Semantic search, AI summaries & security warnings

.gitignore

@@ -30,3 +30,5 @@ src/test/fixtures/workspace/.vscode/tasktree.json
 
 .playwright-mcp/
 website/_site/
+
+.commandtree/

.vscode-test.mjs

@@ -1,12 +1,18 @@
 import { defineConfig } from '@vscode/test-cli';
 import { cpSync, mkdtempSync } from 'fs';
 import { tmpdir } from 'os';
-import { join } from 'path';
+import { join, resolve } from 'path';
+import { fileURLToPath } from 'url';
+import { dirname } from 'path';
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
 
 // Copy fixtures to a temp directory so tests run in full isolation
 const testWorkspace = mkdtempSync(join(tmpdir(), 'commandtree-test-'));
 cpSync('./src/test/fixtures/workspace', testWorkspace, { recursive: true });
 
+const userDataDir = resolve(__dirname, '.vscode-test/user-data');
+
 export default defineConfig({
     files: ['out/test/e2e/**/*.test.js', 'out/test/providers/**/*.test.js'],
     version: 'stable',
@@ -19,8 +25,8 @@ export default defineConfig({
         slow: 10000
     },
     launchArgs: [
-        '--disable-extensions',
-        '--disable-gpu'
+        '--disable-gpu',
+        '--user-data-dir', userDataDir
     ],
     coverage: {
         include: ['out/**/*.js'],

.vscode/launch.json

@@ -23,7 +23,7 @@
         {
             /* Multi-line comment for test */
             "name": "Debug Python",
-            "type": "python",
+            "type": "debugpy",
             "request": "launch",
             "program": "${workspaceFolder}/main.py"
         }

.vscode/settings.json

@@ -3,14 +3,22 @@
   "mochaExplorer.ui": "tdd",
   "mochaExplorer.require": [],
   "typescript.tsserver.experimental.enableProjectDiagnostics": true,
+  "typescript.reportStyleChecksAsErrors": true,
   "eslint.lintTask.enable": true,
   "eslint.run": "onType",
-  "eslint.probe": ["typescript"],
-  "eslint.validate": ["typescript"],
+  "eslint.probe": [
+    "typescript"
+  ],
+  "eslint.validate": [
+    "typescript"
+  ],
   "eslint.useFlatConfig": true,
-  "eslint.workingDirectories": ["."],
+  "eslint.workingDirectories": [
+    "."
+  ],
   "eslint.debug": true,
   "editor.codeActionsOnSave": {
-    "source.fixAll.eslint": "explicit"
+    "source.fixAll.eslint": "explicit",
+    "commandtree.enableAiSummaries": "explicit"
   }
-}
+}

.vscodeignore

@@ -5,6 +5,7 @@ src/**
 test-fixtures/**
 out/test/**
 node_modules/**
+!node_modules/node-sqlite3-wasm/**
 scripts/**
 .too_many_cooks/**
 .claude/**

