|
||||
@@ -79,7 +79,20 @@ describe('GeminiChat Network Retries', () => {
|
||||
// Default mock implementation: execute the function immediately
|
||||
mockRetryWithBackoff.mockImplementation(async (apiCall) => apiCall());
|
||||
|
||||
const mockToolRegistry = { getTool: vi.fn() };
|
||||
const testMessageBus = { publish: vi.fn(), subscribe: vi.fn() };
|
||||
|
||||
mockConfig = {
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
get toolRegistry() {
|
||||
return mockToolRegistry;
|
||||
},
|
||||
get messageBus() {
|
||||
return testMessageBus;
|
||||
},
|
||||
promptId: 'test-session-id',
|
||||
getSessionId: () => 'test-session-id',
|
||||
getTelemetryLogPromptsEnabled: () => true,
|
||||
getUsageStatisticsEnabled: () => true,
|
||||
|
||||
@@ -10,6 +10,7 @@ import fs from 'node:fs';
|
||||
import type { Config } from '../config/config.js';
|
||||
import type { AgentDefinition } from '../agents/types.js';
|
||||
import * as toolNames from '../tools/tool-names.js';
|
||||
import type { ToolRegistry } from '../tools/tool-registry.js';
|
||||
|
||||
vi.mock('node:fs');
|
||||
vi.mock('../utils/gitUtils', () => ({
|
||||
@@ -22,6 +23,17 @@ describe('Core System Prompt Substitution', () => {
|
||||
vi.resetAllMocks();
|
||||
vi.stubEnv('GEMINI_SYSTEM_MD', 'true');
|
||||
mockConfig = {
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
toolRegistry: {
|
||||
getAllToolNames: vi
|
||||
.fn()
|
||||
.mockReturnValue([
|
||||
toolNames.WRITE_FILE_TOOL_NAME,
|
||||
toolNames.READ_FILE_TOOL_NAME,
|
||||
]),
|
||||
},
|
||||
getToolRegistry: vi.fn().mockReturnValue({
|
||||
getAllToolNames: vi
|
||||
.fn()
|
||||
@@ -131,7 +143,10 @@ describe('Core System Prompt Substitution', () => {
|
||||
});
|
||||
|
||||
it('should not substitute disabled tool names', () => {
|
||||
vi.mocked(mockConfig.getToolRegistry().getAllToolNames).mockReturnValue([]);
|
||||
vi.mocked(
|
||||
(mockConfig as unknown as { toolRegistry: ToolRegistry }).toolRegistry
|
||||
.getAllToolNames,
|
||||
).mockReturnValue([]);
|
||||
vi.mocked(fs.existsSync).mockReturnValue(true);
|
||||
vi.mocked(fs.readFileSync).mockReturnValue('Use ${write_file_ToolName}.');
|
||||
|
||||
|
||||
@@ -82,11 +82,12 @@ describe('Core System Prompt (prompts.ts)', () => {
|
||||
vi.stubEnv('SANDBOX', undefined);
|
||||
vi.stubEnv('GEMINI_SYSTEM_MD', undefined);
|
||||
vi.stubEnv('GEMINI_WRITE_SYSTEM_MD', undefined);
|
||||
const mockRegistry = {
|
||||
getAllToolNames: vi.fn().mockReturnValue(['grep_search', 'glob']),
|
||||
getAllTools: vi.fn().mockReturnValue([]),
|
||||
};
|
||||
mockConfig = {
|
||||
getToolRegistry: vi.fn().mockReturnValue({
|
||||
getAllToolNames: vi.fn().mockReturnValue(['grep_search', 'glob']),
|
||||
getAllTools: vi.fn().mockReturnValue([]),
|
||||
}),
|
||||
getToolRegistry: vi.fn().mockReturnValue(mockRegistry),
|
||||
getEnableShellOutputEfficiency: vi.fn().mockReturnValue(true),
|
||||
storage: {
|
||||
getProjectTempDir: vi.fn().mockReturnValue('/tmp/project-temp'),
|
||||
@@ -114,6 +115,12 @@ describe('Core System Prompt (prompts.ts)', () => {
|
||||
getApprovalMode: vi.fn().mockReturnValue(ApprovalMode.DEFAULT),
|
||||
getApprovedPlanPath: vi.fn().mockReturnValue(undefined),
|
||||
isTrackerEnabled: vi.fn().mockReturnValue(false),
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
get toolRegistry() {
|
||||
return mockRegistry;
|
||||
},
|
||||
} as unknown as Config;
|
||||
});
|
||||
|
||||
@@ -374,7 +381,7 @@ describe('Core System Prompt (prompts.ts)', () => {
|
||||
|
||||
it('should redact grep and glob from the system prompt when they are disabled', () => {
|
||||
vi.mocked(mockConfig.getActiveModel).mockReturnValue(PREVIEW_GEMINI_MODEL);
|
||||
vi.mocked(mockConfig.getToolRegistry().getAllToolNames).mockReturnValue([]);
|
||||
vi.mocked(mockConfig.toolRegistry.getAllToolNames).mockReturnValue([]);
|
||||
const prompt = getCoreSystemPrompt(mockConfig);
|
||||
|
||||
expect(prompt).not.toContain('`grep_search`');
|
||||
@@ -390,10 +397,11 @@ describe('Core System Prompt (prompts.ts)', () => {
|
||||
])(
|
||||
'should handle CodebaseInvestigator with tools=%s',
|
||||
(toolNames, expectCodebaseInvestigator) => {
|
||||
const mockToolRegistry = {
|
||||
getAllToolNames: vi.fn().mockReturnValue(toolNames),
|
||||
};
|
||||
const testConfig = {
|
||||
getToolRegistry: vi.fn().mockReturnValue({
|
||||
getAllToolNames: vi.fn().mockReturnValue(toolNames),
|
||||
}),
|
||||
getToolRegistry: vi.fn().mockReturnValue(mockToolRegistry),
|
||||
getEnableShellOutputEfficiency: vi.fn().mockReturnValue(true),
|
||||
storage: {
|
||||
getProjectTempDir: vi.fn().mockReturnValue('/tmp/project-temp'),
|
||||
@@ -413,6 +421,12 @@ describe('Core System Prompt (prompts.ts)', () => {
|
||||
}),
|
||||
getApprovedPlanPath: vi.fn().mockReturnValue(undefined),
|
||||
isTrackerEnabled: vi.fn().mockReturnValue(false),
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
get toolRegistry() {
|
||||
return mockToolRegistry;
|
||||
},
|
||||
} as unknown as Config;
|
||||
|
||||
const prompt = getCoreSystemPrompt(testConfig);
|
||||
@@ -468,7 +482,7 @@ describe('Core System Prompt (prompts.ts)', () => {
|
||||
PREVIEW_GEMINI_MODEL,
|
||||
);
|
||||
vi.mocked(mockConfig.getApprovalMode).mockReturnValue(ApprovalMode.PLAN);
|
||||
vi.mocked(mockConfig.getToolRegistry().getAllTools).mockReturnValue(
|
||||
vi.mocked(mockConfig.toolRegistry.getAllTools).mockReturnValue(
|
||||
planModeTools,
|
||||
);
|
||||
};
|
||||
@@ -522,7 +536,7 @@ describe('Core System Prompt (prompts.ts)', () => {
|
||||
PREVIEW_GEMINI_MODEL,
|
||||
);
|
||||
vi.mocked(mockConfig.getApprovalMode).mockReturnValue(ApprovalMode.PLAN);
|
||||
vi.mocked(mockConfig.getToolRegistry().getAllTools).mockReturnValue(
|
||||
vi.mocked(mockConfig.toolRegistry.getAllTools).mockReturnValue(
|
||||
subsetTools,
|
||||
);
|
||||
|
||||
@@ -667,7 +681,7 @@ describe('Core System Prompt (prompts.ts)', () => {
|
||||
|
||||
it('should include planning phase suggestion when enter_plan_mode tool is enabled', () => {
|
||||
vi.mocked(mockConfig.getActiveModel).mockReturnValue(PREVIEW_GEMINI_MODEL);
|
||||
vi.mocked(mockConfig.getToolRegistry().getAllToolNames).mockReturnValue([
|
||||
vi.mocked(mockConfig.toolRegistry.getAllToolNames).mockReturnValue([
|
||||
'enter_plan_mode',
|
||||
]);
|
||||
const prompt = getCoreSystemPrompt(mockConfig);
|
||||
|
||||
@@ -64,16 +64,22 @@ describe('HookEventHandler', () => {
|
||||
beforeEach(() => {
|
||||
vi.resetAllMocks();
|
||||
|
||||
const mockGeminiClient = {
|
||||
getChatRecordingService: vi.fn().mockReturnValue({
|
||||
getConversationFilePath: vi
|
||||
.fn()
|
||||
