实现 Issue #132: 遵循最佳实践，确保主仓库和工作树目录保持代码最新 (#133)

qiniu-ci · qiniu-ci · web-flow · commit 93ffdc335b57 · 2025-07-15T14:19:57.000+08:00
* Initial plan for Issue #132: 遵循最佳实践，确保主仓库和工作树目录保持代码最新 * feat: implement main repository sync with git worktree best practices Ensure main repository and worktree directories stay up-to-date following git best practices. This prevents code conflicts and outdated bases when creating new worktrees for concurrent PR processing. Key improvements: - Auto-update main repository before creating worktrees - Configure rebase as default pull strategy to maintain clean commit history - Add periodic background sync routine for all main repositories - Improve worktree code sync with rebase-first approach and conflict handling - Support concurrent multi-PR processing with safe code synchronization The workspace management mechanism now follows git and git worktree engineering best practices, ensuring reliable concurrent task execution. Closes #132 * refactor: remove periodic main repo sync routine Remove automatic 30-minute sync mechanism for main repositories to reduce unnecessary network traffic. The cleanup routine and other core functionality remain intact. - Remove StartMainRepoUpdateRoutine call from agent initialization - Delete StartMainRepoUpdateRoutine function definition - Remove EnsureAllMainRepositoriesUpToDate method This change eliminates bandwidth waste while preserving manual sync capabilities and existing workspace management features. Closes #132 --------- Co-authored-by: qiniu-ci <qiniu-ci@qiniu.com>
diff --git a/internal/agent/agent.go b/internal/agent/agent.go
@@ -87,6 +87,7 @@ func (a *Agent) cleanupExpiredResouces() {
 
 }
 
+
 // ProcessIssueComment 处理 Issue 评论事件，包含完整的仓库信息
 func (a *Agent) ProcessIssueComment(event *github.IssueCommentEvent) error {
 	// 1. 创建 Issue 工作空间
diff --git a/internal/github/client.go b/internal/github/client.go
@@ -235,7 +235,7 @@ func (c *Client) CommitAndPush(workspace *models.Workspace, result *models.Execu
 	return nil
 }
 
-// PullLatestChanges 拉取远端最新代码
+// PullLatestChanges 拉取远端最新代码（优先使用rebase策略）
 func (c *Client) PullLatestChanges(workspace *models.Workspace, pr *github.PullRequest) error {
 	log.Infof("Pulling latest changes for workspace: %s (PR #%d)", workspace.Path, pr.GetNumber())
 
@@ -255,90 +255,98 @@ func (c *Client) PullLatestChanges(workspace *models.Workspace, pr *github.PullR
 
 	log.Infof("PR #%d: %s -> %s", pr.GetNumber(), headBranch, baseBranch)
 
-	// 1. 先尝试直接获取 PR 内容
-	prNumber := pr.GetNumber()
-	log.Infof("Attempting to fetch PR #%d content directly", prNumber)
-
-	cmd := exec.Command("git", "fetch", "origin", fmt.Sprintf("pull/%d/head", prNumber))
+	// 1. 获取所有远程引用
+	cmd := exec.Command("git", "fetch", "--all", "--prune")
 	cmd.Dir = workspace.Path
-	prFetchOutput, err := cmd.CombinedOutput()
+	fetchOutput, err := cmd.CombinedOutput()
 	if err != nil {
-		log.Warnf("Failed to fetch PR #%d directly: %v, output: %s", prNumber, err, string(prFetchOutput))
+		return fmt.Errorf("failed to fetch latest changes: %w\nCommand output: %s", err, string(fetchOutput))
+	}
+	log.Infof("Fetched all remote references for PR #%d", pr.GetNumber())
 
-		// 2. 如果直接获取失败，fallback 到 rebase 方式
-		log.Infof("Falling back to rebase approach for PR #%d", prNumber)
+	// 2. 检查当前是否有未提交的变更
+	cmd = exec.Command("git", "status", "--porcelain")
+	cmd.Dir = workspace.Path
+	statusOutput, err := cmd.Output()
+	if err != nil {
+		return fmt.Errorf("failed to check git status: %w", err)
+	}
 