Agents.md

@@ -0,0 +1,183 @@
+# CLAUDE.md - CommandTree Extension
+
+## Too Many Cooks
+
+You are working with many other agents. Make sure there is effective cooperation
+- Register on TMC immediately
+- Don't edit files that are locked; lock files when editing
+- COMMUNICATE REGULARLY AND COORDINATE WITH OTHERS THROUGH MESSAGES
+
+## Coding Rules
+
+- **Zero duplication - TOP PRIORITY** - Always search for existing code before adding. Move; don't copy files. Add assertions to tests rather than duplicating tests. AIM FOR LESS CODE!
+- **No string literals** - Named constants only, and it ONE location
+- **Functional style** - Prefer pure functions, avoid classes where possible
+- **No suppressing warnings** - Fix them properly
+- **No REGEX** It is absolutely ⛔️ illegal
+- **Don't run long runnings tasks** like docker builds, tests. Ask the user to do it!!
+- **Expressions over assignments** - Prefer const and immutable patterns
+- **Named parameters** - Use object params for functions with 3+ args
+- **Keep files under 450 LOC and functions under 20 LOC**
+- **No commented-out code** - Delete it
+- **No placeholders** - If incomplete, leave LOUD compilation error with TODO
+
+### Typescript
+- **TypeScript strict mode** - No `any`, no implicit types, turn all lints up to error
+- **Ignoring lints = ⛔️ illegal** - Fix violations immediately
+- **No throwing** - Only return `Result<T,E>`
+
+### CSS
+- **Minimize duplication** - fewer classes is better
+- **Don't include section in class name** - name them after what they are - not the section they sit in
+
+## Testing
+
+⚠️ NEVER KILL VSCODE PROCESSES
+
+#### Rules
+- **Prefer e2e tests over unit tests** - only unit tests for isolating bugs
+- DO NOT USE GIT
+- Separate e2e tests from unit tests by file. They should not be in the same file together.
+- Prefer adding assertions to existing tests rather than adding new tests
+- Test files in `src/test/suite/*.test.ts`
+- Run tests: `npm test`
+- NEVER remove assertions
+- FAILING TEST = ✅ OK. TEST THAT DOESN'T ENFORCE BEHAVIOR = ⛔️ ILLEGAL
+- Unit test = No VSCODE instance needed = isolation only test
+
+### Automated (E2E) Testing
+
+**AUTOMATED TESTING IS BLACK BOX TESTING ONLY**
+Only test the UI **THROUGH the UI**. Do not run command etc. to coerce the state. You are testing the UI, not the code.
+
+- Tests run in actual VS Code window via `@vscode/test-electron`
+- Automated tests must not modify internal state or call functions that do. They must only use the extension through the UI. 
+ * - ❌ Calling internal methods like provider.updateTasks()
+ * - ❌ Calling provider.refresh() directly
+ * - ❌ Manipulating internal state directly
+ * - ❌ Using any method not exposed via VS Code commands
+ * - ❌ Using commands that should just happen as part of normal use. e.g.: `await vscode.commands.executeCommand('commandtree.refresh');`
+ * - ❌ `executeCommand('commandtree.addToQuick', item)` - TAP the item via the DOM!!!
+
+### Test First Process
+- Write test that fails because of bug/missing feature
+- Run tests to verify that test fails because of this reason
+- Adjust test and repeat until you see failure for the reason above
+- Add missing feature or fix bug
+- Run tests to verify test passes.
+- Repeat and fix until test passes WITHOUT changing the test
+
+**Every test MUST:**
+1. Assert on the ACTUAL OBSERVABLE BEHAVIOR (UI state, view contents, return values)
+2. Fail if the feature is broken
+3. Test the full flow, not just side effects like config files
+
+### ⛔️ FAKE TESTS ARE ILLEGAL
+
+**A "fake test" is any test that passes without actually verifying behavior. These are STRICTLY FORBIDDEN:**
+
+```typescript
+// ❌ ILLEGAL - asserts true unconditionally
+assert.ok(true, 'Should work');
+
+// ❌ ILLEGAL - no assertion on actual behavior
+try { await doSomething(); } catch { }
+assert.ok(true, 'Did not crash');
+
+// ❌ ILLEGAL - only checks config file, not actual UI/view behavior
+writeConfig({ quick: ['task1'] });
+const config = readConfig();
+assert.ok(config.quick.includes('task1')); // This doesn't test the FEATURE
+
+// ❌ ILLEGAL - empty catch with success assertion
+try { await command(); } catch { /* swallow */ }
+assert.ok(true, 'Command ran');
+```
+
+## Critical Docs
+
+[VSCode Extension API](https://code.visualstudio.com/api/)
+[SCode Extension Testing API](https://code.visualstudio.com/api/extension-guides/testing)
+
+## Project Structure
+
+```
+CommandTree/
+├── src/
+│   ├── extension.ts          # Entry point, command registration
+│   ├── CommandTreeProvider.ts   # TreeDataProvider implementation
+│   ├── config/
+│   │   └── TagConfig.ts      # Tag configuration from commandtree.json
+│   ├── discovery/
+│   │   ├── index.ts          # Discovery orchestration
+│   │   ├── shell.ts          # Shell script discovery
+│   │   ├── npm.ts            # NPM script discovery
+│   │   ├── make.ts           # Makefile target discovery
+│   │   ├── launch.ts         # launch.json discovery
+│   │   └── tasks.ts          # tasks.json discovery
+│   ├── models/
+│   │   └── TaskItem.ts       # Task data model and TreeItem
+│   ├── runners/
+│   │   └── TaskRunner.ts     # Task execution logic
+│   └── test/
+│       └── suite/            # E2E test files
+├── test-fixtures/            # Test workspace files
+├── package.json              # Extension manifest
+├── tsconfig.json             # TypeScript config
+└── .vscode-test.mjs          # Test runner config
+```
+
+## Commands
+
+| Command ID | Description |
+|------------|-------------|
+| `commandtree.refresh` | Reload all tasks |
+| `commandtree.run` | Run task in new terminal |
+| `commandtree.runInCurrentTerminal` | Run in active terminal |
+| `commandtree.debug` | Launch with debugger |
+| `commandtree.filter` | Text filter input |
+| `commandtree.filterByTag` | Tag filter picker |
+| `commandtree.clearFilter` | Clear all filters |
+| `commandtree.editTags` | Open commandtree.json |
+
+## Build Commands
+
+See [text](package.json)
+
+## Adding New Task Types
+
+1. Create discovery module in `src/discovery/`
+2. Export discovery function: `discoverXxxTasks(root: string, excludes: string[]): Promise<TaskItem[]>`
+3. Add to `discoverAllTasks()` in `src/discovery/index.ts`
+4. Add category in `CommandTreeProvider.buildRootCategories()`
+5. Handle execution in `TaskRunner.run()`
+6. Add E2E tests in `src/test/suite/discovery.test.ts`
+
+## VS Code API Patterns
+
+```typescript
+// Register command
+context.subscriptions.push(
+    vscode.commands.registerCommand('commandtree.xxx', handler)
+);
+
+// File watcher
+const watcher = vscode.workspace.createFileSystemWatcher('**/pattern');
+watcher.onDidChange(() => refresh());
+context.subscriptions.push(watcher);
+
+// Tree view
+const treeView = vscode.window.createTreeView('commandtree', {
+    treeDataProvider: provider,
+    showCollapseAll: true
+});
+
+// Context for when clauses
+vscode.commands.executeCommand('setContext', 'commandtree.hasFilter', true);
+```
+
+## Configuration
+
+Settings defined in `package.json` under `contributes.configuration`:
+- `commandtree.excludePatterns` - Glob patterns to exclude
+- `commandtree.sortOrder` - Task sort order (folder/name/type)

