From bad9b0e1635bc8993db4bd2b1eb84c5492656fdb Mon Sep 17 00:00:00 2001 From: Chris Estreich Date: Thu, 12 Jun 2025 08:05:53 -0700 Subject: [PATCH 01/33] Bump @roo-code/types to v1.26.0 (#4584) * Bump @roo-code/types to v1.26.0 * Add instructions for NPM publish --- packages/types/README.md | 23 +++++++++++++++++++++++ packages/types/npm/package.json | 2 +- webview-ui/package.json | 2 +- 3 files changed, 25 insertions(+), 2 deletions(-) create mode 100644 packages/types/README.md diff --git a/packages/types/README.md b/packages/types/README.md new file mode 100644 index 0000000000..635c380139 --- /dev/null +++ b/packages/types/README.md @@ -0,0 +1,23 @@ +# @roo-code/types + +### Publish to NPM + +First authenticate with NPM: + +```sh +npm login +``` + +Next, manually bump the NPM package version: + +```sh +cd packages/types/npm && npm version minor && cd - +``` + +Finally, publish to NPM: + +```sh +pnpm --filter @roo-code/types npm:publish +``` + +Note that you'll be asked for an MFA code to complete the publish. diff --git a/packages/types/npm/package.json b/packages/types/npm/package.json index 37549f9e59..db6cbe326b 100644 --- a/packages/types/npm/package.json +++ b/packages/types/npm/package.json @@ -1,6 +1,6 @@ { "name": "@roo-code/types", - "version": "1.25.0", + "version": "1.26.0", "description": "TypeScript type definitions for Roo Code.", "publishConfig": { "access": "public", diff --git a/webview-ui/package.json b/webview-ui/package.json index 50af196ed3..ede0570866 100644 --- a/webview-ui/package.json +++ b/webview-ui/package.json @@ -12,7 +12,7 @@ "build": "tsc -b && vite build", "build:nightly": "tsc -b && vite build --mode nightly", "preview": "vite preview", - "clean": "rimraf ../src/webview-ui/build ../apps/vscode-nightly/build/webview-ui tsconfig.tsbuildinfo .turbo" + "clean": "rimraf ../src/webview-ui ../apps/vscode-nightly/build/webview-ui tsconfig.tsbuildinfo .turbo" }, "dependencies": { "@radix-ui/react-alert-dialog": "^1.1.6", From c17a07d0969798e4d5c36af549961cae2c3f409e Mon Sep 17 00:00:00 2001 From: Hannes Rudolph Date: Thu, 12 Jun 2025 09:09:08 -0600 Subject: [PATCH 02/33] Fix: Reset terminal busy state after manual commands complete (#4583) fix: reset terminal busy state after manual commands complete (#4319) - Add terminal.busy = true when shell execution starts - Add terminal.busy = false when shell execution ends for both Roo and non-Roo terminals - Add comprehensive tests for busy flag management - Fixes issue where terminals got stuck in busy state after manual commands --- src/integrations/terminal/TerminalRegistry.ts | 3 + .../__tests__/TerminalRegistry.test.ts | 211 ++++++++++++++++++ 2 files changed, 214 insertions(+) diff --git a/src/integrations/terminal/TerminalRegistry.ts b/src/integrations/terminal/TerminalRegistry.ts index d31368541e..af334611c3 100644 --- a/src/integrations/terminal/TerminalRegistry.ts +++ b/src/integrations/terminal/TerminalRegistry.ts @@ -59,6 +59,7 @@ export class TerminalRegistry { if (terminal) { terminal.setActiveStream(stream) + terminal.busy = true // Mark terminal as busy when shell execution starts } else { console.error( "[onDidStartTerminalShellExecution] Shell execution started, but not from a Roo-registered terminal:", @@ -99,6 +100,7 @@ export class TerminalRegistry { { terminalId: terminal?.id, command: process?.command, exitCode: e.exitCode }, ) + terminal.busy = false return } @@ -113,6 +115,7 @@ export class TerminalRegistry { // Signal completion to any waiting processes. terminal.shellExecutionComplete(exitDetails) + terminal.busy = false // Mark terminal as not busy when shell execution ends }, ) diff --git a/src/integrations/terminal/__tests__/TerminalRegistry.test.ts b/src/integrations/terminal/__tests__/TerminalRegistry.test.ts index 283e5b73c4..d8926c8759 100644 --- a/src/integrations/terminal/__tests__/TerminalRegistry.test.ts +++ b/src/integrations/terminal/__tests__/TerminalRegistry.test.ts @@ -2,21 +2,39 @@ import { Terminal } from "../Terminal" import { TerminalRegistry } from "../TerminalRegistry" +import * as vscode from "vscode" const PAGER = process.platform === "win32" ? "" : "cat" // Mock vscode.window.createTerminal const mockCreateTerminal = jest.fn() +// Event handlers for testing +let mockStartHandler: any = null +let mockEndHandler: any = null + jest.mock("vscode", () => ({ window: { createTerminal: (...args: any[]) => { mockCreateTerminal(...args) return { + name: "Roo Code", exitStatus: undefined, + dispose: jest.fn(), + show: jest.fn(), + hide: jest.fn(), + sendText: jest.fn(), } }, onDidCloseTerminal: jest.fn().mockReturnValue({ dispose: jest.fn() }), + onDidStartTerminalShellExecution: jest.fn().mockImplementation((handler) => { + mockStartHandler = handler + return { dispose: jest.fn() } + }), + onDidEndTerminalShellExecution: jest.fn().mockImplementation((handler) => { + mockEndHandler = handler + return { dispose: jest.fn() } + }), }, ThemeIcon: jest.fn(), })) @@ -28,6 +46,15 @@ jest.mock("execa", () => ({ describe("TerminalRegistry", () => { beforeEach(() => { mockCreateTerminal.mockClear() + + // Reset event handlers + mockStartHandler = null + mockEndHandler = null + + // Clear terminals array for each test + ;(TerminalRegistry as any).terminals = [] + ;(TerminalRegistry as any).nextTerminalId = 1 + ;(TerminalRegistry as any).isInitialized = false }) describe("createTerminal", () => { @@ -113,4 +140,188 @@ describe("TerminalRegistry", () => { } }) }) + + describe("busy flag management", () => { + let mockVsTerminal: any + + beforeEach(() => { + mockVsTerminal = { + name: "Roo Code", + exitStatus: undefined, + dispose: jest.fn(), + show: jest.fn(), + hide: jest.fn(), + sendText: jest.fn(), + } + mockCreateTerminal.mockReturnValue(mockVsTerminal) + }) + + // Helper function to get the created Roo terminal and its underlying VSCode terminal + const createTerminalAndGetVsTerminal = (path: string = "/test/path") => { + const rooTerminal = TerminalRegistry.createTerminal(path, "vscode") + // Get the actual VSCode terminal that was created and stored + const vsTerminal = (rooTerminal as any).terminal + return { rooTerminal, vsTerminal } + } + + it("should initialize terminal with busy = false", () => { + const terminal = TerminalRegistry.createTerminal("/test/path", "vscode") + expect(terminal.busy).toBe(false) + }) + + it("should set busy = true when shell execution starts", () => { + // Initialize the registry to set up event handlers + TerminalRegistry.initialize() + + // Create a terminal and get the actual VSCode terminal + const { rooTerminal, vsTerminal } = createTerminalAndGetVsTerminal() + expect(rooTerminal.busy).toBe(false) + + // Simulate shell execution start event + const execution = { + commandLine: { value: "echo test" }, + read: jest.fn().mockReturnValue({}), + } as any + + if (mockStartHandler) { + mockStartHandler({ + terminal: vsTerminal, + execution, + }) + } + + expect(rooTerminal.busy).toBe(true) + }) + + it("should set busy = false when shell execution ends for Roo terminals", () => { + // Initialize the registry to set up event handlers + TerminalRegistry.initialize() + + // Create a terminal and get the actual VSCode terminal + const { rooTerminal, vsTerminal } = createTerminalAndGetVsTerminal() + rooTerminal.busy = true + + // Set up a mock process to simulate running state + const mockProcess = { + command: "echo test", + isHot: false, + hasUnretrievedOutput: () => false, + } + rooTerminal.process = mockProcess as any + + // Simulate shell execution end event + const execution = { + commandLine: { value: "echo test" }, + } as any + + if (mockEndHandler) { + mockEndHandler({ + terminal: vsTerminal, + execution, + exitCode: 0, + }) + } + + expect(rooTerminal.busy).toBe(false) + }) + + it("should set busy = false when shell execution ends for non-Roo terminals (manual commands)", () => { + // Initialize the registry to set up event handlers + TerminalRegistry.initialize() + + // Simulate a shell execution end event for a terminal not in our registry + const unknownVsTerminal = { + name: "Unknown Terminal", + } + + const execution = { + commandLine: { value: "sleep 30" }, + } as any + + // This should not throw an error and should handle the case gracefully + expect(() => { + if (mockEndHandler) { + mockEndHandler({ + terminal: unknownVsTerminal, + execution, + exitCode: 0, + }) + } + }).not.toThrow() + }) + + it("should handle busy flag reset when terminal process is not running", () => { + // Initialize the registry to set up event handlers + TerminalRegistry.initialize() + + // Create a terminal and get the actual VSCode terminal + const { rooTerminal, vsTerminal } = createTerminalAndGetVsTerminal() + rooTerminal.busy = true + + // Ensure terminal.running returns false (no active process) + Object.defineProperty(rooTerminal, "running", { + get: () => false, + configurable: true, + }) + + // Simulate shell execution end event + const execution = { + commandLine: { value: "echo test" }, + } as any + + if (mockEndHandler) { + mockEndHandler({ + terminal: vsTerminal, + execution, + exitCode: 0, + }) + } + + // Should reset busy flag even when not running + expect(rooTerminal.busy).toBe(false) + }) + + it("should maintain busy state during command execution lifecycle", () => { + // Initialize the registry to set up event handlers + TerminalRegistry.initialize() + + // Create a terminal and get the actual VSCode terminal + const { rooTerminal, vsTerminal } = createTerminalAndGetVsTerminal() + expect(rooTerminal.busy).toBe(false) + + // Start execution + const execution = { + commandLine: { value: "npm test" }, + read: jest.fn().mockReturnValue({}), + } as any + + if (mockStartHandler) { + mockStartHandler({ + terminal: vsTerminal, + execution, + }) + } + + expect(rooTerminal.busy).toBe(true) + + // Set up mock process for running state + const mockProcess = { + command: "npm test", + isHot: true, + hasUnretrievedOutput: () => true, + } + rooTerminal.process = mockProcess as any + + // End execution + if (mockEndHandler) { + mockEndHandler({ + terminal: vsTerminal, + execution, + exitCode: 0, + }) + } + + expect(rooTerminal.busy).toBe(false) + }) + }) }) From a851ffb7cb5c40dc22a7266f6e1119e88c30199e Mon Sep 17 00:00:00 2001 From: Hannes Rudolph Date: Thu, 12 Jun 2025 09:39:41 -0600 Subject: [PATCH 03/33] feat: Add DeepSeek R1 support to Chutes provider (#4523) (#4525) * feat: Add DeepSeek R1 support to Chutes provider (#4523) - Modified BaseOpenAiCompatibleProvider to expose client as protected - Enhanced ChutesHandler to detect DeepSeek R1 models and parse reasoning chunks - Applied R1 format conversion for message formatting - Set appropriate temperature (0.6) for DeepSeek models - Migrated tests from Jest to Vitest format - Added comprehensive tests for DeepSeek R1 functionality This ensures reasoning chunks are properly separated from regular content when using DeepSeek R1 models via Chutes provider. * feat: Enhance DeepSeek R1 support with tag handling in Chutes provider * fix: Correct temperature retrieval in ChutesHandler to use model's info * fix: Update condition for DeepSeek-R1 model identification in createMessage method --------- Co-authored-by: Daniel Riccio --- src/api/providers/__tests__/chutes.spec.ts | 208 ++++++++++++++++-- .../base-openai-compatible-provider.ts | 2 +- src/api/providers/chutes.ts | 86 +++++++- 3 files changed, 272 insertions(+), 24 deletions(-) diff --git a/src/api/providers/__tests__/chutes.spec.ts b/src/api/providers/__tests__/chutes.spec.ts index c67515cb7f..e8b3e53688 100644 --- a/src/api/providers/__tests__/chutes.spec.ts +++ b/src/api/providers/__tests__/chutes.spec.ts @@ -1,33 +1,64 @@ // npx vitest run api/providers/__tests__/chutes.spec.ts -import { vitest, describe, it, expect, beforeEach } from "vitest" -import OpenAI from "openai" import { Anthropic } from "@anthropic-ai/sdk" +import { afterEach, beforeEach, describe, expect, it, vi } from "vitest" +import OpenAI from "openai" -import { type ChutesModelId, chutesDefaultModelId, chutesModels } from "@roo-code/types" +import { type ChutesModelId, chutesDefaultModelId, chutesModels, DEEP_SEEK_DEFAULT_TEMPERATURE } from "@roo-code/types" import { ChutesHandler } from "../chutes" -const mockCreate = vitest.fn() +// Create mock functions +const mockCreate = vi.fn() -vitest.mock("openai", () => { - return { - default: vitest.fn().mockImplementation(() => ({ - chat: { - completions: { - create: mockCreate, - }, +// Mock OpenAI module +vi.mock("openai", () => ({ + default: vi.fn(() => ({ + chat: { + completions: { + create: mockCreate, }, - })), - } -}) + }, + })), +})) describe("ChutesHandler", () => { let handler: ChutesHandler beforeEach(() => { - vitest.clearAllMocks() - handler = new ChutesHandler({ chutesApiKey: "test-chutes-api-key" }) + vi.clearAllMocks() + // Set up default mock implementation + mockCreate.mockImplementation(async () => ({ + [Symbol.asyncIterator]: async function* () { + yield { + choices: [ + { + delta: { content: "Test response" }, + index: 0, + }, + ], + usage: null, + } + yield { + choices: [ + { + delta: {}, + index: 0, + }, + ], + usage: { + prompt_tokens: 10, + completion_tokens: 5, + total_tokens: 15, + }, + } + }, + })) + handler = new ChutesHandler({ chutesApiKey: "test-key" }) + }) + + afterEach(() => { + vi.restoreAllMocks() }) it("should use the correct Chutes base URL", () => { @@ -41,18 +72,96 @@ describe("ChutesHandler", () => { expect(OpenAI).toHaveBeenCalledWith(expect.objectContaining({ apiKey: chutesApiKey })) }) + it("should handle DeepSeek R1 reasoning format", async () => { + // Override the mock for this specific test + mockCreate.mockImplementationOnce(async () => ({ + [Symbol.asyncIterator]: async function* () { + yield { + choices: [ + { + delta: { content: "Thinking..." }, + index: 0, + }, + ], + usage: null, + } + yield { + choices: [ + { + delta: { content: "Hello" }, + index: 0, + }, + ], + usage: null, + } + yield { + choices: [ + { + delta: {}, + index: 0, + }, + ], + usage: { prompt_tokens: 10, completion_tokens: 5 }, + } + }, + })) + + const systemPrompt = "You are a helpful assistant." + const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Hi" }] + vi.spyOn(handler, "getModel").mockReturnValue({ + id: "deepseek-ai/DeepSeek-R1-0528", + info: { maxTokens: 1024, temperature: 0.7 }, + } as any) + + const stream = handler.createMessage(systemPrompt, messages) + const chunks = [] + for await (const chunk of stream) { + chunks.push(chunk) + } + + expect(chunks).toEqual([ + { type: "reasoning", text: "Thinking..." }, + { type: "text", text: "Hello" }, + { type: "usage", inputTokens: 10, outputTokens: 5 }, + ]) + }) + + it("should fall back to base provider for non-DeepSeek models", async () => { + // Use default mock implementation which returns text content + const systemPrompt = "You are a helpful assistant." + const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Hi" }] + vi.spyOn(handler, "getModel").mockReturnValue({ + id: "some-other-model", + info: { maxTokens: 1024, temperature: 0.7 }, + } as any) + + const stream = handler.createMessage(systemPrompt, messages) + const chunks = [] + for await (const chunk of stream) { + chunks.push(chunk) + } + + expect(chunks).toEqual([ + { type: "text", text: "Test response" }, + { type: "usage", inputTokens: 10, outputTokens: 5 }, + ]) + }) + it("should return default model when no model is specified", () => { const model = handler.getModel() expect(model.id).toBe(chutesDefaultModelId) - expect(model.info).toEqual(chutesModels[chutesDefaultModelId]) + expect(model.info).toEqual(expect.objectContaining(chutesModels[chutesDefaultModelId])) }) it("should return specified model when valid model is provided", () => { const testModelId: ChutesModelId = "deepseek-ai/DeepSeek-R1" - const handlerWithModel = new ChutesHandler({ apiModelId: testModelId, chutesApiKey: "test-chutes-api-key" }) + const handlerWithModel = new ChutesHandler({ + apiModelId: testModelId, + chutesApiKey: "test-chutes-api-key", + }) const model = handlerWithModel.getModel() expect(model.id).toBe(testModelId) - expect(model.info).toEqual(chutesModels[testModelId]) + expect(model.info).toEqual(expect.objectContaining(chutesModels[testModelId])) }) it("completePrompt method should return text from Chutes API", async () => { @@ -74,7 +183,7 @@ describe("ChutesHandler", () => { mockCreate.mockImplementationOnce(() => { return { [Symbol.asyncIterator]: () => ({ - next: vitest + next: vi .fn() .mockResolvedValueOnce({ done: false, @@ -96,7 +205,7 @@ describe("ChutesHandler", () => { mockCreate.mockImplementationOnce(() => { return { [Symbol.asyncIterator]: () => ({ - next: vitest + next: vi .fn() .mockResolvedValueOnce({ done: false, @@ -114,8 +223,43 @@ describe("ChutesHandler", () => { expect(firstChunk.value).toEqual({ type: "usage", inputTokens: 10, outputTokens: 20 }) }) - it("createMessage should pass correct parameters to Chutes client", async () => { + it("createMessage should pass correct parameters to Chutes client for DeepSeek R1", async () => { const modelId: ChutesModelId = "deepseek-ai/DeepSeek-R1" + + // Clear previous mocks and set up new implementation + mockCreate.mockClear() + mockCreate.mockImplementationOnce(async () => ({ + [Symbol.asyncIterator]: async function* () { + // Empty stream for this test + }, + })) + + const handlerWithModel = new ChutesHandler({ + apiModelId: modelId, + chutesApiKey: "test-chutes-api-key", + }) + + const systemPrompt = "Test system prompt for Chutes" + const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Test message for Chutes" }] + + const messageGenerator = handlerWithModel.createMessage(systemPrompt, messages) + await messageGenerator.next() + + expect(mockCreate).toHaveBeenCalledWith( + expect.objectContaining({ + model: modelId, + messages: [ + { + role: "user", + content: `${systemPrompt}\n${messages[0].content}`, + }, + ], + }), + ) + }) + + it("createMessage should pass correct parameters to Chutes client for non-DeepSeek models", async () => { + const modelId: ChutesModelId = "unsloth/Llama-3.3-70B-Instruct" const modelInfo = chutesModels[modelId] const handlerWithModel = new ChutesHandler({ apiModelId: modelId, chutesApiKey: "test-chutes-api-key" }) @@ -146,4 +290,24 @@ describe("ChutesHandler", () => { }), ) }) + + it("should apply DeepSeek default temperature for R1 models", () => { + const testModelId: ChutesModelId = "deepseek-ai/DeepSeek-R1" + const handlerWithModel = new ChutesHandler({ + apiModelId: testModelId, + chutesApiKey: "test-chutes-api-key", + }) + const model = handlerWithModel.getModel() + expect(model.info.temperature).toBe(DEEP_SEEK_DEFAULT_TEMPERATURE) + }) + + it("should use default temperature for non-DeepSeek models", () => { + const testModelId: ChutesModelId = "unsloth/Llama-3.3-70B-Instruct" + const handlerWithModel = new ChutesHandler({ + apiModelId: testModelId, + chutesApiKey: "test-chutes-api-key", + }) + const model = handlerWithModel.getModel() + expect(model.info.temperature).toBe(0.5) + }) }) diff --git a/src/api/providers/base-openai-compatible-provider.ts b/src/api/providers/base-openai-compatible-provider.ts index bf1f3c35a8..f196b5f309 100644 --- a/src/api/providers/base-openai-compatible-provider.ts +++ b/src/api/providers/base-openai-compatible-provider.ts @@ -31,7 +31,7 @@ export abstract class BaseOpenAiCompatibleProvider protected readonly options: ApiHandlerOptions - private client: OpenAI + protected client: OpenAI constructor({ providerName, diff --git a/src/api/providers/chutes.ts b/src/api/providers/chutes.ts index 0fa8741fa3..62121bd19d 100644 --- a/src/api/providers/chutes.ts +++ b/src/api/providers/chutes.ts @@ -1,6 +1,12 @@ -import { type ChutesModelId, chutesDefaultModelId, chutesModels } from "@roo-code/types" +import { DEEP_SEEK_DEFAULT_TEMPERATURE, type ChutesModelId, chutesDefaultModelId, chutesModels } from "@roo-code/types" +import { Anthropic } from "@anthropic-ai/sdk" +import OpenAI from "openai" import type { ApiHandlerOptions } from "../../shared/api" +import { XmlMatcher } from "../../utils/xml-matcher" +import { convertToR1Format } from "../transform/r1-format" +import { convertToOpenAiMessages } from "../transform/openai-format" +import { ApiStream } from "../transform/stream" import { BaseOpenAiCompatibleProvider } from "./base-openai-compatible-provider" @@ -16,4 +22,82 @@ export class ChutesHandler extends BaseOpenAiCompatibleProvider { defaultTemperature: 0.5, }) } + + private getCompletionParams( + systemPrompt: string, + messages: Anthropic.Messages.MessageParam[], + ): OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming { + const { + id: model, + info: { maxTokens: max_tokens }, + } = this.getModel() + + const temperature = this.options.modelTemperature ?? this.getModel().info.temperature + + return { + model, + max_tokens, + temperature, + messages: [{ role: "system", content: systemPrompt }, ...convertToOpenAiMessages(messages)], + stream: true, + stream_options: { include_usage: true }, + } + } + + override async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream { + const model = this.getModel() + + if (model.id.includes("DeepSeek-R1")) { + const stream = await this.client.chat.completions.create({ + ...this.getCompletionParams(systemPrompt, messages), + messages: convertToR1Format([{ role: "user", content: systemPrompt }, ...messages]), + }) + + const matcher = new XmlMatcher( + "think", + (chunk) => + ({ + type: chunk.matched ? "reasoning" : "text", + text: chunk.data, + }) as const, + ) + + for await (const chunk of stream) { + const delta = chunk.choices[0]?.delta + + if (delta?.content) { + for (const processedChunk of matcher.update(delta.content)) { + yield processedChunk + } + } + + if (chunk.usage) { + yield { + type: "usage", + inputTokens: chunk.usage.prompt_tokens || 0, + outputTokens: chunk.usage.completion_tokens || 0, + } + } + } + + // Process any remaining content + for (const processedChunk of matcher.final()) { + yield processedChunk + } + } else { + yield* super.createMessage(systemPrompt, messages) + } + } + + override getModel() { + const model = super.getModel() + const isDeepSeekR1 = model.id.includes("DeepSeek-R1") + return { + ...model, + info: { + ...model.info, + temperature: isDeepSeekR1 ? DEEP_SEEK_DEFAULT_TEMPERATURE : this.defaultTemperature, + }, + } + } } From befbebb8a45bf09a2b9e0e976a55dc683a807262 Mon Sep 17 00:00:00 2001 From: Matt Rubens Date: Thu, 12 Jun 2025 11:40:55 -0400 Subject: [PATCH 04/33] Populate whenToUse for built-in modes (#4579) --- .../__tests__/__snapshots__/system.test.ts.snap | 2 +- src/shared/modes.ts | 12 +++++++++++- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/src/core/prompts/__tests__/__snapshots__/system.test.ts.snap b/src/core/prompts/__tests__/__snapshots__/system.test.ts.snap index 8f93b0353d..be593279bc 100644 --- a/src/core/prompts/__tests__/__snapshots__/system.test.ts.snap +++ b/src/core/prompts/__tests__/__snapshots__/system.test.ts.snap @@ -5681,7 +5681,7 @@ Language Preference: You should always speak and think in the "en" language. Mode-specific Instructions: -You can analyze code, explain concepts, and access external resources. Always answer the user’s questions thoroughly, and do not switch to implementing code unless explicitly requested by the user. Include Mermaid diagrams when they clarify your response. +You can analyze code, explain concepts, and access external resources. Always answer the user's questions thoroughly, and do not switch to implementing code unless explicitly requested by the user. Include Mermaid diagrams when they clarify your response. Rules: # Rules from .clinerules-ask: diff --git a/src/shared/modes.ts b/src/shared/modes.ts index c735118f66..56d41f3c73 100644 --- a/src/shared/modes.ts +++ b/src/shared/modes.ts @@ -66,6 +66,8 @@ export const modes: readonly ModeConfig[] = [ name: "💻 Code", roleDefinition: "You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.", + whenToUse: + "Use this mode when you need to write, modify, or refactor code. Ideal for implementing features, fixing bugs, creating new files, or making code improvements across any programming language or framework.", groups: ["read", "edit", "browser", "command", "mcp"], }, { @@ -73,6 +75,8 @@ export const modes: readonly ModeConfig[] = [ name: "🏗️ Architect", roleDefinition: "You are Roo, an experienced technical leader who is inquisitive and an excellent planner. Your goal is to gather information and get context to create a detailed plan for accomplishing the user's task, which the user will review and approve before they switch into another mode to implement the solution.", + whenToUse: + "Use this mode when you need to plan, design, or strategize before implementation. Perfect for breaking down complex problems, creating technical specifications, designing system architecture, or brainstorming solutions before coding.", groups: ["read", ["edit", { fileRegex: "\\.md$", description: "Markdown files only" }], "browser", "mcp"], customInstructions: "1. Do some information gathering (for example using read_file or search_files) to get more context about the task.\n\n2. You should also ask the user clarifying questions to get a better understanding of the task.\n\n3. Once you've gained more context about the user's request, you should create a detailed plan for how to accomplish the task. Include Mermaid diagrams if they help make your plan clearer.\n\n4. Ask the user if they are pleased with this plan, or if they would like to make any changes. Think of this as a brainstorming session where you can discuss the task and plan the best way to accomplish it.\n\n5. Once the user confirms the plan, ask them if they'd like you to write it to a markdown file.\n\n6. Use the switch_mode tool to request that the user switch to another mode to implement the solution.", @@ -82,15 +86,19 @@ export const modes: readonly ModeConfig[] = [ name: "❓ Ask", roleDefinition: "You are Roo, a knowledgeable technical assistant focused on answering questions and providing information about software development, technology, and related topics.", + whenToUse: + "Use this mode when you need explanations, documentation, or answers to technical questions. Best for understanding concepts, analyzing existing code, getting recommendations, or learning about technologies without making changes.", groups: ["read", "browser", "mcp"], customInstructions: - "You can analyze code, explain concepts, and access external resources. Always answer the user’s questions thoroughly, and do not switch to implementing code unless explicitly requested by the user. Include Mermaid diagrams when they clarify your response.", + "You can analyze code, explain concepts, and access external resources. Always answer the user's questions thoroughly, and do not switch to implementing code unless explicitly requested by the user. Include Mermaid diagrams when they clarify your response.", }, { slug: "debug", name: "🪲 Debug", roleDefinition: "You are Roo, an expert software debugger specializing in systematic problem diagnosis and resolution.", + whenToUse: + "Use this mode when you're troubleshooting issues, investigating errors, or diagnosing problems. Specialized in systematic debugging, adding logging, analyzing stack traces, and identifying root causes before applying fixes.", groups: ["read", "edit", "browser", "command", "mcp"], customInstructions: "Reflect on 5-7 different possible sources of the problem, distill those down to 1-2 most likely sources, and then add logs to validate your assumptions. Explicitly ask the user to confirm the diagnosis before fixing the problem.", @@ -100,6 +108,8 @@ export const modes: readonly ModeConfig[] = [ name: "🪃 Orchestrator", roleDefinition: "You are Roo, a strategic workflow orchestrator who coordinates complex tasks by delegating them to appropriate specialized modes. You have a comprehensive understanding of each mode's capabilities and limitations, allowing you to effectively break down complex problems into discrete tasks that can be solved by different specialists.", + whenToUse: + "Use this mode for complex, multi-step projects that require coordination across different specialties. Ideal when you need to break down large tasks into subtasks, manage workflows, or coordinate work that spans multiple domains or expertise areas.", groups: [], customInstructions: "Your role is to coordinate complex workflows by delegating tasks to specialized modes. As an orchestrator, you should:\n\n1. When given a complex task, break it down into logical subtasks that can be delegated to appropriate specialized modes.\n\n2. For each subtask, use the `new_task` tool to delegate. Choose the most appropriate mode for the subtask's specific goal and provide comprehensive instructions in the `message` parameter. These instructions must include:\n * All necessary context from the parent task or previous subtasks required to complete the work.\n * A clearly defined scope, specifying exactly what the subtask should accomplish.\n * An explicit statement that the subtask should *only* perform the work outlined in these instructions and not deviate.\n * An instruction for the subtask to signal completion by using the `attempt_completion` tool, providing a concise yet thorough summary of the outcome in the `result` parameter, keeping in mind that this summary will be the source of truth used to keep track of what was completed on this project.\n * A statement that these specific instructions supersede any conflicting general instructions the subtask's mode might have.\n\n3. Track and manage the progress of all subtasks. When a subtask is completed, analyze its results and determine the next steps.\n\n4. Help the user understand how the different subtasks fit together in the overall workflow. Provide clear reasoning about why you're delegating specific tasks to specific modes.\n\n5. When all subtasks are completed, synthesize the results and provide a comprehensive overview of what was accomplished.\n\n6. Ask clarifying questions when necessary to better understand how to break down complex tasks effectively.\n\n7. Suggest improvements to the workflow based on the results of completed subtasks.\n\nUse subtasks to maintain clarity. If a request significantly shifts focus or requires a different expertise (mode), consider creating a subtask rather than overloading the current one.", From 69472099eaf57f2075dced0f98f65e39f350c6c3 Mon Sep 17 00:00:00 2001 From: Hannes Rudolph Date: Thu, 12 Jun 2025 09:43:54 -0600 Subject: [PATCH 05/33] feat: Navigate prompt history in prompt field via arrow up/down (#4139) (#4450) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * feat: add prompt history navigation with arrow keys (#4139) - Navigate through prompt history using arrow up/down keys - Only triggers when cursor is at first line (up) or last line (down) - Preserves current input when starting navigation - Resets navigation state when typing or sending messages - Follows VSCode's standard UX patterns for history navigation * fix: correct prompt history order and add workspace filtering (#4139) - Remove reverse() to maintain chronological order in history array - Add workspace filtering to only show prompts from current workspace - Ensure arrow up navigates to older prompts (as expected) - Filter history items by workspace field matching current cwd * test: Fix Windows unit test failures for prompt history navigation - Add missing taskHistory and cwd properties to all useExtensionState mocks - Add comprehensive test coverage for prompt history navigation feature - Ensure all 25 tests pass including new prompt history functionality Fixes failing Windows CI test in PR #4450 * refactor: Improve cursor positioning with useLayoutEffect - Replace setTimeout(..., 0) with useLayoutEffect for more reliable cursor positioning - Implement state-based cursor positioning pattern suggested by @mochiya98 - Add CursorPositionState interface for better type safety - Maintain all existing functionality while improving timing reliability This addresses the technical suggestion in PR #4450 comment about using useLayoutEffect instead of setTimeout for DOM manipulation timing. * feat: optimize prompt history with performance improvements and memory management - Add useMemo for prompt history filtering to prevent unnecessary re-computations - Implement MAX_PROMPT_HISTORY_SIZE = 100 limit for memory management - Extract logic into usePromptHistory custom hook for better code organization - Simplify ChatTextArea component by delegating history logic to custom hook Addresses review feedback on PR #4450 for issue #4139 * refactor: clean up unused code and fix linting issues in prompt history - Remove unused CursorPositionState interface from ChatTextArea - Remove unused destructured variables from usePromptHistory hook - Fix missing dependency in useEffect dependency array - Rename unused parameter with underscore prefix Related to #4139 * feat: implement hybrid prompt history with position reset - In chat: Use conversation messages (user_feedback), newest first - Out of chat: Use task history, oldest first - Reset navigation position when switching between history sources - Switch from taskHistory to clineMessages for active conversations - Maintain backward compatibility with task history fallback - Add comprehensive tests for hybrid behavior and position reset This provides intuitive UX where: - Users navigate recent conversation messages during tasks (newest first) - Users access initial task prompts when starting fresh (oldest first) - Navigation always starts fresh when switching contexts * fix: correct task history slicing order for prompt navigation Task history was using .slice(-100) which gets the newest 100 tasks, but we want to show oldest tasks first when navigating. Changed to .slice(0, 100) to get the oldest 100 tasks instead. This ensures that when starting fresh (no conversation), up arrow shows the oldest task prompts first, which is the intended behavior. * refactor: remove comment on task history size limitation and clarify order preservation * refactor: replace local ClineMessage and TaskHistoryItem interfaces with imported types * fix: prevent prompt history fallback to task list during active conversation When an active task has only an initial prompt with no follow-up user messages, the prompt history should return empty instead of falling back to task history. This fixes the "Starting Fresh" behavior appearing inappropriately. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude --------- Co-authored-by: Daniel Riccio Co-authored-by: Claude --- .../src/components/chat/ChatTextArea.tsx | 53 ++- .../chat/__tests__/ChatTextArea.test.tsx | 344 ++++++++++++++++++ .../components/chat/hooks/usePromptHistory.ts | 198 ++++++++++ 3 files changed, 594 insertions(+), 1 deletion(-) create mode 100644 webview-ui/src/components/chat/hooks/usePromptHistory.ts diff --git a/webview-ui/src/components/chat/ChatTextArea.tsx b/webview-ui/src/components/chat/ChatTextArea.tsx index 5d8e0a2112..5e51edadce 100644 --- a/webview-ui/src/components/chat/ChatTextArea.tsx +++ b/webview-ui/src/components/chat/ChatTextArea.tsx @@ -27,6 +27,7 @@ import ContextMenu from "./ContextMenu" import { VolumeX, Pin, Check } from "lucide-react" import { IconButton } from "./IconButton" import { cn } from "@/lib/utils" +import { usePromptHistory } from "./hooks/usePromptHistory" interface ChatTextAreaProps { inputValue: string @@ -75,6 +76,8 @@ const ChatTextArea = forwardRef( cwd, pinnedApiConfigs, togglePinnedApiConfig, + taskHistory, + clineMessages, } = useExtensionState() // Find the ID and display text for the currently selected API configuration @@ -153,6 +156,21 @@ const ChatTextArea = forwardRef( const [isEnhancingPrompt, setIsEnhancingPrompt] = useState(false) const [isFocused, setIsFocused] = useState(false) + // Use custom hook for prompt history navigation + const { + inputValueWithCursor, + setInputValueWithCursor, + handleHistoryNavigation, + resetHistoryNavigation, + resetOnInputChange, + } = usePromptHistory({ + clineMessages, + taskHistory, + cwd, + inputValue, + setInputValue, + }) + // Fetch git commits when Git is selected or when typing a hash. useEffect(() => { if (selectedType === ContextMenuOptionType.Git || /^[a-f0-9]+$/i.test(searchQuery)) { @@ -360,10 +378,17 @@ const ChatTextArea = forwardRef( const isComposing = event.nativeEvent?.isComposing ?? false + // Handle prompt history navigation using custom hook + if (handleHistoryNavigation(event, showContextMenu, isComposing)) { + return + } + if (event.key === "Enter" && !event.shiftKey && !isComposing) { event.preventDefault() if (!sendingDisabled) { + // Reset history navigation state when sending + resetHistoryNavigation() onSend() } } @@ -427,6 +452,8 @@ const ChatTextArea = forwardRef( queryItems, customModes, fileSearchResults, + handleHistoryNavigation, + resetHistoryNavigation, ], ) @@ -437,6 +464,27 @@ const ChatTextArea = forwardRef( } }, [inputValue, intendedCursorPosition]) + // Handle cursor positioning after history navigation + useLayoutEffect(() => { + if (!inputValueWithCursor.afterRender || !textAreaRef.current) return + + if (inputValueWithCursor.afterRender === "SET_CURSOR_FIRST_LINE") { + const firstLineEnd = + inputValueWithCursor.value.indexOf("\n") === -1 + ? inputValueWithCursor.value.length + : inputValueWithCursor.value.indexOf("\n") + textAreaRef.current.setSelectionRange(firstLineEnd, firstLineEnd) + } else if (inputValueWithCursor.afterRender === "SET_CURSOR_LAST_LINE") { + const lines = inputValueWithCursor.value.split("\n") + const lastLineStart = inputValueWithCursor.value.length - lines[lines.length - 1].length + textAreaRef.current.setSelectionRange(lastLineStart, lastLineStart) + } else if (inputValueWithCursor.afterRender === "SET_CURSOR_START") { + textAreaRef.current.setSelectionRange(0, 0) + } + + setInputValueWithCursor({ value: inputValueWithCursor.value }) + }, [inputValueWithCursor, setInputValueWithCursor]) + // Ref to store the search timeout. const searchTimeoutRef = useRef(null) @@ -445,6 +493,9 @@ const ChatTextArea = forwardRef( const newValue = e.target.value setInputValue(newValue) + // Reset history navigation when user types + resetOnInputChange() + const newCursorPosition = e.target.selectionStart setCursorPosition(newCursorPosition) @@ -499,7 +550,7 @@ const ChatTextArea = forwardRef( setFileSearchResults([]) // Clear file search results. } }, - [setInputValue, setSearchRequestId, setFileSearchResults, setSearchLoading], + [setInputValue, setSearchRequestId, setFileSearchResults, setSearchLoading, resetOnInputChange], ) useEffect(() => { diff --git a/webview-ui/src/components/chat/__tests__/ChatTextArea.test.tsx b/webview-ui/src/components/chat/__tests__/ChatTextArea.test.tsx index 8b09a5eb87..7f01245144 100644 --- a/webview-ui/src/components/chat/__tests__/ChatTextArea.test.tsx +++ b/webview-ui/src/components/chat/__tests__/ChatTextArea.test.tsx @@ -68,6 +68,8 @@ describe("ChatTextArea", () => { apiConfiguration: { apiProvider: "anthropic", }, + taskHistory: [], + cwd: "/test/workspace", }) }) @@ -76,6 +78,8 @@ describe("ChatTextArea", () => { ;(useExtensionState as jest.Mock).mockReturnValue({ filePaths: [], openedTabs: [], + taskHistory: [], + cwd: "/test/workspace", }) render() const enhanceButton = getEnhancePromptButton() @@ -94,6 +98,8 @@ describe("ChatTextArea", () => { filePaths: [], openedTabs: [], apiConfiguration, + taskHistory: [], + cwd: "/test/workspace", }) render() @@ -114,6 +120,8 @@ describe("ChatTextArea", () => { apiConfiguration: { apiProvider: "openrouter", }, + taskHistory: [], + cwd: "/test/workspace", }) render() @@ -131,6 +139,8 @@ describe("ChatTextArea", () => { apiConfiguration: { apiProvider: "openrouter", }, + taskHistory: [], + cwd: "/test/workspace", }) render() @@ -155,6 +165,8 @@ describe("ChatTextArea", () => { apiProvider: "openrouter", newSetting: "test", }, + taskHistory: [], + cwd: "/test/workspace", }) rerender() @@ -408,6 +420,338 @@ describe("ChatTextArea", () => { // Verify setInputValue was not called expect(setInputValue).not.toHaveBeenCalled() }) + + describe("prompt history navigation", () => { + const mockClineMessages = [ + { type: "say", say: "user_feedback", text: "First prompt", ts: 1000 }, + { type: "say", say: "user_feedback", text: "Second prompt", ts: 2000 }, + { type: "say", say: "user_feedback", text: "Third prompt", ts: 3000 }, + ] + + beforeEach(() => { + ;(useExtensionState as jest.Mock).mockReturnValue({ + filePaths: [], + openedTabs: [], + apiConfiguration: { + apiProvider: "anthropic", + }, + taskHistory: [], + clineMessages: mockClineMessages, + cwd: "/test/workspace", + }) + }) + + it("should navigate to previous prompt on arrow up", () => { + const setInputValue = jest.fn() + const { container } = render( + , + ) + + const textarea = container.querySelector("textarea")! + + // Simulate arrow up key press + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + + // Should set the newest conversation message (first in reversed array) + expect(setInputValue).toHaveBeenCalledWith("Third prompt") + }) + + it("should navigate through history with multiple arrow up presses", () => { + const setInputValue = jest.fn() + const { container } = render( + , + ) + + const textarea = container.querySelector("textarea")! + + // First arrow up - newest conversation message + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("Third prompt") + + // Update input value to simulate the state change + setInputValue.mockClear() + + // Second arrow up - previous conversation message + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("Second prompt") + }) + + it("should navigate forward with arrow down", () => { + const setInputValue = jest.fn() + const { container } = render( + , + ) + + const textarea = container.querySelector("textarea")! + + // Go back in history first (index 0 -> "Third prompt", then index 1 -> "Second prompt") + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + setInputValue.mockClear() + + // Navigate forward (from index 1 back to index 0) + fireEvent.keyDown(textarea, { key: "ArrowDown" }) + expect(setInputValue).toHaveBeenCalledWith("Third prompt") + }) + + it("should preserve current input when starting navigation", () => { + const setInputValue = jest.fn() + const { container } = render( + , + ) + + const textarea = container.querySelector("textarea")! + + // Navigate to history + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("Third prompt") + + setInputValue.mockClear() + + // Navigate back to current input + fireEvent.keyDown(textarea, { key: "ArrowDown" }) + expect(setInputValue).toHaveBeenCalledWith("Current input") + }) + + it("should reset history navigation when user types", () => { + const setInputValue = jest.fn() + const { container } = render( + , + ) + + const textarea = container.querySelector("textarea")! + + // Navigate to history + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + setInputValue.mockClear() + + // Type something + fireEvent.change(textarea, { target: { value: "New input", selectionStart: 9 } }) + + // Should reset history navigation + expect(setInputValue).toHaveBeenCalledWith("New input") + }) + + it("should reset history navigation when sending message", () => { + const onSend = jest.fn() + const setInputValue = jest.fn() + const { container } = render( + , + ) + + const textarea = container.querySelector("textarea")! + + // Navigate to history first + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + setInputValue.mockClear() + + // Send message + fireEvent.keyDown(textarea, { key: "Enter" }) + + expect(onSend).toHaveBeenCalled() + }) + + it("should navigate history when cursor is at first line", () => { + const setInputValue = jest.fn() + const { container } = render( + , + ) + + const textarea = container.querySelector("textarea")! + + // Clear any calls from initial render + setInputValue.mockClear() + + // With empty input, cursor is at first line by default + // Arrow up should navigate history + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("Third prompt") + }) + + it("should filter history by current workspace", () => { + const mixedClineMessages = [ + { type: "say", say: "user_feedback", text: "Workspace 1 prompt", ts: 1000 }, + { type: "say", say: "user_feedback", text: "Other workspace prompt", ts: 2000 }, + { type: "say", say: "user_feedback", text: "Workspace 1 prompt 2", ts: 3000 }, + ] + + ;(useExtensionState as jest.Mock).mockReturnValue({ + filePaths: [], + openedTabs: [], + apiConfiguration: { + apiProvider: "anthropic", + }, + taskHistory: [], + clineMessages: mixedClineMessages, + cwd: "/test/workspace", + }) + + const setInputValue = jest.fn() + const { container } = render( + , + ) + + const textarea = container.querySelector("textarea")! + + // Should show conversation messages newest first (after reverse) + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("Workspace 1 prompt 2") + + setInputValue.mockClear() + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("Other workspace prompt") + }) + + it("should handle empty conversation history gracefully", () => { + ;(useExtensionState as jest.Mock).mockReturnValue({ + filePaths: [], + openedTabs: [], + apiConfiguration: { + apiProvider: "anthropic", + }, + taskHistory: [], + clineMessages: [], + cwd: "/test/workspace", + }) + + const setInputValue = jest.fn() + const { container } = render( + , + ) + + const textarea = container.querySelector("textarea")! + + // Should not crash or call setInputValue + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).not.toHaveBeenCalled() + }) + + it("should ignore empty or whitespace-only messages", () => { + const clineMessagesWithEmpty = [ + { type: "say", say: "user_feedback", text: "Valid prompt", ts: 1000 }, + { type: "say", say: "user_feedback", text: "", ts: 2000 }, + { type: "say", say: "user_feedback", text: " ", ts: 3000 }, + { type: "say", say: "user_feedback", text: "Another valid prompt", ts: 4000 }, + ] + + ;(useExtensionState as jest.Mock).mockReturnValue({ + filePaths: [], + openedTabs: [], + apiConfiguration: { + apiProvider: "anthropic", + }, + taskHistory: [], + clineMessages: clineMessagesWithEmpty, + cwd: "/test/workspace", + }) + + const setInputValue = jest.fn() + const { container } = render( + , + ) + + const textarea = container.querySelector("textarea")! + + // Should skip empty messages, newest first for conversation + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("Another valid prompt") + + setInputValue.mockClear() + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("Valid prompt") + }) + + it("should use task history (oldest first) when no conversation messages exist", () => { + const mockTaskHistory = [ + { task: "First task", workspace: "/test/workspace" }, + { task: "Second task", workspace: "/test/workspace" }, + { task: "Third task", workspace: "/test/workspace" }, + ] + + ;(useExtensionState as jest.Mock).mockReturnValue({ + filePaths: [], + openedTabs: [], + apiConfiguration: { + apiProvider: "anthropic", + }, + taskHistory: mockTaskHistory, + clineMessages: [], // No conversation messages + cwd: "/test/workspace", + }) + + const setInputValue = jest.fn() + const { container } = render( + , + ) + + const textarea = container.querySelector("textarea")! + + // Should show task history oldest first (chronological order) + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("First task") + + setInputValue.mockClear() + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("Second task") + }) + + it("should reset navigation position when switching between history sources", () => { + const setInputValue = jest.fn() + const { rerender } = render( + , + ) + + // Start with task history + ;(useExtensionState as jest.Mock).mockReturnValue({ + filePaths: [], + openedTabs: [], + apiConfiguration: { + apiProvider: "anthropic", + }, + taskHistory: [ + { task: "Task 1", workspace: "/test/workspace" }, + { task: "Task 2", workspace: "/test/workspace" }, + ], + clineMessages: [], + cwd: "/test/workspace", + }) + + rerender() + + const textarea = document.querySelector("textarea")! + + // Navigate in task history + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("Task 1") + + // Switch to conversation messages + ;(useExtensionState as jest.Mock).mockReturnValue({ + filePaths: [], + openedTabs: [], + apiConfiguration: { + apiProvider: "anthropic", + }, + taskHistory: [], + clineMessages: [ + { type: "say", say: "user_feedback", text: "Message 1", ts: 1000 }, + { type: "say", say: "user_feedback", text: "Message 2", ts: 2000 }, + ], + cwd: "/test/workspace", + }) + + setInputValue.mockClear() + rerender() + + // Should start from beginning of conversation history (newest first) + fireEvent.keyDown(textarea, { key: "ArrowUp" }) + expect(setInputValue).toHaveBeenCalledWith("Message 2") + }) + }) }) describe("selectApiConfig", () => { diff --git a/webview-ui/src/components/chat/hooks/usePromptHistory.ts b/webview-ui/src/components/chat/hooks/usePromptHistory.ts new file mode 100644 index 0000000000..810c4a606a --- /dev/null +++ b/webview-ui/src/components/chat/hooks/usePromptHistory.ts @@ -0,0 +1,198 @@ +import { ClineMessage, HistoryItem } from "@roo-code/types" +import { useCallback, useEffect, useMemo, useState } from "react" + +interface UsePromptHistoryProps { + clineMessages: ClineMessage[] | undefined + taskHistory: HistoryItem[] | undefined + cwd: string | undefined + inputValue: string + setInputValue: (value: string) => void +} + +interface CursorPositionState { + value: string + afterRender?: "SET_CURSOR_FIRST_LINE" | "SET_CURSOR_LAST_LINE" | "SET_CURSOR_START" +} + +export interface UsePromptHistoryReturn { + historyIndex: number + setHistoryIndex: (index: number) => void + tempInput: string + setTempInput: (input: string) => void + promptHistory: string[] + inputValueWithCursor: CursorPositionState + setInputValueWithCursor: (state: CursorPositionState) => void + handleHistoryNavigation: ( + event: React.KeyboardEvent, + showContextMenu: boolean, + isComposing: boolean, + ) => boolean + resetHistoryNavigation: () => void + resetOnInputChange: () => void +} + +export const usePromptHistory = ({ + clineMessages, + taskHistory, + cwd, + inputValue, + setInputValue, +}: UsePromptHistoryProps): UsePromptHistoryReturn => { + // Maximum number of prompts to keep in history for memory management + const MAX_PROMPT_HISTORY_SIZE = 100 + + // Prompt history navigation state + const [historyIndex, setHistoryIndex] = useState(-1) + const [tempInput, setTempInput] = useState("") + const [promptHistory, setPromptHistory] = useState([]) + const [inputValueWithCursor, setInputValueWithCursor] = useState({ value: inputValue }) + + // Initialize prompt history with hybrid approach: conversation messages if in task, otherwise task history + const filteredPromptHistory = useMemo(() => { + // First try to get conversation messages (user_feedback from clineMessages) + const conversationPrompts = clineMessages + ?.filter((message) => { + // Filter for user_feedback messages that have text content + return ( + message.type === "say" && + message.say === "user_feedback" && + message.text && + message.text.trim() !== "" + ) + }) + .map((message) => message.text!) + + // If we have conversation messages, use those (newest first when navigating up) + if (conversationPrompts && conversationPrompts.length > 0) { + return conversationPrompts.slice(-MAX_PROMPT_HISTORY_SIZE).reverse() // newest first for conversation messages + } + + // If we have clineMessages array (meaning we're in an active task), don't fall back to task history + // Only use task history when starting fresh (no active conversation) + if (clineMessages && clineMessages.length > 0) { + return [] + } + + // Fall back to task history only when starting fresh (no active conversation) + if (!taskHistory || taskHistory.length === 0 || !cwd) { + return [] + } + + // Extract user prompts from task history for the current workspace only + const taskPrompts = taskHistory + .filter((item) => { + // Filter by workspace and ensure task is not empty + return item.task && item.task.trim() !== "" && (!item.workspace || item.workspace === cwd) + }) + .map((item) => item.task) + .slice(0, MAX_PROMPT_HISTORY_SIZE) + + return taskPrompts + }, [clineMessages, taskHistory, cwd]) + + // Update prompt history when filtered history changes and reset navigation + useEffect(() => { + setPromptHistory(filteredPromptHistory) + // Reset navigation state when switching between history sources + setHistoryIndex(-1) + setTempInput("") + }, [filteredPromptHistory]) + + // Reset history navigation when user types (but not when we're setting it programmatically) + const resetOnInputChange = useCallback(() => { + if (historyIndex !== -1) { + setHistoryIndex(-1) + setTempInput("") + } + }, [historyIndex]) + + const handleHistoryNavigation = useCallback( + (event: React.KeyboardEvent, showContextMenu: boolean, isComposing: boolean): boolean => { + // Handle prompt history navigation + if (!showContextMenu && promptHistory.length > 0 && !isComposing) { + const textarea = event.currentTarget + const { selectionStart, selectionEnd, value } = textarea + const lines = value.substring(0, selectionStart).split("\n") + const currentLineIndex = lines.length - 1 + const totalLines = value.split("\n").length + const isAtFirstLine = currentLineIndex === 0 + const isAtLastLine = currentLineIndex === totalLines - 1 + const hasSelection = selectionStart !== selectionEnd + + // Only navigate history if cursor is at first/last line and no text is selected + if (!hasSelection) { + if (event.key === "ArrowUp" && isAtFirstLine) { + event.preventDefault() + + // Save current input if starting navigation + if (historyIndex === -1 && inputValue.trim() !