Compare commits

..
Author SHA1 Message Date
celestial-vault 4b399189ca simplify is
streaming boolean to just use lastMessage.partial
2025-06-23 15:10:47 -07:00
46 changed files with 415 additions and 2345 deletions
+5
View File
@@ -0,0 +1,5 @@
---
"claude-dev": minor
---
Remove the clsx / tailwind merge dependencies and replace with template literals
+5
View File
@@ -0,0 +1,5 @@
---
"claude-dev": minor
---
Migrate fetchUserCreditsData to protobus
+5
View File
@@ -0,0 +1,5 @@
---
"claude-dev": minor
---
Migrate authStateChanged to protobus
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
clearAllTaskHistory protobus migration
+5
View File
@@ -0,0 +1,5 @@
---
"claude-dev": patch
---
Add taskId as metadata to use from LiteLLM
-89
View File
@@ -1,89 +0,0 @@
# Cline Protobuf Development Guide
This guide outlines how to add new gRPC endpoints for communication between the webview (frontend) and the extension host (backend).
## Overview
Cline uses [Protobuf](https://protobuf.dev/) to define a strongly-typed API, ensuring efficient and type-safe communication. All definitions are in the `/proto` directory. The compiler and plugins are included as project dependencies, so no manual installation is needed.
## Key Concepts & Best Practices
- **File Structure**: Each feature domain should have its own `.proto` file (e.g., `account.proto`, `task.proto`).
- **Message Design**:
- For simple, single-value data, use the shared types in `proto/common.proto` (e.g., `StringRequest`, `Empty`, `Int64Request`). This promotes consistency.
- For complex data structures, define custom messages within the feature's `.proto` file (see `task.proto` for examples like `NewTaskRequest`).
- **Naming Conventions**:
- Services: `PascalCaseService` (e.g., `AccountService`).
- RPCs: `camelCase` (e.g., `accountEmailIdentified`).
- Messages: `PascalCase` (e.g., `StringRequest`).
- **Streaming**: For server-to-client streaming, use the `stream` keyword on the response type. See `subscribeToAuthCallback` in `account.proto` for an example.
---
## 4-Step Development Workflow
Heres how to add a new RPC, using `scrollToSettings` as an example.
### 1. Define the RPC in a `.proto` File
Add your service method to the appropriate file in the `proto/` directory.
**File: `proto/ui.proto`**
```proto
service UiService {
// ... other RPCs
// Scrolls to a specific settings section in the settings view
rpc scrollToSettings(StringRequest) returns (KeyValuePair);
}
```
Here, we use the common `StringRequest` and `KeyValuePair` types.
### 2. Compile Definitions
After editing a `.proto` file, regenerate the TypeScript code. From the project root, run:
```bash
npm run protos
```
This command compiles all `.proto` files and outputs the generated code to `src/generated/` and `src/shared/`. Do not edit these generated files manually.
### 3. Implement the Backend Handler
Create the RPC implementation in the backend. Handlers are located in `src/core/controller/[service-name]/`.
**File: `src/core/controller/ui/scrollToSettings.ts`**
```typescript
import { Controller } from ".."
import { StringRequest, KeyValuePair } from "../../../shared/proto/common"
/**
* Executes a scroll to settings action
* @param controller The controller instance
* @param request The request containing the ID of the settings section to scroll to
* @returns KeyValuePair with action and value fields for the UI to process
*/
export async function scrollToSettings(controller: Controller, request: StringRequest): Promise<KeyValuePair> {
return KeyValuePair.create({
key: "scrollToSettings",
value: request.value || "",
})
}
```
### 4. Call the RPC from the Webview
Call the new RPC from a React component in `webview-ui/`. The generated client makes this simple.
**File: `webview-ui/src/components/browser/BrowserSettingsMenu.tsx`** (Example)
```tsx
import { UiServiceClient } from "../../../services/grpc"
import { StringRequest } from "../../../../shared/proto/common"
// ... inside a React component
const handleMenuClick = async () => {
try {
await UiServiceClient.scrollToSettings(StringRequest.create({ value: "browser" }))
} catch (error) {
console.error("Error scrolling to browser settings:", error)
}
}
```
-5
View File
@@ -1,10 +1,5 @@
# Changelog
## [3.17.16]
- Fix Claude Code provider error handling for incomplete messages during long-running tasks (Thanks @BarreiroT!)
- Add taskId as metadata to LiteLLM API requests for better request tracing (Thanks @jorgegarciarey!)
## [3.17.15]
- Fix LiteLLM provider to properly respect selected model IDs when switching between Plan and Act modes (Thanks @sammcj!)
@@ -1,74 +0,0 @@
const { RuleTester: VscodeRuleTester } = require("eslint")
const vscodePostmessageRule = require("../no-vscode-postmessage")
const vscodeRuleTester = new VscodeRuleTester({
parser: require.resolve("@typescript-eslint/parser"),
parserOptions: {
ecmaVersion: 2020,
sourceType: "module",
ecmaFeatures: {
jsx: true,
},
},
})
vscodeRuleTester.run("no-vscode-postmessage", vscodePostmessageRule, {
valid: [
// Should allow vscode.postMessage in grpc-client-base.ts
{
code: `vscode.postMessage({ type: "grpc_request", data: {} })`,
filename: "grpc-client-base.ts",
},
{
code: `vscode.postMessage({ type: "grpc_request_cancel" })`,
filename: "/path/to/grpc-client-base.ts",
},
// Should allow other vscode API calls
{
code: `vscode.window.showInformationMessage("Hello")`,
filename: "test.ts",
},
// Should allow postMessage calls on other objects
{
code: `window.postMessage({ type: "test" }, "*")`,
filename: "test.ts",
},
// Should allow variables named vscode but not calling postMessage
{
code: `const vscode = { other: "method" }; vscode.other()`,
filename: "test.ts",
},
],
invalid: [
// Should ban vscode.postMessage in regular files
{
code: `vscode.postMessage({ type: "test", data: {} })`,
filename: "test.ts",
errors: [
{
messageId: "useGrpcClient",
},
],
},
// Should ban vscode.postMessage in components
{
code: `vscode.postMessage({ type: "apiConfiguration", apiConfiguration })`,
filename: "ApiOptions.tsx",
errors: [
{
messageId: "useGrpcClient",
},
],
},
// Should ban vscode.postMessage in test files
{
code: `vscode.postMessage({ type: "newTask", text: message.text })`,
filename: "test.test.ts",
errors: [
{
messageId: "useGrpcClient",
},
],
},
],
})
-3
View File
@@ -1,13 +1,11 @@
// eslint-rules/index.js
const noProtobufObjectLiterals = require("./no-protobuf-object-literals")
const noGrpcClientObjectLiterals = require("./no-grpc-client-object-literals")
const noVscodePostmessage = require("./no-vscode-postmessage")
module.exports = {
rules: {
"no-protobuf-object-literals": noProtobufObjectLiterals,
"no-grpc-client-object-literals": noGrpcClientObjectLiterals,
"no-vscode-postmessage": noVscodePostmessage,
},
configs: {
recommended: {
@@ -15,7 +13,6 @@ module.exports = {
rules: {
"local/no-protobuf-object-literals": "error",
"local/no-grpc-client-object-literals": "error",
"local/no-vscode-postmessage": "error",
},
},
},
-61
View File
@@ -1,61 +0,0 @@
const { ESLintUtils } = require("@typescript-eslint/utils")
const path = require("path")
const createRule = ESLintUtils.RuleCreator((name) => `https://cline.bot/eslint-rules/${name}`)
module.exports = createRule({
name: "no-vscode-postmessage",
meta: {
type: "problem",
docs: {
description: "Ban vscode.postMessage() calls in favor of gRPC service clients, except in grpc-client-base.ts",
recommended: "error",
},
messages: {
useGrpcClient:
"Use gRPC service clients instead of vscode.postMessage().\n" +
"Example: AccountServiceClient.methodName(RequestType.create({...})) instead of vscode.postMessage({type: '...'}).\n" +
"Found: {{code}}",
},
schema: [],
},
defaultOptions: [],
create(context) {
// Check if current file is grpc-client-base.ts (exception case)
const filename = context.filename
const isGrpcClientBase = path.basename(filename) === "grpc-client-base.ts"
return {
// Detect vscode.postMessage calls
"CallExpression[callee.type='MemberExpression']"(node) {
// Skip if this is grpc-client-base.ts
if (isGrpcClientBase) {
return
}
const callee = node.callee
// Check for vscode.postMessage pattern
if (
callee.object &&
callee.object.type === "Identifier" &&
callee.object.name === "vscode" &&
callee.property &&
callee.property.name === "postMessage"
) {
const sourceCode = context.sourceCode
const callText = sourceCode.getText(node).trim()
context.report({
node,
messageId: "useGrpcClient",
data: {
code: callText,
},
})
}
},
}
},
})
+1 -3
View File
@@ -19,6 +19,4 @@ diff_editing/test_outputs/
.cache
# Python bytecode cache
*__pycache__/
diff-edits/cases.zip
*__pycache__/
-10
View File
@@ -14,8 +14,6 @@ interface RunDiffEvalOptions {
testPath: string
outputPath: string
replay: boolean
replayRunId?: string
diffApplyFile?: string
maxCases?: number
}
@@ -58,14 +56,6 @@ export async function runDiffEvalHandler(options: RunDiffEvalOptions) {
args.push("--replay")
}
if (options.replayRunId) {
args.push("--replay-run-id", options.replayRunId)
}
if (options.diffApplyFile) {
args.push("--diff-apply-file", options.diffApplyFile)
}
if (options.verbose) {
args.push("--verbose")
}
-2
View File
@@ -93,8 +93,6 @@ program
.option("--thinking-budget <tokens>", "Set the thinking tokens budget", "0")
.option("--parallel", "Run tests in parallel", false)
.option("--replay", "Run evaluation from a pre-recorded LLM output, skipping the API call", false)
.option("--replay-run-id <run_id>", "The ID of the run to replay from the database")
.option("--diff-apply-file <filename>", "The name of the diff apply file to use for the replay")
.option("-v, --verbose", "Enable verbose logging", false)
.action(async (options) => {
try {
+1 -5
View File
@@ -9,7 +9,6 @@ import {
AssistantMessageContent,
} from "./parsing/parse-assistant-message-06-06-25" // "../../src/core/assistant-message"
import { constructNewFileContent as constructNewFileContentV1, constructNewFileContentV2 } from "./diff-apply/diff-06-06-25"
import { constructNewFileContent as constructNewFileContentV2_1 } from "./diff-apply/diff-06-23-25"
import { constructNewFileContent as constructNewFileContentV3 } from "../../src/core/assistant-message/diff" // this defaults to the new v1 when called
type ParseAssistantMessageFn = (message: string) => AssistantMessageContent[]
@@ -22,8 +21,6 @@ const parsingFunctions: Record<string, ParseAssistantMessageFn> = {
}
const diffEditingFunctions: Record<string, ConstructNewFileContentFn> = {
"diff-06-06-25": constructNewFileContentV2,
"diff-06-23-25": constructNewFileContentV2_1,
constructNewFileContentV1: constructNewFileContentV1,
constructNewFileContentV2: constructNewFileContentV2,
constructNewFileContentV3: constructNewFileContentV3, // position invariant diff
@@ -154,7 +151,6 @@ export async function runSingleEvaluation(input: TestInput): Promise<TestResult>
diffEditFunction,
thinkingBudgetTokens,
originalDiffEditToolCallMessage,
diffApplyFile,
} = input
const requiredParams = {
@@ -180,7 +176,7 @@ export async function runSingleEvaluation(input: TestInput): Promise<TestResult>
}
const parseAssistantMessage = parsingFunctions[parsingFunction]
const constructNewFileContent = diffEditingFunctions[diffApplyFile || diffEditFunction]
const constructNewFileContent = diffEditingFunctions[diffEditFunction]
if (!parseAssistantMessage || !constructNewFileContent) {
return {
+4 -17
View File
@@ -63,22 +63,9 @@ For example, if we ask for 5 valid attempts per test case, the system will keep
This way, if we're comparing two models and one gets a 10% success rate on its valid diff edit attempts, and another gets 90%, we have a much clearer picture of their actual diff-generating capabilities. It avoids muddying the waters with attempts where the model didn't even try to perform the specific action we're evaluating. This approach helps us isolate and measure the diff-editing skill more directly, despite the non-deterministic nature of these models.
## Replays
## Some known edge cases
You can also use the replay argument to replay a previous benchmark run. This is super useful for iterating on our diffing algorithms without having to re-run expensive and time-consuming LLM calls.
I noticed that some of the current conversation jsons in the `./cases` folder are a little big bogus. Here's a running list of these areas:
When you run an evaluation, every detail is stored in the database—including the raw, unmodified output from the model. The replay feature takes advantage of this by pulling that raw output and feeding it into a *different* diffing algorithm. This lets you isolate the performance of the diffing logic itself. We can see if a new algorithm is better at applying the exact same set of diffs that a model generated in a previous run.
This process is blazingly fast and free, as it completely bypasses the need to make new API calls. It ensures a true apples-to-apples comparison between diffing strategies, since the model's output—the "ground truth" for the evaluation—remains identical.
Heres an example of how you would replay a previous run with a new diffing algorithm:
```shell
cd evals && npm run diff-eval -- --replay-run-id 9902189e-63a8-4210-a4fc-fe59e2eaf2c2 --diff-apply-file diff-06-23-25 --verbose
```
In this command:
- `--replay-run-id` specifies the original run we want to use as our ground truth.
- `--diff-apply-file` tells the script to use the new diffing logic from the `diff-06-23-25.ts` file.
The script will then create a new run in the database that mirrors the original, but with the results of applying the new diffing algorithm. This allows for a direct comparison in the dashboard, helping us quickly see which of our diffing strategies is the most robust.
- ~~What if the conversation json was using a model with a massive context window, like Google Gemini's 1M context window, and we're now re-rolling that case on a smaller context window model like claude 4 (200k) or grok-3 (128k)? It's def gonna fail, and we shouldn't just keep trying. We should have a smart system for selecting which cases we can use given the arguments passed in. For example, if we pass in claude and grok with `max cases = 2`, we shouldn't just pick the first two jsons in the folder. We should go through, use a tokenizer, and make sure it would fit with some padding like 20k tokens. Use tiktoken. 20k padding will be sufficient even though different models tokenize differently.~~
- There are some weird jsons, where something weird happen, where essentially there's a fluke. Maybe the user was using an extremely dumb model that just hallucinated a fake filepath. Now when we try to reroll that case, we never get a valid case. This can easily be handled by making sure that the file is present before selecting that eval for testing. By "file is present" I mean, that file_contents is present in the eval. Additionally, we should in the streamlit dashboard show cases where getting a valid attempt is a challenge, so we can review those cases more easily and throw them out if they're bogus. Maybe a special tab/page in the dashboard for this purpose. Across all runs / cases, what the most consistently problematic cases are. Pop one open to see the case formatted json with all the user/assistant turns.