.mockReturnValue('/test/project/.gemini/tmp/chats/session.json'),
|
||||
}),
|
||||
};
|
||||
|
||||
mockConfig = {
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
geminiClient: mockGeminiClient,
|
||||
getGeminiClient: vi.fn().mockReturnValue(mockGeminiClient),
|
||||
getSessionId: vi.fn().mockReturnValue('test-session'),
|
||||
getWorkingDir: vi.fn().mockReturnValue('/test/project'),
|
||||
getGeminiClient: vi.fn().mockReturnValue({
|
||||
getChatRecordingService: vi.fn().mockReturnValue({
|
||||
getConversationFilePath: vi
|
||||
.fn()
|
||||
.mockReturnValue('/test/project/.gemini/tmp/chats/session.json'),
|
||||
}),
|
||||
}),
|
||||
} as unknown as Config;
|
||||
|
||||
mockHookPlanner = {
|
||||
|
||||
@@ -4,7 +4,6 @@
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import type { Config } from '../config/config.js';
|
||||
import type { HookPlanner, HookEventContext } from './hookPlanner.js';
|
||||
import type { HookRunner } from './hookRunner.js';
|
||||
import type { HookAggregator, AggregatedHookResult } from './hookAggregator.js';
|
||||
@@ -40,12 +39,13 @@ import { logHookCall } from '../telemetry/loggers.js';
|
||||
import { HookCallEvent } from '../telemetry/types.js';
|
||||
import { debugLogger } from '../utils/debugLogger.js';
|
||||
import { coreEvents } from '../utils/events.js';
|
||||
import type { AgentLoopContext } from '../config/agent-loop-context.js';
|
||||
|
||||
/**
|
||||
* Hook event bus that coordinates hook execution across the system
|
||||
*/
|
||||
export class HookEventHandler {
|
||||
private readonly config: Config;
|
||||
private readonly context: AgentLoopContext;
|
||||
private readonly hookPlanner: HookPlanner;
|
||||
private readonly hookRunner: HookRunner;
|
||||
private readonly hookAggregator: HookAggregator;
|
||||
@@ -58,12 +58,12 @@ export class HookEventHandler {
|
||||
private readonly reportedFailures = new WeakMap<object, Set<string>>();
|
||||
|
||||
constructor(
|
||||
config: Config,
|
||||
context: AgentLoopContext,
|
||||
hookPlanner: HookPlanner,
|
||||
hookRunner: HookRunner,
|
||||
hookAggregator: HookAggregator,
|
||||
) {
|
||||
this.config = config;
|
||||
this.context = context;
|
||||
this.hookPlanner = hookPlanner;
|
||||
this.hookRunner = hookRunner;
|
||||
this.hookAggregator = hookAggregator;
|
||||
@@ -370,15 +370,14 @@ export class HookEventHandler {
|
||||
private createBaseInput(eventName: HookEventName): HookInput {
|
||||
// Get the transcript path from the ChatRecordingService if available
|
||||
const transcriptPath =
|
||||
this.config
|
||||
.getGeminiClient()
|
||||
this.context.geminiClient
|
||||
?.getChatRecordingService()
|
||||
?.getConversationFilePath() ?? '';
|
||||
|
||||
return {
|
||||
session_id: this.config.getSessionId(),
|
||||
session_id: this.context.config.getSessionId(),
|
||||
transcript_path: transcriptPath,
|
||||
cwd: this.config.getWorkingDir(),
|
||||
cwd: this.context.config.getWorkingDir(),
|
||||
hook_event_name: eventName,
|
||||
timestamp: new Date().toISOString(),
|
||||
};
|
||||
@@ -457,7 +456,7 @@ export class HookEventHandler {
|
||||
result.error?.message,
|
||||
);
|
||||
|
||||
logHookCall(this.config, hookCallEvent);
|
||||
logHookCall(this.context.config, hookCallEvent);
|
||||
}
|
||||
|
||||
// Log individual errors
|
||||
|
||||
@@ -281,15 +281,105 @@ describe('AntigravityInstaller', () => {
|
||||
);
|
||||
});
|
||||
|
||||
it('returns a failure message if the alias is not set', async () => {
|
||||
it('ignores an unsafe alias and falls back to safe commands', async () => {
|
||||
vi.stubEnv('ANTIGRAVITY_CLI_ALIAS', 'agy;malicious_command');
|
||||
const { installer } = setup();
|
||||
vi.mocked(child_process.execSync).mockImplementationOnce(() => 'agy');
|
||||
|
||||
const result = await installer.install();
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
expect(child_process.execSync).toHaveBeenCalledTimes(1);
|
||||
expect(child_process.execSync).toHaveBeenCalledWith('command -v agy', {
|
||||
stdio: 'ignore',
|
||||
});
|
||||
expect(child_process.spawnSync).toHaveBeenCalledWith(
|
||||
'agy',
|
||||
[
|
||||
'--install-extension',
|
||||
'google.gemini-cli-vscode-ide-companion',
|
||||
'--force',
|
||||
],
|
||||
{ stdio: 'pipe', shell: false },
|
||||
);
|
||||
});
|
||||
|
||||
it('falls back to antigravity when agy is unavailable on linux', async () => {
|
||||
vi.stubEnv('ANTIGRAVITY_CLI_ALIAS', 'agy');
|
||||
const { installer } = setup();
|
||||
vi.mocked(child_process.execSync)
|
||||
.mockImplementationOnce(() => {
|
||||
throw new Error('Command not found');
|
||||
})
|
||||
.mockImplementationOnce(() => 'antigravity');
|
||||
|
||||
const result = await installer.install();
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
expect(child_process.execSync).toHaveBeenNthCalledWith(
|
||||
1,
|
||||
'command -v agy',
|
||||
{
|
||||
stdio: 'ignore',
|
||||
},
|
||||
);
|
||||
expect(child_process.execSync).toHaveBeenNthCalledWith(
|
||||
2,
|
||||
'command -v antigravity',
|
||||
{ stdio: 'ignore' },
|
||||
);
|
||||
expect(child_process.spawnSync).toHaveBeenCalledWith(
|
||||
'antigravity',
|
||||
[
|
||||
'--install-extension',
|
||||
'google.gemini-cli-vscode-ide-companion',
|
||||
'--force',
|
||||
],
|
||||
{ stdio: 'pipe', shell: false },
|
||||
);
|
||||
});
|
||||
|
||||
it('falls back to antigravity.cmd when agy.cmd is unavailable on windows', async () => {
|
||||
vi.stubEnv('ANTIGRAVITY_CLI_ALIAS', 'agy.cmd');
|
||||
const { installer } = setup({
|
||||
platform: 'win32',
|
||||
});
|
||||
vi.mocked(child_process.execSync)
|
||||
.mockImplementationOnce(() => {
|
||||
throw new Error('Command not found');
|
||||
})
|
||||
.mockImplementationOnce(
|
||||
() => 'C:\\Program Files\\Antigravity\\bin\\antigravity.cmd',
|
||||
);
|
||||
|
||||
const result = await installer.install();
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
expect(child_process.execSync).toHaveBeenNthCalledWith(
|
||||
1,
|
||||
'where.exe agy.cmd',
|
||||
);
|
||||
expect(child_process.execSync).toHaveBeenNthCalledWith(
|
||||
2,
|
||||
'where.exe antigravity.cmd',
|
||||
);
|
||||
expect(child_process.spawnSync).toHaveBeenCalledWith(
|
||||
'C:\\Program Files\\Antigravity\\bin\\antigravity.cmd',
|
||||
[
|
||||
'--install-extension',
|
||||
'google.gemini-cli-vscode-ide-companion',
|
||||
'--force',
|
||||
],
|
||||
{ stdio: 'pipe', shell: true },
|
||||
);
|
||||
});
|
||||
|
||||
it('falls back to default commands if the alias is not set', async () => {
|
||||
vi.stubEnv('ANTIGRAVITY_CLI_ALIAS', '');
|
||||
const { installer } = setup({});
|
||||
const result = await installer.install();
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toContain(