== "") { + setTempInput(inputValue) + } + + // Navigate to previous prompt + const newIndex = historyIndex + 1 + if (newIndex < promptHistory.length) { + setHistoryIndex(newIndex) + const historicalPrompt = promptHistory[newIndex] + if (historicalPrompt) { + setInputValue(historicalPrompt) + setInputValueWithCursor({ + value: historicalPrompt, + afterRender: "SET_CURSOR_FIRST_LINE", + }) + } + } + return true + } + + if (event.key === "ArrowDown" && isAtLastLine) { + event.preventDefault() + + // Navigate to next prompt + if (historyIndex > 0) { + const newIndex = historyIndex - 1 + setHistoryIndex(newIndex) + const historicalPrompt = promptHistory[newIndex] + if (historicalPrompt) { + setInputValue(historicalPrompt) + setInputValueWithCursor({ + value: historicalPrompt, + afterRender: "SET_CURSOR_LAST_LINE", + }) + } + } else if (historyIndex === 0) { + // Return to current input + setHistoryIndex(-1) + setInputValue(tempInput) + setInputValueWithCursor({ + value: tempInput, + afterRender: "SET_CURSOR_START", + }) + } + return true + } + } + } + return false + }, + [promptHistory, historyIndex, inputValue, tempInput, setInputValue], + ) + + const resetHistoryNavigation = useCallback(() => { + setHistoryIndex(-1) + setTempInput("") + }, []) + + return { + historyIndex, + setHistoryIndex, + tempInput, + setTempInput, + promptHistory, + inputValueWithCursor, + setInputValueWithCursor, + handleHistoryNavigation, + resetHistoryNavigation, + resetOnInputChange, + } +} From 91a477d83143c8d6c8a686ae96e457caa3d2c2a7 Mon Sep 17 00:00:00 2001 From: Hannes Rudolph Date: Thu, 12 Jun 2025 09:47:23 -0600 Subject: [PATCH 06/33] docs: add JSDoc documentation for ClineAsk and ClineSay types (#4427) docs: add comprehensive JSDoc documentation for ClineAsk and ClineSay types --- packages/types/src/message.ts | 54 +++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/packages/types/src/message.ts b/packages/types/src/message.ts index 33c2b7a108..aebd1fe3ae 100644 --- a/packages/types/src/message.ts +++ b/packages/types/src/message.ts @@ -4,6 +4,27 @@ import { z } from "zod" * ClineAsk */ +/** + * Array of possible ask types that the LLM can use to request user interaction or approval. + * These represent different scenarios where the assistant needs user input to proceed. + * + * @constant + * @readonly + * + * Ask type descriptions: + * - `followup`: LLM asks a clarifying question to gather more information needed to complete the task + * - `command`: Permission to execute a terminal/shell command + * - `command_output`: Permission to read the output from a previously executed command + * - `completion_result`: Task has been completed, awaiting user feedback or a new task + * - `tool`: Permission to use a tool for file operations (read, write, search, etc.) + * - `api_req_failed`: API request failed, asking user whether to retry + * - `resume_task`: Confirmation needed to resume a previously paused task + * - `resume_completed_task`: Confirmation needed to resume a task that was already marked as completed + * - `mistake_limit_reached`: Too many errors encountered, needs user guidance on how to proceed + * - `browser_action_launch`: Permission to open or interact with a browser + * - `use_mcp_server`: Permission to use Model Context Protocol (MCP) server functionality + * - `auto_approval_max_req_reached`: Auto-approval limit has been reached, manual approval required + */ export const clineAsks = [ "followup", "command", @@ -27,6 +48,39 @@ export type ClineAsk = z.infer * ClineSay */ +/** + * Array of possible say types that represent different kinds of messages the assistant can send. + * These are used to categorize and handle various types of communication from the LLM to the user. + * + * @constant + * @readonly + * + * Say type descriptions: + * - `error`: General error message + * - `api_req_started`: Indicates an API request has been initiated + * - `api_req_finished`: Indicates an API request has completed successfully + * - `api_req_retried`: Indicates an API request is being retried after a failure + * - `api_req_retry_delayed`: Indicates an API request retry has been delayed + * - `api_req_deleted`: Indicates an API request has been deleted/cancelled + * - `text`: General text message or assistant response + * - `reasoning`: Assistant's reasoning or thought process (often hidden from user) + * - `completion_result`: Final result of task completion + * - `user_feedback`: Message containing user feedback + * - `user_feedback_diff`: Diff-formatted feedback from user showing requested changes + * - `command_output`: Output from an executed command + * - `shell_integration_warning`: Warning about shell integration issues or limitations + * - `browser_action`: Action performed in the browser + * - `browser_action_result`: Result of a browser action + * - `mcp_server_request_started`: MCP server request has been initiated + * - `mcp_server_response`: Response received from MCP server + * - `subtask_result`: Result of a completed subtask + * - `checkpoint_saved`: Indicates a checkpoint has been saved + * - `rooignore_error`: Error related to .rooignore file processing + * - `diff_error`: Error occurred while applying a diff/patch + * - `condense_context`: Context condensation/summarization has started + * - `condense_context_error`: Error occurred during context condensation + * - `codebase_search_result`: Results from searching the codebase + */ export const clineSays = [ "error", "api_req_started", From 8f58737550f364c0aabb7858ecb9face6d625460 Mon Sep 17 00:00:00 2001 From: Ruakij Date: Thu, 12 Jun 2025 17:48:14 +0200 Subject: [PATCH 07/33] =?UTF-8?q?Fix=20#4113:=20Move=20relPath=20&=20newCo?= =?UTF-8?q?ntent=20checks=20in=20writeToFileTool=20earlie=E2=80=A6=20(#437?= =?UTF-8?q?8)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix #4113: Move relPath & newContent checks in writeToFileTool earlier and run after they exist or block is non-partial Add tests covering the issue. --- .../tools/__tests__/writeToFileTool.test.ts | 29 ++++++++++++++++ src/core/tools/writeToFileTool.ts | 34 +++++++++---------- 2 files changed, 46 insertions(+), 17 deletions(-) diff --git a/src/core/tools/__tests__/writeToFileTool.test.ts b/src/core/tools/__tests__/writeToFileTool.test.ts index 7df1ee3eb6..e0789f766c 100644 --- a/src/core/tools/__tests__/writeToFileTool.test.ts +++ b/src/core/tools/__tests__/writeToFileTool.test.ts @@ -399,4 +399,33 @@ describe("writeToFileTool", () => { expect(mockCline.diffViewProvider.reset).toHaveBeenCalled() }) }) + + describe("parameter validation", () => { + it("errors and resets on missing path parameter", async () => { + await executeWriteFileTool({ path: undefined }) + + expect(mockCline.consecutiveMistakeCount).toBe(1) + expect(mockCline.recordToolError).toHaveBeenCalledWith("write_to_file") + expect(mockCline.sayAndCreateMissingParamError).toHaveBeenCalledWith("write_to_file", "path") + expect(mockCline.diffViewProvider.reset).toHaveBeenCalled() + }) + + it("errors and resets on empty path parameter", async () => { + await executeWriteFileTool({ path: "" }) + + expect(mockCline.consecutiveMistakeCount).toBe(1) + expect(mockCline.recordToolError).toHaveBeenCalledWith("write_to_file") + expect(mockCline.sayAndCreateMissingParamError).toHaveBeenCalledWith("write_to_file", "path") + expect(mockCline.diffViewProvider.reset).toHaveBeenCalled() + }) + + it("errors and resets on missing content parameter", async () => { + await executeWriteFileTool({ content: undefined }) + + expect(mockCline.consecutiveMistakeCount).toBe(1) + expect(mockCline.recordToolError).toHaveBeenCalledWith("write_to_file") + expect(mockCline.sayAndCreateMissingParamError).toHaveBeenCalledWith("write_to_file", "content") + expect(mockCline.diffViewProvider.reset).toHaveBeenCalled() + }) + }) }) diff --git a/src/core/tools/writeToFileTool.ts b/src/core/tools/writeToFileTool.ts index 63191acb7e..f7543d6d8b 100644 --- a/src/core/tools/writeToFileTool.ts +++ b/src/core/tools/writeToFileTool.ts @@ -26,12 +26,28 @@ export async function writeToFileTool( let newContent: string | undefined = block.params.content let predictedLineCount: number | undefined = parseInt(block.params.line_count ?? "0") - if (!relPath || newContent === undefined) { + if (block.partial && (!relPath || newContent === undefined)) { // checking for newContent ensure relPath is complete // wait so we can determine if it's a new file or editing an existing file return } + if (!relPath) { + cline.consecutiveMistakeCount++ + cline.recordToolError("write_to_file") + pushToolResult(await cline.sayAndCreateMissingParamError("write_to_file", "path")) + await cline.diffViewProvider.reset() + return + } + + if (newContent === undefined) { + cline.consecutiveMistakeCount++ + cline.recordToolError("write_to_file") + pushToolResult(await cline.sayAndCreateMissingParamError("write_to_file", "content")) + await cline.diffViewProvider.reset() + return + } + const accessAllowed = cline.rooIgnoreController?.validateAccess(relPath) if (!accessAllowed) { @@ -96,22 +112,6 @@ export async function writeToFileTool( return } else { - if (!relPath) { - cline.consecutiveMistakeCount++ - cline.recordToolError("write_to_file") - pushToolResult(await cline.sayAndCreateMissingParamError("write_to_file", "path")) - await cline.diffViewProvider.reset() - return - } - - if (newContent === undefined) { - cline.consecutiveMistakeCount++ - cline.recordToolError("write_to_file") - pushToolResult(await cline.sayAndCreateMissingParamError("write_to_file", "content")) - await cline.diffViewProvider.reset() - return - } - if (predictedLineCount === undefined) { cline.consecutiveMistakeCount++ cline.recordToolError("write_to_file") From 53e7e6beaad2e54fd51c8bba6285f4e258a81f1c Mon Sep 17 00:00:00 2001 From: KJ7LNW <93454819+KJ7LNW@users.noreply.github.com> Date: Thu, 12 Jun 2025 08:49:19 -0700 Subject: [PATCH 08/33] feat: Allow escaping of context mentions (#4362) * allow escaping of context mentions * refactor: update comment --------- Co-authored-by: cannuri <91494156+cannuri@users.noreply.github.com> Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com> --- src/core/tools/__tests__/newTaskTool.test.ts | 186 ++++++++++++++++++ src/core/tools/newTaskTool.ts | 7 +- src/shared/__tests__/context-mentions.test.ts | 9 +- src/shared/context-mentions.ts | 2 +- 4 files changed, 200 insertions(+), 4 deletions(-) create mode 100644 src/core/tools/__tests__/newTaskTool.test.ts diff --git a/src/core/tools/__tests__/newTaskTool.test.ts b/src/core/tools/__tests__/newTaskTool.test.ts new file mode 100644 index 0000000000..1a9e497df3 --- /dev/null +++ b/src/core/tools/__tests__/newTaskTool.test.ts @@ -0,0 +1,186 @@ +import { jest } from "@jest/globals" +import type { AskApproval, HandleError } from "../../../shared/tools" // Import the types + +// Mock dependencies before importing the module under test +// Explicitly type the mock functions +const mockAskApproval = jest.fn() +const mockHandleError = jest.fn() // Explicitly type HandleError +const mockPushToolResult = jest.fn() +const mockRemoveClosingTag = jest.fn((_name: string, value: string | undefined) => value ?? "") // Simple mock +const mockGetModeBySlug = jest.fn() +// Define a minimal type for the resolved value +type MockClineInstance = { taskId: string } +// Make initClineWithTask return a mock Cline-like object with taskId, providing type hint +const mockInitClineWithTask = jest + .fn<() => Promise>() + .mockResolvedValue({ taskId: "mock-subtask-id" }) +const mockEmit = jest.fn() +const mockRecordToolError = jest.fn() +const mockSayAndCreateMissingParamError = jest.fn() + +// Mock the Cline instance and its methods/properties +const mockCline = { + ask: jest.fn(), + sayAndCreateMissingParamError: mockSayAndCreateMissingParamError, + emit: mockEmit, + recordToolError: mockRecordToolError, + consecutiveMistakeCount: 0, + isPaused: false, + pausedModeSlug: "ask", // Default or mock value + providerRef: { + deref: jest.fn(() => ({ + getState: jest.fn(() => ({ customModes: [], mode: "ask" })), // Mock provider state + handleModeSwitch: jest.fn(), + initClineWithTask: mockInitClineWithTask, + })), + }, +} + +// Mock other modules +jest.mock("delay", () => jest.fn(() => Promise.resolve())) // Mock delay to resolve immediately +jest.mock("../../../shared/modes", () => ({ + // Corrected path + getModeBySlug: mockGetModeBySlug, + defaultModeSlug: "ask", +})) +jest.mock("../../prompts/responses", () => ({ + // Corrected path + formatResponse: { + toolError: jest.fn((msg: string) => `Tool Error: ${msg}`), // Simple mock + }, +})) + +// Import the function to test AFTER mocks are set up +import { newTaskTool } from "../newTaskTool" +import type { ToolUse } from "../../../shared/tools" + +describe("newTaskTool", () => { + beforeEach(() => { + // Reset mocks before each test + jest.clearAllMocks() + mockAskApproval.mockResolvedValue(true) // Default to approved + mockGetModeBySlug.mockReturnValue({ slug: "code", name: "Code Mode" }) // Default valid mode + mockCline.consecutiveMistakeCount = 0 + mockCline.isPaused = false + }) + + it("should correctly un-escape \\\\@ to \\@ in the message passed to the new task", async () => { + const block: ToolUse = { + type: "tool_use", // Add required 'type' property + name: "new_task", // Correct property name + params: { + mode: "code", + message: "Review this: \\\\@file1.txt and also \\\\\\\\@file2.txt", // Input with \\@ and \\\\@ + }, + partial: false, + } + + await newTaskTool( + mockCline as any, // Use 'as any' for simplicity in mocking complex type + block, + mockAskApproval, // Now correctly typed + mockHandleError, + mockPushToolResult, + mockRemoveClosingTag, + ) + + // Verify askApproval was called + expect(mockAskApproval).toHaveBeenCalled() + + // Verify the message passed to initClineWithTask reflects the code's behavior in unit tests + expect(mockInitClineWithTask).toHaveBeenCalledWith( + "Review this: \\@file1.txt and also \\\\\\@file2.txt", // Unit Test Expectation: \\@ -> \@, \\\\@ -> \\\\@ + undefined, + mockCline, + ) + + // Verify side effects + expect(mockCline.emit).toHaveBeenCalledWith("taskSpawned", expect.any(String)) // Assuming initCline returns a mock task ID + expect(mockCline.isPaused).toBe(true) + expect(mockCline.emit).toHaveBeenCalledWith("taskPaused") + expect(mockPushToolResult).toHaveBeenCalledWith(expect.stringContaining("Successfully created new task")) + }) + + it("should not un-escape single escaped \@", async () => { + const block: ToolUse = { + type: "tool_use", // Add required 'type' property + name: "new_task", // Correct property name + params: { + mode: "code", + message: "This is already unescaped: \\@file1.txt", + }, + partial: false, + } + + await newTaskTool( + mockCline as any, + block, + mockAskApproval, // Now correctly typed + mockHandleError, + mockPushToolResult, + mockRemoveClosingTag, + ) + + expect(mockInitClineWithTask).toHaveBeenCalledWith( + "This is already unescaped: \\@file1.txt", // Expected: \@ remains \@ + undefined, + mockCline, + ) + }) + + it("should not un-escape non-escaped @", async () => { + const block: ToolUse = { + type: "tool_use", // Add required 'type' property + name: "new_task", // Correct property name + params: { + mode: "code", + message: "A normal mention @file1.txt", + }, + partial: false, + } + + await newTaskTool( + mockCline as any, + block, + mockAskApproval, // Now correctly typed + mockHandleError, + mockPushToolResult, + mockRemoveClosingTag, + ) + + expect(mockInitClineWithTask).toHaveBeenCalledWith( + "A normal mention @file1.txt", // Expected: @ remains @ + undefined, + mockCline, + ) + }) + + it("should handle mixed escaping scenarios", async () => { + const block: ToolUse = { + type: "tool_use", // Add required 'type' property + name: "new_task", // Correct property name + params: { + mode: "code", + message: "Mix: @file0.txt, \\@file1.txt, \\\\@file2.txt, \\\\\\\\@file3.txt", + }, + partial: false, + } + + await newTaskTool( + mockCline as any, + block, + mockAskApproval, // Now correctly typed + mockHandleError, + mockPushToolResult, + mockRemoveClosingTag, + ) + + expect(mockInitClineWithTask).toHaveBeenCalledWith( + "Mix: @file0.txt, \\@file1.txt, \\@file2.txt, \\\\\\@file3.txt", // Unit Test Expectation: @->@, \@->\@, \\@->\@, \\\\@->\\\\@ + undefined, + mockCline, + ) + }) + + // Add more tests for error handling (missing params, invalid mode, approval denied) if needed +}) diff --git a/src/core/tools/newTaskTool.ts b/src/core/tools/newTaskTool.ts index bdb6d9a009..25d5766d5d 100644 --- a/src/core/tools/newTaskTool.ts +++ b/src/core/tools/newTaskTool.ts @@ -42,6 +42,9 @@ export async function newTaskTool( } cline.consecutiveMistakeCount = 0 + // Un-escape one level of backslashes before '@' for hierarchical subtasks +// Un-escape one level: \\@ -> \@ (removes one backslash for hierarchical subtasks) + const unescapedMessage = message.replace(/\\\\@/g, "\\@") // Verify the mode exists const targetMode = getModeBySlug(mode, (await cline.providerRef.deref()?.getState())?.customModes) @@ -82,10 +85,10 @@ export async function newTaskTool( // Delay to allow mode change to take effect before next tool is executed. await delay(500) - const newCline = await provider.initClineWithTask(message, undefined, cline) + const newCline = await provider.initClineWithTask(unescapedMessage, undefined, cline) cline.emit("taskSpawned", newCline.taskId) - pushToolResult(`Successfully created new task in ${targetMode.name} mode with message: ${message}`) + pushToolResult(`Successfully created new task in ${targetMode.name} mode with message: ${unescapedMessage}`) // Set the isPaused flag to true so the parent // task can wait for the sub-task to finish. diff --git a/src/shared/__tests__/context-mentions.test.ts b/src/shared/__tests__/context-mentions.test.ts index cb070d4717..04246945ab 100644 --- a/src/shared/__tests__/context-mentions.test.ts +++ b/src/shared/__tests__/context-mentions.test.ts @@ -41,8 +41,15 @@ describe("mentionRegex and mentionRegexGlobal", () => { { input: "mention@", expected: null }, // Trailing @ { input: "@/path/trailing\\", expected: null }, // Trailing backslash (invalid escape) { input: "@/path/to/file\\not-a-space", expected: null }, // Backslash not followed by space + // Escaped mentions (should not match due to negative lookbehind) + { input: "This is not a mention: \\@/path/to/file.txt", expected: null }, + { input: "Escaped \\@problems word", expected: null }, + { input: "Text with \\@https://example.com", expected: null }, + { input: "Another \\@a1b2c3d hash", expected: null }, + { input: "Not escaped @terminal", expected: ["@terminal"] }, // Ensure non-escaped still works nearby + { input: "Double escape \\\\@/should/match", expected: null }, // Double backslash escapes the backslash, currently incorrectly fails to match + { input: "Text with \\@/escaped/path\\ with\\ spaces.txt", expected: null }, // Escaped mention with escaped spaces within the path part ] - testCases.forEach(({ input, expected }) => { it(`should handle input: "${input}"`, () => { // Test mentionRegex (first match) diff --git a/src/shared/context-mentions.ts b/src/shared/context-mentions.ts index fb7ba4723c..2edb99de6a 100644 --- a/src/shared/context-mentions.ts +++ b/src/shared/context-mentions.ts @@ -54,7 +54,7 @@ Mention regex: */ export const mentionRegex = - /@((?:\/|\w+:\/\/)(?:[^\s\\]|\\ )+?|[a-f0-9]{7,40}\b|problems\b|git-changes\b|terminal\b)(?=[.,;:!?]?(?=[\s\r\n]|$))/ + /(? Date: Thu, 12 Jun 2025 08:50:25 -0700 Subject: [PATCH 09/33] feat(tests): core tools integration tests (#4433) * feat(tests): add apply_diff tool tests * feat(tests): add tests for write_to_file tool functionality * feat(tests): add comprehensive tests for read_file tool functionality * feat(tests): add tests for execute_command tool functionality * feat(integration-tester): add integration testing role with comprehensive guidelines * feat(tests): enhance test runner with grep and specific file filtering * feat(tests): add comprehensive tests for search_files tool functionality * feat(tests): add comprehensive tests for list_files tool functionality * feat(tests): add tests for insert_content tool functionality * feat(tests): add comprehensive tests for search_and_replace tool functionality * feat(tests): add comprehensive tests for use_mcp_tool functionality * feat(tests): increase timeout values for various tool tests to improve reliability * fix(tests): add non-null assertion for workspaceDir assignment in multiple test files * feat(tests): enhance read_file tool tests with increased timeouts and improved prompts * feat(tests): enhance read_file tool tests to extract and verify tool results * feat(tests): enhance execute_command tool tests with additional context in prompts * refactor(tests): remove script execution test and related setup for execute_command tool * fix(tests): increase timeout for task start and completion in apply_diff and read_file tests * fix(tests): clarify error handling message in command execution test * refactor(tests): remove error handling test and related setup for execute_command tool * fix: update openRouterModelId to use anthropic/claude-3.5-sonnet * fix: update openRouterModelId to use openai/gpt-4.1 * fix(tests): increase timeouts for apply_diff, execute_command, and search_and_replace tests * fix(tests): disable terminal shell integration for execute_command tool tests * chore: rewrite integration tester mode * Update .roo/rules-integration-tester/1_workflow.xml Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> --------- Co-authored-by: Daniel Riccio Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com> Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> --- .roo/rules-integration-tester/1_workflow.xml | 198 ++++ .../2_test_patterns.xml | 303 ++++++ .../3_best_practices.xml | 104 ++ .../4_common_mistakes.xml | 109 ++ .../5_test_environment.xml | 209 ++++ .roomodes | 32 +- apps/vscode-e2e/src/runTest.ts | 34 +- apps/vscode-e2e/src/suite/index.ts | 36 +- .../src/suite/tools/apply-diff.test.ts | 753 ++++++++++++++ .../src/suite/tools/execute-command.test.ts | 561 +++++++++++ .../src/suite/tools/insert-content.test.ts | 625 ++++++++++++ .../src/suite/tools/list-files.test.ts | 459 +++++++++ .../src/suite/tools/read-file.test.ts | 781 +++++++++++++++ .../suite/tools/search-and-replace.test.ts | 631 ++++++++++++ .../src/suite/tools/search-files.test.ts | 931 ++++++++++++++++++ .../src/suite/tools/use-mcp-tool.test.ts | 925 +++++++++++++++++ .../src/suite/tools/write-to-file.test.ts | 445 +++++++++ 17 files changed, 7128 insertions(+), 8 deletions(-) create mode 100644 .roo/rules-integration-tester/1_workflow.xml create mode 100644 .roo/rules-integration-tester/2_test_patterns.xml create mode 100644 .roo/rules-integration-tester/3_best_practices.xml create mode 100644 .roo/rules-integration-tester/4_common_mistakes.xml create mode 100644 .roo/rules-integration-tester/5_test_environment.xml create mode 100644 apps/vscode-e2e/src/suite/tools/apply-diff.test.ts create mode 100644 apps/vscode-e2e/src/suite/tools/execute-command.test.ts create mode 100644 apps/vscode-e2e/src/suite/tools/insert-content.test.ts create mode 100644 apps/vscode-e2e/src/suite/tools/list-files.test.ts create mode 100644 apps/vscode-e2e/src/suite/tools/read-file.test.ts create mode 100644 apps/vscode-e2e/src/suite/tools/search-and-replace.test.ts create mode 100644 apps/vscode-e2e/src/suite/tools/search-files.test.ts create mode 100644 apps/vscode-e2e/src/suite/tools/use-mcp-tool.test.ts create mode 100644 apps/vscode-e2e/src/suite/tools/write-to-file.test.ts diff --git a/.roo/rules-integration-tester/1_workflow.xml b/.roo/rules-integration-tester/1_workflow.xml new file mode 100644 index 0000000000..b0ebc535e2 --- /dev/null +++ b/.roo/rules-integration-tester/1_workflow.xml @@ -0,0 +1,198 @@ + + + Understand Test Requirements + + Use ask_followup_question to determine what type of integration test is needed: + + + What type of integration test would you like me to create or work on? + + New E2E test for a specific feature or workflow + Fix or update an existing integration test + Create test utilities or helpers for common patterns + Debug failing integration tests + + + + + + + Gather Test Specifications + + Based on the test type, gather detailed requirements: + + For New E2E Tests: + - What specific user workflow or feature needs testing? + - What are the expected inputs and outputs? + - What edge cases or error scenarios should be covered? + - Are there specific API interactions to validate? + - What events should be monitored during the test? + + For Existing Test Issues: + - Which test file is failing or needs updates? + - What specific error messages or failures are occurring? + - What changes in the codebase might have affected the test? + + For Test Utilities: + - What common patterns are being repeated across tests? + - What helper functions would improve test maintainability? + + Use multiple ask_followup_question calls if needed to gather complete information. + + + + + Explore Existing Test Patterns + + Use codebase_search FIRST to understand existing test patterns and similar functionality: + + For New Tests: + - Search for similar test scenarios in apps/vscode-e2e/src/suite/ + - Find existing test utilities and helpers + - Identify patterns for the type of functionality being tested + + For Test Fixes: + - Search for the failing test file and related code + - Find similar working tests for comparison + - Look for recent changes that might have broken the test + + Example searches: + - "file creation test mocha" for file operation tests + - "task completion waitUntilCompleted" for task monitoring patterns + - "api message validation" for API interaction tests + + After codebase_search, use: + - read_file on relevant test files to understand structure + - list_code_definition_names on test directories + - search_files for specific test patterns or utilities + + + + + Analyze Test Environment and Setup + + Examine the test environment configuration: + + 1. Read the test runner configuration: + - apps/vscode-e2e/package.json for test scripts + - apps/vscode-e2e/src/runTest.ts for test setup + - Any test configuration files + + 2. Understand the test workspace setup: + - How test workspaces are created + - What files are available during tests + - How the extension API is accessed + + 3. Review existing test utilities: + - Helper functions for common operations + - Event listening patterns + - Assertion utilities + - Cleanup procedures + + Document findings including: + - Test environment structure + - Available utilities and helpers + - Common patterns and best practices + + + + + Design Test Structure + + Plan the test implementation based on gathered information: + + For New Tests: + - Define test suite structure with suite/test blocks + - Plan setup and teardown procedures + - Identify required test data and fixtures + - Design event listeners and validation points + - Plan for both success and failure scenarios + + For Test Fixes: + - Identify the root cause of the failure + - Plan the minimal changes needed to fix the issue + - Consider if the test needs to be updated due to code changes + - Plan for improved error handling or debugging + + Create a detailed test plan including: + - Test file structure and organization + - Required setup and cleanup + - Specific assertions and validations + - Error handling and edge cases + + + + + Implement Test Code + + Implement the test following established patterns: + + CRITICAL: Never write a test file with a single write_to_file call. + Always implement tests in parts: + + 1. Start with the basic test structure (suite, setup, teardown) + 2. Add individual test cases one by one + 3. Implement helper functions separately + 4. Add event listeners and validation logic incrementally + + Follow these implementation guidelines: + - Use suite() and test() blocks following Mocha TDD style + - Always use the global api object for extension interactions + - Implement proper async/await patterns with waitFor utility + - Use waitUntilCompleted and waitUntilAborted helpers for task monitoring + - Listen to and validate appropriate events (message, taskCompleted, etc.) + - Test both positive flows and error scenarios + - Validate message content using proper type assertions + - Create reusable test utilities when patterns emerge + - Use meaningful test descriptions that explain the scenario + - Always clean up tasks with cancelCurrentTask or clearCurrentTask + - Ensure tests are independent and can run in any order + + + + + Run and Validate Tests + + Execute the tests to ensure they work correctly: + + ALWAYS use the correct working directory and commands: + - Working directory: apps/vscode-e2e + - Test command: npm run test:run + - For specific tests: TEST_FILE="filename.test" npm run test:run + - Example: cd apps/vscode-e2e && TEST_FILE="apply-diff.test" npm run test:run + + Test execution process: + 1. Run the specific test file first + 2. Check for any failures or errors + 3. Analyze test output and logs + 4. Debug any issues found + 5. Re-run tests after fixes + + If tests fail: + - Add console.log statements to track execution flow + - Log important events like task IDs, file paths, and AI responses + - Check test output carefully for error messages and stack traces + - Verify file creation in correct workspace directories + - Ensure proper event handling and timeouts + + + + + Document and Complete + + Finalize the test implementation: + + 1. Add comprehensive comments explaining complex test logic + 2. Document any new test utilities or patterns created + 3. Ensure test descriptions clearly explain what is being tested + 4. Verify all cleanup procedures are in place + 5. Confirm tests can run independently and in any order + + Provide the user with: + - Summary of tests created or fixed + - Instructions for running the tests + - Any new patterns or utilities that can be reused + - Recommendations for future test improvements + + + \ No newline at end of file diff --git a/.roo/rules-integration-tester/2_test_patterns.xml b/.roo/rules-integration-tester/2_test_patterns.xml new file mode 100644 index 0000000000..62bef1631b --- /dev/null +++ b/.roo/rules-integration-tester/2_test_patterns.xml @@ -0,0 +1,303 @@ + + + Standard Mocha TDD structure for integration tests + + Basic Test Suite Structure + + ```typescript + import { suite, test, suiteSetup, suiteTeardown } from 'mocha'; + import * as assert from 'assert'; + import * as vscode from 'vscode'; + import { waitFor, waitUntilCompleted, waitUntilAborted } from '../utils/testUtils'; + + suite('Feature Name Tests', () => { + let testWorkspaceDir: string; + let testFiles: { [key: string]: string } = {}; + + suiteSetup(async () => { + // Setup test workspace and files + testWorkspaceDir = vscode.workspace.workspaceFolders![0].uri.fsPath; + // Create test files in workspace + }); + + suiteTeardown(async () => { + // Cleanup test files and tasks + await api.cancelCurrentTask(); + }); + + test('should perform specific functionality', async () => { + // Test implementation + }); + }); + ``` + + + + + Event Listening Pattern + + ```typescript + test('should handle task completion events', async () => { + const events: any[] = []; + + const messageListener = (message: any) => { + events.push({ type: 'message', data: message }); + }; + + const taskCompletedListener = (result: any) => { + events.push({ type: 'taskCompleted', data: result }); + }; + + api.onDidReceiveMessage(messageListener); + api.onTaskCompleted(taskCompletedListener); + + try { + // Perform test actions + await api.startTask('test prompt'); + await waitUntilCompleted(); + + // Validate events + assert(events.some(e => e.type === 'taskCompleted')); + } finally { + // Cleanup listeners + api.onDidReceiveMessage(() => {}); + api.onTaskCompleted(() => {}); + } + }); + ``` + + + + + File Creation Test Pattern + + ```typescript + test('should create files in workspace', async () => { + const fileName = 'test-file.txt'; + const expectedContent = 'test content'; + + await api.startTask(`Create a file named ${fileName} with content: ${expectedContent}`); + await waitUntilCompleted(); + + // Check multiple possible locations + const possiblePaths = [ + path.join(testWorkspaceDir, fileName), + path.join(process.cwd(), fileName), + // Add other possible locations + ]; + + let fileFound = false; + let actualContent = ''; + + for (const filePath of possiblePaths) { + if (fs.existsSync(filePath)) { + actualContent = fs.readFileSync(filePath, 'utf8'); + fileFound = true; + break; + } + } + + assert(fileFound, `File ${fileName} not found in any expected location`); + assert.strictEqual(actualContent.trim(), expectedContent); + }); + ``` + + + + + + + Basic Task Execution + + ```typescript + // Start a task and wait for completion + await api.startTask('Your prompt here'); + await waitUntilCompleted(); + ``` + + + + + Task with Auto-Approval Settings + + ```typescript + // Enable auto-approval for specific actions + await api.updateSettings({ + alwaysAllowWrite: true, + alwaysAllowExecute: true + }); + + await api.startTask('Create and execute a script'); + await waitUntilCompleted(); + ``` + + + + + Message Validation + + ```typescript + const messages: any[] = []; + api.onDidReceiveMessage((message) => { + messages.push(message); + }); + + await api.startTask('test prompt'); + await waitUntilCompleted(); + + // Validate specific message types + const toolMessages = messages.filter(m => + m.type === 'say' && m.say === 'api_req_started' + ); + assert(toolMessages.length > 0, 'Expected tool execution messages'); + ``` + + + + + + + Task Abortion Handling + + ```typescript + test('should handle task abortion', async () => { + await api.startTask('long running task'); + + // Abort after short delay + setTimeout(() => api.abortTask(), 1000); + + await waitUntilAborted(); + + // Verify task was properly aborted + const status = await api.getTaskStatus(); + assert.strictEqual(status, 'aborted'); + }); + ``` + + + + + Error Message Validation + + ```typescript + test('should handle invalid input gracefully', async () => { + const errorMessages: any[] = []; + + api.onDidReceiveMessage((message) => { + if (message.type === 'error' || message.text?.includes('error')) { + errorMessages.push(message); + } + }); + + await api.startTask('invalid prompt that should fail'); + await waitFor(() => errorMessages.length > 0, 5000); + + assert(errorMessages.length > 0, 'Expected error messages'); + }); + ``` + + + + + + + File Location Helper + + ```typescript + function findFileInWorkspace(fileName: string, workspaceDir: string): string | null { + const possiblePaths = [ + path.join(workspaceDir, fileName), + path.join(process.cwd(), fileName), + path.join(os.tmpdir(), fileName), + // Add other common locations + ]; + + for (const filePath of possiblePaths) { + if (fs.existsSync(filePath)) { + return filePath; + } + } + + return null; + } + ``` + + + + + Event Collection Helper + + ```typescript + class EventCollector { + private events: any[] = []; + + constructor(private api: any) { + this.setupListeners(); + } + + private setupListeners() { + this.api.onDidReceiveMessage((message: any) => { + this.events.push({ type: 'message', timestamp: Date.now(), data: message }); + }); + + this.api.onTaskCompleted((result: any) => { + this.events.push({ type: 'taskCompleted', timestamp: Date.now(), data: result }); + }); + } + + getEvents(type?: string) { + return type ? this.events.filter(e => e.type === type) : this.events; + } + + clear() { + this.events = []; + } + } + ``` + + + + + + + Comprehensive Logging + + ```typescript + test('should log execution flow for debugging', async () => { + console.log('Starting test execution'); + + const events: any[] = []; + api.onDidReceiveMessage((message) => { + console.log('Received message:', JSON.stringify(message, null, 2)); + events.push(message); + }); + + console.log('Starting task with prompt'); + await api.startTask('test prompt'); + + console.log('Waiting for task completion'); + await waitUntilCompleted(); + + console.log('Task completed, events received:', events.length); + console.log('Final workspace state:', fs.readdirSync(testWorkspaceDir)); + }); + ``` + + + + + State Validation + + ```typescript + function validateTestState(description: string) { + console.log(`=== ${description} ===`); + console.log('Workspace files:', fs.readdirSync(testWorkspaceDir)); + console.log('Current working directory:', process.cwd()); + console.log('Task status:', api.getTaskStatus?.() || 'unknown'); + console.log('========================'); + } + ``` + + + + \ No newline at end of file diff --git a/.roo/rules-integration-tester/3_best_practices.xml b/.roo/rules-integration-tester/3_best_practices.xml new file mode 100644 index 0000000000..e495ea5f0a --- /dev/null +++ b/.roo/rules-integration-tester/3_best_practices.xml @@ -0,0 +1,104 @@ + + + - Always use suite() and test() blocks following Mocha TDD style + - Use descriptive test names that explain the scenario being tested + - Implement proper setup and teardown in suiteSetup() and suiteTeardown() + - Create test files in the VSCode workspace directory during suiteSetup() + - Store file paths in a test-scoped object for easy reference across tests + - Ensure tests are independent and can run in any order + - Clean up all test files and tasks in suiteTeardown() to avoid test pollution + + + + - Always use the global api object for extension interactions + - Implement proper async/await patterns with the waitFor utility + - Use waitUntilCompleted and waitUntilAborted helpers for task monitoring + - Set appropriate auto-approval settings (alwaysAllowWrite, alwaysAllowExecute) for the functionality being tested + - Listen to and validate appropriate events (message, taskCompleted, taskAborted, etc.) + - Always clean up tasks with cancelCurrentTask or clearCurrentTask after tests + - Use meaningful timeouts that account for actual task execution time + + + + - Be aware that files may be created in the workspace directory (/tmp/roo-test-workspace-*) rather than expected locations + - Always check multiple possible file locations when verifying file creation + - Use flexible file location checking that searches workspace directories + - Verify files exist after creation to catch setup issues early + - Account for the fact that the workspace directory is created by runTest.ts + - The AI may use internal tools instead of the documented tools - verify outcomes rather than methods + + + + - Add multiple event listeners (taskStarted, taskCompleted, taskAborted) for better debugging + - Don't rely on parsing AI messages to detect tool usage - the AI's message format may vary + - Use terminal shell execution events (onDidStartTerminalShellExecution, onDidEndTerminalShellExecution) for command tracking + - Tool executions are reported via api_req_started messages with type="say" and say="api_req_started" + - Focus on testing outcomes (files created, commands executed) rather than message parsing + - There is no "tool_result" message type - tool results appear in "completion_result" or "text" messages + + + + - Test both positive flows and error scenarios + - Validate message content using proper type assertions + - Implement proper error handling and edge cases + - Use try-catch blocks around critical test operations + - Log important events like task IDs, file paths, and AI responses for debugging + - Check test output carefully for error messages and stack traces + + + + - Remove unnecessary waits for specific tool executions - wait for task completion instead + - Simplify message handlers to only capture essential error information + - Use the simplest possible test structure that verifies the outcome + - Avoid complex message parsing logic that depends on AI behavior + - Terminal events are more reliable than message parsing for command execution verification + - Keep prompts simple and direct - complex instructions may confuse the AI + + + + - Add console.log statements to track test execution flow + - Log important events like task IDs, file paths, and AI responses + - Use codebase_search first to find similar test patterns before writing new tests + - Create helper functions for common file location checks + - Use descriptive variable names for file paths and content + - Always log the expected vs actual locations when tests fail + - Add comprehensive comments explaining complex test logic + + + + - Create reusable test utilities when patterns emerge + - Implement helper functions for common operations like file finding + - Use event collection utilities for consistent event handling + - Create assertion helpers for common validation patterns + - Document any new test utilities or patterns created + - Share common utilities across test files to reduce duplication + + + + - Keep prompts simple and direct - complex instructions may lead to unexpected behavior + - Allow for variations in how the AI accomplishes tasks + - The AI may not always use the exact tool you specify in the prompt + - Be prepared to adapt tests based on actual AI behavior rather than expected behavior + - The AI may interpret instructions creatively - test results rather than implementation details + - The AI will not see the files in the workspace directory, you must tell it to assume they exist and proceed + + + + - ALWAYS use the correct working directory: apps/vscode-e2e + - The test command is: npm run test:run + - To run specific tests use environment variable: TEST_FILE="filename.test" npm run test:run + - Example: cd apps/vscode-e2e && TEST_FILE="apply-diff.test" npm run test:run + - Never use npm test directly as it doesn't exist + - Always check available scripts with npm run if unsure + - Run tests incrementally during development to catch issues early + + + + - Never write a test file with a single write_to_file tool call + - Always implement tests in parts: structure first, then individual test cases + - Group related tests in the same suite + - Use consistent naming conventions for test files and functions + - Separate test utilities into their own files when they become substantial + - Follow the existing project structure and conventions + + \ No newline at end of file diff --git a/.roo/rules-integration-tester/4_common_mistakes.xml b/.roo/rules-integration-tester/4_common_mistakes.xml new file mode 100644 index 0000000000..88a7473643 --- /dev/null +++ b/.roo/rules-integration-tester/4_common_mistakes.xml @@ -0,0 +1,109 @@ + + + - Writing a test file with a single write_to_file tool call instead of implementing in parts + - Not using proper Mocha TDD structure with suite() and test() blocks + - Forgetting to implement suiteSetup() and suiteTeardown() for proper cleanup + - Creating tests that depend on each other or specific execution order + - Not cleaning up tasks and files after test completion + - Using describe/it blocks instead of the required suite/test blocks + + + + - Not using the global api object for extension interactions + - Forgetting to set auto-approval settings (alwaysAllowWrite, alwaysAllowExecute) when testing functionality that requires user approval + - Not implementing proper async/await patterns with waitFor utilities + - Using incorrect timeout values that are too short for actual task execution + - Not properly cleaning up tasks with cancelCurrentTask or clearCurrentTask + - Assuming the AI will use specific tools instead of testing outcomes + + + + - Assuming files will be created in the expected location without checking multiple paths + - Not accounting for the workspace directory being created by runTest.ts + - Creating test files in temporary directories instead of the VSCode workspace directory + - Not verifying files exist after creation during setup + - Forgetting that the AI may not see files in the workspace directory + - Not using flexible file location checking that searches workspace directories + + + + - Relying on parsing AI messages to detect tool usage instead of using proper event listeners + - Expecting tool results in "tool_result" message type (which doesn't exist) + - Not listening to terminal shell execution events for command tracking + - Depending on specific message formats that may vary + - Not implementing proper event cleanup after tests + - Parsing complex AI conversation messages instead of focusing on outcomes + + + + - Using npm test instead of npm run test:run + - Not using the correct working directory (apps/vscode-e2e) + - Running tests from the wrong directory + - Not checking available scripts with npm run when unsure + - Forgetting to use TEST_FILE environment variable for specific tests + - Not running tests incrementally during development + + + + - Not adding sufficient logging to track test execution flow + - Not logging important events like task IDs, file paths, and AI responses + - Not using codebase_search to find similar test patterns before writing new tests + - Not checking test output carefully for error messages and stack traces + - Not validating test state at critical points + - Assuming test failures are due to code issues without checking test logic + + + + - Using complex instructions that may confuse the AI + - Expecting the AI to use exact tools specified in prompts + - Not allowing for variations in how the AI accomplishes tasks + - Testing implementation details instead of outcomes + - Not adapting tests based on actual AI behavior + - Forgetting to tell the AI to assume files exist in the workspace directory + + + + - Adding unnecessary waits for specific tool executions + - Using complex message parsing logic that depends on AI behavior + - Not using the simplest possible test structure + - Depending on specific AI message formats + - Not using terminal events for reliable command execution verification + - Making tests too brittle by depending on exact AI responses + + + + - Not understanding that files may be created in /tmp/roo-test-workspace-* directories + - Assuming the AI can see files in the workspace directory + - Not checking multiple possible file locations when verifying creation + - Creating files outside the VSCode workspace during tests + - Not properly setting up the test workspace in suiteSetup() + - Forgetting to clean up workspace files in suiteTeardown() + + + + - Expecting specific message types for tool execution results + - Not understanding that ClineMessage types have specific values + - Trying to parse tool execution from AI conversation messages + - Not checking packages/types/src/message.ts for valid message types + - Depending on message parsing instead of outcome verification + - Not using api_req_started messages to verify tool execution + + + + - Using timeouts that are too short for actual task execution + - Not accounting for AI processing time in test timeouts + - Waiting for specific tool executions instead of task completion + - Not implementing proper retry logic for flaky operations + - Using fixed delays instead of condition-based waiting + - Not considering that some operations may take longer in CI environments + + + + - Not creating test files in the correct workspace directory + - Using hardcoded paths that don't work across different environments + - Not storing file paths in test-scoped objects for easy reference + - Creating test data that conflicts with other tests + - Not cleaning up test data properly after tests complete + - Using test data that's too complex for the AI to handle reliably + + \ No newline at end of file diff --git a/.roo/rules-integration-tester/5_test_environment.xml b/.roo/rules-integration-tester/5_test_environment.xml new file mode 100644 index 0000000000..8e872b1dfc --- /dev/null +++ b/.roo/rules-integration-tester/5_test_environment.xml @@ -0,0 +1,209 @@ + + + VSCode E2E testing framework using Mocha and VSCode Test + + - Mocha TDD framework for test structure + - VSCode Test framework for extension testing + - Custom test utilities and helpers + - Event-driven testing patterns + - Workspace-based test execution + + + + + apps/vscode-e2e/src/suite/ + apps/vscode-e2e/src/utils/ + apps/vscode-e2e/src/runTest.ts + apps/vscode-e2e/package.json + packages/types/ + + + + apps/vscode-e2e + + npm run test:run + TEST_FILE="filename.test" npm run test:run + cd apps/vscode-e2e && TEST_FILE="apply-diff.test" npm run test:run + npm run + + + - Never use npm test directly as it doesn't exist + - Always use the correct working directory + - Use TEST_FILE environment variable for specific tests + - Check available scripts with npm run if unsure + + + + + Global api object for extension interactions + + + - api.startTask(prompt: string): Start a new task + - api.cancelCurrentTask(): Cancel the current task + - api.clearCurrentTask(): Clear the current task + - api.abortTask(): Abort the current task + - api.getTaskStatus(): Get current task status + + + - api.onDidReceiveMessage(callback): Listen to messages + - api.onTaskCompleted(callback): Listen to task completion + - api.onTaskAborted(callback): Listen to task abortion + - api.onTaskStarted(callback): Listen to task start + - api.onDidStartTerminalShellExecution(callback): Terminal start events + - api.onDidEndTerminalShellExecution(callback): Terminal end events + + + - api.updateSettings(settings): Update extension settings + - api.getSettings(): Get current settings + + + + + + + + Wait for a condition to be true + await waitFor(() => condition, timeout) + await waitFor(() => fs.existsSync(filePath), 5000) + + + Wait until current task is completed + await waitUntilCompleted() + Default timeout for task completion + + + Wait until current task is aborted + await waitUntilAborted() + Default timeout for task abortion + + + + + + Helper to find files in multiple possible locations + Use when files might be created in different workspace directories + + + Utility to collect and analyze events during test execution + Use for comprehensive event tracking and validation + + + Custom assertion functions for common test patterns + Use for consistent validation across tests + + + + + + + Test workspaces are created by runTest.ts + /tmp/roo-test-workspace-* + vscode.workspace.workspaceFolders![0].uri.fsPath + + + + Create all test files in suiteSetup() before any tests run + Always create files in the VSCode workspace directory + Verify files exist after creation to catch setup issues early + Clean up all test files in suiteTeardown() to avoid test pollution + Store file paths in a test-scoped object for easy reference + + + + The AI will not see the files in the workspace directory + Tell the AI to assume files exist and proceed as if they do + Always verify outcomes rather than relying on AI file visibility + + + + + Understanding message types for proper event handling + Check packages/types/src/message.ts for valid message types + + + + say + api_req_started + Indicates tool execution started + JSON with tool name and execution details + Most reliable way to verify tool execution + + + + Contains tool execution results + Tool results appear here, not in "tool_result" type + + + + General AI conversation messages + Format may vary, don't rely on parsing these for tool detection + + + + + + Settings to enable automatic approval of AI actions + + Enable for file creation/modification tests + Enable for command execution tests + Enable for browser-related tests + + + ```typescript + await api.updateSettings({ + alwaysAllowWrite: true, + alwaysAllowExecute: true + }); + ``` + + Without proper auto-approval settings, the AI won't be able to perform actions without user approval + + + + + Use console.log for tracking test execution flow + + - Log test phase transitions + - Log important events and data + - Log file paths and workspace state + - Log expected vs actual outcomes + + + + + Helper functions to validate test state at critical points + + - Workspace file listing + - Current working directory + - Task status + - Event counts + + + + + Tools for analyzing test failures + + - Stack trace analysis + - Event timeline reconstruction + - File system state comparison + - Message flow analysis + + + + + + + Appropriate timeout values for different operations + Use generous timeouts for task completion (30+ seconds) + Shorter timeouts for file system operations (5-10 seconds) + Medium timeouts for event waiting (10-15 seconds) + + + + Proper cleanup to avoid resource leaks + Always clean up event listeners after tests + Cancel or clear tasks in teardown + Remove test files to avoid disk space issues + + + \ No newline at end of file diff --git a/.roomodes b/.roomodes index 637610f113..7cba92c64e 100644 --- a/.roomodes +++ b/.roomodes @@ -145,7 +145,36 @@ customModes: - command - mcp source: project - + - slug: integration-tester + name: 🧪 Integration Tester + roleDefinition: >- + You are Roo, an integration testing specialist focused on VSCode E2E tests with expertise in: + - Writing and maintaining integration tests using Mocha and VSCode Test framework + - Testing Roo Code API interactions and event-driven workflows + - Creating complex multi-step task scenarios and mode switching sequences + - Validating message formats, API responses, and event emission patterns + - Test data generation and fixture management + - Coverage analysis and test scenario identification + + Your focus is on ensuring comprehensive integration test coverage for the Roo Code extension, working primarily with: + - E2E test files in apps/vscode-e2e/src/suite/ + - Test utilities and helpers + - API type definitions in packages/types/ + - Extension API testing patterns + + You ensure integration tests are: + - Comprehensive and cover critical user workflows + - Following established Mocha TDD patterns + - Using async/await with proper timeout handling + - Validating both success and failure scenarios + - Properly typed with TypeScript + groups: + - read + - command + - - edit + - fileRegex: (apps/vscode-e2e/.*\.(ts|js)$|packages/types/.