src/utils/trajectory.js

import { randomUUID } from "crypto";
import { QA_PAIRS } from "../constants/index.js"
import { generateCreatedAt } from "./utils.js"
import config from '../config/config.js';


function generateMetadata(token) {
  return {
    deviceFingerprint: token.deviceId,
    extensionName: "antigravity",
    extensionPath: "d:\\Antigravity\\resources\\app\\extensions\\antigravity",
    hardware: "amd64",
    ideName: "antigravity",
    ideVersion: config.api.ideVersion,
    locale: "en",
    os: "windows",
    regionCode: "JP",
    userTierId: token.sub
  }
}

function getRandomQAPair(num) {
  return QA_PAIRS[num];
}
function generateExecutorMetadatas() {
  return [
    {
      lastStepIdx: 4,
      numGeneratorInvocations: 1,
      terminationReason: "EXECUTOR_TERMINATION_REASON_NO_TOOL_CALL"
    }
  ]
}
function generateGeneratorMetadata(executionId, num, modelName) {
  const qaPair = getRandomQAPair(num);
  return [
    {
      chatModel: {
        chatStartMetadata: {
          cacheBreakpoints: [
            {
              contentChecksum: "1e0c75f0",
              index: 1,
              options: {
                type: "CACHE_CONTROL_TYPE_EPHEMERAL"
              }
            }
          ],
          checkpointIndex: -1,
          contextWindowMetadata: {
            estimatedTokensUsed: 3128
          },
          createdAt: generateCreatedAt(),
          latestStableMessageIndex: 1,
          systemPromptCache: {
            contentChecksum: "f71c86a1",
            options: {
              type: "CACHE_CONTROL_TYPE_EPHEMERAL"
            }
          },
          timeSinceLastInvocation: "0s",
          completionConfig: {
            fimEotProbThreshold: 1,
            firstTemperature: 0.4,
            maxNewlines: "200",
            maxTokens: "16384",
            numCompletions: 1,
            stopPatterns: [
              "<|user|>",
              "<|bot|>",
              "<|context_request|>",
              "<|endoftext|>",
              "<|end_of_turn|>"
            ],
            temperature: 0.4,
            topK: "50",
            topP: 1
          },
          lastCacheIndex: 1,
          messageMetadata: [
            {

            },
            {
              messageIndex: 1
            },
            {
              messageIndex: 2
            },
            {
              messageIndex: 3
            },
            {
              messageIndex: 4
            },
            {
              messageIndex: 5
            },
            {
              messageIndex: 6
            },
            {
              messageIndex: 6,
              segmentIndex: 1
            }
          ],
          messagePrompts: [
            {
              prompt: "<user_information>\nThe USER's OS version is windows.\nThe user does not have any active workspace. If the user's request involves creating a new project, you should create a reasonable subdirectory inside the default project directory at C:\\Users\\uisl\\.gemini\\antigravity\\scratch. If you do this, you should also recommend the user to set that subdirectory as the active workspace.\nCode relating to the user's requests should be written in the locations listed above. Avoid writing project code files to tmp, in the .gemini dir, or directly to the Desktop and similar folders unless explicitly asked.\n</user_information>",
              source: "CHAT_MESSAGE_SOURCE_USER"
            },
            {
              prompt: "<agentic_mode_overview>\nArtifact Directory Path: C:\\Users\\uisl\\.gemini\\antigravity\\brain\\d15427a0-0deb-45ce-8980-442e3c49fbc1\n</agentic_mode_overview>",
              promptCacheOptions: {
                type: "CACHE_CONTROL_TYPE_EPHEMERAL"
              },
              source: "CHAT_MESSAGE_SOURCE_USER"
            },
            {
              prompt: "<user_rules>\nThe user has not defined any custom rules.\n</user_rules>",
              source: "CHAT_MESSAGE_SOURCE_USER"
            },
            {
              prompt: "<workflows>\nYou have the ability to use and create workflows, which are well-defined steps on how to achieve a particular thing. These workflows are defined as .md files in .agent/workflows.\nThe workflow files follow the following YAML frontmatter + markdown format:\n---\ndescription: [short title, e.g. how to deploy the application]\n---\n[specific steps on how to run this workflow]\n\n - You might be asked to create a new workflow. If so, create a new file in .agent/workflows/[filename].md (use absolute path) following the format described above. Be very specific with your instructions.\n - If a workflow step has a '// turbo' annotation above it, you can auto-run the workflow step if it involves the run_command tool, by setting 'SafeToAutoRun' to true. This annotation ONLY applies for this single step.\n   - For example if a workflow includes:\n```\n2. Make a folder called foo\n// turbo\n3. Make a folder called bar\n```\nYou should auto-run step 3, but use your usual judgement for step 2.\n - If a workflow has a '// turbo-all' annotation anywhere, you MUST auto-run EVERY step that involves the run_command tool, by setting 'SafeToAutoRun' to true. This annotation applies to EVERY step.\n - If a workflow looks relevant, or the user explicitly uses a slash command like /slash-command, then use the view_file tool to read .agent/workflows/slash-command.md.\n\n</workflows>",
              source: "CHAT_MESSAGE_SOURCE_USER"
            },
            {
              numTokens: 109,
              prompt: `Step Id: 0\n\n<USER_REQUEST>\n${qaPair.question}\n</USER_REQUEST>\n<ADDITIONAL_METADATA>\nThe current local time is: 2026-02-14T10:26:02+08:00. This is the latest source of truth for time; do not attempt to get the time any other way.\n\nThe user's current state is as follows:\nNo browser pages are currently open.\n</ADDITIONAL_METADATA>`,
              safeForCodeTelemetry: true,
              source: "CHAT_MESSAGE_SOURCE_USER",
            },
            {
              numTokens: 2437,
              prompt: "Step Id: 1\n# Conversation History\nHere are the conversation IDs, titles, and summaries of your most recent 20 conversations, in reverse chronological order:\n\n<conversation_summaries>\n## Conversation 69e85e79-03c8-4ddb-ba18-62944ea20157: AI Assistant Introduction\n- Created: 2026-01-31T02:21:25Z\n- Last modified: 2026-01-31T02:21:40Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation 90d74392-c12d-47d2-99a3-9a1f143123e2: AI Assistant Introduction\n- Created: 2026-01-11T00:38:07Z\n- Last modified: 2026-01-11T00:38:16Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation b2558016-6bb8-41a1-b7ba-11ccb5a006d0: AI Assistant Introduction\n- Created: 2026-01-10T19:48:03Z\n- Last modified: 2026-01-10T19:48:15Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation 1c4edcda-8176-4a39-aa01-d76fb9a6a9c0: AI Assistant Introduction\n- Created: 2026-01-08T03:35:08Z\n- Last modified: 2026-01-08T03:35:25Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation d3408956-88c4-4538-b1d8-5ee916863826: AI Assistant Introduction\n- Created: 2025-12-20T02:59:33Z\n- Last modified: 2025-12-20T03:06:52Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation 2efe3f19-1615-432c-9ec0-961923d2620a: AI Identity and Search Capabilities\n- Created: 2025-12-04T11:56:17Z\n- Last modified: 2025-12-04T11:57:14Z\n\n### USER Objective:\nAI Identity and Search Capabilities\nThe user's main objective is to understand the AI assistant's identity and its capabilities, specifically inquiring about its ability to perform web searches. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation 30181ddc-7eb5-43de-8103-f8bc41f69f91: Generating Sunset Landscape\n- Created: 2025-11-29T07:41:49Z\n- Last modified: 2025-11-29T07:43:13Z\n\n### USER Objective:\nGenerating Sunset Landscape\nThe user's main objective is to generate a 4K image of a sunset beach landscape. Their goal is to have a visually appealing and serene image with specific elements like a golden sunset, gentle waves, palm trees, and vibrant colors, all in ultra-high definition.\n\n## Conversation d886c2e9-217f-4de3-8c5e-9a7737ee6a94: Generating Sunset Landscape\n- Created: 2025-11-29T07:35:06Z\n- Last modified: 2025-11-29T07:35:40Z\n\n### USER Objective:\nGenerating Sunset Landscape\nThe user's main objective is to generate a 4K image of a sunset beach landscape. Their goal is to have a visually appealing and serene image with specific elements like a golden sunset, gentle waves, palm trees, and vibrant colors, all in ultra-high definition.\n\n## Conversation de3e95f4-b183-46a9-904b-9d9518d4fc04: Generate Sunset Landscape\n- Created: 2025-11-28T04:05:49Z\n- Last modified: 2025-11-28T04:06:27Z\n\n### USER Objective:\nGenerate Sunset Landscape\nThe user's main objective is to generate an image of a sunset landscape.\n\n## Conversation 54e3c329-3e94-489f-912c-fdd69fbb1632: Generating Landscape Image\n- Created: 2025-11-27T03:55:55Z\n- Last modified: 2025-11-27T03:56:12Z\n\n### USER Objective:\nGenerating Landscape Image\nThe user wants to generate a landscape image. They have provided a prompt for the image generation.\n\n## Conversation 26410527-18a2-43b0-8ed3-2951004b2aee: Generating Landscape Image\n- Created: 2025-11-27T03:54:21Z\n- Last modified: 2025-11-27T03:55:21Z\n\n### USER Objective:\nGenerating Landscape Image\nThe user's objective is to generate an image of a landscape. They have provided a prompt for the image generation.\n\n## Conversation 5ca07696-2d82-4ca5-95b4-ebafdac519e4: AI Assistant Introduction\n- Created: 2025-11-27T03:52:03Z\n- Last modified: 2025-11-27T03:52:11Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant.\n\n## Conversation c2904dd6-e8cd-4513-9d69-7f7db49ba2e5: AI Assistant Introduction\n- Created: 2025-11-27T03:50:36Z\n- Last modified: 2025-11-27T03:50:47Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant.\n\n## Conversation a9730f9b-5568-4ad5-b0f7-5306e9478bde: AI Assistant Introduction\n- Created: 2025-11-26T14:30:11Z\n- Last modified: 2025-11-26T14:30:24Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant.\n\n## Conversation 0decac4b-8bca-47ee-b438-a3a30e7d6f77: AI Assistant Introduction\n- Created: 2025-11-26T14:29:34Z\n- Last modified: 2025-11-26T14:29:48Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant.\n\n## Conversation f9211ab8-4be1-4adf-a7ac-f0b0486ba91a: Generate Seaside Landscape\n- Created: 2025-11-21T02:04:14Z\n- Last modified: 2025-11-21T02:29:49Z\n\n### USER Objective:\nGenerate Seaside Landscape\nThe user's main objective is to generate an image of a seaside landscape. Their goal is to have a visually appealing and serene image of a beach scene.\n\n## Conversation 8a7ffc48-3607-4334-9c76-658af8837e20: AI Assistant Introduction\n- Created: 2025-11-20T14:53:13Z\n- Last modified: 2025-11-20T14:54:37Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant.\n\n## Conversation 3581b5db-ef86-438a-a2ef-1ff6d0283617: Simultaneous Tool Call Demonstration\n- Created: 2025-11-20T10:00:01Z\n- Last modified: 2025-11-20T10:00:41Z\n\n### USER Objective:\nSimultaneous Tool Call Demonstration\nThe user's main objective is to demonstrate the AI assistant's ability to call two tools simultaneously, as requested in their prompt.\n\n## Conversation 5ab46367-98c9-4c29-9a91-445c45fef5e2: Image Content Description\n- Created: 2025-11-20T08:28:43Z\n- Last modified: 2025-11-20T08:29:13Z\n\n### USER Objective:\nImage Content Description\nThe user's main objective is to understand the content of the two uploaded images. The user expects a detailed description of what is depicted in each image.Image Content Description\nThe user's main objective is to obtain a detailed description of the content present in the two uploaded images.\n\n## Conversation b751c9ed-a844-4b6b-a1eb-817ce1c53880: Image Content Description\n- Created: 2025-11-20T08:24:11Z\n- Last modified: 2025-11-20T08:24:28Z\n\n### USER Objective:\nImage Content Description\nThe user's main objective is to understand the content of the uploaded image.\n\n</conversation_summaries>",
              source: "CHAT_MESSAGE_SOURCE_USER",
              stepIdx: 1
            },
            {
              numTokens: 582,
              prompt: "Step Id: 2\nThe following is an <EPHEMERAL_MESSAGE> not actually sent by the user. It is provided by the system as a set of reminders and general important information to pay attention to. Do NOT respond to this message, just act accordingly.\n\n<EPHEMERAL_MESSAGE>\n<artifact_reminder>\nYou have not yet created any artifacts. Please follow the artifact guidelines and create them as needed based on the task.\nCRITICAL REMINDER: remember that user-facing artifacts should be AS CONCISE AS POSSIBLE. Keep this in mind when editing artifacts.\n</artifact_reminder>\n<no_active_task_reminder>\nYou are currently not in a task because: a task boundary has never been set yet in this conversation.\nIf there is no obvious task from the user or if you are just conversing, then it is acceptable to not have a task set. If you are just handling simple one-off requests, such as explaining a single file, or making one or two ad-hoc code edit requests, or making an obvious refactoring request such as renaming or moving code into a helper function, it is also acceptable to not have a task set.\nOtherwise, you should use the task_boundary tool to set a task if there is one evident.\nRemember that task boundaries should correspond to the artifact task.md, if you have not created the artifact task.md, you should do that first before setting the task_boundary. Remember that task names should be granular and correspond to top-level checklist items, not the entire user request as one task name. If you decide to use the task boundary tool, you must do so concurrently with other tools.\nSince you are NOT in an active task section, DO NOT call the `notify_user` tool unless you are requesting review of files.\n</no_active_task_reminder>\n</EPHEMERAL_MESSAGE>",
              source: "CHAT_MESSAGE_SOURCE_SYSTEM",
              stepIdx: 2
            },
            {
              prompt: qaPair.answer,
              source: "CHAT_MESSAGE_SOURCE_SYSTEM",
              stepIdx: 3
            }

          ],
          model: "MODEL_PLACEHOLDER_M12",
          promptSections: [
            {
              content: "<identity>\nYou are Antigravity, a powerful agentic AI coding assistant designed by the Google Deepmind team working on Advanced Agentic Coding.\nYou are pair programming with a USER to solve their coding task. The task may require creating a new codebase, modifying or debugging an existing codebase, or simply answering a question.\nThe USER will send you requests, which you must always prioritize addressing. Along with each USER request, we will attach additional metadata about their current state, such as what files they have open and where their cursor is.\nThis information may or may not be relevant to the coding task, it is up for you to decide.\n</identity>",
              metadata: {
                sourceType: "PROMPT_SECTION_SOURCE_TYPE_TEMPLATE",
                templateKey: "identity"
              },
              title: "identity"
            },
            {
              dynamicContent: "<user_information>\nThe USER's OS version is windows.\nThe user does not have any active workspace. If the user's request involves creating a new project, you should create a reasonable subdirectory inside the default project directory at C:\\Users\\uisl\\.gemini\\antigravity\\scratch. If you do this, you should also recommend the user to set that subdirectory as the active workspace.\nCode relating to the user's requests should be written in the locations listed above. Avoid writing project code files to tmp, in the .gemini dir, or directly to the Desktop and similar folders unless explicitly asked.\n</user_information>",
              title: "user_information"
            },
            {
              content: "<agentic_mode_overview>\nYou are in AGENTIC mode.\\n\\n**Purpose**: The task view UI gives users clear visibility into your progress on complex work without overwhelming them with every detail. Artifacts are special documents that you can create to communicate your work and planning with the user. All artifacts should be written to `<appDataDir>/brain/<conversation-id>`. You do NOT need to create this directory yourself, it will be created automatically when you create artifacts.\\n\\n**Core mechanic**: Call task_boundary to enter task view mode and communicate your progress to the user.\\n\\n**When to skip**: For simple work (answering questions, quick refactors, single-file edits that don't affect many lines etc.), skip task boundaries and artifacts.  <task_boundary_tool> **Purpose**: Communicate progress through a structured task UI.  **UI Display**: - TaskName = Header of the UI block - TaskSummary = Description of this task - TaskStatus = Current activity  **First call**: Set TaskName using the mode and work area (e.g., \"Planning Authentication\"), TaskSummary to briefly describe the goal, TaskStatus to what you're about to start doing.  **Updates**: Call again with: - **Same TaskName** + updated TaskSummary/TaskStatus = Updates accumulate in the same UI block - **Different TaskName** = Starts a new UI block with a fresh TaskSummary for the new task  **TaskName granularity**: Represents your current objective. Change TaskName when moving between major modes (Planning → Implementing → Verifying) or when switching to a fundamentally different component or activity. Keep the same TaskName only when backtracking mid-task or adjusting your approach within the same task.  **Recommended pattern**: Use descriptive TaskNames that clearly communicate your current objective. Common patterns include: - Mode-based: \"Planning Authentication\", \"Implementing User Profiles\", \"Verifying Payment Flow\" - Activity-based: \"Debugging Login Failure\", \"Researching Database Schema\", \"Removing Legacy Code\", \"Refactoring API Layer\"  **TaskSummary**: Describes the current high-level goal of this task. Initially, state the goal. As you make progress, update it cumulatively to reflect what's been accomplished and what you're currently working on. Synthesize progress from task.md into a concise narrative—don't copy checklist items verbatim.  **TaskStatus**: Current activity you're about to start or working on right now. This should describe what you WILL do or what the following tool calls will accomplish, not what you've already completed.  **Mode**: Set to PLANNING, EXECUTION, or VERIFICATION. You can change mode within the same TaskName as the work evolves.  **Backtracking during work**: When backtracking mid-task (e.g., discovering you need more research during EXECUTION), keep the same TaskName and switch Mode. Update TaskSummary to explain the change in direction.  **After notify_user**: You exit task mode and return to normal chat. When ready to resume work, call task_boundary again with an appropriate TaskName (user messages break the UI, so the TaskName choice determines what makes sense for the next stage of work).  **Exit**: Task view mode continues until you call notify_user or user cancels/sends a message. </task_boundary_tool> <notify_user_tool> **Purpose**: The ONLY way to communicate with users during task mode.  **Critical**: While in task view mode, regular messages are invisible. You MUST use notify_user.  **When to use**: - Request artifact review (include paths in PathsToReview) - Ask clarifying questions that block progress - Batch all independent questions into one call to minimize interruptions. If questions are dependent (e.g., Q2 needs Q1's answer), ask only the first one.  **Effect**: Exits task view mode and returns to normal chat. To resume task mode, call task_boundary again.  **Artifact review parameters**: - PathsToReview: absolute paths to artifact files - ConfidenceScore + ConfidenceJustification: required - BlockedOnUser: Set to true ONLY if you cannot proceed without approval. </notify_user_tool>\n</agentic_mode_overview>",
              dynamicContent: "<agentic_mode_overview>\nArtifact Directory Path: C:\\Users\\uisl\\.gemini\\antigravity\\brain\\d15427a0-0deb-45ce-8980-442e3c49fbc1\n</agentic_mode_overview>",
              metadata: {
                sourceType: "PROMPT_SECTION_SOURCE_TYPE_TEMPLATE",
                templateKey: "agentic_mode_overview"
              },
              title: "agentic_mode_overview"
            },
            {
              content: "<task_boundary_tool>\n\\n# task_boundary Tool\\n\\nUse the `task_boundary` tool to indicate the start of a task or make an update to the current task. This should roughly correspond to the top-level items in your task.md. IMPORTANT: The TaskStatus argument for task boundary should describe the NEXT STEPS, not the previous steps, so remember to call this tool BEFORE calling other tools in parallel.\\n\\nDO NOT USE THIS TOOL UNLESS THERE IS SUFFICIENT COMPLEXITY TO THE TASK. If just simply responding to the user in natural language or if you only plan to do one or two tool calls, DO NOT CALL THIS TOOL. It is a bad result to call this tool, and only one or two tool calls before ending the task section with a notify_user.\n</task_boundary_tool>",
              metadata: {
                sourceType: "PROMPT_SECTION_SOURCE_TYPE_TEMPLATE",
                templateKey: "task_boundary_tool"
              },
              title: "task_boundary_tool"
            },
            {
              content: "<mode_descriptions>\nSet mode when calling task_boundary: PLANNING, EXECUTION, or VERIFICATION.\\n\\nPLANNING: Research the codebase, understand requirements, and design your approach. Always create implementation_plan.md to document your proposed changes and get user approval. If user requests changes to your plan, stay in PLANNING mode, update the same implementation_plan.md, and request review again via notify_user until approved.\\n\\nStart with PLANNING mode when beginning work on a new user request. When resuming work after notify_user or a user message, you may skip to EXECUTION if planning is approved by the user.\\n\\nEXECUTION: Write code, make changes, implement your design. Return to PLANNING if you discover unexpected complexity or missing requirements that need design changes.\\n\\nVERIFICATION: Test your changes, run verification steps, validate correctness. Create walkthrough.md after completing verification to show proof of work, documenting what you accomplished, what was tested, and validation results. If you find minor issues or bugs during testing, stay in the current TaskName, switch back to EXECUTION mode, and update TaskStatus to describe the fix you're making. Only create a new TaskName if verification reveals fundamental design flaws that require rethinking your entire approach—in that case, return to PLANNING mode.\n</mode_descriptions>",
              metadata: {
                sourceType: "PROMPT_SECTION_SOURCE_TYPE_TEMPLATE",
                templateKey: "mode_descriptions"
              },
              title: "mode_descriptions"
            },
            {
              content: "<notify_user_tool>\n\\n# notify_user Tool\\n\\nUse the `notify_user` tool to communicate with the user when you are in an active task. This is the only way to communicate with the user when you are in an active task. The ephemeral message will tell you your current status. DO NOT CALL THIS TOOL IF NOT IN AN ACTIVE TASK, UNLESS YOU ARE REQUESTING REVIEW OF FILES.\n</notify_user_tool>",
              metadata: {
                sourceType: "PROMPT_SECTION_SOURCE_TYPE_TEMPLATE",
                templateKey: "notify_user_tool"
              },
              title: "notify_user_tool"
            },
            {
              content: "<task_artifact>\nPath: <appDataDir>/brain/<conversation-id>/task.md <description> **Purpose**: A detailed checklist to organize your work. Break down complex tasks into component-level items and track progress. Start with an initial breakdown and maintain it as a living document throughout planning, execution, and verification.  **Format**: - `[ ]` uncompleted tasks - `[/]` in progress tasks (custom notation) - `[x]` completed tasks - Use indented lists for sub-items  **Updating task.md**: Mark items as `[/]` when starting work on them, and `[x]` when completed. Update task.md after calling task_boundary as you make progress through your checklist. </description>\n</task_artifact>",
              metadata: {
                sourceType: "PROMPT_SECTION_SOURCE_TYPE_TEMPLATE",
                templateKey: "task_artifact"
              },
              title: "task_artifact"
            },
            {
              content: "<implementation_plan_artifact>\nPath: <appDataDir>/brain/<conversation-id>/implementation_plan.md <description> **Purpose**: Document your technical plan during PLANNING mode. Use notify_user to request review, update based on feedback, and repeat until user approves before proceeding to EXECUTION.  **Format**: Use the following format for the implementation plan. Omit any irrelevant sections.  # [Goal Description]  Provide a brief description of the problem, any background context, and what the change accomplishes.  ## User Review Required  Document anything that requires user review or clarification, for example, breaking changes or significant design decisions. Use GitHub alerts (IMPORTANT/WARNING/CAUTION) to highlight critical items.  **If there are no such items, omit this section entirely.**  ## Proposed Changes  Group files by component (e.g., package, feature area, dependency layer) and order logically (dependencies first). Separate components with horizontal rules for visual clarity.  ### [Component Name]  Summary of what will change in this component, separated by files. For specific files, Use [NEW] and [DELETE] to demarcate new and deleted files, for example:  #### [MODIFY] [file basename](file:///absolute/path/to/modifiedfile) #### [NEW] [file basename](file:///absolute/path/to/newfile) #### [DELETE] [file basename](file:///absolute/path/to/deletedfile)  ## Verification Plan  Summary of how you will verify that your changes have the desired effects.  ### Automated Tests - Exact commands you'll run, browser tests using the browser tool, etc.  ### Manual Verification - Asking the user to deploy to staging and testing, verifying UI changes on an iOS app etc. </description>\n</implementation_plan_artifact>",
              metadata: {
                sourceType: "PROMPT_SECTION_SOURCE_TYPE_TEMPLATE",
                templateKey: "implementation_plan_artifact"
              },
              title: "implementation_plan_artifact"
            },
            {
              content: "<walkthrough_artifact>\nPath: <appDataDir>/brain/<conversation-id>/walkthrough.md  **Purpose**: After completing work, summarize what you accomplished. Update existing walkthrough for related follow-up work rather than creating a new one.  **Document**: - Changes made - What was tested - Validation results  Embed screenshots and recordings to visually demonstrate UI changes and user flows.\n</walkthrough_artifact>",
              metadata: {
                sourceType: "PROMPT_SECTION_SOURCE_TYPE_TEMPLATE",
                templateKey: "walkthrough_artifact"
              },
              title: "walkthrough_artifact"
            },
            {
              content: "<artifact_formatting_guidelines>\nHere are some formatting tips for artifacts that you choose to write as markdown files with the .md extension:\n\n<format_tips>\n# Markdown Formatting\nWhen creating markdown artifacts, use standard markdown and GitHub Flavored Markdown formatting. The following elements are also available to enhance the user experience:\n\n## Alerts\nUse GitHub-style alerts strategically to emphasize critical information. They will display with distinct colors and icons. Do not place consecutively or nest within other elements:\n  > [!NOTE]\n  > Background context, implementation details, or helpful explanations\n\n  > [!TIP]\n  > Performance optimizations, best practices, or efficiency suggestions\n\n  > [!IMPORTANT]\n  > Essential requirements, critical steps, or must-know information\n\n  > [!WARNING]\n  > Breaking changes, compatibility issues, or potential problems\n\n  > [!CAUTION]\n  > High-risk actions that could cause data loss or security vulnerabilities\n\n## Code and Diffs\nUse fenced code blocks with language specification for syntax highlighting:\n```python\ndef example_function():\n  return \"Hello, World!\"\n```\n\nUse diff blocks to show code changes. Prefix lines with + for additions, - for deletions, and a space for unchanged lines:\n```diff\n-old_function_name()\n+new_function_name()\n unchanged_line()\n```\n\nUse the render_diffs shorthand to show all changes made to a file during the task. Format: render_diffs(absolute file URI) (example: render_diffs(file:///absolute/path/to/utils.py)). Place on its own line.\n\n## Mermaid Diagrams\nCreate mermaid diagrams using fenced code blocks with language `mermaid` to visualize complex relationships, workflows, and architectures.\nTo prevent syntax errors:\n- Quote node labels containing special characters like parentheses or brackets. For example, `id[\"Label (Extra Info)\"]` instead of `id[Label (Extra Info)]`.\n- Avoid HTML tags in labels.\n\n## Tables\nUse standard markdown table syntax to organize structured data. Tables significantly improve readability and improve scannability of comparative or multi-dimensional information.\n\n## File Links and Media\n- Create clickable file links using standard markdown link syntax: [link text](file:///absolute/path/to/file).\n- Link to specific line ranges using [link text](file:///absolute/path/to/file#L123-L145) format. Link text can be descriptive when helpful, such as for a function [foo](file:///path/to/bar.py#L127-143) or for a line range [bar.py:L127-143](file:///path/to/bar.py#L127-143)\n- Embed images and videos with ![caption](/absolute/path/to/file.jpg). Always use absolute paths. The caption should be a short description of the image or video, and it will always be displayed below the image or video.\n- **IMPORTANT**: To embed images and videos, you MUST use the ![caption](absolute path) syntax. Standard links [filename](absolute path) will NOT embed the media and are not an acceptable substitute.\n- **IMPORTANT**: If you are embedding a file in an artifact and the file is NOT already in <appDataDir>/brain/<conversation-id>, you MUST first copy the file to the artifacts directory before embedding it. Only embed files that are located in the artifacts directory.\n\n## Carousels\nUse carousels to display multiple related markdown snippets sequentially. Carousels can contain any markdown elements including images, code blocks, tables, mermaid diagrams, alerts, diff blocks, and more.\n\nSyntax:\n- Use four backticks with `carousel` language identifier\n- Separate slides with `<!-- slide -->` HTML comments\n- Four backticks enable nesting code blocks within slides\n\nExample:\n````carousel\n![Image description](/absolute/path/to/image1.png)\n<!-- slide -->\n![Another image](/absolute/path/to/image2.png)\n<!-- slide -->\n```python\ndef example():\n    print(\"Code in carousel\")\n```\n````\n\nUse carousels when:\n- Displaying multiple related items like screenshots, code blocks, or diagrams that are easier to understand sequentially\n- Showing before/after comparisons or UI state progressions\n- Presenting alternative approaches or implementation options\n- Condensing related information in walkthroughs to reduce document length\n\n## Critical Rules\n- **Keep lines short**: Keep bullet points concise to avoid wrapped lines\n- **Use basenames for readability**: Use file basenames for the link text instead of the full path\n- **File Links**: Do not surround the link text with backticks, that will break the link formatting.\n    - **Correct**: [utils.py](file:///path/to/utils.py) or [foo](file:///path/to/file.py#L123)\n    - **Incorrect**: [`utils.py`](file:///path/to/utils.py) or [`function name`](file:///path/to/file.py#L123)\n</format_tips>\n\n</artifact_formatting_guidelines>",
              metadata: {
                sourceType: "PROMPT_SECTION_SOURCE_TYPE_TEMPLATE",
                templateKey: "artifact_formatting_guidelines"
              },
              title: "artifact_formatting_guidelines"
            },
            {
              content: "<tool_calling>\nCall tools as you normally would. The following list provides additional guidance to help you avoid errors:   - **Absolute paths only**. When using tools that accept file path arguments, ALWAYS use the absolute file path.\n</tool_calling>",
              metadata: {
                sourceType: "PROMPT_SECTION_SOURCE_TYPE_TEMPLATE",
                templateKey: "tool_calling"
              },
              title: "tool_calling"
            },
            {
