Sparse checkout excludes .story_kit/work/ from agent worktrees

Configures sparse checkout on new and existing worktrees to exclude
the pipeline state directory. This prevents feature branches from
containing .story_kit/work/ file moves that cause rename/delete merge
conflicts when merging back to master.

Also removes "pick up the story from .story_kit/work/" instruction
from agent prompts since the story content is already in the prompt.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.story_kit/project.toml

@@ -54,7 +54,7 @@ role = "Full-stack engineer. Implements features across all components."
 model = "sonnet-4.6"
 max_turns = 50
 max_budget_usd = 5.00
-prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .story_kit/README.md to understand the dev process. Pick up the story from .story_kit/work/ - move it to work/2_current/ if needed. Follow the SDTW process through implementation and verification (Steps 1-3). The worktree and feature branch already exist - do not create them. Check .mcp.json for MCP tools. Do NOT accept the story or merge - commit your work and stop. If the user asks to review your changes, tell them to run: cd \"{{worktree_path}}\" && git difftool {{base_branch}}...HEAD\n\nIMPORTANT: Commit all your work before your process exits. The server will automatically run acceptance gates (cargo clippy + tests) when your process exits and advance the pipeline based on the results."
+prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .story_kit/README.md to understand the dev process. The story details are in your prompt above. Follow the SDTW process through implementation and verification (Steps 1-3). The worktree and feature branch already exist - do not create them. Check .mcp.json for MCP tools. Do NOT accept the story or merge - commit your work and stop. If the user asks to review your changes, tell them to run: cd \"{{worktree_path}}\" && git difftool {{base_branch}}...HEAD\n\nIMPORTANT: Commit all your work before your process exits. The server will automatically run acceptance gates (cargo clippy + tests) when your process exits and advance the pipeline based on the results."
 system_prompt = "You are a full-stack engineer working autonomously in a git worktree. Follow the Story-Driven Test Workflow strictly. Run cargo clippy and biome checks before considering work complete. Commit all your work before finishing - use a descriptive commit message. Do not accept stories, move them to archived, or merge to master - a human will do that. Do not coordinate with other agents - focus on your assigned story. The server automatically runs acceptance gates when your process exits."
 
 [[agent]]
@@ -63,7 +63,7 @@ role = "Full-stack engineer. Implements features across all components."
 model = "sonnet-4.6"
 max_turns = 50
 max_budget_usd = 5.00
-prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .story_kit/README.md to understand the dev process. Pick up the story from .story_kit/work/ - move it to work/2_current/ if needed. Follow the SDTW process through implementation and verification (Steps 1-3). The worktree and feature branch already exist - do not create them. Check .mcp.json for MCP tools. Do NOT accept the story or merge - commit your work and stop. If the user asks to review your changes, tell them to run: cd \"{{worktree_path}}\" && git difftool {{base_branch}}...HEAD\n\nIMPORTANT: Commit all your work before your process exits. The server will automatically run acceptance gates (cargo clippy + tests) when your process exits and advance the pipeline based on the results."
+prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .story_kit/README.md to understand the dev process. The story details are in your prompt above. Follow the SDTW process through implementation and verification (Steps 1-3). The worktree and feature branch already exist - do not create them. Check .mcp.json for MCP tools. Do NOT accept the story or merge - commit your work and stop. If the user asks to review your changes, tell them to run: cd \"{{worktree_path}}\" && git difftool {{base_branch}}...HEAD\n\nIMPORTANT: Commit all your work before your process exits. The server will automatically run acceptance gates (cargo clippy + tests) when your process exits and advance the pipeline based on the results."
 system_prompt = "You are a full-stack engineer working autonomously in a git worktree. Follow the Story-Driven Test Workflow strictly. Run cargo clippy and biome checks before considering work complete. Commit all your work before finishing - use a descriptive commit message. Do not accept stories, move them to archived, or merge to master - a human will do that. Do not coordinate with other agents - focus on your assigned story. The server automatically runs acceptance gates when your process exits."
 
