add error_code_mapping and extracted_information_schema to task v2 (#1950)

alembic/versions/2025_03_18_1850-c6c0eee7f88d_add_error_code_mapping_and_extracted_.py

@@ -0,0 +1,33 @@
+"""add error_code_mapping and extracted_information_schema to task v2
+
+Revision ID: c6c0eee7f88d
+Revises: 268dcc995513
+Create Date: 2025-03-18 18:50:28.930836+00:00
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "c6c0eee7f88d"
+down_revision: Union[str, None] = "268dcc995513"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column("observer_cruises", sa.Column("extracted_information_schema", sa.JSON(), nullable=True))
+    op.add_column("observer_cruises", sa.Column("error_code_mapping", sa.JSON(), nullable=True))
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column("observer_cruises", "error_code_mapping")
+    op.drop_column("observer_cruises", "extracted_information_schema")
+    # ### end Alembic commands ###

skyvern/forge/prompts/skyvern/task_v2_summary.j2

@@ -5,13 +5,15 @@ You want to present the response in a clear way so that user can clearly underst
 Reply in JSON format with the following keys:
 {
     "description": str, // Summarize what has been achieved and describe the information extracted related to the user goal if any. Be precise and concise.
-    "output": json, // Structured data related to the user goal if any.
+    "output": json, // Structured data related to the user goal if any.{% if extracted_information_schema %} Use the data schema for the output field.{% endif %}
 }
 
 User goal:
 ```
 {{ user_goal }}
-```
+```{% if extracted_information_schema %}
+
+The ideal schema for the "output" field: {{ extracted_information_schema }}{% endif %}
 
 Task history (the earliest task is the first in the list and the latest is the last in the list):
 ```

skyvern/forge/sdk/db/models.py

@@ -588,6 +588,8 @@ class TaskV2Model(Base):
     totp_verification_url = Column(String, nullable=True)
     totp_identifier = Column(String, nullable=True)
     proxy_location = Column(String, nullable=True)
+    extracted_information_schema = Column(JSON, nullable=True)
+    error_code_mapping = Column(JSON, nullable=True)
 
     created_at = Column(DateTime, default=datetime.datetime.utcnow, nullable=False)
     modified_at = Column(DateTime, default=datetime.datetime.utcnow, onupdate=datetime.datetime.utcnow, nullable=False)

skyvern/forge/sdk/schemas/task_v2.py

@@ -41,6 +41,8 @@ class TaskV2(BaseModel):
     totp_identifier: str | None = None
     proxy_location: ProxyLocation | None = None
     webhook_callback_url: str | None = None
+    extracted_information_schema: dict | list | str | None = None
+    error_code_mapping: dict | None = None
 
     created_at: datetime
     modified_at: datetime
@@ -117,6 +119,8 @@ class TaskV2Request(BaseModel):
     totp_identifier: str | None = None
     proxy_location: ProxyLocation | None = None
     publish_workflow: bool = False
+    extracted_information_schema: dict | list | str | None = None
+    error_code_mapping: dict[str, str] | None = None
 
     @field_validator("url", "webhook_callback_url", "totp_verification_url")
     @classmethod

skyvern/forge/sdk/services/task_v2_service.py

@@ -1395,6 +1395,7 @@ async def _summarize_task_v2(
         "task_v2_summary",
         user_goal=task_v2.prompt,
         task_history=task_history,
+        extracted_information_schema=task_v2.extracted_information_schema,
         local_datetime=datetime.now(context.tz_info).isoformat(),
     )
     task_v2_summary_resp = await app.LLM_API_HANDLER(