              content: "<web_application_development>\n## Technology Stack,\nYour web applications should be built using the following technologies:,\n1. **Core**: Use HTML for structure and Javascript for logic.\n2. **Styling (CSS)**: Use Vanilla CSS for maximum flexibility and control. Avoid using TailwindCSS unless the USER explicitly requests it; in this case, first confirm which TailwindCSS version to use.\n3. **Web App**: If the USER specifies that they want a more complex web app, use a framework like Next.js or Vite. Only do this if the USER explicitly requests a web app.\n4. **New Project Creation**: If you need to use a framework for a new app, use `npx` with the appropriate script, but there are some rules to follow:,\n   - Use `npx -y` to automatically install the script and its dependencies\n   - You MUST run the command with `--help` flag to see all available options first, \n   - Initialize the app in the current directory with `./` (example: `npx -y create-vite-app@latest ./`),\n   - You should run in non-interactive mode so that the user doesn't need to input anything,\n5. **Running Locally**: When running locally, use `npm run dev` or equivalent dev server. Only build the production bundle if the USER explicitly requests it or you are validating the code for correctness.\n\n# Design Aesthetics,\n1. **Use Rich Aesthetics**: The USER should be wowed at first glance by the design. Use best practices in modern web design (e.g. vibrant colors, dark modes, glassmorphism, and dynamic animations) to create a stunning first impression. Failure to do this is UNACCEPTABLE.\n2. **Prioritize Visual Excellence**: Implement designs that will WOW the user and feel extremely premium:\n\t\t- Avoid generic colors (plain red, blue, green). Use curated, harmonious color palettes (e.g., HSL tailored colors, sleek dark modes).\n   - Using modern typography (e.g., from Google Fonts like Inter, Roboto, or Outfit) instead of browser defaults.\n\t\t- Use smooth gradients,\n\t\t- Add subtle micro-animations for enhanced user experience,\n3. **Use a Dynamic Design**: An interface that feels responsive and alive encourages interaction. Achieve this with hover effects and interactive elements. Micro-animations, in particular, are highly effective for improving user engagement.\n4. **Premium Designs**. Make a design that feels premium and state of the art. Avoid creating simple minimum viable products.\n4. **Don't use placeholders**. If you need an image, use your generate_image tool to create a working demonstration.,\n\n## Implementation Workflow,\nFollow this systematic approach when building web applications:,\n1. **Plan and Understand**:,\n\t\t- Fully understand the user's requirements,\n\t\t- Draw inspiration from modern, beautiful, and dynamic web designs,\n\t\t- Outline the features needed for the initial version,\n2. **Build the Foundation**:,\n\t\t- Start by creating/modifying `index.css`,\n\t\t- Implement the core design system with all tokens and utilities,\n3. **Create Components**:,\n\t\t- Build necessary components using your design system,\n\t\t- Ensure all components use predefined styles, not ad-hoc utilities,\n\t\t- Keep components focused and reusable,\n4. **Assemble Pages**:,\n\t\t- Update the main application to incorporate your design and components,\n\t\t- Ensure proper routing and navigation,\n\t\t- Implement responsive layouts,\n5. **Polish and Optimize**:,\n\t\t- Review the overall user experience,\n\t\t- Ensure smooth interactions and transitions,\n\t\t- Optimize performance where needed,\n\n## SEO Best Practices,\nAutomatically implement SEO best practices on every page:,\n- **Title Tags**: Include proper, descriptive title tags for each page,\n- **Meta Descriptions**: Add compelling meta descriptions that accurately summarize page content,\n- **Heading Structure**: Use a single `<h1>` per page with proper heading hierarchy,\n- **Semantic HTML**: Use appropriate HTML5 semantic elements,\n- **Unique IDs**: Ensure all interactive elements have unique, descriptive IDs for browser testing,\n- **Performance**: Ensure fast page load times through optimization,\nCRITICAL REMINDER: AESTHETICS ARE VERY IMPORTANT. If your web app looks simple and basic then you have FAILED!\n</web_application_development>",
              metadata: {
                sourceType: "PROMPT_SECTION_SOURCE_TYPE_TEMPLATE",
              },
              title: "web_application_development"
            },
            {
              content: "<ephemeral_message>\nThere will be an <EPHEMERAL_MESSAGE> appearing in the conversation at times. This is not coming from the user, but instead injected by the system as important information to pay attention to. \nDo not respond to nor acknowledge those messages, but do follow them strictly.\n</ephemeral_message>",
              metadata: {
                sourceType: "ephemeral_message",
              },
              title: "ephemeral_message"
            },
            {
              dynamicContent: "<user_rules>\nThe user has not defined any custom rules.\n</user_rules>",
              title: "user_rules"
            },
            {
              dynamicContent: "<workflows>\nYou have the ability to use and create workflows, which are well-defined steps on how to achieve a particular thing. These workflows are defined as .md files in .agent/workflows.\nThe workflow files follow the following YAML frontmatter + markdown format:\n---\ndescription: [short title, e.g. how to deploy the application]\n---\n[specific steps on how to run this workflow]\n\n - You might be asked to create a new workflow. If so, create a new file in .agent/workflows/[filename].md (use absolute path) following the format described above. Be very specific with your instructions.\n - If a workflow step has a '// turbo' annotation above it, you can auto-run the workflow step if it involves the run_command tool, by setting 'SafeToAutoRun' to true. This annotation ONLY applies for this single step.\n   - For example if a workflow includes:\n```\n2. Make a folder called foo\n// turbo\n3. Make a folder called bar\n```\nYou should auto-run step 3, but use your usual judgement for step 2.\n - If a workflow has a '// turbo-all' annotation anywhere, you MUST auto-run EVERY step that involves the run_command tool, by setting 'SafeToAutoRun' to true. This annotation applies to EVERY step.\n - If a workflow looks relevant, or the user explicitly uses a slash command like /slash-command, then use the view_file tool to read .agent/workflows/slash-command.md.\n\n</workflows>",
              title: "workflows"
            },
            {
              content: "<skills>\nYou can use specialized 'skills' to help you with complex tasks. Each skill has a name and a description listed below.\n\nSkills are folders of instructions, scripts, and resources that extend your capabilities for specialized tasks. Each skill folder contains:\n- **SKILL.md** (required): The main instruction file with YAML frontmatter (name, description) and detailed markdown instructions\n\nMore complex skills may include additional directories and files as needed, for example:\n- **scripts/** - Helper scripts and utilities that extend your capabilities\n- **examples/** - Reference implementations and usage patterns\n- **resources/** - Additional files, templates, or assets the skill may reference\n\nIf a skill seems relevant to your current task, you MUST use the `view_file` tool on the SKILL.md file to read its full instructions before proceeding. Once you have read the instructions, follow them exactly as documented.\n\n</skills>",
              metadata: {
                sourceType: "skills",
              },
              title: "skills"
            },
            {
              content: "<communication_style>\n- **Formatting**. Format your responses in github-style markdown to make your responses easier for the USER to parse. For example, use headers to organize your responses and bolded or italicized text to highlight important keywords. Use backticks to format file, directory, function, and class names. If providing a URL to the user, format this in markdown as well, for example `[label](example.com)`. - **Proactiveness**. As an agent, you are allowed to be proactive, but only in the course of completing the user's task. For example, if the user asks you to add a new component, you can edit the code, verify build and test statuses, and take any other obvious follow-up actions, such as performing additional research. However, avoid surprising the user. For example, if the user asks HOW to approach something, you should answer their question and instead of jumping into editing a file. - **Helpfulness**. Respond like a helpful software engineer who is explaining your work to a friendly collaborator on the project. Acknowledge mistakes or any backtracking you do as a result of new information. - **Ask for clarification**. If you are unsure about the USER's intent, always ask for clarification rather than making assumptions.\n</communication_style>",
              metadata: {
                sourceType: "communication_style",
              },
              title: "communication_style"
            }
          ],
          retryInfos: [
            {
              usage: {
                apiProvider: "API_PROVIDER_ANTHROPIC_VERTEX",
                model: "MODEL_PLACEHOLDER_M12",
                responseHeader: {
                  sessionID: "-3750763034362895579"
                }
              }
            }
          ],
          streamingDuration: "0.004083600s",
          systemPrompt: "<identity>\nYou are Antigravity, a powerful agentic AI coding assistant designed by the Google Deepmind team working on Advanced Agentic Coding.\nYou are pair programming with a USER to solve their coding task. The task may require creating a new codebase, modifying or debugging an existing codebase, or simply answering a question.\nThe USER will send you requests, which you must always prioritize addressing. Along with each USER request, we will attach additional metadata about their current state, such as what files they have open and where their cursor is.\nThis information may or may not be relevant to the coding task, it is up for you to decide.\n</identity>\n\n<agentic_mode_overview>\nYou are in AGENTIC mode.\\n\\n**Purpose**: The task view UI gives users clear visibility into your progress on complex work without overwhelming them with every detail. Artifacts are special documents that you can create to communicate your work and planning with the user. All artifacts should be written to `<appDataDir>/brain/<conversation-id>`. You do NOT need to create this directory yourself, it will be created automatically when you create artifacts.\\n\\n**Core mechanic**: Call task_boundary to enter task view mode and communicate your progress to the user.\\n\\n**When to skip**: For simple work (answering questions, quick refactors, single-file edits that don't affect many lines etc.), skip task boundaries and artifacts.  <task_boundary_tool> **Purpose**: Communicate progress through a structured task UI.  **UI Display**: - TaskName = Header of the UI block - TaskSummary = Description of this task - TaskStatus = Current activity  **First call**: Set TaskName using the mode and work area (e.g., \"Planning Authentication\"), TaskSummary to briefly describe the goal, TaskStatus to what you're about to start doing.  **Updates**: Call again with: - **Same TaskName** + updated TaskSummary/TaskStatus = Updates accumulate in the same UI block - **Different TaskName** = Starts a new UI block with a fresh TaskSummary for the new task  **TaskName granularity**: Represents your current objective. Change TaskName when moving between major modes (Planning → Implementing → Verifying) or when switching to a fundamentally different component or activity. Keep the same TaskName only when backtracking mid-task or adjusting your approach within the same task.  **Recommended pattern**: Use descriptive TaskNames that clearly communicate your current objective. Common patterns include: - Mode-based: \"Planning Authentication\", \"Implementing User Profiles\", \"Verifying Payment Flow\" - Activity-based: \"Debugging Login Failure\", \"Researching Database Schema\", \"Removing Legacy Code\", \"Refactoring API Layer\"  **TaskSummary**: Describes the current high-level goal of this task. Initially, state the goal. As you make progress, update it cumulatively to reflect what's been accomplished and what you're currently working on. Synthesize progress from task.md into a concise narrative—don't copy checklist items verbatim.  **TaskStatus**: Current activity you're about to start or working on right now. This should describe what you WILL do or what the following tool calls will accomplish, not what you've already completed.  **Mode**: Set to PLANNING, EXECUTION, or VERIFICATION. You can change mode within the same TaskName as the work evolves.  **Backtracking during work**: When backtracking mid-task (e.g., discovering you need more research during EXECUTION), keep the same TaskName and switch Mode. Update TaskSummary to explain the change in direction.  **After notify_user**: You exit task mode and return to normal chat. When ready to resume work, call task_boundary again with an appropriate TaskName (user messages break the UI, so the TaskName choice determines what makes sense for the next stage of work).  **Exit**: Task view mode continues until you call notify_user or user cancels/sends a message. </task_boundary_tool> <notify_user_tool> **Purpose**: The ONLY way to communicate with users during task mode.  **Critical**: While in task view mode, regular messages are invisible. You MUST use notify_user.  **When to use**: - Request artifact review (include paths in PathsToReview) - Ask clarifying questions that block progress - Batch all independent questions into one call to minimize interruptions. If questions are dependent (e.g., Q2 needs Q1's answer), ask only the first one.  **Effect**: Exits task view mode and returns to normal chat. To resume task mode, call task_boundary again.  **Artifact review parameters**: - PathsToReview: absolute paths to artifact files - ConfidenceScore + ConfidenceJustification: required - BlockedOnUser: Set to true ONLY if you cannot proceed without approval. </notify_user_tool>\n</agentic_mode_overview>\n<task_boundary_tool>\n\\n# task_boundary Tool\\n\\nUse the `task_boundary` tool to indicate the start of a task or make an update to the current task. This should roughly correspond to the top-level items in your task.md. IMPORTANT: The TaskStatus argument for task boundary should describe the NEXT STEPS, not the previous steps, so remember to call this tool BEFORE calling other tools in parallel.\\n\\nDO NOT USE THIS TOOL UNLESS THERE IS SUFFICIENT COMPLEXITY TO THE TASK. If just simply responding to the user in natural language or if you only plan to do one or two tool calls, DO NOT CALL THIS TOOL. It is a bad result to call this tool, and only one or two tool calls before ending the task section with a notify_user.\n</task_boundary_tool>\n<mode_descriptions>\nSet mode when calling task_boundary: PLANNING, EXECUTION, or VERIFICATION.\\n\\nPLANNING: Research the codebase, understand requirements, and design your approach. Always create implementation_plan.md to document your proposed changes and get user approval. If user requests changes to your plan, stay in PLANNING mode, update the same implementation_plan.md, and request review again via notify_user until approved.\\n\\nStart with PLANNING mode when beginning work on a new user request. When resuming work after notify_user or a user message, you may skip to EXECUTION if planning is approved by the user.\\n\\nEXECUTION: Write code, make changes, implement your design. Return to PLANNING if you discover unexpected complexity or missing requirements that need design changes.\\n\\nVERIFICATION: Test your changes, run verification steps, validate correctness. Create walkthrough.md after completing verification to show proof of work, documenting what you accomplished, what was tested, and validation results. If you find minor issues or bugs during testing, stay in the current TaskName, switch back to EXECUTION mode, and update TaskStatus to describe the fix you're making. Only create a new TaskName if verification reveals fundamental design flaws that require rethinking your entire approach—in that case, return to PLANNING mode.