HKUDS/nanobot · error · ImageGenerationError

Custom image generation failed

Error message

Custom image generation failed (HTTP {response.status_code}): {detail}

What it means

Raised in the custom OpenAI-compatible image generator's generate when POST {api_base}/images/generations returns a non-2xx status. Wraps httpx.HTTPStatusError with status code and up to 1000 chars of body, meaning the user-configured endpoint rejected the request — usually a misconfigured base URL, key, or unsupported parameter.

Solutions

  1. Verify api_base points at a valid OpenAI-compatible images endpoint
  2. Check the API key/credentials for the custom endpoint
  3. Inspect the detail body for which parameter the server rejected and adjust (size, n, model)
  4. Review extra_body for fields the custom server does not support
Defensive patterns

Strategy: try-catch

When it happens

Trigger: Thrown at nanobot/providers/image_generation.py:1351 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of HKUDS/nanobot@42f37dc4c0 (2026-08-26). Data as JSON: /api/errors/720a94467735d6c9. Report an issue: GitHub.

Appendix: source

Thrown at nanobot/providers/image_generation.py:1351

            "n": 1,
            "size": self._custom_size(aspect_ratio, image_size),
        }
        body.update(self.extra_body)

        logger.info("Custom Images API request: POST {}/images/generations body={}", self.api_base, body)

        response = await self._http_post(
            f"{self.api_base}/images/generations",
            headers=headers,
            body=body,
        )

        try:
            response.raise_for_status()
        except httpx.HTTPStatusError as exc:
            detail = response.text[:1000]
            logger.error("Custom Images API error ({}): {}", response.status_code, detail)
            raise ImageGenerationError(
                f"Custom image generation failed (HTTP {response.status_code}): {detail}"
            ) from exc

        payload = response.json()
        logger.info("Custom Images API response ({}): {}", response.status_code,
                       {k: v for k, v in payload.items() if k != "data"})

        images = await _openai_images_from_payload(payload, proxy=self.proxy)

        self._require_images(images, payload)

        return GeneratedImageResponse(images=images, content="", raw=payload)


# ---------------------------------------------------------------------------
# OpenAI Codex image generation
# ---------------------------------------------------------------------------

View on GitHub (pinned to 42f37dc4c0)