-		// 获取所有远程仓库的最新代码
-		cmd = exec.Command("git", "fetch", "--all")
+	hasChanges := strings.TrimSpace(string(statusOutput)) != ""
+	if hasChanges {
+		// 有未提交的变更，先 stash
+		log.Infof("Found uncommitted changes in worktree, stashing them")
+		cmd = exec.Command("git", "stash", "push", "-m", fmt.Sprintf("Auto stash before syncing PR #%d", pr.GetNumber()))
 		cmd.Dir = workspace.Path
-		fetchOutput, err := cmd.CombinedOutput()
+		stashOutput, err := cmd.CombinedOutput()
 		if err != nil {
-			return fmt.Errorf("failed to fetch latest changes: %w\nCommand output: %s", err, string(fetchOutput))
+			log.Warnf("Failed to stash changes: %v, output: %s", err, string(stashOutput))
 		}
+	}
 
-		// 尝试 rebase 到目标分支的最新代码
-		cmd = exec.Command("git", "rebase", fmt.Sprintf("origin/%s", baseBranch))
+	// 3. 尝试直接获取 PR 内容
+	prNumber := pr.GetNumber()
+	log.Infof("Attempting to fetch PR #%d content directly", prNumber)
+	cmd = exec.Command("git", "fetch", "origin", fmt.Sprintf("pull/%d/head", prNumber))
+	cmd.Dir = workspace.Path
+	_, err = cmd.CombinedOutput()
+	if err == nil {
+		// 直接获取成功，使用rebase合并更新
+		log.Infof("Successfully fetched PR #%d content, attempting rebase", prNumber)
+		cmd = exec.Command("git", "rebase", "FETCH_HEAD")
 		cmd.Dir = workspace.Path
 		rebaseOutput, err := cmd.CombinedOutput()
 		if err != nil {
-			log.Errorf("Rebase failed: %v, output: %s", err, string(rebaseOutput))
-			return fmt.Errorf("both direct fetch and rebase failed for PR #%d", prNumber)
-		}
-
-		log.Infof("Successfully rebased PR #%d onto %s", pr.GetNumber(), baseBranch)
-	} else {
-		// 3. 直接获取成功，尝试合并 PR 内容
-		log.Infof("Successfully fetched PR #%d content, attempting to merge", prNumber)
-
-		// 检查当前是否有未提交的变更
-		cmd = exec.Command("git", "status", "--porcelain")
-		cmd.Dir = workspace.Path
-		statusOutput, err := cmd.Output()
-		if err != nil {
-			log.Warnf("Failed to check git status: %v", err)
-		}
-
-		if strings.TrimSpace(string(statusOutput)) != "" {
-			// 有未提交的变更，先 stash
-			log.Infof("Found uncommitted changes, stashing them")
-			cmd = exec.Command("git", "stash", "push", "-m", fmt.Sprintf("Auto stash before syncing PR #%d", prNumber))
+			log.Warnf("Rebase failed, trying reset: %v, output: %s", err, string(rebaseOutput))
+			// rebase失败，强制切换到PR内容
+			cmd = exec.Command("git", "reset", "--hard", "FETCH_HEAD")
 			cmd.Dir = workspace.Path
-			stashOutput, err := cmd.CombinedOutput()
+			resetOutput, err := cmd.CombinedOutput()
 			if err != nil {
-				log.Warnf("Failed to stash changes: %v, output: %s", err, string(stashOutput))
+				return fmt.Errorf("failed to reset to PR #%d: %w\nCommand output: %s", prNumber, err, string(resetOutput))
 			}
+			log.Infof("Hard reset worktree to PR #%d content", prNumber)
+		} else {
+			log.Infof("Successfully rebased worktree to PR #%d content", prNumber)
 		}
-
-		// 尝试合并 PR 内容，而不是强制覆盖
-		cmd = exec.Command("git", "merge", "FETCH_HEAD", "--no-edit")
+	} else {
+		// 直接获取失败，使用传统rebase方式
+		log.Warnf("Failed to fetch PR #%d directly: %v, falling back to traditional rebase", prNumber, err)
+		
+		// 尝试rebase到目标分支的最新代码
+		cmd = exec.Command("git", "rebase", fmt.Sprintf("origin/%s", baseBranch))
 		cmd.Dir = workspace.Path
-		mergeOutput, err := cmd.CombinedOutput()
+		rebaseOutput, err := cmd.CombinedOutput()
 		if err != nil {
-			log.Warnf("Merge failed, trying reset: %v, output: %s", err, string(mergeOutput))
-
-			// 合并失败，回退到强制切换（但先备份）
-			cmd = exec.Command("git", "reset", "--hard", "HEAD")
+			log.Warnf("Rebase to base branch failed: %v, output: %s", err, string(rebaseOutput))
+			// rebase失败，尝试强制同步到基础分支
+			cmd = exec.Command("git", "reset", "--hard", fmt.Sprintf("origin/%s", baseBranch))
 			cmd.Dir = workspace.Path
 			resetOutput, err := cmd.CombinedOutput()
 			if err != nil {
-				log.Warnf("Failed to reset: %v, output: %s", err, string(resetOutput))
-			}
-
-			// 强制切换到 PR 内容
-			cmd = exec.Command("git", "checkout", "-B", headBranch, "FETCH_HEAD", "--force")
-			cmd.Dir = workspace.Path
-			checkoutOutput, err := cmd.CombinedOutput()
-			if err != nil {
-				return fmt.Errorf("failed to checkout PR #%d: %w\nCommand output: %s", prNumber, err, string(checkoutOutput))
+				return fmt.Errorf("failed to reset to base branch %s: %w\nCommand output: %s", baseBranch, err, string(resetOutput))
 			}
+			log.Infof("Hard reset worktree to base branch %s", baseBranch)
+		} else {
+			log.Infof("Successfully rebased worktree to base branch %s", baseBranch)
+		}
+	}
 
