[fix] dreamverse: steering session-flow, mock parity, and init-image validation

Steering protocol/UI fixes that interlock via one contract change — the
frontend now sends initial_rollout_prompt_id (its own prompt id for the
opening scene) in session-init and reset payloads, and both backend pre-seed
sites use it, so prompt lifecycle events (enhancing/ready/fallback) finally
match the frontend's records instead of no-oping against a backend uuid.

- controller: suppress prompt_sources_blocked while a submission is queued or
  enhancing (fixes the blank player at typed-prompt session start); segment
  prompt logging is now opt-in via DREAMVERSE_SEGMENT_PROMPT_LOG, written off
  the event loop, warning on failure (drops the hardcoded author-machine path
  and bare except).
- web: 'Generating next scene' overlay driven by explicit generation state
  instead of waitingForSegmentPrompt prop edges, so auto_extension_updated
  while idle can't strand it over the video; steering scene history is no
  longer truncated by the 24-event prompt feed cap and keeps stable numbers
  for 30+ scene sessions.
- mock server: manual_continuation_mode parity (no rewrite-flow wait, honors
  initial_rollout_prompt_id, no segment cap in manual mode) so the GPU-less
  dev backend works with the steering-only frontend.
- init image: client-side type/size validation on picker and paste paths
  (png/jpeg/webp, 15MB) with a visible error, and ws_max_size raised to 32MiB
  on both servers so a legitimate ~15MB image reaches the backend's own
  validation instead of tripping uvicorn's 16MiB frame cap.

apps/dreamverse/dreamverse/config.py

@@ -67,7 +67,7 @@ MODEL_REGISTRY = {
     },
 }
 
-DEFAULT_MODEL_ID = "fast-ltx2"
+DEFAULT_MODEL_ID = "fast-ltx23"
 
 ACTIVE_MODEL_ID = (os.getenv("DREAMVERSE_MODEL_ID", "").strip() or DEFAULT_MODEL_ID)
 if ACTIVE_MODEL_ID not in MODEL_REGISTRY:
@@ -76,14 +76,11 @@ if ACTIVE_MODEL_ID not in MODEL_REGISTRY:
 # Active model configuration
 MODEL_CONFIG = MODEL_REGISTRY[ACTIVE_MODEL_ID]
 
-# Generation limits
-SESSION_TIMEOUT_SECONDS = 300
-
 # Frame settings
 NUM_FRAMES = 121
 FRAME_HEIGHT = 1088
 FRAME_WIDTH = 1920
-NUM_INFERENCE_STEPS = 5
+NUM_INFERENCE_STEPS = 6
 JPEG_QUALITY = 100
 BATCH_SIZE = 3
 
@@ -168,6 +165,9 @@ def _optional_env(*names: str) -> str | None:
     return None
 
 
+# Generation limits
+SESSION_TIMEOUT_SECONDS = _env_int("DREAMVERSE_SESSION_TIMEOUT_SECONDS", 300)
+
 DEVTOOLS_ENABLED = _env_bool("FASTVIDEO_ENABLE_DEVTOOLS", False)
 PROMPT_SAFETY_ENABLED = _env_bool("FASTVIDEO_ENABLE_PROMPT_SAFETY", False)
 DREAMVERSE_MAX_AUTOTUNE = _env_bool("DREAMVERSE_MAX_AUTOTUNE", True)

apps/dreamverse/dreamverse/gpu_pool.py

@@ -1023,7 +1023,11 @@ def get_available_gpus() -> list[int]:
     """Get list of available GPU IDs from environment or auto-detect."""
     cuda_visible = os.environ.get("CUDA_VISIBLE_DEVICES", "")
     if cuda_visible:
-        visible_gpu_ids = [int(x.strip()) for x in cuda_visible.split(",") if x.strip()]
+        try:
+            visible_gpu_ids = [int(x.strip()) for x in cuda_visible.split(",") if x.strip()]
+        except ValueError as exc:
+            raise RuntimeError("CUDA_VISIBLE_DEVICES must be a comma-separated list of integer GPU "
+                               f"indices (got {cuda_visible!r}); GPU UUIDs are not supported.") from exc
         return _limit_gpu_ids(visible_gpu_ids)
 
     # Auto-detect available GPUs

apps/dreamverse/dreamverse/main.py

@@ -206,7 +206,9 @@ def cli() -> None:
     args = parser.parse_args()
 
