Workflow Fixes

skyvern/config.py

@@ -43,7 +43,7 @@ class Settings(BaseSettings):
 
     # S3 bucket settings
     AWS_REGION: str = "us-east-1"
-    AWS_S3_BUCKET_DOWNLOADS: str = "skyvern-downloads"
+    AWS_S3_BUCKET_UPLOADS: str = "skyvern-uploads"
 
     SKYVERN_TELEMETRY: bool = True
     ANALYTICS_ID: str = "anonymous"
@@ -54,6 +54,9 @@ class Settings(BaseSettings):
     BROWSER_WIDTH: int = 1920
     BROWSER_HEIGHT: int = 1080
 
+    # Workflow constant parameters
+    WORKFLOW_DOWNLOAD_DIRECTORY_PARAMETER_KEY: str = "SKYVERN_DOWNLOAD_DIRECTORY"
+
     #####################
     # LLM Configuration #
     #####################

skyvern/forge/prompts/skyvern/extract-action.j2

@@ -16,10 +16,11 @@ Reply in JSON format with the following keys:
     [{
         "reasoning": str, // The reasoning behind the action. Be specific, referencing any user information and their fields and element ids in your reasoning. Mention why you chose the action type, and why you chose the element id. Keep the reasoning short and to the point.
         "confidence_float": float, // The confidence of the action. Pick a number between 0.0 and 1.0. 0.0 means no confidence, 1.0 means full confidence
-        "action_type": str, // It's a string enum: "CLICK", "INPUT_TEXT", "UPLOAD_FILE", "SELECT_OPTION", "WAIT", "SOLVE_CAPTCHA", "COMPLETE", "TERMINATE". "CLICK" is an element you'd like to click. "INPUT_TEXT" is an element you'd like to input text into. "UPLOAD_FILE" is an element you'd like to upload a file into. "SELECT_OPTION" is an element you'd like to select an option from. "WAIT" action should be used if there are no actions to take and there is some indication on screen that waiting could yield more actions. "WAIT" should not be used if there are actions to take. "SOLVE_CAPTCHA" should be used if there's a captcha to solve on the screen. "COMPLETE" is used when the user goal has been achieved AND if there's any data extraction goal, you should be able to get data from the page. If there is any other action to take, do not add "COMPLETE" type at all. "TERMINATE" is used to terminate the whole task with a failure when it doesn't seem like the user goal can be achieved. Do not use "TERMINATE" if waiting could lead the user towards the goal. Only return "TERMINATE" if you are on a page where the user goal cannot be achieved. All other actions are ignored when "TERMINATE" is returned.
+        "action_type": str, // It's a string enum: "CLICK", "INPUT_TEXT", "UPLOAD_FILE", "DOWNLOAD_FILE", "SELECT_OPTION", "WAIT", "SOLVE_CAPTCHA", "COMPLETE", "TERMINATE". "CLICK" is an element you'd like to click. "INPUT_TEXT" is an element you'd like to input text into. "UPLOAD_FILE" is an element you'd like to upload a file into. "DOWNLOAD_FILE" is an element you'd like to download a file from, and the file will be saved with the name provided in the "file_name" field. You can download multiple files in one action by returning multiple "DOWNLOAD_FILE" actions in one step. The "file_name" field should be unique for each file download action. Do not download the same file multiple times, check action history to see if the file has already been downloaded. "SELECT_OPTION" is an element you'd like to select an option from. "WAIT" action should be used if there are no actions to take and there is some indication on screen that waiting could yield more actions. "WAIT" should not be used if there are actions to take. "SOLVE_CAPTCHA" should be used if there's a captcha to solve on the screen. "COMPLETE" is used when the user goal has been achieved AND if there's any data extraction goal, you should be able to get data from the page. "TERMINATE" is used to terminate the whole task with a failure when it doesn't seem like the user goal can be achieved. Do not use "TERMINATE" if waiting could lead the user towards the goal. Only return "TERMINATE" if you are on a page where the user goal cannot be achieved. All other actions are ignored when "TERMINATE" is returned.
         "id": int, // The id of the element to take action on. The id has to be one from the elements list
         "text": str, // Text for INPUT_TEXT action only
         "file_url": str, // The url of the file to upload if applicable. This field must be present for UPLOAD_FILE but can also be present for CLICK only if the click is to upload the file. It should be null otherwise.
+        "file_name": str, // The name of the file to save the downloaded file as. This field must be present for DOWNLOAD_FILE only. It should be null otherwise.
         "option": {  // The option to select for SELECT_OPTION action only. null if not SELECT_OPTION action
             "label": str, // the label of the option if any. MAKE SURE YOU USE THIS LABEL TO SELECT THE OPTION. DO NOT PUT ANYTHING OTHER THAN A VALID OPTION LABEL HERE
             "index": int, // the id corresponding to the optionIndex under the the select element.

skyvern/forge/sdk/api/files.py

@@ -1,11 +1,13 @@
 import os
 import tempfile
 import zipfile
+from pathlib import Path
 from urllib.parse import urlparse
 
 import aiohttp
 import structlog
 
+from skyvern.constants import SKYVERN_DIR
 from skyvern.exceptions import DownloadFileMaxSizeExceeded
 
 LOG = structlog.get_logger()
@@ -62,3 +64,7 @@ def zip_files(files_path: str, zip_file_path: str) -> str:
                 zipf.write(file_path, arcname)
 
     return zip_file_path
+
+
+def get_path_for_workflow_download_directory(workflow_run_id: str) -> Path:
+    return Path(f"{SKYVERN_DIR}/downloads/{workflow_run_id}/")

skyvern/forge/sdk/routes/agent_protocol.py

@@ -469,7 +469,10 @@ async def get_workflow_run(
     analytics.capture("skyvern-oss-agent-workflow-run-get")
     request["agent"]
     return await app.WORKFLOW_SERVICE.build_workflow_run_status_response(
-        workflow_id=workflow_id, workflow_run_id=workflow_run_id, organization_id=current_org.organization_id
+        workflow_id=workflow_id,
+        workflow_run_id=workflow_run_id,
+        last_block_result=None,
+        organization_id=current_org.organization_id,
     )