NousResearch/hermes-agent · error · EmptyStreamError

Provider returned an empty stream with no finish_reason (pos

Error message

Provider returned an empty stream with no finish_reason (possible upstream error or malformed SSE response).

What it means

Error "Provider returned an empty stream with no finish_reason (possible upstream error or malformed SSE response)." thrown in NousResearch/hermes-agent.

Source

Thrown at agent/chat_completion_helpers.py:3770

                    id=tc["id"],
                    type=tc["type"],
                    extra_content=tc.get("extra_content"),
                    function=SimpleNamespace(
                        name=tc["function"]["name"],
                        arguments=arguments,
                    ),
                ))

        # Zero-chunk guard: stream yielded nothing usable — a provider/upstream
        # error or malformed SSE, not a legitimate empty completion. Raise so the
        # retry machinery handles it instead of fabricating a successful turn.
        if (
            finish_reason is None
            and not content_parts
            and not reasoning_parts
            and not tool_calls_acc
        ):
            raise EmptyStreamError(
                "Provider returned an empty stream with no finish_reason "
                "(possible upstream error or malformed SSE response)."
            )

        # A stream that delivered a tool call but only partial/unparseable
        # JSON args splits into two very different cases:
        #
        #   1. Provider sent finish_reason="length" → a genuine output-cap
        #      truncation.  Boosting max_tokens on retry is the right move.
        #
        #   2. Provider sent NO finish_reason (the SSE simply stopped after
        #      the opening "{" with no terminator and no [DONE]) → the
        #      upstream dropped/stalled the connection mid tool-call.  This
        #      is NOT an output cap — the model never reported hitting one.
        #      Some dedicated endpoints (e.g. NVIDIA Nemotron Ultra on the
        #      Nous dedicated endpoint) stall for minutes during large
        #      tool-arg generation, then close the stream cleanly without a
        #      finish_reason.  Stamping "length" here sends it down the

View on GitHub (pinned to c896c09c42)

Solutions

1. Retry the request; the provider returned an empty stream, often transient.
2. Check provider status and the request parameters (model name, max_tokens).
3. Switch models/providers if the endpoint consistently returns empty streams.

When it happens

Trigger: Thrown at agent/chat_completion_helpers.py:3770 when the library encounters an invalid state.

Common situations: See trigger scenarios.

Understand the failure class

• Parsing and encoding errors: unexpected token, malformed input — why parsers reject input and how to find the real culprit.

AI-assisted analysis of NousResearch/hermes-agent@c896c09c42 (2026-08-14). Data as JSON: /api/errors/6031d304e32211a9. Report an issue: GitHub.