     _install_heartbeat_log_filter()
-    uvicorn.run(app, host=args.host, port=args.port)
+    # A 15MB init image (session_init_image.MAX_SESSION_INIT_IMAGE_BYTES) is ~20MB
+    # as a base64 ws message, above uvicorn's default 16MiB frame cap.
+    uvicorn.run(app, host=args.host, port=args.port, ws_max_size=32 * 1024 * 1024)
 
 
 if __name__ == "__main__":

apps/dreamverse/dreamverse/mock_server.py

@@ -30,11 +30,11 @@ from fastapi.middleware.cors import CORSMiddleware
 from fastapi.staticfiles import StaticFiles
 
 from dreamverse._deps import require_dreamverse_runtime_deps
-from dreamverse.config import FRONTEND_STATIC_DIR_CANDIDATES, GENERATION_SEGMENT_CAP
+from dreamverse.config import FRONTEND_STATIC_DIR_CANDIDATES, GENERATION_SEGMENT_CAP, SESSION_TIMEOUT_SECONDS
 from dreamverse.session_init_image import cleanup_session_init_image, persist_session_init_image
+from dreamverse.utils import _resolve_generation_segment_cap
 
 LATENCY_MS = 200
-SESSION_TIMEOUT_SECONDS = 300
 MOCK_FRAME_WIDTH = 640
 MOCK_FRAME_HEIGHT = 352
 MOCK_FPS = 24
@@ -334,6 +334,7 @@ async def websocket_endpoint(websocket: WebSocket):
         auto_extension_enabled = bool(init_data.get("auto_extension_enabled", False))
         loop_generation_enabled = bool(init_data.get("loop_generation_enabled", False))
         single_clip_mode = bool(init_data.get("single_clip_mode", False))
+        manual_continuation_mode = bool(init_data.get("manual_continuation_mode", False))
         generation_paused = False
 
         if init_type == "session_init_v2":
@@ -344,7 +345,8 @@ async def websocket_endpoint(websocket: WebSocket):
             incoming_prompts = []
 
         curated_prompts = [prompt.strip() for prompt in incoming_prompts if isinstance(prompt, str) and prompt.strip()]
-        generation_paused = bool(initial_rollout_prompt and not single_clip_mode and len(curated_prompts) == 0)
+        generation_paused = bool(not manual_continuation_mode and initial_rollout_prompt and not single_clip_mode
+                                 and len(curated_prompts) == 0)
 
         try:
             session_init_image = persist_session_init_image(init_data.get("initial_image"))
@@ -373,7 +375,10 @@ async def websocket_endpoint(websocket: WebSocket):
         prompt_sources_blocked = False
         pending_seed_reset = False
         pending_seed_reset_reason = ""
-        pending_simple_submission: PromptSubmission | None = None
+        pending_simple_submission: PromptSubmission | None = (PromptSubmission(
+            prompt_id=str(init_data.get("initial_rollout_prompt_id") or uuid.uuid4()),
+            raw_prompt=initial_rollout_prompt,
+        ) if manual_continuation_mode and initial_rollout_prompt else None)
         single_clip_waiting_for_request = False
         rollout_waiting_for_rewrite = False
         initial_rollout_waiting_for_rewrite = generation_paused
@@ -393,14 +398,26 @@ async def websocket_endpoint(websocket: WebSocket):
 
         async def send_stream_start(seed_reason: str) -> None:
             await ws_send_json({
-                "type": "ltx2_stream_start",
-                "total_segments": len(curated_prompts),
-                "preset_id": preset_id,
-                "stream_mode": "av_fmp4",
-                "live_mode": True,
-                "loop_generation_enabled": loop_generation_enabled,
-                "loop_iteration": loop_iteration,
-                "generation_segment_cap": 0,
+                "type":
+                "ltx2_stream_start",
+                "total_segments":
+                len(curated_prompts),
+                "preset_id":
+                preset_id,
+                "stream_mode":
+                "av_fmp4",
+                "live_mode":
+                True,
+                "loop_generation_enabled":
+                loop_generation_enabled,
+                "loop_iteration":
+                loop_iteration,
+                "generation_segment_cap":
+                _resolve_generation_segment_cap(
+                    single_clip_mode=single_clip_mode,
+                    cap=GENERATION_SEGMENT_CAP,
+                    manual_continuation_mode=manual_continuation_mode,
+                ),
             })
             if seed_reason == "init":
                 await ws_send_json({
@@ -493,6 +510,7 @@ async def websocket_endpoint(websocket: WebSocket):
             nonlocal auto_extension_enabled
             nonlocal loop_generation_enabled
             nonlocal single_clip_mode
+            nonlocal manual_continuation_mode
             nonlocal generation_paused
             nonlocal seed_prompt_memory
             nonlocal curated_prompts
@@ -537,6 +555,7 @@ async def websocket_endpoint(websocket: WebSocket):
             auto_extension_enabled = bool(payload.get("auto_extension_enabled", False))
             loop_generation_enabled = bool(payload.get("loop_generation_enabled", False))
             single_clip_mode = bool(payload.get("single_clip_mode", False))
+            manual_continuation_mode = bool(payload.get("manual_continuation_mode", False))
 
