paperclipai/paperclip · error · Error

OpenCode returned no models. Run `opencode models` and verif

Error message

OpenCode returned no models. Run `opencode models` and verify provider auth.

What it means

Thrown by ensureOpenCodeModelConfiguredAndAvailable (LOCAL, models.ts) when discovery completes but returns zero models, after the OPENCODE_ALLOW_ALL_MODELS bypass was not set. It tells the operator to run `opencode models` and verify provider auth, because the binary ran but enumerated nothing.

Source

Thrown at packages/adapters/opencode-local/src/server/models.ts:209

  // When the caller opts into OPENCODE_ALLOW_ALL_MODELS, OpenCode accepts any
  // provider/model at run time (e.g. gateway-routed models that never appear in
  // `opencode models` output). Honour that by skipping the availability probe;
  // we still enforce the provider/model format above and do not second-guess
  // the configured model. Prefer the explicit run env, then the process env.
  const env = normalizeEnv(input.env);
  if (isTruthyEnvFlag(env.OPENCODE_ALLOW_ALL_MODELS ?? process.env.OPENCODE_ALLOW_ALL_MODELS)) {
    return [{ id: model, label: model }];
  }

  const models = await discoverOpenCodeModelsCached({
    command: input.command,
    cwd: input.cwd,
    env: input.env,
  });

  if (models.length === 0) {
    throw new Error("OpenCode returned no models. Run `opencode models` and verify provider auth.");
  }

  if (!models.some((entry) => entry.id === model)) {
    const sample = models.slice(0, 12).map((entry) => entry.id).join(", ");
    throw new Error(
      `Configured OpenCode model is unavailable: ${model}. Available models: ${sample}${models.length > 12 ? ", ..." : ""}`,
    );
  }

  return models;
}

export async function listOpenCodeModels(): Promise<AdapterModel[]> {
  try {
    return await discoverOpenCodeModelsCached();
  } catch {
    return [];
  }

View on GitHub (pinned to 67001ec6eb)

Solutions

Run `opencode models` locally and confirm it lists provider/model lines.
Set a valid provider API key in the env passed to discovery (e.g. ANTHROPIC_API_KEY / OPENAI_API_KEY).
Run `opencode login` for the relevant provider.
If the model is gateway-routed and won't appear in the list, set OPENCODE_ALLOW_ALL_MODELS=true to bypass the availability check.

Defensive patterns

Strategy: validation

Validate before calling

const allowAll = isTruthyEnvFlag(normalizeEnv(input.env).OPENCODE_ALLOW_ALL_MODELS ?? process.env.OPENCODE_ALLOW_ALL_MODELS);
if (!allowAll) {
  // ensure at least one provider API key is set before calling ensureOpenCodeModelConfiguredAndAvailable
}

Try / catch

try {
  return await ensureOpenCodeModelConfiguredAndAvailable(input);
} catch (e) {
  if (e instanceof Error && /OpenCode returned no models/.test(e.message)) {
    // set provider auth or OPENCODE_ALLOW_ALL_MODELS, then retry
  }
  throw e;
}

Prevention

Set at least one provider API key in the run env.
Run `opencode models` locally during workspace setup to catch auth gaps early.
Use OPENCODE_ALLOW_ALL_MODELS for gateway-routed models.

When it happens

Trigger: discoverOpenCodeModelsCached returns [] and env.OPENCODE_ALLOW_ALL_MODELS is not truthy. The model id already passed requireOpenCodeModelId (format ok); the failure is that no provider serves any model.

Common situations: opencode installed and runs but no provider API key is configured; the provider env vars are present but invalid; opencode config has all providers disabled.

Related errors

AI-assisted analysis of paperclipai/paperclip@67001ec6eb (2026-08-12). Data as JSON: /api/errors/6580be3723c1d29c. Report an issue: GitHub.