Files
automaker/apps/server/tests/unit/providers/copilot-provider.test.ts
Stefan de Vogelaere 0b92349890 feat: Add GitHub Copilot SDK provider integration (#661)
* feat: add GitHub Copilot SDK provider integration

Adds comprehensive GitHub Copilot SDK provider support including:
- CopilotProvider class with CLI detection and OAuth authentication check
- Copilot models definition with GPT-4o, Claude, and o1/o3 series models
- Settings UI integration with provider tab, model configuration, and navigation
- Onboarding flow integration with Copilot setup step
- Model selector integration for all phase-specific model dropdowns
- Persistence of enabled models and default model settings via API sync
- Server route for Copilot CLI status endpoint

https://claude.ai/code/session_01D26w7ZyEzP4H6Dor3ttk9d

* chore: update package-lock.json

https://claude.ai/code/session_01D26w7ZyEzP4H6Dor3ttk9d

* refactor: rename Copilot SDK to Copilot CLI and use GitHub icon

- Update all references from "GitHub Copilot SDK" to "GitHub Copilot CLI"
- Change install command from @github/copilot-sdk to @github/copilot
- Update CopilotIcon to use official GitHub Octocat logo
- Update error codes and comments throughout codebase

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: update Copilot model definitions and add dynamic model discovery

- Update COPILOT_MODEL_MAP with correct models from CLI (claude-sonnet-4.5,
  claude-haiku-4.5, claude-opus-4.5, claude-sonnet-4, gpt-5.x series, gpt-4.1,
  gemini-3-pro-preview)
- Change default Copilot model to copilot-claude-sonnet-4.5
- Add model caching methods to CopilotProvider (hasCachedModels,
  clearModelCache, refreshModels)
- Add API routes for dynamic model discovery:
  - GET /api/setup/copilot/models
  - POST /api/setup/copilot/models/refresh
  - POST /api/setup/copilot/cache/clear

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor: use @github/copilot-sdk instead of direct CLI calls

- Install @github/copilot-sdk package for proper SDK integration
- Rewrite CopilotProvider to use SDK's CopilotClient API
- Use client.createSession() for session management
- Handle SDK events (assistant.message, tool.execution_*, session.idle)
- Auto-approve permissions for autonomous agent operation
- Remove incorrect CLI flags (--mode, --output-format)
- Update default model to claude-sonnet-4.5

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: add Copilot and Gemini model support to model resolver

- Import isCopilotModel and isGeminiModel from types
- Add explicit checks for copilot- and gemini- prefixed models
- Pass through Copilot/Gemini models unchanged to their providers
- Update resolver documentation to list all supported providers

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: pass working directory to Copilot SDK and reduce event noise

- Create CopilotClient per execution with correct cwd from options.cwd
- This ensures the CLI operates in the correct project directory, not the
  server's current directory
- Skip assistant.message_delta events (they create excessive noise)
- Only yield the final assistant.message event which has complete content
- Clean up client on completion and error paths

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: simplify Copilot SDK execution with sendAndWait

- Use sendAndWait() instead of manual event polling for more reliable
  execution
- Disable streaming (streaming: false) to simplify response handling
- Increase timeout to 10 minutes for agentic operations
- Still capture tool execution events for UI display
- Add more debug logging for troubleshooting
- This should fix the "invalid_request_body" error on subsequent calls

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: allow Copilot model IDs with claude-, gemini-, gpt- prefixes

Copilot's bare model IDs legitimately contain prefixes like claude-,
gemini-, gpt- because those are the actual model names from the
Copilot CLI (e.g., claude-sonnet-4.5, gemini-3-pro-preview, gpt-5.1).

