diff --git a/surfsense_backend/app/agents/new_chat/chat_deepagent.py b/surfsense_backend/app/agents/new_chat/chat_deepagent.py index 8fd5f3b71..6c8deb409 100644 --- a/surfsense_backend/app/agents/new_chat/chat_deepagent.py +++ b/surfsense_backend/app/agents/new_chat/chat_deepagent.py @@ -50,6 +50,9 @@ def create_surfsense_deep_agent( - display_image: Display images in chat - scrape_webpage: Extract content from webpages + The agent also includes TodoListMiddleware by default (via create_deep_agent) which provides: + - write_todos: Create and update planning/todo lists for complex tasks + The system prompt can be configured via agent_config: - Custom system instructions (or use defaults) - Citation toggle (enable/disable citation requirements) @@ -138,6 +141,7 @@ def create_surfsense_deep_agent( system_prompt = build_surfsense_system_prompt() # Create the deep agent with system prompt and checkpointer + # Note: TodoListMiddleware (write_todos) is included by default in create_deep_agent agent = create_deep_agent( model=llm, tools=tools, diff --git a/surfsense_backend/app/agents/new_chat/system_prompt.py b/surfsense_backend/app/agents/new_chat/system_prompt.py index 54fa77c2e..ae4f96fdd 100644 --- a/surfsense_backend/app/agents/new_chat/system_prompt.py +++ b/surfsense_backend/app/agents/new_chat/system_prompt.py @@ -111,64 +111,19 @@ You have access to the following tools: * Don't show every image - just the most relevant 1-3 images that enhance understanding. 6. write_todos: Create and update a planning/todo list to break down complex tasks. - - Use this tool when you need to plan your approach to a complex task. - - This displays a visual plan with progress tracking and status indicators. - - - USAGE PATTERN: - * First call: Create the plan with first task as "in_progress", rest as "pending" - * Subsequent calls: ONLY update task statuses (mark completed/in_progress) - * Use the EXACT SAME title and task IDs for all updates - - - ABSOLUTELY FORBIDDEN - WILL BREAK THE SYSTEM: - * ONLY ONE PLAN PER CONVERSATION - NEVER call write_todos a second time to create a new plan - * When all tasks in your plan are "completed", your response is FINISHED - STOP - * NEVER restart your response after completing it - * NEVER generate the same explanation twice - * NEVER create a second introduction or overview after the first one - * NEVER say "Let me explain..." twice for the same topic - * If you've already explained something, DO NOT explain it again - * After your response ends, STOP - do not continue generating - * NEVER say you're creating a "document", "report", "roadmap", "analysis", or any artifact - * Do NOT use phrases like "This report is based on..." or "Based on my research..." - * Just answer the question directly - do not roleplay producing a deliverable - - - CORRECT BEHAVIOR: - * Call write_todos to update statuses as you progress - * Each section of your response appears EXACTLY ONCE - * When you finish explaining all tasks, your response is COMPLETE - * Do NOT generate additional content after concluding - - - CONTENT QUALITY: - * Provide thorough, detailed explanations for each task - * The restriction is on DUPLICATING content, not on depth or detail - * Each task deserves a complete, comprehensive explanation - * Be as detailed as needed - just don't repeat yourself - + - IMPORTANT: Use this tool when the user asks you to create a plan, break down a task, or explain something in structured steps. + - This tool creates a visual plan with progress tracking that the user can see in the UI. - When to use: - * Breaking down a complex multi-step task (3-5 tasks recommended) - * Showing the user what steps you'll take to solve their problem - * Creating an implementation roadmap - + * User asks to "create a plan" or "break down" a task + * User asks for "steps" to do something + * User asks you to "explain" something in sections + * Any multi-step task that would benefit from structured planning - Args: - todos: List of todo items, each with: - * id: Unique identifier (KEEP SAME IDs across updates) - * content: Description of the task (KEEP SAME content across updates) - * status: "pending", "in_progress", or "completed" - * description: Optional subtask/detail text shown when the item is expanded (e.g., "Analyzing document structure and key concepts") - - title: Title for the plan (MUST BE IDENTICAL across all updates) - - description: Optional context description - - - Returns: A visual plan card with progress bar and status indicators - - - CORRECT PATTERN: - 1. Create plan with task 1 as "in_progress" - 2. Explain task 1 content in detail - 3. Update plan: task 1 "completed", task 2 "in_progress" - 4. Explain task 2 content (NEW content, not repeating task 1) - 5. Continue until all tasks are "completed" - 6. When all tasks are "completed", your response is FINISHED - 7. STOP IMMEDIATELY - do NOT create another plan or continue generating - 8. ONE PLAN ONLY - never call write_todos again after completing all tasks + * content: Description of the task (required) + * status: "pending", "in_progress", or "completed" (required) + - The tool automatically adds IDs and formats the output for the UI. + - Example: When user says "Create a plan for building a REST API", call write_todos with todos containing the steps. - User: "Fetch all my notes and what's in them?" @@ -227,21 +182,13 @@ You have access to the following tools: - Call: `display_image(src="https://example.com/nn-diagram.png", alt="Neural Network Diagram", title="Neural Network Architecture")` - Then provide your explanation, referencing the displayed image -- User: "Help me implement a user authentication system" - - Step 1: Create plan with task 1 in_progress: - `write_todos(title="Auth Plan", todos=[{"id": "1", "content": "Design database schema", "status": "in_progress"}, {"id": "2", "content": "Set up password hashing", "status": "pending"}, {"id": "3", "content": "Create endpoints", "status": "pending"}])` - - Step 2: Provide DETAILED explanation of database schema design - - Step 3: Update plan (task 1 done, task 2 in_progress): - `write_todos(title="Auth Plan", todos=[{"id": "1", "content": "Design database schema", "status": "completed"}, {"id": "2", "content": "Set up password hashing", "status": "in_progress"}, {"id": "3", "content": "Create endpoints", "status": "pending"}])` - - Step 4: Provide DETAILED explanation of password hashing (NEW content only) - - Step 5: Update plan, explain endpoints in detail - - Step 6: Mark all complete, END response - DO NOT restart or regenerate - - FORBIDDEN: Do not go back and explain schema again after step 2 +- User: "Create a plan for building a user authentication system" + - Call: `write_todos(todos=[{"content": "Design database schema for users and sessions", "status": "in_progress"}, {"content": "Implement registration and login endpoints", "status": "pending"}, {"content": "Add password reset functionality", "status": "pending"}])` + - Then explain each step in detail as you work through them -- User: "How should I approach refactoring this large codebase?" - - Create plan, explain each step with thorough detail, update statuses as you go - - Each explanation is comprehensive but appears ONLY ONCE - - When finished with all tasks, STOP - do not continue generating +- User: "Break down how to build a REST API into steps" + - Call: `write_todos(todos=[{"content": "Design API endpoints and data models", "status": "in_progress"}, {"content": "Set up server framework and routing", "status": "pending"}, {"content": "Implement CRUD operations", "status": "pending"}, {"content": "Add authentication and error handling", "status": "pending"}])` + - Then provide detailed explanations for each step """ diff --git a/surfsense_backend/app/agents/new_chat/tools/registry.py b/surfsense_backend/app/agents/new_chat/tools/registry.py index 5c746d726..bc305aecc 100644 --- a/surfsense_backend/app/agents/new_chat/tools/registry.py +++ b/surfsense_backend/app/agents/new_chat/tools/registry.py @@ -48,7 +48,6 @@ from .knowledge_base import create_search_knowledge_base_tool from .link_preview import create_link_preview_tool from .podcast import create_generate_podcast_tool from .scrape_webpage import create_scrape_webpage_tool -from .write_todos import create_write_todos_tool # ============================================================================= # Tool Definition @@ -126,13 +125,7 @@ BUILTIN_TOOLS: list[ToolDefinition] = [ ), requires=[], # firecrawl_api_key is optional ), - # Planning/Todo tool - creates visual todo lists - ToolDefinition( - name="write_todos", - description="Create a planning/todo list to break down complex tasks", - factory=lambda deps: create_write_todos_tool(), - requires=[], - ), + # Note: write_todos is now provided by TodoListMiddleware from deepagents # ========================================================================= # ADD YOUR CUSTOM TOOLS BELOW # ========================================================================= diff --git a/surfsense_backend/app/agents/new_chat/tools/write_todos.py b/surfsense_backend/app/agents/new_chat/tools/write_todos.py deleted file mode 100644 index 466c74997..000000000 --- a/surfsense_backend/app/agents/new_chat/tools/write_todos.py +++ /dev/null @@ -1,99 +0,0 @@ -""" -Write todos tool for the SurfSense agent. - -This module provides a tool for creating and displaying a planning/todo list -in the chat UI. It helps the agent break down complex tasks into steps. -""" - -from typing import Any - -from langchain_core.tools import tool - - -def create_write_todos_tool(): - """ - Factory function to create the write_todos tool. - - Returns: - A configured tool function for writing todos/plans. - """ - - @tool - async def write_todos( - todos: list[dict[str, Any]], - title: str = "Planning Approach", - description: str | None = None, - ) -> dict[str, Any]: - """ - Create a planning/todo list to break down a complex task. - - Use this tool when you need to plan your approach to a complex task - or show the user a step-by-step breakdown of what you'll do. - - This displays a visual plan with: - - Progress tracking (X of Y complete) - - Status indicators (pending, in progress, completed, cancelled) - - Expandable details for each step - - Args: - todos: List of todo items. Each item should have: - - id: Unique identifier for the todo - - content: Description of the task - - status: One of "pending", "in_progress", "completed", "cancelled" - - description: Optional subtask/detail text shown when the item is expanded - title: Title for the plan (default: "Planning Approach") - description: Optional description providing context - - Returns: - A dictionary containing the plan data for the UI to render. - - Example: - write_todos( - title="Implementation Plan", - description="Steps to add the new feature", - todos=[ - {"id": "1", "content": "Analyze requirements", "status": "completed", "description": "Reviewed all user stories and acceptance criteria"}, - {"id": "2", "content": "Design solution", "status": "in_progress", "description": "Creating component architecture and data flow diagrams"}, - {"id": "3", "content": "Write code", "status": "pending"}, - {"id": "4", "content": "Add tests", "status": "pending", "description": "Unit tests and integration tests for all new components"}, - ] - ) - """ - # Generate a unique plan ID - import uuid - - plan_id = f"plan-{uuid.uuid4().hex[:8]}" - - # Transform todos to the expected format for the UI - formatted_todos = [] - for i, todo in enumerate(todos): - todo_id = todo.get("id", f"todo-{i}") - content = todo.get("content", "") - status = todo.get("status", "pending") - todo_description = todo.get("description") - - # Validate status - valid_statuses = ["pending", "in_progress", "completed", "cancelled"] - if status not in valid_statuses: - status = "pending" - - todo_item = { - "id": todo_id, - "label": content, - "status": status, - } - - # Only include description if provided - if todo_description: - todo_item["description"] = todo_description - - formatted_todos.append(todo_item) - - return { - "id": plan_id, - "title": title, - "description": description, - "todos": formatted_todos, - } - - return write_todos diff --git a/surfsense_backend/app/tasks/chat/stream_new_chat.py b/surfsense_backend/app/tasks/chat/stream_new_chat.py index 5bb33e399..602dac0a5 100644 --- a/surfsense_backend/app/tasks/chat/stream_new_chat.py +++ b/surfsense_backend/app/tasks/chat/stream_new_chat.py @@ -69,6 +69,30 @@ def format_mentioned_documents_as_context(documents: list[Document]) -> str: return "\n".join(context_parts) +def extract_todos_from_deepagents(command_output) -> dict: + """ + Extract todos from deepagents' TodoListMiddleware Command output. + + deepagents returns a Command object with: + - Command.update['todos'] = [{'content': '...', 'status': '...'