             seed_prompt_memory = list(next_curated_prompts)
             curated_prompts = list(seed_prompt_memory)
@@ -544,10 +563,14 @@ async def websocket_endpoint(websocket: WebSocket):
             segment_idx = 0
             pending_seed_reset = False
             pending_seed_reset_reason = ""
-            pending_simple_submission = None
+            pending_simple_submission = (PromptSubmission(
+                prompt_id=str(payload.get("initial_rollout_prompt_id") or uuid.uuid4()),
+                raw_prompt=initial_rollout_prompt,
+            ) if manual_continuation_mode and initial_rollout_prompt else None)
             single_clip_waiting_for_request = False
             rollout_waiting_for_rewrite = False
-            generation_paused = bool(initial_rollout_prompt and not single_clip_mode and len(curated_prompts) == 0)
+            generation_paused = bool(not manual_continuation_mode and initial_rollout_prompt and not single_clip_mode
+                                     and len(curated_prompts) == 0)
             initial_rollout_waiting_for_rewrite = generation_paused
             rewrite_restart_pending = False
             loop_iteration = 0
@@ -968,10 +991,11 @@ async def websocket_endpoint(websocket: WebSocket):
                     project_stream_started = True
                     await send_stream_start(pending_seed_reset_reason)
                     pending_seed_reset_reason = ""
-                    if pending_simple_submission is not None:
-                        submission = pending_simple_submission
-                        pending_simple_submission = None
-                        await promote_submission_to_ready(submission)
+
+                if pending_simple_submission is not None:
+                    submission = pending_simple_submission
+                    pending_simple_submission = None
+                    await promote_submission_to_ready(submission)
 
                 if generation_paused:
                     await asyncio.sleep(0.05)
@@ -981,8 +1005,8 @@ async def websocket_endpoint(websocket: WebSocket):
                     await asyncio.sleep(0.05)
                     continue
 
-                if (not single_clip_mode and not rollout_waiting_for_rewrite and GENERATION_SEGMENT_CAP > 0
-                        and segment_idx >= GENERATION_SEGMENT_CAP):
+                if (not single_clip_mode and not manual_continuation_mode and not rollout_waiting_for_rewrite
+                        and GENERATION_SEGMENT_CAP > 0 and segment_idx >= GENERATION_SEGMENT_CAP):
                     rollout_waiting_for_rewrite = True
                     loop_generation_enabled = False
                     project_stream_started = False
@@ -1217,7 +1241,9 @@ def cli() -> None:
     print(f"Starting mock server with {LATENCY_MS}ms latency on port {args.port}")
 
     _install_heartbeat_log_filter()
-    uvicorn.run(app, host="0.0.0.0", port=args.port)
+    # A 15MB init image (session_init_image.MAX_SESSION_INIT_IMAGE_BYTES) is ~20MB
+    # as a base64 ws message, above uvicorn's default 16MiB frame cap.
+    uvicorn.run(app, host="0.0.0.0", port=args.port, ws_max_size=32 * 1024 * 1024)
 
 
 if __name__ == "__main__":

apps/dreamverse/dreamverse/prompt_enhancer.py

@@ -313,6 +313,33 @@ def _extract_content_or_empty(response_json: dict[str, Any]) -> str:
         return ""
 