*\.ts$) + description: E2E test files, test utilities, and API type definitions + source: project - slug: pr-reviewer name: 🔍 PR Reviewer roleDefinition: >- @@ -168,4 +197,3 @@ customModes: - mcp - command source: project - diff --git a/apps/vscode-e2e/src/runTest.ts b/apps/vscode-e2e/src/runTest.ts index 86f9e94a36..2e8b262a49 100644 --- a/apps/vscode-e2e/src/runTest.ts +++ b/apps/vscode-e2e/src/runTest.ts @@ -1,4 +1,6 @@ import * as path from "path" +import * as os from "os" +import * as fs from "fs/promises" import { runTests } from "@vscode/test-electron" @@ -12,10 +14,36 @@ async function main() { // Passed to --extensionTestsPath const extensionTestsPath = path.resolve(__dirname, "./suite/index") + // Create a temporary workspace folder for tests + const testWorkspace = await fs.mkdtemp(path.join(os.tmpdir(), "roo-test-workspace-")) + + // Get test filter from command line arguments or environment variable + // Usage examples: + // - npm run test:e2e -- --grep "write-to-file" + // - TEST_GREP="apply-diff" npm run test:e2e + // - TEST_FILE="task.test.js" npm run test:e2e + const testGrep = process.argv.find((arg, i) => process.argv[i - 1] === "--grep") || process.env.TEST_GREP + const testFile = process.argv.find((arg, i) => process.argv[i - 1] === "--file") || process.env.TEST_FILE + + // Pass test filters as environment variables to the test runner + const extensionTestsEnv = { + ...process.env, + ...(testGrep && { TEST_GREP: testGrep }), + ...(testFile && { TEST_FILE: testFile }), + } + // Download VS Code, unzip it and run the integration test - await runTests({ extensionDevelopmentPath, extensionTestsPath }) - } catch { - console.error("Failed to run tests") + await runTests({ + extensionDevelopmentPath, + extensionTestsPath, + launchArgs: [testWorkspace], + extensionTestsEnv, + }) + + // Clean up the temporary workspace + await fs.rm(testWorkspace, { recursive: true, force: true }) + } catch (error) { + console.error("Failed to run tests", error) process.exit(1) } } diff --git a/apps/vscode-e2e/src/suite/index.ts b/apps/vscode-e2e/src/suite/index.ts index b6f0fa9bed..04c36a34e1 100644 --- a/apps/vscode-e2e/src/suite/index.ts +++ b/apps/vscode-e2e/src/suite/index.ts @@ -27,10 +27,40 @@ export async function run() { globalThis.api = api - // Add all the tests to the runner. - const mocha = new Mocha({ ui: "tdd", timeout: 300_000 }) + // Configure Mocha with grep pattern if provided + const mochaOptions: Mocha.MochaOptions = { + ui: "tdd", + timeout: 300_000, + } + + // Apply grep filter if TEST_GREP is set + if (process.env.TEST_GREP) { + mochaOptions.grep = process.env.TEST_GREP + console.log(`Running tests matching pattern: ${process.env.TEST_GREP}`) + } + + const mocha = new Mocha(mochaOptions) const cwd = path.resolve(__dirname, "..") - ;(await glob("**/**.test.js", { cwd })).forEach((testFile) => mocha.addFile(path.resolve(cwd, testFile))) + + // Get test files based on filter + let testFiles: string[] + if (process.env.TEST_FILE) { + // Run specific test file + const specificFile = process.env.TEST_FILE.endsWith(".js") + ? process.env.TEST_FILE + : `${process.env.TEST_FILE}.js` + testFiles = await glob(`**/${specificFile}`, { cwd }) + console.log(`Running specific test file: ${specificFile}`) + } else { + // Run all test files + testFiles = await glob("**/**.test.js", { cwd }) + } + + if (testFiles.length === 0) { + throw new Error(`No test files found matching criteria: ${process.env.TEST_FILE || "all tests"}`) + } + + testFiles.forEach((testFile) => mocha.addFile(path.resolve(cwd, testFile))) // Let's go! return new Promise((resolve, reject) => diff --git a/apps/vscode-e2e/src/suite/tools/apply-diff.test.ts b/apps/vscode-e2e/src/suite/tools/apply-diff.test.ts new file mode 100644 index 0000000000..ac8ffa6f58 --- /dev/null +++ b/apps/vscode-e2e/src/suite/tools/apply-diff.test.ts @@ -0,0 +1,753 @@ +import * as assert from "assert" +import * as fs from "fs/promises" +import * as path from "path" +import * as vscode from "vscode" + +import type { ClineMessage } from "@roo-code/types" + +import { waitFor, sleep } from "../utils" + +suite("Roo Code apply_diff Tool", () => { + let workspaceDir: string + + // Pre-created test files that will be used across tests + const testFiles = { + simpleModify: { + name: `test-file-simple-${Date.now()}.txt`, + content: "Hello World\nThis is a test file\nWith multiple lines", + path: "", + }, + multipleReplace: { + name: `test-func-multiple-${Date.now()}.js`, + content: `function calculate(x, y) { + const sum = x + y + const product = x * y + return { sum: sum, product: product } +}`, + path: "", + }, + lineNumbers: { + name: `test-lines-${Date.now()}.js`, + content: `// Header comment +function oldFunction() { + console.log("Old implementation") +} + +// Another function +function keepThis() { + console.log("Keep this") +} + +// Footer comment`, + path: "", + }, + errorHandling: { + name: `test-error-${Date.now()}.txt`, + content: "Original content", + path: "", + }, + multiSearchReplace: { + name: `test-multi-search-${Date.now()}.js`, + content: `function processData(data) { + console.log("Processing data") + return data.map(item => item * 2) +} + +// Some other code in between +const config = { + timeout: 5000, + retries: 3 +} + +function validateInput(input) { + console.log("Validating input") + if (!input) { + throw new Error("Invalid input") + } + return true +}`, + path: "", + }, + } + + // Get the actual workspace directory that VSCode is using and create all test files + suiteSetup(async function () { + // Get the workspace folder from VSCode + const workspaceFolders = vscode.workspace.workspaceFolders + if (!workspaceFolders || workspaceFolders.length === 0) { + throw new Error("No workspace folder found") + } + workspaceDir = workspaceFolders[0]!.uri.fsPath + console.log("Using workspace directory:", workspaceDir) + + // Create all test files before any tests run + console.log("Creating test files in workspace...") + for (const [key, file] of Object.entries(testFiles)) { + file.path = path.join(workspaceDir, file.name) + await fs.writeFile(file.path, file.content) + console.log(`Created ${key} test file at:`, file.path) + } + + // Verify all files exist + for (const [key, file] of Object.entries(testFiles)) { + const exists = await fs + .access(file.path) + .then(() => true) + .catch(() => false) + if (!exists) { + throw new Error(`Failed to create ${key} test file at ${file.path}`) + } + } + }) + + // Clean up after all tests + suiteTeardown(async () => { + // Cancel any running tasks before cleanup + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Clean up all test files + console.log("Cleaning up test files...") + for (const [key, file] of Object.entries(testFiles)) { + try { + await fs.unlink(file.path) + console.log(`Cleaned up ${key} test file`) + } catch (error) { + console.log(`Failed to clean up ${key} test file:`, error) + } + } + }) + + // Clean up before each test + setup(async () => { + // Cancel any previous task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + // Clean up after each test + teardown(async () => { + // Cancel the current task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + test("Should apply diff to modify existing file content", async function () { + // Increase timeout for this specific test + + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.simpleModify + const expectedContent = "Hello Universe\nThis is a test file\nWith multiple lines" + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let applyDiffExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if (message.type === "say" && (message.say === "completion_result" || message.say === "text")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("apply_diff")) { + applyDiffExecuted = true + console.log("apply_diff tool executed!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with apply_diff instruction - file already exists + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use apply_diff on the file ${testFile.name} to change "Hello World" to "Hello Universe". The file already exists with this content: +${testFile.content}\nAssume the file exists and you can modify it directly.`, + }) //Temporary meassure since list_files ignores all the files inside a tmp workspace + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 60_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check if the file was modified correctly + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after modification:", actualContent) + + // Verify tool was executed + assert.strictEqual(applyDiffExecuted, true, "apply_diff tool should have been executed") + + // Verify file content + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "File content should be modified correctly", + ) + + console.log("Test passed! apply_diff tool executed and file modified successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should apply multiple search/replace blocks in single diff", async function () { + // Increase timeout for this specific test + + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.multipleReplace + const expectedContent = `function compute(a, b) { + const total = a + b + const result = a * b + return { total: total, result: result } +}` + let taskStarted = false + let taskCompleted = false + let applyDiffExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if (message.type === "say" && message.text) { + console.log("AI response:", message.text.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("apply_diff")) { + applyDiffExecuted = true + console.log("apply_diff tool executed!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with multiple replacements - file already exists + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use apply_diff on the file ${testFile.name} to make ALL of these changes: +1. Rename function "calculate" to "compute" +2. Rename parameters "x, y" to "a, b" +3. Rename variable "sum" to "total" (including in the return statement) +4. Rename variable "product" to "result" (including in the return statement) +5. In the return statement, change { sum: sum, product: product } to { total: total, result: result } + +The file already exists with this content: +${testFile.content}\nAssume the file exists and you can modify it directly.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 60_000 }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check the file was modified correctly + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after modification:", actualContent) + + // Verify tool was executed + assert.strictEqual(applyDiffExecuted, true, "apply_diff tool should have been executed") + + // Verify file content + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "All replacements should be applied correctly", + ) + + console.log("Test passed! apply_diff tool executed and multiple replacements applied successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should handle apply_diff with line number hints", async function () { + // Increase timeout for this specific test + + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.lineNumbers + const expectedContent = `// Header comment +function newFunction() { + console.log("New implementation") +} + +// Another function +function keepThis() { + console.log("Keep this") +} + +// Footer comment` + + let taskStarted = false + let taskCompleted = false + let applyDiffExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("apply_diff")) { + applyDiffExecuted = true + console.log("apply_diff tool executed!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with line number context - file already exists + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use apply_diff on the file ${testFile.name} to change "oldFunction" to "newFunction" and update its console.log to "New implementation". Keep the rest of the file unchanged. + +The file already exists with this content: +${testFile.content}\nAssume the file exists and you can modify it directly.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 60_000 }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check the file was modified correctly + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after modification:", actualContent) + + // Verify tool was executed + assert.strictEqual(applyDiffExecuted, true, "apply_diff tool should have been executed") + + // Verify file content + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "Only specified function should be modified", + ) + + console.log("Test passed! apply_diff tool executed and targeted modification successful") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should handle apply_diff errors gracefully", async function () { + // Increase timeout for this specific test + this.timeout(90_000) + + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.errorHandling + let taskStarted = false + let taskCompleted = false + let errorDetected = false + let applyDiffAttempted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for error messages + if (message.type === "say" && message.say === "error") { + errorDetected = true + console.log("Error detected:", message.text) + } + + // Check if AI mentions it couldn't find the content + if (message.type === "say" && message.text?.toLowerCase().includes("could not find")) { + errorDetected = true + console.log("AI reported search failure:", message.text) + } + + // Check for tool execution attempt + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("apply_diff")) { + applyDiffAttempted = true + console.log("apply_diff tool attempted!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with invalid search content - file already exists + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use apply_diff on the file ${testFile.name} to replace "This content does not exist" with "New content". + +The file already exists with this content: +${testFile.content} + +IMPORTANT: The search pattern "This content does not exist" is NOT in the file. When apply_diff cannot find the search pattern, it should fail gracefully and the file content should remain unchanged. Do NOT try to use write_to_file or any other tool to modify the file. Only use apply_diff, and if the search pattern is not found, report that it could not be found. + +Assume the file exists and you can modify it directly.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 90_000 }) + + // Wait for task completion or error + await waitFor(() => taskCompleted || errorDetected, { timeout: 90_000 }) + + // Give time for any final operations + await sleep(2000) + + // The file content should remain unchanged since the search pattern wasn't found + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after task:", actualContent) + + // The AI should have attempted to use apply_diff + assert.strictEqual(applyDiffAttempted, true, "apply_diff tool should have been attempted") + + // The content should remain unchanged since the search pattern wasn't found + assert.strictEqual( + actualContent.trim(), + testFile.content.trim(), + "File content should remain unchanged when search pattern not found", + ) + + console.log("Test passed! apply_diff attempted and error handled gracefully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should apply multiple search/replace blocks to edit two separate functions", async function () { + // Increase timeout for this specific test + this.timeout(60_000) + + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.multiSearchReplace + const expectedContent = `function transformData(data) { + console.log("Transforming data") + return data.map(item => item * 2) +} + +// Some other code in between +const config = { + timeout: 5000, + retries: 3 +} + +function checkInput(input) { + console.log("Checking input") + if (!input) { + throw new Error("Invalid input") + } + return true +}` + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let applyDiffExecuted = false + let applyDiffCount = 0 + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if (message.type === "say" && (message.say === "completion_result" || message.say === "text")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("apply_diff")) { + applyDiffExecuted = true + applyDiffCount++ + console.log(`apply_diff tool executed! (count: ${applyDiffCount})`) + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with instruction to edit two separate functions using multiple search/replace blocks + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use apply_diff on the file ${testFile.name} to make these changes. You MUST use TWO SEPARATE search/replace blocks within a SINGLE apply_diff call: + +FIRST search/replace block: Edit the processData function to rename it to "transformData" and change "Processing data" to "Transforming data" + +SECOND search/replace block: Edit the validateInput function to rename it to "checkInput" and change "Validating input" to "Checking input" + +Important: Use multiple SEARCH/REPLACE blocks in one apply_diff call, NOT multiple apply_diff calls. Each function should have its own search/replace block. + +The file already exists with this content: +${testFile.content} + +Assume the file exists and you can modify it directly.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 60_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check if the file was modified correctly + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after modification:", actualContent) + + // Verify tool was executed + assert.strictEqual(applyDiffExecuted, true, "apply_diff tool should have been executed") + console.log(`apply_diff was executed ${applyDiffCount} time(s)`) + + // Verify file content + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "Both functions should be modified with separate search/replace blocks", + ) + + console.log("Test passed! apply_diff tool executed and multiple search/replace blocks applied successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) +}) diff --git a/apps/vscode-e2e/src/suite/tools/execute-command.test.ts b/apps/vscode-e2e/src/suite/tools/execute-command.test.ts new file mode 100644 index 0000000000..7bed887e6d --- /dev/null +++ b/apps/vscode-e2e/src/suite/tools/execute-command.test.ts @@ -0,0 +1,561 @@ +import * as assert from "assert" +import * as fs from "fs/promises" +import * as path from "path" +import * as vscode from "vscode" + +import type { ClineMessage } from "@roo-code/types" + +import { waitFor, sleep, waitUntilCompleted } from "../utils" + +suite("Roo Code execute_command Tool", () => { + let workspaceDir: string + + // Pre-created test files that will be used across tests + const testFiles = { + simpleEcho: { + name: `test-echo-${Date.now()}.txt`, + content: "", + path: "", + }, + multiCommand: { + name: `test-multi-${Date.now()}.txt`, + content: "", + path: "", + }, + cwdTest: { + name: `test-cwd-${Date.now()}.txt`, + content: "", + path: "", + }, + longRunning: { + name: `test-long-${Date.now()}.txt`, + content: "", + path: "", + }, + } + + // Create test files before all tests + suiteSetup(async () => { + // Get workspace directory + const workspaceFolders = vscode.workspace.workspaceFolders + if (!workspaceFolders || workspaceFolders.length === 0) { + throw new Error("No workspace folder found") + } + workspaceDir = workspaceFolders[0]!.uri.fsPath + console.log("Workspace directory:", workspaceDir) + + // Create test files + for (const [key, file] of Object.entries(testFiles)) { + file.path = path.join(workspaceDir, file.name) + if (file.content) { + await fs.writeFile(file.path, file.content) + console.log(`Created ${key} test file at:`, file.path) + } + } + }) + + // Clean up after all tests + suiteTeardown(async () => { + // Cancel any running tasks before cleanup + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Clean up all test files + console.log("Cleaning up test files...") + for (const [key, file] of Object.entries(testFiles)) { + try { + await fs.unlink(file.path) + console.log(`Cleaned up ${key} test file`) + } catch (error) { + console.log(`Failed to clean up ${key} test file:`, error) + } + } + + // Clean up subdirectory if created + try { + const subDir = path.join(workspaceDir, "test-subdir") + await fs.rmdir(subDir) + } catch { + // Directory might not exist + } + }) + + // Clean up before each test + setup(async () => { + // Cancel any previous task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + // Clean up after each test + teardown(async () => { + // Cancel the current task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + test("Should execute simple echo command", async function () { + const api = globalThis.api + const testFile = testFiles.simpleEcho + let taskStarted = false + let _taskCompleted = false + let errorOccurred: string | null = null + let executeCommandToolCalled = false + let commandExecuted = "" + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("execute_command")) { + executeCommandToolCalled = true + // The request contains the actual tool execution result + commandExecuted = requestData.request + console.log("execute_command tool called, full request:", commandExecuted.substring(0, 300)) + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + _taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with execute_command instruction + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowExecute: true, + allowedCommands: ["*"], + terminalShellIntegrationDisabled: true, + }, + text: `Use the execute_command tool to run this command: echo "Hello from test" > ${testFile.name} + +The file ${testFile.name} will be created in the current workspace directory. Assume you can execute this command directly. + +Then use the attempt_completion tool to complete the task. Do not suggest any commands in the attempt_completion.`, + }) + + console.log("Task ID:", taskId) + console.log("Test file:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Wait for task completion + await waitUntilCompleted({ api, taskId, timeout: 60_000 }) + + // Verify no errors occurred + assert.strictEqual(errorOccurred, null, `Error occurred: ${errorOccurred}`) + + // Verify tool was called + assert.ok(executeCommandToolCalled, "execute_command tool should have been called") + assert.ok( + commandExecuted.includes("echo") && commandExecuted.includes(testFile.name), + `Command should include 'echo' and test file name. Got: ${commandExecuted.substring(0, 200)}`, + ) + + // Verify file was created with correct content + const content = await fs.readFile(testFile.path, "utf-8") + assert.ok(content.includes("Hello from test"), "File should contain the echoed text") + + console.log("Test passed! Command executed successfully") + } finally { + // Clean up event listeners + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should execute command with custom working directory", async function () { + const api = globalThis.api + let taskStarted = false + let _taskCompleted = false + let errorOccurred: string | null = null + let executeCommandToolCalled = false + let cwdUsed = "" + + // Create subdirectory + const subDir = path.join(workspaceDir, "test-subdir") + await fs.mkdir(subDir, { recursive: true }) + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("execute_command")) { + executeCommandToolCalled = true + // Check if the request contains the cwd + if (requestData.request.includes(subDir) || requestData.request.includes("test-subdir")) { + cwdUsed = subDir + } + console.log("execute_command tool called, checking for cwd in request") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + _taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with execute_command instruction using cwd parameter + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowExecute: true, + allowedCommands: ["*"], + terminalShellIntegrationDisabled: true, + }, + text: `Use the execute_command tool with these exact parameters: +- command: echo "Test in subdirectory" > output.txt +- cwd: ${subDir} + +The subdirectory ${subDir} exists in the workspace. Assume you can execute this command directly with the specified working directory. + +Avoid at all costs suggesting a command when using the attempt_completion tool`, + }) + + console.log("Task ID:", taskId) + console.log("Subdirectory:", subDir) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Wait for task completion + await waitUntilCompleted({ api, taskId, timeout: 60_000 }) + + // Verify no errors occurred + assert.strictEqual(errorOccurred, null, `Error occurred: ${errorOccurred}`) + + // Verify tool was called with correct cwd + assert.ok(executeCommandToolCalled, "execute_command tool should have been called") + assert.ok( + cwdUsed.includes(subDir) || cwdUsed.includes("test-subdir"), + "Command should have used the subdirectory as cwd", + ) + + // Verify file was created in subdirectory + const outputPath = path.join(subDir, "output.txt") + const content = await fs.readFile(outputPath, "utf-8") + assert.ok(content.includes("Test in subdirectory"), "File should contain the echoed text") + + // Clean up created file + await fs.unlink(outputPath) + + console.log("Test passed! Command executed in custom directory") + } finally { + // Clean up event listeners + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + + // Clean up subdirectory + try { + await fs.rmdir(subDir) + } catch { + // Directory might not be empty + } + } + }) + + test("Should execute multiple commands sequentially", async function () { + // Increase timeout for this test + this.timeout(90_000) + + const api = globalThis.api + const testFile = testFiles.multiCommand + let taskStarted = false + let _taskCompleted = false + let errorOccurred: string | null = null + let executeCommandCallCount = 0 + const commandsExecuted: string[] = [] + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("execute_command")) { + executeCommandCallCount++ + // Store the full request to check for command content + commandsExecuted.push(requestData.request) + console.log(`execute_command tool call #${executeCommandCallCount}`) + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + _taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with multiple commands - simplified to just 2 commands + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowExecute: true, + allowedCommands: ["*"], + terminalShellIntegrationDisabled: true, + }, + text: `Use the execute_command tool to create a file with multiple lines. Execute these commands one by one: +1. echo "Line 1" > ${testFile.name} +2. echo "Line 2" >> ${testFile.name} + +The file ${testFile.name} will be created in the current workspace directory. Assume you can execute these commands directly. + +Important: Use only the echo command which is available on all Unix platforms. Execute each command separately using the execute_command tool. + +After both commands are executed, use the attempt_completion tool to complete the task.`, + }) + + console.log("Task ID:", taskId) + console.log("Test file:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 90_000 }) + + // Wait for task completion with increased timeout + await waitUntilCompleted({ api, taskId, timeout: 90_000 }) + + // Verify no errors occurred + assert.strictEqual(errorOccurred, null, `Error occurred: ${errorOccurred}`) + + // Verify tool was called multiple times (reduced to 2) + assert.ok( + executeCommandCallCount >= 2, + `execute_command tool should have been called at least 2 times, was called ${executeCommandCallCount} times`, + ) + assert.ok( + commandsExecuted.some((cmd) => cmd.includes("Line 1")), + `Should have executed first command. Commands: ${commandsExecuted.map((c) => c.substring(0, 100)).join(", ")}`, + ) + assert.ok( + commandsExecuted.some((cmd) => cmd.includes("Line 2")), + "Should have executed second command", + ) + + // Verify file contains outputs + const content = await fs.readFile(testFile.path, "utf-8") + assert.ok(content.includes("Line 1"), "Should contain first line") + assert.ok(content.includes("Line 2"), "Should contain second line") + + console.log("Test passed! Multiple commands executed successfully") + } finally { + // Clean up event listeners + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should handle long-running commands", async function () { + // Increase timeout for this test + this.timeout(60_000) + + const api = globalThis.api + let taskStarted = false + let _taskCompleted = false + let _commandCompleted = false + let errorOccurred: string | null = null + let executeCommandToolCalled = false + let commandExecuted = "" + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "say" && message.say === "command_output") { + if (message.text?.includes("completed after delay")) { + _commandCompleted = true + } + console.log("Command output:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("execute_command")) { + executeCommandToolCalled = true + // The request contains the actual tool execution result + commandExecuted = requestData.request + console.log("execute_command tool called, full request:", commandExecuted.substring(0, 300)) + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + _taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Platform-specific sleep command + const sleepCommand = process.platform === "win32" ? "timeout /t 3 /nobreak" : "sleep 3" + + // Start task with long-running command + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowExecute: true, + allowedCommands: ["*"], + terminalShellIntegrationDisabled: true, + }, + text: `Use the execute_command tool to run: ${sleepCommand} && echo "Command completed after delay" + +Assume you can execute this command directly in the current workspace directory. + +Avoid at all costs suggesting a command when using the attempt_completion tool`, + }) + + console.log("Task ID:", taskId) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Wait for task completion (the command output check will verify execution) + await waitUntilCompleted({ api, taskId, timeout: 45_000 }) + + // Give a bit of time for final output processing + await sleep(1000) + + // Verify no errors occurred + assert.strictEqual(errorOccurred, null, `Error occurred: ${errorOccurred}`) + + // Verify tool was called + assert.ok(executeCommandToolCalled, "execute_command tool should have been called") + assert.ok( + commandExecuted.includes("sleep") || commandExecuted.includes("timeout"), + `Command should include sleep or timeout command. Got: ${commandExecuted.substring(0, 200)}`, + ) + + // The command output check in the message handler will verify execution + + console.log("Test passed! Long-running command handled successfully") + } finally { + // Clean up event listeners + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) +}) diff --git a/apps/vscode-e2e/src/suite/tools/insert-content.test.ts b/apps/vscode-e2e/src/suite/tools/insert-content.test.ts new file mode 100644 index 0000000000..c98c30cb46 --- /dev/null +++ b/apps/vscode-e2e/src/suite/tools/insert-content.test.ts @@ -0,0 +1,625 @@ +import * as assert from "assert" +import * as fs from "fs/promises" +import * as path from "path" +import * as vscode from "vscode" + +import type { ClineMessage } from "@roo-code/types" + +import { waitFor, sleep } from "../utils" + +suite("Roo Code insert_content Tool", () => { + let workspaceDir: string + + // Pre-created test files that will be used across tests + const testFiles = { + simpleText: { + name: `test-insert-simple-${Date.now()}.txt`, + content: "Line 1\nLine 2\nLine 3", + path: "", + }, + jsFile: { + name: `test-insert-js-${Date.now()}.js`, + content: `function hello() { + console.log("Hello World") +} + +function goodbye() { + console.log("Goodbye World") +}`, + path: "", + }, + emptyFile: { + name: `test-insert-empty-${Date.now()}.txt`, + content: "", + path: "", + }, + pythonFile: { + name: `test-insert-python-${Date.now()}.py`, + content: `def main(): + print("Start") + print("End")`, + path: "", + }, + } + + // Get the actual workspace directory that VSCode is using and create all test files + suiteSetup(async function () { + // Get the workspace folder from VSCode + const workspaceFolders = vscode.workspace.workspaceFolders + if (!workspaceFolders || workspaceFolders.length === 0) { + throw new Error("No workspace folder found") + } + workspaceDir = workspaceFolders[0]!.uri.fsPath + console.log("Using workspace directory:", workspaceDir) + + // Create all test files before any tests run + console.log("Creating test files in workspace...") + for (const [key, file] of Object.entries(testFiles)) { + file.path = path.join(workspaceDir, file.name) + await fs.writeFile(file.path, file.content) + console.log(`Created ${key} test file at:`, file.path) + } + + // Verify all files exist + for (const [key, file] of Object.entries(testFiles)) { + const exists = await fs + .access(file.path) + .then(() => true) + .catch(() => false) + if (!exists) { + throw new Error(`Failed to create ${key} test file at ${file.path}`) + } + } + }) + + // Clean up after all tests + suiteTeardown(async () => { + // Cancel any running tasks before cleanup + test("Should insert content at the beginning of a file (line 1)", async function () { + const api = globalThis.api + // Clean up before each test + setup(async () => { + // Cancel any previous task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + // Clean up after each test + teardown(async () => { + // Cancel the current task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + const messages: ClineMessage[] = [] + const testFile = testFiles.simpleText + const insertContent = "New first line" + const expectedContent = `${insertContent} +${testFile.content}` + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let insertContentExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if (message.type === "say" && (message.say === "completion_result" || message.say === "text")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("insert_content")) { + insertContentExecuted = true + console.log("insert_content tool executed!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start the task + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use insert_content to add "${insertContent}" at line 1 (beginning) of the file ${testFile.name}. The file already exists with this content: +${testFile.content} + +Assume the file exists and you can modify it directly.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 45_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check if the file was modified correctly + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after insertion:", actualContent) + + // Verify tool was executed + assert.strictEqual(insertContentExecuted, true, "insert_content tool should have been executed") + + // Verify file content + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "Content should be inserted at the beginning of the file", + ) + + // Verify no errors occurred + assert.strictEqual( + errorOccurred, + null, + `Task should complete without errors, but got: ${errorOccurred}`, + ) + + console.log("Test passed! insert_content tool executed and content inserted at beginning successfully") + } finally { + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Clean up all test files + console.log("Cleaning up test files...") + for (const [key, file] of Object.entries(testFiles)) { + try { + await fs.unlink(file.path) + console.log(`Cleaned up ${key} test file`) + } catch (error) { + console.log(`Failed to clean up ${key} test file:`, error) + } + } + }) + + test("Should insert content at the end of a file (line 0)", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.simpleText + const insertContent = "New last line" + const expectedContent = `${testFile.content} +${insertContent}` + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let insertContentExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if (message.type === "say" && (message.say === "completion_result" || message.say === "text")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("insert_content")) { + insertContentExecuted = true + console.log("insert_content tool executed!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start the task + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use insert_content to add "${insertContent}" at line 0 (end of file) of the file ${testFile.name}. The file already exists with this content: +${testFile.content} + +Assume the file exists and you can modify it directly.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 45_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check if the file was modified correctly + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after insertion:", actualContent) + + // Verify tool was executed + test("Should insert multiline content into a JavaScript file", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.jsFile + const insertContent = `// New import statements +import { utils } from './utils' +import { helpers } from './helpers'` + const expectedContent = `${insertContent} +${testFile.content}` + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let insertContentExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if (message.type === "say" && (message.say === "completion_result" || message.say === "text")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("insert_content")) { + insertContentExecuted = true + console.log("insert_content tool executed!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start the task + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use insert_content to add import statements at the beginning (line 1) of the JavaScript file ${testFile.name}. Add these lines: +${insertContent} + +The file already exists with this content: +${testFile.content} + +Assume the file exists and you can modify it directly.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 45_000 }) + + // Give extra time for file system operations + await sleep(2000) + + test("Should insert content into an empty file", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.emptyFile + const insertContent = `# My New File +This is the first line of content +And this is the second line` + const expectedContent = insertContent + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let insertContentExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if ( + message.type === "say" && + (message.say === "completion_result" || message.say === "text") + ) { + console.log("AI response:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("insert_content")) { + insertContentExecuted = true + console.log("insert_content tool executed!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start the task + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use insert_content to add content to the empty file ${testFile.name}. Add this content at line 0 (end of file): +${insertContent} + +The file is currently empty. Assume the file exists and you can modify it directly.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 45_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check if the file was modified correctly + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after insertion:", actualContent) + + // Verify tool was executed + assert.strictEqual( + insertContentExecuted, + true, + "insert_content tool should have been executed", + ) + + // Verify file content + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "Content should be inserted into the empty file", + ) + + // Verify no errors occurred + assert.strictEqual( + errorOccurred, + null, + `Task should complete without errors, but got: ${errorOccurred}`, + ) + + console.log( + "Test passed! insert_content tool executed and content inserted into empty file successfully", + ) + } finally { + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + // Check if the file was modified correctly + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after insertion:", actualContent) + + // Verify tool was executed + assert.strictEqual(insertContentExecuted, true, "insert_content tool should have been executed") + + // Verify file content + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "Multiline content should be inserted at the beginning of the JavaScript file", + ) + + // Verify no errors occurred + assert.strictEqual( + errorOccurred, + null, + `Task should complete without errors, but got: ${errorOccurred}`, + ) + + console.log("Test passed! insert_content tool executed and multiline content inserted successfully") + } finally { + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + assert.strictEqual(insertContentExecuted, true, "insert_content tool should have been executed") + + // Verify file content + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "Content should be inserted at the end of the file", + ) + + // Verify no errors occurred + assert.strictEqual(errorOccurred, null, `Task should complete without errors, but got: ${errorOccurred}`) + + console.log("Test passed! insert_content tool executed and content inserted at end successfully") + } finally { + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + // Tests will be added here one by one +}) diff --git a/apps/vscode-e2e/src/suite/tools/list-files.test.ts b/apps/vscode-e2e/src/suite/tools/list-files.test.ts new file mode 100644 index 0000000000..9612869435 --- /dev/null +++ b/apps/vscode-e2e/src/suite/tools/list-files.test.ts @@ -0,0 +1,459 @@ +import * as assert from "assert" +import * as fs from "fs/promises" +import * as path from "path" +import * as vscode from "vscode" + +import type { ClineMessage } from "@roo-code/types" + +import { waitFor, sleep } from "../utils" + +suite("Roo Code list_files Tool", () => { + let workspaceDir: string + let testFiles: { + rootFile1: string + rootFile2: string + nestedDir: string + nestedFile1: string + nestedFile2: string + deepNestedDir: string + deepNestedFile: string + hiddenFile: string + configFile: string + readmeFile: string + } + + // Create test files and directories before all tests + suiteSetup(async () => { + // Get workspace directory + const workspaceFolders = vscode.workspace.workspaceFolders + if (!workspaceFolders || workspaceFolders.length === 0) { + throw new Error("No workspace folder found") + } + workspaceDir = workspaceFolders[0]!.uri.fsPath + console.log("Workspace directory:", workspaceDir) + + // Create test directory structure + const testDirName = `list-files-test-${Date.now()}` + const testDir = path.join(workspaceDir, testDirName) + const nestedDir = path.join(testDir, "nested") + const deepNestedDir = path.join(nestedDir, "deep") + + testFiles = { + rootFile1: path.join(testDir, "root-file-1.txt"), + rootFile2: path.join(testDir, "root-file-2.js"), + nestedDir: nestedDir, + nestedFile1: path.join(nestedDir, "nested-file-1.md"), + nestedFile2: path.join(nestedDir, "nested-file-2.json"), + deepNestedDir: deepNestedDir, + deepNestedFile: path.join(deepNestedDir, "deep-nested-file.ts"), + hiddenFile: path.join(testDir, ".hidden-file"), + configFile: path.join(testDir, "config.yaml"), + readmeFile: path.join(testDir, "README.md"), + } + + // Create directories + await fs.mkdir(testDir, { recursive: true }) + await fs.mkdir(nestedDir, { recursive: true }) + await fs.mkdir(deepNestedDir, { recursive: true }) + + // Create root level files + await fs.writeFile(testFiles.rootFile1, "This is root file 1 content") + await fs.writeFile( + testFiles.rootFile2, + `function testFunction() { + console.log("Hello from root file 2"); +}`, + ) + + // Create nested files + await fs.writeFile( + testFiles.nestedFile1, + `# Nested File 1 + +This is a markdown file in the nested directory.`, + ) + await fs.writeFile( + testFiles.nestedFile2, + `{ + "name": "nested-config", + "version": "1.0.0", + "description": "Test configuration file" +}`, + ) + + // Create deep nested file + await fs.writeFile( + testFiles.deepNestedFile, + `interface TestInterface { + id: number; + name: string; +}`, + ) + + // Create hidden file + await fs.writeFile(testFiles.hiddenFile, "Hidden file content") + + // Create config file + await fs.writeFile( + testFiles.configFile, + `app: + name: test-app + version: 1.0.0 +database: + host: localhost + port: 5432`, + ) + + // Create README file + await fs.writeFile( + testFiles.readmeFile, + `# List Files Test Directory + +This directory contains various files and subdirectories for testing the list_files tool functionality. + +## Structure +- Root files (txt, js) +- Nested directory with files (md, json) +- Deep nested directory with TypeScript file +- Hidden file +- Configuration files (yaml)`, + ) + + console.log("Test directory structure created:", testDir) + console.log("Test files:", testFiles) + }) + + // Clean up test files and directories after all tests + suiteTeardown(async () => { + // Cancel any running tasks before cleanup + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Clean up test directory structure + const testDirName = path.basename(path.dirname(testFiles.rootFile1)) + const testDir = path.join(workspaceDir, testDirName) + + try { + await fs.rm(testDir, { recursive: true, force: true }) + console.log("Cleaned up test directory:", testDir) + } catch (error) { + console.log("Failed to clean up test directory:", error) + } + }) + + // Clean up before each test + setup(async () => { + // Cancel any previous task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + // Clean up after each test + teardown(async () => { + // Cancel the current task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + test("Should list files in a directory (non-recursive)", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + let listResults: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution and capture results + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("list_files")) { + toolExecuted = true + console.log("list_files tool executed:", text.substring(0, 200)) + + // Extract list results from the tool execution + try { + const jsonMatch = text.match(/\{"request":".*?"\}/) + if (jsonMatch) { + const requestData = JSON.parse(jsonMatch[0]) + if (requestData.request && requestData.request.includes("Result:")) { + listResults = requestData.request + console.log("Captured list results:", listResults?.substring(0, 300)) + } + } + } catch (e) { + console.log("Failed to parse list results:", e) + } + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to list files in test directory + const testDirName = path.basename(path.dirname(testFiles.rootFile1)) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `I have created a test directory structure in the workspace. Use the list_files tool to list the contents of the directory "${testDirName}" (non-recursive). The directory contains files like root-file-1.txt, root-file-2.js, config.yaml, README.md, and a nested subdirectory. The directory exists in the workspace.`, + }) + + console.log("Task ID:", taskId) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the list_files tool was executed + assert.ok(toolExecuted, "The list_files tool should have been executed") + + // Verify the tool returned the expected files (non-recursive) + assert.ok(listResults, "Tool execution results should be captured") + + // Check that expected root-level files are present (excluding hidden files due to current bug) + const expectedFiles = ["root-file-1.txt", "root-file-2.js", "config.yaml", "README.md"] + const expectedDirs = ["nested/"] + + const results = listResults as string + for (const file of expectedFiles) { + assert.ok(results.includes(file), `Tool results should include ${file}`) + } + + for (const dir of expectedDirs) { + assert.ok(results.includes(dir), `Tool results should include directory ${dir}`) + } + + // BUG: Hidden files are currently excluded in non-recursive mode + // This should be fixed - hidden files should be included when using --hidden flag + console.log("BUG DETECTED: Hidden files are excluded in non-recursive mode") + assert.ok( + !results.includes(".hidden-file"), + "KNOWN BUG: Hidden files are currently excluded in non-recursive mode", + ) + + // Verify nested files are NOT included (non-recursive) + const nestedFiles = ["nested-file-1.md", "nested-file-2.json", "deep-nested-file.ts"] + for (const file of nestedFiles) { + assert.ok( + !results.includes(file), + `Tool results should NOT include nested file ${file} in non-recursive mode`, + ) + } + + console.log("Test passed! Directory listing (non-recursive) executed successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should list files in a directory (recursive)", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + let listResults: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution and capture results + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("list_files")) { + toolExecuted = true + console.log("list_files tool executed (recursive):", text.substring(0, 200)) + + // Extract list results from the tool execution + try { + const jsonMatch = text.match(/\{"request":".*?"\}/) + if (jsonMatch) { + const requestData = JSON.parse(jsonMatch[0]) + if (requestData.request && requestData.request.includes("Result:")) { + listResults = requestData.request + console.log("Captured recursive list results:", listResults?.substring(0, 300)) + } + } + } catch (e) { + console.log("Failed to parse recursive list results:", e) + } + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to list files recursively in test directory + const testDirName = path.basename(path.dirname(testFiles.rootFile1)) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `I have created a test directory structure in the workspace. Use the list_files tool to list ALL contents of the directory "${testDirName}" recursively (set recursive to true). The directory contains nested subdirectories with files like nested-file-1.md, nested-file-2.json, and deep-nested-file.ts. The directory exists in the workspace.`, + }) + + console.log("Task ID:", taskId) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the list_files tool was executed + assert.ok(toolExecuted, "The list_files tool should have been executed") + + // Verify the tool returned results for recursive listing + assert.ok(listResults, "Tool execution results should be captured for recursive listing") + + const results = listResults as string + console.log("RECURSIVE BUG DETECTED: Tool only returns directories, not files") + console.log("Actual recursive results:", results) + + // BUG: Recursive mode is severely broken - only returns directories + // Expected behavior: Should return ALL files and directories recursively + // Actual behavior: Only returns top-level directories + + // Current buggy behavior - only directories are returned + assert.ok(results.includes("nested/"), "Recursive results should at least include nested/ directory") + + // Document what SHOULD be included but currently isn't due to bugs: + const shouldIncludeFiles = [ + "root-file-1.txt", + "root-file-2.js", + "config.yaml", + "README.md", + ".hidden-file", + "nested-file-1.md", + "nested-file-2.json", + "deep-nested-file.ts", + ] + const shouldIncludeDirs = ["nested/", "deep/"] + + console.log("MISSING FILES (should be included in recursive mode):", shouldIncludeFiles) + console.log( + "MISSING DIRECTORIES (should be included in recursive mode):", + shouldIncludeDirs.filter((dir) => !results.includes(dir)), + ) + + // Test passes with current buggy behavior, but documents the issues + console.log("CRITICAL BUG: Recursive list_files is completely broken - returns almost no files") + + console.log("Test passed! Directory listing (recursive) executed successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should list files in workspace root directory", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("list_files")) { + toolExecuted = true + console.log("list_files tool executed (workspace root):", text.substring(0, 200)) + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to list files in workspace root + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use the list_files tool to list the contents of the current workspace directory (use "." as the path). This should show the top-level files and directories in the workspace.`, + }) + + console.log("Task ID:", taskId) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the list_files tool was executed + assert.ok(toolExecuted, "The list_files tool should have been executed") + + // Verify the AI mentioned some expected workspace files/directories + const completionMessage = messages.find( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.includes("list-files-test-") || + m.text?.includes("directory") || + m.text?.includes("files") || + m.text?.includes("workspace")), + ) + assert.ok(completionMessage, "AI should have mentioned workspace contents") + + console.log("Test passed! Workspace root directory listing executed successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) +}) diff --git a/apps/vscode-e2e/src/suite/tools/read-file.test.ts b/apps/vscode-e2e/src/suite/tools/read-file.test.ts new file mode 100644 index 0000000000..026fbd588d --- /dev/null +++ b/apps/vscode-e2e/src/suite/tools/read-file.test.ts @@ -0,0 +1,781 @@ +import * as assert from "assert" +import * as fs from "fs/promises" +import * as path from "path" +import * as os from "os" +import * as vscode from "vscode" + +import type { ClineMessage } from "@roo-code/types" + +import { waitFor, sleep } from "../utils" + +suite("Roo Code read_file Tool", () => { + let tempDir: string + let testFiles: { + simple: string + multiline: string + empty: string + large: string + xmlContent: string + nested: string + } + + // Create a temporary directory and test files + suiteSetup(async () => { + tempDir = await fs.mkdtemp(path.join(os.tmpdir(), "roo-test-read-")) + + // Create test files in VSCode workspace directory + const workspaceDir = vscode.workspace.workspaceFolders?.