continuedev/continue · error · Error

await resp.text()

Error message

await resp.text()

What it means

Thrown by the FunctionNetwork embedder._embed when the POST to the embeddings endpoint returns a non-2xx status; the raw response body text becomes the error message. The body carries FunctionNetwork's error payload identifying auth, model, or validation failures.

Source

Thrown at core/llm/llms/FunctionNetwork.ts:55

  public supportsPrefill(): boolean {
    return false;
  }

  protected async _embed(chunks: string[]): Promise<number[][]> {
    const resp = await this.fetch(new URL("embeddings", this.apiBase), {
      method: "POST",
      body: JSON.stringify({
        input: chunks,
        model: this.model,
      }),
      headers: {
        Authorization: `Bearer ${this.apiKey}`,
        "Content-Type": "application/json",
      },
    });

    if (!resp.ok) {
      throw new Error(await resp.text());
    }

    const data = (await resp.json()) as any;
    return data.data.map((result: { embedding: number[] }) => result.embedding);
  }
}

export default FunctionNetwork;

View on GitHub (pinned to 5522c6f44c)

Solutions

1. Read the response body embedded in the message to identify the exact endpoint error
2. Verify FUNCTIONNETWORK_API_KEY is set/valid with a single-input curl test against the embeddings endpoint
3. Confirm the configured embedding model name is valid for FunctionNetwork
4. Batch inputs within limits and add backoff for 429s

if (!process.env.FUNCTIONNETWORK_API_KEY) throw new Error('FUNCTIONNETWORK_API_KEY missing');
const batch = texts.slice(0, 64); // stay within batch limits

function isFunctionNetworkEmbedError(e: unknown): boolean {
  return e instanceof Error && !(e instanceof TypeError) && /embed|api|key|limit/i.test(e.message);
}

try { await embedder.embed(batch); }
catch (e) {
  if (e instanceof Error && /401|unauthorized|api key/i.test(e.message)) throw new ConfigError('Bad FUNCTIONNETWORK_API_KEY');
  throw e;
}

When it happens

Trigger: Calling embed() with a missing/invalid FunctionNetwork API key (401), an embedding model name not offered by the endpoint (404/400), inputs array exceeding endpoint batch/token limits, or rate limiting (429).

Common situations: FUNCTIONNETWORK_API_KEY env var unset or with stray quotes, model slugs copied from OpenAI docs, bulk indexing hitting per-request input limits or QPS caps.

Related errors

• await resp.text()
• Failed to parse config.json: ${e}
• MCP Connection ${serverId} not found
• Failed to fetch messages: ${response.statusText}
• No workspace directories found

AI-assisted analysis of continuedev/continue@5522c6f44c (2026-08-27). Data as JSON: /api/errors/c8530896588df094. Report an issue: GitHub.