fix: resolve checkpoint initialization timeout in large repositories

- Add timeout handling for initial git staging operation (5 seconds)
- Add --ignore-errors flag to git add command for better error handling
- Add isInitialCall parameter to allow unlimited time for first initialization
- Prevent blocking on large repositories during checkpoint setup

This fix addresses issue #7843 where checkpoints would fail to initialize
in large repositories due to the git add operation taking longer than
the 15-second timeout limit.

src/core/checkpoints/index.ts

@@ -18,7 +18,11 @@ import { CheckpointServiceOptions, RepoPerTaskCheckpointService } from "../../se
 
 export async function getCheckpointService(
 	task: Task,
-	{ interval = 250, timeout = 15_000 }: { interval?: number; timeout?: number } = {},
+	{
+		interval = 250,
+		timeout = 15_000,
+		isInitialCall = false,
+	}: { interval?: number; timeout?: number; isInitialCall?: boolean } = {},
 ) {
 	if (!task.enableCheckpoints) {
 		return undefined
@@ -67,13 +71,12 @@ export async function getCheckpointService(
 		}
 
 		if (task.checkpointServiceInitializing) {
-			await pWaitFor(
-				() => {
-					console.log("[Task#getCheckpointService] waiting for service to initialize")
-					return !!task.checkpointService && !!task?.checkpointService?.isInitialized
-				},
-				{ interval, timeout },
-			)
+			// For initial calls, don't apply timeout to allow large repositories to initialize
+			const waitOptions = isInitialCall ? { interval } : { interval, timeout }
+			await pWaitFor(() => {
+				console.log("[Task#getCheckpointService] waiting for service to initialize")
+				return !!task.checkpointService && !!task?.checkpointService?.isInitialized
+			}, waitOptions)
 			if (!task?.checkpointService) {
 				task.enableCheckpoints = false
 				return undefined

src/core/task/Task.ts

@@ -1661,7 +1661,8 @@ export class Task extends EventEmitter<TaskEvents> implements TaskLike {
 
 	private async initiateTaskLoop(userContent: Anthropic.Messages.ContentBlockParam[]): Promise<void> {
 		// Kicks off the checkpoints initialization process in the background.
-		getCheckpointService(this)
+		// Pass isInitialCall=true to allow unlimited time for large repositories
+		getCheckpointService(this, { isInitialCall: true })
 
 		let nextUserContent = userContent
 		let includeFileDetails = true

src/services/checkpoints/ShadowCheckpointService.ts

@@ -105,7 +105,21 @@ export abstract class ShadowCheckpointService extends EventEmitter {
 			await git.addConfig("user.name", "Roo Code")
 			await git.addConfig("user.email", "noreply@example.com")
 			await this.writeExcludeFile()
-			await this.stageAll(git)
+
+			// For initial commit, stage files but with a timeout to prevent hanging on large repos
+			// Use a promise race to ensure we don't wait forever
+			const stagePromise = this.stageAll(git)
+			const timeoutPromise = new Promise<void>((resolve) => {
+				setTimeout(() => {
+					this.log(
+						`[${this.constructor.name}#initShadowGit] Initial staging timed out after 5 seconds, proceeding with empty commit`,
+					)
+					resolve()
+				}, 5000) // 5 second timeout for initial staging
+			})
+
+			await Promise.race([stagePromise, timeoutPromise])
+
 			const { commit } = await git.commit("initial commit", { "--allow-empty": null })
 			this.baseHash = commit
 			created = true
@@ -145,11 +159,14 @@ export abstract class ShadowCheckpointService extends EventEmitter {
 
 	private async stageAll(git: SimpleGit) {
 		try {
-			await git.add(".")
+			// Add --ignore-errors flag to handle permission issues gracefully
+			// This prevents the operation from failing on files with permission issues
+			await git.add([".", "--ignore-errors"])
 		} catch (error) {
 			this.log(
 				`[${this.constructor.name}#stageAll] failed to add files to git: ${error instanceof Error ? error.message : String(error)}`,
 			)
+			// Don't throw - allow the operation to continue with whatever files were successfully staged
 		}
 	}