The generic validateBareModelId function was incorrectly rejecting
these valid model IDs. Now we only check that the copilot- prefix
has been stripped by the ProviderFactory.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat: enable real-time streaming of tool events for Copilot

- Switch back to streaming mode (streaming: true) for real-time events
- Use async queue pattern to bridge SDK callbacks to async generator
- Events are now yielded as they happen, not batched at the end
- Tool calls (Read, Write, Edit, Bash, TodoWrite, etc.) show in real-time
- Better progress visibility during agentic operations

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat: expand Copilot tool name and input normalization

Tool name mapping additions:
- view → Read (Copilot's file viewing tool)
- create_file → Write
- replace, patch → Edit
- run_shell_command, terminal → Bash
- search_file_content → Grep
- list_directory → Ls
- google_web_search → WebSearch
- report_intent → ReportIntent (Copilot-specific planning)
- think, plan → Think, Plan

Input normalization improvements:
- Read/Write/Edit: Map file, filename, filePath → file_path
- Bash: Map cmd, script → command
- Grep: Map query, search, regex → pattern

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: convert git+ssh to git+https in package-lock.json

The @electron/node-gyp dependency was resolved with a git+ssh URL
which fails in CI environments without SSH keys. Convert to HTTPS.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: address code review feedback for Copilot SDK provider

- Add guard for non-text prompts (vision not yet supported)
- Clear runtime model cache on fetch failure
- Fix race condition in async queue error handling
- Import CopilotAuthStatus from shared types
- Fix comment mismatch for default model constant
- Add auth-copilot and deauth-copilot routes
- Extract shared tool normalization utilities
- Create base model configuration UI component
- Add comprehensive unit tests for CopilotProvider
- Replace magic strings with constants
- Add debug logging for cleanup errors

* fix: address CodeRabbit review nitpicks

- Fix test mocks to include --version check for CLI detection
- Add aria-label for accessibility on refresh button
- Ensure default model checkbox always appears checked/enabled

* fix: address CodeRabbit review feedback

- Fix test mocks by creating fresh provider instances after mock setup
- Extract COPILOT_DISCONNECTED_MARKER_FILE constant to common.ts
- Add AUTONOMOUS MODE comment explaining auto-approval of permissions
- Improve tool-normalization with union types and null guards
- Handle 'canceled' (American spelling) status in todo normalization

* refactor: extract copilot connection logic to service and fix test mocks

- Create copilot-connection-service.ts with connect/disconnect logic
- Update auth-copilot and deauth-copilot routes to use service
- Fix test mocks for CLI detection:
  - Mock fs.existsSync for CLI path validation
  - Mock which/where command for CLI path detection