CHANGELOG.md

@@ -1,7 +1,27 @@
 # Changelog
 
+## 0.5.0
+
+### Added
+
+- **GitHub Copilot AI Summaries** — discovered commands are automatically summarised in plain language by GitHub Copilot, displayed in tooltips on hover
+- Security warnings: commands that perform dangerous operations (e.g. `rm -rf`, force-push) are flagged with a warning in the tree view
+- `commandtree.enableAiSummaries` setting to toggle AI summaries (enabled by default)
+- `commandtree.generateSummaries` command to manually trigger summary generation
+- Content-hash change detection — summaries only regenerate when scripts change
+
+### Fixed
+
+- Terminal execution no longer throws when xterm viewport is uninitialised in headless environments
+
 ## 0.4.0
 
+### Added
+
+- SQLite storage for summaries and embeddings via `node-sqlite3-wasm`
+- Automatic migration from legacy JSON store to SQLite on activation
+- File watcher re-summarises scripts when they change, with user notification
+
 ### Fixed
 
 - Corrected homepage link to commandtree.dev in package.json and README

Claude.md

@@ -10,9 +10,11 @@ You are working with many other agents. Make sure there is effective cooperation
 ## Coding Rules
 
 - **Zero duplication - TOP PRIORITY** - Always search for existing code before adding. Move; don't copy files. Add assertions to tests rather than duplicating tests. AIM FOR LESS CODE!
+- **No string literals** - Named constants only, and it ONE location
+- DO NOT USE GIT
 - **Functional style** - Prefer pure functions, avoid classes where possible
 - **No suppressing warnings** - Fix them properly
-- **No REGEX** It is absolutely ⛔️ illegal
+- **No REGEX** It is absolutely ⛔️ illegal, and no text matching in general
 - **Don't run long runnings tasks** like docker builds, tests. Ask the user to do it!!
 - **Expressions over assignments** - Prefer const and immutable patterns
 - **Named parameters** - Use object params for functions with 3+ args
@@ -22,6 +24,8 @@ You are working with many other agents. Make sure there is effective cooperation
 