|
||||
'ANTIGRAVITY_CLI_ALIAS environment variable not set',
|
||||
);
|
||||
expect(result.success).toBe(true);
|
||||
});
|
||||
|
||||
it('returns a failure message if the command is not found', async () => {
|
||||
@@ -302,6 +392,7 @@ describe('AntigravityInstaller', () => {
|
||||
const result = await installer.install();
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toContain('not-a-command not found');
|
||||
expect(result.message).toContain('Antigravity CLI not found');
|
||||
expect(result.message).toContain('agy, antigravity');
|
||||
});
|
||||
});
|
||||
|
||||
@@ -252,19 +252,36 @@ class AntigravityInstaller implements IdeInstaller {
|
||||
) {}
|
||||
|
||||
async install(): Promise<InstallResult> {
|
||||
const command = process.env['ANTIGRAVITY_CLI_ALIAS'];
|
||||
if (!command) {
|
||||
return {
|
||||
success: false,
|
||||
message: 'ANTIGRAVITY_CLI_ALIAS environment variable not set.',
|
||||
};
|
||||
const envCommand = process.env['ANTIGRAVITY_CLI_ALIAS'];
|
||||
const safeCommandPattern = /^[a-zA-Z0-9.\-_/\\]+$/;
|
||||
const sanitizedEnvCommand =
|
||||
envCommand && safeCommandPattern.test(envCommand)
|
||||
? envCommand
|
||||
: undefined;
|
||||
const fallbackCommands =
|
||||
this.platform === 'win32'
|
||||
? ['agy.cmd', 'antigravity.cmd']
|
||||
: ['agy', 'antigravity'];
|
||||
const commands = [
|
||||
...(sanitizedEnvCommand ? [sanitizedEnvCommand] : []),
|
||||
...fallbackCommands,
|
||||
].filter(
|
||||
(command, index, allCommands) => allCommands.indexOf(command) === index,
|
||||
);
|
||||
|
||||
let commandPath: string | null = null;
|
||||
for (const command of commands) {
|
||||
commandPath = await findCommand(command, this.platform);
|
||||
if (commandPath) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
const commandPath = await findCommand(command, this.platform);
|
||||
if (!commandPath) {
|
||||
const supportedCommands = fallbackCommands.join(', ');
|
||||
return {
|
||||
success: false,
|
||||
message: `${command} not found. Please ensure it is in your system's PATH.`,
|
||||
message: `Antigravity CLI not found. Please ensure one of these commands is in your system's PATH: ${supportedCommands}.`,
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -111,7 +111,6 @@ export class MCPOAuthProvider {
|
||||
scope: config.scopes?.join(' ') || '',
|
||||
};
|
||||
|
||||
// eslint-disable-next-line no-restricted-syntax -- TODO: Migrate to safeFetch for SSRF protection
|
||||
const response = await fetch(registrationUrl, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
@@ -301,7 +300,6 @@ export class MCPOAuthProvider {
|
||||
? { Accept: 'text/event-stream' }
|
||||
: { Accept: 'application/json' };
|
||||
|
||||
// eslint-disable-next-line no-restricted-syntax -- TODO: Migrate to safeFetch for SSRF protection
|
||||
const response = await fetch(mcpServerUrl, {
|
||||
method: 'HEAD',
|
||||
headers,
|
||||
|
||||
@@ -97,7 +97,6 @@ export class OAuthUtils {
|
||||
resourceMetadataUrl: string,
|
||||
): Promise<OAuthProtectedResourceMetadata | null> {
|
||||
try {
|
||||
// eslint-disable-next-line no-restricted-syntax -- TODO: Migrate to safeFetch for SSRF protection
|
||||
const response = await fetch(resourceMetadataUrl);
|
||||
if (!response.ok) {
|
||||
return null;
|
||||
@@ -122,7 +121,6 @@ export class OAuthUtils {
|
||||
authServerMetadataUrl: string,
|
||||
): Promise<OAuthAuthorizationServerMetadata | null> {
|
||||
try {
|
||||
// eslint-disable-next-line no-restricted-syntax -- TODO: Migrate to safeFetch for SSRF protection
|
||||
const response = await fetch(authServerMetadataUrl);
|
||||
if (!response.ok) {
|
||||
return null;
|
||||
|
||||
@@ -669,10 +669,13 @@ export function createPolicyUpdater(
|
||||
|
||||
if (message.mcpName) {
|
||||
newRule.mcpName = message.mcpName;
|
||||
// Extract simple tool name
|
||||
newRule.toolName = toolName.startsWith(`${message.mcpName}__`)
|
||||
? toolName.slice(message.mcpName.length + 2)
|
||||
: toolName;
|
||||
|
||||
const expectedPrefix = `${MCP_TOOL_PREFIX}${message.mcpName}_`;
|
||||
if (toolName.startsWith(expectedPrefix)) {
|
||||
newRule.toolName = toolName.slice(expectedPrefix.length);
|
||||
} else {
|
||||
newRule.toolName = toolName;
|
||||
}
|
||||
} else {
|
||||
newRule.toolName = toolName;
|
||||
}
|
||||
|
||||
@@ -17,6 +17,7 @@ import { DiscoveredMCPTool } from '../tools/mcp-tool.js';
|
||||
import { MockTool } from '../test-utils/mock-tool.js';
|
||||
import type { CallableTool } from '@google/genai';
|
||||
import type { MessageBus } from '../confirmation-bus/message-bus.js';
|
||||
import type { ToolRegistry } from '../tools/tool-registry.js';
|
||||
|
||||
vi.mock('../tools/memoryTool.js', async (importOriginal) => {
|
||||
const actual = await importOriginal();
|
||||
@@ -38,11 +39,20 @@ describe('PromptProvider', () => {
|
||||
vi.stubEnv('GEMINI_SYSTEM_MD', '');
|
||||
vi.stubEnv('GEMINI_WRITE_SYSTEM_MD', '');
|
||||
|
||||
const mockToolRegistry = {
|
||||
getAllToolNames: vi.fn().mockReturnValue([]),
|
||||
getAllTools: vi.fn().mockReturnValue([]),
|
||||
};
|
||||
mockConfig = {
|
||||
getToolRegistry: vi.fn().mockReturnValue({
|
||||
getAllToolNames: vi.fn().mockReturnValue([]),
|
||||
getAllTools: vi.fn().mockReturnValue([]),
|
||||
}),
|
||||
get config() {
|
||||
return this as unknown as Config;
|
||||
},
|
||||
get toolRegistry() {
|
||||
return (
|
||||
this as { getToolRegistry: () => ToolRegistry }
|
||||
).getToolRegistry?.() as unknown as ToolRegistry;
|
||||
},
|
||||
getToolRegistry: vi.fn().mockReturnValue(mockToolRegistry),
|
||||
getEnableShellOutputEfficiency: vi.fn().mockReturnValue(true),
|
||||
storage: {
|
||||
getProjectTempDir: vi.fn().mockReturnValue('/tmp/project-temp'),
|
||||
|
||||
@@ -7,7 +7,6 @@
|
||||
import fs from 'node:fs';
|
||||
import path from 'node:path';
|
||||
import process from 'node:process';
|
||||
import type { Config } from '../config/config.js';
|
||||
import type { HierarchicalMemory } from '../config/memory.js';
|
||||
import { GEMINI_DIR } from '../utils/paths.js';
|
||||
import { ApprovalMode } from '../policy/types.js';
|
||||
@@ -31,6 +30,7 @@ import {
|
||||
import { resolveModel, supportsModernFeatures } from '../config/models.js';
|
||||
import { DiscoveredMCPTool } from '../tools/mcp-tool.js';
|
||||
import { getAllGeminiMdFilenames } from '../tools/memoryTool.js';
|
||||
import type { AgentLoopContext } from '../config/agent-loop-context.js';
|
||||
|
||||
/**
|
||||
* Orchestrates prompt generation by gathering context and building options.
|
||||
@@ -40,7 +40,7 @@ export class PromptProvider {
|
||||
* Generates the core system prompt.
|
||||
*/
|
||||
getCoreSystemPrompt(
|
||||
config: Config,
|
||||
context: AgentLoopContext,
|
||||
userMemory?: string | HierarchicalMemory,
|
||||
interactiveOverride?: boolean,
|
||||
): string {
|
||||
@@ -48,27 +48,29 @@ export class PromptProvider {
|
||||
process.env['GEMINI_SYSTEM_MD'],
|
||||
);
|
||||
|
||||
const interactiveMode = interactiveOverride ?? config.isInteractive();
|
||||
const approvalMode = config.getApprovalMode?.() ?? ApprovalMode.DEFAULT;
|
||||
const interactiveMode =
|
||||
interactiveOverride ?? context.config.isInteractive();
|
||||
const approvalMode =
|
||||
context.config.getApprovalMode?.() ?? ApprovalMode.DEFAULT;
|
||||
const isPlanMode = approvalMode === ApprovalMode.PLAN;
|
||||
const isYoloMode = approvalMode === ApprovalMode.YOLO;
|
||||
const skills = config.getSkillManager().getSkills();
|
||||
const toolNames = config.getToolRegistry().getAllToolNames();
|
||||
const skills = context.config.getSkillManager().getSkills();
|
||||
const toolNames = context.toolRegistry.getAllToolNames();
|
||||
const enabledToolNames = new Set(toolNames);
|
||||
const approvedPlanPath = config.getApprovedPlanPath();
|
||||
const approvedPlanPath = context.config.getApprovedPlanPath();
|
||||
|
||||
const desiredModel = resolveModel(
|
||||
config.getActiveModel(),
|
||||
config.getGemini31LaunchedSync?.() ?? false,
|
||||
context.config.getActiveModel(),
|
||||
context.config.getGemini31LaunchedSync?.() ?? false,
|
||||
);
|
||||
const isModernModel = supportsModernFeatures(desiredModel);
|
||||
const isModernModel = supportsModernFeatures(desiredModel, context.config);
|
||||
const activeSnippets = isModernModel ? snippets : legacySnippets;
|
||||
const contextFilenames = getAllGeminiMdFilenames();
|
||||
|
||||
// --- Context Gathering ---
|
||||
let planModeToolsList = '';
|
||||
if (isPlanMode) {
|
||||
const allTools = config.getToolRegistry().getAllTools();
|
||||
const allTools = context.toolRegistry.getAllTools();
|
||||
planModeToolsList = allTools
|
||||
.map((t) => {
|
||||
if (t instanceof DiscoveredMCPTool) {
|
||||
@@ -100,7 +102,7 @@ export class PromptProvider {
|
||||
);
|
||||
basePrompt = applySubstitutions(
|
||||
basePrompt,
|
||||
config,
|
||||
context.config,
|
||||
skillsPrompt,
|
||||
isModernModel,
|
||||
);
|
||||
@@ -124,7 +126,7 @@ export class PromptProvider {
|
||||
contextFilenames,
|
||||
})),
|
||||
subAgents: this.withSection('agentContexts', () =>
|
||||
config
|
||||
context.config
|
||||
.getAgentRegistry()
|
||||
.getAllDefinitions()
|
||||
.map((d) => ({
|
||||
@@ -159,7 +161,7 @@ export class PromptProvider {
|
||||
approvedPlan: approvedPlanPath
|
||||
? { path: approvedPlanPath }
|
||||
: undefined,
|
||||
taskTracker: config.isTrackerEnabled(),
|
||||
taskTracker: context.config.isTrackerEnabled(),
|
||||
}),
|
||||
!isPlanMode,
|
||||
),
|
||||
@@ -167,19 +169,20 @@ export class PromptProvider {
|
||||
'planningWorkflow',
|
||||
() => ({
|
||||
planModeToolsList,
|
||||
plansDir: config.storage.getPlansDir(),
|
||||
approvedPlanPath: config.getApprovedPlanPath(),
|
||||
taskTracker: config.isTrackerEnabled(),
|
||||
plansDir: context.config.storage.getPlansDir(),
|
||||
approvedPlanPath: context.config.getApprovedPlanPath(),
|
||||
taskTracker: context.config.isTrackerEnabled(),
|
||||
}),
|
||||
isPlanMode,
|
||||
),
|
||||
taskTracker: config.isTrackerEnabled(),
|
||||
taskTracker: context.config.isTrackerEnabled(),
|
||||
operationalGuidelines: this.withSection(
|
||||
'operationalGuidelines',
|
||||
() => ({
|
||||
interactive: interactiveMode,
|
||||
enableShellEfficiency: config.getEnableShellOutputEfficiency(),
|
||||
interactiveShellEnabled: config.isInteractiveShellEnabled(),
|
||||
enableShellEfficiency:
|
||||
context.config.getEnableShellOutputEfficiency(),
|
||||
interactiveShellEnabled: context.config.isInteractiveShellEnabled(),
|
||||
}),
|
||||
),
|
||||
sandbox: this.withSection('sandbox', () => getSandboxMode()),
|
||||
@@ -227,14 +230,16 @@ export class PromptProvider {
|
||||
return sanitizedPrompt;
|
||||
}
|
||||
|
||||
getCompressionPrompt(config: Config): string {
|
||||
getCompressionPrompt(context: AgentLoopContext): string {
|
||||
const desiredModel = resolveModel(
|
||||
config.getActiveModel(),
|
||||
config.getGemini31LaunchedSync?.() ?? false,
|
||||
context.config.getActiveModel(),
|
||||
context.config.getGemini31LaunchedSync?.() ?? false,
|
||||
);
|
||||
const isModernModel = supportsModernFeatures(desiredModel);
|
||||
const isModernModel = supportsModernFeatures(desiredModel, context.config);
|
||||
const activeSnippets = isModernModel ? snippets : legacySnippets;
|
||||
return activeSnippets.getCompressionPrompt(config.getApprovedPlanPath());
|
||||
return activeSnippets.getCompressionPrompt(
|
||||
context.config.getApprovedPlanPath(),
|
||||
);
|
||||
}
|
||||
|
||||
private withSection<T>(
|
||||
|
||||
@@ -11,6 +11,7 @@ import {
|
||||
applySubstitutions,
|
||||
} from './utils.js';
|
||||
import type { Config } from '../config/config.js';
|
||||
import type { ToolRegistry } from '../tools/tool-registry.js';
|
||||
|
||||
vi.mock('../utils/paths.js', () => ({
|
||||
homedir: vi.fn().mockReturnValue('/mock/home'),
|
||||
@@ -208,6 +209,13 @@ describe('applySubstitutions', () => {
|
||||
|
||||
beforeEach(() => {
|
||||
mockConfig = {
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
toolRegistry: {
|
||||
getAllToolNames: vi.fn().mockReturnValue([]),
|
||||
getAllTools: vi.fn().mockReturnValue([]),
|
||||
},
|
||||
getAgentRegistry: vi.fn().mockReturnValue({
|
||||
getAllDefinitions: vi.fn().mockReturnValue([]),
|
||||
}),
|
||||
@@ -256,10 +264,10 @@ describe('applySubstitutions', () => {
|
||||
});
|
||||
|
||||
it('should replace ${AvailableTools} with tool names list', () => {
|
||||
vi.mocked(mockConfig.getToolRegistry).mockReturnValue({
|
||||
(mockConfig as unknown as { toolRegistry: ToolRegistry }).toolRegistry = {
|
||||
getAllToolNames: vi.fn().mockReturnValue(['read_file', 'write_file']),
|
||||
getAllTools: vi.fn().mockReturnValue([]),
|
||||
} as unknown as ReturnType<Config['getToolRegistry']>);
|
||||
} as unknown as ToolRegistry;
|
||||
|
||||
const result = applySubstitutions(
|
||||
'Tools: ${AvailableTools}',
|
||||
@@ -280,10 +288,10 @@ describe('applySubstitutions', () => {
|
||||
});
|
||||
|
||||
it('should replace tool-specific ${toolName_ToolName} variables', () => {
|
||||
vi.mocked(mockConfig.getToolRegistry).mockReturnValue({
|
||||
(mockConfig as unknown as { toolRegistry: ToolRegistry }).toolRegistry = {
|
||||
getAllToolNames: vi.fn().mockReturnValue(['read_file']),
|
||||
getAllTools: vi.fn().mockReturnValue([]),
|
||||
} as unknown as ReturnType<Config['getToolRegistry']>);
|
||||
} as unknown as ToolRegistry;
|
||||
|
||||
const result = applySubstitutions(
|
||||
'Use ${read_file_ToolName} to read',
|
||||
|
||||
@@ -8,9 +8,9 @@ import path from 'node:path';
|
||||
import process from 'node:process';
|
||||
import { homedir } from '../utils/paths.js';
|
||||
import { debugLogger } from '../utils/debugLogger.js';
|
||||
import type { Config } from '../config/config.js';
|
||||
import * as snippets from './snippets.js';
|
||||
import * as legacySnippets from './snippets.legacy.js';
|
||||
import type { AgentLoopContext } from '../config/agent-loop-context.js';
|
||||
|
||||
export type ResolvedPath = {
|
||||
isSwitch: boolean;
|
||||
@@ -63,7 +63,7 @@ export function resolvePathFromEnv(envVar?: string): ResolvedPath {
|
||||
*/
|
||||
export function applySubstitutions(
|
||||
prompt: string,
|
||||
config: Config,
|
||||
context: AgentLoopContext,
|
||||
skillsPrompt: string,
|
||||
isGemini3: boolean = false,
|
||||
): string {
|
||||
@@ -73,7 +73,7 @@ export function applySubstitutions(
|
||||
|
||||
const activeSnippets = isGemini3 ? snippets : legacySnippets;
|
||||
const subAgentsContent = activeSnippets.renderSubAgents(
|
||||
config
|
||||
context.config
|
||||
.getAgentRegistry()
|
||||
.getAllDefinitions()
|
||||
.map((d) => ({
|
||||
@@ -84,7 +84,7 @@ export function applySubstitutions(
|
||||
|
||||
result = result.replace(/\${SubAgents}/g, subAgentsContent);
|
||||
|
||||
const toolRegistry = config.getToolRegistry();
|
||||
const toolRegistry = context.toolRegistry;
|
||||
const allToolNames = toolRegistry.getAllToolNames();
|
||||
const availableToolsList =
|
||||
allToolNames.length > 0
|
||||
|
||||
@@ -36,7 +36,7 @@ export class ApprovalModeStrategy implements RoutingStrategy {
|
||||
const model = context.requestedModel ?? config.getModel();
|
||||
|
||||
// This strategy only applies to "auto" models.