 
+def _find_balanced_object_end(text: str, start: int) -> int:
+    """Return the index just past the brace-balanced span opening at
+    ``text[start] == '{'``, honoring JSON string literals and escapes, or -1
+    if the braces never balance (i.e. the object was truncated)."""
+    depth = 0
+    in_string = False
+    escaped = False
+    for i in range(start, len(text)):
+        ch = text[i]
+        if in_string:
+            if escaped:
+                escaped = False
+            elif ch == "\\":
+                escaped = True
+            elif ch == '"':
+                in_string = False
+        elif ch == '"':
+            in_string = True
+        elif ch == "{":
+            depth += 1
+        elif ch == "}":
+            depth -= 1
+            if depth == 0:
+                return i + 1
+    return -1
+
+
 def _parse_json_response(content: str) -> dict[str, Any]:
     text = content.strip()
     if not text:
@@ -330,6 +357,7 @@ def _parse_json_response(content: str) -> dict[str, Any]:
         r"```(?:json)?\s*([\s\S]*?)```",
         flags=re.IGNORECASE,
     )
+    last_fenced: dict[str, Any] | None = None
     for match in fence_pattern.finditer(text):
         block = match.group(1).strip()
         if not block:
@@ -337,21 +365,37 @@ def _parse_json_response(content: str) -> dict[str, Any]:
         try:
             parsed = json.loads(block)
             if isinstance(parsed, dict):
-                return parsed
+                last_fenced = parsed
         except json.JSONDecodeError:
             continue
+    if last_fenced is not None:
+        return last_fenced
 
-    # Fall back to scanning for the first decodable JSON object in free-form text.
+    # Scan for all decodable JSON objects and return the last — chain-of-thought
+    # models emit draft JSON mid-reasoning; the final answer is always last.
     decoder = json.JSONDecoder()
-    for idx, char in enumerate(text):
-        if char != "{":
-            continue
+    last_parsed: dict[str, Any] | None = None
+    pos = 0
+    while (idx := text.find("{", pos)) != -1:
         try:
-            parsed, _ = decoder.raw_decode(text[idx:])
+            parsed, consumed = decoder.raw_decode(text[idx:])
         except json.JSONDecodeError:
+            # Skip the whole failed object rather than rescanning inside it:
+            # fragments nested in a malformed or truncated (finish_reason=
+            # length) object must not override an earlier complete object.
+            span_end = _find_balanced_object_end(text, idx)
+            if span_end == -1:
+                break
+            pos = span_end
             continue
+        # Skip past the consumed span so nested braces inside a decoded
+        # object are not re-parsed as standalone objects.
+        pos = idx + consumed
         if isinstance(parsed, dict):
-            return parsed
+            last_parsed = parsed
+
+    if last_parsed is not None:
+        return last_parsed
 
     raise ValueError("No JSON object found in assistant response.")
 
@@ -381,7 +425,7 @@ def _format_locked_segments(locked_segments: list[str]) -> str:
 
 class PromptEnhancer:
 
-    def __init__(self):
+    def __init__(self) -> None:
         self.provider = PROMPT_PROVIDER
         self.provider_label = _resolve_provider_label(PROMPT_PROVIDER)
         self.api_key = PROMPT_API_KEY
@@ -1417,15 +1461,12 @@ class PromptEnhancer:
             locked_text = _format_locked_segments(locked_segments_clean)
             request_system_prompt = self.enhance_system_prompt
             user_payload = {
-                "request": (
-                    "<locked_segments>\n"
-                    f"{locked_text}\n"
-                    "</locked_segments>\n\n"
-                    f"<conditioning_prompt>{cleaned}</conditioning_prompt>\n\n"
-                    f"Write exactly one new segment ({next_segment_key}) "
-                    "continuing from the locked segments. "
-                    'Respond with valid JSON only as {"next_prompt": "..."}.'  # noqa: E501
-                ),
+                "request": ("<locked_segments>\n"
+                            f"{locked_text}\n"
+                            "</locked_segments>\n\n"
+                            f"<conditioning_prompt>{cleaned}</conditioning_prompt>\n\n"
+                            f"Write exactly one new segment ({next_segment_key}) "
+                            "continuing from the locked segments."),
             }
 
         t0 = time.perf_counter()
@@ -1457,6 +1498,7 @@ class PromptEnhancer:
                             body=request_body,
                             timeout_seconds=timeout_seconds,
                         )
+                        _enhance_print("INFO", f"raw_response: {response_content}")
                         if is_single_clip_mode:
                             prompt = self._extract_single_clip_prompt(response_content)
                         else:
@@ -1539,7 +1581,7 @@ class PromptEnhancer:
                 f"Write exactly one new segment ({next_segment_key}) "
                 "that continues linearly from the locked segments. "
                 "Infer the next narrative beat from this history. "
-                'Respond with valid JSON only as {"next_prompt": "..."}.'  # noqa: E501
+                'Respond with valid JSON only: {"next_prompt": "<your segment description here>"}.'  # noqa: E501
             ),
         }
 