}] + + Returns the todos directly (no transformation needed - UI matches deepagents format). + """ + todos_data = [] + if hasattr(command_output, "update"): + # It's a Command object from deepagents + update = command_output.update + todos_data = update.get("todos", []) + elif isinstance(command_output, dict): + # Already a dict - check if it has todos directly or in update + if "todos" in command_output: + todos_data = command_output.get("todos", []) + elif "update" in command_output and isinstance(command_output["update"], dict): + todos_data = command_output["update"].get("todos", []) + + return {"todos": todos_data} + + async def stream_new_chat( user_query: str, search_space_id: int, @@ -557,9 +581,11 @@ async def stream_new_chat( tool_name = event.get("name", "unknown_tool") raw_output = event.get("data", {}).get("output", "") - # Extract content from ToolMessage if needed - # LangGraph may return a ToolMessage object instead of raw dict - if hasattr(raw_output, "content"): + # Handle deepagents' write_todos Command object specially + if tool_name == "write_todos" and hasattr(raw_output, "update"): + # deepagents returns a Command object - extract todos directly + tool_output = extract_todos_from_deepagents(raw_output) + elif hasattr(raw_output, "content"): # It's a ToolMessage object - extract the content content = raw_output.content # If content is a string that looks like JSON, try to parse it @@ -721,12 +747,10 @@ async def stream_new_chat( elif tool_name == "write_todos": # Build completion items for planning if isinstance(tool_output, dict): - plan_title = tool_output.get("title", "Plan") todos = tool_output.get("todos", []) todo_count = len(todos) if isinstance(todos, list) else 0 completed_items = [ *last_active_step_items, - f"Plan: {plan_title[:50]}{'...' if len(plan_title) > 50 else ''}", f"Tasks: {todo_count} steps defined", ] else: @@ -883,11 +907,10 @@ async def stream_new_chat( ) # Send terminal message with plan info if isinstance(tool_output, dict): - title = tool_output.get("title", "Plan") todos = tool_output.get("todos", []) todo_count = len(todos) if isinstance(todos, list) else 0 yield streaming_service.format_terminal_info( - f"Plan created: {title} ({todo_count} tasks)", + f"Plan created ({todo_count} tasks)", "success", ) else: diff --git a/surfsense_web/atoms/chat/plan-state.atom.ts b/surfsense_web/atoms/chat/plan-state.atom.ts index 22c33ff90..2436dd300 100644 --- a/surfsense_web/atoms/chat/plan-state.atom.ts +++ b/surfsense_web/atoms/chat/plan-state.atom.ts @@ -11,15 +11,13 @@ import { atom } from "jotai"; export interface PlanTodo { id: string; - label: string; + content: string; status: "pending" | "in_progress" | "completed" | "cancelled"; - description?: string; } export interface PlanState { id: string; title: string; - description?: string; todos: PlanTodo[]; lastUpdated: number; /** The toolCallId of the first component that rendered this plan */ @@ -96,7 +94,6 @@ export const planStatesAtom = atom>(new Map()); export interface UpdatePlanInput { id: string; title: string; - description?: string; todos: PlanTodo[]; toolCallId: string; } @@ -119,7 +116,6 @@ export const updatePlanStateAtom = atom(null, (get, set, plan: UpdatePlanInput) states.set(canonicalTitle, { id: plan.id, title: canonicalTitle, - description: plan.description, todos: plan.todos, lastUpdated: Date.now(), ownerToolCallId, @@ -152,12 +148,10 @@ export interface HydratePlanInput { result: { id?: string; title?: string; - description?: string; todos?: Array<{ - id: string; - label: string; + id?: string; + content: string; status: "pending" | "in_progress" | "completed" | "cancelled"; - description?: string; }>; }; } @@ -166,7 +160,7 @@ export const hydratePlanStateAtom = atom(null, (get, set, plan: HydratePlanInput if (!plan.result?.todos || plan.result.todos.length === 0) return; const states = new Map(get(planStatesAtom)); - const title = plan.result.title || "Planning Approach"; + const title = plan.result.title || "Plan"; // Register this as the owner if no plan exists yet registerPlanOwner(title, plan.toolCallId); @@ -181,8 +175,11 @@ export const hydratePlanStateAtom = atom(null, (get, set, plan: HydratePlanInput states.set(canonicalTitle, { id: plan.result.id || `plan-${Date.now()}`, title: canonicalTitle, - description: plan.result.description, - todos: plan.result.todos, + todos: plan.result.todos.map((t, i) => ({ + id: t.id || `todo-${i}`, + content: t.content, + status: t.status, + })), lastUpdated: Date.now(), ownerToolCallId, }); diff --git a/surfsense_web/components/tool-ui/index.ts b/surfsense_web/components/tool-ui/index.ts index 65ddf818c..e48919de2 100644 --- a/surfsense_web/components/tool-ui/index.ts +++ b/surfsense_web/components/tool-ui/index.ts @@ -77,10 +77,4 @@ export { type PlanTodo, type TodoStatus, } from "./plan"; -export { - WriteTodosToolUI, - WriteTodosArgsSchema, - WriteTodosResultSchema, - type WriteTodosArgs, - type WriteTodosResult, -} from "./write-todos"; +export { WriteTodosToolUI, WriteTodosSchema, type WriteTodosData } from "./write-todos"; diff --git a/surfsense_web/components/tool-ui/plan/plan.tsx b/surfsense_web/components/tool-ui/plan/plan.tsx index d99dbc1c6..5c9335022 100644 --- a/surfsense_web/components/tool-ui/plan/plan.tsx +++ b/surfsense_web/components/tool-ui/plan/plan.tsx @@ -1,22 +1,16 @@ "use client"; -import { CheckCircle2, Circle, CircleDashed, PartyPopper, XCircle } from "lucide-react"; +import { CheckCircle2, Circle, CircleDashed, ListTodo, PartyPopper, XCircle } from "lucide-react"; import type { FC } from "react"; import { useMemo, useState } from "react"; -import { - Accordion, - AccordionContent, - AccordionItem, - AccordionTrigger, -} from "@/components/ui/accordion"; import { Button } from "@/components/ui/button"; -import { Card, CardContent, CardDescription, CardHeader, CardTitle } from "@/components/ui/card"; +import { Card, CardContent, CardHeader, CardTitle } from "@/components/ui/card"; import { Collapsible, CollapsibleContent, CollapsibleTrigger } from "@/components/ui/collapsible"; import { TextShimmerLoader } from "@/components/prompt-kit/loader"; import { Progress } from "@/components/ui/progress"; import { cn } from "@/lib/utils"; import type { Action, ActionsConfig } from "../shared/schema"; -import type { PlanTodo, TodoStatus } from "./schema"; +import type { TodoStatus } from "./schema"; // ============================================================================ // Status Icon Component @@ -57,7 +51,7 @@ const StatusIcon: FC = ({ status, className, isStreaming = true // ============================================================================ interface TodoItemProps { - todo: PlanTodo; + todo: { id: string; content: string; status: TodoStatus }; /** When false, in_progress items show as static (no spinner/pulse) */ isStreaming?: boolean; } @@ -67,38 +61,22 @@ const TodoItem: FC = ({ todo, isStreaming = true }) => { // Only show shimmer animation if streaming and in progress const isShimmer = todo.status === "in_progress" && isStreaming; - // Render the label with optional shimmer effect - const renderLabel = () => { + // Render the content with optional shimmer effect + const renderContent = () => { if (isShimmer) { - return ; + return ; } return ( - - {todo.label} + + {todo.content} ); }; - if (todo.description) { - return ( - - -
- - {renderLabel()} -
- - -

{todo.description}

- - - ); - } - return (
- {renderLabel()} + {renderContent()}
); }; @@ -110,8 +88,7 @@ const TodoItem: FC = ({ todo, isStreaming = true }) => { export interface PlanProps { id: string; title: string; - description?: string; - todos: PlanTodo[]; + todos: Array<{ id: string; content: string; status: TodoStatus }>; maxVisibleTodos?: number; showProgress?: boolean; /** When false, in_progress items show as static (no spinner/pulse animations) */ @@ -125,7 +102,6 @@ export interface PlanProps { export const Plan: FC = ({ id, title, - description, todos, maxVisibleTodos = 4, showProgress = true, @@ -151,9 +127,6 @@ export const Plan: FC = ({ const hiddenTodos = todos.slice(maxVisibleTodos); const hasHiddenTodos = hiddenTodos.length > 0; - // Check if any todo has a description (for accordion mode) - const hasDescriptions = todos.some((t) => t.description); - // Handle action click const handleAction = (actionId: string) => { if (onBeforeResponseAction && !onBeforeResponseAction(actionId)) { @@ -172,22 +145,7 @@ export const Plan: FC = ({ ].filter(Boolean) as Action[]; }, [responseActions]); - // Get default expanded items (in_progress items with descriptions) - const defaultExpandedIds = useMemo(() => { - return todos.filter((t) => t.description && t.status === "in_progress").map((t) => t.id); - }, [todos]); - - const TodoList: FC<{ items: PlanTodo[] }> = ({ items }) => { - if (hasDescriptions) { - return ( - - {items.map((todo) => ( - - ))} - - ); - } - + const TodoList: FC<{ items: typeof todos }> = ({ items }) => { return (
{items.map((todo) => ( @@ -201,11 +159,9 @@ export const Plan: FC = ({
-
- {title} - {description && ( - {description} - )} +
+ + {title}
{isAllComplete && (
@@ -216,13 +172,13 @@ export const Plan: FC = ({ {showProgress && (
-
- - {progress.completed} of {progress.total} complete - - {Math.round(progress.percentage)}% -
- +
+ + {progress.completed} of {progress.total} complete + + {Math.round(progress.percentage)}% +
+
)} diff --git a/surfsense_web/components/tool-ui/plan/schema.ts b/surfsense_web/components/tool-ui/plan/schema.ts index fed49128a..a8263cf71 100644 --- a/surfsense_web/components/tool-ui/plan/schema.ts +++ b/surfsense_web/components/tool-ui/plan/schema.ts @@ -8,23 +8,25 @@ export type TodoStatus = z.infer; /** * Single todo item in a plan + * Matches deepagents TodoListMiddleware output: { content, status } + * id is auto-generated if not provided */ export const PlanTodoSchema = z.object({ - id: z.string(), - label: z.string(), + id: z.string().optional(), + content: z.string(), status: TodoStatusSchema, - description: z.string().optional(), }); export type PlanTodo = z.infer; /** * Serializable plan schema for tool results + * Matches deepagents TodoListMiddleware output format + * id/title are auto-generated if not provided */ export const SerializablePlanSchema = z.object({ - id: z.string(), - title: z.string(), - description: z.string().optional(), + id: z.string().optional(), + title: z.string().optional(), todos: z.array(PlanTodoSchema).min(1), maxVisibleTodos: z.number().optional(), showProgress: z.boolean().optional(), @@ -33,9 +35,21 @@ export const SerializablePlanSchema = z.object({ export type SerializablePlan = z.infer; /** - * Parse and validate a serializable plan from tool result + * Normalized plan with required fields (after auto-generation) */ -export function parseSerializablePlan(data: unknown): SerializablePlan { +export interface NormalizedPlan { + id: string; + title: string; + todos: Array<{ id: string; content: string; status: TodoStatus }>; + maxVisibleTodos?: number; + showProgress?: boolean; +} + +/** + * Parse and normalize a plan from tool result + * Auto-generates id/title if not provided (for deepagents compatibility) + */ +export function parseSerializablePlan(data: unknown): NormalizedPlan { const result = SerializablePlanSchema.safeParse(data); if (!result.success) { @@ -45,22 +59,33 @@ export function parseSerializablePlan(data: unknown): SerializablePlan { const obj = (data && typeof data === "object" ? data : {}) as Record; return { - id: typeof obj.id === "string" ? obj.id : "unknown", + id: typeof obj.id === "string" ? obj.id : `plan-${Date.now()}`, title: typeof obj.title === "string" ? obj.title : "Plan", - description: typeof obj.description === "string" ? obj.description : undefined, todos: Array.isArray(obj.todos) - ? obj.todos.map((t, i) => ({ - id: typeof (t as any)?.id === "string" ? (t as any).id : `todo-${i}`, - label: typeof (t as any)?.label === "string" ? (t as any).label : "Task", - status: TodoStatusSchema.safeParse((t as any)?.status).success - ? (t as any).status - : "pending", - description: - typeof (t as any)?.description === "string" ? (t as any).description : undefined, - })) - : [{ id: "1", label: "No tasks", status: "pending" as const }], + ? obj.todos.map((t: unknown, i: number) => { + const todo = t as Record; + return { + id: typeof