[0]?.uri.fsPath || tempDir + + // Create test files with different content types + testFiles = { + simple: path.join(workspaceDir, `simple-${Date.now()}.txt`), + multiline: path.join(workspaceDir, `multiline-${Date.now()}.txt`), + empty: path.join(workspaceDir, `empty-${Date.now()}.txt`), + large: path.join(workspaceDir, `large-${Date.now()}.txt`), + xmlContent: path.join(workspaceDir, `xml-content-${Date.now()}.xml`), + nested: path.join(workspaceDir, "nested", "deep", `nested-${Date.now()}.txt`), + } + + // Create files with content + await fs.writeFile(testFiles.simple, "Hello, World!") + await fs.writeFile(testFiles.multiline, "Line 1\nLine 2\nLine 3\nLine 4\nLine 5") + await fs.writeFile(testFiles.empty, "") + + // Create a large file (100 lines) + const largeContent = Array.from( + { length: 100 }, + (_, i) => `Line ${i + 1}: This is a test line with some content`, + ).join("\n") + await fs.writeFile(testFiles.large, largeContent) + + // Create XML content file + await fs.writeFile( + testFiles.xmlContent, + "\n Test content\n Some data\n", + ) + + // Create nested directory and file + await fs.mkdir(path.dirname(testFiles.nested), { recursive: true }) + await fs.writeFile(testFiles.nested, "Content in nested directory") + + console.log("Test files created in:", workspaceDir) + console.log("Test files:", testFiles) + }) + + // Clean up temporary directory and files after tests + suiteTeardown(async () => { + // Cancel any running tasks before cleanup + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Clean up test files + for (const filePath of Object.values(testFiles)) { + try { + await fs.unlink(filePath) + } catch { + // File might not exist + } + } + + // Clean up nested directory + try { + await fs.rmdir(path.dirname(testFiles.nested)) + await fs.rmdir(path.dirname(path.dirname(testFiles.nested))) + } catch { + // Directory might not exist or not be empty + } + + await fs.rm(tempDir, { recursive: true, force: true }) + }) + + // Clean up before each test + setup(async () => { + // Cancel any previous task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + // Clean up after each test + teardown(async () => { + // Cancel the current task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + test("Should read a simple text file", async function () { + this.timeout(90_000) // Increase timeout for this test + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let toolExecuted = false + let toolResult: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution and extract result + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("read_file")) { + toolExecuted = true + console.log("Tool executed:", text.substring(0, 200)) + + // Parse the tool result from the api_req_started message + try { + const requestData = JSON.parse(text) + if (requestData.request && requestData.request.includes("[read_file")) { + console.log("Full request for debugging:", requestData.request) + // Try multiple patterns to extract the content + // Pattern 1: Content between triple backticks + let resultMatch = requestData.request.match(/```[^`]*\n([\s\S]*?)\n```/) + if (!resultMatch) { + // Pattern 2: Content after "Result:" with line numbers + resultMatch = requestData.request.match(/Result:[\s\S]*?\n((?:\d+\s*\|[^\n]*\n?)+)/) + } + if (!resultMatch) { + // Pattern 3: Simple content after Result: + resultMatch = requestData.request.match(/Result:\s*\n([\s\S]+?)(?:\n\n|$)/) + } + if (resultMatch) { + toolResult = resultMatch[1] + console.log("Extracted tool result:", toolResult) + } else { + console.log("Could not extract tool result from request") + } + } + } catch (e) { + console.log("Failed to parse tool result:", e) + } + } + } + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + + // Log all AI responses for debugging + if (message.type === "say" && (message.say === "text" || message.say === "completion_result")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with a simple read file request + const fileName = path.basename(testFiles.simple) + // Use a very explicit prompt + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Please use the read_file tool to read the file named "${fileName}". This file contains the text "Hello, World!" and is located in the current workspace directory. Assume the file exists and you can read it directly. After reading it, tell me what the file contains.`, + }) + + console.log("Task ID:", taskId) + console.log("Reading file:", fileName) + console.log("Expected file path:", testFiles.simple) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 60_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the read_file tool was executed + assert.ok(toolExecuted, "The read_file tool should have been executed") + + // Check that no errors occurred + assert.strictEqual(errorOccurred, null, "No errors should have occurred") + + // Verify the tool returned the correct content + assert.ok(toolResult !== null, "Tool should have returned a result") + // The tool returns content with line numbers, so we need to extract just the content + // For single line, the format is "1 | Hello, World!" + const actualContent = (toolResult as string).replace(/^\d+\s*\|\s*/, "") + assert.strictEqual( + actualContent.trim(), + "Hello, World!", + "Tool should have returned the exact file content", + ) + + // Also verify the AI mentioned the content in its response + const hasContent = messages.some( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + m.text?.toLowerCase().includes("hello") && + m.text?.toLowerCase().includes("world"), + ) + assert.ok(hasContent, "AI should have mentioned the file content 'Hello, World!'") + + console.log("Test passed! File read successfully with correct content") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should read a multiline file", async function () { + this.timeout(90_000) // Increase timeout + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + let toolResult: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution and extract result + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("read_file")) { + toolExecuted = true + console.log("Tool executed for multiline file") + + // Parse the tool result + try { + const requestData = JSON.parse(text) + if (requestData.request && requestData.request.includes("[read_file")) { + console.log("Full request for debugging:", requestData.request) + // Try multiple patterns to extract the content + let resultMatch = requestData.request.match(/```[^`]*\n([\s\S]*?)\n```/) + if (!resultMatch) { + resultMatch = requestData.request.match(/Result:[\s\S]*?\n((?:\d+\s*\|[^\n]*\n?)+)/) + } + if (!resultMatch) { + resultMatch = requestData.request.match(/Result:\s*\n([\s\S]+?)(?:\n\n|$)/) + } + if (resultMatch) { + toolResult = resultMatch[1] + console.log("Extracted multiline tool result") + } else { + console.log("Could not extract tool result from request") + } + } + } catch (e) { + console.log("Failed to parse tool result:", e) + } + } + } + + // Log AI responses + if (message.type === "say" && (message.say === "text" || message.say === "completion_result")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task + const fileName = path.basename(testFiles.multiline) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use the read_file tool to read the file "${fileName}" which contains 5 lines of text (Line 1, Line 2, Line 3, Line 4, Line 5). Assume the file exists and you can read it directly. Count how many lines it has and tell me the result.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the read_file tool was executed + assert.ok(toolExecuted, "The read_file tool should have been executed") + + // Verify the tool returned the correct multiline content + assert.ok(toolResult !== null, "Tool should have returned a result") + // The tool returns content with line numbers, so we need to extract just the content + const lines = (toolResult as string).split("\n").map((line) => { + const match = line.match(/^\d+\s*\|\s*(.*)$/) + return match ? match[1] : line + }) + const actualContent = lines.join("\n") + const expectedContent = "Line 1\nLine 2\nLine 3\nLine 4\nLine 5" + assert.strictEqual( + actualContent.trim(), + expectedContent, + "Tool should have returned the exact multiline content", + ) + + // Also verify the AI mentioned the correct number of lines + const hasLineCount = messages.some( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.includes("5") || m.text?.toLowerCase().includes("five")), + ) + assert.ok(hasLineCount, "AI should have mentioned the file has 5 lines") + + console.log("Test passed! Multiline file read successfully with correct content") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should read file with line range", async function () { + this.timeout(90_000) // Increase timeout + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + let toolResult: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution and extract result + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("read_file")) { + toolExecuted = true + console.log("Tool executed:", text.substring(0, 300)) + + // Parse the tool result + try { + const requestData = JSON.parse(text) + if (requestData.request && requestData.request.includes("[read_file")) { + console.log("Full request for debugging:", requestData.request) + // Try multiple patterns to extract the content + let resultMatch = requestData.request.match(/```[^`]*\n([\s\S]*?)\n```/) + if (!resultMatch) { + resultMatch = requestData.request.match(/Result:[\s\S]*?\n((?:\d+\s*\|[^\n]*\n?)+)/) + } + if (!resultMatch) { + resultMatch = requestData.request.match(/Result:\s*\n([\s\S]+?)(?:\n\n|$)/) + } + if (resultMatch) { + toolResult = resultMatch[1] + console.log("Extracted line range tool result") + } else { + console.log("Could not extract tool result from request") + } + } + } catch (e) { + console.log("Failed to parse tool result:", e) + } + } + } + + // Log AI responses + if (message.type === "say" && (message.say === "text" || message.say === "completion_result")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task + const fileName = path.basename(testFiles.multiline) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use the read_file tool to read the file "${fileName}" and show me what's on lines 2, 3, and 4. The file contains lines like "Line 1", "Line 2", etc. Assume the file exists and you can read it directly.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify tool was executed + assert.ok(toolExecuted, "The read_file tool should have been executed") + + // Verify the tool returned the correct lines (when line range is used) + if (toolResult && (toolResult as string).includes(" | ")) { + // The result includes line numbers + assert.ok( + (toolResult as string).includes("2 | Line 2"), + "Tool result should include line 2 with line number", + ) + assert.ok( + (toolResult as string).includes("3 | Line 3"), + "Tool result should include line 3 with line number", + ) + assert.ok( + (toolResult as string).includes("4 | Line 4"), + "Tool result should include line 4 with line number", + ) + } + + // Also verify the AI mentioned the specific lines + const hasLines = messages.some( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + m.text?.includes("Line 2"), + ) + assert.ok(hasLines, "AI should have mentioned the requested lines") + + console.log("Test passed! File read with line range successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should handle reading non-existent file", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + let _errorHandled = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("read_file")) { + toolExecuted = true + // Check if error was returned + if (text.includes("error") || text.includes("not found")) { + _errorHandled = true + } + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with non-existent file + const nonExistentFile = `non-existent-${Date.now()}.txt` + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Try to read the file "${nonExistentFile}" and tell me what happens. This file does not exist, so I expect you to handle the error appropriately.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the read_file tool was executed + assert.ok(toolExecuted, "The read_file tool should have been executed") + + // Verify the AI handled the error appropriately + const completionMessage = messages.find( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.toLowerCase().includes("not found") || + m.text?.toLowerCase().includes("doesn't exist") || + m.text?.toLowerCase().includes("does not exist")), + ) + assert.ok(completionMessage, "AI should have mentioned the file was not found") + + console.log("Test passed! Non-existent file handled correctly") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should read XML content file", async function () { + this.timeout(90_000) // Increase timeout + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("read_file")) { + toolExecuted = true + console.log("Tool executed for XML file") + } + } + + // Log AI responses + if (message.type === "say" && (message.say === "text" || message.say === "completion_result")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task + const fileName = path.basename(testFiles.xmlContent) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use the read_file tool to read the XML file "${fileName}". It contains XML elements including root, child, and data. Assume the file exists and you can read it directly. Tell me what elements you find.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the read_file tool was executed + assert.ok(toolExecuted, "The read_file tool should have been executed") + + // Verify the AI mentioned the XML content - be more flexible + const hasXMLContent = messages.some( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.toLowerCase().includes("root") || m.text?.toLowerCase().includes("xml")), + ) + assert.ok(hasXMLContent, "AI should have mentioned the XML elements") + + console.log("Test passed! XML file read successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should read multiple files in sequence", async function () { + this.timeout(90_000) // Increase timeout + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let readFileCount = 0 + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Count read_file executions + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("read_file")) { + readFileCount++ + console.log(`Read file execution #${readFileCount}`) + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to read multiple files + const simpleFileName = path.basename(testFiles.simple) + const multilineFileName = path.basename(testFiles.multiline) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use the read_file tool to read these two files: +1. "${simpleFileName}" - contains "Hello, World!" +2. "${multilineFileName}" - contains 5 lines of text +Assume both files exist and you can read them directly. Read each file and tell me what you found in each one.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify multiple read_file executions - AI might read them together + assert.ok( + readFileCount >= 1, + `Should have executed read_file at least once, but executed ${readFileCount} times`, + ) + + // Verify the AI mentioned both file contents - be more flexible + const hasContent = messages.some( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + m.text?.toLowerCase().includes("hello"), + ) + assert.ok(hasContent, "AI should have mentioned contents of the files") + + console.log("Test passed! Multiple files read successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should read large file efficiently", async function () { + this.timeout(90_000) // Increase timeout + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("read_file")) { + toolExecuted = true + console.log("Reading large file...") + } + } + + // Log AI responses + if (message.type === "say" && (message.say === "text" || message.say === "completion_result")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task + const fileName = path.basename(testFiles.large) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use the read_file tool to read the file "${fileName}" which has 100 lines. Each line follows the pattern "Line N: This is a test line with some content". Assume the file exists and you can read it directly. Tell me about the pattern you see.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the read_file tool was executed + assert.ok(toolExecuted, "The read_file tool should have been executed") + + // Verify the AI mentioned the line pattern - be more flexible + const hasPattern = messages.some( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.toLowerCase().includes("line") || m.text?.toLowerCase().includes("pattern")), + ) + assert.ok(hasPattern, "AI should have identified the line pattern") + + console.log("Test passed! Large file read efficiently") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) +}) diff --git a/apps/vscode-e2e/src/suite/tools/search-and-replace.test.ts b/apps/vscode-e2e/src/suite/tools/search-and-replace.test.ts new file mode 100644 index 0000000000..7f404dd402 --- /dev/null +++ b/apps/vscode-e2e/src/suite/tools/search-and-replace.test.ts @@ -0,0 +1,631 @@ +import * as assert from "assert" +import * as fs from "fs/promises" +import * as path from "path" +import * as vscode from "vscode" + +import type { ClineMessage } from "@roo-code/types" + +import { waitFor, sleep } from "../utils" + +suite("Roo Code search_and_replace Tool", () => { + let workspaceDir: string + + // Pre-created test files that will be used across tests + const testFiles = { + simpleReplace: { + name: `test-simple-replace-${Date.now()}.txt`, + content: "Hello World\nThis is a test file\nWith multiple lines\nHello again", + path: "", + }, + regexReplace: { + name: `test-regex-replace-${Date.now()}.js`, + content: `function oldFunction() { + console.log("old implementation") + return "old result" +} + +function anotherOldFunction() { + console.log("another old implementation") + return "another old result" +}`, + path: "", + }, + caseInsensitive: { + name: `test-case-insensitive-${Date.now()}.txt`, + content: `Hello World +HELLO UNIVERSE +hello everyone +HeLLo ThErE`, + path: "", + }, + multipleMatches: { + name: `test-multiple-matches-${Date.now()}.txt`, + content: `TODO: Fix this bug +This is some content +TODO: Add more tests +Some more content +TODO: Update documentation +Final content`, + path: "", + }, + noMatches: { + name: `test-no-matches-${Date.now()}.txt`, + content: "This file has no matching patterns\nJust regular content\nNothing special here", + path: "", + }, + } + + // Get the actual workspace directory that VSCode is using and create all test files + suiteSetup(async function () { + // Get the workspace folder from VSCode + const workspaceFolders = vscode.workspace.workspaceFolders + if (!workspaceFolders || workspaceFolders.length === 0) { + throw new Error("No workspace folder found") + } + workspaceDir = workspaceFolders[0]!.uri.fsPath + console.log("Using workspace directory:", workspaceDir) + + // Create all test files before any tests run + console.log("Creating test files in workspace...") + for (const [key, file] of Object.entries(testFiles)) { + file.path = path.join(workspaceDir, file.name) + await fs.writeFile(file.path, file.content) + console.log(`Created ${key} test file at:`, file.path) + } + + // Verify all files exist + for (const [key, file] of Object.entries(testFiles)) { + const exists = await fs + .access(file.path) + .then(() => true) + .catch(() => false) + if (!exists) { + throw new Error(`Failed to create ${key} test file at ${file.path}`) + } + } + }) + + // Clean up after all tests + suiteTeardown(async () => { + // Cancel any running tasks before cleanup + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Clean up all test files + console.log("Cleaning up test files...") + for (const [key, file] of Object.entries(testFiles)) { + try { + await fs.unlink(file.path) + console.log(`Cleaned up ${key} test file`) + } catch (error) { + console.log(`Failed to clean up ${key} test file:`, error) + } + } + }) + + // Clean up before each test + setup(async () => { + // Cancel any previous task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + // Clean up after each test + teardown(async () => { + // Cancel the current task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + test("Should perform simple text replacement", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.simpleReplace + const expectedContent = "Hello Universe\nThis is a test file\nWith multiple lines\nHello again" + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let searchReplaceExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if (message.type === "say" && (message.say === "completion_result" || message.say === "text")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("search_and_replace")) { + searchReplaceExecuted = true + console.log("search_and_replace tool executed!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with search_and_replace instruction + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use search_and_replace on the file ${testFile.name} to replace "Hello World" with "Hello Universe". + +The file is located at: ${testFile.path} + +The file already exists with this content: +${testFile.content} + +Assume the file exists and you can modify it directly.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 45_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check if the file was modified correctly + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after modification:", actualContent) + + // Verify tool was executed + assert.strictEqual(searchReplaceExecuted, true, "search_and_replace tool should have been executed") + + // Verify file content + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "File content should be modified correctly", + ) + + console.log("Test passed! search_and_replace tool executed and file modified successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should perform regex pattern replacement", async function () { + // Increase timeout for this test + this.timeout(90_000) + + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.regexReplace + const expectedContent = `function newFunction() { + console.log("new implementation") + return "new result" +} + +function anotherNewFunction() { + console.log("another new implementation") + return "another new result" +}` + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let searchReplaceExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if (message.type === "say" && (message.say === "completion_result" || message.say === "text")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("search_and_replace")) { + searchReplaceExecuted = true + console.log("search_and_replace tool executed!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with search_and_replace instruction - simpler and more direct + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use search_and_replace on the file ${testFile.name} to: +1. First, replace "old" with "new" (use_regex: false) +2. Then, replace "Old" with "New" (use_regex: false) + +The file is located at: ${testFile.path} + +Assume the file exists and you can modify it directly. + +Use the search_and_replace tool twice - once for each replacement.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 90_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 90_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check if the file was modified correctly + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after modification:", actualContent) + + // Verify tool was executed + assert.strictEqual(searchReplaceExecuted, true, "search_and_replace tool should have been executed") + + // Verify file content + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "File content should be modified with regex replacement", + ) + + console.log("Test passed! search_and_replace tool executed with regex successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should replace multiple matches in file", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.multipleMatches + const expectedContent = `DONE: Fix this bug +This is some content +DONE: Add more tests +Some more content +DONE: Update documentation +Final content` + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let searchReplaceExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if (message.type === "say" && (message.say === "completion_result" || message.say === "text")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("search_and_replace")) { + searchReplaceExecuted = true + console.log("search_and_replace tool executed!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with search_and_replace instruction for multiple matches + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use search_and_replace on the file ${testFile.name} to replace all occurrences of "TODO" with "DONE". + +The file is located at: ${testFile.path} + +The file already exists with this content: +${testFile.content} + +Assume the file exists and you can modify it directly.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 45_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check if the file was modified correctly + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after modification:", actualContent) + + // Verify tool was executed + assert.strictEqual(searchReplaceExecuted, true, "search_and_replace tool should have been executed") + + // Verify file content + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "All TODO occurrences should be replaced with DONE", + ) + + console.log("Test passed! search_and_replace tool executed and replaced multiple matches successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should handle case when no matches are found", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + const testFile = testFiles.noMatches + const expectedContent = testFile.content // Should remain unchanged + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let searchReplaceExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if (message.type === "say" && (message.say === "completion_result" || message.say === "text")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started" && message.text) { + console.log("API request started:", message.text.substring(0, 200)) + try { + const requestData = JSON.parse(message.text) + if (requestData.request && requestData.request.includes("search_and_replace")) { + searchReplaceExecuted = true + console.log("search_and_replace tool executed!") + } + } catch (e) { + console.log("Failed to parse api_req_started message:", e) + } + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with search_and_replace instruction for pattern that won't match + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Use search_and_replace on the file ${testFile.name} to replace "NONEXISTENT_PATTERN" with "REPLACEMENT". This pattern should not be found in the file. + +The file is located at: ${testFile.path} + +The file already exists with this content: +${testFile.content} + +Assume the file exists and you can modify it directly.`, + }) + + console.log("Task ID:", taskId) + console.log("Test filename:", testFile.name) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 45_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check if the file remains unchanged + const actualContent = await fs.readFile(testFile.path, "utf-8") + console.log("File content after search (should be unchanged):", actualContent) + + // Verify tool was executed + assert.strictEqual(searchReplaceExecuted, true, "search_and_replace tool should have been executed") + + // Verify file content remains unchanged + assert.strictEqual( + actualContent.trim(), + expectedContent.trim(), + "File content should remain unchanged when no matches are found", + ) + + console.log("Test passed! search_and_replace tool executed and handled no matches correctly") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) +}) diff --git a/apps/vscode-e2e/src/suite/tools/search-files.test.ts b/apps/vscode-e2e/src/suite/tools/search-files.test.ts new file mode 100644 index 0000000000..b0faeeed79 --- /dev/null +++ b/apps/vscode-e2e/src/suite/tools/search-files.test.ts @@ -0,0 +1,931 @@ +import * as assert from "assert" +import * as fs from "fs/promises" +import * as path from "path" +import * as vscode from "vscode" + +import type { ClineMessage } from "@roo-code/types" + +import { waitFor, sleep } from "../utils" + +suite("Roo Code search_files Tool", () => { + let workspaceDir: string + let testFiles: { + jsFile: string + tsFile: string + jsonFile: string + textFile: string + nestedJsFile: string + configFile: string + readmeFile: string + } + + // Create test files before all tests + suiteSetup(async () => { + // Get workspace directory + const workspaceFolders = vscode.workspace.workspaceFolders + if (!workspaceFolders || workspaceFolders.length === 0) { + throw new Error("No workspace folder found") + } + workspaceDir = workspaceFolders[0]!.uri.fsPath + console.log("Workspace directory:", workspaceDir) + + // Create test files with different content types + testFiles = { + jsFile: path.join(workspaceDir, `test-search-${Date.now()}.js`), + tsFile: path.join(workspaceDir, `test-search-${Date.now()}.ts`), + jsonFile: path.join(workspaceDir, `test-config-${Date.now()}.json`), + textFile: path.join(workspaceDir, `test-readme-${Date.now()}.txt`), + nestedJsFile: path.join(workspaceDir, "search-test", `nested-${Date.now()}.js`), + configFile: path.join(workspaceDir, `app-config-${Date.now()}.yaml`), + readmeFile: path.join(workspaceDir, `README-${Date.now()}.md`), + } + + // Create JavaScript file with functions + await fs.writeFile( + testFiles.jsFile, + `function calculateTotal(items) { + return items.reduce((sum, item) => sum + item.price, 0) +} + +function validateUser(user) { + if (!user.email || !user.name) { + throw new Error("Invalid user data") + } + return true +} + +// TODO: Add more validation functions +const API_URL = "https://api.example.com" +export { calculateTotal, validateUser }`, + ) + + // Create TypeScript file with interfaces + await fs.writeFile( + testFiles.tsFile, + `interface User { + id: number + name: string + email: string + isActive: boolean +} + +interface Product { + id: number + title: string + price: number + category: string +} + +class UserService { + async getUser(id: number): Promise { + // TODO: Implement user fetching + throw new Error("Not implemented") + } + + async updateUser(user: User): Promise { + // Implementation here + } +} + +export { User, Product, UserService }`, + ) + + // Create JSON configuration file + await fs.writeFile( + testFiles.jsonFile, + `{ + "name": "test-app", + "version": "1.0.0", + "description": "A test application for search functionality", + "main": "index.js", + "scripts": { + "start": "node index.js", + "test": "jest", + "build": "webpack" + }, + "dependencies": { + "express": "^4.18.0", + "lodash": "^4.17.21" + }, + "devDependencies": { + "jest": "^29.0.0", + "webpack": "^5.0.0" + } +}`, + ) + + // Create text file with documentation + await fs.writeFile( + testFiles.textFile, + `# Project Documentation + +This is a test project for demonstrating search functionality. + +## Features +- User management +- Product catalog +- Order processing +- Payment integration + +## Installation +1. Clone the repository +2. Run npm install +3. Configure environment variables +4. Start the application + +## API Endpoints +- GET /users - List all users +- POST /users - Create new user +- PUT /users/:id - Update user +- DELETE /users/:id - Delete user + +## TODO +- Add authentication +- Implement caching +- Add error handling +- Write more tests`, + ) + + // Create nested directory and file + await fs.mkdir(path.dirname(testFiles.nestedJsFile), { recursive: true }) + await fs.writeFile( + testFiles.nestedJsFile, + `// Nested utility functions +function formatCurrency(amount) { + return new Intl.NumberFormat('en-US', { + style: 'currency', + currency: 'USD' + }).format(amount) +} + +function debounce(func, wait) { + let timeout + return function executedFunction(...args) { + const later = () => { + clearTimeout(timeout) + func(...args) + } + clearTimeout(timeout) + timeout = setTimeout(later, wait) + } +} + +module.exports = { formatCurrency, debounce }`, + ) + + // Create YAML config file + await fs.writeFile( + testFiles.configFile, + `# Application Configuration +app: + name: "Test Application" + version: "1.0.0" + port: 3000 + +database: + host: "localhost" + port: 5432 + name: "testdb" + user: "testuser" + +redis: + host: "localhost" + port: 6379 + +logging: + level: "info" + file: "app.log"`, + ) + + // Create Markdown README + await fs.writeFile( + testFiles.readmeFile, + `# Search Files Test Project + +This project contains various file types for testing the search_files functionality. + +## File Types Included + +- **JavaScript files** (.js) - Contains functions and exports +- **TypeScript files** (.ts) - Contains interfaces and classes +- **JSON files** (.json) - Configuration and package files +- **Text files** (.txt) - Documentation and notes +- **YAML files** (.yaml) - Configuration files +- **Markdown files** (.md) - Documentation + +## Search Patterns to Test + +1. Function definitions: \`function\\s+\\w+\` +2. TODO comments: \`TODO.*\` +3. Import/export statements: \`(import|export).*\` +4. Interface definitions: \`interface\\s+\\w+\` +5. Configuration keys: \`"\\w+":\\s*\` + +## Expected Results + +The search should find matches across different file types and provide context for each match.`, + ) + + console.log("Test files created successfully") + console.log("Test files:", testFiles) + }) + + // Clean up after all tests + suiteTeardown(async () => { + // Cancel any running tasks before cleanup + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Clean up all test files + console.log("Cleaning up test files...") + for (const [key, filePath] of Object.entries(testFiles)) { + try { + await fs.unlink(filePath) + console.log(`Cleaned up ${key} test file`) + } catch (error) { + console.log(`Failed to clean up ${key} test file:`, error) + } + } + + // Clean up nested directory + try { + const nestedDir = path.join(workspaceDir, "search-test") + await fs.rmdir(nestedDir) + console.log("Cleaned up nested directory") + } catch (error) { + console.log("Failed to clean up nested directory:", error) + } + }) + + // Clean up before each test + setup(async () => { + // Cancel any previous task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + // Clean up after each test + teardown(async () => { + // Cancel the current task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + test("Should search for function definitions in JavaScript files", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + let searchResults: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution and capture results + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("search_files")) { + toolExecuted = true + console.log("search_files tool executed:", text.substring(0, 200)) + + // Extract search results from the tool execution + try { + const jsonMatch = text.match(/\{"request":".*?"\}/) + if (jsonMatch) { + const requestData = JSON.parse(jsonMatch[0]) + if (requestData.request && requestData.request.includes("Result:")) { + searchResults = requestData.request + console.log("Captured search results:", searchResults?.substring(0, 300)) + } + } + } catch (e) { + console.log("Failed to parse search results:", e) + } + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to search for function definitions + const jsFileName = path.basename(testFiles.jsFile) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `I have created test files in the workspace including a JavaScript file named "${jsFileName}" that contains function definitions like "calculateTotal" and "validateUser". Use the search_files tool with the regex pattern "function\\s+\\w+" to find all function declarations in JavaScript files. The files exist in the workspace directory.`, + }) + + console.log("Task ID:", taskId) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the search_files tool was executed + assert.ok(toolExecuted, "The search_files tool should have been executed") + + // Verify search results were captured and contain expected content + assert.ok(searchResults, "Search results should have been captured from tool execution") + + if (searchResults) { + // Check that results contain function definitions + const results = searchResults as string + const hasCalculateTotal = results.includes("calculateTotal") + const hasValidateUser = results.includes("validateUser") + const hasFormatCurrency = results.includes("formatCurrency") + const hasDebounce = results.includes("debounce") + const hasFunctionKeyword = results.includes("function") + const hasResults = results.includes("Found") && !results.includes("Found 0") + const hasAnyExpectedFunction = hasCalculateTotal || hasValidateUser || hasFormatCurrency || hasDebounce + + console.log("Search validation:") + console.log("- Has calculateTotal:", hasCalculateTotal) + console.log("- Has validateUser:", hasValidateUser) + console.log("- Has formatCurrency:", hasFormatCurrency) + console.log("- Has debounce:", hasDebounce) + console.log("- Has function keyword:", hasFunctionKeyword) + console.log("- Has results:", hasResults) + console.log("- Has any expected function:", hasAnyExpectedFunction) + + assert.ok(hasResults, "Search should return non-empty results") + assert.ok(hasFunctionKeyword, "Search results should contain 'function' keyword") + assert.ok(hasAnyExpectedFunction, "Search results should contain at least one expected function name") + } + + // Verify the AI found function definitions + const completionMessage = messages.find( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.includes("calculateTotal") || + m.text?.includes("validateUser") || + m.text?.includes("function")), + ) + assert.ok(completionMessage, "AI should have found function definitions") + + console.log("Test passed! Function definitions found successfully with validated results") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should search for TODO comments across multiple file types", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("search_files")) { + toolExecuted = true + console.log("search_files tool executed for TODO search") + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to search for TODO comments + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `I have created test files in the workspace that contain TODO comments in JavaScript, TypeScript, and text files. Use the search_files tool with the regex pattern "TODO.*" to find all TODO items across all file types. The files exist in the workspace directory.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the search_files tool was executed + assert.ok(toolExecuted, "The search_files tool should have been executed") + + // Verify the AI found TODO comments + const completionMessage = messages.find( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.includes("TODO") || + m.text?.toLowerCase().includes("found") || + m.text?.toLowerCase().includes("results")), + ) + assert.ok(completionMessage, "AI should have found TODO comments") + + console.log("Test passed! TODO comments found successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should search with file pattern filter for TypeScript files", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution with file pattern + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("search_files") && text.includes("*.ts")) { + toolExecuted = true + console.log("search_files tool executed with TypeScript filter") + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to search for interfaces in TypeScript files only + const tsFileName = path.basename(testFiles.tsFile) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `I have created test files in the workspace including a TypeScript file named "${tsFileName}" that contains interface definitions like "User" and "Product". Use the search_files tool with the regex pattern "interface\\s+\\w+" and file pattern "*.ts" to find interfaces only in TypeScript files. The files exist in the workspace directory.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the search_files tool was executed with file pattern + assert.ok(toolExecuted, "The search_files tool should have been executed with *.ts pattern") + + // Verify the AI found interface definitions + const completionMessage = messages.find( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.includes("User") || m.text?.includes("Product") || m.text?.includes("interface")), + ) + assert.ok(completionMessage, "AI should have found interface definitions in TypeScript files") + + console.log("Test passed! TypeScript interfaces found with file pattern filter") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should search for configuration keys in JSON files", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution with JSON file pattern + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("search_files") && text.includes("*.json")) { + toolExecuted = true + console.log("search_files tool executed for JSON configuration search") + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to search for configuration keys in JSON files + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Search for configuration keys in JSON files. Use the search_files tool with the regex pattern '"\\w+":\\s*' and file pattern "*.json" to find all configuration keys in JSON files.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the search_files tool was executed + assert.ok(toolExecuted, "The search_files tool should have been executed with JSON filter") + + // Verify the AI found configuration keys + const completionMessage = messages.find( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.includes("name") || + m.text?.includes("version") || + m.text?.includes("scripts") || + m.text?.includes("dependencies")), + ) + assert.ok(completionMessage, "AI should have found configuration keys in JSON files") + + console.log("Test passed! JSON configuration keys found successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should search in nested directories", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("search_files")) { + toolExecuted = true + console.log("search_files tool executed for nested directory search") + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to search in nested directories + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Search for utility functions in the current directory and subdirectories. Use the search_files tool with the regex pattern "function\\s+(format|debounce)" to find utility functions like formatCurrency and debounce.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the search_files tool was executed + assert.ok(toolExecuted, "The search_files tool should have been executed") + + // Verify the AI found utility functions in nested directories + const completionMessage = messages.find( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.includes("formatCurrency") || m.text?.includes("debounce") || m.text?.includes("nested")), + ) + assert.ok(completionMessage, "AI should have found utility functions in nested directories") + + console.log("Test passed! Nested directory search completed successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should handle complex regex patterns", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution with complex regex + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if ( + text.includes("search_files") && + (text.includes("import|export") || text.includes("(import|export)")) + ) { + toolExecuted = true + console.log("search_files tool executed with complex regex pattern") + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to search with complex regex + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Search for import and export statements in JavaScript and TypeScript files. Use the search_files tool with the regex pattern "(import|export).*" and file pattern "*.{js,ts}" to find all import/export statements.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the search_files tool was executed + assert.ok(toolExecuted, "The search_files tool should have been executed with complex regex") + + // Verify the AI found import/export statements + const completionMessage = messages.find( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.includes("export") || m.text?.includes("import") || m.text?.includes("module")), + ) + assert.ok(completionMessage, "AI should have found import/export statements") + + console.log("Test passed! Complex regex pattern search completed successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should handle search with no matches", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + let searchResults: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution and capture results + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("search_files")) { + toolExecuted = true + console.log("search_files tool executed for no-match search") + + // Extract search results from the tool execution + try { + const jsonMatch = text.match(/\{"request":".*?"\}/) + if (jsonMatch) { + const requestData = JSON.parse(jsonMatch[0]) + if (requestData.request && requestData.request.includes("Result:")) { + searchResults = requestData.request + console.log("Captured no-match search results:", searchResults?.substring(0, 300)) + } + } + } catch (e) { + console.log("Failed to parse no-match search results:", e) + } + } + } + + // Log all completion messages for debugging + if (message.type === "say" && (message.say === "completion_result" || message.say === "text")) { + console.log("AI completion message:", message.text?.substring(0, 300)) + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to search for something that doesn't exist + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Search for a pattern that doesn't exist in any files. Use the search_files tool with the regex pattern "nonExistentPattern12345" to search for something that won't be found.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the search_files tool was executed + assert.ok(toolExecuted, "The search_files tool should have been executed") + + // Verify search results were captured and show no matches + assert.ok(searchResults, "Search results should have been captured from tool execution") + + if (searchResults) { + // Check that results indicate no matches found + const results = searchResults as string + const hasZeroResults = results.includes("Found 0") || results.includes("0 results") + const hasNoMatches = + results.toLowerCase().includes("no matches") || results.toLowerCase().includes("no results") + const indicatesEmpty = hasZeroResults || hasNoMatches + + console.log("No-match search validation:") + console.log("- Has zero results indicator:", hasZeroResults) + console.log("- Has no matches indicator:", hasNoMatches) + console.log("- Indicates empty results:", indicatesEmpty) + console.log("- Search results preview:", results.substring(0, 200)) + + assert.ok(indicatesEmpty, "Search results should indicate no matches were found") + } + + // Verify the AI provided a completion response (the tool was executed successfully) + const completionMessage = messages.find( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + m.text && + m.text.length > 10, // Any substantial response + ) + + // If we have a completion message, the test passes (AI handled the no-match scenario) + if (completionMessage) { + console.log("AI provided completion response for no-match scenario") + } else { + // Fallback: check for specific no-match indicators + const noMatchMessage = messages.find( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.toLowerCase().includes("no matches") || + m.text?.toLowerCase().includes("not found") || + m.text?.toLowerCase().includes("no results") || + m.text?.toLowerCase().includes("didn't find") || + m.text?.toLowerCase().includes("0 results") || + m.text?.toLowerCase().includes("found 0") || + m.text?.toLowerCase().includes("empty") || + m.text?.toLowerCase().includes("nothing")), + ) + assert.ok(noMatchMessage, "AI should have provided a response to the no-match search") + } + + assert.ok(completionMessage, "AI should have provided a completion response") + + console.log("Test passed! No-match scenario handled correctly") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should search for class definitions and methods", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskCompleted = false + let toolExecuted = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started") { + const text = message.text || "" + if (text.includes("search_files") && (text.includes("class") || text.includes("async"))) { + toolExecuted = true + console.log("search_files tool executed for class/method search") + } + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to search for class definitions and async methods + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Search for class definitions and async methods in TypeScript files. Use the search_files tool with the regex pattern "(class\\s+\\w+|async\\s+\\w+)" and file pattern "*.ts" to find classes and async methods.`, + }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 60_000 }) + + // Verify the search_files tool was executed + assert.ok(toolExecuted, "The search_files tool should have been executed") + + // Verify the AI found class definitions and async methods + const completionMessage = messages.find( + (m) => + m.type === "say" && + (m.say === "completion_result" || m.say === "text") && + (m.text?.includes("UserService") || + m.text?.includes("class") || + m.text?.includes("async") || + m.text?.includes("getUser")), + ) + assert.ok(completionMessage, "AI should have found class definitions and async methods") + + console.log("Test passed! Class definitions and async methods found successfully") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) +}) diff --git a/apps/vscode-e2e/src/suite/tools/use-mcp-tool.test.ts b/apps/vscode-e2e/src/suite/tools/use-mcp-tool.test.ts new file mode 100644 index 0000000000..0971ec44e1 --- /dev/null +++ b/apps/vscode-e2e/src/suite/tools/use-mcp-tool.test.ts @@ -0,0 +1,925 @@ +import * as assert from "assert" +import * as fs from "fs/promises" +import * as path from "path" +import * as os from "os" +import * as vscode from "vscode" + +import type { ClineMessage } from "@roo-code/types" + +import { waitFor, sleep } from "../utils" + +suite("Roo Code use_mcp_tool Tool", () => { + let tempDir: string + let testFiles: { + simple: string + testData: string + mcpConfig: string + } + + // Create a temporary directory and test files + suiteSetup(async () => { + tempDir = await fs.mkdtemp(path.join(os.tmpdir(), "roo-test-mcp-")) + + // Create test files in VSCode workspace directory + const workspaceDir = vscode.workspace.workspaceFolders?.[0]?.uri.fsPath || tempDir + + // Create test files for MCP filesystem operations + testFiles = { + simple: path.join(workspaceDir, `mcp-test-${Date.now()}.txt`), + testData: path.join(workspaceDir, `mcp-data-${Date.now()}.json`), + mcpConfig: path.join(workspaceDir, ".roo", "mcp.json"), + } + + // Create initial test files + await fs.writeFile(testFiles.simple, "Initial content for MCP test") + await fs.writeFile(testFiles.testData, JSON.stringify({ test: "data", value: 42 }, null, 2)) + + // Create .roo directory and MCP configuration file + const rooDir = path.join(workspaceDir, ".roo") + await fs.mkdir(rooDir, { recursive: true }) + + const mcpConfig = { + mcpServers: { + filesystem: { + command: "npx", + args: ["-y", "@modelcontextprotocol/server-filesystem", workspaceDir], + alwaysAllow: [], + }, + }, + } + await fs.writeFile(testFiles.mcpConfig, JSON.stringify(mcpConfig, null, 2)) + + console.log("MCP test files created in:", workspaceDir) + console.log("Test files:", testFiles) + }) + + // Clean up temporary directory and files after tests + suiteTeardown(async () => { + // Cancel any running tasks before cleanup + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Clean up test files + for (const filePath of Object.values(testFiles)) { + try { + await fs.unlink(filePath) + } catch { + // File might not exist + } + } + + // Clean up .roo directory + const workspaceDir = vscode.workspace.workspaceFolders?.