-230
View File
@@ -1,8 +1,4 @@
import { runSingleEvaluation, TestInput, TestResult } from "./ClineWrapper"
import { parseAssistantMessageV2, AssistantMessageContent } from "./parsing/parse-assistant-message-06-06-25"
import { constructNewFileContent as constructNewFileContentV2 } from "./diff-apply/diff-06-06-25"
import { constructNewFileContent as constructNewFileContentV2_1 } from "./diff-apply/diff-06-23-25"
import { constructNewFileContent as constructNewFileContentV3 } from "../../src/core/assistant-message/diff"
import { basicSystemPrompt } from "./prompts/basicSystemPrompt-06-06-25"
import { claude4SystemPrompt } from "./prompts/claude4SystemPrompt-06-06-25"
import { formatResponse } from "./helpers"
@@ -22,10 +18,6 @@ import {
insertResult,
DatabaseClient,
CreateResultInput,
getResultsByRun,
getCaseById,
getFileByHash,
getBenchmarkRun,
} from "./database"
// Load environment variables from .env file
@@ -192,78 +184,6 @@ class NodeTestRunner {
log(isVerbose, `✓ Created ${this.caseIdMap.size} database case records`);
}
/**
* Store replay result in database, copying original data but with new diffing results
*/
async storeReplayResultInDatabase(replayResult: TestResult, originalResult: any, testId: string, newCaseId: string): Promise<void> {
if (!this.currentRunId || !this.processingFunctionsHash) {
return; // Skip if database not initialized
}
try {
// Map error string to error enum (simple mapping)
const errorEnum = this.mapErrorToEnum(replayResult.error);
// Store diff edit content if available
let fileEditedHash: string | undefined;
if (replayResult.diffEdit) {
fileEditedHash = await upsertFile({
filepath: `diff-edit-${testId}`,
content: replayResult.diffEdit
});
}
// Calculate basic metrics from diff edit if available
let numEdits = 0;
let numLinesAdded = 0;
let numLinesDeleted = 0;
if (replayResult.diffEdit) {
// Simple parsing to count edits - count SEARCH/REPLACE blocks
const searchBlocks = (replayResult.diffEdit.match(/------- SEARCH/g) || []).length;
numEdits = searchBlocks;
// Count added/deleted lines (rough approximation)
const lines = replayResult.diffEdit.split('\n');
for (const line of lines) {
if (line.startsWith('+') && !line.startsWith('+++')) {
numLinesAdded++;
} else if (line.startsWith('-') && !line.startsWith('---')) {
numLinesDeleted++;
}
}
}
// Copy original result data but update replay-specific fields
const resultInput: CreateResultInput = {
run_id: this.currentRunId, // New run ID
case_id: newCaseId, // New case ID
model_id: originalResult.model_id, // Copy from original
processing_functions_hash: this.processingFunctionsHash, // New processing functions
succeeded: replayResult.success && (replayResult.diffEditSuccess ?? false), // New result
error_enum: errorEnum, // New error if any
num_edits: numEdits || originalResult.num_edits, // New or original
num_lines_deleted: numLinesDeleted || originalResult.num_lines_deleted, // New or original
num_lines_added: numLinesAdded || originalResult.num_lines_added, // New or original
// Copy timing and cost data from original (since we didn't make API calls)
time_to_first_token_ms: originalResult.time_to_first_token_ms,
time_to_first_edit_ms: originalResult.time_to_first_edit_ms,
time_round_trip_ms: originalResult.time_round_trip_ms,
cost_usd: originalResult.cost_usd,
completion_tokens: originalResult.completion_tokens,
// Use original model output (since we're replaying)
raw_model_output: originalResult.raw_model_output,
file_edited_hash: fileEditedHash || originalResult.file_edited_hash,
parsed_tool_call_json: replayResult.toolCalls ? JSON.stringify(replayResult.toolCalls) : originalResult.parsed_tool_call_json
};
await insertResult(resultInput);
} catch (error) {
console.error(`Failed to store replay result in database for ${testId}:`, error);
// Continue execution - don't fail the test run
}
}
/**
* Store test result in database
*/
@@ -474,142 +394,6 @@ class NodeTestRunner {
}
}
async runDatabaseReplay(replayRunId: string, diffApplyFile: string, isVerbose: boolean) {
log(isVerbose, `Starting database replay for run_id: ${replayRunId}`)
log(isVerbose, `Using diff apply file: ${diffApplyFile}`)
// 1. Get the correct diffing function
const diffEditingFunctions: Record<string, any> = {
"diff-06-06-25": constructNewFileContentV2,
"diff-06-23-25": constructNewFileContentV2_1,
constructNewFileContentV3: constructNewFileContentV3,
}
const constructNewFileContent = diffEditingFunctions[diffApplyFile]
if (!constructNewFileContent) {
throw new Error(`Could not find diff apply function for: ${diffApplyFile}`)
}
log(isVerbose, `Successfully loaded diff apply function: ${diffApplyFile}`)
// 2. Fetch original run data
const originalResults = await getResultsByRun(replayRunId)
if (originalResults.length === 0) {
throw new Error(`No results found for run_id: ${replayRunId}`)
}
log(isVerbose, `Found ${originalResults.length} results to replay.`)
const originalRun = await getBenchmarkRun(replayRunId)
if (!originalRun) {
throw new Error(`Could not find original run with id ${replayRunId}`)
}
// 3. Create a new benchmark run for the replay
const replayRunDescription = `Replay of run ${replayRunId} using ${diffApplyFile}`
this.currentRunId = await createBenchmarkRun({
description: replayRunDescription,
system_prompt_hash: originalRun.system_prompt_hash,
})
log(isVerbose, `Created new run for replay: ${this.currentRunId}`)
// 4. Set up processing functions for the new run
this.processingFunctionsHash = await upsertProcessingFunctions({
name: `replay-${diffApplyFile}`,
parsing_function: "parseAssistantMessageV2",
diff_edit_function: diffApplyFile,
})
// 5. Process each result from the original run
let replayedCount = 0
const caseIdMirror: Map<string, string> = new Map()
for (const originalResult of originalResults) {
// 5a. Basic validation to ensure we can even process this
if (!originalResult.case_id) {
log(isVerbose, `Skipping result ${originalResult.result_id} due to missing case_id.`)
continue
}
// 5b. Mirror the case for the new run, reusing if already created
let newCaseId = caseIdMirror.get(originalResult.case_id)
if (!newCaseId) {
const originalCase = await getCaseById(originalResult.case_id)
if (!originalCase) {
log(isVerbose, `Skipping result ${originalResult.result_id} because original case could not be found.`)
continue
}
newCaseId = await createCase({
run_id: this.currentRunId,
description: `Replay of case ${originalCase.case_id} from run ${replayRunId}`,
system_prompt_hash: originalCase.system_prompt_hash,
task_id: originalCase.task_id,
tokens_in_context: originalCase.tokens_in_context,
file_hash: originalCase.file_hash,
})
caseIdMirror.set(originalResult.case_id, newCaseId)
}
// 5c. Determine if the original attempt was a "valid attempt"
const isValidOriginalAttempt = originalResult.error_enum === null || originalResult.error_enum === 3 // 3 is diff_edit_error
const newResultInput: CreateResultInput = {
...(originalResult as any),
run_id: this.currentRunId,
case_id: newCaseId,
processing_functions_hash: this.processingFunctionsHash,
}
delete (newResultInput as any).result_id
if (isValidOriginalAttempt) {
// This was a valid attempt. Re-run the diff algorithm.
const originalCase = await getCaseById(originalResult.case_id)
if (!originalCase) {
log(isVerbose, ` [WARN] Replay for result ${originalResult.result_id}: Could not find original case. Copying original result.`)
newResultInput.succeeded = originalResult.succeeded
newResultInput.error_enum = originalResult.error_enum
} else {
const originalFile = originalCase.file_hash ? await getFileByHash(originalCase.file_hash) : null
const parsedToolCall = originalResult.parsed_tool_call_json ? JSON.parse(originalResult.parsed_tool_call_json)[0] : null
const diffContent = parsedToolCall?.input?.diff
if (originalFile && diffContent) {
let diffSuccess = false
try {
await constructNewFileContent(diffContent, originalFile.content, true)
diffSuccess = true
log(isVerbose, ` [OK] Replay for task ${originalCase.task_id}: Diff applied successfully.`)
} catch (e) {
diffSuccess = false
log(isVerbose, ` [FAIL] Replay for task ${originalCase.task_id}: New diff algorithm failed.`)
}
newResultInput.succeeded = diffSuccess
newResultInput.error_enum = diffSuccess ? undefined : 3 // 3 = diff_edit_error
} else {
// Something is wrong with the ground truth data, just copy it.
log(
isVerbose,
` [WARN] Replay for task ${originalCase.task_id}: Valid original attempt but missing file or diff content. Copying original result.`,
)
newResultInput.succeeded = originalResult.succeeded
newResultInput.error_enum = originalResult.error_enum
}
}
} else {
// This was not a valid attempt. Just copy the original result's outcome.
log(isVerbose, ` [SKIP] Replay for task ${originalResult.case_id}: Invalid original attempt. Copying original result.`)
newResultInput.succeeded = originalResult.succeeded
newResultInput.error_enum = originalResult.error_enum
}
await insertResult(newResultInput)
replayedCount++
}
log(isVerbose, `\n✓ Database replay completed successfully.`)
log(isVerbose, ` Total original results: ${originalResults.length}`)
log(isVerbose, ` Total replayed results: ${replayedCount}`)
log(isVerbose, ` New run ID: ${this.currentRunId}`)
}
/**
* Run a single test example
*/
@@ -636,7 +420,6 @@ class NodeTestRunner {
diffEditFunction: testConfig.diff_edit_function,
thinkingBudgetTokens: testConfig.thinking_tokens_budget,
originalDiffEditToolCallMessage: testConfig.replay ? testCase.original_diff_edit_tool_call_message : undefined,
diffApplyFile: testConfig.diff_apply_file,
}
if (isVerbose) {
@@ -929,8 +712,6 @@ async function main() {
.option("--thinking-budget <tokens>", "Set the thinking tokens budget", "0")
.option("--parallel", "Run tests in parallel", false)
.option("--replay", "Run evaluation from a pre-recorded LLM output, skipping the API call", false)
.option("--replay-run-id <run_id>", "The ID of the run to replay from the database")
.option("--diff-apply-file <filename>", "The name of the diff apply file to use for the replay")
.option("-v, --verbose", "Enable verbose logging", false)
.option("--max-concurrency <number>", "Maximum number of parallel requests", "80")
@@ -951,17 +732,6 @@ async function main() {
}
const validAttemptsPerCase = parseInt(options.validAttemptsPerCase, 10);
const runner = new NodeTestRunner(options.replay || !!options.replayRunId)
if (options.replayRunId) {
if (!options.diffApplyFile) {
console.error("Error: --diff-apply-file is required when using --replay-run-id")
process.exit(1)
}
await runner.runDatabaseReplay(options.replayRunId, options.diffApplyFile, isVerbose)
return
}
try {
const startTime = Date.now()
+3 -12
View File
@@ -420,25 +420,16 @@ def render_model_comparison_cards(model_performance):
metric_col1, metric_col2, metric_col3, metric_col4 = st.columns(4)
with metric_col1:
if pd.notna(model['avg_round_trip_ms']):
st.metric("Avg Latency", f"{model['avg_round_trip_ms']:.0f}ms")
else:
st.metric("Avg Latency", "N/A")
st.metric("Avg Latency", f"{model['avg_round_trip_ms']:.0f}ms")
with metric_col2:
if pd.notna(model['avg_cost']):
st.metric("Avg Cost", f"${model['avg_cost']:.4f}")
else:
st.metric("Avg Cost", "N/A")
st.metric("Avg Cost", f"${model['avg_cost']:.4f}")
with metric_col3:
st.metric("Valid Results", f"{model['total_results']}")
with metric_col4:
if pd.notna(model['avg_first_token_ms']):
st.metric("First Token", f"{model['avg_first_token_ms']:.0f}ms")
else:
st.metric("First Token", "N/A")
st.metric("First Token", f"{model['avg_first_token_ms']:.0f}ms")
with col2:
st.write("") # Add some spacing
+1 -13
View File
@@ -33,7 +33,7 @@ This is the most granular and important table in the database. A `result` repres
- **Purpose**: To store the detailed outcome of every single model attempt, providing the raw data for all quantitative and qualitative analysis.
- **Key Columns**:
- `result_id`: The primary key for the result.
- `result_id`: A unique identifier for the individual attempt.
- `run_id`, `case_id`, `model_id`, `processing_functions_hash`: A set of foreign keys that precisely situate this result within the context of a specific run, case, model, and set of helper functions.
- `succeeded`: A boolean indicating if the generated diff was applied successfully.
- `error_enum`: A numeric code representing the specific type of error if the attempt failed (e.g., `1` for `no_tool_calls`, `7` for `wrong_file_edited`).
@@ -82,15 +82,3 @@ This relational schema provides a powerful foundation for sophisticated analysis
- "Which of our internal diffing algorithms is the most robust against a wide range of model-generated edits?"
Ultimately, this data model enables us to move from simply *measuring* performance to truly *understanding* it, providing the insights needed to build more capable and reliable AI engineering systems.
---
## Viewing the Full Schema
To see the most up-to-date and detailed schema for the database, you can use the `sqlite3` command-line tool. From the `evals/diff-edits` directory, run the following command:
```bash
sqlite3 evals.db .schema
```
This will print the complete `CREATE TABLE` statements for all tables in the database, providing a definitive reference for the database structure.
@@ -1,827 +0,0 @@
const SEARCH_BLOCK_START = "------- SEARCH"
const SEARCH_BLOCK_END = "======="
const REPLACE_BLOCK_END = "+++++++ REPLACE"
const SEARCH_BLOCK_CHAR = "-"
const REPLACE_BLOCK_CHAR = "+"
const LEGACY_SEARCH_BLOCK_CHAR = "<"
const LEGACY_REPLACE_BLOCK_CHAR = ">"
// Replace the exact string constants with flexible regex patterns
const SEARCH_BLOCK_START_REGEX = /^[-]{3,} SEARCH$/
const SEARCH_BLOCK_END_REGEX = /^[=]{3,}$/
const REPLACE_BLOCK_END_REGEX = /^[+]{3,} REPLACE$/
const LEGACY_SEARCH_BLOCK_START_REGEX = /^[<]{3,} SEARCH$/
const LEGACY_REPLACE_BLOCK_END_REGEX = /^[>]{3,} REPLACE$/
// Helper functions to check if a line matches the flexible patterns
function isSearchBlockStart(line: string): boolean {
return SEARCH_BLOCK_START_REGEX.test(line) || LEGACY_SEARCH_BLOCK_START_REGEX.test(line)
}
function isSearchBlockEnd(line: string): boolean {
return SEARCH_BLOCK_END_REGEX.test(line)
}
function isReplaceBlockEnd(line: string): boolean {
return REPLACE_BLOCK_END_REGEX.test(line) || LEGACY_REPLACE_BLOCK_END_REGEX.test(line)
}
/**
* Attempts a line-trimmed fallback match for the given search content in the original content.
* It tries to match `searchContent` lines against a block of lines in `originalContent` starting
* from `lastProcessedIndex`. Lines are matched by trimming leading/trailing whitespace and ensuring
* they are identical afterwards.
*
* Returns [matchIndexStart, matchIndexEnd] if found, or false if not found.
*/
function lineTrimmedFallbackMatch(originalContent: string, searchContent: string, startIndex: number): [number, number] | false {
// Split both contents into lines
const originalLines = originalContent.split("\n")
const searchLines = searchContent.split("\n")
// Trim trailing empty line if exists (from the trailing \n in searchContent)
if (searchLines[searchLines.length - 1] === "") {
searchLines.pop()
}
// Find the line number where startIndex falls
let startLineNum = 0
let currentIndex = 0
while (currentIndex < startIndex && startLineNum < originalLines.length) {
currentIndex += originalLines[startLineNum].length + 1 // +1 for \n
startLineNum++
}
// For each possible starting position in original content
for (let i = startLineNum; i <= originalLines.length - searchLines.length; i++) {
let matches = true
// Try to match all search lines from this position
for (let j = 0; j < searchLines.length; j++) {
const originalTrimmed = originalLines[i + j].trim()
const searchTrimmed = searchLines[j].trim()
if (originalTrimmed !== searchTrimmed) {
matches = false
break
}
}
// If we found a match, calculate the exact character positions
if (matches) {
// Find start character index
let matchStartIndex = 0
for (let k = 0; k < i; k++) {
matchStartIndex += originalLines[k].length + 1 // +1 for \n
}
// Find end character index
let matchEndIndex = matchStartIndex
for (let k = 0; k < searchLines.length; k++) {
matchEndIndex += originalLines[i + k].length + 1 // +1 for \n
}
return [matchStartIndex, matchEndIndex]
}
}
return false
}
/**
* Attempts to match blocks of code by using the first and last lines as anchors.
* This is a third-tier fallback strategy that helps match blocks where we can identify
* the correct location by matching the beginning and end, even if the exact content
* differs slightly.