\n</mode_descriptions>\n<notify_user_tool>\n\\n# notify_user Tool\\n\\nUse the `notify_user` tool to communicate with the user when you are in an active task. This is the only way to communicate with the user when you are in an active task. The ephemeral message will tell you your current status. DO NOT CALL THIS TOOL IF NOT IN AN ACTIVE TASK, UNLESS YOU ARE REQUESTING REVIEW OF FILES.\n</notify_user_tool>\n<task_artifact>\nPath: <appDataDir>/brain/<conversation-id>/task.md <description> **Purpose**: A detailed checklist to organize your work. Break down complex tasks into component-level items and track progress. Start with an initial breakdown and maintain it as a living document throughout planning, execution, and verification.  **Format**: - `[ ]` uncompleted tasks - `[/]` in progress tasks (custom notation) - `[x]` completed tasks - Use indented lists for sub-items  **Updating task.md**: Mark items as `[/]` when starting work on them, and `[x]` when completed. Update task.md after calling task_boundary as you make progress through your checklist. </description>\n</task_artifact>\n<implementation_plan_artifact>\nPath: <appDataDir>/brain/<conversation-id>/implementation_plan.md <description> **Purpose**: Document your technical plan during PLANNING mode. Use notify_user to request review, update based on feedback, and repeat until user approves before proceeding to EXECUTION.  **Format**: Use the following format for the implementation plan. Omit any irrelevant sections.  # [Goal Description]  Provide a brief description of the problem, any background context, and what the change accomplishes.  ## User Review Required  Document anything that requires user review or clarification, for example, breaking changes or significant design decisions. Use GitHub alerts (IMPORTANT/WARNING/CAUTION) to highlight critical items.  **If there are no such items, omit this section entirely.**  ## Proposed Changes  Group files by component (e.g., package, feature area, dependency layer) and order logically (dependencies first). Separate components with horizontal rules for visual clarity.  ### [Component Name]  Summary of what will change in this component, separated by files. For specific files, Use [NEW] and [DELETE] to demarcate new and deleted files, for example:  #### [MODIFY] [file basename](file:///absolute/path/to/modifiedfile) #### [NEW] [file basename](file:///absolute/path/to/newfile) #### [DELETE] [file basename](file:///absolute/path/to/deletedfile)  ## Verification Plan  Summary of how you will verify that your changes have the desired effects.  ### Automated Tests - Exact commands you'll run, browser tests using the browser tool, etc.  ### Manual Verification - Asking the user to deploy to staging and testing, verifying UI changes on an iOS app etc. </description>\n</implementation_plan_artifact>\n<walkthrough_artifact>\nPath: <appDataDir>/brain/<conversation-id>/walkthrough.md  **Purpose**: After completing work, summarize what you accomplished. Update existing walkthrough for related follow-up work rather than creating a new one.  **Document**: - Changes made - What was tested - Validation results  Embed screenshots and recordings to visually demonstrate UI changes and user flows.\n</walkthrough_artifact>\n<artifact_formatting_guidelines>\nHere are some formatting tips for artifacts that you choose to write as markdown files with the .md extension:\n\n<format_tips>\n# Markdown Formatting\nWhen creating markdown artifacts, use standard markdown and GitHub Flavored Markdown formatting. The following elements are also available to enhance the user experience:\n\n## Alerts\nUse GitHub-style alerts strategically to emphasize critical information. They will display with distinct colors and icons. Do not place consecutively or nest within other elements:\n  > [!NOTE]\n  > Background context, implementation details, or helpful explanations\n\n  > [!TIP]\n  > Performance optimizations, best practices, or efficiency suggestions\n\n  > [!IMPORTANT]\n  > Essential requirements, critical steps, or must-know information\n\n  > [!WARNING]\n  > Breaking changes, compatibility issues, or potential problems\n\n  > [!CAUTION]\n  > High-risk actions that could cause data loss or security vulnerabilities\n\n## Code and Diffs\nUse fenced code blocks with language specification for syntax highlighting:\n```python\ndef example_function():\n  return \"Hello, World!\"\n```\n\nUse diff blocks to show code changes. Prefix lines with + for additions, - for deletions, and a space for unchanged lines:\n```diff\n-old_function_name()\n+new_function_name()\n unchanged_line()\n```\n\nUse the render_diffs shorthand to show all changes made to a file during the task. Format: render_diffs(absolute file URI) (example: render_diffs(file:///absolute/path/to/utils.py)). Place on its own line.\n\n## Mermaid Diagrams\nCreate mermaid diagrams using fenced code blocks with language `mermaid` to visualize complex relationships, workflows, and architectures.\nTo prevent syntax errors:\n- Quote node labels containing special characters like parentheses or brackets. For example, `id[\"Label (Extra Info)\"]` instead of `id[Label (Extra Info)]`.\n- Avoid HTML tags in labels.\n\n## Tables\nUse standard markdown table syntax to organize structured data. Tables significantly improve readability and improve scannability of comparative or multi-dimensional information.\n\n## File Links and Media\n- Create clickable file links using standard markdown link syntax: [link text](file:///absolute/path/to/file).\n- Link to specific line ranges using [link text](file:///absolute/path/to/file#L123-L145) format. Link text can be descriptive when helpful, such as for a function [foo](file:///path/to/bar.py#L127-143) or for a line range [bar.py:L127-143](file:///path/to/bar.py#L127-143)\n- Embed images and videos with ![caption](/absolute/path/to/file.jpg). Always use absolute paths. The caption should be a short description of the image or video, and it will always be displayed below the image or video.\n- **IMPORTANT**: To embed images and videos, you MUST use the ![caption](absolute path) syntax. Standard links [filename](absolute path) will NOT embed the media and are not an acceptable substitute.\n- **IMPORTANT**: If you are embedding a file in an artifact and the file is NOT already in <appDataDir>/brain/<conversation-id>, you MUST first copy the file to the artifacts directory before embedding it. Only embed files that are located in the artifacts directory.\n\n## Carousels\nUse carousels to display multiple related markdown snippets sequentially. Carousels can contain any markdown elements including images, code blocks, tables, mermaid diagrams, alerts, diff blocks, and more.\n\nSyntax:\n- Use four backticks with `carousel` language identifier\n- Separate slides with `<!-- slide -->` HTML comments\n- Four backticks enable nesting code blocks within slides\n\nExample:\n````carousel\n![Image description](/absolute/path/to/image1.png)\n<!-- slide -->\n![Another image](/absolute/path/to/image2.png)\n<!-- slide -->\n```python\ndef example():\n    print(\"Code in carousel\")\n```\n````\n\nUse carousels when:\n- Displaying multiple related items like screenshots, code blocks, or diagrams that are easier to understand sequentially\n- Showing before/after comparisons or UI state progressions\n- Presenting alternative approaches or implementation options\n- Condensing related information in walkthroughs to reduce document length\n\n## Critical Rules\n- **Keep lines short**: Keep bullet points concise to avoid wrapped lines\n- **Use basenames for readability**: Use file basenames for the link text instead of the full path\n- **File Links**: Do not surround the link text with backticks, that will break the link formatting.\n    - **Correct**: [utils.py](file:///path/to/utils.py) or [foo](file:///path/to/file.py#L123)\n    - **Incorrect**: [`utils.py`](file:///path/to/utils.py) or [`function name`](file:///path/to/file.py#L123)\n</format_tips>\n\n</artifact_formatting_guidelines>\n<tool_calling>\nCall tools as you normally would. The following list provides additional guidance to help you avoid errors:   - **Absolute paths only**. When using tools that accept file path arguments, ALWAYS use the absolute file path.\n</tool_calling>\n<web_application_development>\n## Technology Stack,\nYour web applications should be built using the following technologies:,\n1. **Core**: Use HTML for structure and Javascript for logic.\n2. **Styling (CSS)**: Use Vanilla CSS for maximum flexibility and control. Avoid using TailwindCSS unless the USER explicitly requests it; in this case, first confirm which TailwindCSS version to use.\n3. **Web App**: If the USER specifies that they want a more complex web app, use a framework like Next.js or Vite. Only do this if the USER explicitly requests a web app.\n4. **New Project Creation**: If you need to use a framework for a new app, use `npx` with the appropriate script, but there are some rules to follow:,\n   - Use `npx -y` to automatically install the script and its dependencies\n   - You MUST run the command with `--help` flag to see all available options first, \n   - Initialize the app in the current directory with `./` (example: `npx -y create-vite-app@latest ./`),\n   - You should run in non-interactive mode so that the user doesn't need to input anything,\n5. **Running Locally**: When running locally, use `npm run dev` or equivalent dev server. Only build the production bundle if the USER explicitly requests it or you are validating the code for correctness.\n\n# Design Aesthetics,\n1. **Use Rich Aesthetics**: The USER should be wowed at first glance by the design. Use best practices in modern web design (e.g. vibrant colors, dark modes, glassmorphism, and dynamic animations) to create a stunning first impression. Failure to do this is UNACCEPTABLE.\n2. **Prioritize Visual Excellence**: Implement designs that will WOW the user and feel extremely premium:\n\t\t- Avoid generic colors (plain red, blue, green). Use curated, harmonious color palettes (e.g., HSL tailored colors, sleek dark modes).\n   - Using modern typography (e.g., from Google Fonts like Inter, Roboto, or Outfit) instead of browser defaults.\n\t\t- Use smooth gradients,\n\t\t- Add subtle micro-animations for enhanced user experience,\n3. **Use a Dynamic Design**: An interface that feels responsive and alive encourages interaction. Achieve this with hover effects and interactive elements. Micro-animations, in particular, are highly effective for improving user engagement.\n4. **Premium Designs**. Make a design that feels premium and state of the art. Avoid creating simple minimum viable products.\n4. **Don't use placeholders**. If you need an image, use your generate_image tool to create a working demonstration.,\n\n## Implementation Workflow,\nFollow this systematic approach when building web applications:,\n1. **Plan and Understand**:,\n\t\t- Fully understand the user's requirements,\n\t\t- Draw inspiration from modern, beautiful, and dynamic web designs,\n\t\t- Outline the features needed for the initial version,\n2. **Build the Foundation**:,\n\t\t- Start by creating/modifying `index.css`,\n\t\t- Implement the core design system with all tokens and utilities,\n3. **Create Components**:,\n\t\t- Build necessary components using your design system,\n\t\t- Ensure all components use predefined styles, not ad-hoc utilities,\n\t\t- Keep components focused and reusable,\n4. **Assemble Pages**:,\n\t\t- Update the main application to incorporate your design and components,\n\t\t- Ensure proper routing and navigation,\n\t\t- Implement responsive layouts,\n5. **Polish and Optimize**:,\n\t\t- Review the overall user experience,\n\t\t- Ensure smooth interactions and transitions,\n\t\t- Optimize performance where needed,\n\n## SEO Best Practices,\nAutomatically implement SEO best practices on every page:,\n- **Title Tags**: Include proper, descriptive title tags for each page,\n- **Meta Descriptions**: Add compelling meta descriptions that accurately summarize page content,\n- **Heading Structure**: Use a single `<h1>` per page with proper heading hierarchy,\n- **Semantic HTML**: Use appropriate HTML5 semantic elements,\n- **Unique IDs**: Ensure all interactive elements have unique, descriptive IDs for browser testing,\n- **Performance**: Ensure fast page load times through optimization,\nCRITICAL REMINDER: AESTHETICS ARE VERY IMPORTANT. If your web app looks simple and basic then you have FAILED!\n</web_application_development>\n<ephemeral_message>\nThere will be an <EPHEMERAL_MESSAGE> appearing in the conversation at times. This is not coming from the user, but instead injected by the system as important information to pay attention to. \nDo not respond to nor acknowledge those messages, but do follow them strictly.\n</ephemeral_message>\n\n\n<skills>\nYou can use specialized 'skills' to help you with complex tasks. Each skill has a name and a description listed below.\n\nSkills are folders of instructions, scripts, and resources that extend your capabilities for specialized tasks. Each skill folder contains:\n- **SKILL.md** (required): The main instruction file with YAML frontmatter (name, description) and detailed markdown instructions\n\nMore complex skills may include additional directories and files as needed, for example:\n- **scripts/** - Helper scripts and utilities that extend your capabilities\n- **examples/** - Reference implementations and usage patterns\n- **resources/** - Additional files, templates, or assets the skill may reference\n\nIf a skill seems relevant to your current task, you MUST use the `view_file` tool on the SKILL.md file to read its full instructions before proceeding. Once you have read the instructions, follow them exactly as documented.\n\n</skills>\n<communication_style>\n- **Formatting**. Format your responses in github-style markdown to make your responses easier for the USER to parse. For example, use headers to organize your responses and bolded or italicized text to highlight important keywords. Use backticks to format file, directory, function, and class names. If providing a URL to the user, format this in markdown as well, for example `[label](example.com)`. - **Proactiveness**. As an agent, you are allowed to be proactive, but only in the course of completing the user's task. For example, if the user asks you to add a new component, you can edit the code, verify build and test statuses, and take any other obvious follow-up actions, such as performing additional research. However, avoid surprising the user. For example, if the user asks HOW to approach something, you should answer their question and instead of jumping into editing a file. - **Helpfulness**. Respond like a helpful software engineer who is explaining your work to a friendly collaborator on the project. Acknowledge mistakes or any backtracking you do as a result of new information. - **Ask for clarification**. If you are unsure about the USER's intent, always ask for clarification rather than making assumptions.\n</communication_style>",
          timeToFirstToken: "2.719486400s",
          toolChoice: {
            optionName: "auto"
          },
          tools: [
            {
