fix(images): render agent-generated images in chat (#2809)

* fix(images): render agent-generated images in chat

When a chat model calls generate_image mid-conversation (agentic flow), the image does
not display — it survives only as a URL the model echoes in prose. generate_image runs
as a text-only MCP server, so result['image_url'] is never populated and the existing
buildImageBubble render path never fires. Promote the image URL out of the tool's stdout
in tool_execution so the agent loop's existing forwarding renders it via buildImageBubble
— deterministically, no dependence on the model echoing the URL. Backend-only; reuses
dev's image bubble, forwarding, and the tool's existing parseable output.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(images): fully-qualified, valid generated-image links

The chat model often mangled the generated-image URL it echoed in prose (relative path,
or copying the 'image_url:' label into the link href). Build a fully-qualified link by
prefixing the existing app_public_url setting (empty default keeps relative paths), and
present it as a clean 'Direct link:' the model can echo verbatim (the frontend auto-links
bare https URLs). One file; independent of how the image is rendered.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(images): cover _promote_image_fields; make exit-code guard self-contained

Adds the unit tests requested in review on #2809: absolute URL, relative URL,
no URL (result unchanged), and non-zero exit_code (not promoted). Moves the
dict/exit_code==0 guard from the call site into _promote_image_fields so the
function is self-contained and the failure case is unit-testable; call-site
behavior is unchanged.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
nsgds
2026-06-05 19:04:33 +08:00
committed by GitHub
parent 201e207b56
commit 0f8d12363a
3 changed files with 101 additions and 2 deletions
+12 -2
View File
@@ -115,6 +115,10 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
img = images[0]
image_url = None
# Prefix the instance's public base URL (existing app_public_url setting) so the
# link is fully-qualified and clickable when the model echoes it. Empty = relative
# same-origin path (unchanged default).
_pub_base = (get_setting("app_public_url", "") or "").rstrip("/")
if img.get("b64_json"):
img_dir = Path("data/generated_images")
@@ -122,7 +126,7 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
filename = f"{uuid.uuid4().hex[:12]}.png"
img_path = img_dir / filename
img_path.write_bytes(base64.b64decode(img["b64_json"]))
image_url = f"/api/generated-image/{filename}"
image_url = f"{_pub_base}/api/generated-image/{filename}"
# Save to gallery
try:
@@ -146,7 +150,13 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
else:
return [TextContent(type="text", text="Error: Unexpected image API response format")]
result = f"Generated image for: {prompt[:100]}\nimage_url: {image_url}\nmodel: {model_id}\nsize: {size}"
# "Direct link:" rather than an "image_url:" label — small models copied the
# label token ("image_url") into the link href, producing a broken link.
result = (
f"Generated image for: {prompt[:100]}\n"
f"Direct link: {image_url}\n"
f"model: {model_id}\nsize: {size}"
)
return [TextContent(type="text", text=result)]
except httpx.TimeoutException: