BerriAI/litellm · error · HTTPException
Prompt with ID {prompt_id} not found
Error message
Prompt with ID {prompt_id} not found What it means
Delete guard: the prompt ID (after direct lookup and latest-version fallback in the in-memory registry and DB) resolves to no existing prompt, so there is nothing to delete; surfaced as 404.
Source
Thrown at litellm/proxy/prompts/prompt_endpoints.py:985
if prisma_client is None:
raise HTTPException(status_code=500, detail=CommonProxyErrors.db_not_connected_error.value)
try:
# Try to get prompt directly first
existing_prompt = IN_MEMORY_PROMPT_REGISTRY.get_prompt_by_id(prompt_id)
# If not found, try to find the latest version
if existing_prompt is None:
latest_prompt_id: Final = get_latest_version_prompt_id(
prompt_id=prompt_id,
all_prompt_ids=IN_MEMORY_PROMPT_REGISTRY.IN_MEMORY_PROMPTS,
)
existing_prompt = IN_MEMORY_PROMPT_REGISTRY.get_prompt_by_id(latest_prompt_id)
# Use the resolved prompt_id for deletion
prompt_id = latest_prompt_id
if existing_prompt is None:
raise HTTPException(status_code=404, detail=f"Prompt with ID {prompt_id} not found")
if existing_prompt.prompt_info.prompt_type == "config":
raise HTTPException(
status_code=400,
detail="Cannot delete config prompts.",
)
# Get the base prompt ID (without version suffix) for database deletion
base_prompt_id: Final = get_base_prompt_id(prompt_id=prompt_id)
# Build delete filter; scope to environment if provided
delete_where: Final[dict[str, str]] = {"prompt_id": base_prompt_id}
if environment:
delete_where["environment"] = environment
# Delete versions from the database (scoped to environment if provided)
await _prompt_table(prisma_client).delete_many(where=delete_where)
View on GitHub (pinned to 77b7c6c40c)
Solutions
- Confirm the prompt_id via the prompts list endpoint; recreate the prompt if deleted.
Defensive patterns
Strategy: type-guard
When it happens
Trigger: Thrown at litellm/proxy/prompts/prompt_endpoints.py:985 when the library encounters an invalid state.
Common situations: See trigger scenarios.
AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18).
Data as JSON: /api/errors/0eb363ab87bba2f5.
Report an issue: GitHub.