todo?.id === "string" ? todo.id : `todo-${i}`, + content: typeof todo?.content === "string" ? todo.content : "Task", + status: TodoStatusSchema.safeParse(todo?.status).success + ? (todo.status as TodoStatus) + : ("pending" as const), + }; + }) + : [{ id: "1", content: "No tasks", status: "pending" as const }], }; } - return result.data; + // Normalize: add id/title if missing + return { + id: result.data.id || `plan-${Date.now()}`, + title: result.data.title || "Plan", + todos: result.data.todos.map((t, i) => ({ + id: t.id || `todo-${i}`, + content: t.content, + status: t.status, + })), + maxVisibleTodos: result.data.maxVisibleTodos, + showProgress: result.data.showProgress, + }; } diff --git a/surfsense_web/components/tool-ui/write-todos.tsx b/surfsense_web/components/tool-ui/write-todos.tsx index 81e7ab978..c3db8879a 100644 --- a/surfsense_web/components/tool-ui/write-todos.tsx +++ b/surfsense_web/components/tool-ui/write-todos.tsx @@ -14,73 +14,30 @@ import { import { Plan, PlanErrorBoundary, parseSerializablePlan, TodoStatusSchema } from "./plan"; // ============================================================================ -// Zod Schemas +// Zod Schemas - Matching deepagents TodoListMiddleware output // ============================================================================ /** - * Schema for a single todo item in the args - * Note: Using nullish() with transform to convert null → undefined for Plan compatibility + * Schema for a single todo item (matches deepagents output) */ -const WriteTodosArgsTodoSchema = z.object({ - id: z.string(), +const TodoItemSchema = z.object({ content: z.string(), status: TodoStatusSchema, - description: z - .string() - .nullish() - .transform((v) => v ?? undefined), }); /** - * Schema for write_todos tool arguments - * Note: Using nullish() with transform to convert null → undefined for Plan compatibility + * Schema for write_todos tool args/result (matches deepagents output) + * deepagents provides: { todos: [{ content, status }] } */ -const WriteTodosArgsSchema = z.object({ - title: z - .string() - .nullish() - .transform((v) => v ?? undefined), - description: z - .string() - .nullish() - .transform((v) => v ?? undefined), - todos: z.array(WriteTodosArgsTodoSchema).nullish(), -}); - -/** - * Schema for a single todo item in the result - * Note: Using nullish() with transform to convert null → undefined for Plan compatibility - */ -const WriteTodosResultTodoSchema = z.object({ - id: z.string(), - label: z.string(), - status: TodoStatusSchema, - description: z - .string() - .nullish() - .transform((v) => v ?? undefined), -}); - -/** - * Schema for write_todos tool result - * Note: Using nullish() with transform to convert null → undefined for Plan compatibility - */ -const WriteTodosResultSchema = z.object({ - id: z.string(), - title: z.string(), - description: z - .string() - .nullish() - .transform((v) => v ?? undefined), - todos: z.array(WriteTodosResultTodoSchema), +const WriteTodosSchema = z.object({ + todos: z.array(TodoItemSchema).nullish(), }); // ============================================================================ // Types // ============================================================================ -type WriteTodosArgs = z.infer; -type WriteTodosResult = z.infer; +type WriteTodosData = z.infer; /** * Loading state component @@ -96,103 +53,65 @@ function WriteTodosLoading() { ); } -/** - * Transform tool args to result format - * This handles the case where the LLM is streaming the tool call - */ -function transformArgsToResult(args: WriteTodosArgs): WriteTodosResult | null { - if (!args.todos || !Array.isArray(args.todos) || args.todos.length === 0) { - return null; - } - - return { - id: `plan-${Date.now()}`, - title: args.title || "Planning Approach", - description: args.description, - todos: args.todos.map((todo, index) => ({ - id: todo.id || `todo-${index}`, - label: todo.content || "Task", - status: todo.status || "pending", - description: todo.description, - })), - }; -} - /** * WriteTodos Tool UI Component * * Displays the agent's planning/todo list with a beautiful UI. - * Shows progress, status indicators, and expandable details. + * Uses deepagents TodoListMiddleware output directly: { todos: [{ content, status }] } * - * FIXED POSITION: When the same plan (by title) is updated multiple times, + * FIXED POSITION: When multiple write_todos calls happen in a conversation, * only the FIRST component renders. Subsequent updates just update the - * shared state, and the first component reads from it. This prevents - * layout shift when plans are updated. + * shared state, and the first component reads from it. */ -export const WriteTodosToolUI = makeAssistantToolUI({ +export const WriteTodosToolUI = makeAssistantToolUI({ toolName: "write_todos", render: function WriteTodosUI({ args, result, status, toolCallId }) { const updatePlanState = useSetAtom(updatePlanStateAtom); const planStates = useAtomValue(planStatesAtom); - // Check if the THREAD is running (not just this tool) - // This hook subscribes to state changes, so it re-renders when thread stops + // Check if the THREAD is running const isThreadRunning = useAssistantState(({ thread }) => thread.isRunning); - // Get the plan data (from result or args) - const planData = result || transformArgsToResult(args); - const rawTitle = planData?.title || args.title || "Planning Approach"; + // Use result if available, otherwise args (for streaming) + const data = result || args; + const hasTodos = data?.todos && data.todos.length > 0; - // SYNCHRONOUS ownership check - happens immediately, no race conditions - // ONE PLAN PER CONVERSATION: Only first write_todos call becomes owner + // Fixed title for all plans in conversation + const planTitle = "Plan"; + + // SYNCHRONOUS ownership check const isOwner = useMemo(() => { - return registerPlanOwner(rawTitle, toolCallId); - }, [rawTitle, toolCallId]); + return registerPlanOwner(planTitle, toolCallId); + }, [planTitle, toolCallId]); - // Get canonical title - always use the FIRST plan's title - // This ensures all updates go to the same plan state - const planTitle = useMemo(() => getCanonicalPlanTitle(rawTitle), [rawTitle]); + // Get canonical title + const canonicalTitle = useMemo(() => getCanonicalPlanTitle(planTitle), [planTitle]); - // Register/update the plan state - ALWAYS use canonical title + // Register/update the plan state useEffect(() => { - if (planData) { + if (hasTodos) { + const normalizedPlan = parseSerializablePlan({ todos: data.todos }); updatePlanState({ - id: planData.id, - title: planTitle, // Use canonical title, not raw title - description: planData.description, - todos: planData.todos, + id: normalizedPlan.id, + title: canonicalTitle, + todos: normalizedPlan.todos, toolCallId, }); } - }, [planData, planTitle, updatePlanState, toolCallId]); + }, [data, hasTodos, canonicalTitle, updatePlanState, toolCallId]); - // Update when result changes (for streaming updates) - useEffect(() => { - if (result) { - updatePlanState({ - id: result.id, - title: planTitle, // Use canonical title, not raw title - description: result.description, - todos: result.todos, - toolCallId, - }); - } - }, [result, planTitle, updatePlanState, toolCallId]); + // Get the current plan state + const currentPlanState = planStates.get(canonicalTitle); - // Get the current plan state (may be updated by other components) - const currentPlanState = planStates.get(planTitle); - - // If we're NOT the owner, render nothing (the owner will render) + // If we're NOT the owner, render nothing if (!isOwner) { return null; } - // Loading state - tool is still running (no data yet) + // Loading state if (status.type === "running" || status.type === "requires-action") { - // Try to show partial results from args while streaming - const partialResult = transformArgsToResult(args); - if (partialResult) { - const plan = parseSerializablePlan(partialResult); + if (hasTodos) { + const plan = parseSerializablePlan({ todos: data.todos }); return (
@@ -206,11 +125,8 @@ export const WriteTodosToolUI = makeAssistantToolUI @@ -222,23 +138,20 @@ export const WriteTodosToolUI = makeAssistantToolUI; } - const plan = parseSerializablePlan(planToRender); return (
- +
); }, }); -export { WriteTodosArgsSchema, WriteTodosResultSchema, type WriteTodosArgs, type WriteTodosResult }; +export { WriteTodosSchema, type WriteTodosData };