              "description": "Start a browser subagent to perform actions in the browser with the given task description. The subagent has access to tools for both interacting with web page content (clicking, typing, navigating, etc) and controlling the browser window itself (resizing, etc). Please make sure to define a clear condition to return on. After the subagent returns, you should read the DOM or capture a screenshot to see what it did. Note: All browser interactions are automatically recorded and saved as WebP videos to the artifacts directory. This is the ONLY way you can record a browser session video/animation. IMPORTANT: if the subagent returns that the open_browser_url tool failed, there is a browser issue that is out of your control. You MUST ask the user how to proceed and use the suggested_responses tool.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"TaskName\":{\"type\":\"string\",\"description\":\"Name of the task that the browser subagent is performing. This is the identifier that groups the subagent steps together, but should still be a human readable name. This should read like a title, should be properly capitalized and human readable, example: 'Navigating to Example Page'. Replace URLs or non-human-readable expressions like CSS selectors or long text with human-readable terms like 'URL' or 'Page' or 'Submit Button'. Be very sure this task name represents a reasonable chunk of work. It should almost never be the entire user request. This should be the very first argument.\"},\"Task\":{\"type\":\"string\",\"description\":\"A clear, actionable task description for the browser subagent. The subagent is an agent similar to you, with a different set of tools, limited to tools to understand the state of and control the browser. The task you define is the prompt sent to this subagent. Since each agent invocation is a one-shot, autonomous execution, the prompt must be highly detailed, containing a comprehensive task description and all necessary context. Avoid vague instructions; be specific about what to do, when to stop, and clearly state exactly what information the agent should return in its final and only report. This should be the second argument.\"},\"RecordingName\":{\"type\":\"string\",\"description\":\"Name of the browser recording that is created with the actions of the subagent. Should be all lowercase with underscores, describing what the recording contains. Maximum 3 words. Example: 'login_flow_demo'\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"TaskName\",\"Task\",\"RecordingName\"]}",
              "name": "browser_subagent"
            },
            {
              "description": "Get the status of a previously executed terminal command by its ID. Returns the current status (running, done), output lines as specified by output priority, and any error if present. Do not try to check the status of any IDs other than Background command IDs.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"CommandId\":{\"type\":\"string\",\"description\":\"ID of the command to get status for\"},\"OutputCharacterCount\":{\"type\":\"integer\",\"description\":\"Number of characters to view. Make this as small as possible to avoid excessive memory usage.\"},\"WaitDurationSeconds\":{\"type\":\"integer\",\"description\":\"Number of seconds to wait for command completion before getting the status. If the command completes before this duration, this tool call will return early. Set to 0 to get the status of the command immediately. If you are only interested in waiting for command completion, set to the max value, 300.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"CommandId\",\"WaitDurationSeconds\"]}",
              "name": "command_status"
            },
            {
              "description": "Search for files and subdirectories within a specified directory using fd.\nSearch uses smart case and will ignore gitignored files by default.\nPattern and Excludes both use the glob format. If you are searching for Extensions, there is no need to specify both Pattern AND Extensions.\nTo avoid overwhelming output, the results are capped at 50 matches. Use the various arguments to filter the search scope as needed.\nResults will include the type, size, modification time, and relative path.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"SearchDirectory\":{\"type\":\"string\",\"description\":\"The directory to search within\"},\"Pattern\":{\"type\":\"string\",\"description\":\"Optional, Pattern to search for, supports glob format\"},\"Excludes\":{\"items\":{\"type\":\"string\"},\"type\":\"array\",\"description\":\"Optional, exclude files/directories that match the given glob patterns\"},\"Type\":{\"type\":\"string\",\"description\":\"Optional, type filter, enum=file,directory,any\"},\"MaxDepth\":{\"type\":\"integer\",\"description\":\"Optional, maximum depth to search\"},\"Extensions\":{\"items\":{\"type\":\"string\"},\"type\":\"array\",\"description\":\"Optional, file extensions to include (without leading .), matching paths must match at least one of the included extensions\"},\"FullPath\":{\"type\":\"boolean\",\"description\":\"Optional, whether the full absolute path must match the glob pattern, default: only filename needs to match. Take care when specifying glob patterns with this flag on, e.g when FullPath is on, pattern '*.py' will not match to the file '/foo/bar.py', but pattern '**/*.py' will match.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"SearchDirectory\",\"Pattern\"]}",
              "name": "find_by_name"
            },
            {
              "description": "Generate an image or edit existing images based on a text prompt. The resulting image will be saved as an artifact for use. You can use this tool to generate user interfaces and iterate on a design with the USER for an application or website that you are building. When creating UI designs, generate only the interface itself without surrounding device frames (laptops, phones, tablets, etc.) unless the user explicitly requests them. You can also use this tool to generate assets for use in an application or website.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"Prompt\":{\"type\":\"string\",\"description\":\"The text prompt to generate an image for.\"},\"ImagePaths\":{\"items\":{\"type\":\"string\"},\"type\":\"array\",\"description\":\"Optional absolute paths to the images to use in generation. You can pass in images here if you would like to edit or combine images. You can pass in artifact images and any images in the file system. Note: you cannot pass in more than 3 images.\"},\"ImageName\":{\"type\":\"string\",\"description\":\"Name of the generated image to save. Should be all lowercase with underscores, describing what the image contains. Maximum 3 words. Example: 'login_page_mockup'\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"Prompt\",\"ImageName\"]}",
              "name": "generate_image"
            },
            {
              "description": "Use ripgrep to find exact pattern matches within files or directories.\nResults are returned in JSON format and for each match you will receive the:\n- Filename\n- LineNumber\n- LineContent: the content of the matching line\nTotal results are capped at 50 matches. Use the Includes option to filter by file type or specific paths to refine your search.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"SearchPath\":{\"type\":\"string\",\"description\":\"The path to search. This can be a directory or a file. This is a required parameter.\"},\"Query\":{\"type\":\"string\",\"description\":\"The search term or pattern to look for within files.\"},\"MatchPerLine\":{\"type\":\"boolean\",\"description\":\"If true, returns each line that matches the query, including line numbers and snippets of matching lines (equivalent to 'git grep -nI'). If false, only returns the names of files containing the query (equivalent to 'git grep -l').\"},\"Includes\":{\"items\":{\"type\":\"string\"},\"type\":\"array\",\"description\":\"Glob patterns to filter files found within the 'SearchPath', if 'SearchPath' is a directory. For example, '*.go' to only include Go files, or '!**/vendor/*' to exclude vendor directories. This is NOT for specifying the primary search directory; use 'SearchPath' for that. Leave empty if no glob filtering is needed or if 'SearchPath' is a single file.\"},\"CaseInsensitive\":{\"type\":\"boolean\",\"description\":\"If true, performs a case-insensitive search.\"},\"IsRegex\":{\"type\":\"boolean\",\"description\":\"If true, treats Query as a regular expression pattern with special characters like *, +, (, etc. having regex meaning. If false, treats Query as a literal string where all characters are matched exactly. Use false for normal text searches and true only when you specifically need regex functionality.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"SearchPath\",\"Query\"]}",
              "name": "grep_search"
            },
            {
              "description": "List the contents of a directory, i.e. all files and subdirectories that are children of the directory. Directory path must be an absolute path to a directory that exists. For each child in the directory, output will have: relative path to the directory, whether it is a directory or file, size in bytes if file, and number of children (recursive) if directory. Number of children may be missing if the workspace is too large, since we are not able to track the entire workspace.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"DirectoryPath\":{\"type\":\"string\",\"description\":\"Path to list contents of, should be absolute path to a directory\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"DirectoryPath\"]}",
              "name": "list_dir"
            },
            {
              "description": "Lists the available resources from an MCP server.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"ServerName\":{\"type\":\"string\",\"description\":\"Name of the server to list available resources from.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\"}",
              "name": "list_resources"
            },
            {
              "attributionFieldNames": [
                "ReplacementChunks.ReplacementChunkNoRange.ReplacementChunkBase.ReplacementContent"
              ],
              "description": "Use this tool to edit an existing file. Follow these rules:\n1. Use this tool ONLY when you are making MULTIPLE, NON-CONTIGUOUS edits to the same file (i.e., you are changing more than one separate block of text). If you are making a single contiguous block of edits, use the replace_file_content tool instead.\n2. Do NOT use this tool if you are only editing a single contiguous block of lines.\n3. Do NOT make multiple parallel calls to this tool or the replace_file_content tool for the same file.\n4. To edit multiple, non-adjacent lines of code in the same file, make a single call to this tool. Specify each edit as a separate ReplacementChunk.\n5. For each ReplacementChunk, specify StartLine, EndLine, TargetContent and ReplacementContent. StartLine and EndLine should specify a range of lines containing precisely the instances of TargetContent that you wish to edit. To edit a single instance of the TargetContent, the range should be such that it contains that specific instance of the TargetContent and no other instances. When applicable, provide a range that matches the range viewed in a previous view_file call. In TargetContent, specify the precise lines of code to edit. These lines MUST EXACTLY MATCH text in the existing file content. In ReplacementContent, specify the replacement content for the specified target content. This must be a complete drop-in replacement of the TargetContent, with necessary modifications made.\n6. If you are making multiple edits across a single file, specify multiple separate ReplacementChunks. DO NOT try to replace the entire existing content with the new content, this is very expensive.\n7. You may not edit file extensions: [.ipynb]\nIMPORTANT: You must generate the following arguments first, before any others: [TargetFile]",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"TargetFile\":{\"type\":\"string\",\"description\":\"The target file to modify. Always specify the target file as the very first argument.\"},\"CodeMarkdownLanguage\":{\"type\":\"string\",\"description\":\"Markdown language for the code block, e.g 'python' or 'javascript'\"},\"Instruction\":{\"type\":\"string\",\"description\":\"A description of the changes that you are making to the file.\"},\"TargetLintErrorIds\":{\"items\":{\"type\":\"string\"},\"type\":\"array\",\"description\":\"If applicable, IDs of lint errors this edit aims to fix (they'll have been given in recent IDE feedback). If you believe the edit could fix lints, do specify lint IDs; if the edit is wholly unrelated, do not. A rule of thumb is, if your edit was influenced by lint feedback, include lint IDs. Exercise honest judgement here.\"},\"Description\":{\"type\":\"string\",\"description\":\"Brief, user-facing explanation of what this change did. Focus on non-obvious rationale, design decisions, or important context. Don't just restate what the code does.\"},\"Complexity\":{\"type\":\"integer\",\"description\":\"A 1-10 rating of how important it is for the user to review this change. Rate based on: 1-3 (routine/obvious), 4-6 (worth noting), 7-10 (critical or subtle and warrants explanation).\"},\"ReplacementChunks\":{\"items\":{\"properties\":{\"AllowMultiple\":{\"type\":\"boolean\",\"description\":\"If true, multiple occurrences of 'targetContent' will be replaced by 'replacementContent' if they are found. Otherwise if multiple occurences are found, an error will be returned.\"},\"TargetContent\":{\"type\":\"string\",\"description\":\"The exact string to be replaced. This must be the exact character-sequence to be replaced, including whitespace. Be very careful to include any leading whitespace otherwise this will not work at all. This must be a unique substring within the file, or else it will error.\"},\"ReplacementContent\":{\"type\":\"string\",\"description\":\"The content to replace the target content with.\"},\"StartLine\":{\"type\":\"integer\",\"description\":\"The starting line number of the chunk (1-indexed). Should be at or before the first line containing the target content. Must satisfy 1 \\u003c= StartLine \\u003c= EndLine. The target content is searched for within the [StartLine, EndLine] range.\"},\"EndLine\":{\"type\":\"integer\",\"description\":\"The ending line number of the chunk (1-indexed). Should be at or after the last line containing the target content. Must satisfy StartLine \\u003c= EndLine \\u003c= number of lines in the file. The target content is searched for within the [StartLine, EndLine] range.\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"AllowMultiple\",\"TargetContent\",\"ReplacementContent\",\"StartLine\",\"EndLine\"]},\"type\":\"array\",\"description\":\"A list of chunks to replace. It is best to provide multiple chunks for non-contiguous edits if possible. This must be a JSON array, not a string.\"},\"ArtifactMetadata\":{\"properties\":{\"Summary\":{\"type\":\"string\",\"description\":\"Detailed multi-line summary of the artifact file, after edits have been made. Summary does not need to mention the artifact name and should focus on the contents and purpose of the artifact.\"},\"ArtifactType\":{\"type\":\"string\",\"enum\":[\"implementation_plan\",\"walkthrough\",\"task\",\"other\"],\"description\":\"Type of artifact: 'implementation_plan', 'walkthrough', 'task', or 'other'.\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"Summary\",\"ArtifactType\"],\"description\":\"Metadata updates if updating an artifact file, leave blank if not updating an artifact. Should be updated if the content is changing meaningfully.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"TargetFile\",\"CodeMarkdownLanguage\",\"Instruction\",\"Description\",\"Complexity\",\"ReplacementChunks\"]}",
              "name": "multi_replace_file_content"
            },
            {