|
||||
if (!isAutoModel(model)) {
|
||||
if (!isAutoModel(model, config)) {
|
||||
return null;
|
||||
}
|
||||
|
||||
|
||||
@@ -139,7 +139,7 @@ export class ClassifierStrategy implements RoutingStrategy {
|
||||
const model = context.requestedModel ?? config.getModel();
|
||||
if (
|
||||
(await config.getNumericalRoutingEnabled()) &&
|
||||
isGemini3Model(model)
|
||||
isGemini3Model(model, config)
|
||||
) {
|
||||
return null;
|
||||
}
|
||||
|
||||
@@ -109,7 +109,7 @@ export class NumericalClassifierStrategy implements RoutingStrategy {
|
||||
return null;
|
||||
}
|
||||
|
||||
if (!isGemini3Model(model)) {
|
||||
if (!isGemini3Model(model, config)) {
|
||||
return null;
|
||||
}
|
||||
|
||||
|
||||
@@ -29,7 +29,7 @@ export class OverrideStrategy implements RoutingStrategy {
|
||||
const overrideModel = context.requestedModel ?? config.getModel();
|
||||
|
||||
// If the model is 'auto' we should pass to the next strategy.
|
||||
if (isAutoModel(overrideModel)) {
|
||||
if (isAutoModel(overrideModel, config)) {
|
||||
return null;
|
||||
}
|
||||
|
||||
|
||||
@@ -36,12 +36,15 @@ describe('ConsecaSafetyChecker', () => {
|
||||
checker = ConsecaSafetyChecker.getInstance();
|
||||
|
||||
mockConfig = {
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
enableConseca: true,
|
||||
getToolRegistry: vi.fn().mockReturnValue({
|
||||
getFunctionDeclarations: vi.fn().mockReturnValue([]),
|
||||
}),
|
||||
} as unknown as Config;
|
||||
checker.setConfig(mockConfig);
|
||||
checker.setContext(mockConfig);
|
||||
vi.clearAllMocks();
|
||||
|
||||
// Default mock implementations
|
||||
@@ -72,9 +75,12 @@ describe('ConsecaSafetyChecker', () => {
|
||||
|
||||
it('should return ALLOW if enableConseca is false', async () => {
|
||||
const disabledConfig = {
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
enableConseca: false,
|
||||
} as unknown as Config;
|
||||
checker.setConfig(disabledConfig);
|
||||
checker.setContext(disabledConfig);
|
||||
|
||||
const input: SafetyCheckInput = {
|
||||
protocolVersion: '1.0.0',
|
||||
|
||||
@@ -23,12 +23,13 @@ import type { Config } from '../../config/config.js';
|
||||
import { generatePolicy } from './policy-generator.js';
|
||||
import { enforcePolicy } from './policy-enforcer.js';
|
||||
import type { SecurityPolicy } from './types.js';
|
||||
import type { AgentLoopContext } from '../../config/agent-loop-context.js';
|
||||
|
||||
export class ConsecaSafetyChecker implements InProcessChecker {
|
||||
private static instance: ConsecaSafetyChecker | undefined;
|
||||
private currentPolicy: SecurityPolicy | null = null;
|
||||
private activeUserPrompt: string | null = null;
|
||||
private config: Config | null = null;
|
||||
private context: AgentLoopContext | null = null;
|
||||
|
||||
/**
|
||||
* Private constructor to enforce singleton pattern.
|
||||
@@ -50,8 +51,8 @@ export class ConsecaSafetyChecker implements InProcessChecker {
|
||||
ConsecaSafetyChecker.instance = undefined;
|
||||
}
|
||||
|
||||
setConfig(config: Config): void {
|
||||
this.config = config;
|
||||
setContext(context: AgentLoopContext): void {
|
||||
this.context = context;
|
||||
}
|
||||
|
||||
async check(input: SafetyCheckInput): Promise<SafetyCheckResult> {
|
||||
@@ -59,7 +60,7 @@ export class ConsecaSafetyChecker implements InProcessChecker {
|
||||
`[Conseca] check called. History is: ${JSON.stringify(input.context.history)}`,
|
||||
);
|
||||
|
||||
if (!this.config) {
|
||||
if (!this.context) {
|
||||
debugLogger.debug('[Conseca] check failed: Config not initialized');
|
||||
return {
|
||||
decision: SafetyCheckDecision.ALLOW,
|
||||
@@ -67,7 +68,7 @@ export class ConsecaSafetyChecker implements InProcessChecker {
|
||||
};
|
||||
}
|
||||
|
||||
if (!this.config.enableConseca) {
|
||||
if (!this.context.config.enableConseca) {
|
||||
debugLogger.debug('[Conseca] check skipped: Conseca is not enabled.');
|
||||
return {
|
||||
decision: SafetyCheckDecision.ALLOW,
|
||||
@@ -78,14 +79,14 @@ export class ConsecaSafetyChecker implements InProcessChecker {
|
||||
const userPrompt = this.extractUserPrompt(input);
|
||||
let trustedContent = '';
|
||||
|
||||
const toolRegistry = this.config.getToolRegistry();
|
||||
const toolRegistry = this.context.toolRegistry;
|
||||
if (toolRegistry) {
|
||||
const tools = toolRegistry.getFunctionDeclarations();
|
||||
trustedContent = JSON.stringify(tools, null, 2);
|
||||
}
|
||||
|
||||
if (userPrompt) {
|
||||
await this.getPolicy(userPrompt, trustedContent, this.config);
|
||||
await this.getPolicy(userPrompt, trustedContent, this.context.config);
|
||||
} else {
|
||||
debugLogger.debug(
|
||||
`[Conseca] Skipping policy generation because userPrompt is null`,
|
||||
@@ -104,12 +105,12 @@ export class ConsecaSafetyChecker implements InProcessChecker {
|
||||
result = await enforcePolicy(
|
||||
this.currentPolicy,
|
||||
input.toolCall,
|
||||
this.config,
|
||||
this.context.config,
|
||||
);
|
||||
}
|
||||
|
||||
logConsecaVerdict(
|
||||
this.config,
|
||||
this.context.config,
|
||||
new ConsecaVerdictEvent(
|
||||
userPrompt || '',
|
||||
JSON.stringify(this.currentPolicy || {}),
|
||||
|
||||
@@ -8,6 +8,7 @@ import { describe, it, expect, vi, beforeEach } from 'vitest';
|
||||
import { ContextBuilder } from './context-builder.js';
|
||||
import type { Config } from '../config/config.js';
|
||||
import type { Content, FunctionCall } from '@google/genai';
|
||||
import type { GeminiClient } from '../core/client.js';
|
||||
|
||||
describe('ContextBuilder', () => {
|
||||
let contextBuilder: ContextBuilder;
|
||||
@@ -20,15 +21,20 @@ describe('ContextBuilder', () => {
|
||||
vi.spyOn(process, 'cwd').mockReturnValue(mockCwd);
|
||||
mockHistory = [];
|
||||
|
||||
const mockGeminiClient = {
|
||||
getHistory: vi.fn().mockImplementation(() => mockHistory),
|
||||
};
|
||||
mockConfig = {
|
||||
get config() {
|
||||
return this as unknown as Config;
|
||||
},
|
||||
geminiClient: mockGeminiClient as unknown as GeminiClient,
|
||||
getWorkspaceContext: vi.fn().mockReturnValue({
|
||||
getDirectories: vi.fn().mockReturnValue(mockWorkspaces),
|
||||
}),
|
||||
getQuestion: vi.fn().mockReturnValue('mock question'),
|
||||
getGeminiClient: vi.fn().mockReturnValue({
|
||||
getHistory: vi.fn().mockImplementation(() => mockHistory),
|
||||
}),
|
||||
};
|
||||
getGeminiClient: vi.fn().mockReturnValue(mockGeminiClient),
|
||||
} as Partial<Config>;
|
||||
contextBuilder = new ContextBuilder(mockConfig as unknown as Config);
|
||||
});
|
||||
|
||||
|
||||
@@ -5,21 +5,21 @@
|
||||
*/
|
||||
|
||||
import type { SafetyCheckInput, ConversationTurn } from './protocol.js';
|
||||
import type { Config } from '../config/config.js';
|
||||
import { debugLogger } from '../utils/debugLogger.js';
|
||||
import type { Content, FunctionCall } from '@google/genai';
|
||||
import type { AgentLoopContext } from '../config/agent-loop-context.js';
|
||||
|
||||
/**
|
||||
* Builds context objects for safety checkers, ensuring sensitive data is filtered.