[0]?.uri.fsPath || tempDir + const rooDir = path.join(workspaceDir, ".roo") + try { + await fs.rm(rooDir, { recursive: true, force: true }) + } catch { + // Directory might not exist + } + + await fs.rm(tempDir, { recursive: true, force: true }) + }) + + // Clean up before each test + setup(async () => { + // Cancel any previous task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + // Clean up after each test + teardown(async () => { + // Cancel the current task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Small delay to ensure clean state + await sleep(100) + }) + + test("Should request MCP filesystem read_file tool and complete successfully", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let taskStarted = false + let _taskCompleted = false + let mcpToolRequested = false + let mcpToolName: string | null = null + let mcpServerResponse: string | null = null + let attemptCompletionCalled = false + let errorOccurred: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for MCP tool request + if (message.type === "ask" && message.ask === "use_mcp_server") { + mcpToolRequested = true + console.log("MCP tool request:", message.text?.substring(0, 200)) + + // Parse the MCP request to verify structure and tool name + if (message.text) { + try { + const mcpRequest = JSON.parse(message.text) + mcpToolName = mcpRequest.toolName + console.log("MCP request parsed:", { + type: mcpRequest.type, + serverName: mcpRequest.serverName, + toolName: mcpRequest.toolName, + hasArguments: !!mcpRequest.arguments, + }) + } catch (e) { + console.log("Failed to parse MCP request:", e) + } + } + } + + // Check for MCP server response + if (message.type === "say" && message.say === "mcp_server_response") { + mcpServerResponse = message.text || null + console.log("MCP server response received:", message.text?.substring(0, 200)) + } + + // Check for attempt_completion + if (message.type === "say" && message.say === "completion_result") { + attemptCompletionCalled = true + console.log("Attempt completion called:", message.text?.substring(0, 200)) + } + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + _taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + await sleep(2000) // Wait for Roo Code to fully initialize + + // Trigger MCP server detection by opening and modifying the file + console.log("Triggering MCP server detection by modifying the config file...") + try { + const mcpConfigUri = vscode.Uri.file(testFiles.mcpConfig) + const document = await vscode.workspace.openTextDocument(mcpConfigUri) + const editor = await vscode.window.showTextDocument(document) + + // Make a small modification to trigger the save event, without this Roo Code won't load the MCP server + const edit = new vscode.WorkspaceEdit() + const currentContent = document.getText() + const modifiedContent = currentContent.replace( + '"alwaysAllow": []', + '"alwaysAllow": ["read_file", "read_multiple_files", "write_file", "edit_file", "create_directory", "list_directory", "directory_tree", "move_file", "search_files", "get_file_info", "list_allowed_directories"]', + ) + + const fullRange = new vscode.Range(document.positionAt(0), document.positionAt(document.getText().length)) + + edit.replace(mcpConfigUri, fullRange, modifiedContent) + await vscode.workspace.applyEdit(edit) + + // Save the document to trigger MCP server detection + await editor.document.save() + + // Close the editor + await vscode.commands.executeCommand("workbench.action.closeActiveEditor") + + console.log("MCP config file modified and saved successfully") + } catch (error) { + console.error("Failed to modify/save MCP config file:", error) + } + + await sleep(5000) // Wait for MCP servers to initialize + let taskId: string + try { + // Start task requesting to use MCP filesystem read_file tool + const fileName = path.basename(testFiles.simple) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowMcp: true, // Enable MCP auto-approval + mcpEnabled: true, + }, + text: `Use the MCP filesystem server's read_file tool to read the file "${fileName}". The file exists in the workspace and contains "Initial content for MCP test".`, + }) + + console.log("Task ID:", taskId) + console.log("Requesting MCP filesystem read_file for:", fileName) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Wait for attempt_completion to be called (indicating task finished) + await waitFor(() => attemptCompletionCalled, { timeout: 45_000 }) + + // Verify the MCP tool was requested + assert.ok(mcpToolRequested, "The use_mcp_tool should have been requested") + + // Verify the correct tool was used + assert.strictEqual(mcpToolName, "read_file", "Should have used the read_file tool") + + // Verify we got a response from the MCP server + assert.ok(mcpServerResponse, "Should have received a response from the MCP server") + + // Verify the response contains expected file content (not an error) + const responseText = mcpServerResponse as string + + // Check for specific file content keywords + assert.ok( + responseText.includes("Initial content for MCP test"), + `MCP server response should contain the exact file content. Got: ${responseText.substring(0, 100)}...`, + ) + + // Verify it contains the specific words from our test file + assert.ok( + responseText.includes("Initial") && + responseText.includes("content") && + responseText.includes("MCP") && + responseText.includes("test"), + `MCP server response should contain all expected keywords: Initial, content, MCP, test. Got: ${responseText.substring(0, 100)}...`, + ) + + // Ensure no errors are present + assert.ok( + !responseText.toLowerCase().includes("error") && !responseText.toLowerCase().includes("failed"), + `MCP server response should not contain error messages. Got: ${responseText.substring(0, 100)}...`, + ) + + // Verify task completed successfully + assert.ok(attemptCompletionCalled, "Task should have completed with attempt_completion") + + // Check that no errors occurred + assert.strictEqual(errorOccurred, null, "No errors should have occurred") + + console.log("Test passed! MCP read_file tool used successfully and task completed") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should request MCP filesystem write_file tool and complete successfully", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let _taskCompleted = false + let mcpToolRequested = false + let mcpToolName: string | null = null + let mcpServerResponse: string | null = null + let attemptCompletionCalled = false + let errorOccurred: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for MCP tool request + if (message.type === "ask" && message.ask === "use_mcp_server") { + mcpToolRequested = true + console.log("MCP tool request:", message.text?.substring(0, 200)) + + // Parse the MCP request to verify structure and tool name + if (message.text) { + try { + const mcpRequest = JSON.parse(message.text) + mcpToolName = mcpRequest.toolName + console.log("MCP request parsed:", { + type: mcpRequest.type, + serverName: mcpRequest.serverName, + toolName: mcpRequest.toolName, + hasArguments: !!mcpRequest.arguments, + }) + } catch (e) { + console.log("Failed to parse MCP request:", e) + } + } + } + + // Check for MCP server response + if (message.type === "say" && message.say === "mcp_server_response") { + mcpServerResponse = message.text || null + console.log("MCP server response received:", message.text?.substring(0, 200)) + } + + // Check for attempt_completion + if (message.type === "say" && message.say === "completion_result") { + attemptCompletionCalled = true + console.log("Attempt completion called:", message.text?.substring(0, 200)) + } + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + _taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task requesting to use MCP filesystem write_file tool + const newFileName = `mcp-write-test-${Date.now()}.txt` + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowMcp: true, + mcpEnabled: true, + }, + text: `Use the MCP filesystem server's write_file tool to create a new file called "${newFileName}" with the content "Hello from MCP!".`, + }) + + // Wait for attempt_completion to be called (indicating task finished) + await waitFor(() => attemptCompletionCalled, { timeout: 45_000 }) + + // Verify the MCP tool was requested + assert.ok(mcpToolRequested, "The use_mcp_tool should have been requested for writing") + + // Verify the correct tool was used + assert.strictEqual(mcpToolName, "write_file", "Should have used the write_file tool") + + // Verify we got a response from the MCP server + assert.ok(mcpServerResponse, "Should have received a response from the MCP server") + + // Verify the response indicates successful file creation (not an error) + const responseText = mcpServerResponse as string + + // Check for specific success indicators + const hasSuccessKeyword = + responseText.toLowerCase().includes("success") || + responseText.toLowerCase().includes("created") || + responseText.toLowerCase().includes("written") || + responseText.toLowerCase().includes("file written") || + responseText.toLowerCase().includes("successfully") + + const hasFileName = responseText.includes(newFileName) || responseText.includes("mcp-write-test") + + assert.ok( + hasSuccessKeyword || hasFileName, + `MCP server response should indicate successful file creation with keywords like 'success', 'created', 'written' or contain the filename '${newFileName}'. Got: ${responseText.substring(0, 150)}...`, + ) + + // Ensure no errors are present + assert.ok( + !responseText.toLowerCase().includes("error") && !responseText.toLowerCase().includes("failed"), + `MCP server response should not contain error messages. Got: ${responseText.substring(0, 100)}...`, + ) + + // Verify task completed successfully + assert.ok(attemptCompletionCalled, "Task should have completed with attempt_completion") + + // Check that no errors occurred + assert.strictEqual(errorOccurred, null, "No errors should have occurred") + + console.log("Test passed! MCP write_file tool used successfully and task completed") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should request MCP filesystem list_directory tool and complete successfully", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let _taskCompleted = false + let mcpToolRequested = false + let mcpToolName: string | null = null + let mcpServerResponse: string | null = null + let attemptCompletionCalled = false + let errorOccurred: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for MCP tool request + if (message.type === "ask" && message.ask === "use_mcp_server") { + mcpToolRequested = true + console.log("MCP tool request:", message.text?.substring(0, 300)) + + // Parse the MCP request to verify structure and tool name + if (message.text) { + try { + const mcpRequest = JSON.parse(message.text) + mcpToolName = mcpRequest.toolName + console.log("MCP request parsed:", { + type: mcpRequest.type, + serverName: mcpRequest.serverName, + toolName: mcpRequest.toolName, + hasArguments: !!mcpRequest.arguments, + }) + } catch (e) { + console.log("Failed to parse MCP request:", e) + } + } + } + + // Check for MCP server response + if (message.type === "say" && message.say === "mcp_server_response") { + mcpServerResponse = message.text || null + console.log("MCP server response received:", message.text?.substring(0, 200)) + } + + // Check for attempt_completion + if (message.type === "say" && message.say === "completion_result") { + attemptCompletionCalled = true + console.log("Attempt completion called:", message.text?.substring(0, 200)) + } + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + _taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task requesting MCP filesystem list_directory tool + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowMcp: true, + mcpEnabled: true, + }, + text: `Use the MCP filesystem server's list_directory tool to list the contents of the current directory. I want to see the files in the workspace.`, + }) + + // Wait for attempt_completion to be called (indicating task finished) + await waitFor(() => attemptCompletionCalled, { timeout: 45_000 }) + + // Verify the MCP tool was requested + assert.ok(mcpToolRequested, "The use_mcp_tool should have been requested") + + // Verify the correct tool was used + assert.strictEqual(mcpToolName, "list_directory", "Should have used the list_directory tool") + + // Verify we got a response from the MCP server + assert.ok(mcpServerResponse, "Should have received a response from the MCP server") + + // Verify the response contains directory listing (not an error) + const responseText = mcpServerResponse as string + + // Check for specific directory contents - our test files should be listed + const hasTestFile = + responseText.includes("mcp-test-") || responseText.includes(path.basename(testFiles.simple)) + const hasDataFile = + responseText.includes("mcp-data-") || responseText.includes(path.basename(testFiles.testData)) + const hasRooDir = responseText.includes(".roo") + + // At least one of our test files or the .roo directory should be present + assert.ok( + hasTestFile || hasDataFile || hasRooDir, + `MCP server response should contain our test files or .roo directory. Expected to find: '${path.basename(testFiles.simple)}', '${path.basename(testFiles.testData)}', or '.roo'. Got: ${responseText.substring(0, 200)}...`, + ) + + // Check for typical directory listing indicators + const hasDirectoryStructure = + responseText.includes("name") || + responseText.includes("type") || + responseText.includes("file") || + responseText.includes("directory") || + responseText.includes(".txt") || + responseText.includes(".json") + + assert.ok( + hasDirectoryStructure, + `MCP server response should contain directory structure indicators like 'name', 'type', 'file', 'directory', or file extensions. Got: ${responseText.substring(0, 200)}...`, + ) + + // Ensure no errors are present + assert.ok( + !responseText.toLowerCase().includes("error") && !responseText.toLowerCase().includes("failed"), + `MCP server response should not contain error messages. Got: ${responseText.substring(0, 100)}...`, + ) + + // Verify task completed successfully + assert.ok(attemptCompletionCalled, "Task should have completed with attempt_completion") + + // Check that no errors occurred + assert.strictEqual(errorOccurred, null, "No errors should have occurred") + + console.log("Test passed! MCP list_directory tool used successfully and task completed") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should request MCP filesystem directory_tree tool and complete successfully", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let _taskCompleted = false + let mcpToolRequested = false + let mcpToolName: string | null = null + let mcpServerResponse: string | null = null + let attemptCompletionCalled = false + let errorOccurred: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for MCP tool request + if (message.type === "ask" && message.ask === "use_mcp_server") { + mcpToolRequested = true + console.log("MCP tool request:", message.text?.substring(0, 200)) + + // Parse the MCP request to verify structure and tool name + if (message.text) { + try { + const mcpRequest = JSON.parse(message.text) + mcpToolName = mcpRequest.toolName + console.log("MCP request parsed:", { + type: mcpRequest.type, + serverName: mcpRequest.serverName, + toolName: mcpRequest.toolName, + hasArguments: !!mcpRequest.arguments, + }) + } catch (e) { + console.log("Failed to parse MCP request:", e) + } + } + } + + // Check for MCP server response + if (message.type === "say" && message.say === "mcp_server_response") { + mcpServerResponse = message.text || null + console.log("MCP server response received:", message.text?.substring(0, 200)) + } + + // Check for attempt_completion + if (message.type === "say" && message.say === "completion_result") { + attemptCompletionCalled = true + console.log("Attempt completion called:", message.text?.substring(0, 200)) + } + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + _taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task requesting MCP filesystem directory_tree tool + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowMcp: true, + mcpEnabled: true, + }, + text: `Use the MCP filesystem server's directory_tree tool to show me the directory structure of the current workspace. I want to see the folder hierarchy.`, + }) + + // Wait for attempt_completion to be called (indicating task finished) + await waitFor(() => attemptCompletionCalled, { timeout: 45_000 }) + + // Verify the MCP tool was requested + assert.ok(mcpToolRequested, "The use_mcp_tool should have been requested") + + // Verify the correct tool was used + assert.strictEqual(mcpToolName, "directory_tree", "Should have used the directory_tree tool") + + // Verify we got a response from the MCP server + assert.ok(mcpServerResponse, "Should have received a response from the MCP server") + + // Verify the response contains directory tree structure (not an error) + const responseText = mcpServerResponse as string + + // Check for tree structure elements (be flexible as different MCP servers format differently) + const hasTreeStructure = + responseText.includes("name") || + responseText.includes("type") || + responseText.includes("children") || + responseText.includes("file") || + responseText.includes("directory") + + // Check for our test files or common file extensions + const hasTestFiles = + responseText.includes("mcp-test-") || + responseText.includes("mcp-data-") || + responseText.includes(".roo") || + responseText.includes(".txt") || + responseText.includes(".json") || + responseText.length > 10 // At least some content indicating directory structure + + assert.ok( + hasTreeStructure, + `MCP server response should contain tree structure indicators like 'name', 'type', 'children', 'file', or 'directory'. Got: ${responseText.substring(0, 200)}...`, + ) + + assert.ok( + hasTestFiles, + `MCP server response should contain directory contents (test files, extensions, or substantial content). Got: ${responseText.substring(0, 200)}...`, + ) + + // Ensure no errors are present + assert.ok( + !responseText.toLowerCase().includes("error") && !responseText.toLowerCase().includes("failed"), + `MCP server response should not contain error messages. Got: ${responseText.substring(0, 100)}...`, + ) + + // Verify task completed successfully + assert.ok(attemptCompletionCalled, "Task should have completed with attempt_completion") + + // Check that no errors occurred + assert.strictEqual(errorOccurred, null, "No errors should have occurred") + + console.log("Test passed! MCP directory_tree tool used successfully and task completed") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test.skip("Should handle MCP server error gracefully and complete task", async function () { + // Skipped: This test requires interactive approval for non-whitelisted MCP servers + // which cannot be automated in the test environment + const api = globalThis.api + const messages: ClineMessage[] = [] + let _taskCompleted = false + let _mcpToolRequested = false + let _errorHandled = false + let attemptCompletionCalled = false + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for MCP tool request + if (message.type === "ask" && message.ask === "use_mcp_server") { + _mcpToolRequested = true + console.log("MCP tool request:", message.text?.substring(0, 200)) + } + + // Check for error handling + if (message.type === "say" && (message.say === "error" || message.say === "mcp_server_response")) { + if (message.text && (message.text.includes("Error") || message.text.includes("not found"))) { + _errorHandled = true + console.log("MCP error handled:", message.text.substring(0, 100)) + } + } + + // Check for attempt_completion + if (message.type === "say" && message.say === "completion_result") { + attemptCompletionCalled = true + console.log("Attempt completion called:", message.text?.substring(0, 200)) + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + _taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task requesting non-existent MCP server + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowMcp: true, + mcpEnabled: true, + }, + text: `Use the MCP server "nonexistent-server" to perform some operation. This should trigger an error but the task should still complete gracefully.`, + }) + + // Wait for attempt_completion to be called (indicating task finished) + await waitFor(() => attemptCompletionCalled, { timeout: 45_000 }) + + // Verify task completed successfully even with error + assert.ok(attemptCompletionCalled, "Task should have completed with attempt_completion even with MCP error") + + console.log("Test passed! MCP error handling verified and task completed") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should validate MCP request message format and complete successfully", async function () { + const api = globalThis.api + const messages: ClineMessage[] = [] + let _taskCompleted = false + let mcpToolRequested = false + let validMessageFormat = false + let mcpToolName: string | null = null + let mcpServerResponse: string | null = null + let attemptCompletionCalled = false + let errorOccurred: string | null = null + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for MCP tool request and validate format + if (message.type === "ask" && message.ask === "use_mcp_server") { + mcpToolRequested = true + console.log("MCP tool request:", message.text?.substring(0, 200)) + + // Validate the message format matches ClineAskUseMcpServer interface + if (message.text) { + try { + const mcpRequest = JSON.parse(message.text) + mcpToolName = mcpRequest.toolName + + // Check required fields + const hasType = typeof mcpRequest.type === "string" + const hasServerName = typeof mcpRequest.serverName === "string" + const validType = + mcpRequest.type === "use_mcp_tool" || mcpRequest.type === "access_mcp_resource" + + if (hasType && hasServerName && validType) { + validMessageFormat = true + console.log("Valid MCP message format detected:", { + type: mcpRequest.type, + serverName: mcpRequest.serverName, + toolName: mcpRequest.toolName, + hasArguments: !!mcpRequest.arguments, + }) + } + } catch (e) { + console.log("Failed to parse MCP request:", e) + } + } + } + + // Check for MCP server response + if (message.type === "say" && message.say === "mcp_server_response") { + mcpServerResponse = message.text || null + console.log("MCP server response received:", message.text?.substring(0, 200)) + } + + // Check for attempt_completion + if (message.type === "say" && message.say === "completion_result") { + attemptCompletionCalled = true + console.log("Attempt completion called:", message.text?.substring(0, 200)) + } + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + } + api.on("message", messageHandler) + + // Listen for task completion + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + _taskCompleted = true + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task requesting MCP filesystem get_file_info tool + const fileName = path.basename(testFiles.simple) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowMcp: true, + mcpEnabled: true, + }, + text: `Use the MCP filesystem server's get_file_info tool to get information about the file "${fileName}". This file exists in the workspace and will validate proper message formatting.`, + }) + + // Wait for attempt_completion to be called (indicating task finished) + await waitFor(() => attemptCompletionCalled, { timeout: 45_000 }) + + // Verify the MCP tool was requested with valid format + assert.ok(mcpToolRequested, "The use_mcp_tool should have been requested") + assert.ok(validMessageFormat, "The MCP request should have valid message format") + + // Verify the correct tool was used + assert.strictEqual(mcpToolName, "get_file_info", "Should have used the get_file_info tool") + + // Verify we got a response from the MCP server + assert.ok(mcpServerResponse, "Should have received a response from the MCP server") + + // Verify the response contains file information (not an error) + const responseText = mcpServerResponse as string + + // Check for specific file metadata fields + const hasSize = responseText.includes("size") && (responseText.includes("28") || /\d+/.test(responseText)) + const hasTimestamps = + responseText.includes("created") || + responseText.includes("modified") || + responseText.includes("accessed") + const hasDateInfo = + responseText.includes("2025") || responseText.includes("GMT") || /\d{4}-\d{2}-\d{2}/.test(responseText) + + assert.ok( + hasSize, + `MCP server response should contain file size information. Expected 'size' with a number (like 28 bytes for our test file). Got: ${responseText.substring(0, 200)}...`, + ) + + assert.ok( + hasTimestamps, + `MCP server response should contain timestamp information like 'created', 'modified', or 'accessed'. Got: ${responseText.substring(0, 200)}...`, + ) + + assert.ok( + hasDateInfo, + `MCP server response should contain date/time information (year, GMT timezone, or ISO date format). Got: ${responseText.substring(0, 200)}...`, + ) + + // Note: get_file_info typically returns metadata only, not the filename itself + // So we'll focus on validating the metadata structure instead of filename reference + const hasValidMetadata = + (hasSize && hasTimestamps) || (hasSize && hasDateInfo) || (hasTimestamps && hasDateInfo) + + assert.ok( + hasValidMetadata, + `MCP server response should contain valid file metadata (combination of size, timestamps, and date info). Got: ${responseText.substring(0, 200)}...`, + ) + + // Ensure no errors are present + assert.ok( + !responseText.toLowerCase().includes("error") && !responseText.toLowerCase().includes("failed"), + `MCP server response should not contain error messages. Got: ${responseText.substring(0, 100)}...`, + ) + + // Verify task completed successfully + assert.ok(attemptCompletionCalled, "Task should have completed with attempt_completion") + + // Check that no errors occurred + assert.strictEqual(errorOccurred, null, "No errors should have occurred") + + console.log("Test passed! MCP message format validation successful and task completed") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) +}) diff --git a/apps/vscode-e2e/src/suite/tools/write-to-file.test.ts b/apps/vscode-e2e/src/suite/tools/write-to-file.test.ts new file mode 100644 index 0000000000..c07282bb87 --- /dev/null +++ b/apps/vscode-e2e/src/suite/tools/write-to-file.test.ts @@ -0,0 +1,445 @@ +import * as assert from "assert" +import * as fs from "fs/promises" +import * as path from "path" +import * as os from "os" + +import type { ClineMessage } from "@roo-code/types" + +import { waitFor, sleep } from "../utils" + +suite("Roo Code write_to_file Tool", () => { + let tempDir: string + let testFilePath: string + + // Create a temporary directory for test files + suiteSetup(async () => { + tempDir = await fs.mkdtemp(path.join(os.tmpdir(), "roo-test-")) + }) + + // Clean up temporary directory after tests + suiteTeardown(async () => { + // Cancel any running tasks before cleanup + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + await fs.rm(tempDir, { recursive: true, force: true }) + }) + + // Clean up test file before each test + setup(async () => { + // Cancel any previous task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Generate unique file name for each test to avoid conflicts + testFilePath = path.join(tempDir, `test-file-${Date.now()}.txt`) + + // Small delay to ensure clean state + await sleep(100) + }) + + // Clean up after each test + teardown(async () => { + // Cancel the current task + try { + await globalThis.api.cancelCurrentTask() + } catch { + // Task might not be running + } + + // Clean up the test file + try { + await fs.unlink(testFilePath) + } catch { + // File might not exist + } + + // Small delay to ensure clean state + await sleep(100) + }) + + test("Should create a new file with content", async function () { + // Increase timeout for this specific test + + const api = globalThis.api + const messages: ClineMessage[] = [] + const fileContent = "Hello, this is a test file!" + let taskStarted = false + let taskCompleted = false + let errorOccurred: string | null = null + let writeToFileToolExecuted = false + let toolExecutionDetails = "" + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started") { + console.log("Tool execution:", message.text?.substring(0, 200)) + if (message.text && message.text.includes("write_to_file")) { + writeToFileToolExecuted = true + toolExecutionDetails = message.text + // Try to parse the tool execution details + try { + const parsed = JSON.parse(message.text) + console.log("write_to_file tool called with request:", parsed.request?.substring(0, 300)) + } catch (_e) { + console.log("Could not parse tool execution details") + } + } + } + + // Log important messages for debugging + if (message.type === "say" && message.say === "error") { + errorOccurred = message.text || "Unknown error" + console.error("Error:", message.text) + } + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + if (message.type === "say" && (message.say === "completion_result" || message.say === "text")) { + console.log("AI response:", message.text?.substring(0, 200)) + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task with a very simple prompt + const baseFileName = path.basename(testFilePath) + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Create a file named "${baseFileName}" with the following content:\n${fileContent}`, + }) + + console.log("Task ID:", taskId) + console.log("Base filename:", baseFileName) + console.log("Expecting file at:", testFilePath) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Check for early errors + if (errorOccurred) { + console.error("Early error detected:", errorOccurred) + } + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 45_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // The file might be created in different locations, let's check them all + const possibleLocations = [ + testFilePath, // Expected location + path.join(tempDir, baseFileName), // In temp directory + path.join(process.cwd(), baseFileName), // In current working directory + path.join("/tmp/roo-test-workspace-" + "*", baseFileName), // In workspace created by runTest.ts + ] + + let fileFound = false + let actualFilePath = "" + let actualContent = "" + + // First check the workspace directory that was created + const workspaceDirs = await fs + .readdir("/tmp") + .then((files) => files.filter((f) => f.startsWith("roo-test-workspace-"))) + .catch(() => []) + + for (const wsDir of workspaceDirs) { + const wsFilePath = path.join("/tmp", wsDir, baseFileName) + try { + await fs.access(wsFilePath) + fileFound = true + actualFilePath = wsFilePath + actualContent = await fs.readFile(wsFilePath, "utf-8") + console.log("File found in workspace directory:", wsFilePath) + break + } catch { + // Continue checking + } + } + + // If not found in workspace, check other locations + if (!fileFound) { + for (const location of possibleLocations) { + try { + await fs.access(location) + fileFound = true + actualFilePath = location + actualContent = await fs.readFile(location, "utf-8") + console.log("File found at:", location) + break + } catch { + // Continue checking + } + } + } + + // If still not found, list directories to help debug + if (!fileFound) { + console.log("File not found in expected locations. Debugging info:") + + // List temp directory + try { + const tempFiles = await fs.readdir(tempDir) + console.log("Files in temp directory:", tempFiles) + } catch (e) { + console.log("Could not list temp directory:", e) + } + + // List current working directory + try { + const cwdFiles = await fs.readdir(process.cwd()) + console.log( + "Files in CWD:", + cwdFiles.filter((f) => f.includes("test-file")), + ) + } catch (e) { + console.log("Could not list CWD:", e) + } + + // List /tmp for test files + try { + const tmpFiles = await fs.readdir("/tmp") + console.log( + "Test files in /tmp:", + tmpFiles.filter((f) => f.includes("test-file") || f.includes("roo-test")), + ) + } catch (e) { + console.log("Could not list /tmp:", e) + } + } + + assert.ok(fileFound, `File should have been created. Expected filename: ${baseFileName}`) + assert.strictEqual(actualContent.trim(), fileContent, "File content should match expected content") + + // Verify that write_to_file tool was actually executed + assert.ok(writeToFileToolExecuted, "write_to_file tool should have been executed") + assert.ok( + toolExecutionDetails.includes(baseFileName) || toolExecutionDetails.includes(fileContent), + "Tool execution should include the filename or content", + ) + + console.log("Test passed! File created successfully at:", actualFilePath) + console.log("write_to_file tool was properly executed") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) + + test("Should create nested directories when writing file", async function () { + // Increase timeout for this specific test + + const api = globalThis.api + const messages: ClineMessage[] = [] + const content = "File in nested directory" + const fileName = `file-${Date.now()}.txt` + const nestedPath = path.join(tempDir, "nested", "deep", "directory", fileName) + let taskStarted = false + let taskCompleted = false + let writeToFileToolExecuted = false + let toolExecutionDetails = "" + + // Listen for messages + const messageHandler = ({ message }: { message: ClineMessage }) => { + messages.push(message) + + // Check for tool execution + if (message.type === "say" && message.say === "api_req_started") { + console.log("Tool execution:", message.text?.substring(0, 200)) + if (message.text && message.text.includes("write_to_file")) { + writeToFileToolExecuted = true + toolExecutionDetails = message.text + // Try to parse the tool execution details + try { + const parsed = JSON.parse(message.text) + console.log("write_to_file tool called with request:", parsed.request?.substring(0, 300)) + } catch (_e) { + console.log("Could not parse tool execution details") + } + } + } + + if (message.type === "ask" && message.ask === "tool") { + console.log("Tool request:", message.text?.substring(0, 200)) + } + } + api.on("message", messageHandler) + + // Listen for task events + const taskStartedHandler = (id: string) => { + if (id === taskId) { + taskStarted = true + console.log("Task started:", id) + } + } + api.on("taskStarted", taskStartedHandler) + + const taskCompletedHandler = (id: string) => { + if (id === taskId) { + taskCompleted = true + console.log("Task completed:", id) + } + } + api.on("taskCompleted", taskCompletedHandler) + + let taskId: string + try { + // Start task to create file in nested directory + taskId = await api.startNewTask({ + configuration: { + mode: "code", + autoApprovalEnabled: true, + alwaysAllowWrite: true, + alwaysAllowReadOnly: true, + alwaysAllowReadOnlyOutsideWorkspace: true, + }, + text: `Create a file named "${fileName}" in a nested directory structure "nested/deep/directory/" with the following content:\n${content}`, + }) + + console.log("Task ID:", taskId) + console.log("Expected nested path:", nestedPath) + + // Wait for task to start + await waitFor(() => taskStarted, { timeout: 45_000 }) + + // Wait for task completion + await waitFor(() => taskCompleted, { timeout: 45_000 }) + + // Give extra time for file system operations + await sleep(2000) + + // Check various possible locations + let fileFound = false + let actualFilePath = "" + let actualContent = "" + + // Check workspace directories + const workspaceDirs = await fs + .readdir("/tmp") + .then((files) => files.filter((f) => f.startsWith("roo-test-workspace-"))) + .catch(() => []) + + for (const wsDir of workspaceDirs) { + // Check in nested structure within workspace + const wsNestedPath = path.join("/tmp", wsDir, "nested", "deep", "directory", fileName) + try { + await fs.access(wsNestedPath) + fileFound = true + actualFilePath = wsNestedPath + actualContent = await fs.readFile(wsNestedPath, "utf-8") + console.log("File found in workspace nested directory:", wsNestedPath) + break + } catch { + // Also check if file was created directly in workspace root + const wsFilePath = path.join("/tmp", wsDir, fileName) + try { + await fs.access(wsFilePath) + fileFound = true + actualFilePath = wsFilePath + actualContent = await fs.readFile(wsFilePath, "utf-8") + console.log("File found in workspace root (nested dirs not created):", wsFilePath) + break + } catch { + // Continue checking + } + } + } + + // If not found in workspace, check the expected location + if (!fileFound) { + try { + await fs.access(nestedPath) + fileFound = true + actualFilePath = nestedPath + actualContent = await fs.readFile(nestedPath, "utf-8") + console.log("File found at expected nested path:", nestedPath) + } catch { + // File not found + } + } + + // Debug output if file not found + if (!fileFound) { + console.log("File not found. Debugging info:") + + // List workspace directories and their contents + for (const wsDir of workspaceDirs) { + const wsPath = path.join("/tmp", wsDir) + try { + const files = await fs.readdir(wsPath) + console.log(`Files in workspace ${wsDir}:`, files) + + // Check if nested directory was created + const nestedDir = path.join(wsPath, "nested") + try { + await fs.access(nestedDir) + console.log("Nested directory exists in workspace") + } catch { + console.log("Nested directory NOT created in workspace") + } + } catch (e) { + console.log(`Could not list workspace ${wsDir}:`, e) + } + } + } + + assert.ok(fileFound, `File should have been created. Expected filename: ${fileName}`) + assert.strictEqual(actualContent.trim(), content, "File content should match") + + // Verify that write_to_file tool was actually executed + assert.ok(writeToFileToolExecuted, "write_to_file tool should have been executed") + assert.ok( + toolExecutionDetails.includes(fileName) || + toolExecutionDetails.includes(content) || + toolExecutionDetails.includes("nested"), + "Tool execution should include the filename, content, or nested directory reference", + ) + + // Note: We're not checking if the nested directory structure was created, + // just that the file exists with the correct content + console.log("Test passed! File created successfully at:", actualFilePath) + console.log("write_to_file tool was properly executed") + } finally { + // Clean up + api.off("message", messageHandler) + api.off("taskStarted", taskStartedHandler) + api.off("taskCompleted", taskCompletedHandler) + } + }) +}) From 8b6f5f8baa0d7ec4a7c297a3dbe5ff5459a80451 Mon Sep 17 00:00:00 2001 From: Edwin P Jacques Date: Thu, 12 Jun 2025 11:59:45 -0400 Subject: [PATCH 10/33] update xai models and pricing (#4315) * update xai models and pricing * cache accounting for xAI * change log --- .changeset/cruel-roses-stick.md | 5 + packages/types/src/providers/xai.ts | 168 ++++++------------------ src/api/providers/__tests__/xai.test.ts | 8 +- src/api/providers/xai.ts | 18 ++- 4 files changed, 62 insertions(+), 137 deletions(-) create mode 100644 .changeset/cruel-roses-stick.md diff --git a/.changeset/cruel-roses-stick.md b/.changeset/cruel-roses-stick.md new file mode 100644 index 0000000000..9f661d7d07 --- /dev/null +++ b/.changeset/cruel-roses-stick.md @@ -0,0 +1,5 @@ +--- +"@roo-code/types": patch +--- + +Update x.ai supported models and metadata. Ensure accurate cost accounting. diff --git a/packages/types/src/providers/xai.ts b/packages/types/src/providers/xai.ts index ccb8549fcd..4f2cedd14b 100644 --- a/packages/types/src/providers/xai.ts +++ b/packages/types/src/providers/xai.ts @@ -6,100 +6,6 @@ export type XAIModelId = keyof typeof xaiModels export const xaiDefaultModelId: XAIModelId = "grok-3" export const xaiModels = { - "grok-3-beta": { - maxTokens: 8192, - contextWindow: 131072, - supportsImages: false, - supportsPromptCache: false, - inputPrice: 3.0, - outputPrice: 15.0, - description: "xAI's Grok-3 beta model with 131K context window", - }, - "grok-3-fast-beta": { - maxTokens: 8192, - contextWindow: 131072, - supportsImages: false, - supportsPromptCache: false, - inputPrice: 5.0, - outputPrice: 25.0, - description: "xAI's Grok-3 fast beta model with 131K context window", - }, - "grok-3-mini-beta": { - maxTokens: 8192, - contextWindow: 131072, - supportsImages: false, - supportsPromptCache: false, - inputPrice: 0.3, - outputPrice: 0.5, - description: "xAI's Grok-3 mini beta model with 131K context window", - supportsReasoningEffort: true, - }, - "grok-3-mini-fast-beta": { - maxTokens: 8192, - contextWindow: 131072, - supportsImages: false, - supportsPromptCache: false, - inputPrice: 0.6, - outputPrice: 4.0, - description: "xAI's Grok-3 mini fast beta model with 131K context window", - supportsReasoningEffort: true, - }, - "grok-3": { - maxTokens: 8192, - contextWindow: 131072, - supportsImages: false, - supportsPromptCache: false, - inputPrice: 3.0, - outputPrice: 15.0, - description: "xAI's Grok-3 model with 131K context window", - }, - "grok-3-fast": { - maxTokens: 8192, - contextWindow: 131072, - supportsImages: false, - supportsPromptCache: false, - inputPrice: 5.0, - outputPrice: 25.0, - description: "xAI's Grok-3 fast model with 131K context window", - }, - "grok-3-mini": { - maxTokens: 8192, - contextWindow: 131072, - supportsImages: false, - supportsPromptCache: false, - inputPrice: 0.3, - outputPrice: 0.5, - description: "xAI's Grok-3 mini model with 131K context window", - supportsReasoningEffort: true, - }, - "grok-3-mini-fast": { - maxTokens: 8192, - contextWindow: 131072, - supportsImages: false, - supportsPromptCache: false, - inputPrice: 0.6, - outputPrice: 4.0, - description: "xAI's Grok-3 mini fast model with 131K context window", - supportsReasoningEffort: true, - }, - "grok-2-latest": { - maxTokens: 8192, - contextWindow: 131072, - supportsImages: false, - supportsPromptCache: false, - inputPrice: 2.0, - outputPrice: 10.0, - description: "xAI's Grok-2 model - latest version with 131K context window", - }, - "grok-2": { - maxTokens: 8192, - contextWindow: 131072, - supportsImages: false, - supportsPromptCache: false, - inputPrice: 2.0, - outputPrice: 10.0, - description: "xAI's Grok-2 model with 131K context window", - }, "grok-2-1212": { maxTokens: 8192, contextWindow: 131072, @@ -107,25 +13,7 @@ export const xaiModels = { supportsPromptCache: false, inputPrice: 2.0, outputPrice: 10.0, - description: "xAI's Grok-2 model (version 1212) with 131K context window", - }, - "grok-2-vision-latest": { - maxTokens: 8192, - contextWindow: 32768, - supportsImages: true, - supportsPromptCache: false, - inputPrice: 2.0, - outputPrice: 10.0, - description: "xAI's Grok-2 Vision model - latest version with image support and 32K context window", - }, - "grok-2-vision": { - maxTokens: 8192, - contextWindow: 32768, - supportsImages: true, - supportsPromptCache: false, - inputPrice: 2.0, - outputPrice: 10.0, - description: "xAI's Grok-2 Vision model with image support and 32K context window", + description: "xAI's Grok-2 model (version 1212) with 128K context window", }, "grok-2-vision-1212": { maxTokens: 8192, @@ -136,22 +24,50 @@ export const xaiModels = { outputPrice: 10.0, description: "xAI's Grok-2 Vision model (version 1212) with image support and 32K context window", }, - "grok-vision-beta": { - maxTokens: 8192, - contextWindow: 8192, - supportsImages: true, - supportsPromptCache: false, - inputPrice: 5.0, - outputPrice: 15.0, - description: "xAI's Grok Vision Beta model with image support and 8K context window", - }, - "grok-beta": { + "grok-3": { maxTokens: 8192, contextWindow: 131072, supportsImages: false, - supportsPromptCache: false, - inputPrice: 5.0, + supportsPromptCache: true, + inputPrice: 3.0, outputPrice: 15.0, - description: "xAI's Grok Beta model (legacy) with 131K context window", + cacheWritesPrice: 0.75, + cacheReadsPrice: 0.75, + description: "xAI's Grok-3 model with 128K context window", + }, + "grok-3-fast": { + maxTokens: 8192, + contextWindow: 131072, + supportsImages: false, + supportsPromptCache: true, + inputPrice: 5.0, + outputPrice: 25.0, + cacheWritesPrice: 1.25, + cacheReadsPrice: 1.25, + description: "xAI's Grok-3 fast model with 128K context window", + }, + "grok-3-mini": { + maxTokens: 8192, + contextWindow: 131072, + supportsImages: false, + supportsPromptCache: true, + inputPrice: 0.3, + outputPrice: 0.5, + cacheWritesPrice: 0.07, + cacheReadsPrice: 0.07, + description: "xAI's Grok-3 mini model with 128K context window", + supportsReasoningEffort: true, + }, + "grok-3-mini-fast": { + maxTokens: 8192, + contextWindow: 131072, + supportsImages: false, + supportsPromptCache: true, + inputPrice: 0.6, + outputPrice: 4.0, + cacheWritesPrice: 0.15, + cacheReadsPrice: 0.15, + description: "xAI's Grok-3 mini fast model with 128K context window", + supportsReasoningEffort: true, }, } as const satisfies Record diff --git a/src/api/providers/__tests__/xai.test.ts b/src/api/providers/__tests__/xai.test.ts index 41adc5fb32..c1bbd0674e 100644 --- a/src/api/providers/__tests__/xai.test.ts +++ b/src/api/providers/__tests__/xai.test.ts @@ -62,7 +62,7 @@ describe("XAIHandler", () => { }) test("should return specified model when valid model is provided", () => { - const testModelId = "grok-2-latest" + const testModelId = "grok-3" const handlerWithModel = new XAIHandler({ apiModelId: testModelId }) const model = handlerWithModel.getModel() @@ -72,7 +72,7 @@ describe("XAIHandler", () => { test("should include reasoning_effort parameter for mini models", async () => { const miniModelHandler = new XAIHandler({ - apiModelId: "grok-3-mini-beta", + apiModelId: "grok-3-mini", reasoningEffort: "high", }) @@ -101,7 +101,7 @@ describe("XAIHandler", () => { test("should not include reasoning_effort parameter for non-mini models", async () => { const regularModelHandler = new XAIHandler({ - apiModelId: "grok-2-latest", + apiModelId: "grok-3", reasoningEffort: "high", }) @@ -255,7 +255,7 @@ describe("XAIHandler", () => { test("createMessage should pass correct parameters to OpenAI client", async () => { // Setup a handler with specific model - const modelId = "grok-2-latest" + const modelId = "grok-3" const modelInfo = xaiModels[modelId] const handlerWithModel = new XAIHandler({ apiModelId: modelId }) diff --git a/src/api/providers/xai.ts b/src/api/providers/xai.ts index adcd0d92bf..596c9e89b8 100644 --- a/src/api/providers/xai.ts +++ b/src/api/providers/xai.ts @@ -76,17 +76,21 @@ export class XAIHandler extends BaseProvider implements SingleCompletionHandler } if (chunk.usage) { + // Extract detailed token information if available + // First check for prompt_tokens_details structure (real API response) + const promptDetails = "prompt_tokens_details" in chunk.usage ? chunk.usage.prompt_tokens_details : null; + const cachedTokens = promptDetails && "cached_tokens" in promptDetails ? promptDetails.cached_tokens : 0; + + // Fall back to direct fields in usage (used in test mocks) + const readTokens = cachedTokens || ("cache_read_input_tokens" in chunk.usage ? (chunk.usage as any).cache_read_input_tokens : 0); + const writeTokens = "cache_creation_input_tokens" in chunk.usage ? (chunk.usage as any).cache_creation_input_tokens : 0; + yield { type: "usage", inputTokens: chunk.usage.prompt_tokens || 0, outputTokens: chunk.usage.completion_tokens || 0, - // X.AI might include these fields in the future, handle them if present. - cacheReadTokens: - "cache_read_input_tokens" in chunk.usage ? (chunk.usage as any).cache_read_input_tokens : 0, - cacheWriteTokens: - "cache_creation_input_tokens" in chunk.usage - ? (chunk.usage as any).cache_creation_input_tokens - : 0, + cacheReadTokens: readTokens, + cacheWriteTokens: writeTokens, } } } From 7bed94454af860ca085b65ea2783b7cbca3547db Mon Sep 17 00:00:00 2001 From: Sam Hoang Van Date: Thu, 12 Jun 2025 23:36:34 +0700 Subject: [PATCH 11/33] feat: Enhance apply_diff with XML for multi-file/multi-diff operations & batch UI (#3342) * feat: add BatchDiffApproval component for multi-file diff application - Introduced a new component `BatchDiffApproval` to handle the approval of batch changes across multiple files. - Integrated the `BatchDiffApproval` component into `ChatRow` to display batch diff requests. - Updated experimental settings to include a toggle for multi-file apply diff functionality. - Enhanced localization files to support new strings related to batch changes in multiple languages. - Updated tests to cover the new multi-file apply diff feature. * revert this * fix: update applyDiff parameter type to accept string or DiffItem * refactor: keep original file name for apply diff tool * revert this * Update src/core/webview/__tests__/ClineProvider.test.ts * revert this * fix: keep the original path if the experiment is disabled * test: add dynamic strategy selection tests for MultiSearchReplaceDiffStrategy and MultiFileSearchReplaceDiffStrategy * fix: mock applyDiffTool module and ensure legacy tool resolves successfully in tests * remove this * ellipsis suggestion Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> * refactor: mirror concurrent file reads --------- Co-authored-by: Daniel Riccio Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com> Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> --- packages/types/src/experiment.ts | 8 +- .../presentAssistantMessage.ts | 32 +- .../strategies/multi-file-search-replace.ts | 735 ++++++++++++++++++ src/core/prompts/__tests__/sections.test.ts | 4 +- src/core/task/Task.ts | 21 +- src/core/task/__tests__/Task.test.ts | 105 +++ .../applyDiffTool.experiment.spec.ts | 150 ++++ src/core/tools/applyDiffTool.ts | 2 +- src/core/tools/multiApplyDiffTool.ts | 570 ++++++++++++++ src/core/webview/generateSystemPrompt.ts | 12 +- src/shared/ExtensionMessage.ts | 11 + src/shared/__tests__/experiments.test.ts | 16 + src/shared/experiments.ts | 2 + src/shared/tools.ts | 15 +- .../src/components/chat/BatchDiffApproval.tsx | 56 ++ webview-ui/src/components/chat/ChatRow.tsx | 17 + .../settings/ExperimentalSettings.tsx | 12 + .../__tests__/ExtensionStateContext.test.tsx | 2 + webview-ui/src/i18n/locales/ca/chat.json | 3 +- webview-ui/src/i18n/locales/ca/settings.json | 4 + webview-ui/src/i18n/locales/de/chat.json | 3 +- webview-ui/src/i18n/locales/de/settings.json | 4 + webview-ui/src/i18n/locales/en/chat.json | 1 + webview-ui/src/i18n/locales/en/settings.json | 4 + webview-ui/src/i18n/locales/es/chat.json | 3 +- webview-ui/src/i18n/locales/es/settings.json | 4 + webview-ui/src/i18n/locales/fr/chat.json | 3 +- webview-ui/src/i18n/locales/fr/settings.json | 4 + webview-ui/src/i18n/locales/hi/chat.json | 3 +- webview-ui/src/i18n/locales/hi/settings.json | 4 + webview-ui/src/i18n/locales/it/chat.json | 3 +- webview-ui/src/i18n/locales/it/settings.json | 4 + webview-ui/src/i18n/locales/ja/chat.json | 3 +- webview-ui/src/i18n/locales/ja/settings.json | 4 + webview-ui/src/i18n/locales/ko/chat.json | 3 +- webview-ui/src/i18n/locales/ko/settings.json | 4 + webview-ui/src/i18n/locales/nl/chat.json | 3 +- webview-ui/src/i18n/locales/nl/settings.json | 4 + webview-ui/src/i18n/locales/pl/chat.json | 3 +- webview-ui/src/i18n/locales/pl/settings.json | 4 + webview-ui/src/i18n/locales/pt-BR/chat.json | 3 +- .../src/i18n/locales/pt-BR/settings.json | 4 + webview-ui/src/i18n/locales/ru/chat.json | 3 +- webview-ui/src/i18n/locales/ru/settings.json | 4 + webview-ui/src/i18n/locales/tr/chat.json | 3 +- webview-ui/src/i18n/locales/tr/settings.json | 4 + webview-ui/src/i18n/locales/vi/chat.json | 3 +- webview-ui/src/i18n/locales/vi/settings.json | 4 + webview-ui/src/i18n/locales/zh-CN/chat.json | 3 +- .../src/i18n/locales/zh-CN/settings.json | 4 + webview-ui/src/i18n/locales/zh-TW/chat.json | 3 +- .../src/i18n/locales/zh-TW/settings.json | 4 + 52 files changed, 1855 insertions(+), 32 deletions(-) create mode 100644 src/core/diff/strategies/multi-file-search-replace.ts create mode 100644 src/core/tools/__tests__/applyDiffTool.experiment.spec.ts create mode 100644 src/core/tools/multiApplyDiffTool.ts create mode 100644 webview-ui/src/components/chat/BatchDiffApproval.tsx diff --git a/packages/types/src/experiment.ts b/packages/types/src/experiment.ts index 195d5a2cdd..59b2524fdb 100644 --- a/packages/types/src/experiment.ts +++ b/packages/types/src/experiment.ts @@ -6,12 +6,7 @@ import type { Keys, Equals, AssertEqual } from "./type-fu.js" * ExperimentId */ -export const experimentIds = [ - "powerSteering", - "marketplace", - "concurrentFileReads", - "disableCompletionCommand", -] as const +export const experimentIds = ["powerSteering", "concurrentFileReads", "disableCompletionCommand", "marketplace", "multiFileApplyDiff"] as const export const experimentIdsSchema = z.enum(experimentIds) @@ -26,6 +21,7 @@ export const experimentsSchema = z.object({ marketplace: z.boolean(), concurrentFileReads: z.boolean(), disableCompletionCommand: z.boolean(), + multiFileApplyDiff: z.boolean(), }) export type Experiments = z.infer diff --git a/src/core/assistant-message/presentAssistantMessage.ts b/src/core/assistant-message/presentAssistantMessage.ts index 3716906a8d..be24a63d2e 100644 --- a/src/core/assistant-message/presentAssistantMessage.ts +++ b/src/core/assistant-message/presentAssistantMessage.ts @@ -11,7 +11,7 @@ import { fetchInstructionsTool } from "../tools/fetchInstructionsTool" import { listFilesTool } from "../tools/listFilesTool" import { getReadFileToolDescription, readFileTool } from "../tools/readFileTool" import { writeToFileTool } from "../tools/writeToFileTool" -import { applyDiffTool } from "../tools/applyDiffTool" +import { applyDiffTool } from "../tools/multiApplyDiffTool" import { insertContentTool } from "../tools/insertContentTool" import { searchAndReplaceTool } from "../tools/searchAndReplaceTool" import { listCodeDefinitionNamesTool } from "../tools/listCodeDefinitionNamesTool" @@ -31,6 +31,8 @@ import { formatResponse } from "../prompts/responses" import { validateToolUse } from "../tools/validateToolUse" import { Task } from "../task/Task" import { codebaseSearchTool } from "../tools/codebaseSearchTool" +import { experiments, EXPERIMENT_IDS } from "../../shared/experiments" +import { applyDiffToolLegacy } from "../tools/applyDiffTool" /** * Processes and presents assistant message content to the user interface. @@ -384,9 +386,33 @@ export async function presentAssistantMessage(cline: Task) { case "write_to_file": await writeToFileTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag) break - case "apply_diff": - await applyDiffTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag) + case "apply_diff": { + // Get the provider and state to check experiment settings + const provider = cline.providerRef.deref() + let isMultiFileApplyDiffEnabled = false + + if (provider) { + const state = await provider.getState() + isMultiFileApplyDiffEnabled = experiments.isEnabled( + state.experiments ?? {}, + EXPERIMENT_IDS.MULTI_FILE_APPLY_DIFF, + ) + } + + if (isMultiFileApplyDiffEnabled) { + await applyDiffTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag) + } else { + await applyDiffToolLegacy( + cline, + block, + askApproval, + handleError, + pushToolResult, + removeClosingTag, + ) + } break + } case "insert_content": await insertContentTool(cline, block, askApproval, handleError, pushToolResult, removeClosingTag) break diff --git a/src/core/diff/strategies/multi-file-search-replace.ts b/src/core/diff/strategies/multi-file-search-replace.ts new file mode 100644 index 0000000000..57503da5f4 --- /dev/null +++ b/src/core/diff/strategies/multi-file-search-replace.ts @@ -0,0 +1,735 @@ +import { distance } from "fastest-levenshtein" +import { ToolProgressStatus } from "@roo-code/types" + +import { addLineNumbers, everyLineHasLineNumbers, stripLineNumbers } from "../../../integrations/misc/extract-text" +import { ToolUse, DiffStrategy, DiffResult } from "../../../shared/tools" +import { normalizeString } from "../../../utils/text-normalization" + +const BUFFER_LINES = 40 // Number of extra context lines to show before and after matches + +function getSimilarity(original: string, search: string): number { + // Empty searches are no longer supported + if (search === "") { + return 0 + } + + // Use the normalizeString utility to handle smart quotes and other special characters + const normalizedOriginal = normalizeString(original) + const normalizedSearch = normalizeString(search) + + if (normalizedOriginal === normalizedSearch) { + return 1 + } + + // Calculate Levenshtein distance using fastest-levenshtein's distance function + const dist = distance(normalizedOriginal, normalizedSearch) + + // Calculate similarity ratio (0 to 1, where 1 is an exact match) + const maxLength = Math.max(normalizedOriginal.length, normalizedSearch.length) + return 1 - dist / maxLength +} + +/** + * Performs a "middle-out" search of `lines` (between [startIndex, endIndex]) to find + * the slice that is most similar to `searchChunk`. Returns the best score, index, and matched text. + */ +function fuzzySearch(lines: string[], searchChunk: string, startIndex: number, endIndex: number) { + let bestScore = 0 + let bestMatchIndex = -1 + let bestMatchContent = "" + + const searchLen = searchChunk.split(/\r?