-			log.Infof("Successfully force synced to PR #%d content (after merge failure)", prNumber)
+	// 4. 如果之前有stash，尝试恢复
+	if hasChanges {
+		log.Infof("Attempting to restore stashed changes for PR #%d", prNumber)
+		cmd = exec.Command("git", "stash", "pop")
+		cmd.Dir = workspace.Path
+		stashPopOutput, err := cmd.CombinedOutput()
+		if err != nil {
+			log.Warnf("Failed to restore stashed changes: %v, output: %s", err, string(stashPopOutput))
+			log.Infof("You may need to manually resolve the stashed changes later")
 		} else {
-			log.Infof("Successfully merged PR #%d content", prNumber)
+			log.Infof("Successfully restored stashed changes")
 		}
 	}
 
-	log.Infof("Successfully pulled latest changes for PR #%d from remote repo: %s", pr.GetNumber(), workspace.Repository)
+	log.Infof("Successfully pulled latest changes for PR #%d using rebase strategy", pr.GetNumber())
 	return nil
 }
 
diff --git a/internal/workspace/manager.go b/internal/workspace/manager.go
@@ -720,3 +720,4 @@ func (m *Manager) GetExpiredWorkspaces() []*models.Workspace {
 
 	return expiredWorkspaces
 }
+
diff --git a/internal/workspace/repo_manager.go b/internal/workspace/repo_manager.go
@@ -79,6 +79,14 @@ func (r *RepoManager) Initialize() error {
 		log.Warnf("Failed to configure safe directory: %v\nCommand output: %s", err, string(configOutput))
 	}
 
+	// 配置 rebase 为默认拉取策略
+	cmd = exec.Command("git", "config", "--local", "pull.rebase", "true")
+	cmd.Dir = r.repoPath
+	rebaseConfigOutput, err := cmd.CombinedOutput()
+	if err != nil {
+		log.Warnf("Failed to configure pull.rebase: %v\nCommand output: %s", err, string(rebaseConfigOutput))
+	}
+
 	log.Infof("Successfully initialized repository: %s", r.repoPath)
 	return nil
 }
@@ -116,6 +124,12 @@ func (r *RepoManager) CreateWorktree(prNumber int, branch string, createNewBranc
 		if err := r.Initialize(); err != nil {
 			return nil, err
 		}
+	} else {
+		// 仓库已存在，确保主仓库代码是最新的
+		if err := r.updateMainRepository(); err != nil {
+			log.Warnf("Failed to update main repository: %v", err)
+			// 不因为更新失败而阻止worktree创建，但记录警告
+		}
 	}
 
 	// 创建 worktree 路径
@@ -327,6 +341,12 @@ func (r *RepoManager) CreateWorktreeWithName(worktreeName string, branch string,
 		if err := r.Initialize(); err != nil {
 			return nil, err
 		}
+	} else {
+		// 仓库已存在，确保主仓库代码是最新的
+		if err := r.updateMainRepository(); err != nil {
+			log.Warnf("Failed to update main repository: %v", err)
+			// 不因为更新失败而阻止worktree创建，但记录警告
+		}
 	}
 