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-01-23 14:48:33 +01:00

518 lines
16 KiB
TypeScript

import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
import { CopilotProvider, CopilotErrorCode } from '@/providers/copilot-provider.js';
// Mock the Copilot SDK
vi.mock('@github/copilot-sdk', () => ({
CopilotClient: vi.fn().mockImplementation(() => ({
start: vi.fn().mockResolvedValue(undefined),
stop: vi.fn().mockResolvedValue(undefined),
createSession: vi.fn().mockResolvedValue({
sessionId: 'test-session',
send: vi.fn().mockResolvedValue(undefined),
destroy: vi.fn().mockResolvedValue(undefined),
on: vi.fn(),
}),
})),
}));
// Mock child_process with all needed exports
vi.mock('child_process', async (importOriginal) => {
const actual = await importOriginal<typeof import('child_process')>();
return {
...actual,
execSync: vi.fn(),
};
});
// Mock fs (synchronous) for CLI detection (existsSync)
vi.mock('fs', async (importOriginal) => {
const actual = await importOriginal<typeof import('fs')>();
return {
...actual,
existsSync: vi.fn().mockReturnValue(true),
};
});
// Mock fs/promises
vi.mock('fs/promises', () => ({
access: vi.fn().mockRejectedValue(new Error('Not found')),
readFile: vi.fn().mockRejectedValue(new Error('Not found')),
mkdir: vi.fn().mockResolvedValue(undefined),
}));
// Import execSync after mocking
import { execSync } from 'child_process';
import * as fs from 'fs';
describe('copilot-provider.ts', () => {
let provider: CopilotProvider;
beforeEach(() => {
vi.clearAllMocks();
// Mock fs.existsSync for CLI path validation
vi.mocked(fs.existsSync).mockReturnValue(true);
// Mock CLI detection to find the CLI
// The CliProvider base class uses 'which copilot' (Unix) or 'where copilot' (Windows)
// to find the CLI path, then validates with fs.existsSync
vi.mocked(execSync).mockImplementation((cmd: string) => {
// CLI path detection (which/where command)
if (cmd.startsWith('which ') || cmd.startsWith('where ')) {
return '/usr/local/bin/copilot';
}
if (cmd.includes('--version')) {
return '1.0.0';
}
if (cmd.includes('gh auth status')) {
return 'Logged in to github.com account testuser';
}
if (cmd.includes('models list')) {
return JSON.stringify([{ id: 'claude-sonnet-4.5', name: 'Claude Sonnet 4.5' }]);
}
return '';
});
provider = new CopilotProvider();
delete process.env.GITHUB_TOKEN;
});
afterEach(() => {
vi.restoreAllMocks();
});
describe('getName', () => {
it("should return 'copilot' as provider name", () => {
expect(provider.getName()).toBe('copilot');
});
});
describe('getCliName', () => {
it("should return 'copilot' as CLI name", () => {
expect(provider.getCliName()).toBe('copilot');
});
});
describe('supportsFeature', () => {
it('should support tools feature', () => {
expect(provider.supportsFeature('tools')).toBe(true);
});
it('should support text feature', () => {
expect(provider.supportsFeature('text')).toBe(true);
});
it('should support streaming feature', () => {
expect(provider.supportsFeature('streaming')).toBe(true);
});
it('should NOT support vision feature (not implemented yet)', () => {
expect(provider.supportsFeature('vision')).toBe(false);
});
it('should not support unknown feature', () => {
expect(provider.supportsFeature('unknown')).toBe(false);
});
});
describe('getAvailableModels', () => {
it('should return static model definitions', () => {
const models = provider.getAvailableModels();
expect(Array.isArray(models)).toBe(true);
expect(models.length).toBeGreaterThan(0);
// All models should have required fields
models.forEach((model) => {
expect(model.id).toBeDefined();
expect(model.name).toBeDefined();
expect(model.provider).toBe('copilot');
});
});
it('should include copilot- prefix in model IDs', () => {
const models = provider.getAvailableModels();
models.forEach((model) => {
expect(model.id).toMatch(/^copilot-/);
});
});
});
describe('checkAuth', () => {
it('should return authenticated status when gh CLI is logged in', async () => {
// Set up mocks BEFORE creating provider to ensure CLI detection succeeds
vi.mocked(fs.existsSync).mockReturnValue(true);
vi.mocked(execSync).mockImplementation((cmd: string) => {
// CLI path detection (which/where command)
if (cmd.startsWith('which ') || cmd.startsWith('where ')) {
return '/usr/local/bin/copilot';
}
if (cmd.includes('--version')) {
return '1.0.0';
}
if (cmd.includes('gh auth status')) {
return 'Logged in to github.com account testuser';
}
return '';
});
// Create fresh provider with the mock in place
const freshProvider = new CopilotProvider();
const status = await freshProvider.checkAuth();
