BerriAI/litellm · error · HTTPException
Prompt {prompt_id} not found in environment {environment}
Error message
Prompt {prompt_id} not found in environment {environment} What it means
Prompt fetch fallback exhausted: neither the DB query for the prompt in the requested environment nor the in-memory registry lookup (including latest-version resolution) produced a prompt with that prompt_id, so nothing can be returned for the given environment.
Source
Thrown at litellm/proxy/prompts/prompt_endpoints.py:688
where=where_clause,
order={"version": "desc"},
take=1,
)
if env_prompts:
prompt_spec = create_versioned_prompt_spec(db_prompt=env_prompts[0])
# Fallback: use in-memory registry (no environment filter)
if prompt_spec is None and environment is None:
prompt_spec = IN_MEMORY_PROMPT_REGISTRY.get_prompt_by_id(prompt_id)
if prompt_spec 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,
)
prompt_spec = IN_MEMORY_PROMPT_REGISTRY.get_prompt_by_id(latest_prompt_id)
if prompt_spec is None:
raise HTTPException(
status_code=400,
detail=f"Prompt {prompt_id} not found" + (f" in environment {environment}" if environment else ""),
)
# Extract version number from the prompt_id
version_number: Final = get_version_number(prompt_id=prompt_spec.prompt_id)
# Create a copy of the prompt spec with the base prompt ID (stripped of version)
prompt_spec_response: Final = PromptSpec(
prompt_id=get_base_prompt_id(prompt_id=prompt_spec.prompt_id),
litellm_params=prompt_spec.litellm_params,
prompt_info=prompt_spec.prompt_info,
created_at=prompt_spec.created_at,
updated_at=prompt_spec.updated_at,
version=version_number,
environment=prompt_spec.environment,
created_by=prompt_spec.created_by,
)View on GitHub (pinned to 77b7c6c40c)
Solutions
- Check the prompt exists in the requested environment (e.g. production vs staging); promote or create it there.
Defensive patterns
Strategy: type-guard
When it happens
Trigger: Thrown at litellm/proxy/prompts/prompt_endpoints.py:688 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/cd3b26eb3ab9e761.
Report an issue: GitHub.