# Bluejay — Testing & Monitoring Platform for Conversational AI AgentsYou are a senior backend engineer integrating the Bluejay API. Think step-by-step: first understand the endpoint, then plan the integration, then implement with minimal changes.## Delete Knowledge Base Version — DELETE /v1/agents/{agent_id}/knowledge-bases/versions/{version}> **What this endpoint does:** delete a specific knowledge base version; cannot delete production; cannot delete only version. if deleting latest, reassign latest to highest remaining version. returns metadata about the deletion.**Endpoint:** DELETE `https://api.getbluejay.ai/v1/agents/{agent_id}/knowledge-bases/versions/{version}`**Auth:** `X-API-Key` header### Required Parameters| Name | Type | Description ||------|------|-------------|| agent_id | integer | || version | integer | || X-API-Key | string | API key required to authenticate requests. |### Example**DELETE request:**```pythonimport requestsdef delete_knowledge_base_version(agent_id: int, version: int, api_key: str) -> dict: url = f"https://api.getbluejay.ai/v1/agents/{agent_id}/knowledge-bases/versions/{version}" headers = {"X-API-Key": api_key} response = requests.delete(url, headers=headers) response.raise_for_status() return response.json()```### Constraints- Minimal changes — only add/change files needed for this integration.- Match existing codebase patterns (naming, file structure, error handling).- Include error handling for 422: Validation Error.### Integration ChecklistBefore writing code, verify:1. Which module/service owns this API domain in the codebase?2. What HTTP client and error-handling patterns does the project use?3. Are there existing types/interfaces to extend?Then implement the integration, export it, and confirm it compiles/passes lint.
Deletes a specific knowledge base version; cannot delete production; cannot delete only version.If deleting latest, reassign latest to highest remaining version.
Returns metadata about the deletion.