*
* The matching strategy:
* 1. Only attempts to match blocks of 3 or more lines to avoid false positives
* 2. Extracts from the search content:
* - First line as the "start anchor"
* - Last line as the "end anchor"
* 3. For each position in the original content:
* - Checks if the next line matches the start anchor
* - If it does, jumps ahead by the search block size
* - Checks if that line matches the end anchor
* - All comparisons are done after trimming whitespace
*
* This approach is particularly useful for matching blocks of code where:
* - The exact content might have minor differences
* - The beginning and end of the block are distinctive enough to serve as anchors
* - The overall structure (number of lines) remains the same
*
* @param originalContent - The full content of the original file
* @param searchContent - The content we're trying to find in the original file
* @param startIndex - The character index in originalContent where to start searching
* @returns A tuple of [startIndex, endIndex] if a match is found, false otherwise
*/
function blockAnchorFallbackMatch(originalContent: string, searchContent: string, startIndex: number): [number, number] | false {
const originalLines = originalContent.split("\n")
const searchLines = searchContent.split("\n")
// Only use this approach for blocks of 3+ lines
if (searchLines.length < 3) {
return false
}
// Trim trailing empty line if exists
if (searchLines[searchLines.length - 1] === "") {
searchLines.pop()
}
const firstLineSearch = searchLines[0].trim()
const lastLineSearch = searchLines[searchLines.length - 1].trim()
const searchBlockSize = searchLines.length
// Find the line number where startIndex falls
let startLineNum = 0
let currentIndex = 0
while (currentIndex < startIndex && startLineNum < originalLines.length) {
currentIndex += originalLines[startLineNum].length + 1
startLineNum++
}
// Look for matching start and end anchors
for (let i = startLineNum; i <= originalLines.length - searchBlockSize; i++) {
// Check if first line matches
if (originalLines[i].trim() !== firstLineSearch) {
continue
}
// Check if last line matches at the expected position
if (originalLines[i + searchBlockSize - 1].trim() !== lastLineSearch) {
continue
}
// Calculate exact character positions
let matchStartIndex = 0
for (let k = 0; k < i; k++) {
matchStartIndex += originalLines[k].length + 1
}
let matchEndIndex = matchStartIndex
for (let k = 0; k < searchBlockSize; k++) {
matchEndIndex += originalLines[i + k].length + 1
}
return [matchStartIndex, matchEndIndex]
}
return false
}
/**
* This function reconstructs the file content by applying a streamed diff (in a
* specialized SEARCH/REPLACE block format) to the original file content. It is designed
* to handle both incremental updates and the final resulting file after all chunks have
* been processed.
*
* The diff format is a custom structure that uses three markers to define changes:
*
* ------- SEARCH
* [Exact content to find in the original file]
* =======
* [Content to replace with]
* +++++++ REPLACE
*
* Behavior and Assumptions:
* 1. The file is processed chunk-by-chunk. Each chunk of `diffContent` may contain
* partial or complete SEARCH/REPLACE blocks. By calling this function with each
* incremental chunk (with `isFinal` indicating the last chunk), the final reconstructed
* file content is produced.
*
* 2. Matching Strategy (in order of attempt):
* a. Exact Match: First attempts to find the exact SEARCH block text in the original file
* b. Line-Trimmed Match: Falls back to line-by-line comparison ignoring leading/trailing whitespace
* c. Block Anchor Match: For blocks of 3+ lines, tries to match using first/last lines as anchors
* If all matching strategies fail, an error is thrown.
*
* 3. Empty SEARCH Section:
* - If SEARCH is empty and the original file is empty, this indicates creating a new file
* (pure insertion).
* - If SEARCH is empty and the original file is not empty, this indicates a complete
* file replacement (the entire original content is considered matched and replaced).
*
* 4. Applying Changes:
* - Before encountering the "=======" marker, lines are accumulated as search content.
* - After "=======" and before ">>>>>>> REPLACE", lines are accumulated as replacement content.
* - Once the block is complete (">>>>>>> REPLACE"), the matched section in the original
* file is replaced with the accumulated replacement lines, and the position in the original
* file is advanced.
*
* 5. Incremental Output:
* - As soon as the match location is found and we are in the REPLACE section, each new
* replacement line is appended to the result so that partial updates can be viewed
* incrementally.
*
* 6. Partial Markers:
* - If the final line of the chunk looks like it might be part of a marker but is not one
* of the known markers, it is removed. This prevents incomplete or partial markers
* from corrupting the output.
*
* 7. Finalization:
* - Once all chunks have been processed (when `isFinal` is true), any remaining original
* content after the last replaced section is appended to the result.
* - Trailing newlines are not forcibly added. The code tries to output exactly what is specified.
*
* Errors:
* - If the search block cannot be matched using any of the available matching strategies,
* an error is thrown.
*/
export async function constructNewFileContent(
diffContent: string,
originalContent: string,
isFinal: boolean,
version: "v1" | "v2" = "v1",
): Promise<string> {
const constructor = constructNewFileContentVersionMapping[version]
if (!constructor) {
throw new Error(`Invalid version '${version}' for file content constructor`)
}
return constructor(diffContent, originalContent, isFinal)
}
const constructNewFileContentVersionMapping: Record<
string,
(diffContent: string, originalContent: string, isFinal: boolean) => Promise<string>
> = {
v1: constructNewFileContentV1,
v2: constructNewFileContentV2,
} as const
async function constructNewFileContentV1(diffContent: string, originalContent: string, isFinal: boolean): Promise<string> {
let result = ""
let lastProcessedIndex = 0
let currentSearchContent = ""
let currentReplaceContent = ""
let inSearch = false
let inReplace = false
let searchMatchIndex = -1
let searchEndIndex = -1
// Track all replacements to handle out-of-order edits
let replacements: Array<{ start: number; end: number; content: string }> = []
let pendingOutOfOrderReplacement = false
let lines = diffContent.split("\n")
// If the last line looks like a partial marker but isn't recognized,
// remove it because it might be incomplete.
const lastLine = lines[lines.length - 1]
if (
lines.length > 0 &&
(lastLine.startsWith(SEARCH_BLOCK_CHAR) ||
lastLine.startsWith(LEGACY_SEARCH_BLOCK_CHAR) ||
lastLine.startsWith("=") ||
lastLine.startsWith(REPLACE_BLOCK_CHAR) ||
lastLine.startsWith(LEGACY_REPLACE_BLOCK_CHAR)) &&
!isSearchBlockStart(lastLine) &&
!isSearchBlockEnd(lastLine) &&
!isReplaceBlockEnd(lastLine)
) {
lines.pop()
}
for (const line of lines) {
if (isSearchBlockStart(line)) {
inSearch = true
currentSearchContent = ""
currentReplaceContent = ""
continue
}
if (isSearchBlockEnd(line)) {
inSearch = false
inReplace = true
// Remove trailing linebreak for adding the === marker
// if (currentSearchContent.endsWith("\r\n")) {
// currentSearchContent = currentSearchContent.slice(0, -2)
// } else if (currentSearchContent.endsWith("\n")) {
// currentSearchContent = currentSearchContent.slice(0, -1)
// }
if (!currentSearchContent) {
// Empty search block
if (originalContent.length === 0) {
// New file scenario: nothing to match, just start inserting
searchMatchIndex = 0
searchEndIndex = 0
} else {
// ERROR: Empty search block with non-empty file indicates malformed SEARCH marker
throw new Error(
"Empty SEARCH block detected with non-empty file. This usually indicates a malformed SEARCH marker.\n" +
"Please ensure your SEARCH marker follows the correct format:\n" +
"- Use '------- SEARCH' (7+ dashes + space + SEARCH)\n",
)
}
} else {
// Add check for inefficient full-file search
// if (currentSearchContent.trim() === originalContent.trim()) {
// throw new Error(
// "The SEARCH block contains the entire file content. Please either:\n" +
// "1. Use an empty SEARCH block to replace the entire file, or\n" +
// "2. Make focused changes to specific parts of the file that need modification.",
// )
// }
// Exact search match scenario
const exactIndex = originalContent.indexOf(currentSearchContent, lastProcessedIndex)
if (exactIndex !== -1) {
searchMatchIndex = exactIndex
searchEndIndex = exactIndex + currentSearchContent.length
} else {
// Attempt fallback line-trimmed matching
const lineMatch = lineTrimmedFallbackMatch(originalContent, currentSearchContent, lastProcessedIndex)
if (lineMatch) {
;[searchMatchIndex, searchEndIndex] = lineMatch
} else {
// Try block anchor fallback for larger blocks
const blockMatch = blockAnchorFallbackMatch(originalContent, currentSearchContent, lastProcessedIndex)
if (blockMatch) {
;[searchMatchIndex, searchEndIndex] = blockMatch
} else {
// Last resort: search the entire file from the beginning
const fullFileIndex = originalContent.indexOf(currentSearchContent, 0)
if (fullFileIndex !== -1) {
// Found in the file - could be out of order
searchMatchIndex = fullFileIndex
searchEndIndex = fullFileIndex + currentSearchContent.length
if (searchMatchIndex < lastProcessedIndex) {
pendingOutOfOrderReplacement = true
}
} else {
throw new Error(
`The SEARCH block:\n${currentSearchContent.trimEnd()}\n...does not match anything in the file.`,
)
}
}
}
}
}
// Check if this is an out-of-order replacement
if (searchMatchIndex < lastProcessedIndex) {
pendingOutOfOrderReplacement = true
}
// For in-order replacements, output everything up to the match location
if (!pendingOutOfOrderReplacement) {
result += originalContent.slice(lastProcessedIndex, searchMatchIndex)
}
continue
}
if (isReplaceBlockEnd(line)) {
// Finished one replace block
// Store this replacement
replacements.push({
start: searchMatchIndex,
end: searchEndIndex,
content: currentReplaceContent,
})
// If this was an in-order replacement, advance lastProcessedIndex
if (!pendingOutOfOrderReplacement) {
lastProcessedIndex = searchEndIndex
}
// Reset for next block
inSearch = false
inReplace = false
currentSearchContent = ""
currentReplaceContent = ""
searchMatchIndex = -1
searchEndIndex = -1
pendingOutOfOrderReplacement = false
continue
}
// Accumulate content for search or replace
// (currentReplaceContent is not being used for anything right now since we directly append to result.)
// (We artificially add a linebreak since we split on \n at the beginning. In order to not include a trailing linebreak in the final search/result blocks we need to remove it before using them. This allows for partial line matches to be correctly identified.)
// NOTE: search/replace blocks must be arranged in the order they appear in the file due to how we build the content using lastProcessedIndex. We also cannot strip the trailing newline since for non-partial lines it would remove the linebreak from the original content. (If we remove end linebreak from search, then we'd also have to remove it from replace but we can't know if it's a partial line or not since the model may be using the line break to indicate the end of the block rather than as part of the search content.) We require the model to output full lines in order for our fallbacks to work as well.
if (inSearch) {
currentSearchContent += line + "\n"
} else if (inReplace) {
currentReplaceContent += line + "\n"
// Only output replacement lines immediately for in-order replacements
if (searchMatchIndex !== -1 && !pendingOutOfOrderReplacement) {
result += line + "\n"
}
}
}
// If this is the final chunk, we need to apply all replacements and build the final result
if (isFinal) {
// Handle the case where we're still in replace mode when processing ends
// and this is the final chunk - treat it as if we encountered the REPLACE marker
if (inReplace && searchMatchIndex !== -1) {
// Store this replacement
replacements.push({
start: searchMatchIndex,
end: searchEndIndex,
content: currentReplaceContent,
})
// If this was an in-order replacement, advance lastProcessedIndex
if (!pendingOutOfOrderReplacement) {
lastProcessedIndex = searchEndIndex
}
// Reset state
inSearch = false
inReplace = false
currentSearchContent = ""
currentReplaceContent = ""
searchMatchIndex = -1
searchEndIndex = -1
pendingOutOfOrderReplacement = false
}
// end of handling missing replace marker
// Sort replacements by start position
replacements.sort((a, b) => a.start - b.start)
// Rebuild the entire result by applying all replacements
result = ""
let currentPos = 0
for (const replacement of replacements) {
// Add original content up to this replacement
result += originalContent.slice(currentPos, replacement.start)
// Add the replacement content
result += replacement.content
// Move position to after the replaced section
currentPos = replacement.end
}
// Add any remaining original content
result += originalContent.slice(currentPos)
}
return result
}
enum ProcessingState {
Idle = 0,
StateSearch = 1 << 0,
StateReplace = 1 << 1,
}
class NewFileContentConstructor {
private originalContent: string
private isFinal: boolean
private state: number
private pendingNonStandardLines: string[]
private result: string
private lastProcessedIndex: number
private currentSearchContent: string
private currentReplaceContent: string
private searchMatchIndex: number
private searchEndIndex: number
constructor(originalContent: string, isFinal: boolean) {
this.originalContent = originalContent
this.isFinal = isFinal
this.pendingNonStandardLines = []
this.result = ""
this.lastProcessedIndex = 0
this.state = ProcessingState.Idle
this.currentSearchContent = ""
this.currentReplaceContent = ""
this.searchMatchIndex = -1
this.searchEndIndex = -1
}
private resetForNextBlock() {
// Reset for next block
this.state = ProcessingState.Idle
this.currentSearchContent = ""
this.currentReplaceContent = ""
this.searchMatchIndex = -1
this.searchEndIndex = -1
}
private findLastMatchingLineIndex(regx: RegExp, lineLimit: number) {
for (let i = lineLimit; i > 0; ) {
i--
if (this.pendingNonStandardLines[i].match(regx)) {
return i
}
}
return -1
}
private updateProcessingState(newState: ProcessingState) {
const isValidTransition =
(this.state === ProcessingState.Idle && newState === ProcessingState.StateSearch) ||
(this.state === ProcessingState.StateSearch && newState === ProcessingState.StateReplace)
if (!isValidTransition) {
throw new Error(
`Invalid state transition.\n` +
"Valid transitions are:\n" +
"- Idle → StateSearch\n" +
"- StateSearch → StateReplace",
)
}
this.state |= newState
}
private isStateActive(state: ProcessingState): boolean {
return (this.state & state) === state
}
private activateReplaceState() {
this.updateProcessingState(ProcessingState.StateReplace)
}
private activateSearchState() {
this.updateProcessingState(ProcessingState.StateSearch)
this.currentSearchContent = ""
this.currentReplaceContent = ""
}
private isSearchingActive(): boolean {
return this.isStateActive(ProcessingState.StateSearch)
}
private isReplacingActive(): boolean {
return this.isStateActive(ProcessingState.StateReplace)
}
private hasPendingNonStandardLines(pendingNonStandardLineLimit: number): boolean {
return this.pendingNonStandardLines.length - pendingNonStandardLineLimit < this.pendingNonStandardLines.length
}
public processLine(line: string) {
this.internalProcessLine(line, true, this.pendingNonStandardLines.length)
}
public getResult() {
// If this is the final chunk, append any remaining original content
if (this.isFinal && this.lastProcessedIndex < this.originalContent.length) {
this.result += this.originalContent.slice(this.lastProcessedIndex)
}
if (this.isFinal && this.state !== ProcessingState.Idle) {
throw new Error("File processing incomplete - SEARCH/REPLACE operations still active during finalization")
}
return this.result
}
private internalProcessLine(
line: string,
canWritependingNonStandardLines: boolean,
pendingNonStandardLineLimit: number,
): number {
let removeLineCount = 0
if (isSearchBlockStart(line)) {
removeLineCount = this.trimPendingNonStandardTrailingEmptyLines(pendingNonStandardLineLimit)
if (removeLineCount > 0) {
pendingNonStandardLineLimit = pendingNonStandardLineLimit - removeLineCount
}
if (this.hasPendingNonStandardLines(pendingNonStandardLineLimit)) {
this.tryFixSearchReplaceBlock(pendingNonStandardLineLimit)
canWritependingNonStandardLines && (this.pendingNonStandardLines.length = 0)
}
this.activateSearchState()
} else if (isSearchBlockEnd(line)) {
// 校验非标内容
if (!this.isSearchingActive()) {
this.tryFixSearchBlock(pendingNonStandardLineLimit)
canWritependingNonStandardLines && (this.pendingNonStandardLines.length = 0)
}
this.activateReplaceState()
this.beforeReplace()
} else if (isReplaceBlockEnd(line)) {
if (!this.isReplacingActive()) {
this.tryFixReplaceBlock(pendingNonStandardLineLimit)
canWritependingNonStandardLines && (this.pendingNonStandardLines.length = 0)
}
this.lastProcessedIndex = this.searchEndIndex
this.resetForNextBlock()
} else {
// Accumulate content for search or replace
// (currentReplaceContent is not being used for anything right now since we directly append to result.)