 [[agent]]
@@ -72,7 +72,7 @@ role = "Full-stack engineer. Implements features across all components."
 model = "sonnet-4.6"
 max_turns = 50
 max_budget_usd = 5.00
-prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .story_kit/README.md to understand the dev process. Pick up the story from .story_kit/work/ - move it to work/2_current/ if needed. Follow the SDTW process through implementation and verification (Steps 1-3). The worktree and feature branch already exist - do not create them. Check .mcp.json for MCP tools. Do NOT accept the story or merge - commit your work and stop. If the user asks to review your changes, tell them to run: cd \"{{worktree_path}}\" && git difftool {{base_branch}}...HEAD\n\nIMPORTANT: Commit all your work before your process exits. The server will automatically run acceptance gates (cargo clippy + tests) when your process exits and advance the pipeline based on the results."
+prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .story_kit/README.md to understand the dev process. The story details are in your prompt above. Follow the SDTW process through implementation and verification (Steps 1-3). The worktree and feature branch already exist - do not create them. Check .mcp.json for MCP tools. Do NOT accept the story or merge - commit your work and stop. If the user asks to review your changes, tell them to run: cd \"{{worktree_path}}\" && git difftool {{base_branch}}...HEAD\n\nIMPORTANT: Commit all your work before your process exits. The server will automatically run acceptance gates (cargo clippy + tests) when your process exits and advance the pipeline based on the results."
 system_prompt = "You are a full-stack engineer working autonomously in a git worktree. Follow the Story-Driven Test Workflow strictly. Run cargo clippy and biome checks before considering work complete. Commit all your work before finishing - use a descriptive commit message. Do not accept stories, move them to archived, or merge to master - a human will do that. Do not coordinate with other agents - focus on your assigned story. The server automatically runs acceptance gates when your process exits."
 
 [[agent]]
@@ -81,7 +81,7 @@ role = "Senior full-stack engineer for complex tasks. Implements features across
 model = "opus"
 max_turns = 80
 max_budget_usd = 20.00
-prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .story_kit/README.md to understand the dev process. Pick up the story from .story_kit/work/ - move it to work/2_current/ if needed. Follow the SDTW process through implementation and verification (Steps 1-3). The worktree and feature branch already exist - do not create them. Check .mcp.json for MCP tools. Do NOT accept the story or merge - commit your work and stop. If the user asks to review your changes, tell them to run: cd \"{{worktree_path}}\" && git difftool {{base_branch}}...HEAD\n\nIMPORTANT: Commit all your work before your process exits. The server will automatically run acceptance gates (cargo clippy + tests) when your process exits and advance the pipeline based on the results."
+prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .story_kit/README.md to understand the dev process. The story details are in your prompt above. Follow the SDTW process through implementation and verification (Steps 1-3). The worktree and feature branch already exist - do not create them. Check .mcp.json for MCP tools. Do NOT accept the story or merge - commit your work and stop. If the user asks to review your changes, tell them to run: cd \"{{worktree_path}}\" && git difftool {{base_branch}}...HEAD\n\nIMPORTANT: Commit all your work before your process exits. The server will automatically run acceptance gates (cargo clippy + tests) when your process exits and advance the pipeline based on the results."
 system_prompt = "You are a senior full-stack engineer working autonomously in a git worktree. You handle complex tasks requiring deep architectural understanding. Follow the Story-Driven Test Workflow strictly. Run cargo clippy and biome checks before considering work complete. Commit all your work before finishing - use a descriptive commit message. Do not accept stories, move them to archived, or merge to master - a human will do that. Do not coordinate with other agents - focus on your assigned story. The server automatically runs acceptance gates when your process exits."
 
 [[agent]]

server/src/worktree.rs

@@ -71,8 +71,12 @@ pub async fn create_worktree(
     let base_branch = detect_base_branch(project_root);
     let root = project_root.to_path_buf();
 
-    // Already exists — reuse
+    // Already exists — reuse (ensure sparse checkout is configured)
     if wt_path.exists() {
+        let wt_clone = wt_path.clone();
+        tokio::task::spawn_blocking(move || configure_sparse_checkout(&wt_clone))
+            .await
+            .map_err(|e| format!("spawn_blocking: {e}"))??;
         write_mcp_json(&wt_path, port)?;
         run_setup_commands(&wt_path, config).await?;
         return Ok(WorktreeInfo {
@@ -143,6 +147,62 @@ fn create_worktree_sync(
         return Err(format!("git worktree add failed: {stderr}"));
     }
 