expect(status.authenticated).toBe(true);
expect(status.method).toBe('oauth');
expect(status.login).toBe('testuser');
});
it('should return unauthenticated when gh auth fails', async () => {
// Set up mocks BEFORE creating provider
vi.mocked(fs.existsSync).mockReturnValue(true);
vi.mocked(execSync).mockImplementation((cmd: string) => {
// CLI path detection (which/where command)
if (cmd.startsWith('which ') || cmd.startsWith('where ')) {
return '/usr/local/bin/copilot';
}
if (cmd.includes('--version')) {
return '1.0.0';
}
if (cmd.includes('gh auth status')) {
throw new Error('Not logged in');
}
if (cmd.includes('copilot auth status')) {
throw new Error('Not logged in');
}
return '';
});
// Create fresh provider with the mock in place
const freshProvider = new CopilotProvider();
const status = await freshProvider.checkAuth();
expect(status.authenticated).toBe(false);
expect(status.method).toBe('none');
});
it('should detect GITHUB_TOKEN environment variable', async () => {
process.env.GITHUB_TOKEN = 'test-token';
// Set up mocks BEFORE creating provider
vi.mocked(fs.existsSync).mockReturnValue(true);
vi.mocked(execSync).mockImplementation((cmd: string) => {
// CLI path detection (which/where command)
if (cmd.startsWith('which ') || cmd.startsWith('where ')) {
return '/usr/local/bin/copilot';
}
if (cmd.includes('--version')) {
return '1.0.0';
}
if (cmd.includes('gh auth status')) {
throw new Error('Not logged in');
}
if (cmd.includes('copilot auth status')) {
throw new Error('Not logged in');
}
return '';
});
// Create fresh provider with the mock in place
const freshProvider = new CopilotProvider();
const status = await freshProvider.checkAuth();
expect(status.authenticated).toBe(true);
expect(status.method).toBe('oauth');
delete process.env.GITHUB_TOKEN;
});
});
describe('detectInstallation', () => {
it('should detect installed CLI', async () => {
// Set up mocks BEFORE creating provider
vi.mocked(fs.existsSync).mockReturnValue(true);
vi.mocked(execSync).mockImplementation((cmd: string) => {
// CLI path detection (which/where command)
if (cmd.startsWith('which ') || cmd.startsWith('where ')) {
return '/usr/local/bin/copilot';
}
if (cmd.includes('--version')) {
return '1.2.3';
}
if (cmd.includes('gh auth status')) {
return 'Logged in to github.com account testuser';
}
return '';
});
// Create fresh provider with the mock in place
const freshProvider = new CopilotProvider();
const status = await freshProvider.detectInstallation();
expect(status.installed).toBe(true);
expect(status.version).toBe('1.2.3');
expect(status.authenticated).toBe(true);
});
});
describe('normalizeEvent', () => {
it('should normalize assistant.message event', () => {
const event = {
type: 'assistant.message',
data: { content: 'Hello, world!' },
};
const result = provider.normalizeEvent(event);
expect(result).toEqual({
type: 'assistant',
message: {
role: 'assistant',
content: [{ type: 'text', text: 'Hello, world!' }],
},
});
});
it('should skip assistant.message_delta event', () => {
const event = {
type: 'assistant.message_delta',
data: { delta: 'partial' },
};
const result = provider.normalizeEvent(event);
expect(result).toBeNull();
});
it('should normalize tool.execution_start event', () => {
const event = {
type: 'tool.execution_start',
data: {
toolName: 'read_file',
toolCallId: 'call-123',
input: { path: '/test/file.txt' },
},
};
const result = provider.normalizeEvent(event);
expect(result).toEqual({
type: 'assistant',
message: {
role: 'assistant',
content: [
{
type: 'tool_use',
name: 'Read', // Normalized from read_file
tool_use_id: 'call-123',
input: { path: '/test/file.txt', file_path: '/test/file.txt' }, // Path normalized
},
],
},
});
});
it('should normalize tool.execution_end event', () => {
const event = {
type: 'tool.execution_end',
data: {
toolName: 'read_file',
toolCallId: 'call-123',
result: 'file content',
},
};
const result = provider.normalizeEvent(event);
expect(result).toEqual({
type: 'assistant',
message: {
role: 'assistant',
content: [
{
type: 'tool_result',
tool_use_id: 'call-123',
content: 'file content',
},
],
},
});
});
it('should handle tool.execution_end with error', () => {
const event = {
type: 'tool.execution_end',
data: {
toolName: 'bash',
toolCallId: 'call-456',
error: 'Command failed',
},
};
const result = provider.normalizeEvent(event);
expect(result?.message?.content?.[0]).toMatchObject({
type: 'tool_result',
content: '[ERROR] Command failed',
});
});
it('should normalize session.idle to success result', () => {
const event = { type: 'session.idle' };
const result = provider.normalizeEvent(event);