// (We artificially add a linebreak since we split on \n at the beginning. In order to not include a trailing linebreak in the final search/result blocks we need to remove it before using them. This allows for partial line matches to be correctly identified.)
// NOTE: search/replace blocks must be arranged in the order they appear in the file due to how we build the content using lastProcessedIndex. We also cannot strip the trailing newline since for non-partial lines it would remove the linebreak from the original content. (If we remove end linebreak from search, then we'd also have to remove it from replace but we can't know if it's a partial line or not since the model may be using the line break to indicate the end of the block rather than as part of the search content.) We require the model to output full lines in order for our fallbacks to work as well.
if (this.isReplacingActive()) {
this.currentReplaceContent += line + "\n"
// Output replacement lines immediately if we know the insertion point
if (this.searchMatchIndex !== -1) {
this.result += line + "\n"
}
} else if (this.isSearchingActive()) {
this.currentSearchContent += line + "\n"
} else {
let appendToPendingNonStandardLines = canWritependingNonStandardLines
if (appendToPendingNonStandardLines) {
// 处理非标内容
this.pendingNonStandardLines.push(line)
}
}
}
return removeLineCount
}
private beforeReplace() {
// Remove trailing linebreak for adding the === marker
// if (currentSearchContent.endsWith("\r\n")) {
// currentSearchContent = currentSearchContent.slice(0, -2)
// } else if (currentSearchContent.endsWith("\n")) {
// currentSearchContent = currentSearchContent.slice(0, -1)
// }
if (!this.currentSearchContent) {
// Empty search block
if (this.originalContent.length === 0) {
// New file scenario: nothing to match, just start inserting
this.searchMatchIndex = 0
this.searchEndIndex = 0
} else {
// Complete file replacement scenario: treat the entire file as matched
this.searchMatchIndex = 0
this.searchEndIndex = this.originalContent.length
}
} else {
// Add check for inefficient full-file search
// if (currentSearchContent.trim() === originalContent.trim()) {
// throw new Error(
// "The SEARCH block contains the entire file content. Please either:\n" +
// "1. Use an empty SEARCH block to replace the entire file, or\n" +
// "2. Make focused changes to specific parts of the file that need modification.",
// )
// }
// Exact search match scenario
const exactIndex = this.originalContent.indexOf(this.currentSearchContent, this.lastProcessedIndex)
if (exactIndex !== -1) {
this.searchMatchIndex = exactIndex
this.searchEndIndex = exactIndex + this.currentSearchContent.length
} else {
// Attempt fallback line-trimmed matching
const lineMatch = lineTrimmedFallbackMatch(
this.originalContent,
this.currentSearchContent,
this.lastProcessedIndex,
)
if (lineMatch) {
;[this.searchMatchIndex, this.searchEndIndex] = lineMatch
} else {
// Try block anchor fallback for larger blocks
const blockMatch = blockAnchorFallbackMatch(
this.originalContent,
this.currentSearchContent,
this.lastProcessedIndex,
)
if (blockMatch) {
;[this.searchMatchIndex, this.searchEndIndex] = blockMatch
} else {
throw new Error(
`The SEARCH block:\n${this.currentSearchContent.trimEnd()}\n...does not match anything in the file.`,
)
}
}
}
}
if (this.searchMatchIndex < this.lastProcessedIndex) {
throw new Error(
`The SEARCH block:\n${this.currentSearchContent.trimEnd()}\n...matched an incorrect content in the file.`,
)
}
// Output everything up to the match location
this.result += this.originalContent.slice(this.lastProcessedIndex, this.searchMatchIndex)
}
private tryFixSearchBlock(lineLimit: number): number {
let removeLineCount = 0
if (lineLimit < 0) {
lineLimit = this.pendingNonStandardLines.length
}
if (!lineLimit) {
throw new Error("Invalid SEARCH/REPLACE block structure - no lines available to process")
}
let searchTagRegexp = /^([-]{3,}|[<]{3,}) SEARCH$/
const searchTagIndex = this.findLastMatchingLineIndex(searchTagRegexp, lineLimit)
if (searchTagIndex !== -1) {
let fixLines = this.pendingNonStandardLines.slice(searchTagIndex, lineLimit)
fixLines[0] = SEARCH_BLOCK_START
for (const line of fixLines) {
removeLineCount += this.internalProcessLine(line, false, searchTagIndex)
}
} else {
throw new Error(
`Invalid REPLACE marker detected - could not find matching SEARCH block starting from line ${searchTagIndex + 1}`,
)
}
return removeLineCount
}
private tryFixReplaceBlock(lineLimit: number): number {
let removeLineCount = 0
if (lineLimit < 0) {
lineLimit = this.pendingNonStandardLines.length
}
if (!lineLimit) {
throw new Error()
}
let replaceBeginTagRegexp = /^[=]{3,}$/
const replaceBeginTagIndex = this.findLastMatchingLineIndex(replaceBeginTagRegexp, lineLimit)
if (replaceBeginTagIndex !== -1) {
// // 校验非标内容
// if (!this.isSearchingActive()) {
// removeLineCount += this.tryFixSearchBlock(replaceBeginTagIndex)
// }
let fixLines = this.pendingNonStandardLines.slice(replaceBeginTagIndex - removeLineCount, lineLimit - removeLineCount)
fixLines[0] = SEARCH_BLOCK_END
for (const line of fixLines) {
removeLineCount += this.internalProcessLine(line, false, replaceBeginTagIndex - removeLineCount)
}
} else {
throw new Error(`Malformed REPLACE block - missing valid separator after line ${replaceBeginTagIndex + 1}`)
}
return removeLineCount
}
private tryFixSearchReplaceBlock(lineLimit: number): number {
let removeLineCount = 0
if (lineLimit < 0) {
lineLimit = this.pendingNonStandardLines.length
}
if (!lineLimit) {
throw new Error()
}
let replaceEndTagRegexp = /^([+]{3,}|[>]{3,}) REPLACE$/
const replaceEndTagIndex = this.findLastMatchingLineIndex(replaceEndTagRegexp, lineLimit)
const likeReplaceEndTag = replaceEndTagIndex === lineLimit - 1
if (likeReplaceEndTag) {
// // 校验非标内容
// if (!this.isReplacingActive()) {
// removeLineCount += this.tryFixReplaceBlock(replaceEndTagIndex)
// }
let fixLines = this.pendingNonStandardLines.slice(replaceEndTagIndex - removeLineCount, lineLimit - removeLineCount)
fixLines[fixLines.length - 1] = REPLACE_BLOCK_END
for (const line of fixLines) {
removeLineCount += this.internalProcessLine(line, false, replaceEndTagIndex - removeLineCount)
}
} else {
throw new Error("Malformed SEARCH/REPLACE block structure: Missing valid closing REPLACE marker")
}
return removeLineCount
}
/**
* Removes trailing empty lines from the pendingNonStandardLines array
* @param lineLimit - The index to start checking from (exclusive).
* Removes empty lines from lineLimit-1 backwards.
* @returns The number of empty lines removed
*/
private trimPendingNonStandardTrailingEmptyLines(lineLimit: number): number {
let removedCount = 0
let i = Math.min(lineLimit, this.pendingNonStandardLines.length) - 1
while (i >= 0 && this.pendingNonStandardLines[i].trim() === "") {
this.pendingNonStandardLines.pop()
removedCount++
i--
}
return removedCount
}
}
export async function constructNewFileContentV2(diffContent: string, originalContent: string, isFinal: boolean): Promise<string> {
let newFileContentConstructor = new NewFileContentConstructor(originalContent, isFinal)
let lines = diffContent.split("\n")
// If the last line looks like a partial marker but isn't recognized,
// remove it because it might be incomplete.
const lastLine = lines[lines.length - 1]
if (
lines.length > 0 &&
(lastLine.startsWith(SEARCH_BLOCK_CHAR) ||
lastLine.startsWith(LEGACY_SEARCH_BLOCK_CHAR) ||
lastLine.startsWith("=") ||
lastLine.startsWith(REPLACE_BLOCK_CHAR) ||
lastLine.startsWith(LEGACY_REPLACE_BLOCK_CHAR)) &&
lastLine !== SEARCH_BLOCK_START &&
lastLine !== SEARCH_BLOCK_END &&
lastLine !== REPLACE_BLOCK_END
) {
lines.pop()
}
for (const line of lines) {
newFileContentConstructor.processLine(line)
}
let result = newFileContentConstructor.getResult()
return result
}
-2
View File
@@ -33,7 +33,6 @@ export interface TestConfig {
diff_edit_function: string
thinking_tokens_budget: number
replay: boolean
diff_apply_file?: string
}
export interface SystemPromptDetails {
@@ -101,5 +100,4 @@ export interface TestInput {
diffEditFunction: string
thinkingBudgetTokens: number
originalDiffEditToolCallMessage?: string
diffApplyFile?: string
}
+70 -377
View File
@@ -1,12 +1,12 @@
{
"name": "claude-dev",
"version": "3.17.16",
"version": "3.17.15",
"lockfileVersion": 2,
"requires": true,
"packages": {
"": {
"name": "claude-dev",
"version": "3.17.16",
"version": "3.17.15",
"license": "Apache-2.0",
"dependencies": {
"@anthropic-ai/sdk": "^0.37.0",
@@ -109,7 +109,6 @@
"prettier": "^3.3.3",
"protoc-gen-ts": "^0.8.7",
"proxyquire": "^2.1.3",
"rimraf": "^6.0.1",
"should": "^13.2.3",
"sinon": "^19.0.2",
"ts-node": "^10.9.2",
@@ -3702,29 +3701,6 @@
}
}
},
"node_modules/@isaacs/balanced-match": {
"version": "4.0.1",
"resolved": "https://registry.npmjs.org/@isaacs/balanced-match/-/balanced-match-4.0.1.tgz",
"integrity": "sha512-yzMTt9lEb8Gv7zRioUilSglI0c0smZ9k5D65677DLWLtWJaXIS3CqcGyUFByYKlnUj6TkjLVs54fBl6+TiGQDQ==",
"dev": true,
"license": "MIT",
"engines": {
"node": "20 || >=22"
}
},
"node_modules/@isaacs/brace-expansion": {
"version": "5.0.0",
"resolved": "https://registry.npmjs.org/@isaacs/brace-expansion/-/brace-expansion-5.0.0.tgz",
"integrity": "sha512-ZT55BDLV0yv0RBm2czMiZ+SqCGO7AvmOM3G/w2xhVPH+te0aKgFjmBvGlL1dH+ql2tgGO3MVrbb3jCKyvpgnxA==",
"dev": true,
"license": "MIT",
"dependencies": {
"@isaacs/balanced-match": "^4.0.1"
},
"engines": {
"node": "20 || >=22"
}
},
"node_modules/@isaacs/cliui": {
"version": "8.0.2",
"resolved": "https://registry.npmjs.org/@isaacs/cliui/-/cliui-8.0.2.tgz",
@@ -4049,17 +4025,6 @@
"node": ">= 6.0.0"
}
},
"node_modules/@mapbox/node-pre-gyp/node_modules/brace-expansion": {
"version": "1.1.12",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
"integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
"dev": true,
"license": "MIT",
"dependencies": {
"balanced-match": "^1.0.0",
"concat-map": "0.0.1"
}
},
"node_modules/@mapbox/node-pre-gyp/node_modules/detect-libc": {
"version": "2.0.4",
"resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.0.4.tgz",
@@ -4070,28 +4035,6 @@
"node": ">=8"
}
},
"node_modules/@mapbox/node-pre-gyp/node_modules/glob": {
"version": "7.2.3",
"resolved": "https://registry.npmjs.org/glob/-/glob-7.2.3.tgz",
"integrity": "sha512-nFR0zLpU2YCaRxwoCJvL6UvCH2JFyFVIvwTLsIf21AuHlMskA1hhTdk+LlYJtOlYt9v6dvszD2BGRqBL+iQK9Q==",
"deprecated": "Glob versions prior to v9 are no longer supported",
"dev": true,
"license": "ISC",
"dependencies": {
"fs.realpath": "^1.0.0",
"inflight": "^1.0.4",
"inherits": "2",
"minimatch": "^3.1.1",
"once": "^1.3.0",
"path-is-absolute": "^1.0.0"
},
"engines": {
"node": "*"
},
"funding": {
"url": "https://github.com/sponsors/isaacs"
}
},
"node_modules/@mapbox/node-pre-gyp/node_modules/https-proxy-agent": {
"version": "5.0.1",
"resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-5.0.1.tgz",
@@ -4132,36 +4075,6 @@
"semver": "bin/semver.js"
}
},
"node_modules/@mapbox/node-pre-gyp/node_modules/minimatch": {
"version": "3.1.2",
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.2.tgz",
"integrity": "sha512-J7p63hRiAjw1NDEww1W7i37+ByIrOWO5XQQAzZ3VOcL0PNybwpfmV/N05zFAzwQ9USyEcX6t3UO+K5aqBQOIHw==",
"dev": true,
"license": "ISC",
"dependencies": {
"brace-expansion": "^1.1.7"
},
"engines": {
"node": "*"
}
},
"node_modules/@mapbox/node-pre-gyp/node_modules/rimraf": {
"version": "3.0.2",
"resolved": "https://registry.npmjs.org/rimraf/-/rimraf-3.0.2.tgz",
"integrity": "sha512-JZkJMZkAGFFPP2YqXZXPbMlMBgsxzE8ILs4lMIX/2o0L9UBw9O/Y3o6wFw/i9YLapcUJWwqbi3kdxIPdC62TIA==",
"deprecated": "Rimraf versions prior to v4 are no longer supported",
"dev": true,
"license": "ISC",
"dependencies": {
"glob": "^7.1.3"
},
"bin": {
"rimraf": "bin.js"
},
"funding": {
"url": "https://github.com/sponsors/isaacs"
}
},
"node_modules/@mdx-js/mdx": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/@mdx-js/mdx/-/mdx-3.1.0.tgz",
@@ -13256,69 +13169,6 @@
"node": "^10.12.0 || >=12.0.0"
}
},
"node_modules/flat-cache/node_modules/brace-expansion": {
"version": "1.1.12",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
"integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
"dev": true,
"license": "MIT",
"dependencies": {
"balanced-match": "^1.0.0",
"concat-map": "0.0.1"
}
},
"node_modules/flat-cache/node_modules/glob": {
"version": "7.2.3",
"resolved": "https://registry.npmjs.org/glob/-/glob-7.2.3.tgz",
"integrity": "sha512-nFR0zLpU2YCaRxwoCJvL6UvCH2JFyFVIvwTLsIf21AuHlMskA1hhTdk+LlYJtOlYt9v6dvszD2BGRqBL+iQK9Q==",
"deprecated": "Glob versions prior to v9 are no longer supported",
"dev": true,
"license": "ISC",
"dependencies": {
"fs.realpath": "^1.0.0",
"inflight": "^1.0.4",
"inherits": "2",
"minimatch": "^3.1.1",
"once": "^1.3.0",
"path-is-absolute": "^1.0.0"
},
"engines": {
"node": "*"
},
"funding": {
"url": "https://github.com/sponsors/isaacs"
}
},
"node_modules/flat-cache/node_modules/minimatch": {
"version": "3.1.2",
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.2.tgz",
"integrity": "sha512-J7p63hRiAjw1NDEww1W7i37+ByIrOWO5XQQAzZ3VOcL0PNybwpfmV/N05zFAzwQ9USyEcX6t3UO+K5aqBQOIHw==",
"dev": true,
"license": "ISC",
"dependencies": {
"brace-expansion": "^1.1.7"
},
"engines": {
"node": "*"
}
},
"node_modules/flat-cache/node_modules/rimraf": {
"version": "3.0.2",
"resolved": "https://registry.npmjs.org/rimraf/-/rimraf-3.0.2.tgz",
"integrity": "sha512-JZkJMZkAGFFPP2YqXZXPbMlMBgsxzE8ILs4lMIX/2o0L9UBw9O/Y3o6wFw/i9YLapcUJWwqbi3kdxIPdC62TIA==",
"deprecated": "Rimraf versions prior to v4 are no longer supported",
"dev": true,
"license": "ISC",
"dependencies": {
"glob": "^7.1.3"
},
"bin": {
"rimraf": "bin.js"
},
"funding": {
"url": "https://github.com/sponsors/isaacs"
}
},
"node_modules/flatted": {
"version": "3.3.1",
