HKUDS/DeepTutor · error · GenerationProviderError

Malformed image data URI.

Error message

Malformed image data URI.

What it means

_materialize received a data: URI whose payload after the comma is empty (src.partition(',') yielded nothing), so base64 decoding is impossible. The header exists but the base64 image body is missing or truncated before the comma.

Source

Thrown at deeptutor/services/imagegen/adapters/chat_completions.py:103

                    sources.append(src)
            # Fallback: some variants nest images in the content parts array.
            content = message.get("content")
            if isinstance(content, list):
                for part in content:
                    if not isinstance(part, dict):
                        continue
                    src = (part.get("image_url") or {}).get("url") or part.get("url")
                    if isinstance(src, str) and src.startswith(("data:image", "http")):
                        sources.append(src)
        if not sources:
            raise GenerationProviderError("Image response had no image in the assistant message.")
        return sources

    async def _materialize(self, client: httpx.AsyncClient, src: str) -> tuple[bytes, str]:
        if src.startswith("data:"):
            header, _, encoded = src.partition(",")
            if not encoded:
                raise GenerationProviderError("Malformed image data URI.")
            content_type = header[5:].split(";", 1)[0].strip() or "image/png"
            return base64.b64decode(encoded), content_type
        resp = await client.get(src)
        raise_for_provider(resp, "Image download")
        content_type = resp.headers.get("content-type") or "image/png"
        if not content_type.startswith("image/"):
            content_type = "image/png"
        return resp.content, content_type


__all__ = ["ChatCompletionsImagegenAdapter"]

View on GitHub (pinned to 3e82f13042)

Solutions

1. Retry the generation — transient truncation from the provider is the most common cause
2. Log the offending src string length to confirm it's empty vs truncated
3. If reproducible with one model/provider, report or switch providers/adapters

def valid_data_uri(src: str) -> bool:
    return src.startswith("data:") and len(src.partition(",")[2]) > 0

try:
    img = await adapter._materialize(client, src)
except GenerationProviderError as exc:
    if "Malformed image data URI" in str(exc):
        continue  # skip bad part, try next source

When it happens

Trigger: A content part with url like "data:image/png;base64," (empty payload), or a malformed URI where the image bytes were dropped/truncated in transit or by the provider.

Common situations: Provider bug or truncation when inlining images; intermediary proxy stripping large bodies; model emitting a placeholder data URI.

Understand the failure class

• Parsing and encoding errors: unexpected token, malformed input — why parsers reject input and how to find the real culprit.

Related errors

• No endpoint URL configured for image generation.
• Image generation request error: {exc}
• Chat model returned no image. Check the model supports image
• Image response had no image in the assistant message.
• No endpoint URL configured for image generation.

AI-assisted analysis of HKUDS/DeepTutor@3e82f13042 (2026-08-27). Data as JSON: /api/errors/b000c8557fe0dd3b. Report an issue: GitHub.