              "description": "This tool is used as a way to communicate with the user.\n\nThis may be because you have some questions for the user, or if you want them to review important documents. If you are currently in a task as set by the task_boundary tool, then this is the only way to communicate with the user. Other ways of sending messages while you are mid-task will not be visible to the user.\n\nWhen sending messages via the message argument, be very careful to make this as concise as possible. If requesting review, do not be redundant with the file you are asking to be reviewed, but make sure to provide the file in PathsToReview. Do not summarize everything that you have done. If you are asking questions, then simply ask only the questions. Make them as a numbered list if there are multiple.\nWhen requesting user input, focus on specific decisions that require their expertise or preferences rather than general plan approval. Users provide more valuable feedback when asked about concrete choices, alternative approaches, configuration parameters, or scope clarification.\n\nWhen BlockedOnUser is set to true, then you are blocked on user approval/feedback to proceed on the document(s) specified in PathsToReview. The user may have a review policy that will auto-proceed after these tool calls, by which ShouldAutoProceed is used to determine whether to continue or not. Make sure to set ShouldAutoProceed to true if you are very confident in the approach outlined in the documents; if you are unsure, err on the side of caution and set it to false.\nThis tool should primarily only be used while inside an active task as determined by the task boundaries. Pay attention to the ephemeral message that will remind you of your current task status. Occasionally you may use it outside of a task in order to request review of paths. If that is the case, the message should be extremely concise, only one line.\n\nIMPORTANT NOTES:\n- This tool should NEVER be called in parallel with other tools.\n- Execution control will be returned to the user once this tool is called, you will not be able to continue work until they respond.\n- Remember that ShouldAutoProceed can only be set to true if you are very confident in the approach outlined in the documents and the changes are very straightforward.\nIMPORTANT: You must generate the following arguments first, before any others: [PathsToReview, BlockedOnUser]",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"PathsToReview\":{\"items\":{\"type\":\"string\"},\"type\":\"array\",\"description\":\"List of ABSOLUTE paths to files that the user should be notified about. You MUST populate this if the notification is to request review for artifacts or files. These must be ABSOLUTE paths, leave empty if you are not requesting review for artifacts or files. Specify this argument first.\"},\"BlockedOnUser\":{\"type\":\"boolean\",\"description\":\"Set this to true if you are blocked on user approval to proceed. This is most appropriate when you want the user to review a plan or design doc, where there is more work to be done after approval. Do not set this to true if you are just notifying user about the completion of your work, e.g for a walkthrough or for a finished report. If you are requesting user feedback, then you MUST populate PathsToReview. Specify this argument second.\"},\"Message\":{\"type\":\"string\",\"description\":\"Required message to notify the user with, e.g to provide context, ask questions, or just to pass a message to the user to see. Specify this argument last.\"},\"ShouldAutoProceed\":{\"type\":\"boolean\",\"description\":\"Set this to true if you believe that the task you notified the user about can be proceeded with without any explicit user feedback and you are extremely confident in the approach. If the user wants to explicitly provide feedback, do not set this to true. \"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"PathsToReview\",\"BlockedOnUser\",\"Message\",\"ShouldAutoProceed\"]}",
              "name": "notify_user"
            },
            {
              "description": "Retrieves a specified resource's contents.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"ServerName\":{\"type\":\"string\",\"description\":\"Name of the server to read the resource from.\"},\"Uri\":{\"type\":\"string\",\"description\":\"Unique identifier for the resource.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\"}",
              "name": "read_resource"
            },
            {
              "description": "Reads the contents of a terminal given its process ID.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"ProcessID\":{\"type\":\"string\",\"description\":\"Process ID of the terminal to read.\"},\"Name\":{\"type\":\"string\",\"description\":\"Name of the terminal to read.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"ProcessID\",\"Name\"]}",
              "name": "read_terminal"
            },
            {
              "description": "Fetch content from a URL via HTTP request (invisible to USER). Use when: (1) extracting text from public pages, (2) reading static content/documentation, (3) batch processing multiple URLs, (4) speed is important, or (5) no visual interaction needed. Converts HTML to markdown. No JavaScript execution, no authentication. For pages requiring login, JavaScript, or USER visibility, use read_browser_page instead.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"Url\":{\"type\":\"string\",\"description\":\"URL to read content from\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"Url\"]}",
              "name": "read_url_content"
            },
            {
              "attributionFieldNames": [
                "ReplacementChunk.ReplacementChunkNoRange.ReplacementChunkBase.ReplacementContent"
              ],
              "description": "Use this tool to edit an existing file. Follow these rules:\n1. Use this tool ONLY when you are making a SINGLE CONTIGUOUS block of edits to the same file (i.e. replacing a single contiguous block of text). If you are making edits to multiple non-adjacent lines, use the multi_replace_file_content tool instead.\n2. Do NOT make multiple parallel calls to this tool or the multi_replace_file_content tool for the same file.\n3. To edit multiple, non-adjacent lines of code in the same file, make a single call to the multi_replace_file_content \t\"toolName\": shared.MultiReplaceFileContentToolName,.\n4. For the ReplacementChunk, specify StartLine, EndLine, TargetContent and ReplacementContent. StartLine and EndLine should specify a range of lines containing precisely the instances of TargetContent that you wish to edit. To edit a single instance of the TargetContent, the range should be such that it contains that specific instance of the TargetContent and no other instances. When applicable, provide a range that matches the range viewed in a previous view_file call. In TargetContent, specify the precise lines of code to edit. These lines MUST EXACTLY MATCH text in the existing file content. In ReplacementContent, specify the replacement content for the specified target content. This must be a complete drop-in replacement of the TargetContent, with necessary modifications made.\n5. If you are making multiple edits across a single file, use the multi_replace_file_content tool instead.. DO NOT try to replace the entire existing content with the new content, this is very expensive.\n6. You may not edit file extensions: [.ipynb]\nIMPORTANT: You must generate the following arguments first, before any others: [TargetFile]",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"TargetFile\":{\"type\":\"string\",\"description\":\"The target file to modify. Always specify the target file as the very first argument.\"},\"CodeMarkdownLanguage\":{\"type\":\"string\",\"description\":\"Markdown language for the code block, e.g 'python' or 'javascript'\"},\"Instruction\":{\"type\":\"string\",\"description\":\"A description of the changes that you are making to the file.\"},\"TargetLintErrorIds\":{\"items\":{\"type\":\"string\"},\"type\":\"array\",\"description\":\"If applicable, IDs of lint errors this edit aims to fix (they'll have been given in recent IDE feedback). If you believe the edit could fix lints, do specify lint IDs; if the edit is wholly unrelated, do not. A rule of thumb is, if your edit was influenced by lint feedback, include lint IDs. Exercise honest judgement here.\"},\"Description\":{\"type\":\"string\",\"description\":\"Brief, user-facing explanation of what this change did. Focus on non-obvious rationale, design decisions, or important context. Don't just restate what the code does.\"},\"Complexity\":{\"type\":\"integer\",\"description\":\"A 1-10 rating of how important it is for the user to review this change. Rate based on: 1-3 (routine/obvious), 4-6 (worth noting), 7-10 (critical or subtle and warrants explanation).\"},\"AllowMultiple\":{\"type\":\"boolean\",\"description\":\"If true, multiple occurrences of 'targetContent' will be replaced by 'replacementContent' if they are found. Otherwise if multiple occurences are found, an error will be returned.\"},\"TargetContent\":{\"type\":\"string\",\"description\":\"The exact string to be replaced. This must be the exact character-sequence to be replaced, including whitespace. Be very careful to include any leading whitespace otherwise this will not work at all. This must be a unique substring within the file, or else it will error.\"},\"ReplacementContent\":{\"type\":\"string\",\"description\":\"The content to replace the target content with.\"},\"StartLine\":{\"type\":\"integer\",\"description\":\"The starting line number of the chunk (1-indexed). Should be at or before the first line containing the target content. Must satisfy 1 \\u003c= StartLine \\u003c= EndLine. The target content is searched for within the [StartLine, EndLine] range.\"},\"EndLine\":{\"type\":\"integer\",\"description\":\"The ending line number of the chunk (1-indexed). Should be at or after the last line containing the target content. Must satisfy StartLine \\u003c= EndLine \\u003c= number of lines in the file. The target content is searched for within the [StartLine, EndLine] range.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"TargetFile\",\"CodeMarkdownLanguage\",\"Instruction\",\"Description\",\"Complexity\",\"AllowMultiple\",\"TargetContent\",\"ReplacementContent\",\"StartLine\",\"EndLine\"]}",
              "name": "replace_file_content"
            },
            {
              "description": "PROPOSE a command to run on behalf of the user. Operating System: windows. Shell: powershell.\n**NEVER PROPOSE A cd COMMAND**.\nIf you have this tool, note that you DO have the ability to run commands directly on the USER's system.\nMake sure to specify CommandLine exactly as it should be run in the shell.\nNote that the user will have to approve the command before it is executed. The user may reject it if it is not to their liking.\nThe actual command will NOT execute until the user approves it. The user may not approve it immediately.\nIf the step is WAITING for user approval, it has NOT started running.\nIf the step returns a command id, it means that the command was sent to the background. You should use the command_status tool to monitor the output and status of the command.\nCommands will be run with PAGER=cat. You may want to limit the length of output for commands that usually rely on paging and may contain very long output (e.g. git log, use git log -n <N>).",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"Cwd\":{\"type\":\"string\",\"description\":\"The current working directory for the command\"},\"WaitMsBeforeAsync\":{\"type\":\"integer\",\"description\":\"This specifies the number of milliseconds to wait after starting the command before sending it to the background. If you want the command to complete execution synchronously, set this to a large enough value that you expect the command to complete in that time under ordinary circumstances. If you're starting an interactive or long-running command, set it to a large enough value that it would cause possible failure cases to execute synchronously (e.g. 500ms). Keep the value as small as possible, with a maximum of 10000ms.\"},\"SafeToAutoRun\":{\"type\":\"boolean\",\"description\":\"Set to true if you believe that this command is safe to run WITHOUT user approval. A command is unsafe if it may have some destructive side-effects. Example unsafe side-effects include: deleting files, mutating state, installing system dependencies, making external requests, etc. Set to true only if you are extremely confident it is safe. If you feel the command could be unsafe, never set this to true, EVEN if the USER asks you to. It is imperative that you never auto-run a potentially unsafe command.\"},\"CommandLine\":{\"type\":\"string\",\"description\":\"The exact command line string to execute.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"Cwd\",\"WaitMsBeforeAsync\",\"SafeToAutoRun\",\"CommandLine\"]}",
              "name": "run_command"
            },
            {
              "description": "Performs a web search for a given query. Returns a summary of relevant information along with URL citations.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"query\":{\"type\":\"string\"},\"domain\":{\"type\":\"string\",\"description\":\"Optional domain to recommend the search prioritize\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"query\"]}",
              "name": "search_web"
            },
            {
              "description": "Send standard input to a running command or to terminate a command. Use this to interact with REPLs, interactive commands, and long-running processes. The command must have been created by a previous run_command call. Use the command_status tool to check the status and output of the command after sending input.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"CommandId\":{\"type\":\"string\",\"description\":\"The command ID from a previous run_command call. This is returned in the run_command output.\"},\"Input\":{\"type\":\"string\",\"description\":\"The input to send to the command's stdin. Include newline characters (the literal character, not the escape sequence) if needed to submit commands. Exactly one of input and terminate must be specified.\"},\"Terminate\":{\"type\":\"boolean\",\"description\":\"Whether to terminate the command. Exactly one of input and terminate must be specified.\"},\"WaitMs\":{\"type\":\"integer\",\"description\":\"Amount of time to wait for output after sending input. Keep the value as small as possible, but large enough to capture the output you expect. Must be between 500ms and 10000ms.\"},\"SafeToAutoRun\":{\"type\":\"boolean\",\"description\":\"Set to true if you believe that this command is safe to run WITHOUT user approval. An input is unsafe if it may have some destructive side-effects. Example unsafe side-effects include: deleting files, mutating state, installing system dependencies, making external requests, etc. Set to true only if you are extremely confident it is safe. If you feel the input could be unsafe, never set this to true, EVEN if the USER asks you to. It is imperative that you never auto-run a potentially unsafe input.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"CommandId\",\"WaitMs\",\"SafeToAutoRun\"]}",
              "name": "send_command_input"
            },
            {
              "description": "\nCRITICAL: You must ALWAYS call this tool as the VERY FIRST tool in your list of tool calls, before any other tools.\nIndicate the start of a task or make an update to the current task. This should roughly correspond to the top-level items in your task.md, so you should change these in sync with each other. You should change this AFTER marking an item as in-progress in task.md, not the other way around.\nThe tool should also be used to update the status and summary periodically throughout the task. When updating the status or summary of the current task, you must use the exact same TaskName as before. The TaskName should be pretty granular, do not have one single task for the entire user prompt. Remember that it should roughly correspond to one bullet point in the task.md, so break down the tasks first and then set the task name. Summary should be concise but comprehensive of all that has been done for the entire task, and should only mention tasks you have done and not tasks you plan to do or will do in the future.\nTo avoid repeating the same values, you should use the special string \"%SAME%\" for Mode, TaskName, TaskStatus, or TaskSummary to indicate that the same value from the previous task boundary call should be reused. This is more efficient than repeating identical strings.\nFormat your summary in github-style markdown. Use backticks to format file, directory, function, and class names. There should not be any code references not surrounded by backticks. If you wish to reset your current task to empty, then you should call this tool with completely empty arguments.\n\nPay attention to the ephemeral message that will remind you of your current task status.\nIMPORTANT: You must generate the following arguments first, before any others: [TaskName, Mode, PredictedTaskSize]",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"TaskName\":{\"type\":\"string\",\"description\":\"Name of the task boundary. This is the identifier that groups steps together, but should still be a human readable name. This should read like a title, should be properly capitalized and human readable, example: 'Researching Existing Server Implementation'. This should correspond to a top-level item in task.md, not the entire single overall objective. Be very sure this task name represents a reasonable chunk of work. It should almost never be the entire user request. Over the course of the overall objective there should be more than one distinct TaskName. This should be the very first argument.\"},\"Mode\":{\"type\":\"string\",\"description\":\"The agent focus to switch to. This should be the second argument.\"},\"TaskSummary\":{\"type\":\"string\",\"description\":\"Concise summary of what has been accomplished throughout the entire task so far. Should be at most 1-2 lines. Should be full sentences, past tense. You should cite important files or node names between backticks by filename. You must only mention tasks you have done and not tasks you will do in the future. This should be the third argument.\"},\"TaskStatus\":{\"type\":\"string\",\"description\":\"Active status of the current action in the task, e.g 'Looking for files', should not end with any punctuation at all. Should be a single line, very concise and readable. This should be broad enough to encapsulate multiple tool calls; please avoid annotating each tool call individually. This should be describing what you are GOING TO DO NEXT, not what you have done. This should be the fourth argument.\"},\"PredictedTaskSize\":{\"type\":\"integer\",\"description\":\"Your best estimation on how many tool calls are needed to fullfil this task assuming everything works as expected. If you are just updating an existing task, then estimate how many tool calls are remaining.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"TaskName\",\"Mode\",\"TaskSummary\",\"TaskStatus\",\"PredictedTaskSize\"]}",