"resolved": "https://registry.npmjs.org/flatted/-/flatted-3.3.1.tgz",
@@ -13356,12 +13206,12 @@
}
},
"node_modules/foreground-child": {
"version": "3.3.1",
"resolved": "https://registry.npmjs.org/foreground-child/-/foreground-child-3.3.1.tgz",
"integrity": "sha512-gIXjKqtFuWEgzFRJA9WCQeSJLZDjgJUOMCMzxtvFq/37KojM1BFGufqsCy0r4qSQmYLsZYMeyRqzIWOMup03sw==",
"version": "3.2.1",
"resolved": "https://registry.npmjs.org/foreground-child/-/foreground-child-3.2.1.tgz",
"integrity": "sha512-PXUUyLqrR2XCWICfv6ukppP96sdFwWbNEnfEMt7jNsISjMsvaLNinAHNDYyvkyU+SZG2BTSbT5NjG+vZslfGTA==",
"license": "ISC",
"dependencies": {
"cross-spawn": "^7.0.6",
"cross-spawn": "^7.0.0",
"signal-exit": "^4.0.1"
},
"engines": {
@@ -20928,106 +20778,66 @@
"license": "MIT"
},
"node_modules/rimraf": {
"version": "6.0.1",
"resolved": "https://registry.npmjs.org/rimraf/-/rimraf-6.0.1.tgz",
"integrity": "sha512-9dkvaxAsk/xNXSJzMgFqqMCuFgt2+KsOFek3TMLfo8NCPfWpBmqwyNn5Y+NX56QUYfCtsyhF3ayiboEoUmJk/A==",
"version": "3.0.2",
"resolved": "https://registry.npmjs.org/rimraf/-/rimraf-3.0.2.tgz",
"integrity": "sha512-JZkJMZkAGFFPP2YqXZXPbMlMBgsxzE8ILs4lMIX/2o0L9UBw9O/Y3o6wFw/i9YLapcUJWwqbi3kdxIPdC62TIA==",
"deprecated": "Rimraf versions prior to v4 are no longer supported",
"dev": true,
"license": "ISC",
"dependencies": {
"glob": "^11.0.0",
"package-json-from-dist": "^1.0.0"
"glob": "^7.1.3"
},
"bin": {
"rimraf": "dist/esm/bin.mjs"
},
"engines": {
"node": "20 || >=22"
"rimraf": "bin.js"
},
"funding": {
"url": "https://github.com/sponsors/isaacs"
}
},
"node_modules/rimraf/node_modules/brace-expansion": {
"version": "1.1.11",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
"integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
"dev": true,
"license": "MIT",
"dependencies": {
"balanced-match": "^1.0.0",
"concat-map": "0.0.1"
}
},
"node_modules/rimraf/node_modules/glob": {
"version": "11.0.3",
"resolved": "https://registry.npmjs.org/glob/-/glob-11.0.3.tgz",
"integrity": "sha512-2Nim7dha1KVkaiF4q6Dj+ngPPMdfvLJEOpZk/jKiUAkqKebpGAWQXAq9z1xu9HKu5lWfqw/FASuccEjyznjPaA==",
"version": "7.2.3",
"resolved": "https://registry.npmjs.org/glob/-/glob-7.2.3.tgz",
"integrity": "sha512-nFR0zLpU2YCaRxwoCJvL6UvCH2JFyFVIvwTLsIf21AuHlMskA1hhTdk+LlYJtOlYt9v6dvszD2BGRqBL+iQK9Q==",
"deprecated": "Glob versions prior to v9 are no longer supported",
"dev": true,
"license": "ISC",
"dependencies": {
"foreground-child": "^3.3.1",
"jackspeak": "^4.1.1",
"minimatch": "^10.0.3",
"minipass": "^7.1.2",
"package-json-from-dist": "^1.0.0",
"path-scurry": "^2.0.0"
},
"bin": {
"glob": "dist/esm/bin.mjs"
"fs.realpath": "^1.0.0",
"inflight": "^1.0.4",
"inherits": "2",
"minimatch": "^3.1.1",
"once": "^1.3.0",
"path-is-absolute": "^1.0.0"
},
"engines": {
"node": "20 || >=22"
"node": "*"
},
"funding": {
"url": "https://github.com/sponsors/isaacs"
}
},
"node_modules/rimraf/node_modules/jackspeak": {
"version": "4.1.1",
"resolved": "https://registry.npmjs.org/jackspeak/-/jackspeak-4.1.1.tgz",
"integrity": "sha512-zptv57P3GpL+O0I7VdMJNBZCu+BPHVQUk55Ft8/QCJjTVxrnJHuVuX/0Bl2A6/+2oyR/ZMEuFKwmzqqZ/U5nPQ==",
"dev": true,
"license": "BlueOak-1.0.0",
"dependencies": {
"@isaacs/cliui": "^8.0.2"
},
"engines": {
"node": "20 || >=22"
},
"funding": {
"url": "https://github.com/sponsors/isaacs"
}
},
"node_modules/rimraf/node_modules/lru-cache": {
"version": "11.1.0",
"resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-11.1.0.tgz",
"integrity": "sha512-QIXZUBJUx+2zHUdQujWejBkcD9+cs94tLn0+YL8UrCh+D5sCXZ4c7LaEH48pNwRY3MLDgqUFyhlCyjJPf1WP0A==",
"dev": true,
"license": "ISC",
"engines": {
"node": "20 || >=22"
}
},
"node_modules/rimraf/node_modules/minimatch": {
"version": "10.0.3",
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-10.0.3.tgz",
"integrity": "sha512-IPZ167aShDZZUMdRk66cyQAW3qr0WzbHkPdMYa8bzZhlHhO3jALbKdxcaak7W9FfT2rZNpQuUu4Od7ILEpXSaw==",
"version": "3.1.2",
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.2.tgz",
"integrity": "sha512-J7p63hRiAjw1NDEww1W7i37+ByIrOWO5XQQAzZ3VOcL0PNybwpfmV/N05zFAzwQ9USyEcX6t3UO+K5aqBQOIHw==",
"dev": true,
"license": "ISC",
"dependencies": {
"@isaacs/brace-expansion": "^5.0.0"
"brace-expansion": "^1.1.7"
},
"engines": {
"node": "20 || >=22"
},
"funding": {
"url": "https://github.com/sponsors/isaacs"
}
},
"node_modules/rimraf/node_modules/path-scurry": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/path-scurry/-/path-scurry-2.0.0.tgz",
"integrity": "sha512-ypGJsmGtdXUOeM5u93TyeIEfEhM6s+ljAhrk5vAvSx8uyY/02OvrZnA0YNGUrPXfpJMgI1ODd3nwz8Npx4O4cg==",
"dev": true,
"license": "BlueOak-1.0.0",
"dependencies": {
"lru-cache": "^11.0.0",
"minipass": "^7.1.2"
},
"engines": {
"node": "20 || >=22"
},
"funding": {
"url": "https://github.com/sponsors/isaacs"
"node": "*"
}
},
"node_modules/router": {
@@ -26860,21 +26670,6 @@
"dev": true,
"requires": {}
},
"@isaacs/balanced-match": {
"version": "4.0.1",
"resolved": "https://registry.npmjs.org/@isaacs/balanced-match/-/balanced-match-4.0.1.tgz",
"integrity": "sha512-yzMTt9lEb8Gv7zRioUilSglI0c0smZ9k5D65677DLWLtWJaXIS3CqcGyUFByYKlnUj6TkjLVs54fBl6+TiGQDQ==",
"dev": true
},
"@isaacs/brace-expansion": {
"version": "5.0.0",
"resolved": "https://registry.npmjs.org/@isaacs/brace-expansion/-/brace-expansion-5.0.0.tgz",
"integrity": "sha512-ZT55BDLV0yv0RBm2czMiZ+SqCGO7AvmOM3G/w2xhVPH+te0aKgFjmBvGlL1dH+ql2tgGO3MVrbb3jCKyvpgnxA==",
"dev": true,
"requires": {
"@isaacs/balanced-match": "^4.0.1"
}
},
"@isaacs/cliui": {
"version": "8.0.2",
"resolved": "https://registry.npmjs.org/@isaacs/cliui/-/cliui-8.0.2.tgz",
@@ -27114,36 +26909,12 @@
"debug": "4"
}
},
"brace-expansion": {
"version": "1.1.12",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
"integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
"dev": true,
"requires": {
"balanced-match": "^1.0.0",
"concat-map": "0.0.1"
}
},
"detect-libc": {
"version": "2.0.4",
"resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.0.4.tgz",
"integrity": "sha512-3UDv+G9CsCKO1WKMGw9fwq/SWJYbI0c5Y7LU1AXYoDdbhE2AHQ6N6Nb34sG8Fj7T5APy8qXDCKuuIHd1BR0tVA==",
"dev": true
},
"glob": {
"version": "7.2.3",
"resolved": "https://registry.npmjs.org/glob/-/glob-7.2.3.tgz",
"integrity": "sha512-nFR0zLpU2YCaRxwoCJvL6UvCH2JFyFVIvwTLsIf21AuHlMskA1hhTdk+LlYJtOlYt9v6dvszD2BGRqBL+iQK9Q==",
"dev": true,
"requires": {
"fs.realpath": "^1.0.0",
"inflight": "^1.0.4",
"inherits": "2",
"minimatch": "^3.1.1",
"once": "^1.3.0",
"path-is-absolute": "^1.0.0"
}
},
"https-proxy-agent": {
"version": "5.0.1",
"resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-5.0.1.tgz",
@@ -27170,24 +26941,6 @@
"dev": true
}
}
},
"minimatch": {
"version": "3.1.2",
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.2.tgz",
"integrity": "sha512-J7p63hRiAjw1NDEww1W7i37+ByIrOWO5XQQAzZ3VOcL0PNybwpfmV/N05zFAzwQ9USyEcX6t3UO+K5aqBQOIHw==",
"dev": true,
"requires": {
"brace-expansion": "^1.1.7"
}
},
"rimraf": {
"version": "3.0.2",
"resolved": "https://registry.npmjs.org/rimraf/-/rimraf-3.0.2.tgz",
"integrity": "sha512-JZkJMZkAGFFPP2YqXZXPbMlMBgsxzE8ILs4lMIX/2o0L9UBw9O/Y3o6wFw/i9YLapcUJWwqbi3kdxIPdC62TIA==",
"dev": true,
"requires": {
"glob": "^7.1.3"
}
}
}
},
@@ -33687,50 +33440,6 @@
"flatted": "^3.2.9",
"keyv": "^4.5.3",
"rimraf": "^3.0.2"
},
"dependencies": {
"brace-expansion": {
"version": "1.1.12",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
"integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
"dev": true,
"requires": {
"balanced-match": "^1.0.0",
"concat-map": "0.0.1"
}
},
"glob": {
"version": "7.2.3",
"resolved": "https://registry.npmjs.org/glob/-/glob-7.2.3.tgz",
"integrity": "sha512-nFR0zLpU2YCaRxwoCJvL6UvCH2JFyFVIvwTLsIf21AuHlMskA1hhTdk+LlYJtOlYt9v6dvszD2BGRqBL+iQK9Q==",
"dev": true,
"requires": {
"fs.realpath": "^1.0.0",
"inflight": "^1.0.4",
"inherits": "2",
"minimatch": "^3.1.1",
"once": "^1.3.0",
"path-is-absolute": "^1.0.0"
}
},
"minimatch": {
"version": "3.1.2",
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.2.tgz",
"integrity": "sha512-J7p63hRiAjw1NDEww1W7i37+ByIrOWO5XQQAzZ3VOcL0PNybwpfmV/N05zFAzwQ9USyEcX6t3UO+K5aqBQOIHw==",
"dev": true,
"requires": {
"brace-expansion": "^1.1.7"
}
},
"rimraf": {
"version": "3.0.2",
"resolved": "https://registry.npmjs.org/rimraf/-/rimraf-3.0.2.tgz",
"integrity": "sha512-JZkJMZkAGFFPP2YqXZXPbMlMBgsxzE8ILs4lMIX/2o0L9UBw9O/Y3o6wFw/i9YLapcUJWwqbi3kdxIPdC62TIA==",
"dev": true,
"requires": {
"glob": "^7.1.3"
}
}
}
},
"flatted": {
@@ -33754,11 +33463,11 @@
}
},
"foreground-child": {
"version": "3.3.1",
"resolved": "https://registry.npmjs.org/foreground-child/-/foreground-child-3.3.1.tgz",
"integrity": "sha512-gIXjKqtFuWEgzFRJA9WCQeSJLZDjgJUOMCMzxtvFq/37KojM1BFGufqsCy0r4qSQmYLsZYMeyRqzIWOMup03sw==",
"version": "3.2.1",
"resolved": "https://registry.npmjs.org/foreground-child/-/foreground-child-3.2.1.tgz",
"integrity": "sha512-PXUUyLqrR2XCWICfv6ukppP96sdFwWbNEnfEMt7jNsISjMsvaLNinAHNDYyvkyU+SZG2BTSbT5NjG+vZslfGTA==",
"requires": {
"cross-spawn": "^7.0.6",
"cross-spawn": "^7.0.0",
"signal-exit": "^4.0.1"
}
},
@@ -38914,61 +38623,45 @@
"dev": true
},
"rimraf": {
"version": "6.0.1",
"resolved": "https://registry.npmjs.org/rimraf/-/rimraf-6.0.1.tgz",
"integrity": "sha512-9dkvaxAsk/xNXSJzMgFqqMCuFgt2+KsOFek3TMLfo8NCPfWpBmqwyNn5Y+NX56QUYfCtsyhF3ayiboEoUmJk/A==",
"version": "3.0.2",
"resolved": "https://registry.npmjs.org/rimraf/-/rimraf-3.0.2.tgz",
"integrity": "sha512-JZkJMZkAGFFPP2YqXZXPbMlMBgsxzE8ILs4lMIX/2o0L9UBw9O/Y3o6wFw/i9YLapcUJWwqbi3kdxIPdC62TIA==",
"dev": true,
"requires": {
"glob": "^11.0.0",
"package-json-from-dist": "^1.0.0"
"glob": "^7.1.3"
},
"dependencies": {
"brace-expansion": {
"version": "1.1.11",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
"integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
"dev": true,
"requires": {
"balanced-match": "^1.0.0",
"concat-map": "0.0.1"
}
},
"glob": {
"version": "11.0.3",
"resolved": "https://registry.npmjs.org/glob/-/glob-11.0.3.tgz",
"integrity": "sha512-2Nim7dha1KVkaiF4q6Dj+ngPPMdfvLJEOpZk/jKiUAkqKebpGAWQXAq9z1xu9HKu5lWfqw/FASuccEjyznjPaA==",
"version": "7.2.3",
"resolved": "https://registry.npmjs.org/glob/-/glob-7.2.3.tgz",
"integrity": "sha512-nFR0zLpU2YCaRxwoCJvL6UvCH2JFyFVIvwTLsIf21AuHlMskA1hhTdk+LlYJtOlYt9v6dvszD2BGRqBL+iQK9Q==",
"dev": true,
"requires": {
"foreground-child": "^3.3.1",
"jackspeak": "^4.1.1",
"minimatch": "^10.0.3",
"minipass": "^7.1.2",
"package-json-from-dist": "^1.0.0",
"path-scurry": "^2.0.0"
"fs.realpath": "^1.0.0",
"inflight": "^1.0.4",
"inherits": "2",
"minimatch": "^3.1.1",
"once": "^1.3.0",
"path-is-absolute": "^1.0.0"
}
},
"jackspeak": {
"version": "4.1.1",
"resolved": "https://registry.npmjs.org/jackspeak/-/jackspeak-4.1.1.tgz",
"integrity": "sha512-zptv57P3GpL+O0I7VdMJNBZCu+BPHVQUk55Ft8/QCJjTVxrnJHuVuX/0Bl2A6/+2oyR/ZMEuFKwmzqqZ/U5nPQ==",
"dev": true,
"requires": {
"@isaacs/cliui": "^8.0.2"
}
},
"lru-cache": {
"version": "11.1.0",
"resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-11.1.0.tgz",
"integrity": "sha512-QIXZUBJUx+2zHUdQujWejBkcD9+cs94tLn0+YL8UrCh+D5sCXZ4c7LaEH48pNwRY3MLDgqUFyhlCyjJPf1WP0A==",
"dev": true
},
"minimatch": {
"version": "10.0.3",
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-10.0.3.tgz",
"integrity": "sha512-IPZ167aShDZZUMdRk66cyQAW3qr0WzbHkPdMYa8bzZhlHhO3jALbKdxcaak7W9FfT2rZNpQuUu4Od7ILEpXSaw==",
"version": "3.1.2",
"resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.2.tgz",
"integrity": "sha512-J7p63hRiAjw1NDEww1W7i37+ByIrOWO5XQQAzZ3VOcL0PNybwpfmV/N05zFAzwQ9USyEcX6t3UO+K5aqBQOIHw==",
"dev": true,
"requires": {
"@isaacs/brace-expansion": "^5.0.0"
}
},
"path-scurry": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/path-scurry/-/path-scurry-2.0.0.tgz",
"integrity": "sha512-ypGJsmGtdXUOeM5u93TyeIEfEhM6s+ljAhrk5vAvSx8uyY/02OvrZnA0YNGUrPXfpJMgI1ODd3nwz8Npx4O4cg==",
"dev": true,
"requires": {
"lru-cache": "^11.0.0",
"minipass": "^7.1.2"
"brace-expansion": "^1.1.7"
}
}
}
+1 -3
View File
@@ -2,7 +2,7 @@
"name": "claude-dev",
"displayName": "Cline",
"description": "Autonomous coding agent right in your IDE, capable of creating/editing files, running commands, using the browser, and more with your permission every step of the way.",
"version": "3.17.16",
"version": "3.17.15",
"icon": "assets/icons/icon.png",
"engines": {
"vscode": "^1.84.0"
@@ -332,7 +332,6 @@
"package": "npm run check-types && npm run build:webview && npm run lint && node esbuild.js --production",
"protos": "node proto/build-proto.js && node scripts/generate-server-setup.mjs && node scripts/generate-host-bridge-client.mjs",
"postprotos": "prettier src/shared/proto src/core/controller src/hosts/ webview-ui/src/services src/generated --write --log-level warn",
"clean": "rimraf dist dist-standalone webview-ui/build src/generated",
"compile-tests": "node ./scripts/build-tests.js",
"watch-tests": "tsc -p . -w --outDir out",
"pretest": "npm run compile-tests && npm run compile && npm run compile-standalone && npm run lint",
@@ -397,7 +396,6 @@
"prettier": "^3.3.3",
"protoc-gen-ts": "^0.8.7",
"proxyquire": "^2.1.3",
"rimraf": "^6.0.1",
"should": "^13.2.3",
"sinon": "^19.0.2",
"ts-node": "^10.9.2",
-7
View File
@@ -35,8 +35,6 @@ service TaskService {
rpc taskCompletionViewChanges(Int64Request) returns (Empty);
// Executes a quick win task with command and title
rpc executeQuickWin(ExecuteQuickWinRequest) returns (Empty);
// Deletes all task history
rpc deleteAllTaskHistory(BooleanRequest) returns (DeleteAllTaskHistoryCount);
}
// Request message for creating a new task
@@ -118,8 +116,3 @@ message ExecuteQuickWinRequest {
string command = 2;
string title = 3;
}
// Results returned when deleting all task history
message DeleteAllTaskHistoryCount {
int32 tasks_deleted = 1;
}
+1 -2
View File
@@ -13,8 +13,7 @@ grep -Ev '//.*vscode' | # remove commented out code
sed 's|.*vscode\.|vscode.|'| # remove everything before vscode.