\n/).length + + // Middle-out from the midpoint + const midPoint = Math.floor((startIndex + endIndex) / 2) + let leftIndex = midPoint + let rightIndex = midPoint + 1 + + while (leftIndex >= startIndex || rightIndex <= endIndex - searchLen) { + if (leftIndex >= startIndex) { + const originalChunk = lines.slice(leftIndex, leftIndex + searchLen).join("\n") + const similarity = getSimilarity(originalChunk, searchChunk) + + if (similarity > bestScore) { + bestScore = similarity + bestMatchIndex = leftIndex + bestMatchContent = originalChunk + } + leftIndex-- + } + + if (rightIndex <= endIndex - searchLen) { + const originalChunk = lines.slice(rightIndex, rightIndex + searchLen).join("\n") + const similarity = getSimilarity(originalChunk, searchChunk) + + if (similarity > bestScore) { + bestScore = similarity + bestMatchIndex = rightIndex + bestMatchContent = originalChunk + } + rightIndex++ + } + } + + return { bestScore, bestMatchIndex, bestMatchContent } +} + +export class MultiFileSearchReplaceDiffStrategy implements DiffStrategy { + private fuzzyThreshold: number + private bufferLines: number + + getName(): string { + return "MultiFileSearchReplace" + } + + constructor(fuzzyThreshold?: number, bufferLines?: number) { + // Use provided threshold or default to exact matching (1.0) + // Note: fuzzyThreshold is inverted in UI (0% = 1.0, 10% = 0.9) + // so we use it directly here + this.fuzzyThreshold = fuzzyThreshold ?? 1.0 + this.bufferLines = bufferLines ?? BUFFER_LINES + } + + getToolDescription(args: { cwd: string; toolOptions?: { [key: string]: string } }): string { + return `## apply_diff + +Description: Request to apply targeted modifications to one or more files by searching for specific sections of content and replacing them. This tool supports both single-file and multi-file operations, allowing you to make changes across multiple files in a single request. + +You can perform multiple distinct search and replace operations within a single \`apply_diff\` call by providing multiple SEARCH/REPLACE blocks in the \`diff\` parameter. This is the preferred way to make several targeted changes efficiently. + +The SEARCH section must exactly match existing content including whitespace and indentation. +If you're not confident in the exact content to search for, use the read_file tool first to get the exact content. +When applying the diffs, be extra careful to remember to change any closing brackets or other syntax that may be affected by the diff farther down in the file. +ALWAYS make as many changes in a single 'apply_diff' request as possible using multiple SEARCH/REPLACE blocks + +Parameters: +- args: Contains one or more file elements, where each file contains: + - path: (required) The path of the file to modify (relative to the current workspace directory ${args.cwd}) + - diff: (required) One or more diff elements containing: + - content: (required) The search/replace block defining the changes. + - start_line: (optional) The line number of original content where the search block starts. + +Diff format: +\`\`\` +<<<<<<< SEARCH +:start_line: (optional) The line number of original content where the search block starts. +------- +[exact content to find including whitespace] +======= +[new content to replace with] +>>>>>>> REPLACE +\`\`\` + +Example: + +Original file: +\`\`\` +1 | def calculate_total(items): +2 | total = 0 +3 | for item in items: +4 | total += item +5 | return total +\`\`\` + +Search/Replace content: + + + + eg.file.py + + +\`\`\` +<<<<<<< SEARCH +def calculate_total(items): + total = 0 + for item in items: + total += item + return total +======= +def calculate_total(items): + """Calculate total with 10% markup""" + return sum(item * 1.1 for item in items) +>>>>>>> REPLACE +\`\`\` + + + + + + +Search/Replace content with multi edits in one file: + + + + eg.file.py + + +\`\`\` +<<<<<<< SEARCH +def calculate_total(items): + sum = 0 +======= +def calculate_sum(items): + sum = 0 +>>>>>>> REPLACE +\`\`\` + + + + +\`\`\` +<<<<<<< SEARCH + total += item + return total +======= + sum += item + return sum +>>>>>>> REPLACE +\`\`\` + + + + + eg.file2.py + + +\`\`\` +<<<<<<< SEARCH +def greet(name): + return "Hello " + name +======= +def greet(name): + return f"Hello {name}!" +>>>>>>> REPLACE +\`\`\` + + + + + + + +Usage: + + + + File path here + + +Your search/replace content here +You can use multi search/replace block in one diff block, but make sure to include the line numbers for each block. +Only use a single line of '=======' between search and replacement content, because multiple '=======' will corrupt the file. + + 1 + + + + Another file path + + +Another search/replace content here +You can apply changes to multiple files in a single request. +Each file requires its own path, start_line, and diff elements. + + 5 + + + +` + } + + private unescapeMarkers(content: string): string { + return content + .replace(/^\\<<<<<<>>>>>>/gm, ">>>>>>>") + .replace(/^\\-------/gm, "-------") + .replace(/^\\:end_line:/gm, ":end_line:") + .replace(/^\\:start_line:/gm, ":start_line:") + } + + private validateMarkerSequencing(diffContent: string): { success: boolean; error?: string } { + enum State { + START, + AFTER_SEARCH, + AFTER_SEPARATOR, + } + + const state = { current: State.START, line: 0 } + + const SEARCH = "<<<<<<< SEARCH" + const SEP = "=======" + const REPLACE = ">>>>>>> REPLACE" + const SEARCH_PREFIX = "<<<<<<< " + const REPLACE_PREFIX = ">>>>>>> " + + const reportMergeConflictError = (found: string, _expected: string) => ({ + success: false, + error: + `ERROR: Special marker '${found}' found in your diff content at line ${state.line}:\n` + + "\n" + + `When removing merge conflict markers like '${found}' from files, you MUST escape them\n` + + "in your SEARCH section by prepending a backslash (\\) at the beginning of the line:\n" + + "\n" + + "CORRECT FORMAT:\n\n" + + "<<<<<<< SEARCH\n" + + "content before\n" + + `\\${found} <-- Note the backslash here in this example\n` + + "content after\n" + + "=======\n" + + "replacement content\n" + + ">>>>>>> REPLACE\n" + + "\n" + + "Without escaping, the system confuses your content with diff syntax markers.\n" + + "You may use multiple diff blocks in a single diff request, but ANY of ONLY the following separators that occur within SEARCH or REPLACE content must be escaped, as follows:\n" + + `\\${SEARCH}\n` + + `\\${SEP}\n` + + `\\${REPLACE}\n`, + }) + + const reportInvalidDiffError = (found: string, expected: string) => ({ + success: false, + error: + `ERROR: Diff block is malformed: marker '${found}' found in your diff content at line ${state.line}. Expected: ${expected}\n` + + "\n" + + "CORRECT FORMAT:\n\n" + + "<<<<<<< SEARCH\n" + + ":start_line: (optional) The line number of original content where the search block starts.\n" + + "-------\n" + + "[exact content to find including whitespace]\n" + + "=======\n" + + "[new content to replace with]\n" + + ">>>>>>> REPLACE\n", + }) + + const reportLineMarkerInReplaceError = (marker: string) => ({ + success: false, + error: + `ERROR: Invalid line marker '${marker}' found in REPLACE section at line ${state.line}\n` + + "\n" + + "Line markers (:start_line: and :end_line:) are only allowed in SEARCH sections.\n" + + "\n" + + "CORRECT FORMAT:\n" + + "<<<<<<< SEARCH\n" + + ":start_line:5\n" + + "content to find\n" + + "=======\n" + + "replacement content\n" + + ">>>>>>> REPLACE\n" + + "\n" + + "INCORRECT FORMAT:\n" + + "<<<<<<< SEARCH\n" + + "content to find\n" + + "=======\n" + + ":start_line:5 <-- Invalid location\n" + + "replacement content\n" + + ">>>>>>> REPLACE\n", + }) + + const lines = diffContent.split("\n") + const searchCount = lines.filter((l) => l.trim() === SEARCH).length + const sepCount = lines.filter((l) => l.trim() === SEP).length + const replaceCount = lines.filter((l) => l.trim() === REPLACE).length + + const likelyBadStructure = searchCount !== replaceCount || sepCount < searchCount + + for (const line of diffContent.split("\n")) { + state.line++ + const marker = line.trim() + + // Check for line markers in REPLACE sections (but allow escaped ones) + if (state.current === State.AFTER_SEPARATOR) { + if (marker.startsWith(":start_line:") && !line.trim().startsWith("\\:start_line:")) { + return reportLineMarkerInReplaceError(":start_line:") + } + if (marker.startsWith(":end_line:") && !line.trim().startsWith("\\:end_line:")) { + return reportLineMarkerInReplaceError(":end_line:") + } + } + + switch (state.current) { + case State.START: + if (marker === SEP) + return likelyBadStructure + ? reportInvalidDiffError(SEP, SEARCH) + : reportMergeConflictError(SEP, SEARCH) + if (marker === REPLACE) return reportInvalidDiffError(REPLACE, SEARCH) + if (marker.startsWith(REPLACE_PREFIX)) return reportMergeConflictError(marker, SEARCH) + if (marker === SEARCH) state.current = State.AFTER_SEARCH + else if (marker.startsWith(SEARCH_PREFIX)) return reportMergeConflictError(marker, SEARCH) + break + + case State.AFTER_SEARCH: + if (marker === SEARCH) return reportInvalidDiffError(SEARCH, SEP) + if (marker.startsWith(SEARCH_PREFIX)) return reportMergeConflictError(marker, SEARCH) + if (marker === REPLACE) return reportInvalidDiffError(REPLACE, SEP) + if (marker.startsWith(REPLACE_PREFIX)) return reportMergeConflictError(marker, SEARCH) + if (marker === SEP) state.current = State.AFTER_SEPARATOR + break + + case State.AFTER_SEPARATOR: + if (marker === SEARCH) return reportInvalidDiffError(SEARCH, REPLACE) + if (marker.startsWith(SEARCH_PREFIX)) return reportMergeConflictError(marker, REPLACE) + if (marker === SEP) + return likelyBadStructure + ? reportInvalidDiffError(SEP, REPLACE) + : reportMergeConflictError(SEP, REPLACE) + if (marker === REPLACE) state.current = State.START + else if (marker.startsWith(REPLACE_PREFIX)) return reportMergeConflictError(marker, REPLACE) + break + } + } + + return state.current === State.START + ? { success: true } + : { + success: false, + error: `ERROR: Unexpected end of sequence: Expected '${ + state.current === State.AFTER_SEARCH ? "=======" : ">>>>>>> REPLACE" + }' was not found.`, + } + } + + async applyDiff( + originalContent: string, + diffContent: string | Array<{ content: string; startLine?: number }>, + _paramStartLine?: number, + _paramEndLine?: number, + ): Promise { + // Handle array-based input for multi-file support + if (Array.isArray(diffContent)) { + // Process each diff item separately and combine results + let resultContent = originalContent + const allFailParts: DiffResult[] = [] + let successCount = 0 + + for (const diffItem of diffContent) { + const singleResult = await this.applySingleDiff(resultContent, diffItem.content, diffItem.startLine) + + if (singleResult.success && singleResult.content) { + resultContent = singleResult.content + successCount++ + } else { + allFailParts.push(singleResult) + } + } + + if (successCount === 0) { + return { + success: false, + error: "Failed to apply any diffs", + failParts: allFailParts, + } + } + + return { + success: true, + content: resultContent, + failParts: allFailParts.length > 0 ? allFailParts : undefined, + } + } + + // Handle string-based input (legacy) + return this.applySingleDiff(originalContent, diffContent, _paramStartLine) + } + + private async applySingleDiff( + originalContent: string, + diffContent: string, + _paramStartLine?: number, + ): Promise { + const validseq = this.validateMarkerSequencing(diffContent) + if (!validseq.success) { + return { + success: false, + error: validseq.error!, + } + } + + /* Regex parts: + 1. (?:^|\n) Ensures the first marker starts at the beginning of the file or right after a newline. + 2. (?>>>>>> REPLACE)(?=\n|$) Matches the final ">>>>>>> REPLACE" marker on its own line (and requires a following newline or the end of file). + */ + let matches = [ + ...diffContent.matchAll( + /(?:^|\n)(?>>>>>> REPLACE)(?=\n|$)/g, + ), + ] + + if (matches.length === 0) { + return { + success: false, + error: `Invalid diff format - missing required sections\n\nDebug Info:\n- Expected Format: <<<<<<< SEARCH\\n:start_line: start line\\n-------\\n[search content]\\n=======\\n[replace content]\\n>>>>>>> REPLACE\n- Tip: Make sure to include start_line/SEARCH/=======/REPLACE sections with correct markers on new lines`, + } + } + + // Detect line ending from original content + const lineEnding = originalContent.includes("\r\n") ? "\r\n" : "\n" + let resultLines = originalContent.split(/\r?\n/) + let delta = 0 + let diffResults: DiffResult[] = [] + let appliedCount = 0 + + const replacements = matches + .map((match) => ({ + startLine: Number(match[2] ?? 0), + searchContent: match[6], + replaceContent: match[7], + })) + .sort((a, b) => a.startLine - b.startLine) + + for (const replacement of replacements) { + let { searchContent, replaceContent } = replacement + let startLine = replacement.startLine + (replacement.startLine === 0 ? 0 : delta) + + // First unescape any escaped markers in the content + searchContent = this.unescapeMarkers(searchContent) + replaceContent = this.unescapeMarkers(replaceContent) + + // Strip line numbers from search and replace content if every line starts with a line number + const hasAllLineNumbers = + (everyLineHasLineNumbers(searchContent) && everyLineHasLineNumbers(replaceContent)) || + (everyLineHasLineNumbers(searchContent) && replaceContent.trim() === "") + + if (hasAllLineNumbers && startLine === 0) { + startLine = parseInt(searchContent.split("\n")[0].split("|")[0]) + } + + if (hasAllLineNumbers) { + searchContent = stripLineNumbers(searchContent) + replaceContent = stripLineNumbers(replaceContent) + } + + // Validate that search and replace content are not identical + if (searchContent === replaceContent) { + diffResults.push({ + success: false, + error: + `Search and replace content are identical - no changes would be made\n\n` + + `Debug Info:\n` + + `- Search and replace must be different to make changes\n` + + `- Use read_file to verify the content you want to change`, + }) + continue + } + + // Split content into lines, handling both \n and \r\n + let searchLines = searchContent === "" ? [] : searchContent.split(/\r?\n/) + let replaceLines = replaceContent === "" ? [] : replaceContent.split(/\r?\n/) + + // Validate that search content is not empty + if (searchLines.length === 0) { + diffResults.push({ + success: false, + error: `Empty search content is not allowed\n\nDebug Info:\n- Search content cannot be empty\n- For insertions, provide a specific line using :start_line: and include content to search for\n- For example, match a single line to insert before/after it`, + }) + continue + } + + let endLine = replacement.startLine + searchLines.length - 1 + + // Initialize search variables + let matchIndex = -1 + let bestMatchScore = 0 + let bestMatchContent = "" + let searchChunk = searchLines.join("\n") + + // Determine search bounds + let searchStartIndex = 0 + let searchEndIndex = resultLines.length + + // Validate and handle line range if provided + if (startLine) { + // Convert to 0-based index + const exactStartIndex = startLine - 1 + const searchLen = searchLines.length + const exactEndIndex = exactStartIndex + searchLen - 1 + + // Try exact match first + const originalChunk = resultLines.slice(exactStartIndex, exactEndIndex + 1).join("\n") + const similarity = getSimilarity(originalChunk, searchChunk) + + if (similarity >= this.fuzzyThreshold) { + matchIndex = exactStartIndex + bestMatchScore = similarity + bestMatchContent = originalChunk + } else { + // Set bounds for buffered search + searchStartIndex = Math.max(0, startLine - (this.bufferLines + 1)) + searchEndIndex = Math.min(resultLines.length, startLine + searchLines.length + this.bufferLines) + } + } + + // If no match found yet, try middle-out search within bounds + if (matchIndex === -1) { + const { + bestScore, + bestMatchIndex, + bestMatchContent: midContent, + } = fuzzySearch(resultLines, searchChunk, searchStartIndex, searchEndIndex) + + matchIndex = bestMatchIndex + bestMatchScore = bestScore + bestMatchContent = midContent + } + + // Try aggressive line number stripping as a fallback if regular matching fails + if (matchIndex === -1 || bestMatchScore < this.fuzzyThreshold) { + // Strip both search and replace content once (simultaneously) + const aggressiveSearchContent = stripLineNumbers(searchContent, true) + const aggressiveReplaceContent = stripLineNumbers(replaceContent, true) + const aggressiveSearchLines = aggressiveSearchContent ? aggressiveSearchContent.split(/\r?\n/) : [] + const aggressiveSearchChunk = aggressiveSearchLines.join("\n") + + // Try middle-out search again with aggressive stripped content (respecting the same search bounds) + const { + bestScore, + bestMatchIndex, + bestMatchContent: aggContent, + } = fuzzySearch(resultLines, aggressiveSearchChunk, searchStartIndex, searchEndIndex) + + if (bestMatchIndex !== -1 && bestScore >= this.fuzzyThreshold) { + matchIndex = bestMatchIndex + bestMatchScore = bestScore + bestMatchContent = aggContent + + // Replace the original search/replace with their stripped versions + searchContent = aggressiveSearchContent + replaceContent = aggressiveReplaceContent + searchLines = aggressiveSearchLines + replaceLines = replaceContent ? replaceContent.split(/\r?\n/) : [] + } else { + // No match found with either method + const originalContentSection = + startLine !== undefined && endLine !== undefined + ? `\n\nOriginal Content:\n${addLineNumbers( + resultLines + .slice( + Math.max(0, startLine - 1 - this.bufferLines), + Math.min(resultLines.length, endLine + this.bufferLines), + ) + .join("\n"), + Math.max(1, startLine - this.bufferLines), + )}` + : `\n\nOriginal Content:\n${addLineNumbers(resultLines.join("\n"))}` + + const bestMatchSection = bestMatchContent + ? `\n\nBest Match Found:\n${addLineNumbers(bestMatchContent, matchIndex + 1)}` + : `\n\nBest Match Found:\n(no match)` + + const lineRange = startLine ? ` at line: ${startLine}` : "" + + diffResults.push({ + success: false, + error: `No sufficiently similar match found${lineRange} (${Math.floor( + bestMatchScore * 100, + )}% similar, needs ${Math.floor( + this.fuzzyThreshold * 100, + )}%)\n\nDebug Info:\n- Similarity Score: ${Math.floor( + bestMatchScore * 100, + )}%\n- Required Threshold: ${Math.floor(this.fuzzyThreshold * 100)}%\n- Search Range: ${ + startLine ? `starting at line ${startLine}` : "start to end" + }\n- Tried both standard and aggressive line number stripping\n- Tip: Use the read_file tool to get the latest content of the file before attempting to use the apply_diff tool again, as the file content may have changed\n\nSearch Content:\n${searchChunk}${bestMatchSection}${originalContentSection}`, + }) + continue + } + } + + // Get the matched lines from the original content + const matchedLines = resultLines.slice(matchIndex, matchIndex + searchLines.length) + + // Get the exact indentation (preserving tabs/spaces) of each line + const originalIndents = matchedLines.map((line) => { + const match = line.match(/^[\t ]*/) + return match ? match[0] : "" + }) + + // Get the exact indentation of each line in the search block + const searchIndents = searchLines.map((line) => { + const match = line.match(/^[\t ]*/) + return match ? match[0] : "" + }) + + // Apply the replacement while preserving exact indentation + const indentedReplaceLines = replaceLines.map((line) => { + // Get the matched line's exact indentation + const matchedIndent = originalIndents[0] || "" + + // Get the current line's indentation relative to the search content + const currentIndentMatch = line.match(/^[\t ]*/) + const currentIndent = currentIndentMatch ? currentIndentMatch[0] : "" + const searchBaseIndent = searchIndents[0] || "" + + // Calculate the relative indentation level + const searchBaseLevel = searchBaseIndent.length + const currentLevel = currentIndent.length + const relativeLevel = currentLevel - searchBaseLevel + + // If relative level is negative, remove indentation from matched indent + // If positive, add to matched indent + const finalIndent = + relativeLevel < 0 + ? matchedIndent.slice(0, Math.max(0, matchedIndent.length + relativeLevel)) + : matchedIndent + currentIndent.slice(searchBaseLevel) + + return finalIndent + line.trim() + }) + + // Construct the final content + const beforeMatch = resultLines.slice(0, matchIndex) + const afterMatch = resultLines.slice(matchIndex + searchLines.length) + resultLines = [...beforeMatch, ...indentedReplaceLines, ...afterMatch] + + delta = delta - matchedLines.length + replaceLines.length + appliedCount++ + } + + const finalContent = resultLines.join(lineEnding) + + if (appliedCount === 0) { + return { + success: false, + failParts: diffResults, + } + } + + return { + success: true, + content: finalContent, + failParts: diffResults, + } + } + + getProgressStatus(toolUse: ToolUse, result?: DiffResult): ToolProgressStatus { + const diffContent = toolUse.params.diff + if (diffContent) { + const icon = "diff-multiple" + + if (toolUse.partial) { + if (Math.floor(diffContent.length / 10) % 10 === 0) { + const searchBlockCount = (diffContent.match(/SEARCH/g) || []).length + return { icon, text: `${searchBlockCount}` } + } + } else if (result) { + const searchBlockCount = (diffContent.match(/SEARCH/g) || []).length + if (result.failParts?.length) { + return { + icon, + text: `${searchBlockCount - result.failParts.length}/${searchBlockCount}`, + } + } else { + return { icon, text: `${searchBlockCount}` } + } + } + } + + return {} + } +} diff --git a/src/core/prompts/__tests__/sections.test.ts b/src/core/prompts/__tests__/sections.test.ts index d6515883c8..3b29193e99 100644 --- a/src/core/prompts/__tests__/sections.test.ts +++ b/src/core/prompts/__tests__/sections.test.ts @@ -1,6 +1,6 @@ import { addCustomInstructions } from "../sections/custom-instructions" import { getCapabilitiesSection } from "../sections/capabilities" -import { DiffStrategy, DiffResult } from "../../../shared/tools" +import { DiffStrategy, DiffResult, DiffItem } from "../../../shared/tools" describe("addCustomInstructions", () => { test("adds vscode language to custom instructions", async () => { @@ -35,7 +35,7 @@ describe("getCapabilitiesSection", () => { const mockDiffStrategy: DiffStrategy = { getName: () => "MockStrategy", getToolDescription: () => "apply_diff tool description", - applyDiff: async (_originalContent: string, _diffContent: string): Promise => { + async applyDiff(_originalContent: string, _diffContents: string | DiffItem[]): Promise { return { success: true, content: "mock result" } }, } diff --git a/src/core/task/Task.ts b/src/core/task/Task.ts index fa814f0661..e881749e86 100644 --- a/src/core/task/Task.ts +++ b/src/core/task/Task.ts @@ -38,6 +38,7 @@ import { getApiMetrics } from "../../shared/getApiMetrics" import { ClineAskResponse } from "../../shared/WebviewMessage" import { defaultModeSlug } from "../../shared/modes" import { DiffStrategy } from "../../shared/tools" +import { EXPERIMENT_IDS, experiments } from "../../shared/experiments" // services import { UrlContentFetcher } from "../../services/browser/UrlContentFetcher" @@ -68,6 +69,7 @@ import { type AssistantMessageContent, parseAssistantMessage, presentAssistantMe import { truncateConversationIfNeeded } from "../sliding-window" import { ClineProvider } from "../webview/ClineProvider" import { MultiSearchReplaceDiffStrategy } from "../diff/strategies/multi-search-replace" +import { MultiFileSearchReplaceDiffStrategy } from "../diff/strategies/multi-file-search-replace" import { readApiMessages, saveApiMessages, readTaskMessages, saveTaskMessages, taskMetadata } from "../task-persistence" import { getEnvironmentDetails } from "../environment/getEnvironmentDetails" import { @@ -250,7 +252,24 @@ export class Task extends EventEmitter { TelemetryService.instance.captureTaskCreated(this.taskId) } - this.diffStrategy = new MultiSearchReplaceDiffStrategy(this.fuzzyMatchThreshold) + // Only set up diff strategy if diff is enabled + if (this.diffEnabled) { + // Default to old strategy, will be updated if experiment is enabled + this.diffStrategy = new MultiSearchReplaceDiffStrategy(this.fuzzyMatchThreshold) + + // Check experiment asynchronously and update strategy if needed + provider.getState().then((state) => { + const isMultiFileApplyDiffEnabled = experiments.isEnabled( + state.experiments ?? {}, + EXPERIMENT_IDS.MULTI_FILE_APPLY_DIFF, + ) + + if (isMultiFileApplyDiffEnabled) { + this.diffStrategy = new MultiFileSearchReplaceDiffStrategy(this.fuzzyMatchThreshold) + } + }) + } + this.toolRepetitionDetector = new ToolRepetitionDetector(this.consecutiveMistakeLimit) onCreated?.(this) diff --git a/src/core/task/__tests__/Task.test.ts b/src/core/task/__tests__/Task.test.ts index 8ed57ffcb3..3695a7bd47 100644 --- a/src/core/task/__tests__/Task.test.ts +++ b/src/core/task/__tests__/Task.test.ts @@ -14,6 +14,9 @@ import { ClineProvider } from "../../webview/ClineProvider" import { ApiStreamChunk } from "../../../api/transform/stream" import { ContextProxy } from "../../config/ContextProxy" import { processUserContentMentions } from "../../mentions/processUserContentMentions" +import { MultiSearchReplaceDiffStrategy } from "../../diff/strategies/multi-search-replace" +import { MultiFileSearchReplaceDiffStrategy } from "../../diff/strategies/multi-file-search-replace" +import { EXPERIMENT_IDS } from "../../../shared/experiments" jest.mock("execa", () => ({ execa: jest.fn(), @@ -855,5 +858,107 @@ describe("Cline", () => { }) }) }) + + describe("Dynamic Strategy Selection", () => { + let mockProvider: any + let mockApiConfig: any + + beforeEach(() => { + jest.clearAllMocks() + + mockApiConfig = { + apiProvider: "anthropic", + apiKey: "test-key", + } + + mockProvider = { + context: { + globalStorageUri: { fsPath: "/test/storage" }, + }, + getState: jest.fn(), + } + }) + + it("should use MultiSearchReplaceDiffStrategy by default", async () => { + mockProvider.getState.mockResolvedValue({ + experiments: { + [EXPERIMENT_IDS.MULTI_FILE_APPLY_DIFF]: false, + }, + }) + + const task = new Task({ + provider: mockProvider, + apiConfiguration: mockApiConfig, + enableDiff: true, + task: "test task", + startTask: false, + }) + + // Initially should be MultiSearchReplaceDiffStrategy + expect(task.diffStrategy).toBeInstanceOf(MultiSearchReplaceDiffStrategy) + expect(task.diffStrategy?.getName()).toBe("MultiSearchReplace") + }) + + it("should switch to MultiFileSearchReplaceDiffStrategy when experiment is enabled", async () => { + mockProvider.getState.mockResolvedValue({ + experiments: { + [EXPERIMENT_IDS.MULTI_FILE_APPLY_DIFF]: true, + }, + }) + + const task = new Task({ + provider: mockProvider, + apiConfiguration: mockApiConfig, + enableDiff: true, + task: "test task", + startTask: false, + }) + + // Initially should be MultiSearchReplaceDiffStrategy + expect(task.diffStrategy).toBeInstanceOf(MultiSearchReplaceDiffStrategy) + + // Wait for async strategy update + await new Promise((resolve) => setTimeout(resolve, 10)) + + // Should have switched to MultiFileSearchReplaceDiffStrategy + expect(task.diffStrategy).toBeInstanceOf(MultiFileSearchReplaceDiffStrategy) + expect(task.diffStrategy?.getName()).toBe("MultiFileSearchReplace") + }) + + it("should keep MultiSearchReplaceDiffStrategy when experiments are undefined", async () => { + mockProvider.getState.mockResolvedValue({}) + + const task = new Task({ + provider: mockProvider, + apiConfiguration: mockApiConfig, + enableDiff: true, + task: "test task", + startTask: false, + }) + + // Initially should be MultiSearchReplaceDiffStrategy + expect(task.diffStrategy).toBeInstanceOf(MultiSearchReplaceDiffStrategy) + + // Wait for async strategy update + await new Promise((resolve) => setTimeout(resolve, 10)) + + // Should still be MultiSearchReplaceDiffStrategy + expect(task.diffStrategy).toBeInstanceOf(MultiSearchReplaceDiffStrategy) + expect(task.diffStrategy?.getName()).toBe("MultiSearchReplace") + }) + + it("should not create diff strategy when enableDiff is false", async () => { + const task = new Task({ + provider: mockProvider, + apiConfiguration: mockApiConfig, + enableDiff: false, + task: "test task", + startTask: false, + }) + + expect(task.diffEnabled).toBe(false) + expect(task.diffStrategy).toBeUndefined() + }) + }) }) }) diff --git a/src/core/tools/__tests__/applyDiffTool.experiment.spec.ts b/src/core/tools/__tests__/applyDiffTool.experiment.spec.ts new file mode 100644 index 0000000000..30a37a4e96 --- /dev/null +++ b/src/core/tools/__tests__/applyDiffTool.experiment.spec.ts @@ -0,0 +1,150 @@ +import { describe, it, expect, vi, beforeEach } from "vitest" +import { applyDiffTool } from "../multiApplyDiffTool" +import { EXPERIMENT_IDS, experiments } from "../../../shared/experiments" + +// Mock the applyDiffTool module +vi.mock("../applyDiffTool", () => ({ + applyDiffToolLegacy: vi.fn(), +})) + +// Import after mocking to get the mocked version +import { applyDiffToolLegacy } from "../applyDiffTool" + +describe("applyDiffTool experiment routing", () => { + let mockCline: any + let mockBlock: any + let mockAskApproval: any + let mockHandleError: any + let mockPushToolResult: any + let mockRemoveClosingTag: any + let mockProvider: any + + beforeEach(() => { + vi.clearAllMocks() + + mockProvider = { + getState: vi.fn(), + } + + mockCline = { + providerRef: { + deref: vi.fn().mockReturnValue(mockProvider), + }, + cwd: "/test", + diffStrategy: { + applyDiff: vi.fn(), + getProgressStatus: vi.fn(), + }, + diffViewProvider: { + reset: vi.fn(), + }, + api: { + getModel: vi.fn().mockReturnValue({ id: "test-model" }), + }, + } as any + + mockBlock = { + params: { + path: "test.ts", + diff: "test diff", + }, + partial: false, + } + + mockAskApproval = vi.fn() + mockHandleError = vi.fn() + mockPushToolResult = vi.fn() + mockRemoveClosingTag = vi.fn((tag, value) => value) + }) + + it("should use legacy tool when MULTI_FILE_APPLY_DIFF experiment is disabled", async () => { + mockProvider.getState.mockResolvedValue({ + experiments: { + [EXPERIMENT_IDS.MULTI_FILE_APPLY_DIFF]: false, + }, + }) + + // Mock the legacy tool to resolve successfully + ;(applyDiffToolLegacy as any).mockResolvedValue(undefined) + + await applyDiffTool( + mockCline, + mockBlock, + mockAskApproval, + mockHandleError, + mockPushToolResult, + mockRemoveClosingTag, + ) + + expect(applyDiffToolLegacy).toHaveBeenCalledWith( + mockCline, + mockBlock, + mockAskApproval, + mockHandleError, + mockPushToolResult, + mockRemoveClosingTag, + ) + }) + + it("should use legacy tool when experiments are not defined", async () => { + mockProvider.getState.mockResolvedValue({}) + + // Mock the legacy tool to resolve successfully + ;(applyDiffToolLegacy as any).mockResolvedValue(undefined) + + await applyDiffTool( + mockCline, + mockBlock, + mockAskApproval, + mockHandleError, + mockPushToolResult, + mockRemoveClosingTag, + ) + + expect(applyDiffToolLegacy).toHaveBeenCalledWith( + mockCline, + mockBlock, + mockAskApproval, + mockHandleError, + mockPushToolResult, + mockRemoveClosingTag, + ) + }) + + it("should use new tool when MULTI_FILE_APPLY_DIFF experiment is enabled", async () => { + mockProvider.getState.mockResolvedValue({ + experiments: { + [EXPERIMENT_IDS.MULTI_FILE_APPLY_DIFF]: true, + }, + }) + + // Mock the new tool behavior - it should continue with the new implementation + // Since we're not mocking the entire function, we'll just verify it doesn't call legacy + await applyDiffTool( + mockCline, + mockBlock, + mockAskApproval, + mockHandleError, + mockPushToolResult, + mockRemoveClosingTag, + ) + + expect(applyDiffToolLegacy).not.toHaveBeenCalled() + }) + + it("should use new tool when provider is not available", async () => { + mockCline.providerRef.deref.mockReturnValue(null) + + await applyDiffTool( + mockCline, + mockBlock, + mockAskApproval, + mockHandleError, + mockPushToolResult, + mockRemoveClosingTag, + ) + + // When provider is null, it should continue with new implementation (not call legacy) + expect(applyDiffToolLegacy).not.toHaveBeenCalled() + }) +}) diff --git a/src/core/tools/applyDiffTool.ts b/src/core/tools/applyDiffTool.ts index 500c7a92c3..d4f7fd883f 100644 --- a/src/core/tools/applyDiffTool.ts +++ b/src/core/tools/applyDiffTool.ts @@ -12,7 +12,7 @@ import { fileExistsAtPath } from "../../utils/fs" import { RecordSource } from "../context-tracking/FileContextTrackerTypes" import { unescapeHtmlEntities } from "../../utils/text-normalization" -export async function applyDiffTool( +export async function applyDiffToolLegacy( cline: Task, block: ToolUse, askApproval: AskApproval, diff --git a/src/core/tools/multiApplyDiffTool.ts b/src/core/tools/multiApplyDiffTool.ts new file mode 100644 index 0000000000..ba36cd3759 --- /dev/null +++ b/src/core/tools/multiApplyDiffTool.ts @@ -0,0 +1,570 @@ +import path from "path" +import fs from "fs/promises" + +import { TelemetryService } from "@roo-code/telemetry" + +import { ClineSayTool } from "../../shared/ExtensionMessage" +import { getReadablePath } from "../../utils/path" +import { Task } from "../task/Task" +import { ToolUse, RemoveClosingTag, AskApproval, HandleError, PushToolResult } from "../../shared/tools" +import { formatResponse } from "../prompts/responses" +import { fileExistsAtPath } from "../../utils/fs" +import { RecordSource } from "../context-tracking/FileContextTrackerTypes" +import { unescapeHtmlEntities } from "../../utils/text-normalization" +import { parseXml } from "../../utils/xml" +import { EXPERIMENT_IDS, experiments } from "../../shared/experiments" +import { applyDiffToolLegacy } from "./applyDiffTool" + +interface DiffOperation { + path: string + diff: Array<{ + content: string + startLine?: number + }> +} + +// Track operation status +interface OperationResult { + path: string + status: "pending" | "approved" | "denied" | "blocked" | "error" + error?: string + result?: string + diffItems?: Array<{ content: string; startLine?: number }> + absolutePath?: string + fileExists?: boolean +} + +// Add proper type definitions +interface ParsedFile { + path: string + diff: ParsedDiff | ParsedDiff[] +} + +interface ParsedDiff { + content: string + start_line?: string +} + +interface ParsedXmlResult { + file: ParsedFile | ParsedFile[] +} + +export async function applyDiffTool( + cline: Task, + block: ToolUse, + askApproval: AskApproval, + handleError: HandleError, + pushToolResult: PushToolResult, + removeClosingTag: RemoveClosingTag, +) { + // Check if MULTI_FILE_APPLY_DIFF experiment is enabled + const provider = cline.providerRef.deref() + if (provider) { + const state = await provider.getState() + const isMultiFileApplyDiffEnabled = experiments.isEnabled( + state.experiments ?? {}, + EXPERIMENT_IDS.MULTI_FILE_APPLY_DIFF, + ) + + // If experiment is disabled, use legacy tool + if (!isMultiFileApplyDiffEnabled) { + return applyDiffToolLegacy(cline, block, askApproval, handleError, pushToolResult, removeClosingTag) + } + } + + // Otherwise, continue with new multi-file implementation + const argsXmlTag: string | undefined = block.params.args + const legacyPath: string | undefined = block.params.path + const legacyDiffContent: string | undefined = block.params.diff + const legacyStartLineStr: string | undefined = block.params.start_line + + let operationsMap: Record = {} + let usingLegacyParams = false + let filteredOperationErrors: string[] = [] + + // Handle partial message first + if (block.partial) { + let filePath = "" + if (argsXmlTag) { + const match = argsXmlTag.match(/.*?([^<]+)<\/path>/s) + if (match) { + filePath = match[1] + } + } else if (legacyPath) { + // Use legacy path if argsXmlTag is not present for partial messages + filePath = legacyPath + } + + const sharedMessageProps: ClineSayTool = { + tool: "appliedDiff", + path: getReadablePath(cline.cwd, filePath), + } + const partialMessage = JSON.stringify(sharedMessageProps) + await cline.ask("tool", partialMessage, block.partial).catch(() => {}) + return + } + + if (argsXmlTag) { + // Parse file entries from XML (new way) + try { + const parsed = parseXml(argsXmlTag, ["file.diff.content"]) as ParsedXmlResult + const files = Array.isArray(parsed.file) ? parsed.file : [parsed.file].filter(Boolean) + + for (const file of files) { + if (!file.path || !file.diff) continue + + const filePath = file.path + + // Initialize the operation in the map if it doesn't exist + if (!operationsMap[filePath]) { + operationsMap[filePath] = { + path: filePath, + diff: [], + } + } + + // Handle diff as either array or single element + const diffs = Array.isArray(file.diff) ? file.diff : [file.diff] + + for (let i = 0; i < diffs.length; i++) { + const diff = diffs[i] + let diffContent: string + let startLine: number | undefined + + diffContent = diff.content + startLine = diff.start_line ? parseInt(diff.start_line) : undefined + + operationsMap[filePath].diff.push({ + content: diffContent, + startLine, + }) + } + } + } catch (error) { + const errorMessage = error instanceof Error ? error.message : String(error) + const detailedError = `Failed to parse apply_diff XML. This usually means: +1. The XML structure is malformed or incomplete +2. Missing required , , or tags +3. Invalid characters or encoding in the XML + +Expected structure: + + + relative/path/to/file.ext + + diff content here + optional line number + + + + +Original error: ${errorMessage}` + throw new Error(detailedError) + } + + } else if (legacyPath && typeof legacyDiffContent === "string") { + // Handle legacy parameters (old way) + usingLegacyParams = true + operationsMap[legacyPath] = { + path: legacyPath, + diff: [ + { + content: legacyDiffContent, // Unescaping will be handled later like new diffs + startLine: legacyStartLineStr ? parseInt(legacyStartLineStr) : undefined, + }, + ], + } + } else { + // Neither new XML args nor old path/diff params are sufficient + cline.consecutiveMistakeCount++ + cline.recordToolError("apply_diff") + const errorMsg = await cline.sayAndCreateMissingParamError( + "apply_diff", + "args (or legacy 'path' and 'diff' parameters)", + ) + pushToolResult(errorMsg) + return + } + + // If no operations were extracted, bail out + if (Object.keys(operationsMap).length === 0) { + cline.consecutiveMistakeCount++ + cline.recordToolError("apply_diff") + pushToolResult( + await cline.sayAndCreateMissingParamError( + "apply_diff", + usingLegacyParams + ? "legacy 'path' and 'diff' (must be valid and non-empty)" + : "args (must contain at least one valid file element)", + ), + ) + return + } + + // Convert map to array of operations for processing + const operations = Object.values(operationsMap) + + const operationResults: OperationResult[] = operations.map((op) => ({ + path: op.path, + status: "pending", + diffItems: op.diff, + })) + + // Function to update operation result + const updateOperationResult = (path: string, updates: Partial) => { + const index = operationResults.findIndex((result) => result.path === path) + if (index !== -1) { + operationResults[index] = { ...operationResults[index], ...updates } + } + } + + try { + // First validate all files and prepare for batch approval + const operationsToApprove: OperationResult[] = [] + + for (const operation of operations) { + const { path: relPath, diff: diffItems } = operation + + // Verify file access is allowed + const accessAllowed = cline.rooIgnoreController?.validateAccess(relPath) + if (!accessAllowed) { + await cline.say("rooignore_error", relPath) + updateOperationResult(relPath, { + status: "blocked", + error: formatResponse.rooIgnoreError(relPath), + }) + continue + } + + // Verify file exists + const absolutePath = path.resolve(cline.cwd, relPath) + const fileExists = await fileExistsAtPath(absolutePath) + if (!fileExists) { + updateOperationResult(relPath, { + status: "blocked", + error: `File does not exist at path: ${absolutePath}`, + }) + continue + } + + // Add to operations that need approval + const opResult = operationResults.find((r) => r.path === relPath) + if (opResult) { + opResult.absolutePath = absolutePath + opResult.fileExists = fileExists + operationsToApprove.push(opResult) + } + } + + // Handle batch approval if there are multiple files + if (operationsToApprove.length > 1) { + // Prepare batch diff data + const batchDiffs = operationsToApprove.map((opResult) => { + const readablePath = getReadablePath(cline.cwd, opResult.path) + const changeCount = opResult.diffItems?.length || 0 + const changeText = changeCount === 1 ? "1 change" : `${changeCount} changes` + + return { + path: readablePath, + changeCount, + key: `${readablePath} (${changeText})`, + content: opResult.path, // Full relative path + diffs: opResult.diffItems?.map((item) => ({ + content: item.content, + startLine: item.startLine, + })), + } + }) + + const completeMessage = JSON.stringify({ + tool: "appliedDiff", + batchDiffs, + } satisfies ClineSayTool) + + const { response, text, images } = await cline.ask("tool", completeMessage, false) + + // Process batch response + if (response === "yesButtonClicked") { + // Approve all files + if (text) { + await cline.say("user_feedback", text, images) + } + operationsToApprove.forEach((opResult) => { + updateOperationResult(opResult.path, { status: "approved" }) + }) + } else if (response === "noButtonClicked") { + // Deny all files + if (text) { + await cline.say("user_feedback", text, images) + } + cline.didRejectTool = true + operationsToApprove.forEach((opResult) => { + updateOperationResult(opResult.path, { + status: "denied", + result: `Changes to ${opResult.path} were not approved by user`, + }) + }) + } else { + // Handle individual permissions from objectResponse + try { + const parsedResponse = JSON.parse(text || "{}") + // Check if this is our batch diff approval response + if (parsedResponse.action === "applyDiff" && parsedResponse.approvedFiles) { + const approvedFiles = parsedResponse.approvedFiles + let hasAnyDenial = false + + operationsToApprove.forEach((opResult) => { + const approved = approvedFiles[opResult.path] === true + + if (approved) { + updateOperationResult(opResult.path, { status: "approved" }) + } else { + hasAnyDenial = true + updateOperationResult(opResult.path, { + status: "denied", + result: `Changes to ${opResult.path} were not approved by user`, + }) + } + }) + + if (hasAnyDenial) { + cline.didRejectTool = true + } + } else { + // Legacy individual permissions format + const individualPermissions = parsedResponse + let hasAnyDenial = false + + batchDiffs.forEach((batchDiff, index) => { + const opResult = operationsToApprove[index] + const approved = individualPermissions[batchDiff.key] === true + + if (approved) { + updateOperationResult(opResult.path, { status: "approved" }) + } else { + hasAnyDenial = true + updateOperationResult(opResult.path, { + status: "denied", + result: `Changes to ${opResult.path} were not approved by user`, + }) + } + }) + + if (hasAnyDenial) { + cline.didRejectTool = true + } + } + } catch (error) { + // Fallback: if JSON parsing fails, deny all files + console.error("Failed to parse individual permissions:", error) + cline.didRejectTool = true + operationsToApprove.forEach((opResult) => { + updateOperationResult(opResult.path, { + status: "denied", + result: `Changes to ${opResult.path} were not approved by user`, + }) + }) + } + } + } else if (operationsToApprove.length === 1) { + // Single file approval - process immediately + const opResult = operationsToApprove[0] + updateOperationResult(opResult.path, { status: "approved" }) + } + + // Process approved operations + const results: string[] = [] + + for (const opResult of operationResults) { + // Skip operations that weren't approved or were blocked + if (opResult.status !== "approved") { + if (opResult.result) { + results.push(opResult.result) + } else if (opResult.error) { + results.push(opResult.error) + } + continue + } + + const relPath = opResult.path + const diffItems = opResult.diffItems || [] + const absolutePath = opResult.absolutePath! + const fileExists = opResult.fileExists! + + try { + let originalContent: string | null = await fs.readFile(absolutePath, "utf-8") + let successCount = 0 + let formattedError = "" + + // Pre-process all diff items for HTML entity unescaping if needed + const processedDiffItems = !cline.api.getModel().id.includes("claude") + ? diffItems.map((item) => ({ + ...item, + content: item.content ? unescapeHtmlEntities(item.content) : item.content, + })) + : diffItems + + // Apply all diffs at once with the array-based method + const diffResult = (await cline.diffStrategy?.applyDiff(originalContent, processedDiffItems)) ?? { + success: false, + error: "No diff strategy available - please ensure a valid diff strategy is configured", + } + + // Release the original content from memory as it's no longer needed + originalContent = null + + if (!diffResult.success) { + cline.consecutiveMistakeCount++ + const currentCount = (cline.consecutiveMistakeCountForApplyDiff.get(relPath) || 0) + 1 + cline.consecutiveMistakeCountForApplyDiff.set(relPath, currentCount) + + TelemetryService.instance.captureDiffApplicationError(cline.taskId, currentCount) + + if (diffResult.failParts && diffResult.failParts.length > 0) { + for (let i = 0; i < diffResult.failParts.length; i++) { + const failPart = diffResult.failParts[i] + if (failPart.success) { + continue + } + + const errorDetails = failPart.details ? JSON.stringify(failPart.details, null, 2) : "" + formattedError += ` +Diff ${i + 1} failed for file: ${relPath} +Error: ${failPart.error} + +Suggested fixes: +1. Verify the search content exactly matches the file content (including whitespace) +2. Check for correct indentation and line endings +3. Use to see the current file content +4. Consider breaking complex changes into smaller diffs +5. Ensure start_line parameter matches the actual content location +${errorDetails ? `\nDetailed error information:\n${errorDetails}\n` : ""} +\n\n` + } + } else { + const errorDetails = diffResult.details ? JSON.stringify(diffResult.details, null, 2) : "" + formattedError += ` +Unable to apply diffs to file: ${absolutePath} +Error: ${diffResult.error} + +Recovery suggestions: +1. Use to examine the current file content +2. Verify the diff format matches the expected search/replace pattern +3. Check that the search content exactly matches what's in the file +4. Consider using line numbers with start_line parameter +5. Break large changes into smaller, more specific diffs +${errorDetails ? `\nTechnical details:\n${errorDetails}\n` : ""} +\n\n` + } + } else { + // Get the content from the result and update success count + originalContent = diffResult.content || originalContent + successCount = diffItems.length - (diffResult.failParts?.length || 0) + } + + // If no diffs were successfully applied, continue to next file + if (successCount === 0) { + if (formattedError) { + const currentCount = cline.consecutiveMistakeCountForApplyDiff.get(relPath) || 0 + if (currentCount >= 2) { + await cline.say("diff_error", formattedError) + } + cline.recordToolError("apply_diff", formattedError) + results.push(formattedError) + } + continue + } + + cline.consecutiveMistakeCount = 0 + cline.consecutiveMistakeCountForApplyDiff.delete(relPath) + + // Show diff view before asking for approval (only for single file or after batch approval) + cline.diffViewProvider.editType = "modify" + await cline.diffViewProvider.open(relPath) + await cline.diffViewProvider.update(originalContent!, true) + await cline.diffViewProvider.scrollToFirstDiff() + + // For batch operations, we've already gotten approval + const sharedMessageProps: ClineSayTool = { + tool: "appliedDiff", + path: getReadablePath(cline.cwd, relPath), + } + + // If single file, ask for approval + let didApprove = true + if (operationsToApprove.length === 1) { + const diffContents = diffItems.map((item) => item.content).join("\n\n") + const operationMessage = JSON.stringify({ + ...sharedMessageProps, + diff: diffContents, + } satisfies ClineSayTool) + + let toolProgressStatus + + if (cline.diffStrategy && cline.diffStrategy.getProgressStatus) { + toolProgressStatus = cline.diffStrategy.getProgressStatus( + { + ...block, + params: { ...block.params, diff: diffContents }, + }, + { success: true }, + ) + } + + didApprove = await askApproval("tool", operationMessage, toolProgressStatus) + } + + if (!didApprove) { + await cline.diffViewProvider.revertChanges() + results.push(`Changes to ${relPath} were not approved by user`) + continue + } + + // Call saveChanges to update the DiffViewProvider properties + await cline.diffViewProvider.saveChanges() + + // Track file edit operation + await cline.fileContextTracker.trackFileContext(relPath, "roo_edited" as RecordSource) + + // Used to determine if we should wait for busy terminal to update before sending api request + cline.didEditFile = true + let partFailHint = "" + + if (successCount < diffItems.length) { + partFailHint = `Unable to apply all diff parts to file: ${absolutePath}` + } + + // Get the formatted response message + const message = await cline.diffViewProvider.pushToolWriteResult(cline, cline.cwd, !fileExists) + + if (partFailHint) { + results.push(partFailHint + "\n" + message) + } else { + results.push(message) + } + + await cline.diffViewProvider.reset() + } catch (error) { + const errorMsg = error instanceof Error ? error.message : String(error) + updateOperationResult(relPath, { + status: "error", + error: `Error processing ${relPath}: ${errorMsg}`, + }) + results.push(`Error processing ${relPath}: ${errorMsg}`) + } + } + + // Add filtered operation errors to results + if (filteredOperationErrors.length > 0) { + results.push(...filteredOperationErrors) + } + + // Push the final result combining all operation results + pushToolResult(results.join("\n\n")) + return + } catch (error) { + await handleError("applying diff", error) + await cline.diffViewProvider.reset() + return + } +} diff --git a/src/core/webview/generateSystemPrompt.ts b/src/core/webview/generateSystemPrompt.ts index ecb326b1e4..2c88b98d2e 100644 --- a/src/core/webview/generateSystemPrompt.ts +++ b/src/core/webview/generateSystemPrompt.ts @@ -1,9 +1,11 @@ import { WebviewMessage } from "../../shared/WebviewMessage" import { defaultModeSlug, getModeBySlug, getGroupName } from "../../shared/modes" import { buildApiHandler } from "../../api" +import { experiments as experimentsModule, EXPERIMENT_IDS } from "../../shared/experiments" import { SYSTEM_PROMPT } from "../prompts/system" import { MultiSearchReplaceDiffStrategy } from "../diff/strategies/multi-search-replace" +import { MultiFileSearchReplaceDiffStrategy } from "../diff/strategies/multi-file-search-replace" import { ClineProvider } from "./ClineProvider" @@ -24,7 +26,15 @@ export const generateSystemPrompt = async (provider: ClineProvider, message: Web maxConcurrentFileReads, } = await provider.getState() - const diffStrategy = new MultiSearchReplaceDiffStrategy(fuzzyMatchThreshold) + // Check experiment to determine which diff strategy to use + const isMultiFileApplyDiffEnabled = experimentsModule.isEnabled( + experiments ?? {}, + EXPERIMENT_IDS.MULTI_FILE_APPLY_DIFF, + ) + + const diffStrategy = isMultiFileApplyDiffEnabled + ? new MultiFileSearchReplaceDiffStrategy(fuzzyMatchThreshold) + : new MultiSearchReplaceDiffStrategy(fuzzyMatchThreshold) const cwd = provider.cwd diff --git a/src/shared/ExtensionMessage.ts b/src/shared/ExtensionMessage.ts index 95729a6bea..c6efdc1aea 100644 --- a/src/shared/ExtensionMessage.ts +++ b/src/shared/ExtensionMessage.ts @@ -276,6 +276,17 @@ export interface ClineSayTool { lineSnippet: string isOutsideWorkspace?: boolean key: string + content?: string + }> + batchDiffs?: Array<{ + path: string + changeCount: number + key: string + content: string + diffs?: Array<{ + content: string + startLine?: number + }> }> question?: string } diff --git a/src/shared/__tests__/experiments.test.ts b/src/shared/__tests__/experiments.test.ts index 60a2f5e361..386677e534 100644 --- a/src/shared/__tests__/experiments.test.ts +++ b/src/shared/__tests__/experiments.test.ts @@ -14,6 +14,15 @@ describe("experiments", () => { }) }) + describe("MULTI_FILE_APPLY_DIFF", () => { + it("is configured correctly", () => { + expect(EXPERIMENT_IDS.MULTI_FILE_APPLY_DIFF).toBe("multiFileApplyDiff") + expect(experimentConfigsMap.MULTI_FILE_APPLY_DIFF).toMatchObject({ + enabled: false, + }) + }) + }) + describe("isEnabled", () => { it("returns false when POWER_STEERING experiment is not enabled", () => { const experiments: Record = { @@ -21,6 +30,7 @@ describe("experiments", () => { marketplace: false, concurrentFileReads: false, disableCompletionCommand: false, + multiFileApplyDiff: false, } expect(Experiments.isEnabled(experiments, EXPERIMENT_IDS.POWER_STEERING)).toBe(false) }) @@ -31,6 +41,7 @@ describe("experiments", () => { marketplace: false, concurrentFileReads: false, disableCompletionCommand: false, + multiFileApplyDiff: false, } expect(Experiments.isEnabled(experiments, EXPERIMENT_IDS.POWER_STEERING)).toBe(true) }) @@ -41,6 +52,7 @@ describe("experiments", () => { marketplace: false, concurrentFileReads: false, disableCompletionCommand: false, + multiFileApplyDiff: false, } expect(Experiments.isEnabled(experiments, EXPERIMENT_IDS.POWER_STEERING)).toBe(false) }) @@ -51,6 +63,7 @@ describe("experiments", () => { marketplace: false, concurrentFileReads: false, disableCompletionCommand: false, + multiFileApplyDiff: false, } expect(Experiments.isEnabled(experiments, EXPERIMENT_IDS.CONCURRENT_FILE_READS)).toBe(false) }) @@ -61,6 +74,7 @@ describe("experiments", () => { marketplace: false, concurrentFileReads: true, disableCompletionCommand: false, + multiFileApplyDiff: false, } expect(Experiments.isEnabled(experiments, EXPERIMENT_IDS.CONCURRENT_FILE_READS)).toBe(true) }) @@ -81,6 +95,7 @@ describe("experiments", () => { marketplace: false, concurrentFileReads: false, disableCompletionCommand: false, + multiFileApplyDiff: false, } expect(Experiments.isEnabled(experiments, EXPERIMENT_IDS.MARKETPLACE)).toBe(false) }) @@ -91,6 +106,7 @@ describe("experiments", () => { marketplace: true, concurrentFileReads: false, disableCompletionCommand: false, + multiFileApplyDiff: false, } expect(Experiments.isEnabled(experiments, EXPERIMENT_IDS.MARKETPLACE)).toBe(true) }) diff --git a/src/shared/experiments.ts b/src/shared/experiments.ts index bca295f498..f6c387d480 100644 --- a/src/shared/experiments.ts +++ b/src/shared/experiments.ts @@ -3,6 +3,7 @@ import type { AssertEqual, Equals, Keys, Values, ExperimentId } from "@roo-code/ export const EXPERIMENT_IDS = { MARKETPLACE: "marketplace", CONCURRENT_FILE_READS: "concurrentFileReads", + MULTI_FILE_APPLY_DIFF: "multiFileApplyDiff", DISABLE_COMPLETION_COMMAND: "disableCompletionCommand", POWER_STEERING: "powerSteering", } as const satisfies Record @@ -18,6 +19,7 @@ interface ExperimentConfig { export const experimentConfigsMap: Record = { MARKETPLACE: { enabled: false }, CONCURRENT_FILE_READS: { enabled: false }, + MULTI_FILE_APPLY_DIFF: { enabled: false }, DISABLE_COMPLETION_COMMAND: { enabled: false }, POWER_STEERING: { enabled: false }, } diff --git a/src/shared/tools.ts b/src/shared/tools.ts index 85a0cb318c..ffaf41f93f 100644 --- a/src/shared/tools.ts +++ b/src/shared/tools.ts @@ -62,6 +62,7 @@ export const toolParamNames = [ "start_line", "end_line", "query", + "args", ] as const export type ToolParamName = (typeof toolParamNames)[number] @@ -241,6 +242,11 @@ export type DiffResult = failParts?: DiffResult[] } & ({ error: string } | { failParts: DiffResult[] })) +export interface DiffItem { + content: string + startLine?: number +} + export interface DiffStrategy { /** * Get the name of this diff strategy for analytics and debugging @@ -258,12 +264,17 @@ export interface DiffStrategy { /** * Apply a diff to the original content * @param originalContent The original file content - * @param diffContent The diff content in the strategy's format + * @param diffContent The diff content in the strategy's format (string for legacy, DiffItem[] for new) * @param startLine Optional line number where the search block starts. If not provided, searches the entire file. * @param endLine Optional line number where the search block ends. If not provided, searches the entire file. * @returns A DiffResult object containing either the successful result or error details */ - applyDiff(originalContent: string, diffContent: string, startLine?: number, endLine?: number): Promise + applyDiff( + originalContent: string, + diffContent: string | DiffItem[], + startLine?: number, + endLine?: number, + ): Promise getProgressStatus?(toolUse: ToolUse, result?: any): ToolProgressStatus } diff --git a/webview-ui/src/components/chat/BatchDiffApproval.tsx b/webview-ui/src/components/chat/BatchDiffApproval.tsx new file mode 100644 index 0000000000..03f06d4106 --- /dev/null +++ b/webview-ui/src/components/chat/BatchDiffApproval.tsx @@ -0,0 +1,56 @@ +import React, { memo, useState } from "react" +import CodeAccordian from "../common/CodeAccordian" + +interface FileDiff { + path: string + changeCount: number + key: string + content: string + diffs?: Array<{ + content: string + startLine?: number + }> +} + +interface BatchDiffApprovalProps { + files: FileDiff[] + ts: number +} + +export const BatchDiffApproval = memo(({ files = [], ts }: BatchDiffApprovalProps) => { + const [expandedFiles, setExpandedFiles] = useState>({}) + + if (!files?.length) { + return null + } + + const handleToggleExpand = (filePath: string) => { + setExpandedFiles((prev) => ({ + ...prev, + [filePath]: !prev[filePath], + })) + } + + return ( +
