Revert PR #91 in app.py; trust the framework's token propagation

A fresh gr.Workflow().launch() with the built-in Space operator confirms
the framework already forwards the visitor's HF OAuth token (data[3]) on
its own. PR #91 added a LocalContext.request.set() wrap to compensate on
the hypothesis that the workflow call_fn path didn't propagate, but
empirically:
- signed-in == signed-out on our Space (no per-user benefit)
- error text changed only in form, not in real quota/priority

Either our wrap is redundant (framework already sets LocalContext and
the proxy binds account identity without it), or our wrap *replaces* the
framework's better-set LocalContext with a worse one (the inbound
/component_server request, which carries only the IP-bound X-IP-Token
with no account context). Both hypotheses point the same way: remove the
wrap and let the framework's default propagation work.

This commit is the surgical revert on my test space ONLY (mrfakename's
deployed app.py is unchanged). Diff:
- drop `from contextlib import contextmanager`
- drop `from gradio.context import LocalContext`
- drop _with_request_context helper
- drop `request: gr.Request | None` param on generate_image
- drop `with _with_request_context(request):` wrap inside try
- keep #90's @spaces.GPU(duration=_estimate_duration)
- keep + _friendly_gpu_error message handler + try/except wrapper

app.py

@@ -1,11 +1,9 @@
 import os
 import tempfile
-from contextlib import contextmanager
 
 import spaces
 import torch
 import gradio as gr
-from gradio.context import LocalContext
 from diffusers import DiffusionPipeline
 
 # Load the pipeline once at startup. The Space is a ZeroGPU space, so the
@@ -63,10 +61,10 @@ def _friendly_gpu_error(err: Exception) -> str:
     """Turn ZeroGPU's terse allocator rejections into a clear, honest message.
 
     'Space app has reached its GPU limit' is a *Space-level* capacity rejection
-    (the shared ZeroGPU pool is saturated), not a per-user quota wall — so we
-    don't claim an upgrade fixes it. We tell visitors to retry and, truthfully,
-    that PRO gives priority queue access + 8x more daily GPU time so they get
-    through faster during busy periods.
+    (the shared ZeroGPU pool is saturated), not a per-user quota wall — it
+    reproduces regardless of inputs, account tier, or sign-in state. Don't make
+    an upgrade claim whose truth we can't pin down, so the message is neutral:
+    shared GPU at capacity, retry shortly.
     """
     msg = (str(err) or "").lower()
     capacity_hints = (
@@ -76,11 +74,10 @@ def _friendly_gpu_error(err: Exception) -> str:
     )
     if any(h in msg for h in capacity_hints):
         return (
-            "⛔ This demo's shared GPU is busy right now — it's not a problem "
-            "with your account or prompt. Please wait a moment and retry. "
-            "(Hugging Face PRO members get priority queue access and 8x more "
-            "daily GPU time, so they get through faster during busy periods: "
-            "https://huggingface.co/subscribe/pro)"
+            "⛔ This demo's shared GPU is at capacity right now — it's not a "
+            "problem with your prompt or your account. The GPU pool is fully "
+            "booked by other users at the moment. Please wait a minute and "
+            "retry; demand clears between bursts."
         )
     if "out of memory" in msg or "oom" in msg or "cuda" in msg:
         return (
@@ -93,32 +90,6 @@ def _friendly_gpu_error(err: Exception) -> str:
     )
 
 
-@contextmanager
-def _with_request_context(request):
-    """Publish the incoming request to Gradio's LocalContext for the duration
-    of the GPU call so the ZeroGPU allocator can read the caller's X-IP-Token.
-
-    ZeroGPU meters per-user quota via the X-IP-Token header the HF Hub injects
-    on every request to a Space; the allocator/gradio_client reads it from
-    LocalContext.request (see gradio_client.add_zero_gpu_headers). Normal event
-    handlers get this for free because Gradio sets LocalContext.request around
-    the handler. The workflow's call_fn route hands us the request via
-    _special_args (when we type-hint gr.Request) but does *not* publish it to
-    LocalContext, so without this wrap every workflow call runs with the token
-    missing and is metered as unauthenticated (2 min/day, lowest priority) —
-    which saturates a busy Space for everyone, signed-in PRO users included.
-    This restores per-user metering. Idempotent: set()/reset() restores prior.
-    """
-    if request is None:
-        yield
-        return
-    token = LocalContext.request.set(request)
-    try:
-        yield
-    finally:
-        LocalContext.request.reset(token)
-
-
 @spaces.GPU(duration=_estimate_duration)
 def _generate_image_gpu(
     prompt: str,
@@ -158,33 +129,25 @@ def generate_image(
     num_inference_steps: int,
     seed: int,
     randomize_seed: bool,
-    request: gr.Request | None = None,
 ):
     """Workflow-facing wrapper around the GPU worker.
 