sed 's/[^a-zA-Z0-9_.].*$//' | # remove everything after last identifier
grep -E '\.[a-z][^.]+$' | # remove types (last part of identifier should be lowercase)
sort | uniq -c | sort -n | # Count occurrences
cat > $SDK_DEST
sort | uniq > $SDK_DEST
}
echo Wrote uses of the vscode SDK to $(realpath $SDK_DEST)
+77 -62
View File
@@ -4,7 +4,7 @@ import { type ApiHandler } from ".."
import { ApiStreamUsageChunk, type ApiStream } from "../transform/stream"
import { withRetry } from "../retry"
import { runClaudeCode } from "@/integrations/claude-code/run"
import { filterMessagesForClaudeCode } from "@/integrations/claude-code/message-filter"
import { ClaudeCodeMessage } from "@/integrations/claude-code/types"
export class ClaudeCodeHandler implements ApiHandler {
private options: ApiHandlerOptions
@@ -19,16 +19,39 @@ export class ClaudeCodeHandler implements ApiHandler {
maxDelay: 15000,
})
async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
// Filter out image blocks since Claude Code doesn't support them
const filteredMessages = filterMessagesForClaudeCode(messages)
const claudeProcess = runClaudeCode({
systemPrompt,
messages: filteredMessages,
messages,
path: this.options.claudeCodePath,
modelId: this.getModel().id,
})
const dataQueue: string[] = []
let processError = null
let errorOutput = ""
let exitCode: number | null = null
claudeProcess.stdout.on("data", (data) => {
const output = data.toString()
const lines = output.split("\n").filter((line: string) => line.trim() !== "")
for (const line of lines) {
dataQueue.push(line)
}
})
claudeProcess.stderr.on("data", (data) => {
errorOutput += data.toString()
})
claudeProcess.on("close", (code) => {
exitCode = code
})
claudeProcess.on("error", (error) => {
processError = error
})
// Usage is included with assistant messages,
// but cost is included in the result chunk
let usage: ApiStreamUsageChunk = {
@@ -39,75 +62,61 @@ export class ClaudeCodeHandler implements ApiHandler {
cacheWriteTokens: 0,
}
let isPaidUsage = true
while (exitCode !== 0 || dataQueue.length > 0) {
if (dataQueue.length === 0) {
await new Promise((resolve) => setImmediate(resolve))
}
for await (const chunk of claudeProcess) {
if (typeof chunk === "string") {
if (exitCode !== null && exitCode !== 0) {
throw new Error(
`Claude Code process exited with code ${exitCode}.${errorOutput ? ` Error output: ${errorOutput.trim()}` : ""}`,
)
}
const data = dataQueue.shift()
if (!data) {
continue
}
const chunk = this.attemptParseChunk(data)
if (!chunk) {
yield {
type: "text",
text: chunk,
text: data || "",
}
continue
}
if (chunk.type === "system" && chunk.subtype === "init") {
// Based on my tests, subscription usage sets the `apiKeySource` to "none"
isPaidUsage = chunk.apiKeySource !== "none"
continue
}
if (chunk.type === "assistant" && "message" in chunk) {
const message = chunk.message
if (message.stop_reason !== null) {
const content = "text" in message.content[0] ? message.content[0] : undefined
if (message.stop_reason !== null && message.stop_reason !== "tool_use") {
const errorMessage = message.content[0]?.text || `Claude Code stopped with reason: ${message.stop_reason}`
const isError = content && content.text.startsWith(`API Error`)
if (isError) {
// Error messages are formatted as: `API Error: <<status code>> <<json>>`
const errorMessageStart = content.text.indexOf("{")
const errorMessage = content.text.slice(errorMessageStart)
const error = this.attemptParse(errorMessage)
if (!error) {
throw new Error(content.text)
}
if (error.error.message.includes("Invalid model name")) {
throw new Error(
content.text +
`\n\nAPI keys and subscription plans allow different models. Make sure the selected model is included in your plan.`,
)
}
throw new Error(errorMessage)
if (errorMessage.includes("Invalid model name")) {
throw new Error(
errorMessage +
`\n\nAPI keys and subscription plans allow different models. Make sure the selected model is included in your plan.`,
)
}
throw new Error(errorMessage)
}
for (const content of message.content) {
switch (content.type) {
case "text":
yield {
type: "text",
text: content.text,
}
break
case "thinking":
yield {
type: "reasoning",
reasoning: content.thinking || "",
}
break
case "redacted_thinking":
yield {
type: "reasoning",
reasoning: "[Redacted thinking block]",
}
break
case "tool_use":
console.error(`tool_use is not supported yet. Received: ${JSON.stringify(content)}`)
break
if (content.type === "text") {
yield {
type: "text",
text: content.text,
}
} else {
console.warn("Unsupported content type:", content.type)
}
}
@@ -120,18 +129,14 @@ export class ClaudeCodeHandler implements ApiHandler {
}
if (chunk.type === "result" && "result" in chunk) {
usage.totalCost = isPaidUsage ? chunk.total_cost_usd : 0
usage.totalCost = chunk.cost_usd || 0
yield usage
}
}
}
private attemptParse(str: string) {
try {
return JSON.parse(str)
} catch (err) {
return null
if (processError) {
throw processError
}
}
}
@@ -147,4 +152,14 @@ export class ClaudeCodeHandler implements ApiHandler {
info: claudeCodeModels[claudeCodeDefaultModelId],
}
}
// TOOD: Validate instead of parsing
private attemptParseChunk(data: string): ClaudeCodeMessage | null {
try {
return JSON.parse(data)
} catch (error) {
console.error("Error parsing chunk:", error)
return null
}
}
}
+129 -25
View File
@@ -16,7 +16,7 @@ import { McpHub } from "@services/mcp/McpHub"
import { telemetryService } from "@/services/posthog/telemetry/TelemetryService"
import { ApiProvider, ModelInfo } from "@shared/api"
import { ChatContent } from "@shared/ChatContent"
import { ChatSettings, StoredChatSettings } from "@shared/ChatSettings"
import { ChatSettings } from "@shared/ChatSettings"
import { ExtensionMessage, ExtensionState, Platform } from "@shared/ExtensionMessage"
import { HistoryItem } from "@shared/HistoryItem"
import { McpMarketplaceCatalog } from "@shared/mcp"
@@ -44,8 +44,6 @@ import { sendAddToInputEvent } from "./ui/subscribeToAddToInput"
import { sendAuthCallbackEvent } from "./account/subscribeToAuthCallback"
import { sendMcpMarketplaceCatalogEvent } from "./mcp/subscribeToMcpMarketplaceCatalog"
import { sendRelinquishControlEvent } from "./ui/subscribeToRelinquishControl"
import { handleTaskServiceRequest } from "./task"
import { BooleanRequest } from "@shared/proto/common"
/*
https://github.com/microsoft/vscode-webview-ui-toolkit-samples/blob/main/default/weather-webview/src/providers/WeatherViewProvider.ts
@@ -58,7 +56,6 @@ export class Controller {
private postMessage: (message: ExtensionMessage) => Thenable<boolean> | undefined
private disposables: vscode.Disposable[] = []
private mode: "plan" | "act" = "plan" // In-memory plan/act mode state
task?: Task
workspaceTracker: WorkspaceTracker
mcpHub: McpHub
@@ -138,7 +135,7 @@ export class Controller {
apiConfiguration,
autoApprovalSettings,
browserSettings,
chatSettings: storedChatSettings,
chatSettings,
shellIntegrationTimeout,
terminalReuseEnabled,
terminalOutputLineLimit,
@@ -148,12 +145,6 @@ export class Controller {
taskHistory,
} = await getAllExtensionState(this.context)
// Reconstruct ChatSettings with in-memory mode and stored preferences
const chatSettings: ChatSettings = {
...storedChatSettings, // Spread stored preferences (preferredLanguage, openAIReasoningEffort)
mode: this.mode, // Use in-memory mode (override any stored mode)
}
const NEW_USER_TASK_COUNT_THRESHOLD = 10
// Check if the user has completed enough tasks to no longer be considered a "new user"
@@ -227,6 +218,26 @@ export class Controller {
await this.postStateToWebview()
break
}
case "clearAllTaskHistory": {
const answer = await vscode.window.showWarningMessage(
"What would you like to delete?",
{ modal: true },
"Delete All Except Favorites",
"Delete Everything",
"Cancel",
)
if (answer === "Delete All Except Favorites") {
await this.deleteNonFavoriteTaskHistory()
await this.postStateToWebview()
} else if (answer === "Delete Everything") {
await this.deleteAllTaskHistory()
await this.postStateToWebview()
}
sendRelinquishControlEvent()
break
}
case "grpc_request": {
if (message.grpc_request) {
await handleGrpcRequest(this, message.grpc_request)
@@ -254,9 +265,6 @@ export class Controller {
async togglePlanActModeWithChatSettings(chatSettings: ChatSettings, chatContent?: ChatContent): Promise<boolean> {
const didSwitchToActMode = chatSettings.mode === "act"
// Store mode in-memory only
this.mode = chatSettings.mode
// Capture mode switch telemetry | Capture regardless of if we know the taskId
telemetryService.captureModeSwitch(this.task?.taskId ?? "0", chatSettings.mode)
@@ -426,9 +434,7 @@ export class Controller {
}
}
// Save only non-mode properties to workspace storage
const { mode, ...persistentChatSettings }: { mode: string } & StoredChatSettings = chatSettings
await updateWorkspaceState(this.context, "chatSettings", persistentChatSettings)
await updateWorkspaceState(this.context, "chatSettings", chatSettings)
await this.postStateToWebview()
if (this.task) {
@@ -824,6 +830,110 @@ export class Controller {
await downloadTask(historyItem.ts, apiConversationHistory)
}
async deleteAllTaskHistory() {
await this.clearTask()
await updateGlobalState(this.context, "taskHistory", undefined)
try {
// Remove all contents of tasks directory
const taskDirPath = path.join(this.context.globalStorageUri.fsPath, "tasks")
if (await fileExistsAtPath(taskDirPath)) {
await fs.rm(taskDirPath, { recursive: true, force: true })
}
// Remove checkpoints directory contents
const checkpointsDirPath = path.join(this.context.globalStorageUri.fsPath, "checkpoints")
if (await fileExistsAtPath(checkpointsDirPath)) {
await fs.rm(checkpointsDirPath, { recursive: true, force: true })
}
} catch (error) {
vscode.window.showErrorMessage(
`Encountered error while deleting task history, there may be some files left behind. Error: ${error instanceof Error ? error.message : String(error)}`,
)
}
// await this.postStateToWebview()
}
async deleteNonFavoriteTaskHistory() {
await this.clearTask()
const taskHistory = ((await getGlobalState(this.context, "taskHistory")) as HistoryItem[]) || []
const favoritedTasks = taskHistory.filter((task) => task.isFavorited === true)
// If user has no favorited tasks, show a warning message
if (favoritedTasks.length === 0) {
vscode.window.showWarningMessage("No favorited tasks found. Please favorite tasks before using this option.")