expect(result).toEqual({
type: 'result',
subtype: 'success',
});
});
it('should normalize session.error to error event', () => {
const event = {
type: 'session.error',
data: { message: 'Something went wrong' },
};
const result = provider.normalizeEvent(event);
expect(result).toEqual({
type: 'error',
error: 'Something went wrong',
});
});
it('should return null for unknown event types', () => {
const event = { type: 'unknown.event' };
const result = provider.normalizeEvent(event);
expect(result).toBeNull();
});
});
describe('mapError', () => {
it('should map authentication errors', () => {
const errorInfo = (provider as any).mapError('not authenticated', null);
expect(errorInfo.code).toBe(CopilotErrorCode.NOT_AUTHENTICATED);
expect(errorInfo.recoverable).toBe(true);
});
it('should map rate limit errors', () => {
const errorInfo = (provider as any).mapError('rate limit exceeded', null);
expect(errorInfo.code).toBe(CopilotErrorCode.RATE_LIMITED);
expect(errorInfo.recoverable).toBe(true);
});
it('should map model unavailable errors', () => {
const errorInfo = (provider as any).mapError('model not available', null);
expect(errorInfo.code).toBe(CopilotErrorCode.MODEL_UNAVAILABLE);
expect(errorInfo.recoverable).toBe(true);
});
it('should map network errors', () => {
const errorInfo = (provider as any).mapError('connection refused', null);
expect(errorInfo.code).toBe(CopilotErrorCode.NETWORK_ERROR);
expect(errorInfo.recoverable).toBe(true);
});
it('should map process crash (exit code 137)', () => {
const errorInfo = (provider as any).mapError('', 137);
expect(errorInfo.code).toBe(CopilotErrorCode.PROCESS_CRASHED);
expect(errorInfo.recoverable).toBe(true);
});
it('should return unknown error for unrecognized errors', () => {
const errorInfo = (provider as any).mapError('some random error', 1);
expect(errorInfo.code).toBe(CopilotErrorCode.UNKNOWN);
expect(errorInfo.recoverable).toBe(false);
});
});
describe('model cache', () => {
it('should indicate when cache is empty', () => {
expect(provider.hasCachedModels()).toBe(false);
});
it('should clear model cache', () => {
provider.clearModelCache();
expect(provider.hasCachedModels()).toBe(false);
});
});
describe('tool name normalization', () => {
it('should normalize read_file to Read', () => {
const event = {
type: 'tool.execution_start',
data: { toolName: 'read_file', toolCallId: 'id', input: {} },
};
const result = provider.normalizeEvent(event);
expect(result?.message?.content?.[0]).toMatchObject({ name: 'Read' });
});
it('should normalize write_file to Write', () => {
const event = {
type: 'tool.execution_start',
data: { toolName: 'write_file', toolCallId: 'id', input: {} },
};
const result = provider.normalizeEvent(event);
expect(result?.message?.content?.[0]).toMatchObject({ name: 'Write' });
});
it('should normalize run_shell to Bash', () => {
const event = {
type: 'tool.execution_start',
data: { toolName: 'run_shell', toolCallId: 'id', input: {} },
};
const result = provider.normalizeEvent(event);
expect(result?.message?.content?.[0]).toMatchObject({ name: 'Bash' });
});
it('should normalize search to Grep', () => {
const event = {
type: 'tool.execution_start',
data: { toolName: 'search', toolCallId: 'id', input: {} },
};
const result = provider.normalizeEvent(event);
expect(result?.message?.content?.[0]).toMatchObject({ name: 'Grep' });
});
it('should normalize todo_write to TodoWrite', () => {
const event = {
type: 'tool.execution_start',
data: {
toolName: 'todo_write',
toolCallId: 'id',
input: {
todos: [{ description: 'Test task', status: 'pending' }],
},
},
};
const result = provider.normalizeEvent(event);
expect(result?.message?.content?.[0]).toMatchObject({ name: 'TodoWrite' });
});
it('should normalize todo content from description', () => {
const event = {
type: 'tool.execution_start',
data: {
toolName: 'todo_write',
toolCallId: 'id',
input: {
todos: [{ description: 'Test task', status: 'pending' }],
},
},
};
const result = provider.normalizeEvent(event);
const todoInput = (result?.message?.content?.[0] as any)?.input;
expect(todoInput.todos[0]).toMatchObject({
content: 'Test task',
status: 'pending',
activeForm: 'Test task',
});
});
it('should map cancelled status to completed', () => {
const event = {
type: 'tool.execution_start',
data: {
toolName: 'todo_write',
toolCallId: 'id',
input: {
todos: [{ description: 'Cancelled task', status: 'cancelled' }],
},
},
};
const result = provider.normalizeEvent(event);
const todoInput = (result?.message?.content?.[0] as any)?.input;
expect(todoInput.todos[0].status).toBe('completed');
});
});
});