apps/dreamverse/dreamverse/session/controller.py

@@ -20,6 +20,7 @@ from __future__ import annotations
 # mypy: ignore-errors
 
 import asyncio
+import os
 import time
 import uuid
 from typing import TYPE_CHECKING
@@ -52,6 +53,14 @@ if TYPE_CHECKING:
     from dreamverse.prompt_enhancer import PromptEnhancer
     from dreamverse.prompt_safety import PromptSafetyFilter
 
+# Optional append-only log of every generated segment prompt; unset disables it.
+SEGMENT_PROMPT_LOG_PATH = os.environ.get("DREAMVERSE_SEGMENT_PROMPT_LOG", "")
+
+
+def _append_segment_prompt_log(path: str, text: str) -> None:
+    with open(path, "a") as f:
+        f.write(text)
+
 
 class SessionController:
     """Runs one WebSocket session from accept() through disconnect."""
@@ -198,6 +207,7 @@ class SessionController:
             auto_extension_enabled = bool(init_data.get("auto_extension_enabled", False))
             loop_generation_enabled = bool(init_data.get("loop_generation_enabled", False))
             single_clip_mode = bool(init_data.get("single_clip_mode", False))
+            manual_continuation_mode = bool(init_data.get("manual_continuation_mode", False))
             rewrite_model = self.prompt_enhancer.resolve_rewrite_model(init_data.get("rewrite_model"))
             rewrite_system_prompt_override = str(init_data.get("rewrite_window_system_prompt") or "").strip()
             rewrite_user_system_prompt_override = str(init_data.get("rewrite_user_system_prompt") or "").strip()
@@ -282,6 +292,9 @@ class SessionController:
             # Session queues and mutable state.
             raw_prompt_queue: asyncio.Queue[PromptSubmission] = asyncio.Queue()
             ready_prompt_queue: asyncio.Queue[ReadyPrompt] = asyncio.Queue()
+            # Submissions dequeued by prompt_worker_loop but not yet resolved; while
+            # non-zero the prompt sources are busy, not drained.
+            prompt_enhancement_inflight = 0
 
             curated_idx = 0
             segment_idx = 0
@@ -291,13 +304,20 @@ class SessionController:
             generation_cap_blocked = False
             auto_extension_blocked_segment_idx: int | None = None
             prompt_sources_drained_logged = False
-            generation_paused = bool(initial_rollout_prompt and not single_clip_mode and len(curated_prompts) == 0)
+            generation_paused = bool(not manual_continuation_mode and initial_rollout_prompt and not single_clip_mode
+                                     and len(curated_prompts) == 0)
             pending_seed_reset = False
             pending_seed_reset_reason = ""
             pending_reset_conditioning = False
             loop_iteration = 0 if generation_paused else 1
             force_curated_restart_segment = False
-            pending_simple_prompt_submission: PromptSubmission | None = None
+            # The frontend records the opening scene under this id; reuse it so
+            # prompt lifecycle events for the opening prompt reach that record.
+            pending_simple_prompt_submission: PromptSubmission | None = (PromptSubmission(
+                prompt_id=str(init_data.get("initial_rollout_prompt_id") or uuid.uuid4()),
+                raw_prompt=initial_rollout_prompt,
+                created_at_s=time.time(),
+            ) if manual_continuation_mode and initial_rollout_prompt else None)
             single_clip_waiting_for_request = False
             rollout_waiting_for_rewrite = False
             initial_rollout_waiting_for_rewrite = generation_paused
@@ -306,6 +326,7 @@ class SessionController:
             project_active = True
             project_stream_started = False
             pending_project_end = False
+            segment_prompt_log_warned = False
 
             def replace_session_init_image(initial_image_payload: object) -> None:
                 nonlocal session_init_image
@@ -424,6 +445,7 @@ class SessionController:
                 nonlocal auto_extension_enabled
                 nonlocal loop_generation_enabled
                 nonlocal single_clip_mode
+                nonlocal manual_continuation_mode
                 nonlocal generation_paused
                 nonlocal curated_prompts
                 nonlocal seed_prompt_memory
@@ -458,6 +480,7 @@ class SessionController:
                 next_auto_extension_enabled = bool(payload.get("auto_extension_enabled", False))
                 next_loop_generation_enabled = bool(payload.get("loop_generation_enabled", False))
                 next_single_clip_mode = bool(payload.get("single_clip_mode", False))
+                next_manual_continuation_mode = bool(payload.get("manual_continuation_mode", False))
 