|
||||
*/
|
||||
export class ContextBuilder {
|
||||
constructor(private readonly config: Config) {}
|
||||
constructor(private readonly context: AgentLoopContext) {}
|
||||
|
||||
/**
|
||||
* Builds the full context object with all available data.
|
||||
*/
|
||||
buildFullContext(): SafetyCheckInput['context'] {
|
||||
const clientHistory = this.config.getGeminiClient()?.getHistory() || [];
|
||||
const clientHistory = this.context.geminiClient?.getHistory() || [];
|
||||
const history = this.convertHistoryToTurns(clientHistory);
|
||||
|
||||
debugLogger.debug(
|
||||
@@ -29,7 +29,7 @@ export class ContextBuilder {
|
||||
// ContextBuilder's responsibility is to provide the *current* context.
|
||||
// If the conversation hasn't started (history is empty), we check if there's a pending question.
|
||||
// However, if the history is NOT empty, we trust it reflects the true state.
|
||||
const currentQuestion = this.config.getQuestion();
|
||||
const currentQuestion = this.context.config.getQuestion();
|
||||
if (currentQuestion && history.length === 0) {
|
||||
history.push({
|
||||
user: {
|
||||
@@ -43,7 +43,7 @@ export class ContextBuilder {
|
||||
environment: {
|
||||
cwd: process.cwd(),
|
||||
// eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
|
||||
workspaces: this.config
|
||||
workspaces: this.context.config
|
||||
.getWorkspaceContext()
|
||||
.getDirectories() as string[],
|
||||
},
|
||||
|
||||
@@ -227,6 +227,7 @@ describe('policy.ts', () => {
|
||||
ToolConfirmationOutcome.ProceedAlways,
|
||||
undefined,
|
||||
mockConfig,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockConfig.setApprovalMode).toHaveBeenCalledWith(
|
||||
@@ -254,6 +255,7 @@ describe('policy.ts', () => {
|
||||
ToolConfirmationOutcome.ProceedAlways,
|
||||
undefined,
|
||||
mockConfig,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).toHaveBeenCalledWith(
|
||||
@@ -286,6 +288,7 @@ describe('policy.ts', () => {
|
||||
ToolConfirmationOutcome.ProceedAlwaysAndSave,
|
||||
undefined,
|
||||
mockConfig,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).toHaveBeenCalledWith(
|
||||
@@ -324,6 +327,7 @@ describe('policy.ts', () => {
|
||||
ToolConfirmationOutcome.ProceedAlways,
|
||||
details,
|
||||
mockConfig,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).toHaveBeenCalledWith(
|
||||
@@ -362,12 +366,13 @@ describe('policy.ts', () => {
|
||||
ToolConfirmationOutcome.ProceedAlwaysServer,
|
||||
details,
|
||||
mockConfig,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
type: MessageBusType.UPDATE_POLICY,
|
||||
toolName: 'my-server__*',
|
||||
toolName: 'mcp_my-server_*',
|
||||
mcpName: 'my-server',
|
||||
persist: false,
|
||||
}),
|
||||
@@ -393,6 +398,7 @@ describe('policy.ts', () => {
|
||||
ToolConfirmationOutcome.ProceedOnce,
|
||||
undefined,
|
||||
mockConfig,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).not.toHaveBeenCalled();
|
||||
@@ -418,6 +424,7 @@ describe('policy.ts', () => {
|
||||
ToolConfirmationOutcome.Cancel,
|
||||
undefined,
|
||||
mockConfig,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).not.toHaveBeenCalled();
|
||||
@@ -442,6 +449,7 @@ describe('policy.ts', () => {
|
||||
ToolConfirmationOutcome.ModifyWithEditor,
|
||||
undefined,
|
||||
mockConfig,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).not.toHaveBeenCalled();
|
||||
@@ -474,6 +482,7 @@ describe('policy.ts', () => {
|
||||
ToolConfirmationOutcome.ProceedAlwaysTool,
|
||||
details,
|
||||
mockConfig,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).toHaveBeenCalledWith(
|
||||
@@ -513,6 +522,7 @@ describe('policy.ts', () => {
|
||||
ToolConfirmationOutcome.ProceedAlways,
|
||||
details,
|
||||
mockConfig,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).toHaveBeenCalledWith(
|
||||
@@ -554,6 +564,7 @@ describe('policy.ts', () => {
|
||||
ToolConfirmationOutcome.ProceedAlwaysAndSave,
|
||||
details,
|
||||
mockConfig,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).toHaveBeenCalledWith(
|
||||
@@ -585,8 +596,8 @@ describe('policy.ts', () => {
|
||||
undefined,
|
||||
{
|
||||
config: mockConfig,
|
||||
messageBus: mockMessageBus,
|
||||
} as unknown as AgentLoopContext,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).toHaveBeenCalledWith(
|
||||
@@ -615,8 +626,8 @@ describe('policy.ts', () => {
|
||||
undefined,
|
||||
{
|
||||
config: mockConfig,
|
||||
messageBus: mockMessageBus,
|
||||
} as unknown as AgentLoopContext,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).toHaveBeenCalledWith(
|
||||
@@ -653,8 +664,8 @@ describe('policy.ts', () => {
|
||||
details,
|
||||
{
|
||||
config: mockConfig,
|
||||
messageBus: mockMessageBus,
|
||||
} as unknown as AgentLoopContext,
|
||||
mockMessageBus,
|
||||
);
|
||||
|
||||
expect(mockMessageBus.publish).toHaveBeenCalledWith(
|
||||
@@ -777,7 +788,11 @@ describe('Plan Mode Denial Consistency', () => {
|
||||
|
||||
if (enableEventDrivenScheduler) {
|
||||
const scheduler = new Scheduler({
|
||||
context: mockConfig,
|
||||
context: {
|
||||
config: mockConfig,
|
||||
messageBus: mockMessageBus,
|
||||
toolRegistry: mockToolRegistry,
|
||||
} as unknown as AgentLoopContext,
|
||||
getPreferredEditor: () => undefined,
|
||||
schedulerId: ROOT_SCHEDULER_ID,
|
||||
});
|
||||
@@ -793,7 +808,11 @@ describe('Plan Mode Denial Consistency', () => {
|
||||
} else {
|
||||
let capturedCalls: CompletedToolCall[] = [];
|
||||
const scheduler = new CoreToolScheduler({
|
||||
config: mockConfig,
|
||||
context: {
|
||||
config: mockConfig,
|
||||
messageBus: mockMessageBus,
|
||||
toolRegistry: mockToolRegistry,
|
||||
} as unknown as AgentLoopContext,
|
||||
getPreferredEditor: () => undefined,
|
||||
onAllToolCallsComplete: async (calls) => {
|
||||
capturedCalls = calls;
|
||||
|
||||
@@ -25,7 +25,7 @@ import {
|
||||
} from '../tools/tools.js';
|
||||
import { buildFilePathArgsPattern } from '../policy/utils.js';
|
||||
import { makeRelative } from '../utils/paths.js';
|
||||
import { DiscoveredMCPTool } from '../tools/mcp-tool.js';
|
||||
import { DiscoveredMCPTool, formatMcpToolName } from '../tools/mcp-tool.js';
|
||||
import { EDIT_TOOL_NAMES } from '../tools/tool-names.js';
|
||||
import type { ValidatingToolCall } from './types.js';
|
||||
import type { AgentLoopContext } from '../config/agent-loop-context.js';
|
||||
@@ -114,13 +114,12 @@ export async function updatePolicy(
|
||||
outcome: ToolConfirmationOutcome,
|
||||
confirmationDetails: SerializableConfirmationDetails | undefined,
|
||||
context: AgentLoopContext,
|
||||
messageBus: MessageBus,
|
||||
toolInvocation?: AnyToolInvocation,
|
||||
): Promise<void> {
|
||||
const deps = { ...context, toolInvocation };
|
||||
|
||||
// Mode Transitions (AUTO_EDIT)
|
||||
if (isAutoEditTransition(tool, outcome)) {
|
||||
deps.config.setApprovalMode(ApprovalMode.AUTO_EDIT);
|
||||
context.config.setApprovalMode(ApprovalMode.AUTO_EDIT);
|
||||
return;
|
||||
}
|
||||
|
||||
@@ -129,8 +128,9 @@ export async function updatePolicy(
|
||||
if (outcome === ToolConfirmationOutcome.ProceedAlwaysAndSave) {
|
||||
// If folder is trusted and workspace policies are enabled, we prefer workspace scope.
