BerriAI/litellm · critical · HTTPException

Prompt '{prompt_id}' not found

Error message

Prompt '{prompt_id}' not found

What it means

The client-resolution guard on the retrieve path: retrieve_fine_tuning_job builds a client via get_openai_client(); if it returns None (no api_key argument, no OPENAI_API_KEY environment/secret value, no custom client), this ValueError is raised before any HTTP request. It is a missing-credentials error, local to litellm.

Source

Thrown at cookbook/mock_prompt_management_server/mock_prompt_management_server.py:303

    return {"prompts": prompts_list, "total": len(prompts_list)}


@app.get("/prompts/{prompt_id}/variables")
async def get_prompt_variables(
    prompt_id: str, authorization: Optional[str] = Header(None)
):
    """
    Get all variables in a prompt template.

    This is a convenience endpoint (not part of the LiteLLM spec) for
    discovering what variables a prompt expects.
    """
    # Verify authentication
    verify_api_key(authorization)

    if prompt_id not in PROMPTS_DB:
        raise HTTPException(
            status_code=status.HTTP_404_NOT_FOUND,
            detail=f"Prompt '{prompt_id}' not found",
        )

    prompt_data = PROMPTS_DB[prompt_id]
    variables = set()

    # Extract variables from the prompt template
    import re

    for message in prompt_data["prompt_template"]:
        content = message.get("content", "")
        # Find all {variable} patterns
        found_vars = re.findall(r"\{(\w+)\}", content)
        variables.update(found_vars)

    return {
        "prompt_id": prompt_id,

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Ensure OPENAI_API_KEY is exported in the polling process.
2. Or pass api_key=... to retrieve_fine_tuning_job.
3. Or pass a prebuilt client via client=.

Example fix

# before
job = litellm.retrieve_fine_tuning_job(fine_tuning_job_id="ftjob-abc")

# after
job = litellm.retrieve_fine_tuning_job(fine_tuning_job_id="ftjob-abc", api_key=os.environ["OPENAI_API_KEY"])

import os

def can_retrieve_jobs(api_key: str | None) -> bool:
    return bool(api_key or os.environ.get("OPENAI_API_KEY"))

try:
    job = litellm.retrieve_fine_tuning_job(fine_tuning_job_id=jid)
except ValueError as e:
    if "not initialized" in str(e):
        job = litellm.retrieve_fine_tuning_job(fine_tuning_job_id=jid, api_key=os.environ["OPENAI_API_KEY"])
    else:
        raise

When it happens

Trigger: Calling litellm.retrieve_fine_tuning_job(fine_tuning_job_id=...) with no key in the call, module globals, or environment.

Common situations: Status-checking scripts run from schedulers (cron, Airflow) that lack the interactive shell's env; key present under a different variable name; secrets injected only into web processes, not the polling job.

Related errors

• Missing Authorization header
• Invalid bearer token
• Invalid API key
• Error: {response.status_code} - {response.text}
• Invalid Authorization header format. Expected: Bearer <token

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/42ab44b458bec076. Report an issue: GitHub.