Pass the caller's x-ip-token to the conditioner explicitly

LocalContext-based token forwarding is unreliable in Server mode, so the
conditioner's ZeroGPU booking fell back to this Space's pod IP and its
shared quota ('quota exceeded' despite the caller having quota). Extract
the header from the injected Request and hand it to a per-request
gradio_client, per the gradio ZeroGPU docs.

app.py

@@ -12,7 +12,7 @@ from functools import cache
 # startup rather than on GPU time.
 import spaces
 from fastapi.responses import HTMLResponse
-from gradio import Server
+from gradio import Request, Server
 from gradio.data_classes import FileData
 
 MODEL_REPO = os.environ.get("H3_MODEL_REPO", "MiniMaxAI/MiniMax-H3")
@@ -177,20 +177,31 @@ def _arm_decode_hooks(pipe):
 
 @cache
 def conditioner():
-    """The other half, over the gradio API. `gradio_client` attaches the caller's own ZeroGPU token per call, so the
-    conditioner's booking is billed to whoever asked for the video."""
+    """The other half, over the gradio API. Used only when the caller's token could not be extracted; the booking is
+    then billed to this Space's pod IP and its small shared quota."""
     from gradio_client import Client
 
     return Client(CONDITIONER_SPACE)
 
 
-def encode_remote(prompt, image_path, last_image_path, canvas, num_frames, rewrite_prompt=False):
+def conditioner_client(ip_token):
+    """A conditioner client billed to the caller. `LocalContext`-based token forwarding is not reliable in Server
+    mode, so the `x-ip-token` header is extracted from the incoming request and passed explicitly (per the gradio
+    ZeroGPU docs); a per-request Client is cheap next to a 45s encode."""
+    if not ip_token:
+        return conditioner()
+    from gradio_client import Client
+
+    return Client(CONDITIONER_SPACE, headers={"x-ip-token": ip_token})
+
+
+def encode_remote(prompt, image_path, last_image_path, canvas, num_frames, rewrite_prompt=False, ip_token=None):
     """`/encode` on the conditioner Space: a safetensors file holding `prompt_embeds` + `text_token_tags`, with the
     resolved `height` / `width` / `num_frames` in its metadata, plus the plan. `canvas` is the label."""
     from gradio_client import handle_file
     from safetensors import safe_open
 
-    path, plan = conditioner().predict(
+    path, plan = conditioner_client(ip_token).predict(
         prompt=prompt,
         image_path=handle_file(image_path) if image_path else None,
         last_image_path=handle_file(last_image_path) if last_image_path else None,
@@ -286,7 +297,7 @@ def _fit_keyframe(image_path, current_canvas):
     return image_path, label
 
 
-def generate(prompt, image_path=None, last_image_path=None, canvas=DEFAULT_CANVAS, duration=5, steps=4, seed=42, upsample=False):
+def generate(prompt, image_path=None, last_image_path=None, canvas=DEFAULT_CANVAS, duration=5, steps=4, seed=42, upsample=False, ip_token=None):
     """One request. `upsample` is last and defaults off, so a positional API client that predates it is unaffected."""
     if LOAD_ERROR:
         raise Exception(LOAD_ERROR)
@@ -312,7 +323,7 @@ def generate(prompt, image_path=None, last_image_path=None, canvas=DEFAULT_CANVA
 
     conditioned = time.time()
     prompt_embeds, text_token_tags, metadata, plan = encode_remote(
-        prompt, first, last, canvas, num_frames, rewrite_prompt=upsample
+        prompt, first, last, canvas, num_frames, rewrite_prompt=upsample, ip_token=ip_token
     )
     condition_seconds = time.time() - conditioned
     height, width, num_frames = (int(metadata[key]) for key in ("height", "width", "num_frames"))
@@ -362,9 +373,11 @@ app = Server(title="MiniMax-H3 Studio")
 @app.api(name="generate")
 def _generate_api(prompt: str, image_path: FileData | None = None, last_image_path: FileData | None = None,
                   canvas: str = DEFAULT_CANVAS, duration: float = 5, steps: int = 4, seed: float = 42,
-                  upsample: bool = False) -> tuple[FileData, str, str]:
+                  upsample: bool = False, request: Request = None) -> tuple[FileData, str, str]:
     """Generate a video with a synchronized soundtrack. Returns (video, report, refined prompt)."""
-    return generate(prompt, image_path, last_image_path, canvas, duration, steps, seed, upsample)
+    # `request` is injected by the event system, not an API input; its x-ip-token bills the conditioner to the caller.
+    ip_token = request.headers.get("x-ip-token") if request is not None else None
+    return generate(prompt, image_path, last_image_path, canvas, duration, steps, seed, upsample, ip_token=ip_token)
 
 
 @app.get("/status")