NousResearch/hermes-agent · error · RuntimeError

{formatted runtime provider/auth error}

Error message

{formatted runtime provider/auth error}

What it means

Error "{formatted runtime provider/auth error}" thrown in NousResearch/hermes-agent.

Source

Thrown at cron/scheduler.py:4219

                    }
                    if entry.get("base_url"):
                        fb_kwargs["explicit_base_url"] = entry["base_url"]
                    fb_api_key = resolve_entry_api_key(entry)
                    if fb_api_key:
                        fb_kwargs["explicit_api_key"] = fb_api_key
                    runtime = resolve_runtime_provider(**fb_kwargs)
                    model = fb_model
                    logger.info(
                        "Job '%s': fallback resolved to %s model %s",
                        job_id,
                        runtime.get("provider"),
                        fb_model,
                    )
                    break
                except Exception as fb_exc:
                    logger.debug("Job '%s': fallback %s failed: %s", job_id, fb_provider, fb_exc)
            if runtime is None:
                raise RuntimeError(format_runtime_provider_error(auth_exc)) from auth_exc
        except Exception as exc:
            message = format_runtime_provider_error(exc)
            raise RuntimeError(message) from exc

        reasoning_config = resolve_reasoning_config(
            _cfg if isinstance(_cfg, dict) else {}, str(model)
        )

        # Provider/model-drift fail-closed guard (#44585).
        #
        # An UNPINNED job (no explicit job["provider"]/["model"]) follows the
        # global default, which can change after the job was created — a switch
        # to a paid PROVIDER (e.g. nous) OR a paid MODEL on the same provider
        # (e.g. claude-fable-5 on openrouter). Without a guard the job would
        # silently inherit that change and spend real money on every tick — the
        # $7.73 incident named BOTH a provider and a model.
        #
        # create_job() snapshots whatever resolution would have picked at

View on GitHub (pinned to c896c09c42)

Solutions

1. Fix the provider/auth error shown (API key, base URL, model) and rerun the job.
2. Run `hermes setup` or `hermes model` to repair provider configuration.

When it happens

Trigger: Thrown at cron/scheduler.py:4219 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/df0ff3bd435b4527. Report an issue: GitHub.