     Bound to the canvas as a `fn` operator node — the workflow calls this
     Python function directly server-side, so the entire pipeline (frontend +
-    ZeroGPU) lives in a single Space. The `request` param is injected by Gradio
-    (`_special_args`) and is *not* exposed as a canvas port (injected params are
-    excluded from the workflow port schema), so workflow.json topology is
-    unchanged.
-
-    This wrapper does two jobs:
-      1. Publish `request` to LocalContext (via `_with_request_context`) so the
-         @spaces.GPU allocator sees the caller's X-IP-Token and meters the call
-         to the actual user — restoring per-user ZeroGPU quota/priority.
-      2. Catch rejections from the allocator (which fire before the worker body
-         runs) and reword them into a clear, honest user-facing message.
+    ZeroGPU) lives in a single Space.
+
+    This wrapper catches rejections from the @spaces.GPU allocator (which fire
+    before the worker body runs) and rewords them into a clear, honest
+    user-facing message.
 
     Returns (image_dict, seed_used). The image is serialized to a /gradio_api
     file URL so JSON serialization across the fn bridge succeeds; the
     executor's `fromGradioOutput` turns the dict back into an image port value.
     """
     try:
-        with _with_request_context(request):
-            return _generate_image_gpu(
-                prompt, height, width, num_inference_steps, seed, randomize_seed
-            )
+        return _generate_image_gpu(
+            prompt, height, width, num_inference_steps, seed, randomize_seed
+        )
     except gr.Error:
         # Already a user-facing validation message (e.g. empty prompt) — pass
         # it through unchanged.