|
||||
if (
|
||||
deps.config.isTrustedFolder() &&
|
||||
deps.config.getWorkspacePoliciesDir() !== undefined
|
||||
context.config &&
|
||||
context.config.isTrustedFolder() &&
|
||||
context.config.getWorkspacePoliciesDir() !== undefined
|
||||
) {
|
||||
persistScope = 'workspace';
|
||||
} else {
|
||||
@@ -144,7 +144,7 @@ export async function updatePolicy(
|
||||
tool,
|
||||
outcome,
|
||||
confirmationDetails,
|
||||
deps.messageBus,
|
||||
messageBus,
|
||||
persistScope,
|
||||
);
|
||||
return;
|
||||
@@ -155,10 +155,10 @@ export async function updatePolicy(
|
||||
tool,
|
||||
outcome,
|
||||
confirmationDetails,
|
||||
deps.messageBus,
|
||||
messageBus,
|
||||
persistScope,
|
||||
deps.toolInvocation,
|
||||
deps.config,
|
||||
toolInvocation,
|
||||
context.config,
|
||||
);
|
||||
}
|
||||
|
||||
@@ -247,7 +247,7 @@ async function handleMcpPolicyUpdate(
|
||||
|
||||
// If "Always allow all tools from this server", use the wildcard pattern
|
||||
if (outcome === ToolConfirmationOutcome.ProceedAlwaysServer) {
|
||||
toolName = `${confirmationDetails.serverName}__*`;
|
||||
toolName = formatMcpToolName(confirmationDetails.serverName, '*');
|
||||
}
|
||||
|
||||
await messageBus.publish({
|
||||
|
||||
@@ -845,6 +845,7 @@ describe('Scheduler (Orchestrator)', () => {
|
||||
resolution.lastDetails,
|
||||
mockConfig,
|
||||
expect.anything(),
|
||||
expect.anything(),
|
||||
);
|
||||
|
||||
expect(mockExecutor.execute).toHaveBeenCalled();
|
||||
|
||||
@@ -623,6 +623,7 @@ export class Scheduler {
|
||||
outcome,
|
||||
lastDetails,
|
||||
this.context,
|
||||
this.messageBus,
|
||||
toolCall.invocation,
|
||||
);
|
||||
}
|
||||
|
||||
@@ -172,6 +172,9 @@ describe('ChatCompressionService', () => {
|
||||
} as unknown as GenerateContentResponse);
|
||||
|
||||
mockConfig = {
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
getCompressionThreshold: vi.fn(),
|
||||
getBaseLlmClient: vi.fn().mockReturnValue({
|
||||
generateContent: mockGenerateContent,
|
||||
|
||||
@@ -43,6 +43,13 @@ describe('ChatRecordingService', () => {
|
||||
);
|
||||
|
||||
mockConfig = {
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
toolRegistry: {
|
||||
getTool: vi.fn(),
|
||||
},
|
||||
promptId: 'test-session-id',
|
||||
getSessionId: vi.fn().mockReturnValue('test-session-id'),
|
||||
getProjectRoot: vi.fn().mockReturnValue('/test/project/root'),
|
||||
storage: {
|
||||
|
||||
@@ -4,7 +4,6 @@
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { type Config } from '../config/config.js';
|
||||
import { type Status } from '../core/coreToolScheduler.js';
|
||||
import { type ThoughtSummary } from '../utils/thoughtUtils.js';
|
||||
import { getProjectHash } from '../utils/paths.js';
|
||||
@@ -20,6 +19,7 @@ import type {
|
||||
} from '@google/genai';
|
||||
import { debugLogger } from '../utils/debugLogger.js';
|
||||
import type { ToolResultDisplay } from '../tools/tools.js';
|
||||
import type { AgentLoopContext } from '../config/agent-loop-context.js';
|
||||
|
||||
export const SESSION_FILE_PREFIX = 'session-';
|
||||
|
||||
@@ -134,12 +134,12 @@ export class ChatRecordingService {
|
||||
private kind?: 'main' | 'subagent';
|
||||
private queuedThoughts: Array<ThoughtSummary & { timestamp: string }> = [];
|
||||
private queuedTokens: TokensSummary | null = null;
|
||||
private config: Config;
|
||||
private context: AgentLoopContext;
|
||||
|
||||
constructor(config: Config) {
|
||||
this.config = config;
|
||||
this.sessionId = config.getSessionId();
|
||||
this.projectHash = getProjectHash(config.getProjectRoot());
|
||||
constructor(context: AgentLoopContext) {
|
||||
this.context = context;
|
||||
this.sessionId = context.promptId;
|
||||
this.projectHash = getProjectHash(context.config.getProjectRoot());
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -171,9 +171,9 @@ export class ChatRecordingService {
|
||||
this.cachedConversation = null;
|
||||
} else {
|
||||
// Create new session
|
||||
this.sessionId = this.config.getSessionId();
|
||||
this.sessionId = this.context.promptId;
|
||||
const chatsDir = path.join(
|
||||
this.config.storage.getProjectTempDir(),
|
||||
this.context.config.storage.getProjectTempDir(),
|
||||
'chats',
|
||||
);
|
||||
fs.mkdirSync(chatsDir, { recursive: true });
|
||||
@@ -341,7 +341,7 @@ export class ChatRecordingService {
|
||||
if (!this.conversationFile) return;
|
||||
|
||||
// Enrich tool calls with metadata from the ToolRegistry
|
||||
const toolRegistry = this.config.getToolRegistry();
|
||||
const toolRegistry = this.context.toolRegistry;
|
||||
const enrichedToolCalls = toolCalls.map((toolCall) => {
|
||||
const toolInstance = toolRegistry.getTool(toolCall.name);
|
||||
return {
|
||||
@@ -594,7 +594,7 @@ export class ChatRecordingService {
|
||||
*/
|
||||
deleteSession(sessionId: string): void {
|
||||
try {
|
||||
const tempDir = this.config.storage.getProjectTempDir();
|
||||
const tempDir = this.context.config.storage.getProjectTempDir();
|
||||
const chatsDir = path.join(tempDir, 'chats');
|
||||
const sessionPath = path.join(chatsDir, `${sessionId}.json`);
|
||||
if (fs.existsSync(sessionPath)) {
|
||||
|
||||
@@ -36,6 +36,9 @@ describe('LoopDetectionService', () => {
|
||||
|
||||
beforeEach(() => {
|
||||
mockConfig = {
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
getTelemetryEnabled: () => true,
|
||||
isInteractive: () => false,
|
||||
getDisableLoopDetection: () => false,
|
||||
@@ -806,7 +809,13 @@ describe('LoopDetectionService LLM Checks', () => {
|
||||
vi.mocked(mockAvailability.snapshot).mockReturnValue({ available: true });
|
||||
|
||||
mockConfig = {
|
||||
get config() {
|
||||
return this;
|
||||
},
|
||||
getGeminiClient: () => mockGeminiClient,
|
||||
get geminiClient() {
|
||||
return mockGeminiClient;
|
||||
},
|
||||
getBaseLlmClient: () => mockBaseLlmClient,
|
||||
getDisableLoopDetection: () => false,
|
||||
getDebugMode: () => false,
|
||||
|
||||
@@ -19,12 +19,12 @@ import {
|
||||
LlmLoopCheckEvent,
|
||||
LlmRole,
|
||||
} from '../telemetry/types.js';
|
||||
import type { Config } from '../config/config.js';
|
||||
import {
|
||||
isFunctionCall,
|
||||
isFunctionResponse,
|
||||
} from '../utils/messageInspectors.js';
|
||||
import { debugLogger } from '../utils/debugLogger.js';
|
||||
import type { AgentLoopContext } from '../config/agent-loop-context.js';
|
||||
|
||||
const TOOL_CALL_LOOP_THRESHOLD = 5;
|
||||
const CONTENT_LOOP_THRESHOLD = 10;
|
||||
@@ -131,7 +131,7 @@ export interface LoopDetectionResult {
|
||||
* Monitors tool call repetitions and content sentence repetitions.