await this.postStateToWebview()
return
}
await updateGlobalState(this.context, "taskHistory", favoritedTasks)
// Delete non-favorited task directories
try {
const preserveTaskIds = favoritedTasks.map((task) => task.id)
const taskDirPath = path.join(this.context.globalStorageUri.fsPath, "tasks")
if (await fileExistsAtPath(taskDirPath)) {
const taskDirs = await fs.readdir(taskDirPath)
for (const taskDir of taskDirs) {
if (!preserveTaskIds.includes(taskDir)) {
await fs.rm(path.join(taskDirPath, taskDir), { recursive: true, force: true })
}
}
}
} catch (error) {
vscode.window.showErrorMessage(
`Error deleting task history: ${error instanceof Error ? error.message : String(error)}`,
)
}
await this.postStateToWebview()
}
async deleteTaskWithId(id: string) {
console.info("deleteTaskWithId: ", id)
try {
if (id === this.task?.taskId) {
await this.clearTask()
console.debug("cleared task")
}
const {
taskDirPath,
apiConversationHistoryFilePath,
uiMessagesFilePath,
contextHistoryFilePath,
taskMetadataFilePath,
} = await this.getTaskWithId(id)
const legacyMessagesFilePath = path.join(taskDirPath, "claude_messages.json")
const updatedTaskHistory = await this.deleteTaskFromState(id)
// Delete the task files
for (const filePath of [
apiConversationHistoryFilePath,
uiMessagesFilePath,
contextHistoryFilePath,
taskMetadataFilePath,
legacyMessagesFilePath,
]) {
const fileExists = await fileExistsAtPath(filePath)
if (fileExists) {
await fs.unlink(filePath)
}
}
await fs.rmdir(taskDirPath) // succeeds if the dir is empty
if (updatedTaskHistory.length === 0) {
await this.deleteAllTaskHistory()
}
} catch (error) {
console.debug(`Error deleting task:`, error)
}
await this.postStateToWebview()
}
async deleteTaskFromState(id: string) {
// Remove the task from history
const taskHistory = ((await getGlobalState(this.context, "taskHistory")) as HistoryItem[] | undefined) || []
@@ -838,7 +948,7 @@ export class Controller {
async postStateToWebview() {
const state = await this.getStateToPostToWebview()
await sendStateUpdate(this.id, state)
await sendStateUpdate(state)
}
async getStateToPostToWebview(): Promise<ExtensionState> {
@@ -848,7 +958,7 @@ export class Controller {
taskHistory,
autoApprovalSettings,
browserSettings,
chatSettings: storedChatSettings,
chatSettings,
userInfo,
mcpMarketplaceEnabled,
mcpRichDisplayEnabled,
@@ -865,12 +975,6 @@ export class Controller {
terminalOutputLineLimit,
} = await getAllExtensionState(this.context)
// Reconstruct ChatSettings with in-memory mode and stored preferences
const chatSettings: ChatSettings = {
...storedChatSettings, // Spread stored preferences (preferredLanguage, openAIReasoningEffort)
mode: this.mode, // Use in-memory mode (override any stored mode)
}
const localClineRulesToggles =
((await getWorkspaceState(this.context, "localClineRulesToggles")) as ClineRulesToggles) || {}
+29 -32
View File
@@ -3,8 +3,8 @@ import { Controller } from "../index"
import { EmptyRequest } from "../../../shared/proto/common"
import { StreamingResponseHandler, getRequestRegistry } from "../grpc-handler"
// Keep track of active state subscriptions by controller ID
const activeStateSubscriptions = new Map<string, StreamingResponseHandler>()
// Keep track of active state subscriptions
const activeStateSubscriptions = new Set<StreamingResponseHandler>()
/**
* Subscribe to state updates
@@ -19,25 +19,23 @@ export async function subscribeToState(
responseStream: StreamingResponseHandler,
requestId?: string,
): Promise<void> {
const controllerId = controller.id
// Send the initial state
const initialState = await controller.getStateToPostToWebview()
const initialStateJson = JSON.stringify(initialState)
console.log(`[DEBUG] set up state subscription for controller ${controllerId}`)
console.log("[DEBUG] set up state subscription")
await responseStream({
stateJson: initialStateJson,
})
// Add this subscription to the active subscriptions with the controller ID
activeStateSubscriptions.set(controllerId, responseStream)
// Add this subscription to the active subscriptions
activeStateSubscriptions.add(responseStream)
// Register cleanup when the connection is closed
const cleanup = () => {
activeStateSubscriptions.delete(controllerId)
console.log(`[DEBUG] Cleaned up state subscription for controller ${controllerId}`)
activeStateSubscriptions.delete(responseStream)
console.log("[DEBUG] Cleaned up state subscription")
}
// Register the cleanup function with the request registry if we have a requestId
@@ -47,31 +45,30 @@ export async function subscribeToState(
}
/**
* Send a state update to a specific controller's subscription
* @param controllerId The ID of the controller to send the state to
* Send a state update to all active subscribers
* @param state The state to send
*/
export async function sendStateUpdate(controllerId: string, state: any): Promise<void> {
// Get the subscription for this specific controller
const responseStream = activeStateSubscriptions.get(controllerId)
export async function sendStateUpdate(state: any): Promise<void> {
const stateJson = JSON.stringify(state)
if (!responseStream) {
console.log(`[DEBUG] No active state subscription for controller ${controllerId}`)
return
}
// Send the update to all active subscribers
const promises = Array.from(activeStateSubscriptions).map(async (responseStream) => {
try {
// The issue might be that we're not properly formatting the response
// Let's ensure we're sending a properly formatted State message
await responseStream(
{
stateJson,
},
false, // Not the last message
)
console.log("[DEBUG] sending followup state", stateJson.length, "chars")
} catch (error) {
console.error("Error sending state update:", error)
// Remove the subscription if there was an error
activeStateSubscriptions.delete(responseStream)
}
})
try {
const stateJson = JSON.stringify(state)
await responseStream(
{
stateJson,
},
false, // Not the last message
)
console.log(`[DEBUG] sending followup state to controller ${controllerId}`, stateJson.length, "chars")
} catch (error) {
console.error(`Error sending state update to controller ${controllerId}:`, error)
// Remove the subscription if there was an error
activeStateSubscriptions.delete(controllerId)
}
await Promise.all(promises)
}
@@ -1,114 +0,0 @@
import path from "path"
import fs from "fs/promises"
import { Controller } from ".."
import { DeleteAllTaskHistoryCount } from "../../../shared/proto/task"
import { BooleanRequest } from "../../../shared/proto/common"
import { getGlobalState, updateGlobalState } from "../../storage/state"
import { fileExistsAtPath } from "../../../utils/fs"
import vscode from "vscode"
/**
* Deletes all task history, with an option to preserve favorites
* @param controller The controller instance
* @param request Request with option to preserve favorites
* @returns Results with count of deleted tasks
*/
export async function deleteAllTaskHistory(controller: Controller, request: BooleanRequest): Promise<DeleteAllTaskHistoryCount> {
try {
// Clear current task first
await controller.clearTask()
// Get existing task history
const taskHistory = ((await getGlobalState(controller.context, "taskHistory")) as any[]) || []
const totalTasks = taskHistory.length
// If preserving favorites, filter out non-favorites
if (request.value) {
const favoritedTasks = taskHistory.filter((task) => task.isFavorited === true)
// If there are favorited tasks, update state
if (favoritedTasks.length > 0) {
await updateGlobalState(controller.context, "taskHistory", favoritedTasks)
// Delete non-favorited task directories
const preserveTaskIds = favoritedTasks.map((task) => task.id)
await cleanupTaskFiles(controller, preserveTaskIds)
// Update webview
try {
await controller.postStateToWebview()
} catch (webviewErr) {
console.error("Error posting to webview:", webviewErr)
}
return DeleteAllTaskHistoryCount.create({
tasksDeleted: totalTasks - favoritedTasks.length,
})
} else {
return DeleteAllTaskHistoryCount.create({
tasksDeleted: 0,
})
}
}
// Delete everything (not preserving favorites)
await updateGlobalState(controller.context, "taskHistory", undefined)
try {
// Remove all contents of tasks directory
const taskDirPath = path.join(controller.context.globalStorageUri.fsPath, "tasks")
if (await fileExistsAtPath(taskDirPath)) {
await fs.rm(taskDirPath, { recursive: true, force: true })
}
// Remove checkpoints directory contents
const checkpointsDirPath = path.join(controller.context.globalStorageUri.fsPath, "checkpoints")
if (await fileExistsAtPath(checkpointsDirPath)) {
await fs.rm(checkpointsDirPath, { recursive: true, force: true })
}
} catch (error) {
vscode.window.showErrorMessage(
`Encountered error while deleting task history, there may be some files left behind. Error: ${error instanceof Error ? error.message : String(error)}`,
)
}
// Update webview
try {
await controller.postStateToWebview()
} catch (webviewErr) {
console.error("Error posting to webview:", webviewErr)
}
return DeleteAllTaskHistoryCount.create({
tasksDeleted: totalTasks,
})
} catch (error) {
console.error("Error in deleteAllTaskHistory:", error)
throw error
}
}
/**
* Helper function to cleanup task files while preserving specified tasks
*/
async function cleanupTaskFiles(controller: Controller, preserveTaskIds: string[]) {
const taskDirPath = path.join(controller.context.globalStorageUri.fsPath, "tasks")
try {
if (await fileExistsAtPath(taskDirPath)) {
const taskDirs = await fs.readdir(taskDirPath)
console.debug(`[cleanupTaskFiles] Found ${taskDirs.length} task directories`)
// Delete only non-preserved task directories
for (const dir of taskDirs) {
if (!preserveTaskIds.includes(dir)) {
await fs.rm(path.join(taskDirPath, dir), { recursive: true, force: true })
}
}
}
} catch (error) {
console.error("Error cleaning up task files:", error)
}
return true
}
+2 -70
View File
@@ -1,9 +1,6 @@
import path from "path"
import fs from "fs/promises"
import { Controller } from ".."
import { Empty, StringArrayRequest, BooleanRequest } from "../../../shared/proto/common"
import { Empty, StringArrayRequest } from "../../../shared/proto/common"
import { TaskMethodHandler } from "./index"
import { fileExistsAtPath } from "../../../utils/fs"
/**
* Deletes tasks with the specified IDs
@@ -20,72 +17,7 @@ export const deleteTasksWithIds: TaskMethodHandler = async (
throw new Error("Missing task IDs")
}
for (const id of request.value) {
await deleteTaskWithId(controller, id)
}
await Promise.all(request.value.map((value) => controller.deleteTaskWithId(value)))
return Empty.create()
}
/**
* Deletes a single task with the specified ID
* @param controller The controller instance
* @param id The task ID to delete
*/
async function deleteTaskWithId(controller: Controller, id: string): Promise<void> {
console.info("deleteTaskWithId: ", id)
try {
// Clear current task if it matches the ID being deleted
if (id === controller.task?.taskId) {
await controller.clearTask()
console.debug("cleared task")
}
// Get task file paths
const { taskDirPath, apiConversationHistoryFilePath, uiMessagesFilePath, contextHistoryFilePath, taskMetadataFilePath } =
await controller.getTaskWithId(id)
// Remove task from state
const updatedTaskHistory = await controller.deleteTaskFromState(id)
// Delete the task files
for (const filePath of [
apiConversationHistoryFilePath,
uiMessagesFilePath,
contextHistoryFilePath,
taskMetadataFilePath,
]) {
const fileExists = await fileExistsAtPath(filePath)
if (fileExists) {
await fs.unlink(filePath)
}
}
// Remove empty task directory
try {
await fs.rmdir(taskDirPath) // succeeds if the dir is empty
} catch (error) {
console.debug("Could not remove task directory (may not be empty):", error)
}
// If no tasks remain, clean up everything
if (updatedTaskHistory.length === 0) {
const taskDirPath = path.join(controller.context.globalStorageUri.fsPath, "tasks")
const checkpointsDirPath = path.join(controller.context.globalStorageUri.fsPath, "checkpoints")
if (await fileExistsAtPath(taskDirPath)) {
await fs.rm(taskDirPath, { recursive: true, force: true })
}
if (await fileExistsAtPath(checkpointsDirPath)) {
await fs.rm(checkpointsDirPath, { recursive: true, force: true })
}
}
} catch (error) {
console.debug(`Error deleting task ${id}:`, error)
throw error // Re-throw to let caller handle the error
}
// Update webview state
await controller.postStateToWebview()
}
+2 -24
View File
@@ -7,7 +7,7 @@ import { ApiConfiguration, ApiProvider, BedrockModelId, ModelInfo } from "@share
import { HistoryItem } from "@shared/HistoryItem"
import { AutoApprovalSettings } from "@shared/AutoApprovalSettings"
import { BrowserSettings } from "@shared/BrowserSettings"
import { ChatSettings, StoredChatSettings } from "@shared/ChatSettings"
import { ChatSettings } from "@shared/ChatSettings"
import { TelemetrySetting } from "@shared/TelemetrySetting"
import { UserInfo } from "@shared/UserInfo"
import { ClineRulesToggles } from "@shared/cline-rules"
@@ -173,28 +173,6 @@ export async function migrateCustomInstructionsToGlobalRules(context: vscode.Ext
}
}
export async function cleanupModeFromWorkspaceStorage(context: vscode.ExtensionContext) {
try {
// Get current chatSettings from workspace storage
const chatSettings = (await getWorkspaceState(context, "chatSettings")) as any
if (chatSettings && typeof chatSettings === "object" && "mode" in chatSettings) {
console.log("Cleaning up mode from workspace storage...")
// Remove mode property from chatSettings
const { mode, ...cleanedChatSettings } = chatSettings
// Save cleaned chatSettings back to workspace storage
await updateWorkspaceState(context, "chatSettings", cleanedChatSettings)
console.log("Successfully removed mode from workspace storage chatSettings")
}
} catch (error) {
console.error("Failed to cleanup mode from workspace storage:", error)
// Continue execution - migration failure shouldn't break extension startup
}
}
export async function getAllExtensionState(context: vscode.ExtensionContext) {
const [
isNewUser,
@@ -382,7 +360,7 @@ export async function getAllExtensionState(context: vscode.ExtensionContext) {
previousModeSapAiCoreResourceGroup,
previousModeSapAiCoreModelId,
] = await Promise.all([
getWorkspaceState(context, "chatSettings") as Promise<StoredChatSettings | undefined>,
getWorkspaceState(context, "chatSettings") as Promise<ChatSettings | undefined>,
getWorkspaceState(context, "apiProvider") as Promise<ApiProvider | undefined>,
getWorkspaceState(context, "apiModelId") as Promise<string | undefined>,
getWorkspaceState(context, "thinkingBudgetTokens") as Promise<number | undefined>,
+1 -1
View File
@@ -200,7 +200,7 @@ export abstract class WebviewProvider {
<link href="${codiconsUri}" rel="stylesheet" />
<link href="${katexCssUri}" rel="stylesheet" />
<meta http-equiv="Content-Security-Policy" content="default-src 'none';
connect-src https://*.posthog.com https://*.cline.bot https://*.firebaseauth.com https://*.firebaseio.com https://*.googleapis.com https://*.firebase.com;
connect-src https://*.posthog.com https://*.firebaseauth.com https://*.firebaseio.com https://*.googleapis.com https://*.firebase.com;
font-src ${this.getCspSource()} data:;
style-src ${this.getCspSource()} 'unsafe-inline';
img-src ${this.getCspSource()} https: data:;
+1 -8
View File
@@ -22,11 +22,7 @@ import { WebviewProviderType as WebviewProviderTypeEnum } from "@shared/proto/ui
import { WebviewProviderType } from "./shared/webview/types"
import { sendHistoryButtonClickedEvent } from "./core/controller/ui/subscribeToHistoryButtonClicked"
import { sendAccountButtonClickedEvent } from "./core/controller/ui/subscribeToAccountButtonClicked"
import {
migratePlanActGlobalToWorkspaceStorage,
migrateCustomInstructionsToGlobalRules,
cleanupModeFromWorkspaceStorage,
} from "./core/storage/state"
import { migratePlanActGlobalToWorkspaceStorage, migrateCustomInstructionsToGlobalRules } from "./core/storage/state"
import { sendFocusChatInputEvent } from "./core/controller/ui/subscribeToFocusChatInput"
import { FileContextTracker } from "./core/context/context-tracking/FileContextTracker"
@@ -64,9 +60,6 @@ export async function activate(context: vscode.ExtensionContext) {
// Migrate custom instructions to global Cline rules (one-time cleanup)
await migrateCustomInstructionsToGlobalRules(context)
// Clean up mode from workspace storage (one-time cleanup)
await cleanupModeFromWorkspaceStorage(context)
// Clean up orphaned file context warnings (startup cleanup)
await FileContextTracker.cleanupOrphanedWarnings(context)
@@ -1,33 +0,0 @@
import type { Anthropic } from "@anthropic-ai/sdk"
/**
* Filters out image blocks from messages since Claude Code doesn't support images.
* Replaces image blocks with text placeholders similar to how VSCode LM provider handles it.
