openai/openai-python · error · ValueError

Expected a non-empty value for `run_id` but received {run_id

Error message

Expected a non-empty value for `run_id` but received {run_id!r}

What it means

The sync EvalRunOutputItem.retrieve() method requires run_id to be non-empty because it is interpolated into the request path /evals/{eval_id}/runs/{run_id}/output_items/{output_item_id}. An empty or None run_id would yield a malformed URL, so the SDK raises ValueError before any network call.

Source

Thrown at src/openai/resources/evals/runs/output_items.py:74

        extra_body: Body | None = None,
        timeout: float | httpx2.Timeout | None | NotGiven = not_given,
    ) -> OutputItemRetrieveResponse:
        """
        Get an evaluation run output item by ID.

        Args:
          extra_headers: Send extra headers

          extra_query: Add additional query parameters to the request

          extra_body: Add additional JSON properties to the request

          timeout: Override the client-level default timeout for this request, in seconds
        """
        if not eval_id:
            raise ValueError(f"Expected a non-empty value for `eval_id` but received {eval_id!r}")
        if not run_id:
            raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
        if not output_item_id:
            raise ValueError(f"Expected a non-empty value for `output_item_id` but received {output_item_id!r}")
        return self._get(
            path_template(
                "/evals/{eval_id}/runs/{run_id}/output_items/{output_item_id}",
                eval_id=eval_id,
                run_id=run_id,
                output_item_id=output_item_id,
            ),
            options=make_request_options(
                extra_headers=extra_headers,
                extra_query=extra_query,
                extra_body=extra_body,
                timeout=timeout,
                security={"bearer_auth": True},
            ),
            cast_to=OutputItemRetrieveResponse,
        )

View on GitHub (pinned to 9917c6e28e)

Solutions

  1. Verify run_id is set to the id of an existing eval run (created via client.evals.runs.create).
  2. Log or debug-print run_id right before the call to confirm its value.
  3. If it comes from storage, add a check for missing/empty values at load time.
  4. Guard with: if not run_id: raise ValueError('run_id is required').

Example fix

// before
item = client.evals.runs.output_items.retrieve(eval_id=eval_id, run_id=run_id, output_item_id=output_item_id)

// after
if not run_id:
    raise ValueError(f"run_id is required, got {run_id!r}")
item = client.evals.runs.output_items.retrieve(eval_id=eval_id, run_id=run_id, output_item_id=output_item_id)
Defensive patterns

Strategy: validation

Validate before calling

if not isinstance(run_id, str) or not run_id.strip():
    raise ValueError(f"run_id must be a non-empty string, got {run_id!r}")

Type guard

def is_valid_run_id(run_id: object) -> bool:
    return isinstance(run_id, str) and bool(run_id.strip())

Try / catch

try:
    item = client.evals.runs.output_items.retrieve(eval_id=eval_id, run_id=run_id, output_item_id=output_item_id)
except ValueError as e:
    if 'run_id' in str(e):
        raise ValueError(f'Skipping retrieve: {e}') from e
    raise

Prevention

When it happens

Trigger: Calling client.evals.runs.output_items.retrieve() with run_id='' or None while eval_id is valid. Common when run_id is stored from a previous run but the run creation failed or returned no id.

Common situations: Run id fetched from client.evals.runs.create(...) whose response lacked an id, ids read from a database/CSV with empty cells, or variables shadowed/typo'd so run_id is never assigned.

Related errors

AI-assisted analysis of openai/openai-python@9917c6e28e (2026-08-28). Data as JSON: /api/errors/f7c02dc299bdac13. Report an issue: GitHub.