NousResearch/hermes-agent · error · RuntimeError

agent reported failure

Error message

agent reported failure

What it means

Error "agent reported failure" thrown in NousResearch/hermes-agent.

Source

Thrown at cron/scheduler.py:4548

        # on these paths and may put the error into `final_response`, which
        # would otherwise be delivered as if it were the agent's reply and the
        # job's `last_status` set to "ok". Raise so the except handler below
        # builds the proper failure tuple. (issue #17855)
        turn_exit_reason = str(result.get("turn_exit_reason") or "")
        final_response_text = (result.get("final_response") or "").strip()
        max_iteration_summary = (
            result.get("failed") is not True
            and result.get("completed") is False
            and turn_exit_reason.startswith("max_iterations_reached(")
            and bool(final_response_text)
        )
        if result.get("failed") is True or (result.get("completed") is False and not max_iteration_summary):
            _err_text = (
                result.get("error")
                or final_response_text
                or "agent reported failure"
            )
            raise RuntimeError(_err_text)
        if max_iteration_summary:
            logger.warning(
                "Job '%s' reached the iteration limit but produced a final fallback response; "
                "delivering the response instead of failing the cron run",
                job_name,
            )

        final_response = result.get("final_response", "") or ""
        # Strip leaked placeholder text that upstream may inject on empty completions.
        if final_response.strip() == "(No response generated)":
            final_response = ""
        # Cron silence on abnormal empty turns.  The turn-completion explainer
        # (#34452) replaces a blank/empty model turn with a "⚠️ No reply: …"
        # string so interactive surfaces (CLI/gateway) explain why the box is
        # empty.  In a cron context that turns a previously-silent empty turn
        # into a delivered warning (Manfredi's Telegram symptom).  Detect the
        # explainer text deterministically (via the same formatter that
        # produced it) and treat it as empty so the empty-response suppression

View on GitHub (pinned to c896c09c42)

Solutions

1. Check the job's session/logs for the agent's reported failure reason.
2. Fix the underlying prompt/tool/provider issue and rerun the job.

When it happens

Trigger: Thrown at cron/scheduler.py:4548 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of NousResearch/hermes-agent@c896c09c42 (2026-08-14). Data as JSON: /api/errors/1516fb5f5ac604d0. Report an issue: GitHub.