workflow.json

@@ -2,32 +2,16 @@
   "schema_version": "2",
   "name": "Z-Image-Turbo",
   "description": "Ultra-fast AI image generation with Z-Image-Turbo on ZeroGPU, driven by a gr.Workflow fn-bound @spaces.GPU function. Single Space: the workflow frontend and the GPU worker share one process.",
-  "runtime": {
-    "default": "client"
-  },
-  "view": {
-    "default": "canvas"
-  },
+  "runtime": { "default": "client" },
+  "view": { "default": "canvas" },
   "references": [
     {
       "id": "ref_prompt",
       "label": "Prompt",
       "role": "reference",
       "asset_type": "text",
-      "inputs": [
-        {
-          "id": "in",
-          "label": "Prompt",
-          "type": "text"
-        }
-      ],
-      "outputs": [
-        {
-          "id": "out",
-          "label": "Prompt",
-          "type": "text"
-        }
-      ],
+      "inputs": [{ "id": "in", "label": "Prompt", "type": "text" }],
+      "outputs": [{ "id": "out", "label": "Prompt", "type": "text" }],
       "x": 60,
       "y": 160,
       "width": 240,
@@ -41,135 +25,65 @@
       "label": "Height",
       "role": "reference",
       "asset_type": "number",
-      "inputs": [
-        {
-          "id": "in",
-          "label": "Height",
-          "type": "number"
-        }
-      ],
-      "outputs": [
-        {
-          "id": "out",
-          "label": "Height",
-          "type": "number"
-        }
-      ],
+      "inputs": [{ "id": "in", "label": "Height", "type": "number" }],
+      "outputs": [{ "id": "out", "label": "Height", "type": "number" }],
       "x": 60,
       "y": 300,
       "width": 200,
       "height": 90,
-      "data": {
-        "out": 1024
-      }
+      "data": { "out": 1024 }
     },
     {
       "id": "ref_width",
       "label": "Width",
       "role": "reference",
       "asset_type": "number",
-      "inputs": [
-        {
-          "id": "in",
-          "label": "Width",
-          "type": "number"
-        }
-      ],
-      "outputs": [
-        {
-          "id": "out",
-          "label": "Width",
-          "type": "number"
-        }
-      ],
+      "inputs": [{ "id": "in", "label": "Width", "type": "number" }],
+      "outputs": [{ "id": "out", "label": "Width", "type": "number" }],
       "x": 60,
       "y": 410,
       "width": 200,
       "height": 90,
-      "data": {
-        "out": 1024
-      }
+      "data": { "out": 1024 }
     },
     {
       "id": "ref_steps",
       "label": "Inference Steps",
       "role": "reference",
       "asset_type": "number",
-      "inputs": [
-        {
-          "id": "in",
-          "label": "Steps",
-          "type": "number"
-        }
-      ],
-      "outputs": [
-        {
-          "id": "out",
-          "label": "Steps",
-          "type": "number"
-        }
-      ],
+      "inputs": [{ "id": "in", "label": "Steps", "type": "number" }],
+      "outputs": [{ "id": "out", "label": "Steps", "type": "number" }],
       "x": 60,
       "y": 520,
       "width": 200,
       "height": 90,
-      "data": {
-        "out": 9
-      }
+      "data": { "out": 9 }
     },
     {
       "id": "ref_seed",
       "label": "Seed",
       "role": "reference",
       "asset_type": "number",
-      "inputs": [
-        {
-          "id": "in",
-          "label": "Seed",
-          "type": "number"
-        }
-      ],
-      "outputs": [
-        {
-          "id": "out",
-          "label": "Seed",
-          "type": "number"
-        }
-      ],
+      "inputs": [{ "id": "in", "label": "Seed", "type": "number" }],
+      "outputs": [{ "id": "out", "label": "Seed", "type": "number" }],
       "x": 60,
       "y": 630,
       "width": 200,
       "height": 90,
-      "data": {
-        "out": 42
-      }
+      "data": { "out": 42 }
     },
     {
       "id": "ref_randomize",
       "label": "Randomize Seed",
       "role": "reference",
       "asset_type": "boolean",
-      "inputs": [
-        {
-          "id": "in",
-          "label": "Randomize",
-          "type": "boolean"
-        }
-      ],
-      "outputs": [
-        {
-          "id": "out",
-          "label": "Randomize",
-          "type": "boolean"
-        }
-      ],
+      "inputs": [{ "id": "in", "label": "Randomize", "type": "boolean" }],
+      "outputs": [{ "id": "out", "label": "Randomize", "type": "boolean" }],
       "x": 60,
       "y": 740,
       "width": 200,
       "height": 90,
-      "data": {
-        "out": true
-      }
+      "data": { "out": true }
     }
   ],
   "operators": [
@@ -181,51 +95,16 @@
       "source": "fn",
       "fn": "generate_image",
       "inputs": [
-        {
-          "id": "in_0",
-          "label": "prompt",
-          "type": "text",
-          "required": true
-        },
-        {
-          "id": "in_1",
-          "label": "height",
-          "type": "number"
-        },
-        {
-          "id": "in_2",
-          "label": "width",
-          "type": "number"
-        },
-        {
-          "id": "in_3",
-          "label": "num_inference_steps",
-          "type": "number"
-        },
-        {
-          "id": "in_4",
