97afba2f7e
- Add ChatStore mock to all dashboard route tests that mock @fusion/core, since server.ts now instantiates ChatStore(store.getFusionDir(), ...) - Add getFusionDir to createMockStore in server.test.ts - Gate AI session cleanup scheduling behind shouldScheduleAiSessionCleanup() (returns false in test env) to prevent open handle warnings - Fix desktop tests: DASHBOARD_URL is now exported as a function alias, update assertions to call DASHBOARD_URL() instead of using as string - Add node:os mocks to system-metrics.test.ts for deterministic results - Replace hardcoded maxWorkers=16 with availableParallelism()-based calculation in all vitest configs to prevent OOM on 2-core CI runners - Add --workspace-concurrency=2 to pnpm test commands - Fix TaskCard tests: update mission badge title assertions to full titles - Remove unused /api/mesh/state route - Fix plugin-auto-label: add isError field, async onTaskCreated, "tests" keyword - Fix plugin-ci-status: add module-level logger, tighten test assertions Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Auto-Label Plugin
Automatically labels tasks based on their description content using keyword matching. Also provides an AI agent tool for manual text classification.
Features
- Automatic Classification: Labels tasks as they're created based on keywords in the description
- Multiple Categories: Supports bug, feature, documentation, testing, refactor, and performance labels
- AI Agent Tool: Provides
auto_label_classifytool for AI agents to classify text - Event Emission: Emits
auto-label:classifiedevents for integration with other plugins
Installation
Option 1: Copy to plugins directory
cp -r fusion-plugin-auto-label ~/.fusion/plugins/
Option 2: Install via CLI
fn plugin install /path/to/fusion-plugin-auto-label
Categories
The plugin classifies text into the following categories:
| Category | Keywords |
|---|---|
bug |
bug, fix, broken, crash, error |
feature |
feature, add, new, implement |
documentation |
docs, documentation, readme, guide |
testing |
test, testing, spec, coverage |
refactor |
refactor, cleanup, clean up, reorganize |
performance |
perf, performance, optimize, slow |
How It Works
Automatic Classification (onTaskCreated hook)
When a task is created, the plugin:
- Scans the task description for keywords
- Matches against category rules
- Logs the matched labels
- Emits an
auto-label:classifiedevent with the task ID and labels
AI Agent Tool
The plugin provides an auto_label_classify tool that AI agents can use:
{
name: "auto_label_classify",
description: "Classify a text description into categories...",
parameters: {
type: "object",
properties: {
text: { type: "string", description: "The text to classify" }
},
required: ["text"]
}
}
Example usage:
Use auto_label_classify with text: "Fix the login bug"
Configuration
This plugin has no required settings. It works out of the box with its built-in keyword rules.
Events
The plugin emits the following events:
| Event | Data | Description |
|---|---|---|
auto-label:classified |
{ taskId, labels } |
Emitted when a task is classified |
Development
# Install dependencies
pnpm install
# Run tests
pnpm test
# Build
pnpm build
License
MIT