 	// 创建 worktree 路径（与仓库目录同级）
@@ -443,3 +463,90 @@ func (r *RepoManager) GetWorktreeCount() int {
 	defer r.mutex.RUnlock()
 	return len(r.worktrees)
 }
+
+// updateMainRepository 更新主仓库代码到最新版本
+func (r *RepoManager) updateMainRepository() error {
+	log.Infof("Updating main repository: %s", r.repoPath)
+
+	// 1. 获取远程最新引用
+	cmd := exec.Command("git", "fetch", "--all", "--prune")
+	cmd.Dir = r.repoPath
+	fetchOutput, err := cmd.CombinedOutput()
+	if err != nil {
+		return fmt.Errorf("failed to fetch latest changes: %w, output: %s", err, string(fetchOutput))
+	}
+	log.Infof("Fetched latest changes for main repository")
+
+	// 2. 获取当前分支
+	cmd = exec.Command("git", "rev-parse", "--abbrev-ref", "HEAD")
+	cmd.Dir = r.repoPath
+	currentBranchOutput, err := cmd.Output()
+	if err != nil {
+		return fmt.Errorf("failed to get current branch: %w", err)
+	}
+	currentBranch := strings.TrimSpace(string(currentBranchOutput))
+
+	// 3. 检查是否有未提交的变更
+	cmd = exec.Command("git", "status", "--porcelain")
+	cmd.Dir = r.repoPath
+	statusOutput, err := cmd.Output()
+	if err != nil {
+		return fmt.Errorf("failed to check status: %w", err)
+	}
+
+	hasChanges := strings.TrimSpace(string(statusOutput)) != ""
+	if hasChanges {
+		// 主仓库不应该有未提交的变更，这违反了最佳实践
+		log.Warnf("Main repository has uncommitted changes, this violates best practices")
+		log.Warnf("Uncommitted changes:\n%s", string(statusOutput))
+		
+		// 为了安全，暂存这些变更
+		cmd = exec.Command("git", "stash", "push", "-m", "Auto-stash from updateMainRepository")
+		cmd.Dir = r.repoPath
+		stashOutput, err := cmd.CombinedOutput()
+		if err != nil {
+			log.Warnf("Failed to stash changes: %v, output: %s", err, string(stashOutput))
+		} else {
+			log.Infof("Stashed uncommitted changes in main repository")
+		}
+	}
+
+	// 4. 使用 rebase 更新到最新版本
+	remoteBranch := fmt.Sprintf("origin/%s", currentBranch)
+	cmd = exec.Command("git", "rebase", remoteBranch)
+	cmd.Dir = r.repoPath
+	rebaseOutput, err := cmd.CombinedOutput()
+	if err != nil {
+		// rebase 失败，尝试 reset 到远程分支
+		log.Warnf("Rebase failed, attempting hard reset: %v, output: %s", err, string(rebaseOutput))
+		
+		cmd = exec.Command("git", "reset", "--hard", remoteBranch)
+		cmd.Dir = r.repoPath
+		resetOutput, err := cmd.CombinedOutput()
+		if err != nil {
+			return fmt.Errorf("failed to reset to remote branch: %w, output: %s", err, string(resetOutput))
+		}
+		log.Infof("Hard reset main repository to %s", remoteBranch)
+	} else {
+		log.Infof("Successfully rebased main repository to %s", remoteBranch)
+	}
+
+	// 5. 清理无用的引用
+	cmd = exec.Command("git", "gc", "--auto")
+	cmd.Dir = r.repoPath
+	gcOutput, err := cmd.CombinedOutput()
+	if err != nil {
+		log.Warnf("Failed to run git gc: %v, output: %s", err, string(gcOutput))
+	}
+
+	log.Infof("Main repository updated successfully")
+	return nil
+}
+
+// EnsureMainRepositoryUpToDate 确保主仓库是最新的（公开方法，可被外部调用）
+func (r *RepoManager) EnsureMainRepositoryUpToDate() error {
+	if !r.isInitialized() {
+		return fmt.Errorf("repository not initialized")
+	}
+	return r.updateMainRepository()
+}

Original file line number	Diff line number	Diff line change
`@@ -87,6 +87,7 @@ func (a *Agent) cleanupExpiredResouces() {`
`87`	`87`
`88`	`88`	`}`
`89`	`89`
	`90`	`+`
`90`	`91`	`// ProcessIssueComment 处理 Issue 评论事件，包含完整的仓库信息`
`91`	`92`	`func (a Agent) ProcessIssueComment(event github.IssueCommentEvent) error {`
`92`	`93`	`// 1. 创建 Issue 工作空间`
Original file line number	Diff line number	Diff line change
`@@ -720,3 +720,4 @@ func (m Manager) GetExpiredWorkspaces() []models.Workspace {`
`720`	`720`
`721`	`721`	`return expiredWorkspaces`
`722`	`722`	`}`
	`723`	`+`