HKUDS/nanobot · error · ImageGenerationError

Gemini image generation failed

Error message

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

What it means

Raised in GeminiImageGenerator._generate_gemini_flash when the POST to {api_base}/models/{model}:generateContent returns a non-2xx status. Wraps httpx.HTTPStatusError with status code and detail, meaning the Gemini generateContent endpoint rejected the image-generation request (auth, model, quota, or safety-block issues).

Solutions

1. Verify the Gemini API key and model name are correct
2. Check the detail for safety-block or quota reasons and adjust the prompt
3. Confirm network/proxy access to the Gemini endpoint
4. Retry after fixing configuration or prompt

When it happens

Trigger: Thrown at nanobot/providers/image_generation.py:837 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/aae637fdc9f8d2ae. Report an issue: GitHub.

Appendix: source

Thrown at nanobot/providers/image_generation.py:837

            "contents": [{"role": "user", "parts": parts}],
            "generationConfig": generation_config,
        }
        body.update(self.extra_body)

        url = f"{self.api_base}/models/{model}:generateContent"
        headers = {
            "x-goog-api-key": self.api_key or "",
            "Content-Type": "application/json",
            **self.extra_headers,
        }
        response = await self._http_post(url, headers=headers, body=body)

        try:
            response.raise_for_status()
        except httpx.HTTPStatusError as exc:
            detail = _http_error_detail(response)
            logger.error("Gemini image generation failed (HTTP {}): {}", response.status_code, detail)
            raise ImageGenerationError(
                f"Gemini image generation failed (HTTP {response.status_code}): {detail}"
            ) from exc

        data = _as_json_object(response.json()) or {}
        images: list[str] = []
        text_parts: list[str] = []
        for candidate in _as_json_objects(data.get("candidates")):
            content = _as_json_object(candidate.get("content")) or {}
            for part in _as_json_objects(content.get("parts")):
                if "text" in part:
                    text = part["text"]
                    if isinstance(text, str):
                        text_parts.append(text)
                inline = _as_json_object(part.get("inlineData"))
                if inline is not None:
                    mime = inline.get("mimeType", "image/png")
                    b64 = inline.get("data", "")
                    if isinstance(mime, str) and isinstance(b64, str) and b64:

View on GitHub (pinned to 42f37dc4c0)