coleam00/Archon · error · Error

Model override '${targetName}' has an empty model id.

Error message

Model override '${targetName}' has an empty model id.

What it means

Thrown by resolveRunOverrideSpec when a model override spec like 'provider/' specifies a registered provider but no model id after the slash. The library cannot resolve an override whose model portion is empty, so it fails fast with a targeted message naming the override.

Source

Thrown at packages/workflows/src/model-validation.ts:357

  if (isTierName(spec) || spec.startsWith('@')) {
    const resolved = resolveModelSpec(profile, spec);
    if (isLiteralSpec(resolved)) {
      throw new Error(`Model override '${targetName}' could not resolve '${spec}'.`);
    }
    return normalizeRunOverridePreset(targetName, { ...resolved });
  }

  const slash = spec.indexOf('/');
  if (slash === -1) {
    const target = presetForOverrideTarget(profile, targetName);
    return normalizeRunOverridePreset(targetName, { provider: target.provider, model: spec });
  }

  const prefix = spec.slice(0, slash);
  const remainder = spec.slice(slash + 1);
  if (isRegisteredProvider(prefix)) {
    if (remainder.length === 0) {
      throw new Error(`Model override '${targetName}' has an empty model id.`);
    }
    if (prefix === 'pi' && !parsePiModelRef(remainder)) {
      throw new Error(
        `Model override '${targetName}' has invalid Pi model '${remainder}'. ` +
          "Pi overrides need a vendor prefix, e.g. 'pi/minimax/minimax-m3'."
      );
    }
    return normalizeRunOverridePreset(targetName, { provider: prefix, model: remainder });
  }

  if (!parsePiModelRef(spec)) {
    throw new Error(
      `Model override '${targetName}' has invalid model '${spec}'. Expected <agent>/<model> or <vendor>/<model>.`
    );
  }
  return normalizeRunOverridePreset(targetName, { provider: 'pi', model: spec });
}

View on GitHub (pinned to 0773b97458)

Solutions

  1. Provide a model id after the provider prefix, e.g. 'openai/gpt-4o' instead of 'openai/'.
  2. If the spec came from a variable/interpolation, log the raw value to find why it expanded empty.
  3. For Pi alias entries keep a vendor segment, e.g. 'pi/minimax/minimax-m3'.
  4. Strip accidental trailing slashes from user/config supplied specs before calling the API.

Example fix

// before
--model large=openai/
// after
--model large=openai/gpt-4o
Defensive patterns

Strategy: validation

Validate before calling

function isValidOverrideSpec(spec: string, isRegistered: (p: string) => boolean): boolean {
  const slash = spec.indexOf('/');
  if (slash <= 0) return false;
  const prefix = spec.slice(0, slash);
  if (isRegistered(prefix)) return spec.slice(slash + 1).length > 0;
  return true;
}

Type guard

function hasNonEmptyModelId(spec: string): spec is `${string}/${string}` {
  const slash = spec.indexOf('/');
  return slash > 0 && slash < spec.length - 1;
}

Try / catch

try {
  resolveRunModelOverrides(assignments);
} catch (err) {
  if (err instanceof Error && err.message.includes('empty model id')) {
    throw new Error(`Config error: fill in the model after the provider slash (${err.message})`);
  }
  throw err;
}

Prevention

When it happens

Trigger: Calling resolveRunModelOverrides (or resolveRunOverrideSpec directly) with a spec string of the form '<registered-provider>/' e.g. 'openai/' or 'pi/' — the first '/' yields an empty remainder.

Common situations: Hand-edited config files or CLI flags where the model after the slash was deleted or never filled in; templated YAML where a model variable expanded to empty; trailing-slash typos.

Related errors

AI-assisted analysis of coleam00/Archon@0773b97458 (2026-09-01). Data as JSON: /api/errors/ffe381f2faff4d1f. Report an issue: GitHub.