+    // Enable sparse checkout to exclude pipeline files from the worktree.
+    // This prevents .story_kit/work/ changes from ending up in feature branches,
+    // which cause rename/delete merge conflicts when merging back to master.
+    configure_sparse_checkout(wt_path)?;
+
+    Ok(())
+}
+
+/// Configure sparse checkout on a worktree to exclude `.story_kit/work/`.
+///
+/// This prevents pipeline file moves (upcoming → current → qa → merge → archived)
+/// from being committed on feature branches, which avoids rename/delete merge
+/// conflicts when merging back to master.
+fn configure_sparse_checkout(wt_path: &Path) -> Result<(), String> {
+    // Enable sparse checkout via git config (non-cone mode for pattern support)
+    let output = Command::new("git")
+        .args(["config", "core.sparseCheckout", "true"])
+        .current_dir(wt_path)
+        .output()
+        .map_err(|e| format!("sparse-checkout config: {e}"))?;
+
+    if !output.status.success() {
+        let stderr = String::from_utf8_lossy(&output.stderr);
+        return Err(format!("sparse-checkout config failed: {stderr}"));
+    }
+
+    // Resolve the actual git dir (worktrees use a .git file pointing elsewhere)
+    let git_dir_output = Command::new("git")
+        .args(["rev-parse", "--git-dir"])
+        .current_dir(wt_path)
+        .output()
+        .map_err(|e| format!("git rev-parse --git-dir: {e}"))?;
+
+    let git_dir = PathBuf::from(
+        String::from_utf8_lossy(&git_dir_output.stdout).trim().to_string(),
+    );
+
+    // Write sparse-checkout patterns: include everything, exclude .story_kit/work/
+    let info_dir = git_dir.join("info");
+    std::fs::create_dir_all(&info_dir)
+        .map_err(|e| format!("Create sparse-checkout dir: {e}"))?;
+    std::fs::write(info_dir.join("sparse-checkout"), "/*\n!.story_kit/work/\n")
+        .map_err(|e| format!("Write sparse-checkout: {e}"))?;
+
+    // Re-read the working tree to apply sparse checkout rules
+    let output = Command::new("git")
+        .args(["read-tree", "-mu", "HEAD"])
+        .current_dir(wt_path)
+        .output()
+        .map_err(|e| format!("git read-tree: {e}"))?;
+
+    if !output.status.success() {
+        let stderr = String::from_utf8_lossy(&output.stderr);
+        return Err(format!("git read-tree failed: {stderr}"));
+    }
+
     Ok(())
 }
 
@@ -380,4 +440,40 @@ mod tests {
         );
         assert!(wt_path.exists());
     }
+
+    #[test]
+    fn sparse_checkout_excludes_story_kit_work() {
+        let tmp = TempDir::new().unwrap();
+        let project_root = tmp.path().join("my-project");
+        fs::create_dir_all(&project_root).unwrap();
+        init_git_repo(&project_root);
+
+        // Create a tracked file under .story_kit/work/ on the initial branch
+        let work_dir = project_root.join(".story_kit").join("work");
+        fs::create_dir_all(&work_dir).unwrap();
+        fs::write(work_dir.join("test_story.md"), "# Test").unwrap();
+        Command::new("git")
+            .args(["add", "."])
+            .current_dir(&project_root)
+            .output()
+            .unwrap();
+        Command::new("git")
+            .args(["commit", "-m", "add work file"])
+            .current_dir(&project_root)
+            .output()
+            .unwrap();
+
+        let wt_path = tmp.path().join("my-worktree");
+        let branch = "feature/test-sparse";
+        create_worktree_sync(&project_root, &wt_path, branch).unwrap();
+
+        // .story_kit/work/ should not exist in the worktree
+        assert!(
+            !wt_path.join(".story_kit").join("work").exists(),
+            ".story_kit/work/ should be excluded by sparse checkout"
+        );
+
+        // Other files should still exist
+        assert!(wt_path.join(".git").exists());
+    }
 }