​
Overview

The update_event function allows you to modify an existing event’s information while it’s still active. This is useful for tracking progress, adding details discovered during execution, or updating costs.

​
Syntax

lai.update_event(
    event_id: Optional[str] = None,
    description: Optional[str] = None,
    result: Optional[str] = None,
    cost_added: Optional[float] = None,
    model: Optional[str] = None,
    screenshots: Optional[List[str]] = None
) -> None

​
Parameters

​
event_id
string
The ID of the event to update. If not provided, updates the most recent event in the current step.
​
description
string
Updated description of the event.
​
result
string
Updated result or outcome of the event.
​
cost_added
float
Updated cost for the event.
​
model
string
Updated model or service identifier.
​
screenshots
List[str]
Updated list of screenshots. Each screenshot should be provided as a file path (which will be read and uploaded) or as base64-encoded image data.

​
Returns

This function returns None.

​
Examples

​
Progress Updates

import lucidicai as lai

lai.init(session_name="Progress Tracking")

lai.create_step(state="Data processing", action="Analyze dataset")

# Create initial event
event_id = lai.create_event(
    description="Starting data analysis",
    model="analyzer-v1"
)

# Update as processing progresses
for i in range(10):
    process_batch(i)
    
    lai.update_event(
        event_id=event_id,
        result=f"Processed {i+1}/10 batches"
    )

# Final update
lai.update_event(
    event_id=event_id,
    result="All batches processed successfully",
    cost_added=0.05
)

lai.end_step()

​
Adding Details During Execution

import lucidicai as lai

lai.init(session_name="Dynamic Updates")

lai.create_step(state="API integration", action="Fetch and process data")

# Create event
event_id = lai.create_event(
    description="Calling external API",
    model="external-api-v2"
)

# Make API call
response = call_external_api()

# Update with response info
lai.update_event(
    event_id=event_id,
    result=f"Received {len(response.data)} records",
    cost_added=response.billing_info.cost
)

# Process data
processed = process_response(response)

# Update again with processing results
lai.update_event(
    event_id=event_id,
    result=f"Processed {len(processed)} valid records from {len(response.data)} total"
)

lai.end_step()

​
Screenshot Updates

import lucidicai as lai

lai.init(session_name="Visual Processing")

lai.create_step(state="UI automation", action="Navigate application")

# Create event for UI interaction
event_id = lai.create_event(
    description="Navigating through application flow"
)

# Take initial screenshot
initial_screenshot = capture_screenshot()
lai.update_event(
    event_id=event_id,
    screenshots=[encode_base64(initial_screenshot)]
)

# Navigate and update
navigate_to_page("settings")
settings_screenshot = capture_screenshot()

lai.update_event(
    event_id=event_id,
    result="Navigated to settings page",
    screenshots=[
        encode_base64(initial_screenshot),
        encode_base64(settings_screenshot)
    ]
)

lai.end_step()

​
Cost Accumulation

import lucidicai as lai

lai.init(session_name="Cost Tracking")

lai.create_step(state="Multi-service operation", action="Use various APIs")

# Track cumulative costs
event_id = lai.create_event(
    description="Multi-service workflow",
    cost_added=0.0
)

total_cost = 0.0

# Service 1
cost1 = use_translation_service()
total_cost += cost1
lai.update_event(event_id=event_id, cost_added=total_cost)

# Service 2
cost2 = use_sentiment_analysis()
total_cost += cost2
lai.update_event(event_id=event_id, cost_added=total_cost)

# Service 3
cost3 = use_summarization()
total_cost += cost3
lai.update_event(
    event_id=event_id,
    cost_added=total_cost,
    result=f"Completed all services. Total cost: ${total_cost:.3f}"
)

lai.end_step()

​
Auto-Update Latest Event

import lucidicai as lai

lai.init(session_name="Quick Updates")

lai.create_step(state="Processing", action="Execute tasks")

# Create events
lai.create_event(description="Task 1")
lai.create_event(description="Task 2")
lai.create_event(description="Task 3")  # This is the latest

# Update the latest event (Task 3)
lai.update_event(
    result="Task 3 completed with warnings",
    model="task-processor-v3"
)

lai.end_step()

​
Notes

  • Can only update active (not ended) events
  • If event_id is not provided, updates the most recent event
  • Updates are incremental - only provided fields are updated
  • Multiple updates can be made to the same event
  • Screenshot updates replace the entire screenshot list

​
Error Handling

from lucidicai.errors import InvalidOperationError

try:
    lai.update_event(
        event_id="non-existent-id",
        result="This will fail"
    )
except InvalidOperationError:
    print("Event not found or already ended")

# Updating without active events
try:
    lai.update_event(result="No events to update")
except Exception:
    print("No active events in current step")

​
Best Practices

  1. Incremental Updates: Update events as information becomes available
  2. Cost Tracking: Keep costs updated for accurate billing
  3. Progress Indication: Use result field to show progress
  4. Error Context: Update with error information if failures occur
  5. Meaningful Updates: Only update when there’s new information

​
See Also