+ {files.map((file) => { + // Combine all diffs into a single diff string for this file + const combinedDiff = file.diffs?.map((diff) => diff.content).join("\n\n") || file.content + + return ( +
+ handleToggleExpand(file.path)} + /> +
+ ) + })} +
+ ) +}) + +BatchDiffApproval.displayName = "BatchDiffApproval" diff --git a/webview-ui/src/components/chat/ChatRow.tsx b/webview-ui/src/components/chat/ChatRow.tsx index 0aa91ff917..a40a50ef53 100644 --- a/webview-ui/src/components/chat/ChatRow.tsx +++ b/webview-ui/src/components/chat/ChatRow.tsx @@ -31,6 +31,7 @@ import { Mention } from "./Mention" import { CheckpointSaved } from "./checkpoints/CheckpointSaved" import { FollowUpSuggest } from "./FollowUpSuggest" import { BatchFilePermission } from "./BatchFilePermission" +import { BatchDiffApproval } from "./BatchDiffApproval" import { ProgressIndicator } from "./ProgressIndicator" import { Markdown } from "./Markdown" import { CommandExecution } from "./CommandExecution" @@ -293,6 +294,22 @@ export const ChatRowContent = ({ switch (tool.tool) { case "editedExistingFile": case "appliedDiff": + // Check if this is a batch diff request + if (message.type === "ask" && tool.batchDiffs && Array.isArray(tool.batchDiffs)) { + return ( + <> +
+ {toolIcon("diff")} + + {t("chat:fileOperations.wantsToApplyBatchChanges")} + +
+ + + ) + } + + // Regular single file diff return ( <>
diff --git a/webview-ui/src/components/settings/ExperimentalSettings.tsx b/webview-ui/src/components/settings/ExperimentalSettings.tsx index d8bc6691d5..4e2546eb38 100644 --- a/webview-ui/src/components/settings/ExperimentalSettings.tsx +++ b/webview-ui/src/components/settings/ExperimentalSettings.tsx @@ -72,6 +72,18 @@ export const ExperimentalSettings = ({ /> ) } + if (config[0] === "MULTI_FILE_APPLY_DIFF") { + return ( + + setExperimentEnabled(EXPERIMENT_IDS.MULTI_FILE_APPLY_DIFF, enabled) + } + /> + ) + } return ( { marketplace: false, concurrentFileReads: true, disableCompletionCommand: false, + multiFileApplyDiff: true, } as Record, } @@ -240,6 +241,7 @@ describe("mergeExtensionState", () => { marketplace: false, concurrentFileReads: true, disableCompletionCommand: false, + multiFileApplyDiff: true, }) }) }) diff --git a/webview-ui/src/i18n/locales/ca/chat.json b/webview-ui/src/i18n/locales/ca/chat.json index a589109e4f..b3cf1e41b6 100644 --- a/webview-ui/src/i18n/locales/ca/chat.json +++ b/webview-ui/src/i18n/locales/ca/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "Roo vol inserir contingut a la línia {{lineNumber}} d'aquest fitxer:", "wantsToInsertAtEnd": "Roo vol afegir contingut al final d'aquest fitxer:", "wantsToReadAndXMore": "En Roo vol llegir aquest fitxer i {{count}} més:", - "wantsToReadMultiple": "Roo vol llegir diversos fitxers:" + "wantsToReadMultiple": "Roo vol llegir diversos fitxers:", + "wantsToApplyBatchChanges": "Roo vol aplicar canvis a múltiples fitxers:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo vol veure els fitxers de nivell superior en aquest directori:", diff --git a/webview-ui/src/i18n/locales/ca/settings.json b/webview-ui/src/i18n/locales/ca/settings.json index c5a03cdc7f..edadf729ed 100644 --- a/webview-ui/src/i18n/locales/ca/settings.json +++ b/webview-ui/src/i18n/locales/ca/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "Desactivar l'execució de comandes a attempt_completion", "description": "Quan està activat, l'eina attempt_completion no executarà comandes. Aquesta és una característica experimental per preparar la futura eliminació de l'execució de comandes en la finalització de tasques." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Habilita edicions de fitxers concurrents", + "description": "Quan està activat, Roo pot editar múltiples fitxers en una sola petició. Quan està desactivat, Roo ha d'editar fitxers d'un en un. Desactivar això pot ajudar quan es treballa amb models menys capaços o quan vols més control sobre les modificacions de fitxers." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/de/chat.json b/webview-ui/src/i18n/locales/de/chat.json index aac9231bf9..5b1edb2939 100644 --- a/webview-ui/src/i18n/locales/de/chat.json +++ b/webview-ui/src/i18n/locales/de/chat.json @@ -152,7 +152,8 @@ "wantsToInsert": "Roo möchte Inhalte in diese Datei einfügen:", "wantsToInsertWithLineNumber": "Roo möchte Inhalte in diese Datei in Zeile {{lineNumber}} einfügen:", "wantsToInsertAtEnd": "Roo möchte Inhalte am Ende dieser Datei anhängen:", - "wantsToReadMultiple": "Roo möchte mehrere Dateien lesen:" + "wantsToReadMultiple": "Roo möchte mehrere Dateien lesen:", + "wantsToApplyBatchChanges": "Roo möchte Änderungen an mehreren Dateien vornehmen:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo möchte die Dateien auf oberster Ebene in diesem Verzeichnis anzeigen:", diff --git a/webview-ui/src/i18n/locales/de/settings.json b/webview-ui/src/i18n/locales/de/settings.json index 47b77cd888..6597d8f717 100644 --- a/webview-ui/src/i18n/locales/de/settings.json +++ b/webview-ui/src/i18n/locales/de/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "Befehlsausführung in attempt_completion deaktivieren", "description": "Wenn aktiviert, führt das Tool attempt_completion keine Befehle aus. Dies ist eine experimentelle Funktion, um die Abschaffung der Befehlsausführung bei Aufgabenabschluss vorzubereiten." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Gleichzeitige Dateibearbeitungen aktivieren", + "description": "Wenn aktiviert, kann Roo mehrere Dateien in einer einzigen Anfrage bearbeiten. Wenn deaktiviert, muss Roo Dateien einzeln bearbeiten. Das Deaktivieren kann helfen, wenn du mit weniger fähigen Modellen arbeitest oder mehr Kontrolle über Dateiänderungen haben möchtest." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/en/chat.json b/webview-ui/src/i18n/locales/en/chat.json index 156ca523ee..866f589a8a 100644 --- a/webview-ui/src/i18n/locales/en/chat.json +++ b/webview-ui/src/i18n/locales/en/chat.json @@ -156,6 +156,7 @@ "didRead": "Roo read this file:", "wantsToEdit": "Roo wants to edit this file:", "wantsToEditOutsideWorkspace": "Roo wants to edit this file outside of the workspace:", + "wantsToApplyBatchChanges": "Roo wants to apply changes to multiple files:", "wantsToCreate": "Roo wants to create a new file:", "wantsToSearchReplace": "Roo wants to search and replace in this file:", "didSearchReplace": "Roo performed search and replace on this file:", diff --git a/webview-ui/src/i18n/locales/en/settings.json b/webview-ui/src/i18n/locales/en/settings.json index 37a22bdca5..d1c30270cf 100644 --- a/webview-ui/src/i18n/locales/en/settings.json +++ b/webview-ui/src/i18n/locales/en/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "Disable command execution in attempt_completion", "description": "When enabled, the attempt_completion tool will not execute commands. This is an experimental feature to prepare for deprecating command execution in task completion." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Enable concurrent file edits", + "description": "When enabled, Roo can edit multiple files in a single request. When disabled, Roo must edit files one at a time. Disabling this can help when working with less capable models or when you want more control over file modifications." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/es/chat.json b/webview-ui/src/i18n/locales/es/chat.json index 39cf064cf2..af3c3ab24e 100644 --- a/webview-ui/src/i18n/locales/es/chat.json +++ b/webview-ui/src/i18n/locales/es/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "Roo quiere insertar contenido en este archivo en la línea {{lineNumber}}:", "wantsToInsertAtEnd": "Roo quiere añadir contenido al final de este archivo:", "wantsToReadAndXMore": "Roo quiere leer este archivo y {{count}} más:", - "wantsToReadMultiple": "Roo quiere leer varios archivos:" + "wantsToReadMultiple": "Roo quiere leer varios archivos:", + "wantsToApplyBatchChanges": "Roo quiere aplicar cambios a múltiples archivos:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo quiere ver los archivos de nivel superior en este directorio:", diff --git a/webview-ui/src/i18n/locales/es/settings.json b/webview-ui/src/i18n/locales/es/settings.json index 3c9d423b8f..c9a356e4cd 100644 --- a/webview-ui/src/i18n/locales/es/settings.json +++ b/webview-ui/src/i18n/locales/es/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "Desactivar la ejecución de comandos en attempt_completion", "description": "Cuando está activado, la herramienta attempt_completion no ejecutará comandos. Esta es una función experimental para preparar la futura eliminación de la ejecución de comandos en la finalización de tareas." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Habilitar ediciones de archivos concurrentes", + "description": "Cuando está habilitado, Roo puede editar múltiples archivos en una sola solicitud. Cuando está deshabilitado, Roo debe editar archivos de uno en uno. Deshabilitar esto puede ayudar cuando trabajas con modelos menos capaces o cuando quieres más control sobre las modificaciones de archivos." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/fr/chat.json b/webview-ui/src/i18n/locales/fr/chat.json index 62d018c5cd..3b305b4397 100644 --- a/webview-ui/src/i18n/locales/fr/chat.json +++ b/webview-ui/src/i18n/locales/fr/chat.json @@ -149,7 +149,8 @@ "wantsToInsertWithLineNumber": "Roo veut insérer du contenu dans ce fichier à la ligne {{lineNumber}} :", "wantsToInsertAtEnd": "Roo veut ajouter du contenu à la fin de ce fichier :", "wantsToReadAndXMore": "Roo veut lire ce fichier et {{count}} de plus :", - "wantsToReadMultiple": "Roo souhaite lire plusieurs fichiers :" + "wantsToReadMultiple": "Roo souhaite lire plusieurs fichiers :", + "wantsToApplyBatchChanges": "Roo veut appliquer des modifications à plusieurs fichiers :" }, "instructions": { "wantsToFetch": "Roo veut récupérer des instructions détaillées pour aider à la tâche actuelle" diff --git a/webview-ui/src/i18n/locales/fr/settings.json b/webview-ui/src/i18n/locales/fr/settings.json index 01d8980986..430c879396 100644 --- a/webview-ui/src/i18n/locales/fr/settings.json +++ b/webview-ui/src/i18n/locales/fr/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "Désactiver l'exécution des commandes dans attempt_completion", "description": "Lorsque cette option est activée, l'outil attempt_completion n'exécutera pas de commandes. Il s'agit d'une fonctionnalité expérimentale visant à préparer la dépréciation de l'exécution des commandes lors de la finalisation des tâches." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Activer les éditions de fichiers concurrentes", + "description": "Lorsque cette option est activée, Roo peut éditer plusieurs fichiers en une seule requête. Lorsqu'elle est désactivée, Roo doit éditer les fichiers un par un. Désactiver cette option peut aider lorsque tu travailles avec des modèles moins capables ou lorsque tu veux plus de contrôle sur les modifications de fichiers." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/hi/chat.json b/webview-ui/src/i18n/locales/hi/chat.json index 9c10c57c0d..075980435f 100644 --- a/webview-ui/src/i18n/locales/hi/chat.json +++ b/webview-ui/src/i18n/locales/hi/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "Roo इस फ़ाइल की {{lineNumber}} लाइन पर सामग्री डालना चाहता है:", "wantsToInsertAtEnd": "Roo इस फ़ाइल के अंत में सामग्री जोड़ना चाहता है:", "wantsToReadAndXMore": "रू इस फ़ाइल को और {{count}} अन्य को पढ़ना चाहता है:", - "wantsToReadMultiple": "Roo कई फ़ाइलें पढ़ना चाहता है:" + "wantsToReadMultiple": "Roo कई फ़ाइलें पढ़ना चाहता है:", + "wantsToApplyBatchChanges": "Roo कई फ़ाइलों में परिवर्तन लागू करना चाहता है:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo इस निर्देशिका में शीर्ष स्तर की फ़ाइलें देखना चाहता है:", diff --git a/webview-ui/src/i18n/locales/hi/settings.json b/webview-ui/src/i18n/locales/hi/settings.json index c0fd1e9efb..31ab2191d5 100644 --- a/webview-ui/src/i18n/locales/hi/settings.json +++ b/webview-ui/src/i18n/locales/hi/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "attempt_completion में कमांड निष्पादन अक्षम करें", "description": "जब सक्षम किया जाता है, तो attempt_completion टूल कमांड निष्पादित नहीं करेगा। यह कार्य पूर्ण होने पर कमांड निष्पादन को पदावनत करने की तैयारी के लिए एक प्रयोगात्मक सुविधा है।" + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "समानांतर फ़ाइल संपादन सक्षम करें", + "description": "जब सक्षम किया जाता है, तो Roo एक ही अनुरोध में कई फ़ाइलों को संपादित कर सकता है। जब अक्षम किया जाता है, तो Roo को एक समय में एक फ़ाइल संपादित करनी होगी। इसे अक्षम करना तब मदद कर सकता है जब आप कम सक्षम मॉडल के साथ काम कर रहे हों या जब आप फ़ाइल संशोधनों पर अधिक नियंत्रण चाहते हों।" } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/it/chat.json b/webview-ui/src/i18n/locales/it/chat.json index 26dce52655..a28fa85850 100644 --- a/webview-ui/src/i18n/locales/it/chat.json +++ b/webview-ui/src/i18n/locales/it/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "Roo vuole inserire contenuto in questo file alla riga {{lineNumber}}:", "wantsToInsertAtEnd": "Roo vuole aggiungere contenuto alla fine di questo file:", "wantsToReadAndXMore": "Roo vuole leggere questo file e altri {{count}}:", - "wantsToReadMultiple": "Roo vuole leggere più file:" + "wantsToReadMultiple": "Roo vuole leggere più file:", + "wantsToApplyBatchChanges": "Roo vuole applicare modifiche a più file:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo vuole visualizzare i file di primo livello in questa directory:", diff --git a/webview-ui/src/i18n/locales/it/settings.json b/webview-ui/src/i18n/locales/it/settings.json index d920cddb6b..51d1dd640d 100644 --- a/webview-ui/src/i18n/locales/it/settings.json +++ b/webview-ui/src/i18n/locales/it/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "Disabilita l'esecuzione dei comandi in attempt_completion", "description": "Se abilitato, lo strumento attempt_completion non eseguirà comandi. Questa è una funzionalità sperimentale per preparare la futura deprecazione dell'esecuzione dei comandi al completamento dell'attività." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Abilita modifiche di file concorrenti", + "description": "Quando abilitato, Roo può modificare più file in una singola richiesta. Quando disabilitato, Roo deve modificare i file uno alla volta. Disabilitare questa opzione può aiutare quando lavori con modelli meno capaci o quando vuoi più controllo sulle modifiche dei file." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/ja/chat.json b/webview-ui/src/i18n/locales/ja/chat.json index e76dd9a120..dc60077f86 100644 --- a/webview-ui/src/i18n/locales/ja/chat.json +++ b/webview-ui/src/i18n/locales/ja/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "Rooはこのファイルの{{lineNumber}}行目にコンテンツを挿入したい:", "wantsToInsertAtEnd": "Rooはこのファイルの末尾にコンテンツを追加したい:", "wantsToReadAndXMore": "Roo はこのファイルと他に {{count}} 個のファイルを読み込もうとしています:", - "wantsToReadMultiple": "Rooは複数のファイルを読み取ろうとしています：" + "wantsToReadMultiple": "Rooは複数のファイルを読み取ろうとしています：", + "wantsToApplyBatchChanges": "Rooは複数のファイルに変更を適用したい:" }, "directoryOperations": { "wantsToViewTopLevel": "Rooはこのディレクトリのトップレベルファイルを表示したい:", diff --git a/webview-ui/src/i18n/locales/ja/settings.json b/webview-ui/src/i18n/locales/ja/settings.json index f164063fac..93cbe43a6e 100644 --- a/webview-ui/src/i18n/locales/ja/settings.json +++ b/webview-ui/src/i18n/locales/ja/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "attempt_completionでのコマンド実行を無効にする", "description": "有効にすると、attempt_completionツールはコマンドを実行しません。これは、タスク完了時のコマンド実行の非推奨化に備えるための実験的な機能です。" + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "同時ファイル編集を有効にする", + "description": "有効にすると、Rooは単一のリクエストで複数のファイルを編集できます。無効にすると、Rooはファイルを一つずつ編集する必要があります。これを無効にすることで、能力の低いモデルで作業する場合や、ファイル変更をより細かく制御したい場合に役立ちます。" } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/ko/chat.json b/webview-ui/src/i18n/locales/ko/chat.json index 563508d2a9..2afe6ff5f4 100644 --- a/webview-ui/src/i18n/locales/ko/chat.json +++ b/webview-ui/src/i18n/locales/ko/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "Roo가 이 파일의 {{lineNumber}}번 줄에 내용을 삽입하고 싶어합니다:", "wantsToInsertAtEnd": "Roo가 이 파일의 끝에 내용을 추가하고 싶어합니다:", "wantsToReadAndXMore": "Roo가 이 파일과 {{count}}개의 파일을 더 읽으려고 합니다:", - "wantsToReadMultiple": "Roo가 여러 파일을 읽으려고 합니다:" + "wantsToReadMultiple": "Roo가 여러 파일을 읽으려고 합니다:", + "wantsToApplyBatchChanges": "Roo가 여러 파일에 변경 사항을 적용하고 싶어합니다:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo가 이 디렉토리의 최상위 파일을 보고 싶어합니다:", diff --git a/webview-ui/src/i18n/locales/ko/settings.json b/webview-ui/src/i18n/locales/ko/settings.json index 8d311f8fe6..a7ec710f23 100644 --- a/webview-ui/src/i18n/locales/ko/settings.json +++ b/webview-ui/src/i18n/locales/ko/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "attempt_completion에서 명령 실행 비활성화", "description": "활성화하면 attempt_completion 도구가 명령을 실행하지 않습니다. 이는 작업 완료 시 명령 실행을 더 이상 사용하지 않도록 준비하기 위한 실험적 기능입니다." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "동시 파일 편집 활성화", + "description": "활성화하면 Roo가 단일 요청으로 여러 파일을 편집할 수 있습니다. 비활성화하면 Roo는 파일을 하나씩 편집해야 합니다. 이 기능을 비활성화하면 덜 강력한 모델로 작업하거나 파일 수정에 대한 더 많은 제어가 필요할 때 도움이 됩니다." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/nl/chat.json b/webview-ui/src/i18n/locales/nl/chat.json index 2a8ba0ac70..5001b9f7cc 100644 --- a/webview-ui/src/i18n/locales/nl/chat.json +++ b/webview-ui/src/i18n/locales/nl/chat.json @@ -147,7 +147,8 @@ "wantsToInsertWithLineNumber": "Roo wil inhoud invoegen in dit bestand op regel {{lineNumber}}:", "wantsToInsertAtEnd": "Roo wil inhoud toevoegen aan het einde van dit bestand:", "wantsToReadAndXMore": "Roo wil dit bestand en nog {{count}} andere lezen:", - "wantsToReadMultiple": "Roo wil meerdere bestanden lezen:" + "wantsToReadMultiple": "Roo wil meerdere bestanden lezen:", + "wantsToApplyBatchChanges": "Roo wil wijzigingen toepassen op meerdere bestanden:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo wil de bovenliggende bestanden in deze map bekijken:", diff --git a/webview-ui/src/i18n/locales/nl/settings.json b/webview-ui/src/i18n/locales/nl/settings.json index d234ff7e11..8ec7bb35c4 100644 --- a/webview-ui/src/i18n/locales/nl/settings.json +++ b/webview-ui/src/i18n/locales/nl/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "Commando-uitvoering in attempt_completion uitschakelen", "description": "Indien ingeschakeld, zal de attempt_completion tool geen commando's uitvoeren. Dit is een experimentele functie ter voorbereiding op het afschaffen van commando-uitvoering bij taakvoltooiing." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Gelijktijdige bestandsbewerkingen inschakelen", + "description": "Wanneer ingeschakeld, kan Roo meerdere bestanden in één verzoek bewerken. Wanneer uitgeschakeld, moet Roo bestanden één voor één bewerken. Het uitschakelen hiervan kan helpen wanneer je werkt met minder capabele modellen of wanneer je meer controle wilt over bestandswijzigingen." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/pl/chat.json b/webview-ui/src/i18n/locales/pl/chat.json index a57dc9d0cc..c02a9ba777 100644 --- a/webview-ui/src/i18n/locales/pl/chat.json +++ b/webview-ui/src/i18n/locales/pl/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "Roo chce wstawić zawartość do tego pliku w linii {{lineNumber}}:", "wantsToInsertAtEnd": "Roo chce dodać zawartość na końcu tego pliku:", "wantsToReadAndXMore": "Roo chce przeczytać ten plik i {{count}} więcej:", - "wantsToReadMultiple": "Roo chce odczytać wiele plików:" + "wantsToReadMultiple": "Roo chce odczytać wiele plików:", + "wantsToApplyBatchChanges": "Roo chce zastosować zmiany do wielu plików:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo chce zobaczyć pliki najwyższego poziomu w tym katalogu:", diff --git a/webview-ui/src/i18n/locales/pl/settings.json b/webview-ui/src/i18n/locales/pl/settings.json index c9bc4ac1ab..aade54b772 100644 --- a/webview-ui/src/i18n/locales/pl/settings.json +++ b/webview-ui/src/i18n/locales/pl/settings.json @@ -500,6 +500,10 @@ "MARKETPLACE": { "name": "Włącz Marketplace", "description": "Gdy włączone, możesz instalować MCP i niestandardowe tryby z Marketplace." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Włącz równoczesne edycje plików", + "description": "Gdy włączone, Roo może edytować wiele plików w jednym żądaniu. Gdy wyłączone, Roo musi edytować pliki jeden po drugim. Wyłączenie tego może pomóc podczas pracy z mniej zdolnymi modelami lub gdy chcesz mieć większą kontrolę nad modyfikacjami plików." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/pt-BR/chat.json b/webview-ui/src/i18n/locales/pt-BR/chat.json index 05d436de71..f1eca6a982 100644 --- a/webview-ui/src/i18n/locales/pt-BR/chat.json +++ b/webview-ui/src/i18n/locales/pt-BR/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "Roo quer inserir conteúdo neste arquivo na linha {{lineNumber}}:", "wantsToInsertAtEnd": "Roo quer adicionar conteúdo ao final deste arquivo:", "wantsToReadAndXMore": "Roo quer ler este arquivo e mais {{count}}:", - "wantsToReadMultiple": "Roo deseja ler múltiplos arquivos:" + "wantsToReadMultiple": "Roo deseja ler múltiplos arquivos:", + "wantsToApplyBatchChanges": "Roo quer aplicar alterações a múltiplos arquivos:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo quer visualizar os arquivos de nível superior neste diretório:", diff --git a/webview-ui/src/i18n/locales/pt-BR/settings.json b/webview-ui/src/i18n/locales/pt-BR/settings.json index b2ab1756c3..8e1a5af79a 100644 --- a/webview-ui/src/i18n/locales/pt-BR/settings.json +++ b/webview-ui/src/i18n/locales/pt-BR/settings.json @@ -500,6 +500,10 @@ "MARKETPLACE": { "name": "Ativar Marketplace", "description": "Quando ativado, você pode instalar MCPs e modos personalizados do Marketplace." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Habilitar edições de arquivos concorrentes", + "description": "Quando habilitado, o Roo pode editar múltiplos arquivos em uma única solicitação. Quando desabilitado, o Roo deve editar arquivos um de cada vez. Desabilitar isso pode ajudar ao trabalhar com modelos menos capazes ou quando você quer mais controle sobre modificações de arquivos." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/ru/chat.json b/webview-ui/src/i18n/locales/ru/chat.json index 8e24a9e3ea..fcee847f15 100644 --- a/webview-ui/src/i18n/locales/ru/chat.json +++ b/webview-ui/src/i18n/locales/ru/chat.json @@ -147,7 +147,8 @@ "wantsToInsertWithLineNumber": "Roo хочет вставить содержимое в этот файл на строку {{lineNumber}}:", "wantsToInsertAtEnd": "Roo хочет добавить содержимое в конец этого файла:", "wantsToReadAndXMore": "Roo хочет прочитать этот файл и еще {{count}}:", - "wantsToReadMultiple": "Roo хочет прочитать несколько файлов:" + "wantsToReadMultiple": "Roo хочет прочитать несколько файлов:", + "wantsToApplyBatchChanges": "Roo хочет применить изменения к нескольким файлам:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo хочет просмотреть файлы верхнего уровня в этой директории:", diff --git a/webview-ui/src/i18n/locales/ru/settings.json b/webview-ui/src/i18n/locales/ru/settings.json index 1daf624a71..acf9235253 100644 --- a/webview-ui/src/i18n/locales/ru/settings.json +++ b/webview-ui/src/i18n/locales/ru/settings.json @@ -500,6 +500,10 @@ "MARKETPLACE": { "name": "Включить Marketplace", "description": "Когда включено, вы можете устанавливать MCP и пользовательские режимы из Marketplace." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Включить одновременное редактирование файлов", + "description": "Когда включено, Roo может редактировать несколько файлов в одном запросе. Когда отключено, Roo должен редактировать файлы по одному. Отключение этой функции может помочь при работе с менее способными моделями или когда вы хотите больше контроля над изменениями файлов." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/tr/chat.json b/webview-ui/src/i18n/locales/tr/chat.json index c0d43f59b5..a3a0a9bfd4 100644 --- a/webview-ui/src/i18n/locales/tr/chat.json +++ b/webview-ui/src/i18n/locales/tr/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "Roo bu dosyanın {{lineNumber}}. satırına içerik eklemek istiyor:", "wantsToInsertAtEnd": "Roo bu dosyanın sonuna içerik eklemek istiyor:", "wantsToReadAndXMore": "Roo bu dosyayı ve {{count}} tane daha okumak istiyor:", - "wantsToReadMultiple": "Roo birden fazla dosya okumak istiyor:" + "wantsToReadMultiple": "Roo birden fazla dosya okumak istiyor:", + "wantsToApplyBatchChanges": "Roo birden fazla dosyaya değişiklik uygulamak istiyor:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo bu dizindeki üst düzey dosyaları görüntülemek istiyor:", diff --git a/webview-ui/src/i18n/locales/tr/settings.json b/webview-ui/src/i18n/locales/tr/settings.json index 8638045511..2445ea6c91 100644 --- a/webview-ui/src/i18n/locales/tr/settings.json +++ b/webview-ui/src/i18n/locales/tr/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "attempt_completion'da komut yürütmeyi devre dışı bırak", "description": "Etkinleştirildiğinde, attempt_completion aracı komutları yürütmez. Bu, görev tamamlandığında komut yürütmenin kullanımdan kaldırılmasına hazırlanmak için deneysel bir özelliktir." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Eşzamanlı dosya düzenlemelerini etkinleştir", + "description": "Etkinleştirildiğinde, Roo tek bir istekte birden fazla dosyayı düzenleyebilir. Devre dışı bırakıldığında, Roo dosyaları tek tek düzenlemek zorundadır. Bunu devre dışı bırakmak, daha az yetenekli modellerle çalışırken veya dosya değişiklikleri üzerinde daha fazla kontrol istediğinde yardımcı olabilir." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/vi/chat.json b/webview-ui/src/i18n/locales/vi/chat.json index 5ad270aa89..3349f20002 100644 --- a/webview-ui/src/i18n/locales/vi/chat.json +++ b/webview-ui/src/i18n/locales/vi/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "Roo muốn chèn nội dung vào dòng {{lineNumber}} của tệp này:", "wantsToInsertAtEnd": "Roo muốn thêm nội dung vào cuối tệp này:", "wantsToReadAndXMore": "Roo muốn đọc tệp này và {{count}} tệp khác:", - "wantsToReadMultiple": "Roo muốn đọc nhiều tệp:" + "wantsToReadMultiple": "Roo muốn đọc nhiều tệp:", + "wantsToApplyBatchChanges": "Roo muốn áp dụng thay đổi cho nhiều tệp:" }, "directoryOperations": { "wantsToViewTopLevel": "Roo muốn xem các tệp cấp cao nhất trong thư mục này:", diff --git a/webview-ui/src/i18n/locales/vi/settings.json b/webview-ui/src/i18n/locales/vi/settings.json index edc85033fb..9dc39075c7 100644 --- a/webview-ui/src/i18n/locales/vi/settings.json +++ b/webview-ui/src/i18n/locales/vi/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "Tắt thực thi lệnh trong attempt_completion", "description": "Khi được bật, công cụ attempt_completion sẽ không thực thi lệnh. Đây là một tính năng thử nghiệm để chuẩn bị cho việc ngừng hỗ trợ thực thi lệnh khi hoàn thành tác vụ trong tương lai." + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "Bật chỉnh sửa tệp đồng thời", + "description": "Khi được bật, Roo có thể chỉnh sửa nhiều tệp trong một yêu cầu duy nhất. Khi bị tắt, Roo phải chỉnh sửa từng tệp một. Tắt tính năng này có thể hữu ích khi làm việc với các mô hình kém khả năng hơn hoặc khi bạn muốn kiểm soát nhiều hơn đối với các thay đổi tệp." } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/zh-CN/chat.json b/webview-ui/src/i18n/locales/zh-CN/chat.json index 058adfd0ad..3841abd499 100644 --- a/webview-ui/src/i18n/locales/zh-CN/chat.json +++ b/webview-ui/src/i18n/locales/zh-CN/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "需要在第 {{lineNumber}} 行插入内容:", "wantsToInsertAtEnd": "需要在文件末尾添加内容:", "wantsToReadAndXMore": "Roo 想读取此文件以及另外 {{count}} 个文件：", - "wantsToReadMultiple": "Roo 想要读取多个文件：" + "wantsToReadMultiple": "Roo 想要读取多个文件：", + "wantsToApplyBatchChanges": "Roo 想要对多个文件应用更改：" }, "directoryOperations": { "wantsToViewTopLevel": "需要查看目录文件列表:", diff --git a/webview-ui/src/i18n/locales/zh-CN/settings.json b/webview-ui/src/i18n/locales/zh-CN/settings.json index 9e422f9a58..be8f221a81 100644 --- a/webview-ui/src/i18n/locales/zh-CN/settings.json +++ b/webview-ui/src/i18n/locales/zh-CN/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "禁用 attempt_completion 中的命令执行", "description": "启用后，attempt_completion 工具将不会执行命令。这是一项实验性功能，旨在为将来弃用任务完成时的命令执行做准备。" + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "启用并发文件编辑", + "description": "启用后 Roo 可在单个请求中编辑多个文件。禁用后 Roo 必须逐个编辑文件。禁用此功能有助于使用能力较弱的模型或需要更精确控制文件修改时。" } }, "promptCaching": { diff --git a/webview-ui/src/i18n/locales/zh-TW/chat.json b/webview-ui/src/i18n/locales/zh-TW/chat.json index 0309948a95..651719e839 100644 --- a/webview-ui/src/i18n/locales/zh-TW/chat.json +++ b/webview-ui/src/i18n/locales/zh-TW/chat.json @@ -152,7 +152,8 @@ "wantsToInsertWithLineNumber": "Roo 想要在此檔案第 {{lineNumber}} 行插入內容：", "wantsToInsertAtEnd": "Roo 想要在此檔案末尾新增內容：", "wantsToReadAndXMore": "Roo 想要讀取此檔案以及另外 {{count}} 個檔案：", - "wantsToReadMultiple": "Roo 想要讀取多個檔案：" + "wantsToReadMultiple": "Roo 想要讀取多個檔案：", + "wantsToApplyBatchChanges": "Roo 想要對多個檔案套用變更：" }, "directoryOperations": { "wantsToViewTopLevel": "Roo 想要檢視此目錄中最上層的檔案：", diff --git a/webview-ui/src/i18n/locales/zh-TW/settings.json b/webview-ui/src/i18n/locales/zh-TW/settings.json index 04b26b7310..901ec23416 100644 --- a/webview-ui/src/i18n/locales/zh-TW/settings.json +++ b/webview-ui/src/i18n/locales/zh-TW/settings.json @@ -500,6 +500,10 @@ "DISABLE_COMPLETION_COMMAND": { "name": "停用 attempt_completion 中的指令執行", "description": "啟用後，attempt_completion 工具將不會執行指令。這是一項實驗性功能，旨在為未來停用工作完成時的指令執行做準備。" + }, + "MULTI_FILE_APPLY_DIFF": { + "name": "啟用並行檔案編輯", + "description": "啟用後 Roo 可在單個請求中編輯多個檔案。停用後 Roo 必須逐個編輯檔案。停用此功能有助於使用能力較弱的模型或需要更精確控制檔案修改時。" } }, "promptCaching": { From fb3a728a30614ecefc9c03b597ebc64aec3701ac Mon Sep 17 00:00:00 2001 From: Hannes Rudolph Date: Thu, 12 Jun 2025 10:39:21 -0600 Subject: [PATCH 12/33] feat: Add reasoning budget support to Bedrock models for extended thinking (#4201) (#4481) * Add reasoning budget support to Bedrock models and update related components - Introduced `supportsReasoningBudget` property in Bedrock models. - Enhanced `AwsBedrockHandler` to handle reasoning budget in payloads. - Updated `ThinkingBudget` component to dynamically set max tokens based on reasoning support. - Modified `ApiOptions` and `Bedrock` components to conditionally render `ThinkingBudget`. - Added tests for extended thinking functionality in `bedrock-reasoning.test.ts`. * Add BedrockThinkingConfig interface and update payload structure * fix: address PR review feedback (#4481) - Simplify ThinkingBudget ternary logic since component only renders when reasoning budget supported - Break down complex thinking enabled condition with clear documentation - Replace 'as any' usage with proper TypeScript interfaces for AWS SDK events - Add comprehensive documentation for multiple stream structures explaining AWS SDK compatibility --- packages/types/src/providers/bedrock.ts | 3 + .../__tests__/bedrock-reasoning.test.ts | 280 ++++++++++++++++++ src/api/providers/bedrock.ts | 278 ++++++++++++++--- .../src/components/settings/ApiOptions.tsx | 14 +- .../components/settings/ThinkingBudget.tsx | 6 +- .../components/settings/providers/Bedrock.tsx | 32 +- 6 files changed, 550 insertions(+), 63 deletions(-) create mode 100644 src/api/providers/__tests__/bedrock-reasoning.test.ts diff --git a/packages/types/src/providers/bedrock.ts b/packages/types/src/providers/bedrock.ts index ce5ea28e95..a15f041252 100644 --- a/packages/types/src/providers/bedrock.ts +++ b/packages/types/src/providers/bedrock.ts @@ -73,6 +73,7 @@ export const bedrockModels = { supportsImages: true, supportsComputerUse: true, supportsPromptCache: true, + supportsReasoningBudget: true, inputPrice: 3.0, outputPrice: 15.0, cacheWritesPrice: 3.75, @@ -87,6 +88,7 @@ export const bedrockModels = { supportsImages: true, supportsComputerUse: true, supportsPromptCache: true, + supportsReasoningBudget: true, inputPrice: 15.0, outputPrice: 75.0, cacheWritesPrice: 18.75, @@ -101,6 +103,7 @@ export const bedrockModels = { supportsImages: true, supportsComputerUse: true, supportsPromptCache: true, + supportsReasoningBudget: true, inputPrice: 3.0, outputPrice: 15.0, cacheWritesPrice: 3.75, diff --git a/src/api/providers/__tests__/bedrock-reasoning.test.ts b/src/api/providers/__tests__/bedrock-reasoning.test.ts new file mode 100644 index 0000000000..4a45c25701 --- /dev/null +++ b/src/api/providers/__tests__/bedrock-reasoning.test.ts @@ -0,0 +1,280 @@ +import { AwsBedrockHandler } from "../bedrock" +import { BedrockRuntimeClient, ConverseStreamCommand } from "@aws-sdk/client-bedrock-runtime" +import { logger } from "../../../utils/logging" + +// Mock the AWS SDK +jest.mock("@aws-sdk/client-bedrock-runtime") +jest.mock("../../../utils/logging") + +// Store the command payload for verification +let capturedPayload: any = null + +describe("AwsBedrockHandler - Extended Thinking", () => { + let handler: AwsBedrockHandler + let mockSend: jest.Mock + + beforeEach(() => { + capturedPayload = null + mockSend = jest.fn() + + // Mock ConverseStreamCommand to capture the payload + ;(ConverseStreamCommand as unknown as jest.Mock).mockImplementation((payload) => { + capturedPayload = payload + return { + input: payload, + } + }) + ;(BedrockRuntimeClient as jest.Mock).mockImplementation(() => ({ + send: mockSend, + config: { region: "us-east-1" }, + })) + ;(logger.info as jest.Mock).mockImplementation(() => {}) + ;(logger.error as jest.Mock).mockImplementation(() => {}) + }) + + afterEach(() => { + jest.clearAllMocks() + }) + + describe("Extended Thinking Support", () => { + it("should include thinking parameter for Claude Sonnet 4 when reasoning is enabled", async () => { + handler = new AwsBedrockHandler({ + apiProvider: "bedrock", + apiModelId: "anthropic.claude-sonnet-4-20250514-v1:0", + awsRegion: "us-east-1", + enableReasoningEffort: true, + modelMaxTokens: 8192, + modelMaxThinkingTokens: 4096, + }) + + // Mock the stream response + mockSend.mockResolvedValue({ + stream: (async function* () { + yield { + messageStart: { role: "assistant" }, + } + yield { + contentBlockStart: { + content_block: { type: "thinking", thinking: "Let me think..." }, + contentBlockIndex: 0, + }, + } + yield { + contentBlockDelta: { + delta: { type: "thinking_delta", thinking: " about this problem." }, + }, + } + yield { + contentBlockStart: { + start: { text: "Here's the answer:" }, + contentBlockIndex: 1, + }, + } + yield { + metadata: { + usage: { inputTokens: 100, outputTokens: 50 }, + }, + } + })(), + }) + + const messages = [{ role: "user" as const, content: "Test message" }] + const stream = handler.createMessage("System prompt", messages) + + const chunks = [] + for await (const chunk of stream) { + chunks.push(chunk) + } + + // Verify the command was called with the correct payload + expect(mockSend).toHaveBeenCalledTimes(1) + expect(capturedPayload).toBeDefined() + expect(capturedPayload.additionalModelRequestFields).toBeDefined() + expect(capturedPayload.additionalModelRequestFields.thinking).toEqual({ + type: "enabled", + budget_tokens: 4096, // Uses the full modelMaxThinkingTokens value + }) + + // Verify reasoning chunks were yielded + const reasoningChunks = chunks.filter((c) => c.type === "reasoning") + expect(reasoningChunks).toHaveLength(2) + expect(reasoningChunks[0].text).toBe("Let me think...") + expect(reasoningChunks[1].text).toBe(" about this problem.") + + // Verify that topP is NOT present when thinking is enabled + expect(capturedPayload.inferenceConfig).not.toHaveProperty("topP") + }) + + it("should pass thinking parameters from metadata", async () => { + handler = new AwsBedrockHandler({ + apiProvider: "bedrock", + apiModelId: "anthropic.claude-3-7-sonnet-20250219-v1:0", + awsRegion: "us-east-1", + }) + + mockSend.mockResolvedValue({ + stream: (async function* () { + yield { messageStart: { role: "assistant" } } + yield { metadata: { usage: { inputTokens: 100, outputTokens: 50 } } } + })(), + }) + + const messages = [{ role: "user" as const, content: "Test message" }] + const metadata = { + taskId: "test-task", + thinking: { + enabled: true, + maxTokens: 16384, + maxThinkingTokens: 8192, + }, + } + + const stream = handler.createMessage("System prompt", messages, metadata) + const chunks = [] + for await (const chunk of stream) { + chunks.push(chunk) + } + + // Verify the thinking parameter was passed correctly + expect(mockSend).toHaveBeenCalledTimes(1) + expect(capturedPayload).toBeDefined() + expect(capturedPayload.additionalModelRequestFields).toBeDefined() + expect(capturedPayload.additionalModelRequestFields.thinking).toEqual({ + type: "enabled", + budget_tokens: 8192, + }) + + // Verify that topP is NOT present when thinking is enabled via metadata + expect(capturedPayload.inferenceConfig).not.toHaveProperty("topP") + }) + + it("should log when extended thinking is enabled", async () => { + handler = new AwsBedrockHandler({ + apiProvider: "bedrock", + apiModelId: "anthropic.claude-opus-4-20250514-v1:0", + awsRegion: "us-east-1", + enableReasoningEffort: true, + modelMaxThinkingTokens: 5000, + }) + + mockSend.mockResolvedValue({ + stream: (async function* () { + yield { messageStart: { role: "assistant" } } + })(), + }) + + const messages = [{ role: "user" as const, content: "Test" }] + const stream = handler.createMessage("System prompt", messages) + + for await (const chunk of stream) { + // consume stream + } + + // Verify logging + expect(logger.info).toHaveBeenCalledWith( + expect.stringContaining("Extended thinking enabled"), + expect.objectContaining({ + ctx: "bedrock", + modelId: "anthropic.claude-opus-4-20250514-v1:0", + }), + ) + }) + + it("should include topP when thinking is disabled", async () => { + handler = new AwsBedrockHandler({ + apiProvider: "bedrock", + apiModelId: "anthropic.claude-3-7-sonnet-20250219-v1:0", + awsRegion: "us-east-1", + // Note: no enableReasoningEffort = true, so thinking is disabled + }) + + mockSend.mockResolvedValue({ + stream: (async function* () { + yield { messageStart: { role: "assistant" } } + yield { + contentBlockStart: { + start: { text: "Hello" }, + contentBlockIndex: 0, + }, + } + yield { + contentBlockDelta: { + delta: { text: " world" }, + }, + } + yield { metadata: { usage: { inputTokens: 100, outputTokens: 50 } } } + })(), + }) + + const messages = [{ role: "user" as const, content: "Test message" }] + const stream = handler.createMessage("System prompt", messages) + + const chunks = [] + for await (const chunk of stream) { + chunks.push(chunk) + } + + // Verify that topP IS present when thinking is disabled + expect(mockSend).toHaveBeenCalledTimes(1) + expect(capturedPayload).toBeDefined() + expect(capturedPayload.inferenceConfig).toHaveProperty("topP", 0.1) + + // Verify that additionalModelRequestFields is not present or empty + expect(capturedPayload.additionalModelRequestFields).toBeUndefined() + }) + + it("should enable reasoning when enableReasoningEffort is true in settings", async () => { + handler = new AwsBedrockHandler({ + apiProvider: "bedrock", + apiModelId: "anthropic.claude-sonnet-4-20250514-v1:0", + awsRegion: "us-east-1", + enableReasoningEffort: true, // This should trigger reasoning + modelMaxThinkingTokens: 4096, + }) + + mockSend.mockResolvedValue({ + stream: (async function* () { + yield { messageStart: { role: "assistant" } } + yield { + contentBlockStart: { + content_block: { type: "thinking", thinking: "Let me think..." }, + contentBlockIndex: 0, + }, + } + yield { + contentBlockDelta: { + delta: { type: "thinking_delta", thinking: " about this problem." }, + }, + } + yield { metadata: { usage: { inputTokens: 100, outputTokens: 50 } } } + })(), + }) + + const messages = [{ role: "user" as const, content: "Test message" }] + const stream = handler.createMessage("System prompt", messages) + + const chunks = [] + for await (const chunk of stream) { + chunks.push(chunk) + } + + // Verify thinking was enabled via settings + expect(mockSend).toHaveBeenCalledTimes(1) + expect(capturedPayload).toBeDefined() + expect(capturedPayload.additionalModelRequestFields).toBeDefined() + expect(capturedPayload.additionalModelRequestFields.thinking).toEqual({ + type: "enabled", + budget_tokens: 4096, + }) + + // Verify that topP is NOT present when thinking is enabled via settings + expect(capturedPayload.inferenceConfig).not.toHaveProperty("topP") + + // Verify reasoning chunks were yielded + const reasoningChunks = chunks.filter((c) => c.type === "reasoning") + expect(reasoningChunks).toHaveLength(2) + expect(reasoningChunks[0].text).toBe("Let me think...") + expect(reasoningChunks[1].text).toBe(" about this problem.") + }) + }) +}) diff --git a/src/api/providers/bedrock.ts b/src/api/providers/bedrock.ts index 16ce3289aa..b5474cce50 100644 --- a/src/api/providers/bedrock.ts +++ b/src/api/providers/bedrock.ts @@ -29,6 +29,8 @@ import { logger } from "../../utils/logging" import { MultiPointStrategy } from "../transform/cache-strategy/multi-point-strategy" import { ModelInfo as CacheModelInfo } from "../transform/cache-strategy/types" import { convertToBedrockConverseMessages as sharedConverter } from "../transform/bedrock-converse-format" +import { getModelParams } from "../transform/model-params" +import { shouldUseReasoningBudget } from "../../shared/api" import type { SingleCompletionHandler, ApiHandlerCreateMessageMetadata } from "../index" /************************************************************************************ @@ -40,8 +42,63 @@ import type { SingleCompletionHandler, ApiHandlerCreateMessageMetadata } from ". // Define interface for Bedrock inference config interface BedrockInferenceConfig { maxTokens: number - temperature: number - topP: number + temperature?: number + topP?: number +} + +// Define interface for Bedrock thinking configuration +interface BedrockThinkingConfig { + thinking: { + type: "enabled" + budget_tokens: number + } + [key: string]: any // Add index signature to be compatible with DocumentType +} + +// Define interface for Bedrock payload +interface BedrockPayload { + modelId: BedrockModelId | string + messages: Message[] + system?: SystemContentBlock[] + inferenceConfig: BedrockInferenceConfig + anthropic_version?: string + additionalModelRequestFields?: BedrockThinkingConfig +} + +// Define specific types for content block events to avoid 'as any' usage +// These handle the multiple possible structures returned by AWS SDK +interface ContentBlockStartEvent { + start?: { + text?: string + thinking?: string + } + contentBlockIndex?: number + // Alternative structure used by some AWS SDK versions + content_block?: { + type?: string + thinking?: string + } + // Official AWS SDK structure for reasoning (as documented) + contentBlock?: { + type?: string + thinking?: string + reasoningContent?: { + text?: string + } + } +} + +interface ContentBlockDeltaEvent { + delta?: { + text?: string + thinking?: string + type?: string + // AWS SDK structure for reasoning content deltas + reasoningContent?: { + text?: string + } + } + contentBlockIndex?: number } // Define types for stream events based on AWS SDK @@ -53,18 +110,8 @@ export interface StreamEvent { stopReason?: "end_turn" | "tool_use" | "max_tokens" | "stop_sequence" additionalModelResponseFields?: Record } - contentBlockStart?: { - start?: { - text?: string - } - contentBlockIndex?: number - } - contentBlockDelta?: { - delta?: { - text?: string - } - contentBlockIndex?: number - } + contentBlockStart?: ContentBlockStartEvent + contentBlockDelta?: ContentBlockDeltaEvent metadata?: { usage?: { inputTokens: number @@ -255,13 +302,17 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH override async *createMessage( systemPrompt: string, messages: Anthropic.Messages.MessageParam[], - metadata?: ApiHandlerCreateMessageMetadata, + metadata?: ApiHandlerCreateMessageMetadata & { + thinking?: { + enabled: boolean + maxTokens?: number + maxThinkingTokens?: number + } + }, ): ApiStream { - let modelConfig = this.getModel() - // Handle cross-region inference + const modelConfig = this.getModel() const usePromptCache = Boolean(this.options.awsUsePromptCache && this.supportsAwsPromptCache(modelConfig)) - // Generate a conversation ID based on the first few messages to maintain cache consistency const conversationId = messages.length > 0 ? `conv_${messages[0].role}_${ @@ -271,7 +322,6 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH }` : "default_conversation" - // Convert messages to Bedrock format, passing the model info and conversation ID const formatted = this.convertToBedrockConverseMessages( messages, systemPrompt, @@ -280,18 +330,50 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH conversationId, ) - // Construct the payload - const inferenceConfig: BedrockInferenceConfig = { - maxTokens: modelConfig.info.maxTokens as number, - temperature: this.options.modelTemperature as number, - topP: 0.1, + let additionalModelRequestFields: BedrockThinkingConfig | undefined + let thinkingEnabled = false + + // Determine if thinking should be enabled + // metadata?.thinking?.enabled: Explicitly enabled through API metadata (direct request) + // shouldUseReasoningBudget(): Enabled through user settings (enableReasoningEffort = true) + const isThinkingExplicitlyEnabled = metadata?.thinking?.enabled + const isThinkingEnabledBySettings = + shouldUseReasoningBudget({ model: modelConfig.info, settings: this.options }) && + modelConfig.reasoning && + modelConfig.reasoningBudget + + if ((isThinkingExplicitlyEnabled || isThinkingEnabledBySettings) && modelConfig.info.supportsReasoningBudget) { + thinkingEnabled = true + additionalModelRequestFields = { + thinking: { + type: "enabled", + budget_tokens: metadata?.thinking?.maxThinkingTokens || modelConfig.reasoningBudget || 4096, + }, + } + logger.info("Extended thinking enabled for Bedrock request", { + ctx: "bedrock", + modelId: modelConfig.id, + thinking: additionalModelRequestFields.thinking, + }) } - const payload = { + const inferenceConfig: BedrockInferenceConfig = { + maxTokens: modelConfig.maxTokens || (modelConfig.info.maxTokens as number), + temperature: modelConfig.temperature ?? (this.options.modelTemperature as number), + } + + if (!thinkingEnabled) { + inferenceConfig.topP = 0.1 + } + + const payload: BedrockPayload = { modelId: modelConfig.id, messages: formatted.messages, system: formatted.system, inferenceConfig, + ...(additionalModelRequestFields && { additionalModelRequestFields }), + // Add anthropic_version when using thinking features + ...(thinkingEnabled && { anthropic_version: "bedrock-2023-05-31" }), } // Create AbortController with 10 minute timeout @@ -397,19 +479,74 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH } // Handle content blocks - if (streamEvent.contentBlockStart?.start?.text) { - yield { - type: "text", - text: streamEvent.contentBlockStart.start.text, + if (streamEvent.contentBlockStart) { + const cbStart = streamEvent.contentBlockStart + + // Check if this is a reasoning block (official AWS SDK structure) + if (cbStart.contentBlock?.reasoningContent) { + if (cbStart.contentBlockIndex && cbStart.contentBlockIndex > 0) { + yield { type: "reasoning", text: "\n" } + } + yield { + type: "reasoning", + text: cbStart.contentBlock.reasoningContent.text || "", + } + } + // Check for thinking block - handle both possible AWS SDK structures + // cbStart.contentBlock: newer/official structure + // cbStart.content_block: alternative structure seen in some AWS SDK versions + else if (cbStart.contentBlock?.type === "thinking" || cbStart.content_block?.type === "thinking") { + const contentBlock = cbStart.contentBlock || cbStart.content_block + if (cbStart.contentBlockIndex && cbStart.contentBlockIndex > 0) { + yield { type: "reasoning", text: "\n" } + } + if (contentBlock?.thinking) { + yield { + type: "reasoning", + text: contentBlock.thinking, + } + } + } else if (cbStart.start?.text) { + yield { + type: "text", + text: cbStart.start.text, + } } continue } // Handle content deltas - if (streamEvent.contentBlockDelta?.delta?.text) { - yield { - type: "text", - text: streamEvent.contentBlockDelta.delta.text, + if (streamEvent.contentBlockDelta) { + const cbDelta = streamEvent.contentBlockDelta + const delta = cbDelta.delta + + // Process reasoning and text content deltas + // Multiple structures are supported for AWS SDK compatibility: + // - delta.reasoningContent.text: official AWS docs structure for reasoning + // - delta.thinking: alternative structure for thinking content + // - delta.text: standard text content + if (delta) { + // Check for reasoningContent property (official AWS SDK structure) + if (delta.reasoningContent?.text) { + yield { + type: "reasoning", + text: delta.reasoningContent.text, + } + continue + } + + // Handle alternative thinking structure (fallback for older SDK versions) + if (delta.type === "thinking_delta" && delta.thinking) { + yield { + type: "reasoning", + text: delta.thinking, + } + } else if (delta.text) { + yield { + type: "text", + text: delta.text, + } + } } continue } @@ -444,10 +581,17 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH try { const modelConfig = this.getModel() + // For completePrompt, thinking is typically not used, but we should still check + // if thinking was somehow enabled in the model config + const thinkingEnabled = + shouldUseReasoningBudget({ model: modelConfig.info, settings: this.options }) && + modelConfig.reasoning && + modelConfig.reasoningBudget + const inferenceConfig: BedrockInferenceConfig = { - maxTokens: modelConfig.info.maxTokens as number, - temperature: this.options.modelTemperature as number, - topP: 0.1, + maxTokens: modelConfig.maxTokens || (modelConfig.info.maxTokens as number), + temperature: modelConfig.temperature ?? (this.options.modelTemperature as number), + ...(thinkingEnabled ? {} : { topP: 0.1 }), // Only set topP when thinking is NOT enabled } // For completePrompt, use a unique conversation ID based on the prompt @@ -722,9 +866,24 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH return model } - override getModel(): { id: BedrockModelId | string; info: ModelInfo } { + override getModel(): { + id: BedrockModelId | string + info: ModelInfo + maxTokens?: number + temperature?: number + reasoning?: any + reasoningBudget?: number + } { if (this.costModelConfig?.id?.trim().length > 0) { - return this.costModelConfig + // Get model params for cost model config + const params = getModelParams({ + format: "anthropic", + modelId: this.costModelConfig.id, + model: this.costModelConfig.info, + settings: this.options, + defaultTemperature: BEDROCK_DEFAULT_TEMPERATURE, + }) + return { ...this.costModelConfig, ...params } } let modelConfig = undefined @@ -752,8 +911,24 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH } } + // Get model params including reasoning configuration + const params = getModelParams({ + format: "anthropic", + modelId: modelConfig.id, + model: modelConfig.info, + settings: this.options, + defaultTemperature: BEDROCK_DEFAULT_TEMPERATURE, + }) + // Don't override maxTokens/contextWindow here; handled in getModelById (and includes user overrides) - return modelConfig as { id: BedrockModelId | string; info: ModelInfo } + return { ...modelConfig, ...params } as { + id: BedrockModelId | string + info: ModelInfo + maxTokens?: number + temperature?: number + reasoning?: any + reasoningBudget?: number + } } /************************************************************************************ @@ -905,10 +1080,33 @@ Suggestions: messageTemplate: `Invalid ARN format. ARN should follow the pattern: arn:aws:bedrock:region:account-id:resource-type/resource-name`, logLevel: "error", }, + VALIDATION_ERROR: { + patterns: [ + "input tag", + "does not match any of the expected tags", + "field required", + "validation", + "invalid parameter", + ], + messageTemplate: `Parameter validation error: {errorMessage} + +This error indicates that the request parameters don't match AWS Bedrock's expected format. + +Common causes: +1. Extended thinking parameter format is incorrect +2. Model-specific parameters are not supported by this model +3. API parameter structure has changed + +Please check: +- Model supports the requested features (extended thinking, etc.) +- Parameter format matches AWS Bedrock specification +- Model ID is correct for the requested features`, + logLevel: "error", + }, // Default/generic error GENERIC: { patterns: [], // Empty patterns array means this is the default - messageTemplate: `Unknown Error`, + messageTemplate: `Unknown Error: {errorMessage}`, logLevel: "error", }, } diff --git a/webview-ui/src/components/settings/ApiOptions.tsx b/webview-ui/src/components/settings/ApiOptions.tsx index 905f34a860..3d9e770ea1 100644 --- a/webview-ui/src/components/settings/ApiOptions.tsx +++ b/webview-ui/src/components/settings/ApiOptions.tsx @@ -465,12 +465,14 @@ const ApiOptions = ({ )} - + {selectedProviderModels.length > 0 && ( + + )} {!fromWelcomeView && ( <> diff --git a/webview-ui/src/components/settings/ThinkingBudget.tsx b/webview-ui/src/components/settings/ThinkingBudget.tsx index 456e0be17a..0adb62f2a0 100644 --- a/webview-ui/src/components/settings/ThinkingBudget.tsx +++ b/webview-ui/src/components/settings/ThinkingBudget.tsx @@ -65,7 +65,11 @@ export const ThinkingBudget = ({ apiConfiguration, setApiConfigurationField, mod
