Timestamp when the event was created.
ISO 8601 formatted date-time string indicating when this event was emitted by the system. This timestamp is crucial for event ordering, performance analysis, and debugging the agent workflow execution timeline.
Format: "YYYY-MM-DDTHH:mm:ss.sssZ" (e.g., "2024-01-15T14:30:45.123Z")
Array of API endpoint groups organized by Prisma schema structure.
Each group represents a logical partition of the API based on database schema organization. Groups are mutually exclusive (no entity appears in multiple groups) and collectively exhaustive (all entities are covered). The array typically contains 2-20 groups depending on the project scale and schema complexity.
These groups will be used by subsequent Interface agent invocations to generate endpoints for specific subsets of the application.
A unique identifier for the event.
Function calling trial statistics for the operation.
Records the complete trial history of function calling attempts, tracking total executions, successful completions, consent requests, validation failures, and invalid JSON responses. These metrics reveal the reliability and quality of AI agent autonomous operation with tool usage.
Trial statistics are critical for identifying operations where agents struggle with tool interfaces, generate invalid outputs, or require multiple correction attempts through self-healing spiral loops. High failure rates indicate opportunities for system prompt optimization or tool interface improvements.
Iteration number of the requirements analysis this grouping reflects.
Indicates which version of the requirements analysis and Prisma schema this group organization is based on. This step number ensures that the API grouping remains synchronized with evolving requirements and database schema changes throughout the development lifecycle.
The step value enables proper tracking of how API organization evolves as the project requirements and data model are refined through iterations.
Detailed token usage metrics for the operation.
Contains comprehensive token consumption data including total usage, input token breakdown with cache hit rates, and output token categorization by generation type (reasoning, predictions). This component-level tracking enables precise cost analysis and identification of operations that benefit most from prompt caching or require optimization.
Token usage directly translates to operational costs, making this metric essential for understanding the financial implications of different operation types and guiding resource allocation decisions.
Unique identifier for the event type.
A literal string that discriminates between different event types in the AutoBE system. This field enables TypeScript's discriminated union feature, allowing type-safe event handling through switch statements or conditional checks.
Examples: "analyzeWrite", "prismaSchema", "interfaceOperation", "testScenario"
Event fired when the Interface agent generates logical groups for organizing API endpoints.
This event occurs specifically in large-scale projects where the volume of database entities and requirements necessitates dividing API generation into manageable chunks. The Interface agent analyzes the Prisma schema structure and creates organizational groups that partition the API development work based on schema namespaces, file boundaries, or table prefix patterns.
The groups generated in this event serve as the foundation for subsequent endpoint generation cycles, ensuring that:
This grouping phase is critical for maintaining scalability and consistency in projects with extensive database schemas and complex business requirements.
Author
Samchon