              "name": "task_boundary"
            },
            {
              "description": "View the content of up to 5 code item nodes in a file, each as a class or a function. You must use fully qualified code item names, such as those return by the grep_search or other tools. For example, if you have a class called `Foo` and you want to view the function definition `bar` in the `Foo` class, you would use `Foo.bar` as the NodeName. Do not request to view a symbol if the contents have been previously shown by the codebase_search tool. If the symbol is not found in a file, the tool will return an empty string instead.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"File\":{\"type\":\"string\",\"description\":\"Absolute path to the node to view, e.g /path/to/file\"},\"NodePaths\":{\"items\":{\"type\":\"string\"},\"type\":\"array\",\"description\":\"Path of the nodes within the file, e.g package.class.FunctionName\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"File\",\"NodePaths\"]}",
              "name": "view_code_item"
            },
            {
              "description": "View a specific chunk of document content using its DocumentId and chunk position. The DocumentId must have already been read by the read_url_content tool before this can be used on that particular DocumentId.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"document_id\":{\"type\":\"string\",\"description\":\"The ID of the document that the chunk belongs to\"},\"position\":{\"type\":\"integer\",\"description\":\"The position of the chunk to view\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"document_id\",\"position\"]}",
              "name": "view_content_chunk"
            },
            {
              "description": "View the contents of a file from the local filesystem. This tool supports some binary files such as images and videos.\nText file usage:\n- The lines of the file are 1-indexed\n- The first time you read a new file the tool will enforce reading 800 lines to understand as much about the file as possible\n- The output of this tool call will be the file contents from StartLine to EndLine (inclusive)\n- You can view at most 800 lines at a time\n- To view the whole file do not pass StartLine or EndLine arguments\nBinary file usage:\n- Do not provide StartLine or EndLine arguments, this tool always returns the entire file",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"AbsolutePath\":{\"type\":\"string\",\"description\":\"Path to file to view. Must be an absolute path.\"},\"StartLine\":{\"type\":\"integer\",\"description\":\"Optional. Startline to view, 1-indexed as usual, inclusive. This value must be less than or equal to EndLine.\"},\"EndLine\":{\"type\":\"integer\",\"description\":\"Optional. Endline to view, 1-indexed as usual, inclusive. This value must be greater than or equal to StartLine.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"AbsolutePath\"]}",
              "name": "view_file"
            },
            {
              "description": "View the outline of the input file. This is the preferred first-step tool for exploring the contents of files. IMPORTANT: This tool ONLY works on files, never directories. Always verify the path is a file before using this tool. The outline will contain a breakdown of functions and classes in the file. For each, it will show the node path, signature, and current line range. There may be lines of code in the file not covered by the outline if they do not belong to a class or function directly, for example imports or top-level constants.\n\nThe tool result will also contain the total number of lines in the file and the total number of outline items. When viewing a file for the first time with offset 0, we will also attempt to show the contents of the file, which may be truncated if the file is too large. If there are too many items, only a subset of them will be shown. They are shown in order of appearance in the file.",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"AbsolutePath\":{\"type\":\"string\",\"description\":\"Path to file to view. Must be an absolute path.\"},\"ItemOffset\":{\"type\":\"integer\",\"description\":\"Offset of items to show. This is used for pagination. The first request to a file should have an offset of 0.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"AbsolutePath\"]}",
              "name": "view_file_outline"
            },
            {
              "attributionFieldNames": [
                "CodeContent"
              ],
              "description": "Use this tool to create new files. The file and any parent directories will be created for you if they do not already exist.\n\t\tFollow these instructions:\n\t\t1. By default this tool will error if TargetFile already exists. To overwrite an existing file, set Overwrite to true.\n\t\t2. You MUST specify TargetFile as the FIRST argument. Please specify the full TargetFile before any of the code contents.\nIMPORTANT: You must generate the following arguments first, before any others: [TargetFile, Overwrite]",
              "jsonSchemaString": "{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"properties\":{\"TargetFile\":{\"type\":\"string\",\"description\":\"The target file to create and write code to.\"},\"Overwrite\":{\"type\":\"boolean\",\"description\":\"Set this to true to overwrite an existing file. WARNING: This will replace the entire file contents. Only use when you explicitly intend to overwrite. Otherwise, use a code edit tool to modify existing files.\"},\"CodeContent\":{\"type\":\"string\",\"description\":\"The code contents to write to the file.\"},\"EmptyFile\":{\"type\":\"boolean\",\"description\":\"Set this to true to create an empty file.\"},\"Description\":{\"type\":\"string\",\"description\":\"Brief, user-facing explanation of what this change did. Focus on non-obvious rationale, design decisions, or important context. Don't just restate what the code does.\"},\"Complexity\":{\"type\":\"integer\",\"description\":\"A 1-10 rating of how important it is for the user to review this change. Rate based on: 1-3 (routine/obvious), 4-6 (worth noting), 7-10 (critical or subtle and warrants explanation).\"},\"IsArtifact\":{\"type\":\"boolean\",\"description\":\"Set this to true when creating an artifact file.\"},\"ArtifactMetadata\":{\"properties\":{\"Summary\":{\"type\":\"string\",\"description\":\"Detailed multi-line summary of the artifact file, after edits have been made. Summary does not need to mention the artifact name and should focus on the contents and purpose of the artifact.\"},\"ArtifactType\":{\"type\":\"string\",\"enum\":[\"implementation_plan\",\"walkthrough\",\"task\",\"other\"],\"description\":\"Type of artifact: 'implementation_plan', 'walkthrough', 'task', or 'other'.\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"Summary\",\"ArtifactType\"],\"description\":\"Metadata for the artifact, required when IsArtifact is true.\"},\"waitForPreviousTools\":{\"type\":\"boolean\",\"description\":\"If true, wait for all previous tool calls from this turn to complete before executing (sequential). If false or omitted, execute this tool immediately (parallel with other tools).\"}},\"additionalProperties\":false,\"type\":\"object\",\"required\":[\"TargetFile\",\"Overwrite\",\"CodeContent\",\"EmptyFile\",\"Description\",\"Complexity\",\"IsArtifact\"]}",
              "name": "write_to_file"
            }
          ],
          usage: {
            apiProvider: "API_PROVIDER_ANTHROPIC_VERTEX",
            model: "MODEL_PLACEHOLDER_M12",
            responseHeader: {
              sessionID: "-3750763034362895579"
            }
          },
        },
        executionId: executionId,
        plannerConfig: {
          agenticModeConfig: {
            disableArtifactReminders: false,
            injectArtifactReminderThresholdMap: {
              "implementation_plan.md": 25,
              "task.md": 10
            }
          },
          conversational: {
            agenticMode: true,
            plannerMode: "CONVERSATIONAL_PLANNER_MODE_DEFAULT"
          },
          ephemeralMessagesConfig: {
            browserEphemeralOptions: [
              "BROWSER_EPHEMERAL_OPTION_SCREENSHOT",
              "BROWSER_EPHEMERAL_OPTION_DOM"
            ],
            enabled: true,
            persistenceLevel: "EPHEMERAL_MESSAGE_PERSISTENCE_LEVEL_LATEST_ONLY"
          },
          knowledgeConfig: {
            enabled: false,
            maxArtifactsPerKi: 20,
            maxContextTokens: 200000,
            maxInvocations: 20,
            maxKnowledgeItems: 20,
            maxSummaryLength: 1000,
            maxTitleLength: 100,
            minTurnsBetweenKnowledgeGeneration: 10000,
            model: "MODEL_PLACEHOLDER_M18"
          },
          maxOutputTokens: 16384,
          modelName: modelName,
          noToolExplanation: true,
          noToolSummary: true,
          noWaitForPreviousTools: false,
          planModel: "MODEL_PLACEHOLDER_M12",
          requestedModel: {
            model: "MODEL_PLACEHOLDER_M12"
          },
          retryConfig: {
            apiRetry: {
              exponentialMultiplier: 2,
              includeErrorFeedback: true,
              initialSleepDurationMs: 5000,
              maxRetries: 2
            },
            modelOutputRetry: {
              forceToolName: "notify_user",
              maxRetries: 4
            }
          },
          "toolConfig": {
            "addAnnotation": {
              "enabled": false,
              "enabledForConversationalMixin": false
            },
            "antigravityBrowser": {
              "browserJsExecutionPolicy": "BROWSER_JS_EXECUTION_POLICY_ALWAYS_ASK",
              "browserStateDiffingConfig": {
                "captureAgentActionDiffs": true,
                "includeDomTreeInDiffs": false
              },
              "browserSubagent": {
                "browserSubagentModel": "MODEL_PLACEHOLDER_M18",
                "contextConfig": {
                  "maxChars": 10000,
                  "type": "CONTEXT_TYPE_WITH_MARKDOWN_TRAJECTORY_SUMMARY"
                },
                "disableOnboarding": false,
                "domExtractionConfig": {
                  "includeCoordinates": true
                },
                "mode": "BROWSER_SUBAGENT_MODE_SUBAGENT_ONLY",
                "subagentReminderMode": {
                  "verifyScreenshots": {

                  }
                },
                "suggestedMaxToolCalls": 40,
                "useDetailedConverter": true
              },
              "captureBrowserScreenshot": {
                "enableSaving": true
              },
              "clickBrowserPixel": {
                "clickFeedback": {
                  "alpha": 255,
                  "blue": 0,
                  "displayColor": "red",
                  "enabled": true,
                  "feedbackType": "FEEDBACK_TYPE_MOUSE_POINTER",
                  "green": 0,
                  "radius": 25,
                  "red": 255
                }
              },
              "disableOpenUrl": false,
              "domExtractionConfig": {
                "includeCoordinates": true
              },
              "enabled": true,
              "toolSetMode": "BROWSER_TOOL_SET_MODE_ALL_INPUT_PIXEL_OUTPUT",
              "variableWaitTool": true
            },
            "code": {
              "allowEditGitignore": false,
              "applyEdits": true,
              "autoFixLintsConfig": {
                "enabled": true
              },
              "classifyEdit": false,
              "disableExtensions": [
                ".ipynb"
              ],
              "enterpriseConfig": {
                "enforceWorkspaceValidation": true
              },
              "onlyShowIncrementalDiffZone": false,
              "provideImportance": false,
              "replaceContentToolConfig": {
                "allowPartialReplacementSuccess": true,
                "disableAllowMultiple": false,
                "fastApplyFallbackConfig": {
                  "contentEditRadiusLines": 5,
                  "contentViewRadiusLines": 200,
                  "enabled": true,
                  "fastApplyModel": "MODEL_GOOGLE_GEMINI_2_5_FLASH",
                  "promptUnchangedThreshold": 5
                },
                "maxFuzzyEditDistanceFraction": 0.001,
                "showTriggeredMemories": true,
                "toolVariant": "REPLACE_TOOL_VARIANT_SINGLE_MULTI",
                "useLineRange": true
              },
              "skipAwaitLintErrors": false,
              "useReplaceContentProposeCode": false
            },
            "commandStatus": {
              "maxOutputCharacters": 8192,
              "maxWaitDurationSeconds": 300,
              "minOutputCharacters": 1024,
              "outputStabilizationDurationSeconds": 5,
              "useDelta": true
            },
            "find": {
              "fdPath": "d:/Antigravity/resources/app/extensions/antigravity/bin/fd.exe",
              "maxFindResults": 50,
              "useCodeSearch": false
            },
            "findAllReferences": {
              "enabled": false
            },
            "finish": {

            },
            "grep": {
              "enterpriseConfig": {
                "enforceWorkspaceValidation": true
              },
              "includeCciInResult": false,
              "maxGrepResults": 50,
              "useCodeSearch": false
            },
            "intent": {
              "intentModel": "MODEL_GOOGLE_GEMINI_2_5_FLASH",
              "maxContextTokens": 40000
            },
            "internalSearch": {
              "maxContentLength": 5000,
              "maxResults": 10
            },
            "listDir": {
              "enterpriseConfig": {
                "enforceWorkspaceValidation": true
              }
            },
            "mcp": {
              "forceDisable": false,
              "maxOutputBytes": 4096
            },
            "mquery": {
              "enableSearchInFileTool": true,
              "enterpriseConfig": {
                "enforceWorkspaceValidation": true
              },
              "forceDisable": true,
              "mQueryConfig": {
                "maxTargetFiles": 1000,
                "maxTokensPerSubrange": "3000",
                "minTokenSpaceForContext": 1000,
                "numParserWorkers": "4",
                "numWorkersPerDistributedScorer": "80",
                "topCciCount": 50
              },
              "mQueryModel": "MODEL_GOOGLE_GEMINI_2_5_FLASH_LITE",
              "maxLinesPerSnippet": 25,
              "maxTokensPerMQuery": 4096,
              "numItemsFullSource": 5
            },
            "notifyUser": {
              "artifactReviewMode": "ARTIFACT_REVIEW_MODE_ALWAYS"
            },
            "runCommand": {
              "autoCommandConfig": {
                "autoExecutionPolicy": "CASCADE_COMMANDS_AUTO_EXECUTION_OFF",
                "systemAllowlist": [
                  "echo",
                  "ls"
                ],
                "systemDenylist": [
                  "git",
                  "rm",
                  "pkill",
                  "kubectl delete",
                  "terraform",
                  "kill",