|
||||
*/
|
||||
export class LoopDetectionService {
|
||||
private readonly config: Config;
|
||||
private readonly context: AgentLoopContext;
|
||||
private promptId = '';
|
||||
private userPrompt = '';
|
||||
|
||||
@@ -157,8 +157,8 @@ export class LoopDetectionService {
|
||||
// Session-level disable flag
|
||||
private disabledForSession = false;
|
||||
|
||||
constructor(config: Config) {
|
||||
this.config = config;
|
||||
constructor(context: AgentLoopContext) {
|
||||
this.context = context;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -167,7 +167,7 @@ export class LoopDetectionService {
|
||||
disableForSession(): void {
|
||||
this.disabledForSession = true;
|
||||
logLoopDetectionDisabled(
|
||||
this.config,
|
||||
this.context.config,
|
||||
new LoopDetectionDisabledEvent(this.promptId),
|
||||
);
|
||||
}
|
||||
@@ -184,7 +184,10 @@ export class LoopDetectionService {
|
||||
* @returns A LoopDetectionResult
|
||||
*/
|
||||
addAndCheck(event: ServerGeminiStreamEvent): LoopDetectionResult {
|
||||
if (this.disabledForSession || this.config.getDisableLoopDetection()) {
|
||||
if (
|
||||
this.disabledForSession ||
|
||||
this.context.config.getDisableLoopDetection()
|
||||
) {
|
||||
return { count: 0 };
|
||||
}
|
||||
if (this.loopDetected) {
|
||||
@@ -228,7 +231,7 @@ export class LoopDetectionService {
|
||||
: LoopType.CONTENT_CHANTING_LOOP;
|
||||
|
||||
logLoopDetected(
|
||||
this.config,
|
||||
this.context.config,
|
||||
new LoopDetectedEvent(
|
||||
this.lastLoopType,
|
||||
this.promptId,
|
||||
@@ -256,7 +259,10 @@ export class LoopDetectionService {
|
||||
* @returns A promise that resolves to a LoopDetectionResult.
|
||||
*/
|
||||
async turnStarted(signal: AbortSignal): Promise<LoopDetectionResult> {
|
||||
if (this.disabledForSession || this.config.getDisableLoopDetection()) {
|
||||
if (
|
||||
this.disabledForSession ||
|
||||
this.context.config.getDisableLoopDetection()
|
||||
) {
|
||||
return { count: 0 };
|
||||
}
|
||||
if (this.loopDetected) {
|
||||
@@ -283,7 +289,7 @@ export class LoopDetectionService {
|
||||
this.lastLoopType = LoopType.LLM_DETECTED_LOOP;
|
||||
|
||||
logLoopDetected(
|
||||
this.config,
|
||||
this.context.config,
|
||||
new LoopDetectedEvent(
|
||||
this.lastLoopType,
|
||||
this.promptId,
|
||||
@@ -536,8 +542,7 @@ export class LoopDetectionService {
|
||||
analysis?: string;
|
||||
confirmedByModel?: string;
|
||||
}> {
|
||||
const recentHistory = this.config
|
||||
.getGeminiClient()
|
||||
const recentHistory = this.context.geminiClient
|
||||
.getHistory()
|
||||
.slice(-LLM_LOOP_CHECK_HISTORY_COUNT);
|
||||
|
||||
@@ -590,13 +595,13 @@ export class LoopDetectionService {
|
||||
: '';
|
||||
|
||||
const doubleCheckModelName =
|
||||
this.config.modelConfigService.getResolvedConfig({
|
||||
this.context.config.modelConfigService.getResolvedConfig({
|
||||
model: DOUBLE_CHECK_MODEL_ALIAS,
|
||||
}).model;
|
||||
|
||||
if (flashConfidence < LLM_CONFIDENCE_THRESHOLD) {
|
||||
logLlmLoopCheck(
|
||||
this.config,
|
||||
this.context.config,
|
||||
new LlmLoopCheckEvent(
|
||||
this.promptId,
|
||||
flashConfidence,
|
||||
@@ -608,12 +613,13 @@ export class LoopDetectionService {
|
||||
return { isLoop: false };
|
||||
}
|
||||
|
||||
const availability = this.config.getModelAvailabilityService();
|
||||
const availability = this.context.config.getModelAvailabilityService();
|
||||
|
||||
if (!availability.snapshot(doubleCheckModelName).available) {
|
||||
const flashModelName = this.config.modelConfigService.getResolvedConfig({
|
||||
model: 'loop-detection',
|
||||
}).model;
|
||||
const flashModelName =
|
||||
this.context.config.modelConfigService.getResolvedConfig({
|
||||
model: 'loop-detection',
|
||||
}).model;
|
||||
return {
|
||||
isLoop: true,
|
||||
analysis: flashAnalysis,
|
||||
@@ -642,7 +648,7 @@ export class LoopDetectionService {
|
||||
: undefined;
|
||||
|
||||
logLlmLoopCheck(
|
||||
this.config,
|
||||
this.context.config,
|
||||
new LlmLoopCheckEvent(
|
||||
this.promptId,
|
||||
flashConfidence,
|
||||
@@ -672,7 +678,7 @@ export class LoopDetectionService {
|
||||
signal: AbortSignal,
|
||||
): Promise<Record<string, unknown> | null> {
|
||||
try {
|
||||
const result = await this.config.getBaseLlmClient().generateJson({
|
||||
const result = await this.context.config.getBaseLlmClient().generateJson({
|
||||
modelConfigKey: { model },
|
||||
contents,
|
||||
schema: LOOP_DETECTION_SCHEMA,
|
||||
@@ -692,7 +698,7 @@ export class LoopDetectionService {
|
||||
}
|
||||
return null;
|
||||
} catch (error) {
|
||||
if (this.config.getDebugMode()) {
|
||||
if (this.context.config.getDebugMode()) {
|
||||
debugLogger.warn(
|
||||
`Error querying loop detection model (${model}): ${String(error)}`,
|
||||
);
|
||||
|
||||
@@ -51,11 +51,34 @@ export interface ModelConfigAlias {
|
||||
modelConfig: ModelConfig;
|
||||
}
|
||||
|
||||
// A model definition is a mapping from a model name to a list of features
|
||||
// that the model supports. Model names can be either direct model IDs
|
||||
// (gemini-2.5-pro) or aliases (auto).
|
||||
export interface ModelDefinition {
|
||||
displayName?: string;
|
||||
tier?: string; // 'pro' | 'flash' | 'flash-lite' | 'custom' | 'auto'
|
||||
family?: string; // The gemini family, e.g. 'gemini-3' | 'gemini-2'
|
||||
isPreview?: boolean;
|
||||
// Specifies which view the model should appear in. If unset, the model will
|
||||
// not appear in the dialog.
|
||||
dialogLocation?: 'main' | 'manual';
|
||||
/** A short description of the model for the dialog. */
|
||||
dialogDescription?: string;
|
||||
features?: {
|
||||
// Whether the model supports thinking.
|
||||
thinking?: boolean;
|
||||
// Whether the model supports mutlimodal function responses. This is
|
||||
// supported in Gemini 3.
|
||||
multimodalToolUse?: boolean;
|
||||
};
|
||||
}
|
||||
|
||||
export interface ModelConfigServiceConfig {
|
||||
aliases?: Record<string, ModelConfigAlias>;
|
||||
customAliases?: Record<string, ModelConfigAlias>;
|
||||
overrides?: ModelConfigOverride[];
|
||||
customOverrides?: ModelConfigOverride[];
|
||||
modelDefinitions?: Record<string, ModelDefinition>;
|
||||
}
|
||||
|
||||
const MAX_ALIAS_CHAIN_DEPTH = 100;
|
||||
@@ -76,6 +99,28 @@ export class ModelConfigService {
|
||||
// TODO(12597): Process config to build a typed alias hierarchy.
|
||||
constructor(private readonly config: ModelConfigServiceConfig) {}
|
||||
|
||||
getModelDefinition(modelId: string): ModelDefinition | undefined {
|
||||
const definition = this.config.modelDefinitions?.[modelId];
|
||||
if (definition) {
|
||||
return definition;
|
||||
}
|
||||
|
||||
// For unknown models, return an implicit custom definition to match legacy behavior.
|
||||
if (!modelId.startsWith('gemini-')) {
|
||||
return {
|
||||
tier: 'custom',
|
||||
family: 'custom',
|
||||
features: {},
|
||||
};
|
||||
}
|
||||
|
||||
return undefined;
|
||||
}
|
||||
|
||||
getModelDefinitions(): Record<string, ModelDefinition> {
|
||||
return this.config.modelDefinitions ?? {};
|
||||
}
|
||||
|
||||
registerRuntimeModelConfig(aliasName: string, alias: ModelConfigAlias): void {
|
||||
this.runtimeAliases[aliasName] = alias;
|
||||
}
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user