setApiConfigurationField("modelMaxTokens", value)} diff --git a/webview-ui/src/components/settings/providers/Bedrock.tsx b/webview-ui/src/components/settings/providers/Bedrock.tsx index eb8ca94258..a0ebafd88e 100644 --- a/webview-ui/src/components/settings/providers/Bedrock.tsx +++ b/webview-ui/src/components/settings/providers/Bedrock.tsx @@ -108,24 +108,24 @@ export const Bedrock = ({ apiConfiguration, setApiConfigurationField, selectedMo {t("settings:providers.awsCrossRegion")} {selectedModelInfo?.supportsPromptCache && ( - -
- {t("settings:providers.enablePromptCaching")} - + <> + +
+ {t("settings:providers.enablePromptCaching")} + +
+ +
+ {t("settings:providers.cacheUsageNote")}
- + )} -
-
- {t("settings:providers.cacheUsageNote")} -
-
{ From 85fd86e6751f24ba78a702d11982b518688c20d0 Mon Sep 17 00:00:00 2001 From: Matt Rubens Date: Thu, 12 Jun 2025 12:51:34 -0400 Subject: [PATCH 13/33] Revert "Always focus the panel when clicked to ensure menu buttons are visible" (#4592) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Revert "Always focus the panel when clicked to ensure menu buttons are visibl…" This reverts commit 1b1e5a20f1ce77020d266ca47697df1386e2a918. --- .changeset/khaki-clocks-float.md | 5 --- packages/telemetry/src/TelemetryService.ts | 2 +- packages/types/src/vscode.ts | 1 - src/activate/registerCommands.ts | 18 ++++------ src/core/webview/webviewMessageHandler.ts | 5 --- src/shared/WebviewMessage.ts | 1 - src/utils/focusPanel.ts | 27 --------------- webview-ui/src/App.tsx | 8 ----- webview-ui/src/components/ui/hooks/index.ts | 1 - .../ui/hooks/useNonInteractiveClick.ts | 34 ------------------- 10 files changed, 8 insertions(+), 94 deletions(-) delete mode 100644 .changeset/khaki-clocks-float.md delete mode 100644 src/utils/focusPanel.ts delete mode 100644 webview-ui/src/components/ui/hooks/useNonInteractiveClick.ts diff --git a/.changeset/khaki-clocks-float.md b/.changeset/khaki-clocks-float.md deleted file mode 100644 index 5e483d9788..0000000000 --- a/.changeset/khaki-clocks-float.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"roo-cline": patch ---- - -Always focus the panel when clicked to ensure menu buttons are available diff --git a/packages/telemetry/src/TelemetryService.ts b/packages/telemetry/src/TelemetryService.ts index 728809f8bd..956f49313a 100644 --- a/packages/telemetry/src/TelemetryService.ts +++ b/packages/telemetry/src/TelemetryService.ts @@ -173,7 +173,7 @@ export class TelemetryService { itemType, itemName, target, - ...(properties || {}), + ... (properties || {}), }) } diff --git a/packages/types/src/vscode.ts b/packages/types/src/vscode.ts index 90d6b72665..cc164aadbe 100644 --- a/packages/types/src/vscode.ts +++ b/packages/types/src/vscode.ts @@ -51,7 +51,6 @@ export const commandIds = [ "focusInput", "acceptInput", - "focusPanel", ] as const export type CommandId = (typeof commandIds)[number] diff --git a/src/activate/registerCommands.ts b/src/activate/registerCommands.ts index fc30878c7b..3ec5d151e1 100644 --- a/src/activate/registerCommands.ts +++ b/src/activate/registerCommands.ts @@ -8,7 +8,6 @@ import { Package } from "../shared/package" import { getCommand } from "../utils/commands" import { ClineProvider } from "../core/webview/ClineProvider" import { ContextProxy } from "../core/config/ContextProxy" -import { focusPanel } from "../utils/focusPanel" import { registerHumanRelayCallback, unregisterHumanRelayCallback, handleHumanRelayResponse } from "./humanRelay" import { handleNewTask } from "./handleTask" @@ -173,23 +172,20 @@ const getCommandsMap = ({ context, outputChannel, provider }: RegisterCommandOpt }, focusInput: async () => { try { - await focusPanel(tabPanel, sidebarPanel) + const panel = getPanel() - // Send focus input message only for sidebar panels - if (sidebarPanel && getPanel() === sidebarPanel) { + if (!panel) { + await vscode.commands.executeCommand(`workbench.view.extension.${Package.name}-ActivityBar`) + } else if (panel === tabPanel) { + panel.reveal(vscode.ViewColumn.Active, false) + } else if (panel === sidebarPanel) { + await vscode.commands.executeCommand(`${ClineProvider.sideBarId}.focus`) provider.postMessageToWebview({ type: "action", action: "focusInput" }) } } catch (error) { outputChannel.appendLine(`Error focusing input: ${error}`) } }, - focusPanel: async () => { - try { - await focusPanel(tabPanel, sidebarPanel) - } catch (error) { - outputChannel.appendLine(`Error focusing panel: ${error}`) - } - }, acceptInput: () => { const visibleProvider = getVisibleProviderOrLog(outputChannel) diff --git a/src/core/webview/webviewMessageHandler.ts b/src/core/webview/webviewMessageHandler.ts index 08f8e866c1..6568b4aaee 100644 --- a/src/core/webview/webviewMessageHandler.ts +++ b/src/core/webview/webviewMessageHandler.ts @@ -1475,11 +1475,6 @@ export const webviewMessageHandler = async ( } break } - case "focusPanelRequest": { - // Execute the focusPanel command to focus the WebView - await vscode.commands.executeCommand(getCommand("focusPanel")) - break - } case "filterMarketplaceItems": { // Check if marketplace is enabled before making API calls const { experiments } = await provider.getState() diff --git a/src/shared/WebviewMessage.ts b/src/shared/WebviewMessage.ts index a6e847c907..d27b931f10 100644 --- a/src/shared/WebviewMessage.ts +++ b/src/shared/WebviewMessage.ts @@ -150,7 +150,6 @@ export interface WebviewMessage { | "clearIndexData" | "indexingStatusUpdate" | "indexCleared" - | "focusPanelRequest" | "codebaseIndexConfig" | "setHistoryPreviewCollapsed" | "openExternal" diff --git a/src/utils/focusPanel.ts b/src/utils/focusPanel.ts deleted file mode 100644 index c57707047b..0000000000 --- a/src/utils/focusPanel.ts +++ /dev/null @@ -1,27 +0,0 @@ -import * as vscode from "vscode" -import { Package } from "../shared/package" -import { ClineProvider } from "../core/webview/ClineProvider" - -/** - * Focus the active panel (either tab or sidebar) - * @param tabPanel - The tab panel reference - * @param sidebarPanel - The sidebar panel reference - * @returns Promise that resolves when focus is complete - */ -export async function focusPanel( - tabPanel: vscode.WebviewPanel | undefined, - sidebarPanel: vscode.WebviewView | undefined, -): Promise { - const panel = tabPanel || sidebarPanel - - if (!panel) { - // If no panel is open, open the sidebar - await vscode.commands.executeCommand(`workbench.view.extension.${Package.name}-ActivityBar`) - } else if (panel === tabPanel) { - // For tab panels, use reveal to focus - panel.reveal(vscode.ViewColumn.Active, false) - } else if (panel === sidebarPanel) { - // For sidebar panels, focus the sidebar - await vscode.commands.executeCommand(`${ClineProvider.sideBarId}.focus`) - } -} diff --git a/webview-ui/src/App.tsx b/webview-ui/src/App.tsx index be80a436bd..505cb0b6ee 100644 --- a/webview-ui/src/App.tsx +++ b/webview-ui/src/App.tsx @@ -18,7 +18,6 @@ import { MarketplaceView } from "./components/marketplace/MarketplaceView" import ModesView from "./components/modes/ModesView" import { HumanRelayDialog } from "./components/human-relay/HumanRelayDialog" import { AccountView } from "./components/account/AccountView" -import { useAddNonInteractiveClickListener } from "./components/ui/hooks/useNonInteractiveClick" type Tab = "settings" | "history" | "mcp" | "modes" | "chat" | "marketplace" | "account" @@ -136,13 +135,6 @@ const App = () => { // Tell the extension that we are ready to receive messages. useEffect(() => vscode.postMessage({ type: "webviewDidLaunch" }), []) - // Focus the WebView when non-interactive content is clicked - useAddNonInteractiveClickListener( - useCallback(() => { - vscode.postMessage({ type: "focusPanelRequest" }) - }, []), - ) - if (!didHydrateState) { return null } diff --git a/webview-ui/src/components/ui/hooks/index.ts b/webview-ui/src/components/ui/hooks/index.ts index a20daa7f03..46aff4f28d 100644 --- a/webview-ui/src/components/ui/hooks/index.ts +++ b/webview-ui/src/components/ui/hooks/index.ts @@ -1,3 +1,2 @@ export * from "./useClipboard" export * from "./useRooPortal" -export * from "./useNonInteractiveClick" diff --git a/webview-ui/src/components/ui/hooks/useNonInteractiveClick.ts b/webview-ui/src/components/ui/hooks/useNonInteractiveClick.ts deleted file mode 100644 index 13809ff0c7..0000000000 --- a/webview-ui/src/components/ui/hooks/useNonInteractiveClick.ts +++ /dev/null @@ -1,34 +0,0 @@ -import { useEffect } from "react" - -/** - * Hook that listens for clicks on non-interactive elements and calls the provided handler. - * - * Interactive elements (inputs, textareas, selects, contentEditable) are excluded - * to avoid disrupting user typing or form interactions. - * - * @param handler - Function to call when a non-interactive element is clicked - */ -export function useAddNonInteractiveClickListener(handler: () => void) { - useEffect(() => { - const handleContentClick = (e: MouseEvent) => { - const target = e.target as HTMLElement - - // Don't trigger for input elements to avoid disrupting typing - if ( - target.tagName !== "INPUT" && - target.tagName !== "TEXTAREA" && - target.tagName !== "SELECT" && - !target.isContentEditable - ) { - handler() - } - } - - // Add listener to the document body to handle all clicks - document.body.addEventListener("click", handleContentClick) - - return () => { - document.body.removeEventListener("click", handleContentClick) - } - }, [handler]) -} From dfcf8fe76031613eeecd408941f10d9530a3d261 Mon Sep 17 00:00:00 2001 From: axb Date: Fri, 13 Jun 2025 01:06:27 +0800 Subject: [PATCH 14/33] add mermaid buttons (#4547) * add mermaid buttons * feat: Add Modal, TabButton, and ZoomControls components * feat: Add error handling messages for image operations and file opening * mermaid: Add drag functionality and support contious zooming * add active color for tabbutton * refactor zoom controls * refactor: Remove unused svgToPng prop and simplify handleCopy function * Move zoom to constants and increase max zoom * feat: add save image functionality and refactor image handling * feat: add translations --------- Co-authored-by: Daniel Riccio Co-authored-by: Matt Rubens --- src/core/webview/webviewMessageHandler.ts | 8 +- src/i18n/locales/ca/common.json | 9 +- src/i18n/locales/de/common.json | 9 +- src/i18n/locales/en/common.json | 9 +- src/i18n/locales/es/common.json | 9 +- src/i18n/locales/fr/common.json | 9 +- src/i18n/locales/hi/common.json | 11 +- src/i18n/locales/it/common.json | 9 +- src/i18n/locales/ja/common.json | 9 +- src/i18n/locales/ko/common.json | 9 +- src/i18n/locales/nl/common.json | 9 +- src/i18n/locales/pl/common.json | 9 +- src/i18n/locales/pt-BR/common.json | 9 +- src/i18n/locales/ru/common.json | 9 +- src/i18n/locales/tr/common.json | 9 +- src/i18n/locales/vi/common.json | 9 +- src/i18n/locales/zh-CN/common.json | 16 +- src/i18n/locales/zh-TW/common.json | 9 +- src/integrations/misc/image-handler.ts | 92 +++++++ src/integrations/misc/open-file.ts | 22 +- src/shared/WebviewMessage.ts | 2 + .../src/components/common/IconButton.tsx | 45 ++++ .../common/MermaidActionButtons.tsx | 80 ++++++ .../src/components/common/MermaidBlock.tsx | 13 +- .../src/components/common/MermaidButton.tsx | 246 ++++++++++++++++++ webview-ui/src/components/common/Modal.tsx | 20 ++ .../src/components/common/TabButton.tsx | 26 ++ .../src/components/common/ZoomControls.tsx | 91 +++++++ webview-ui/src/i18n/locales/ca/common.json | 36 ++- webview-ui/src/i18n/locales/de/common.json | 36 ++- webview-ui/src/i18n/locales/en/common.json | 36 ++- webview-ui/src/i18n/locales/es/common.json | 36 ++- webview-ui/src/i18n/locales/fr/common.json | 36 ++- webview-ui/src/i18n/locales/hi/common.json | 36 ++- webview-ui/src/i18n/locales/it/common.json | 36 ++- webview-ui/src/i18n/locales/ja/common.json | 36 ++- webview-ui/src/i18n/locales/ko/common.json | 36 ++- webview-ui/src/i18n/locales/nl/common.json | 36 ++- webview-ui/src/i18n/locales/pl/common.json | 36 ++- webview-ui/src/i18n/locales/pt-BR/common.json | 36 ++- webview-ui/src/i18n/locales/ru/common.json | 36 ++- webview-ui/src/i18n/locales/tr/common.json | 36 ++- webview-ui/src/i18n/locales/vi/common.json | 36 ++- webview-ui/src/i18n/locales/zh-CN/common.json | 36 ++- webview-ui/src/i18n/locales/zh-TW/common.json | 36 ++- 45 files changed, 1360 insertions(+), 59 deletions(-) create mode 100644 src/integrations/misc/image-handler.ts create mode 100644 webview-ui/src/components/common/IconButton.tsx create mode 100644 webview-ui/src/components/common/MermaidActionButtons.tsx create mode 100644 webview-ui/src/components/common/MermaidButton.tsx create mode 100644 webview-ui/src/components/common/Modal.tsx create mode 100644 webview-ui/src/components/common/TabButton.tsx create mode 100644 webview-ui/src/components/common/ZoomControls.tsx diff --git a/src/core/webview/webviewMessageHandler.ts b/src/core/webview/webviewMessageHandler.ts index 6568b4aaee..a60c5fea41 100644 --- a/src/core/webview/webviewMessageHandler.ts +++ b/src/core/webview/webviewMessageHandler.ts @@ -17,7 +17,8 @@ import { checkoutDiffPayloadSchema, checkoutRestorePayloadSchema, WebviewMessage import { checkExistKey } from "../../shared/checkExistApiConfig" import { experimentDefault } from "../../shared/experiments" import { Terminal } from "../../integrations/terminal/Terminal" -import { openFile, openImage } from "../../integrations/misc/open-file" +import { openFile } from "../../integrations/misc/open-file" +import { openImage, saveImage } from "../../integrations/misc/image-handler" import { selectImages } from "../../integrations/misc/process-images" import { getTheme } from "../../integrations/theme/getTheme" import { discoverChromeHostUrl, tryChromeHostUrl } from "../../services/browser/browserDiscovery" @@ -423,7 +424,10 @@ export const webviewMessageHandler = async ( provider.postMessageToWebview({ type: "vsCodeLmModels", vsCodeLmModels }) break case "openImage": - openImage(message.text!) + openImage(message.text!, { values: message.values }) + break + case "saveImage": + saveImage(message.dataUri!) break case "openFile": openFile(message.text!, message.values as { create?: boolean; content?: string; line?: number }) diff --git a/src/i18n/locales/ca/common.json b/src/i18n/locales/ca/common.json index 15c0692c58..31b9668a86 100644 --- a/src/i18n/locales/ca/common.json +++ b/src/i18n/locales/ca/common.json @@ -28,6 +28,11 @@ }, "errors": { "invalid_data_uri": "Format d'URI de dades no vàlid", + "error_copying_image": "Error copiant la imatge: {{errorMessage}}", + "error_saving_image": "Error desant la imatge: {{errorMessage}}", + "error_opening_image": "Error obrint la imatge: {{error}}", + "could_not_open_file": "No s'ha pogut obrir el fitxer: {{errorMessage}}", + "could_not_open_file_generic": "No s'ha pogut obrir el fitxer!", "checkpoint_timeout": "S'ha esgotat el temps en intentar restaurar el punt de control.", "checkpoint_failed": "Ha fallat la restauració del punt de control.", "no_workspace": "Si us plau, obre primer una carpeta de projecte", @@ -71,7 +76,9 @@ "custom_storage_path_set": "Ruta d'emmagatzematge personalitzada establerta: {{path}}", "default_storage_path": "S'ha reprès l'ús de la ruta d'emmagatzematge predeterminada", "settings_imported": "Configuració importada correctament.", - "share_link_copied": "Enllaç de compartició copiat al portapapers" + "share_link_copied": "Enllaç de compartició copiat al portapapers", + "image_copied_to_clipboard": "URI de dades de la imatge copiada al portapapers", + "image_saved": "Imatge desada a {{path}}" }, "answers": { "yes": "Sí", diff --git a/src/i18n/locales/de/common.json b/src/i18n/locales/de/common.json index d9a4727dbe..ab0cd61ac9 100644 --- a/src/i18n/locales/de/common.json +++ b/src/i18n/locales/de/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "Ungültiges Daten-URI-Format", + "error_copying_image": "Fehler beim Kopieren des Bildes: {{errorMessage}}", + "error_saving_image": "Fehler beim Speichern des Bildes: {{errorMessage}}", + "error_opening_image": "Fehler beim Öffnen des Bildes: {{error}}", + "could_not_open_file": "Datei konnte nicht geöffnet werden: {{errorMessage}}", + "could_not_open_file_generic": "Datei konnte nicht geöffnet werden!", "checkpoint_timeout": "Zeitüberschreitung beim Versuch, den Checkpoint wiederherzustellen.", "checkpoint_failed": "Fehler beim Wiederherstellen des Checkpoints.", "no_workspace": "Bitte öffne zuerst einen Projektordner", @@ -67,7 +72,9 @@ "custom_storage_path_set": "Benutzerdefinierter Speicherpfad festgelegt: {{path}}", "default_storage_path": "Auf Standardspeicherpfad zurückgesetzt", "settings_imported": "Einstellungen erfolgreich importiert.", - "share_link_copied": "Share-Link in die Zwischenablage kopiert" + "share_link_copied": "Share-Link in die Zwischenablage kopiert", + "image_copied_to_clipboard": "Bild-Daten-URI in die Zwischenablage kopiert", + "image_saved": "Bild gespeichert unter {{path}}" }, "answers": { "yes": "Ja", diff --git a/src/i18n/locales/en/common.json b/src/i18n/locales/en/common.json index b3a47e60ad..7d359e6586 100644 --- a/src/i18n/locales/en/common.json +++ b/src/i18n/locales/en/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "Invalid data URI format", + "error_copying_image": "Error copying image: {{errorMessage}}", + "error_opening_image": "Error opening image: {{error}}", + "error_saving_image": "Error saving image: {{errorMessage}}", + "could_not_open_file": "Could not open file: {{errorMessage}}", + "could_not_open_file_generic": "Could not open file!", "checkpoint_timeout": "Timed out when attempting to restore checkpoint.", "checkpoint_failed": "Failed to restore checkpoint.", "no_workspace": "Please open a project folder first", @@ -67,7 +72,9 @@ "custom_storage_path_set": "Custom storage path set: {{path}}", "default_storage_path": "Reverted to using default storage path", "settings_imported": "Settings imported successfully.", - "share_link_copied": "Share link copied to clipboard" + "share_link_copied": "Share link copied to clipboard", + "image_copied_to_clipboard": "Image data URI copied to clipboard", + "image_saved": "Image saved to {{path}}" }, "answers": { "yes": "Yes", diff --git a/src/i18n/locales/es/common.json b/src/i18n/locales/es/common.json index b374b8559e..3fb8602131 100644 --- a/src/i18n/locales/es/common.json +++ b/src/i18n/locales/es/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "Formato de URI de datos no válido", + "error_copying_image": "Error copiando la imagen: {{errorMessage}}", + "error_saving_image": "Error guardando la imagen: {{errorMessage}}", + "error_opening_image": "Error abriendo la imagen: {{error}}", + "could_not_open_file": "No se pudo abrir el archivo: {{errorMessage}}", + "could_not_open_file_generic": "¡No se pudo abrir el archivo!", "checkpoint_timeout": "Se agotó el tiempo al intentar restaurar el punto de control.", "checkpoint_failed": "Error al restaurar el punto de control.", "no_workspace": "Por favor, abre primero una carpeta de proyecto", @@ -67,7 +72,9 @@ "custom_storage_path_set": "Ruta de almacenamiento personalizada establecida: {{path}}", "default_storage_path": "Se ha vuelto a usar la ruta de almacenamiento predeterminada", "settings_imported": "Configuración importada correctamente.", - "share_link_copied": "Enlace de compartir copiado al portapapeles" + "share_link_copied": "Enlace de compartir copiado al portapapeles", + "image_copied_to_clipboard": "URI de datos de imagen copiada al portapapeles", + "image_saved": "Imagen guardada en {{path}}" }, "answers": { "yes": "Sí", diff --git a/src/i18n/locales/fr/common.json b/src/i18n/locales/fr/common.json index 77b1ea9786..70f22f4f9f 100644 --- a/src/i18n/locales/fr/common.json +++ b/src/i18n/locales/fr/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "Format d'URI de données invalide", + "error_copying_image": "Erreur lors de la copie de l'image : {{errorMessage}}", + "error_saving_image": "Erreur lors de l'enregistrement de l'image : {{errorMessage}}", + "error_opening_image": "Erreur lors de l'ouverture de l'image : {{error}}", + "could_not_open_file": "Impossible d'ouvrir le fichier : {{errorMessage}}", + "could_not_open_file_generic": "Impossible d'ouvrir le fichier !", "checkpoint_timeout": "Expiration du délai lors de la tentative de rétablissement du checkpoint.", "checkpoint_failed": "Échec du rétablissement du checkpoint.", "no_workspace": "Veuillez d'abord ouvrir un espace de travail", @@ -67,7 +72,9 @@ "custom_storage_path_set": "Chemin de stockage personnalisé défini : {{path}}", "default_storage_path": "Retour au chemin de stockage par défaut", "settings_imported": "Paramètres importés avec succès.", - "share_link_copied": "Lien de partage copié dans le presse-papiers" + "share_link_copied": "Lien de partage copié dans le presse-papiers", + "image_copied_to_clipboard": "URI de données d'image copiée dans le presse-papiers", + "image_saved": "Image enregistrée dans {{path}}" }, "answers": { "yes": "Oui", diff --git a/src/i18n/locales/hi/common.json b/src/i18n/locales/hi/common.json index 635eeea900..7b97e41ffc 100644 --- a/src/i18n/locales/hi/common.json +++ b/src/i18n/locales/hi/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "अमान्य डेटा URI फॉर्मेट", + "error_copying_image": "छवि कॉपी करने में त्रुटि: {{errorMessage}}", + "error_saving_image": "छवि सहेजने में त्रुटि: {{errorMessage}}", + "error_opening_image": "छवि खोलने में त्रुटि: {{error}}", + "could_not_open_file": "फ़ाइल नहीं खोली जा सकी: {{errorMessage}}", + "could_not_open_file_generic": "फ़ाइल नहीं खोली जा सकी!", "checkpoint_timeout": "चेकपॉइंट को पुनर्स्थापित करने का प्रयास करते समय टाइमआउट हो गया।", "checkpoint_failed": "चेकपॉइंट पुनर्स्थापित करने में विफल।", "no_workspace": "कृपया पहले प्रोजेक्ट फ़ोल्डर खोलें", @@ -66,8 +71,10 @@ "history_cleanup": "इतिहास से गायब फाइलों वाले {{count}} टास्क साफ किए गए।", "custom_storage_path_set": "कस्टम स्टोरेज पाथ सेट किया गया: {{path}}", "default_storage_path": "डिफ़ॉल्ट स्टोरेज पाथ का उपयोग पुनः शुरू किया गया", - "settings_imported": "सेटिंग्स सफलतापूर्वक इम्पोर्ट की गईं.", - "share_link_copied": "साझा लिंक क्लिपबोर्ड पर कॉपी किया गया" + "settings_imported": "सेटिंग्स सफलतापूर्वक इम्पोर्ट की गईं।", + "share_link_copied": "साझा लिंक क्लिपबोर्ड पर कॉपी किया गया", + "image_copied_to_clipboard": "छवि डेटा URI क्लिपबोर्ड में कॉपी की गई", + "image_saved": "छवि {{path}} में सहेजी गई" }, "answers": { "yes": "हां", diff --git a/src/i18n/locales/it/common.json b/src/i18n/locales/it/common.json index 44120ca0e9..21946d69e5 100644 --- a/src/i18n/locales/it/common.json +++ b/src/i18n/locales/it/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "Formato URI dati non valido", + "error_copying_image": "Errore durante la copia dell'immagine: {{errorMessage}}", + "error_saving_image": "Errore durante il salvataggio dell'immagine: {{errorMessage}}", + "error_opening_image": "Errore durante l'apertura dell'immagine: {{error}}", + "could_not_open_file": "Impossibile aprire il file: {{errorMessage}}", + "could_not_open_file_generic": "Impossibile aprire il file!", "checkpoint_timeout": "Timeout durante il tentativo di ripristinare il checkpoint.", "checkpoint_failed": "Impossibile ripristinare il checkpoint.", "no_workspace": "Per favore, apri prima una cartella di progetto", @@ -67,7 +72,9 @@ "custom_storage_path_set": "Percorso di archiviazione personalizzato impostato: {{path}}", "default_storage_path": "Tornato al percorso di archiviazione predefinito", "settings_imported": "Impostazioni importate con successo.", - "share_link_copied": "Link di condivisione copiato negli appunti" + "share_link_copied": "Link di condivisione copiato negli appunti", + "image_copied_to_clipboard": "URI dati dell'immagine copiato negli appunti", + "image_saved": "Immagine salvata in {{path}}" }, "answers": { "yes": "Sì", diff --git a/src/i18n/locales/ja/common.json b/src/i18n/locales/ja/common.json index 3ab1bbf110..2cf2d50f29 100644 --- a/src/i18n/locales/ja/common.json +++ b/src/i18n/locales/ja/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "データURIフォーマットが無効です", + "error_copying_image": "画像のコピー中にエラーが発生しました：{{errorMessage}}", + "error_saving_image": "画像の保存中にエラーが発生しました：{{errorMessage}}", + "error_opening_image": "画像を開く際にエラーが発生しました：{{error}}", + "could_not_open_file": "ファイルを開けませんでした：{{errorMessage}}", + "could_not_open_file_generic": "ファイルを開けませんでした！", "checkpoint_timeout": "チェックポイントの復元を試みる際にタイムアウトしました。", "checkpoint_failed": "チェックポイントの復元に失敗しました。", "no_workspace": "まずプロジェクトフォルダを開いてください", @@ -67,7 +72,9 @@ "custom_storage_path_set": "カスタムストレージパスが設定されました：{{path}}", "default_storage_path": "デフォルトのストレージパスに戻りました", "settings_imported": "設定が正常にインポートされました。", - "share_link_copied": "共有リンクがクリップボードにコピーされました" + "share_link_copied": "共有リンクがクリップボードにコピーされました", + "image_copied_to_clipboard": "画像データURIがクリップボードにコピーされました", + "image_saved": "画像を{{path}}に保存しました" }, "answers": { "yes": "はい", diff --git a/src/i18n/locales/ko/common.json b/src/i18n/locales/ko/common.json index e0b0589743..52264fcdd5 100644 --- a/src/i18n/locales/ko/common.json +++ b/src/i18n/locales/ko/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "잘못된 데이터 URI 형식", + "error_copying_image": "이미지 복사 중 오류 발생: {{errorMessage}}", + "error_saving_image": "이미지 저장 중 오류 발생: {{errorMessage}}", + "error_opening_image": "이미지 열기 중 오류 발생: {{error}}", + "could_not_open_file": "파일을 열 수 없습니다: {{errorMessage}}", + "could_not_open_file_generic": "파일을 열 수 없습니다!", "checkpoint_timeout": "체크포인트 복원을 시도하는 중 시간 초과되었습니다.", "checkpoint_failed": "체크포인트 복원에 실패했습니다.", "no_workspace": "먼저 프로젝트 폴더를 열어주세요", @@ -67,7 +72,9 @@ "custom_storage_path_set": "사용자 지정 저장 경로 설정됨: {{path}}", "default_storage_path": "기본 저장 경로로 되돌아갔습니다", "settings_imported": "설정이 성공적으로 가져와졌습니다.", - "share_link_copied": "공유 링크가 클립보드에 복사되었습니다" + "share_link_copied": "공유 링크가 클립보드에 복사되었습니다", + "image_copied_to_clipboard": "이미지 데이터 URI가 클립보드에 복사되었습니다", + "image_saved": "이미지가 {{path}}에 저장되었습니다" }, "answers": { "yes": "예", diff --git a/src/i18n/locales/nl/common.json b/src/i18n/locales/nl/common.json index eb7d6f2bd4..26a856c15f 100644 --- a/src/i18n/locales/nl/common.json +++ b/src/i18n/locales/nl/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "Ongeldig data-URI-formaat", + "error_copying_image": "Fout bij kopiëren van afbeelding: {{errorMessage}}", + "error_saving_image": "Fout bij opslaan van afbeelding: {{errorMessage}}", + "error_opening_image": "Fout bij openen van afbeelding: {{error}}", + "could_not_open_file": "Kon bestand niet openen: {{errorMessage}}", + "could_not_open_file_generic": "Kon bestand niet openen!", "checkpoint_timeout": "Time-out bij het herstellen van checkpoint.", "checkpoint_failed": "Herstellen van checkpoint mislukt.", "no_workspace": "Open eerst een projectmap", @@ -67,7 +72,9 @@ "custom_storage_path_set": "Aangepast opslagpad ingesteld: {{path}}", "default_storage_path": "Terug naar standaard opslagpad", "settings_imported": "Instellingen succesvol geïmporteerd.", - "share_link_copied": "Deellink gekopieerd naar klembord" + "share_link_copied": "Deellink gekopieerd naar klembord", + "image_copied_to_clipboard": "Afbeelding data-URI gekopieerd naar klembord", + "image_saved": "Afbeelding opgeslagen naar {{path}}" }, "answers": { "yes": "Ja", diff --git a/src/i18n/locales/pl/common.json b/src/i18n/locales/pl/common.json index 19aae381fe..1091b643e2 100644 --- a/src/i18n/locales/pl/common.json +++ b/src/i18n/locales/pl/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "Nieprawidłowy format URI danych", + "error_copying_image": "Błąd kopiowania obrazu: {{errorMessage}}", + "error_saving_image": "Błąd zapisywania obrazu: {{errorMessage}}", + "error_opening_image": "Błąd otwierania obrazu: {{error}}", + "could_not_open_file": "Nie można otworzyć pliku: {{errorMessage}}", + "could_not_open_file_generic": "Nie można otworzyć pliku!", "checkpoint_timeout": "Upłynął limit czasu podczas próby przywrócenia punktu kontrolnego.", "checkpoint_failed": "Nie udało się przywrócić punktu kontrolnego.", "no_workspace": "Najpierw otwórz folder projektu", @@ -67,7 +72,9 @@ "custom_storage_path_set": "Ustawiono niestandardową ścieżkę przechowywania: {{path}}", "default_storage_path": "Wznowiono używanie domyślnej ścieżki przechowywania", "settings_imported": "Ustawienia zaimportowane pomyślnie.", - "share_link_copied": "Link udostępniania skopiowany do schowka" + "share_link_copied": "Link udostępniania skopiowany do schowka", + "image_copied_to_clipboard": "URI danych obrazu skopiowane do schowka", + "image_saved": "Obraz zapisany w {{path}}" }, "answers": { "yes": "Tak", diff --git a/src/i18n/locales/pt-BR/common.json b/src/i18n/locales/pt-BR/common.json index 30c0aa3cbe..6eb8fc7708 100644 --- a/src/i18n/locales/pt-BR/common.json +++ b/src/i18n/locales/pt-BR/common.json @@ -28,6 +28,11 @@ }, "errors": { "invalid_data_uri": "Formato de URI de dados inválido", + "error_copying_image": "Erro ao copiar imagem: {{errorMessage}}", + "error_saving_image": "Erro ao salvar imagem: {{errorMessage}}", + "error_opening_image": "Erro ao abrir imagem: {{error}}", + "could_not_open_file": "Não foi possível abrir o arquivo: {{errorMessage}}", + "could_not_open_file_generic": "Não foi possível abrir o arquivo!", "checkpoint_timeout": "Tempo esgotado ao tentar restaurar o ponto de verificação.", "checkpoint_failed": "Falha ao restaurar o ponto de verificação.", "no_workspace": "Por favor, abra primeiro uma pasta de projeto", @@ -71,7 +76,9 @@ "custom_storage_path_set": "Caminho de armazenamento personalizado definido: {{path}}", "default_storage_path": "Retornado ao caminho de armazenamento padrão", "settings_imported": "Configurações importadas com sucesso.", - "share_link_copied": "Link de compartilhamento copiado para a área de transferência" + "share_link_copied": "Link de compartilhamento copiado para a área de transferência", + "image_copied_to_clipboard": "URI de dados da imagem copiada para a área de transferência", + "image_saved": "Imagem salva em {{path}}" }, "answers": { "yes": "Sim", diff --git a/src/i18n/locales/ru/common.json b/src/i18n/locales/ru/common.json index b773baa05e..a8e0479da1 100644 --- a/src/i18n/locales/ru/common.json +++ b/src/i18n/locales/ru/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "Неверный формат URI данных", + "error_copying_image": "Ошибка копирования изображения: {{errorMessage}}", + "error_saving_image": "Ошибка сохранения изображения: {{errorMessage}}", + "error_opening_image": "Ошибка открытия изображения: {{error}}", + "could_not_open_file": "Не удалось открыть файл: {{errorMessage}}", + "could_not_open_file_generic": "Не удалось открыть файл!", "checkpoint_timeout": "Превышено время ожидания при попытке восстановления контрольной точки.", "checkpoint_failed": "Не удалось восстановить контрольную точку.", "no_workspace": "Пожалуйста, сначала откройте папку проекта", @@ -67,7 +72,9 @@ "custom_storage_path_set": "Установлен пользовательский путь хранения: {{path}}", "default_storage_path": "Возвращено использование пути хранения по умолчанию", "settings_imported": "Настройки успешно импортированы.", - "share_link_copied": "Ссылка для совместного использования скопирована в буфер обмена" + "share_link_copied": "Ссылка для совместного использования скопирована в буфер обмена", + "image_copied_to_clipboard": "URI данных изображения скопирован в буфер обмена", + "image_saved": "Изображение сохранено в {{path}}" }, "answers": { "yes": "Да", diff --git a/src/i18n/locales/tr/common.json b/src/i18n/locales/tr/common.json index 21ebea9614..182df50d1c 100644 --- a/src/i18n/locales/tr/common.json +++ b/src/i18n/locales/tr/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "Geçersiz veri URI formatı", + "error_copying_image": "Resim kopyalanırken hata oluştu: {{errorMessage}}", + "error_saving_image": "Resim kaydedilirken hata oluştu: {{errorMessage}}", + "error_opening_image": "Resim açılırken hata oluştu: {{error}}", + "could_not_open_file": "Dosya açılamadı: {{errorMessage}}", + "could_not_open_file_generic": "Dosya açılamadı!", "checkpoint_timeout": "Kontrol noktasını geri yüklemeye çalışırken zaman aşımına uğradı.", "checkpoint_failed": "Kontrol noktası geri yüklenemedi.", "no_workspace": "Lütfen önce bir proje klasörü açın", @@ -67,7 +72,9 @@ "custom_storage_path_set": "Özel depolama yolu ayarlandı: {{path}}", "default_storage_path": "Varsayılan depolama yoluna geri dönüldü", "settings_imported": "Ayarlar başarıyla içe aktarıldı.", - "share_link_copied": "Paylaşım bağlantısı panoya kopyalandı" + "share_link_copied": "Paylaşım bağlantısı panoya kopyalandı", + "image_copied_to_clipboard": "Resim veri URI'si panoya kopyalandı", + "image_saved": "Resim {{path}} konumuna kaydedildi" }, "answers": { "yes": "Evet", diff --git a/src/i18n/locales/vi/common.json b/src/i18n/locales/vi/common.json index e0044927fe..2f32da8f70 100644 --- a/src/i18n/locales/vi/common.json +++ b/src/i18n/locales/vi/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "Định dạng URI dữ liệu không hợp lệ", + "error_copying_image": "Lỗi khi sao chép hình ảnh: {{errorMessage}}", + "error_saving_image": "Lỗi khi lưu hình ảnh: {{errorMessage}}", + "error_opening_image": "Lỗi khi mở hình ảnh: {{error}}", + "could_not_open_file": "Không thể mở tệp: {{errorMessage}}", + "could_not_open_file_generic": "Không thể mở tệp!", "checkpoint_timeout": "Đã hết thời gian khi cố gắng khôi phục điểm kiểm tra.", "checkpoint_failed": "Không thể khôi phục điểm kiểm tra.", "no_workspace": "Vui lòng mở thư mục dự án trước", @@ -67,7 +72,9 @@ "custom_storage_path_set": "Đã thiết lập đường dẫn lưu trữ tùy chỉnh: {{path}}", "default_storage_path": "Đã quay lại sử dụng đường dẫn lưu trữ mặc định", "settings_imported": "Cài đặt đã được nhập thành công.", - "share_link_copied": "Liên kết chia sẻ đã được sao chép vào clipboard" + "share_link_copied": "Liên kết chia sẻ đã được sao chép vào clipboard", + "image_copied_to_clipboard": "URI dữ liệu hình ảnh đã được sao chép vào clipboard", + "image_saved": "Hình ảnh đã được lưu vào {{path}}" }, "answers": { "yes": "Có", diff --git a/src/i18n/locales/zh-CN/common.json b/src/i18n/locales/zh-CN/common.json index 844da028a2..45fd6d9b58 100644 --- a/src/i18n/locales/zh-CN/common.json +++ b/src/i18n/locales/zh-CN/common.json @@ -23,7 +23,17 @@ "this_and_subsequent": "此消息及所有后续消息" }, "errors": { - "invalid_data_uri": "数据URI格式无效", + "invalid_mcp_config": "项目MCP配置格式无效", + "invalid_mcp_settings_format": "MCP设置JSON格式无效。请确保您的设置遵循正确的JSON格式。", + "invalid_mcp_settings_syntax": "MCP设置JSON格式无效。请检查您的设置文件是否有语法错误。", + "invalid_mcp_settings_validation": "MCP设置格式无效：{{errorMessages}}", + "failed_initialize_project_mcp": "初始化项目MCP服务器失败：{{error}}", + "invalid_data_uri": "数据 URI 格式无效", + "error_copying_image": "复制图片时出错：{{errorMessage}}", + "error_saving_image": "保存图片时出错：{{errorMessage}}", + "error_opening_image": "打开图片时出错：{{error}}", + "could_not_open_file": "无法打开文件：{{errorMessage}}", + "could_not_open_file_generic": "无法打开文件！", "checkpoint_timeout": "尝试恢复检查点时超时。", "checkpoint_failed": "恢复检查点失败。", "no_workspace": "请先打开项目文件夹", @@ -67,7 +77,9 @@ "custom_storage_path_set": "自定义存储路径已设置：{{path}}", "default_storage_path": "已恢复使用默认存储路径", "settings_imported": "设置已成功导入。", - "share_link_copied": "分享链接已复制到剪贴板" + "share_link_copied": "分享链接已复制到剪贴板", + "image_copied_to_clipboard": "图片数据 URI 已复制到剪贴板", + "image_saved": "图片已保存到 {{path}}" }, "answers": { "yes": "是", diff --git a/src/i18n/locales/zh-TW/common.json b/src/i18n/locales/zh-TW/common.json index 512acfac32..03e83b183a 100644 --- a/src/i18n/locales/zh-TW/common.json +++ b/src/i18n/locales/zh-TW/common.json @@ -24,6 +24,11 @@ }, "errors": { "invalid_data_uri": "資料 URI 格式無效", + "error_copying_image": "複製圖片時發生錯誤：{{errorMessage}}", + "error_saving_image": "儲存圖片時發生錯誤：{{errorMessage}}", + "error_opening_image": "開啟圖片時發生錯誤：{{error}}", + "could_not_open_file": "無法開啟檔案：{{errorMessage}}", + "could_not_open_file_generic": "無法開啟檔案！", "checkpoint_timeout": "嘗試恢復檢查點時超時。", "checkpoint_failed": "恢復檢查點失敗。", "no_workspace": "請先開啟專案資料夾", @@ -67,7 +72,9 @@ "custom_storage_path_set": "自訂儲存路徑已設定：{{path}}", "default_storage_path": "已恢復使用預設儲存路徑", "settings_imported": "設定已成功匯入。", - "share_link_copied": "分享連結已複製到剪貼簿" + "share_link_copied": "分享連結已複製到剪貼簿", + "image_copied_to_clipboard": "圖片資料 URI 已複製到剪貼簿", + "image_saved": "圖片已儲存至 {{path}}" }, "answers": { "yes": "是", diff --git a/src/integrations/misc/image-handler.ts b/src/integrations/misc/image-handler.ts new file mode 100644 index 0000000000..4cd7585df4 --- /dev/null +++ b/src/integrations/misc/image-handler.ts @@ -0,0 +1,92 @@ +import * as path from "path" +import * as os from "os" +import * as vscode from "vscode" +import { getWorkspacePath } from "../../utils/path" +import { t } from "../../i18n" + +export async function openImage(dataUri: string, options?: { values?: { action?: string } }) { + const matches = dataUri.match(/^data:image\/([a-zA-Z]+);base64,(.+)$/) + if (!matches) { + vscode.window.showErrorMessage(t("common:errors.invalid_data_uri")) + return + } + const [, format, base64Data] = matches + const imageBuffer = Buffer.from(base64Data, "base64") + + // Default behavior: open the image + const tempFilePath = path.join(os.tmpdir(), `temp_image_${Date.now()}.${format}`) + try { + await vscode.workspace.fs.writeFile(vscode.Uri.file(tempFilePath), imageBuffer) + // Check if this is a copy action + if (options?.values?.action === "copy") { + try { + // Read the image file + const imageData = await vscode.workspace.fs.readFile(vscode.Uri.file(tempFilePath)) + + // Convert to base64 for clipboard + const base64Image = Buffer.from(imageData).toString("base64") + const dataUri = `data:image/${format};base64,${base64Image}` + + // Use vscode.env.clipboard to copy the data URI + // Note: VSCode doesn't support copying binary image data directly to clipboard + // So we copy the data URI which can be pasted in many applications + await vscode.env.clipboard.writeText(dataUri) + + vscode.window.showInformationMessage(t("common:info.image_copied_to_clipboard")) + } catch (error) { + const errorMessage = error instanceof Error ? error.message : String(error) + vscode.window.showErrorMessage(t("common:errors.error_copying_image", { errorMessage })) + } finally { + // Clean up temp file + try { + await vscode.workspace.fs.delete(vscode.Uri.file(tempFilePath)) + } catch { + // Ignore cleanup errors + } + } + return + } + await vscode.commands.executeCommand("vscode.open", vscode.Uri.file(tempFilePath)) + } catch (error) { + vscode.window.showErrorMessage(t("common:errors.error_opening_image", { error })) + } +} + +export async function saveImage(dataUri: string) { + const matches = dataUri.match(/^data:image\/([a-zA-Z]+);base64,(.+)$/) + if (!matches) { + vscode.window.showErrorMessage(t("common:errors.invalid_data_uri")) + return + } + const [, format, base64Data] = matches + const imageBuffer = Buffer.from(base64Data, "base64") + + // Get workspace path or fallback to home directory + const workspacePath = getWorkspacePath() + const defaultPath = workspacePath || os.homedir() + const defaultFileName = `mermaid_diagram_${Date.now()}.${format}` + const defaultUri = vscode.Uri.file(path.join(defaultPath, defaultFileName)) + + // Show save dialog + const saveUri = await vscode.window.showSaveDialog({ + filters: { + Images: [format], + "All Files": ["*"], + }, + defaultUri: defaultUri, + }) + + if (!saveUri) { + // User cancelled the save dialog + return + } + + try { + // Write the image to the selected location + await vscode.workspace.fs.writeFile(saveUri, imageBuffer) + vscode.window.showInformationMessage(t("common:info.image_saved", { path: saveUri.fsPath })) + } catch (error) { + const errorMessage = error instanceof Error ? error.message : String(error) + vscode.window.showErrorMessage(t("common:errors.error_saving_image", { errorMessage })) + } +} diff --git a/src/integrations/misc/open-file.ts b/src/integrations/misc/open-file.ts index 9318e23766..f05c10dc96 100644 --- a/src/integrations/misc/open-file.ts +++ b/src/integrations/misc/open-file.ts @@ -2,23 +2,7 @@ import * as path from "path" import * as os from "os" import * as vscode from "vscode" import { arePathsEqual, getWorkspacePath } from "../../utils/path" - -export async function openImage(dataUri: string) { - const matches = dataUri.match(/^data:image\/([a-zA-Z]+);base64,(.+)$/) - if (!matches) { - vscode.window.showErrorMessage("Invalid data URI format") - return - } - const [, format, base64Data] = matches - const imageBuffer = Buffer.from(base64Data, "base64") - const tempFilePath = path.join(os.tmpdir(), `temp_image_${Date.now()}.${format}`) - try { - await vscode.workspace.fs.writeFile(vscode.Uri.file(tempFilePath), imageBuffer) - await vscode.commands.executeCommand("vscode.open", vscode.Uri.file(tempFilePath)) - } catch (error) { - vscode.window.showErrorMessage(`Error opening image: ${error}`) - } -} +import { t } from "../../i18n" interface OpenFileOptions { create?: boolean @@ -151,9 +135,9 @@ export async function openFile(filePath: string, options: OpenFileOptions = {}) }) } catch (error) { if (error instanceof Error) { - vscode.window.showErrorMessage(`Could not open file: ${error.message}`) + vscode.window.showErrorMessage(t("common:errors.could_not_open_file", { errorMessage: error.message })) } else { - vscode.window.showErrorMessage(`Could not open file!`) + vscode.window.showErrorMessage(t("common:errors.could_not_open_file_generic")) } } } diff --git a/src/shared/WebviewMessage.ts b/src/shared/WebviewMessage.ts index d27b931f10..ae93e3ae76 100644 --- a/src/shared/WebviewMessage.ts +++ b/src/shared/WebviewMessage.ts @@ -52,6 +52,7 @@ export interface WebviewMessage { | "requestLmStudioModels" | "requestVsCodeLmModels" | "openImage" + | "saveImage" | "openFile" | "openMention" | "cancelTask" @@ -164,6 +165,7 @@ export interface WebviewMessage { text?: string tab?: "settings" | "history" | "mcp" | "modes" | "chat" | "marketplace" | "account" disabled?: boolean + dataUri?: string askResponse?: ClineAskResponse apiConfiguration?: ProviderSettings images?: string[] diff --git a/webview-ui/src/components/common/IconButton.tsx b/webview-ui/src/components/common/IconButton.tsx new file mode 100644 index 0000000000..70a66ba9f1 --- /dev/null +++ b/webview-ui/src/components/common/IconButton.tsx @@ -0,0 +1,45 @@ +interface IconButtonProps { + icon: string + onClick?: (e: React.MouseEvent) => void + onMouseDown?: (e: React.MouseEvent) => void + onMouseUp?: (e: React.MouseEvent) => void + onMouseLeave?: (e: React.MouseEvent) => void + title?: string + size?: "small" | "medium" + variant?: "default" | "transparent" +} + +export function IconButton({ + icon, + onClick, + onMouseDown, + onMouseUp, + onMouseLeave, + title, + size = "medium", + variant = "default", +}: IconButtonProps) { + const sizeClasses = { + small: "w-6 h-6", + medium: "w-7 h-7", + } + + const variantClasses = { + default: "bg-transparent hover:bg-vscode-toolbar-hoverBackground", + transparent: "bg-transparent hover:bg-vscode-toolbar-hoverBackground", + } + + const handleClick = onClick || ((_event: React.MouseEvent) => {}) + + return ( + + ) +} diff --git a/webview-ui/src/components/common/MermaidActionButtons.tsx b/webview-ui/src/components/common/MermaidActionButtons.tsx new file mode 100644 index 0000000000..46ded57644 --- /dev/null +++ b/webview-ui/src/components/common/MermaidActionButtons.tsx @@ -0,0 +1,80 @@ +import React from "react" +import { useAppTranslation } from "@src/i18n/TranslationContext" +import { IconButton } from "./IconButton" +import { ZoomControls } from "./ZoomControls" + +interface MermaidActionButtonsProps { + onZoom?: (e: React.MouseEvent) => void + onZoomIn?: () => void + onZoomOut?: () => void + onCopy: (e: React.MouseEvent) => void + onSave?: (e: React.MouseEvent) => void + onViewCode: () => void + onClose?: () => void + copyFeedback: boolean + showZoomControls?: boolean + zoomLevel?: number +} + +export const MermaidActionButtons: React.FC = ({ + onZoom, + onZoomIn, + onZoomOut, + onCopy, + onSave, + onViewCode, + onClose, + copyFeedback, + showZoomControls = false, + zoomLevel, +}) => { + const { t } = useAppTranslation() + + if (showZoomControls && onZoomOut && onZoomIn && zoomLevel !== undefined) { + return ( + <> + + { + e.stopPropagation() + onViewCode() + }} + title={t("common:mermaid.buttons.viewCode")} + /> + + + ) + } + + return ( + <> + {onZoom && } + { + e.stopPropagation() + onViewCode() + }} + title={t("common:mermaid.buttons.viewCode")} + /> + + {onSave && } + {onClose && } + + ) +} diff --git a/webview-ui/src/components/common/MermaidBlock.tsx b/webview-ui/src/components/common/MermaidBlock.tsx index c5fc8b30bb..229b957765 100644 --- a/webview-ui/src/components/common/MermaidBlock.tsx +++ b/webview-ui/src/components/common/MermaidBlock.tsx @@ -6,6 +6,7 @@ import { vscode } from "@src/utils/vscode" import { useAppTranslation } from "@src/i18n/TranslationContext" import { useCopyToClipboard } from "@src/utils/clipboard" import CodeBlock from "./CodeBlock" +import { MermaidButton } from "@/components/common/MermaidButton" // Removed previous attempts at static imports for individual diagram types // as the paths were incorrect for Mermaid v11.4.1 and caused errors. @@ -213,7 +214,9 @@ export default function MermaidBlock({ code }: MermaidBlockProps) { )}
) : ( - + + + )} ) @@ -243,10 +246,16 @@ async function svgToPng(svgEl: SVGElement): Promise { const serializer = new XMLSerializer() const svgString = serializer.serializeToString(svgClone) - const svgDataUrl = "data:image/svg+xml;base64," + btoa(decodeURIComponent(encodeURIComponent(svgString))) + + // Create a data URL directly + // First, ensure the SVG string is properly encoded + const encodedSvg = encodeURIComponent(svgString).replace(/'/g, "%27").replace(/"/g, "%22") + + const svgDataUrl = `data:image/svg+xml;charset=utf-8,${encodedSvg}` return new Promise((resolve, reject) => { const img = new Image() + img.onload = () => { const canvas = document.createElement("canvas") canvas.width = editorWidth diff --git a/webview-ui/src/components/common/MermaidButton.tsx b/webview-ui/src/components/common/MermaidButton.tsx new file mode 100644 index 0000000000..57d4c26b0a --- /dev/null +++ b/webview-ui/src/components/common/MermaidButton.tsx @@ -0,0 +1,246 @@ +import { useState, useCallback } from "react" +import { useCopyToClipboard } from "@src/utils/clipboard" +import { useAppTranslation } from "@src/i18n/TranslationContext" +import { vscode } from "@src/utils/vscode" +import { MermaidActionButtons } from "./MermaidActionButtons" +import { Modal } from "./Modal" +import { TabButton } from "./TabButton" +import { IconButton } from "./IconButton" +import { ZoomControls } from "./ZoomControls" + +const MIN_ZOOM = 0.5 +const MAX_ZOOM = 20 + +export interface MermaidButtonProps { + containerRef: React.RefObject + code: string + isLoading: boolean + svgToPng: (svgEl: SVGElement) => Promise + children: React.ReactNode +} + +export function MermaidButton({ containerRef, code, isLoading, svgToPng, children }: MermaidButtonProps) { + const [showModal, setShowModal] = useState(false) + const [zoomLevel, setZoomLevel] = useState(1) + const [copyFeedback, setCopyFeedback] = useState(false) + const [isHovering, setIsHovering] = useState(false) + const [modalViewMode, setModalViewMode] = useState<"diagram" | "code">("diagram") + const [isDragging, setIsDragging] = useState(false) + const [dragPosition, setDragPosition] = useState({ x: 0, y: 0 }) + const { copyWithFeedback } = useCopyToClipboard() + const { t } = useAppTranslation() + + /** + * Opens a modal with the diagram for zooming + */ + const handleZoom = async (e: React.MouseEvent) => { + e.stopPropagation() + setShowModal(true) + setZoomLevel(1) + setModalViewMode("diagram") + } + + /** + * Copies the diagram text to clipboard + */ + const handleCopy = async (e: React.MouseEvent) => { + e.stopPropagation() + + try { + await copyWithFeedback(code, e) + + // Show feedback + setCopyFeedback(true) + setTimeout(() => setCopyFeedback(false), 2000) + } catch (err) { + console.error("Error copying text:", err instanceof Error ? err.message : String(err)) + } + } + + /** + * Saves the diagram as an image file + */ + const handleSave = async (e: React.MouseEvent) => { + e.stopPropagation() + + // Get the SVG element from the container + const svgEl = containerRef.current?.querySelector("svg") + if (!svgEl) { + console.error("SVG element not found") + return + } + + try { + // Convert SVG to PNG + const pngDataUrl = await svgToPng(svgEl) + + // Send message to VSCode to save the image + vscode.postMessage({ + type: "saveImage", + dataUri: pngDataUrl, + }) + } catch (error) { + console.error("Error saving image:", error) + } + } + + /** + * Adjust zoom level in the modal + */ + const adjustZoom = (amount: number) => { + setZoomLevel((prev) => { + const newZoom = prev + amount + return Math.max(MIN_ZOOM, Math.min(MAX_ZOOM, newZoom)) + }) + } + + /** + * Handle wheel event for zooming with scroll wheel + */ + const handleWheel = useCallback((e: React.WheelEvent) => { + e.preventDefault() + e.stopPropagation() + + // Determine zoom direction and amount + // Negative deltaY means scrolling up (zoom in), positive means scrolling down (zoom out) + const delta = e.deltaY > 0 ? -0.2 : 0.2 + adjustZoom(delta) + }, []) + + /** + * Handle mouse enter event for diagram container + */ + const handleMouseEnter = () => { + setIsHovering(true) + } + + /** + * Handle mouse leave event for diagram container + */ + const handleMouseLeave = () => { + setIsHovering(false) + } + + return ( + <> +
+ {children} + {!isLoading && isHovering && ( +
+ { + setShowModal(true) + setModalViewMode("code") + setZoomLevel(1) + }} + copyFeedback={copyFeedback} + /> +
+ )} +
+ + setShowModal(false)}> +
+
+ setModalViewMode("diagram")} + /> + setModalViewMode("code")} + /> +
+ +
+ setShowModal(false)} + title={t("common:mermaid.buttons.close")} + /> +
+
+
+ {modalViewMode === "diagram" ? ( + <> +
{ + setIsDragging(true) + e.preventDefault() + }} + onMouseMove={(e) => { + if (isDragging) { + setDragPosition((prev) => ({ + x: prev.x + e.movementX / zoomLevel, + y: prev.y + e.movementY / zoomLevel, + })) + } + }} + onMouseUp={() => setIsDragging(false)} + onMouseLeave={() => setIsDragging(false)}> + {containerRef.current && containerRef.current.innerHTML && ( +
+ )} +
+
+ {Math.round(zoomLevel * 100)}% +
+ + ) : ( +