*/
export function filterMessagesForClaudeCode(messages: Anthropic.Messages.MessageParam[]): Anthropic.Messages.MessageParam[] {
return messages.map((message) => {
// Handle simple string messages
if (typeof message.content === "string") {
return message
}
// Handle complex message structures
const filteredContent = message.content.map((block) => {
if (block.type === "image") {
// Replace image blocks with text placeholders
const sourceType = block.source?.type || "unknown"
const mediaType = block.source?.media_type || "unknown"
return {
type: "text" as const,
text: `[Image (${sourceType}): ${mediaType} not supported by Claude Code]`,
}
}
return block
})
return {
...message,
content: filteredContent,
}
})
}
+10 -142
View File
@@ -1,115 +1,23 @@
import * as vscode from "vscode"
import type Anthropic from "@anthropic-ai/sdk"
import Anthropic from "@anthropic-ai/sdk"
import { execa } from "execa"
import { ClaudeCodeMessage } from "./types"
import readline from "readline"
const cwd = vscode.workspace.workspaceFolders?.map((folder) => folder.uri.fsPath).at(0)
type ClaudeCodeOptions = {
export function runClaudeCode({
systemPrompt,
messages,
path,
modelId,
}: {
systemPrompt: string
messages: Anthropic.Messages.MessageParam[]
path?: string
modelId?: string
}
type ProcessState = {
partialData: string | null
error: Error | null
stderrLogs: string
exitCode: number | null
}
export async function* runClaudeCode(options: ClaudeCodeOptions): AsyncGenerator<ClaudeCodeMessage | string> {
const process = runProcess(options)
const rl = readline.createInterface({
input: process.stdout,
})
try {
const processState: ProcessState = {
error: null,
stderrLogs: "",
exitCode: null,
partialData: null,
}
process.stderr.on("data", (data) => {
processState.stderrLogs += data.toString()
})
process.on("close", (code) => {
processState.exitCode = code
})
process.on("error", (err) => {
processState.error = err
})
for await (const line of rl) {
if (processState.error) {
throw processState.error
}
if (line.trim()) {
const chunk = parseChunk(line, processState)
if (!chunk) {
continue
}
yield chunk
}
}
// We rely on the assistant message. If the output was truncated, it's better having a poorly formatted message
// from which to extract something, than throwing an error/showing the model didn't return any messages.
if (processState.partialData && processState.partialData.startsWith(`{"type":"assistant"`)) {
yield processState.partialData
}
const { exitCode } = await process
if (exitCode !== null && exitCode !== 0) {
const errorOutput = processState.error?.message || processState.stderrLogs?.trim()
throw new Error(
`Claude Code process exited with code ${exitCode}.${errorOutput ? ` Error output: ${errorOutput}` : ""}`,
)
}
} finally {
rl.close()
if (!process.killed) {
process.kill()
}
}
}
// We want the model to use our custom tool format instead of built-in tools.
// Disabling built-in tools prevents tool-only responses and ensures text output.
const claudeCodeTools = [
"Task",
"Bash",
"Glob",
"Grep",
"LS",
"exit_plan_mode",
"Read",
"Edit",
"MultiEdit",
"Write",
"NotebookRead",
"NotebookEdit",
"WebFetch",
"TodoRead",
"TodoWrite",
"WebSearch",
].join(",")
const CLAUDE_CODE_TIMEOUT = 600000 // 10 minutes
function runProcess({ systemPrompt, messages, path, modelId }: ClaudeCodeOptions) {
}) {
const claudePath = path || "claude"
// TODO: Is it worh using sessions? Where do we store the session ID?
const args = [
"-p",
JSON.stringify(messages),
@@ -118,8 +26,6 @@ function runProcess({ systemPrompt, messages, path, modelId }: ClaudeCodeOptions
"--verbose",
"--output-format",
"stream-json",
"--disallowedTools",
claudeCodeTools,
// Cline will handle recursive calls
"--max-turns",
"1",
@@ -133,45 +39,7 @@ function runProcess({ systemPrompt, messages, path, modelId }: ClaudeCodeOptions
stdin: "ignore",
stdout: "pipe",
stderr: "pipe",
env: {
...process.env,
// The default is 32000. However, I've gotten larger responses, so we increase it unless the user specified it.
CLAUDE_CODE_MAX_OUTPUT_TOKENS: process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS || "64000",
},
env: process.env,
cwd,
maxBuffer: 1024 * 1024 * 1000,
timeout: CLAUDE_CODE_TIMEOUT,
})
}
function parseChunk(data: string, processState: ProcessState) {
if (processState.partialData) {
processState.partialData += data
const chunk = attemptParseChunk(processState.partialData)
if (!chunk) {
return null
}
processState.partialData = null
return chunk
}
const chunk = attemptParseChunk(data)
if (!chunk) {
processState.partialData = data
}
return chunk
}
function attemptParseChunk(data: string): ClaudeCodeMessage | null {
try {
return JSON.parse(data)
} catch (error) {
console.error("Error parsing chunk:", error, data.length)
return null
}
}
+23 -5
View File
@@ -1,17 +1,34 @@
import type { Anthropic } from "@anthropic-ai/sdk"
type InitMessage = {
type: "system"
subtype: "init"
session_id: string
tools: string[]
mcp_servers: string[]
apiKeySource: "none" | "/login managed key" | string
}
type ClaudeCodeContent = {
type: "text"
text: string
}
type AssistantMessage = {
type: "assistant"
message: Anthropic.Messages.Message
message: {
id: string
type: "message"
role: "assistant"
model: string
content: ClaudeCodeContent[]
stop_reason: null
stop_sequence: null
usage: {
input_tokens: number
cache_creation_input_tokens?: number
cache_read_input_tokens?: number
output_tokens: number
service_tier: "standard"
}
}
session_id: string
}
@@ -22,12 +39,13 @@ type ErrorMessage = {
type ResultMessage = {
type: "result"
subtype: "success"
total_cost_usd: number
cost_usd: number
is_error: boolean
duration_ms: number
duration_api_ms: number
num_turns: number
result: string
total_cost: number
session_id: string
}
-3
View File
@@ -8,9 +8,6 @@ export interface ChatSettings {
export type PartialChatSettings = Partial<ChatSettings>
// Type for chat settings stored in workspace (excludes in-memory mode)
export type StoredChatSettings = Omit<ChatSettings, "mode">
export const DEFAULT_CHAT_SETTINGS: ChatSettings = {
mode: "act",
preferredLanguage: "English",
+1
View File
@@ -12,6 +12,7 @@ export interface WebviewMessage {
| "fetchMcpMarketplace"
| "searchCommits"
| "telemetrySetting"
| "clearAllTaskHistory"
| "grpc_request"
| "grpc_request_cancel"
+5 -25
View File
@@ -230,31 +230,11 @@ export const anthropicModels = {
export type ClaudeCodeModelId = keyof typeof claudeCodeModels
export const claudeCodeDefaultModelId: ClaudeCodeModelId = "claude-sonnet-4-20250514"
export const claudeCodeModels = {
"claude-sonnet-4-20250514": {
...anthropicModels["claude-sonnet-4-20250514"],
supportsImages: false,
supportsPromptCache: false,
},
"claude-opus-4-20250514": {
...anthropicModels["claude-opus-4-20250514"],
supportsImages: false,
supportsPromptCache: false,
},
"claude-3-7-sonnet-20250219": {
...anthropicModels["claude-3-7-sonnet-20250219"],
supportsImages: false,
supportsPromptCache: false,
},
"claude-3-5-sonnet-20241022": {
...anthropicModels["claude-3-5-sonnet-20241022"],
supportsImages: false,
supportsPromptCache: false,
},
"claude-3-5-haiku-20241022": {
...anthropicModels["claude-3-5-haiku-20241022"],
supportsImages: false,
supportsPromptCache: false,
},
"claude-sonnet-4-20250514": anthropicModels["claude-sonnet-4-20250514"],
"claude-opus-4-20250514": anthropicModels["claude-opus-4-20250514"],
"claude-3-7-sonnet-20250219": anthropicModels["claude-3-7-sonnet-20250219"],
"claude-3-5-sonnet-20241022": anthropicModels["claude-3-5-sonnet-20241022"],
"claude-3-5-haiku-20241022": anthropicModels["claude-3-5-haiku-20241022"],
} as const satisfies Record<string, ModelInfo>
// AWS Bedrock
+3 -5
View File
@@ -10,9 +10,7 @@ https://github.com/KumarVariable/vscode-extension-sidebar-html/blob/master/src/c
*/
export class ExternalWebviewProvider extends WebviewProvider {
// This hostname cannot be changed without updating the external webview handler.
private RESOURCE_HOSTNAME: string = "internal.resources"
private RESOURCE_AUTHORITY: string = "file.resources"
constructor(context: vscode.ExtensionContext, outputChannel: vscode.OutputChannel, providerType: WebviewProviderType) {
super(context, outputChannel, providerType)
}
@@ -21,10 +19,10 @@ export class ExternalWebviewProvider extends WebviewProvider {
if (uri.scheme !== "file") {
return uri
}
return URI.from({ scheme: "https", authority: this.RESOURCE_HOSTNAME, path: uri.fsPath })
return URI.from({ scheme: "https", authority: this.RESOURCE_AUTHORITY, path: uri.fsPath })
}
override getCspSource() {
return `'self' https://${this.RESOURCE_HOSTNAME}`
return "csp-source"
}
override postMessageToWebview(message: ExtensionMessage) {
console.log(`postMessageToWebview: ${message}`)
+3 -18
View File
@@ -20,10 +20,6 @@ async function main() {
hostProviders.initializeHostProviders(createWebview, new ExternalHostBridgeClientManager())
activate(extensionContext)
const controller = new Controller(extensionContext, outputChannel, postMessage, uuidv4())
startProtobusService(controller)
}
function startProtobusService(controller: Controller) {
const server = new grpc.Server()
// Set up health check.
@@ -33,15 +29,12 @@ function startProtobusService(controller: Controller) {
// Add all the handlers for the ProtoBus services to the server.
addProtobusServices(server, controller, wrapHandler, wrapStreamingResponseHandler)
// Create reflection service with protobus service names
const packageDefinition = getPackageDefinition()
const reflection = new ReflectionService(packageDefinition, {
services: getProtobusServiceNames(packageDefinition),
})
// Set up reflection.
const reflection = new ReflectionService(getPackageDefinition())
reflection.addToServer(server)
// Start the server.
const host = process.env.PROTOBUS_ADDRESS || "127.0.0.1:50051"
const host = "127.0.0.1:50051"
server.bindAsync(host, grpc.ServerCredentials.createInsecure(), (err) => {
if (err) {
log(`Error: Failed to bind to ${host}, port may be unavailable. ${err.message}`)
@@ -52,14 +45,6 @@ function startProtobusService(controller: Controller) {
})
}
function getProtobusServiceNames(packageDefinition: { [x: string]: any }): string[] {
// Filter service names to only include cline services
const protobusServiceNames = Object.keys(packageDefinition).filter(
(name) => name.startsWith("cline.") || name.startsWith("grpc.health"),
)
return protobusServiceNames
}
const createWebview = () => {
return new ExternalWebviewProvider(extensionContext, outputChannel, WebviewProviderType.SIDEBAR)
}
+2 -2
View File
@@ -11,9 +11,9 @@ const log = (...args: unknown[]) => {
function getPackageDefinition() {
// Load service definitions.
const descriptorSet = fs.readFileSync("proto/descriptor_set.pb")
const descriptorDefs = protoLoader.loadFileDescriptorSetFromBuffer(descriptorSet)
const clineDef = protoLoader.loadFileDescriptorSetFromBuffer(descriptorSet)
const healthDef = protoLoader.loadSync(health.protoPath)
const packageDefinition = { ...descriptorDefs, ...healthDef }
const packageDefinition = { ...clineDef, ...healthDef }
return packageDefinition
}
-1
View File
@@ -28,7 +28,6 @@
"no-extra-semi": "off",
"eslint-rules/no-protobuf-object-literals": "error",
"eslint-rules/no-grpc-client-object-literals": "error",
"eslint-rules/no-vscode-postmessage": "warn",
"no-restricted-syntax": [
"error",
{
@@ -21,6 +21,13 @@ import {
} from "@vscode/webview-ui-toolkit/react"
function Demo() {
// function handleHowdyClick() {
// vscode.postMessage({
// command: "hello",
// text: "Hey there partner! 🤠",
// })
// }
const rowData = [
{
cell1: "Cell Data",
@@ -4,7 +4,7 @@ import { TaskServiceClient } from "@/services/grpc-client"
import { formatLargeNumber, formatSize } from "@/utils/format"
import { vscode } from "@/utils/vscode"
import { ExtensionMessage } from "@shared/ExtensionMessage"
import { BooleanRequest, EmptyRequest, StringArrayRequest, StringRequest } from "@shared/proto/common"
import { EmptyRequest, StringArrayRequest, StringRequest } from "@shared/proto/common"
import { GetTaskHistoryRequest, TaskFavoriteRequest } from "@shared/proto/task"
import { VSCodeButton, VSCodeCheckbox, VSCodeRadio, VSCodeRadioGroup, VSCodeTextField } from "@vscode/webview-ui-toolkit/react"
import Fuse, { FuseResult } from "fuse.js"
@@ -727,17 +727,7 @@ const HistoryView = ({ onDone }: HistoryViewProps) => {
disabled={deleteAllDisabled || taskHistory.length === 0}
onClick={() => {
setDeleteAllDisabled(true)
const confirmDelete = window.confirm("Are you sure you want to delete all task history?")
if (confirmDelete) {
const preserveFavorites = window.confirm(
"Would you like to preserve favorited tasks?\n\nClick 'OK' to preserve favorites, or 'Cancel' to delete everything.",
)
TaskServiceClient.deleteAllTaskHistory(BooleanRequest.create({ value: preserveFavorites }))
.catch((error) => console.error("Error deleting task history:", error))
.finally(() => setDeleteAllDisabled(false))
} else {
setDeleteAllDisabled(false)
}
vscode.postMessage({ type: "clearAllTaskHistory" })
}}>
Delete All History{totalTasksSize !== null ? ` (${formatSize(totalTasksSize)})` : ""}
</DangerButton>
@@ -11,12 +11,10 @@ import {
import { McpMarketplaceItem } from "@shared/mcp"
import { useExtensionState } from "@/context/ExtensionStateContext"
import { vscode } from "@/utils/vscode"
import { McpServiceClient } from "@/services/grpc-client"
import { EmptyRequest } from "@shared/proto/common"
import McpMarketplaceCard from "./McpMarketplaceCard"
import McpSubmitCard from "./McpSubmitCard"
const McpMarketplaceView = () => {
const { mcpServers, mcpMarketplaceCatalog, setMcpMarketplaceCatalog, mcpMarketplaceEnabled } = useExtensionState()
const { mcpServers, mcpMarketplaceCatalog } = useExtensionState()
const [isLoading, setIsLoading] = useState(true)
const [error, setError] = useState<string | null>(null)
const [isRefreshing, setIsRefreshing] = useState(false)
@@ -94,19 +92,7 @@ const McpMarketplaceView = () => {
setIsLoading(true)
}
setError(null)
if (mcpMarketplaceEnabled) {
McpServiceClient.refreshMcpMarketplace(EmptyRequest.create({}))
.then((response) => {
setMcpMarketplaceCatalog(response)
})
.catch((error) => {
console.error("Error refreshing MCP marketplace:", error)
setError("Failed to load marketplace data")
setIsLoading(false)
setIsRefreshing(false)
})
}
vscode.postMessage({ type: "fetchMcpMarketplace", bool: forceRefresh })
}
if (isLoading || isRefreshing) {
@@ -1529,6 +1529,20 @@ const ApiOptions = ({
</VSCodeLink>
)}
</p>
{/* Note: To fully implement this, you would need to add a handler in ClineProvider.ts */}
{/* {apiConfiguration?.xaiApiKey && (
<button
onClick={() => {
vscode.postMessage({
type: "requestXAIModels",
text: apiConfiguration?.xaiApiKey,
})
}}
style={{ margin: "5px 0 0 0" }}
className="vscode-button">
Fetch Available Models
</button>
)} */}
</div>
)}