 ### Typescript
 - **TypeScript strict mode** - No `any`, no implicit types, turn all lints up to error
+- **Regularly run the linter** - Fix lint errors IMMEDIATELY
+- **Decouple providers from the VSCODE SDK** - No vscode sdk use within the providers
 - **Ignoring lints = ⛔️ illegal** - Fix violations immediately
 - **No throwing** - Only return `Result<T,E>`
 
@@ -35,7 +39,6 @@ You are working with many other agents. Make sure there is effective cooperation
 
 #### Rules
 - **Prefer e2e tests over unit tests** - only unit tests for isolating bugs
-- DO NOT USE GIT
 - Separate e2e tests from unit tests by file. They should not be in the same file together.
 - Prefer adding assertions to existing tests rather than adding new tests
 - Test files in `src/test/suite/*.test.ts`
@@ -95,8 +98,21 @@ assert.ok(true, 'Command ran');
 
 ## Critical Docs
 
+### Vscode SDK
 [VSCode Extension API](https://code.visualstudio.com/api/)
-[SCode Extension Testing API](https://code.visualstudio.com/api/extension-guides/testing)
+[VSCode Extension Testing API](https://code.visualstudio.com/api/extension-guides/testing)
+[VSCODE Language Model API](https://code.visualstudio.com/api/extension-guides/ai/language-model)
+[Language Model Tool API](https://code.visualstudio.com/api/extension-guides/ai/tools)
+[AI extensibility in VS Cod](https://code.visualstudio.com/api/extension-guides/ai/ai-extensibility-overview)
+[AI language models in VS Code](https://code.visualstudio.com/docs/copilot/customization/language-models)
+
+### Website
+
+https://developers.google.com/search/blog/2025/05/succeeding-in-ai-search
+https://developers.google.com/search/docs/fundamentals/seo-starter-guide
+
+https://studiohawk.com.au/blog/how-to-optimise-ai-overviews/
+https://about.ads.microsoft.com/en/blog/post/october-2025/optimizing-your-content-for-inclusion-in-ai-search-answers
 
 ## Project Structure
 
@@ -109,11 +125,25 @@ CommandTree/
 │   │   └── TagConfig.ts      # Tag configuration from commandtree.json
 │   ├── discovery/
 │   │   ├── index.ts          # Discovery orchestration
-│   │   ├── shell.ts          # Shell script discovery
-│   │   ├── npm.ts            # NPM script discovery
-│   │   ├── make.ts           # Makefile target discovery
-│   │   ├── launch.ts         # launch.json discovery
-│   │   └── tasks.ts          # tasks.json discovery
+│   │   ├── shell.ts          # Shell scripts (.sh, .bash, .zsh)
+│   │   ├── npm.ts            # NPM scripts (package.json)
+│   │   ├── make.ts           # Makefile targets
+│   │   ├── launch.ts         # VS Code launch configs
+│   │   ├── tasks.ts          # VS Code tasks
+│   │   ├── python.ts         # Python scripts (.py)
+│   │   ├── powershell.ts     # PowerShell scripts (.ps1)
+│   │   ├── gradle.ts         # Gradle tasks
+│   │   ├── cargo.ts          # Cargo (Rust) tasks
+│   │   ├── maven.ts          # Maven goals (pom.xml)
+│   │   ├── ant.ts            # Ant targets (build.xml)
+│   │   ├── just.ts           # Just recipes (justfile)
+│   │   ├── taskfile.ts       # Taskfile tasks (Taskfile.yml)
+│   │   ├── deno.ts           # Deno tasks (deno.json)
+│   │   ├── rake.ts           # Rake tasks (Rakefile)
+│   │   ├── composer.ts       # Composer scripts (composer.json)
+│   │   ├── docker.ts         # Docker Compose services
+│   │   ├── dotnet.ts         # .NET projects (.csproj)
+│   │   └── markdown.ts       # Markdown files (.md)
 │   ├── models/
 │   │   └── TaskItem.ts       # Task data model and TreeItem
 │   ├── runners/
@@ -179,5 +209,4 @@ vscode.commands.executeCommand('setContext', 'commandtree.hasFilter', true);
 
 Settings defined in `package.json` under `contributes.configuration`:
 - `commandtree.excludePatterns` - Glob patterns to exclude
-- `commandtree.showEmptyCategories` - Show empty category nodes
 - `commandtree.sortOrder` - Task sort order (folder/name/type)