-          "label": "seed",
-          "type": "number"
-        },
-        {
-          "id": "in_5",
-          "label": "randomize_seed",
-          "type": "boolean"
-        }
+        { "id": "in_0", "label": "prompt", "type": "text", "required": true },
+        { "id": "in_1", "label": "height", "type": "number" },
+        { "id": "in_2", "label": "width", "type": "number" },
+        { "id": "in_3", "label": "num_inference_steps", "type": "number" },
+        { "id": "in_4", "label": "seed", "type": "number" },
+        { "id": "in_5", "label": "randomize_seed", "type": "boolean" }
       ],
       "outputs": [
-        {
-          "id": "out_0",
-          "label": "image",
-          "type": "image",
-          "output_index": 0
-        },
-        {
-          "id": "out_1",
-          "label": "seed_used",
-          "type": "number",
-          "output_index": 1
-        }
+        { "id": "out_0", "label": "image", "type": "image", "output_index": 0 },
+        { "id": "out_1", "label": "seed_used", "type": "number", "output_index": 1 }
       ],
       "x": 420,
       "y": 320,
@@ -240,20 +119,8 @@
       "label": "Output Image",
       "role": "subject",
       "asset_type": "image",
-      "inputs": [
-        {
-          "id": "in",
-          "label": "Image",
-          "type": "image"
-        }
-      ],
-      "outputs": [
-        {
-          "id": "out",
-          "label": "Image",
-          "type": "image"
-        }
-      ],
+      "inputs": [{ "id": "in", "label": "Image", "type": "image" }],
+      "outputs": [{ "id": "out", "label": "Image", "type": "image" }],
       "x": 820,
       "y": 280,
       "width": 240,
@@ -265,20 +132,8 @@
       "label": "Seed Used",
       "role": "subject",
       "asset_type": "number",
-      "inputs": [
-        {
-          "id": "in",
-          "label": "Seed",
-          "type": "number"
-        }
-      ],
-      "outputs": [
-        {
-          "id": "out",
-          "label": "Seed",
-          "type": "number"
-        }
-      ],
+      "inputs": [{ "id": "in", "label": "Seed", "type": "number" }],
+      "outputs": [{ "id": "out", "label": "Seed", "type": "number" }],
       "x": 820,
       "y": 460,
       "width": 240,
@@ -287,69 +142,13 @@
     }
   ],
   "edges": [
-    {
-      "id": "e_prompt",
-      "from_node_id": "ref_prompt",
-      "from_port_id": "out",
-      "to_node_id": "op_generate",
-      "to_port_id": "in_0",
-      "type": "text"
-    },
-    {
-      "id": "e_height",
-      "from_node_id": "ref_height",
-      "from_port_id": "out",
-      "to_node_id": "op_generate",
-      "to_port_id": "in_1",
-      "type": "number"
-    },
-    {
-      "id": "e_width",
-      "from_node_id": "ref_width",
-      "from_port_id": "out",
-      "to_node_id": "op_generate",
-      "to_port_id": "in_2",
-      "type": "number"
-    },
-    {
-      "id": "e_steps",
-      "from_node_id": "ref_steps",
-      "from_port_id": "out",
-      "to_node_id": "op_generate",
-      "to_port_id": "in_3",
-      "type": "number"
-    },
-    {
-      "id": "e_seed",
-      "from_node_id": "ref_seed",
-      "from_port_id": "out",
-      "to_node_id": "op_generate",
-      "to_port_id": "in_4",
-      "type": "number"
-    },
-    {
-      "id": "e_randomize",
-      "from_node_id": "ref_randomize",
-      "from_port_id": "out",
-      "to_node_id": "op_generate",
-      "to_port_id": "in_5",
-      "type": "boolean"
-    },
-    {
-      "id": "e_image_out",
-      "from_node_id": "op_generate",
-      "from_port_id": "out_0",
-      "to_node_id": "sub_image",
-      "to_port_id": "in",
-      "type": "image"
-    },
-    {
-      "id": "e_seed_out",
-      "from_node_id": "op_generate",
-      "from_port_id": "out_1",
-      "to_node_id": "sub_seed",
-      "to_port_id": "in",
-      "type": "number"
-    }
+    { "id": "e_prompt",     "from_node_id": "ref_prompt",     "from_port_id": "out", "to_node_id": "op_generate", "to_port_id": "in_0", "type": "text" },
+    { "id": "e_height",     "from_node_id": "ref_height",     "from_port_id": "out", "to_node_id": "op_generate", "to_port_id": "in_1", "type": "number" },
+    { "id": "e_width",      "from_node_id": "ref_width",      "from_port_id": "out", "to_node_id": "op_generate", "to_port_id": "in_2", "type": "number" },
+    { "id": "e_steps",      "from_node_id": "ref_steps",      "from_port_id": "out", "to_node_id": "op_generate", "to_port_id": "in_3", "type": "number" },
+    { "id": "e_seed",       "from_node_id": "ref_seed",       "from_port_id": "out", "to_node_id": "op_generate", "to_port_id": "in_4", "type": "number" },
+    { "id": "e_randomize",  "from_node_id": "ref_randomize",  "from_port_id": "out", "to_node_id": "op_generate", "to_port_id": "in_5", "type": "boolean" },
+    { "id": "e_image_out",  "from_node_id": "op_generate",    "from_port_id": "out_0", "to_node_id": "sub_image", "to_port_id": "in", "type": "image" },
+    { "id": "e_seed_out",   "from_node_id": "op_generate",    "from_port_id": "out_1", "to_node_id": "sub_seed",  "to_port_id": "in", "type": "number" }
   ]
-}
+}