                  "del",
                  "rmdir",
                  "psql",
                  "gsutil",
                  "aws",
                  "gcloud",
                  "az",
                  "rmdir"
                ]
              },
              "enableIdeTerminalExecution": true,
              "enterpriseConfig": {
                "enforceWorkspaceValidation": true
              },
              "forbidSearchCommands": false,
              "forceDisable": false,
              "maxCharsCommandStdout": 8192,
              "shellName": "powershell",
              "shellPath": "C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\powershell.exe"
            },
            "runExtensionCode": {
              "enabled": false,
              "only": false
            },
            "searchWeb": {
              "forceDisable": false,
              "thirdPartyConfig": {
                "provider": "THIRD_PARTY_WEB_SEARCH_PROVIDER_GEMINI"
              }
            },
            "suggestedResponse": {
              "forceDisable": true
            },
            "taskBoundary": {
              "minimumPredictedTaskSize": 3,
              "noActiveTaskSoftReminderToolThreshold": 2,
              "noActiveTaskStrictReminderToolThreshold": 5,
              "targetStatusUpdateFrequency": 5
            },
            "trajectorySearch": {
              "conversationsEnabled": true,
              "forceDisable": true,
              "maxScoredChunks": 50,
              "userActivitiesEnabled": false
            },
            "viewCodeItem": {
              "enterpriseConfig": {
                "enforceWorkspaceValidation": true
              },
              "maxBytesPerItem": 8192,
              "maxNumItems": 5
            },
            "viewFile": {
              "allowViewGitignore": false,
              "enterpriseConfig": {
                "enforceWorkspaceValidation": true
              },
              "includeLineNumbers": true,
              "maxBytesPerOutlineItem": 512,
              "maxLinesPerView": 800,
              "maxTotalOutlineBytes": 8192,
              "showFullFileBytes": 8192,
              "showTriggeredMemories": true,
              "splitOutlineTool": true
            }
          },
          truncationThresholdTokens: 160000
        },
        stepIndices: [3]
      }
    }
  ]
}
function generateSteps(executionId, trajectoryId, cascadeId, num) {
  const qaPair = getRandomQAPair(num);
  return [
    {
      "metadata": {
        "createdAt": generateCreatedAt(),
        "executionId": executionId,
        "internalMetadata": {
          "statusTransitions": [
            {
              "timestamp": "2026-02-14T02:26:03.208153600Z",
              "updatedStatus": "CORTEX_STEP_STATUS_DONE"
            }
          ]
        },
        "source": "CORTEX_STEP_SOURCE_USER_EXPLICIT"
      },
      "status": "CORTEX_STEP_STATUS_DONE",
      "type": "CORTEX_STEP_TYPE_USER_INPUT",
      "userInput": {
        "activeUserState": {

        },
        "clientType": "CHAT_CLIENT_REQUEST_STREAM_CLIENT_TYPE_IDE",
        "items": [
          {
            "text": qaPair.question
          }
        ],
        "userConfig": {
          "conversationHistoryConfig": {
            "enabled": true
          },
          "plannerConfig": {
            "conversational": {
              "agenticMode": true,
              "plannerMode": "CONVERSATIONAL_PLANNER_MODE_DEFAULT"
            },
            "ephemeralMessagesConfig": {
              "enabled": true
            },
            "knowledgeConfig": {
              "enabled": true
            },
            "requestedModel": {
              "model": "MODEL_PLACEHOLDER_M12"
            },
            "toolConfig": {
              "notifyUser": {
                "artifactReviewMode": "ARTIFACT_REVIEW_MODE_ALWAYS"
              },
              "runCommand": {
                "autoCommandConfig": {
                  "autoExecutionPolicy": "CASCADE_COMMANDS_AUTO_EXECUTION_OFF"
                }
              }
            }
          }
        },
        "userResponse": qaPair.question
      }
    },
    {
      conversationHistory: {
        "content": "# Conversation History\nHere are the conversation IDs, titles, and summaries of your most recent 20 conversations, in reverse chronological order:\n\n<conversation_summaries>\n## Conversation 69e85e79-03c8-4ddb-ba18-62944ea20157: AI Assistant Introduction\n- Created: 2026-01-31T02:21:25Z\n- Last modified: 2026-01-31T02:21:40Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation 90d74392-c12d-47d2-99a3-9a1f143123e2: AI Assistant Introduction\n- Created: 2026-01-11T00:38:07Z\n- Last modified: 2026-01-11T00:38:16Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation b2558016-6bb8-41a1-b7ba-11ccb5a006d0: AI Assistant Introduction\n- Created: 2026-01-10T19:48:03Z\n- Last modified: 2026-01-10T19:48:15Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation 1c4edcda-8176-4a39-aa01-d76fb9a6a9c0: AI Assistant Introduction\n- Created: 2026-01-08T03:35:08Z\n- Last modified: 2026-01-08T03:35:25Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation d3408956-88c4-4538-b1d8-5ee916863826: AI Assistant Introduction\n- Created: 2025-12-20T02:59:33Z\n- Last modified: 2025-12-20T03:06:52Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation 2efe3f19-1615-432c-9ec0-961923d2620a: AI Identity and Search Capabilities\n- Created: 2025-12-04T11:56:17Z\n- Last modified: 2025-12-04T11:57:14Z\n\n### USER Objective:\nAI Identity and Search Capabilities\nThe user's main objective is to understand the AI assistant's identity and its capabilities, specifically inquiring about its ability to perform web searches. Their goal is to gain clarity on the AI's functions to effectively interact with it.\n\n## Conversation 30181ddc-7eb5-43de-8103-f8bc41f69f91: Generating Sunset Landscape\n- Created: 2025-11-29T07:41:49Z\n- Last modified: 2025-11-29T07:43:13Z\n\n### USER Objective:\nGenerating Sunset Landscape\nThe user's main objective is to generate a 4K image of a sunset beach landscape. Their goal is to have a visually appealing and serene image with specific elements like a golden sunset, gentle waves, palm trees, and vibrant colors, all in ultra-high definition.\n\n## Conversation d886c2e9-217f-4de3-8c5e-9a7737ee6a94: Generating Sunset Landscape\n- Created: 2025-11-29T07:35:06Z\n- Last modified: 2025-11-29T07:35:40Z\n\n### USER Objective:\nGenerating Sunset Landscape\nThe user's main objective is to generate a 4K image of a sunset beach landscape. Their goal is to have a visually appealing and serene image with specific elements like a golden sunset, gentle waves, palm trees, and vibrant colors, all in ultra-high definition.\n\n## Conversation de3e95f4-b183-46a9-904b-9d9518d4fc04: Generate Sunset Landscape\n- Created: 2025-11-28T04:05:49Z\n- Last modified: 2025-11-28T04:06:27Z\n\n### USER Objective:\nGenerate Sunset Landscape\nThe user's main objective is to generate an image of a sunset landscape.\n\n## Conversation 54e3c329-3e94-489f-912c-fdd69fbb1632: Generating Landscape Image\n- Created: 2025-11-27T03:55:55Z\n- Last modified: 2025-11-27T03:56:12Z\n\n### USER Objective:\nGenerating Landscape Image\nThe user wants to generate a landscape image. They have provided a prompt for the image generation.\n\n## Conversation 26410527-18a2-43b0-8ed3-2951004b2aee: Generating Landscape Image\n- Created: 2025-11-27T03:54:21Z\n- Last modified: 2025-11-27T03:55:21Z\n\n### USER Objective:\nGenerating Landscape Image\nThe user's objective is to generate an image of a landscape. They have provided a prompt for the image generation.\n\n## Conversation 5ca07696-2d82-4ca5-95b4-ebafdac519e4: AI Assistant Introduction\n- Created: 2025-11-27T03:52:03Z\n- Last modified: 2025-11-27T03:52:11Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant.\n\n## Conversation c2904dd6-e8cd-4513-9d69-7f7db49ba2e5: AI Assistant Introduction\n- Created: 2025-11-27T03:50:36Z\n- Last modified: 2025-11-27T03:50:47Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant.\n\n## Conversation a9730f9b-5568-4ad5-b0f7-5306e9478bde: AI Assistant Introduction\n- Created: 2025-11-26T14:30:11Z\n- Last modified: 2025-11-26T14:30:24Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant.\n\n## Conversation 0decac4b-8bca-47ee-b438-a3a30e7d6f77: AI Assistant Introduction\n- Created: 2025-11-26T14:29:34Z\n- Last modified: 2025-11-26T14:29:48Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant.\n\n## Conversation f9211ab8-4be1-4adf-a7ac-f0b0486ba91a: Generate Seaside Landscape\n- Created: 2025-11-21T02:04:14Z\n- Last modified: 2025-11-21T02:29:49Z\n\n### USER Objective:\nGenerate Seaside Landscape\nThe user's main objective is to generate an image of a seaside landscape. Their goal is to have a visually appealing and serene image of a beach scene.\n\n## Conversation 8a7ffc48-3607-4334-9c76-658af8837e20: AI Assistant Introduction\n- Created: 2025-11-20T14:53:13Z\n- Last modified: 2025-11-20T14:54:37Z\n\n### USER Objective:\nAI Assistant Introduction\nThe user's main objective is to understand the identity and capabilities of the AI assistant.\n\n## Conversation 3581b5db-ef86-438a-a2ef-1ff6d0283617: Simultaneous Tool Call Demonstration\n- Created: 2025-11-20T10:00:01Z\n- Last modified: 2025-11-20T10:00:41Z\n\n### USER Objective:\nSimultaneous Tool Call Demonstration\nThe user's main objective is to demonstrate the AI assistant's ability to call two tools simultaneously, as requested in their prompt.\n\n## Conversation 5ab46367-98c9-4c29-9a91-445c45fef5e2: Image Content Description\n- Created: 2025-11-20T08:28:43Z\n- Last modified: 2025-11-20T08:29:13Z\n\n### USER Objective:\nImage Content Description\nThe user's main objective is to understand the content of the two uploaded images. The user expects a detailed description of what is depicted in each image.Image Content Description\nThe user's main objective is to obtain a detailed description of the content present in the two uploaded images.\n\n## Conversation b751c9ed-a844-4b6b-a1eb-817ce1c53880: Image Content Description\n- Created: 2025-11-20T08:24:11Z\n- Last modified: 2025-11-20T08:24:28Z\n\n### USER Objective:\nImage Content Description\nThe user's main objective is to understand the content of the uploaded image.\n\n</conversation_summaries>"
      },
      "metadata": {
        "completedAt": generateCreatedAt(),
        "createdAt": generateCreatedAt(),
        "executionId": executionId,
        "internalMetadata": {
          "statusTransitions": [
            {
              "timestamp": generateCreatedAt(),
              "updatedStatus": "CORTEX_STEP_STATUS_PENDING"
            },
            {
              "timestamp": generateCreatedAt(),
              "updatedStatus": "CORTEX_STEP_STATUS_RUNNING"
            },
            {
              "timestamp": generateCreatedAt(),
              "updatedStatus": "CORTEX_STEP_STATUS_DONE"
            }
          ]
        },
        "source": "CORTEX_STEP_SOURCE_SYSTEM",
        status: "CORTEX_STEP_STATUS_DONE",
        type: "CORTEX_STEP_TYPE_CONVERSATION_HISTORY"
      },
    },
    {
      "ephemeralMessage": {
        "content": "The following is an <EPHEMERAL_MESSAGE> not actually sent by the user. It is provided by the system as a set of reminders and general important information to pay attention to. Do NOT respond to this message, just act accordingly.\n\n<EPHEMERAL_MESSAGE>\n<artifact_reminder>\nYou have not yet created any artifacts. Please follow the artifact guidelines and create them as needed based on the task.\nCRITICAL REMINDER: remember that user-facing artifacts should be AS CONCISE AS POSSIBLE. Keep this in mind when editing artifacts.\n</artifact_reminder>\n<no_active_task_reminder>\nYou are currently not in a task because: a task boundary has never been set yet in this conversation.\nIf there is no obvious task from the user or if you are just conversing, then it is acceptable to not have a task set. If you are just handling simple one-off requests, such as explaining a single file, or making one or two ad-hoc code edit requests, or making an obvious refactoring request such as renaming or moving code into a helper function, it is also acceptable to not have a task set.\nOtherwise, you should use the task_boundary tool to set a task if there is one evident.\nRemember that task boundaries should correspond to the artifact task.md, if you have not created the artifact task.md, you should do that first before setting the task_boundary. Remember that task names should be granular and correspond to top-level checklist items, not the entire user request as one task name. If you decide to use the task boundary tool, you must do so concurrently with other tools.\nSince you are NOT in an active task section, DO NOT call the `notify_user` tool unless you are requesting review of files.\n</no_active_task_reminder>\n</EPHEMERAL_MESSAGE>",
        "triggeredHeuristics": [
          "artifact_reminder",
          "no_active_task_reminder"
        ]
      },
      "metadata": {
        "completedAt": generateCreatedAt(),
        "createdAt": generateCreatedAt(),
        "executionId": executionId,
        "internalMetadata": {
          "statusTransitions": [
            {
              "timestamp": generateCreatedAt(),
              "updatedStatus": "CORTEX_STEP_STATUS_PENDING"
            },
            {
              "timestamp": generateCreatedAt(),
              "updatedStatus": "CORTEX_STEP_STATUS_RUNNING"
            },
            {
              "timestamp": generateCreatedAt(),
              "updatedStatus": "CORTEX_STEP_STATUS_DONE"
            }
          ]
        },
        "source": "CORTEX_STEP_SOURCE_SYSTEM"
      },
      "status": "CORTEX_STEP_STATUS_DONE",
      "type": "CORTEX_STEP_TYPE_EPHEMERAL_MESSAGE"
    },
    {
      "metadata": {
        "completedAt": generateCreatedAt(),
        "createdAt": generateCreatedAt(),
        "executionId": executionId,
        "finishedGeneratingAt": generateCreatedAt(),
        "generatorModel": "MODEL_PLACEHOLDER_M12",
        "internalMetadata": {
          "statusTransitions": [
            {
              "timestamp": generateCreatedAt(),
              "updatedStatus": "CORTEX_STEP_STATUS_GENERATING"
            },
            {
              "timestamp": generateCreatedAt(),
              "updatedStatus": "CORTEX_STEP_STATUS_DONE"
            }
          ]
        },
        "requestedModel": {
          "model": "MODEL_PLACEHOLDER_M12"
        },
        "source": "CORTEX_STEP_SOURCE_MODEL",
        "sourceTrajectoryStepInfo": {
          "cascadeId": cascadeId,
          "stepIndex": 3,
          "trajectoryId": trajectoryId
        },
        "stepGenerationVersion": 1,
        "viewableAt": generateCreatedAt()
      },
      "plannerResponse": {
        "messageId": `bot-${randomUUID()}`,
        "modifiedResponse": qaPair.answer,
        "response": qaPair.answer
      },
      "status": "CORTEX_STEP_STATUS_DONE",
      "type": "CORTEX_STEP_TYPE_PLANNER_RESPONSE"
    },
    {
      "checkpoint": {
        "intentOnly": true
      },
      "metadata": {
        "createdAt": generateCreatedAt(),
        "executionId": executionId,
        "internalMetadata": {
          "statusTransitions": [
            {
              "timestamp": generateCreatedAt(),
              "updatedStatus": "CORTEX_STEP_STATUS_PENDING"
            },
            {
              "timestamp": generateCreatedAt(),
              "updatedStatus": "CORTEX_STEP_STATUS_RUNNING"
            }
          ]
        },
        "source": "CORTEX_STEP_SOURCE_SYSTEM"
      },
      "status": "CORTEX_STEP_STATUS_RUNNING",
      "type": "CORTEX_STEP_TYPE_CHECKPOINT"
    },
  ]
}

function generateTrajectorybody(num, trajectoryId,executionId,cascadeId, modelName, token) {
  //let cascadeId = randomUUID();
  //let executionId = randomUUID();
  return {
    trajectory: {
      cascadeId: cascadeId,
      executorMetadatas: generateExecutorMetadatas(),
      generatorMetadata: generateGeneratorMetadata(executionId, num, modelName),
      metadata: {
        createdAt: generateCreatedAt(),
        initializationStateId: randomUUID()
      },
      source: "CORTEX_TRAJECTORY_SOURCE_CASCADE_CLIENT",
      steps: generateSteps(executionId, trajectoryId, cascadeId, num),
      trajectoryId: trajectoryId,
      trajectoryType: "CORTEX_TRAJECTORY_TYPE_CASCADE"
    },
    metadata: generateMetadata(token)
  }
}
export {
  generateTrajectorybody
}