                 next_preset_id = str(payload.get("preset_id") or "").strip()
                 if next_preset_id:
@@ -510,6 +533,7 @@ class SessionController:
                 auto_extension_enabled = next_auto_extension_enabled
                 loop_generation_enabled = next_loop_generation_enabled
                 single_clip_mode = next_single_clip_mode
+                manual_continuation_mode = next_manual_continuation_mode
                 rewrite_model = next_rewrite_model
                 rewrite_system_prompt_override = (next_rewrite_system_prompt_override)
                 rewrite_user_system_prompt_override = (next_rewrite_user_system_prompt_override)
@@ -530,10 +554,15 @@ class SessionController:
                 generation_cap_blocked = False
                 auto_extension_blocked_segment_idx = None
                 prompt_sources_drained_logged = False
-                pending_simple_prompt_submission = None
+                pending_simple_prompt_submission = (PromptSubmission(
+                    prompt_id=str(payload.get("initial_rollout_prompt_id") or uuid.uuid4()),
+                    raw_prompt=initial_rollout_prompt,
+                    created_at_s=time.time(),
+                ) if manual_continuation_mode and initial_rollout_prompt else None)
                 single_clip_waiting_for_request = False
                 rollout_waiting_for_rewrite = False
-                generation_paused = bool(initial_rollout_prompt and not single_clip_mode and len(curated_prompts) == 0)
+                generation_paused = bool(not manual_continuation_mode and initial_rollout_prompt
+                                         and not single_clip_mode and len(curated_prompts) == 0)
                 initial_rollout_waiting_for_rewrite = generation_paused
                 rewrite_restart_pending = False
                 loop_iteration = 0
@@ -942,6 +971,7 @@ class SessionController:
                             _resolve_generation_segment_cap(
                                 single_clip_mode=single_clip_mode,
                                 cap=GENERATION_SEGMENT_CAP,
+                                manual_continuation_mode=manual_continuation_mode,
                             ),
                         })
                         continue
@@ -1005,11 +1035,9 @@ class SessionController:
                         continue
 
             async def prompt_worker_loop():
-                while not stop_event.is_set():
-                    try:
-                        submission = await asyncio.wait_for(raw_prompt_queue.get(), timeout=0.1)
-                    except asyncio.TimeoutError:
-                        continue
+                nonlocal prompt_enhancement_inflight
+
+                async def process_submission(submission: PromptSubmission) -> None:
                     _main_print("INFO", f"Received user prompt for enhancement: {submission.raw_prompt}")
                     prompt_id = submission.prompt_id
                     raw_prompt = submission.raw_prompt
@@ -1032,8 +1060,9 @@ class SessionController:
                         await ws_send_json({
                             "type": "error",
                             "message": blocked_raw_prompt_error,
+                            "prompt_id": prompt_id,
                         })
-                        continue
+                        return
                     await log_event(
                         "enhance_request",
                         {
@@ -1093,8 +1122,9 @@ class SessionController:
                             await ws_send_json({
                                 "type": "error",
                                 "message": blocked_final_prompt_error,
+                                "prompt_id": prompt_id,
                             })
-                            continue
+                            return
                         if result.fallback_used or not final_prompt:
                             source = "user_enhancement_failed"
                             _main_print(
@@ -1113,7 +1143,7 @@ class SessionController:
                             })
                             # Enhancement is strict JSON-only; do not enqueue raw
                             # prompt when enhancement fails.
-                            continue
+                            return
                         else:
                             source = "user_enhanced"
                             await ws_send_json({
@@ -1130,6 +1160,7 @@ class SessionController:
                                 source=source,
                                 fallback_used=result.fallback_used,
                                 loop_iteration=loop_iteration,
+                                raw_prompt=raw_prompt,
                             ))
                     else:
                         await ready_prompt_queue.put(
@@ -1139,6 +1170,7 @@ class SessionController:
                                 source="user_raw",
                                 fallback_used=False,
                                 loop_iteration=loop_iteration,
+                                raw_prompt=raw_prompt,
                             ))
                         await ws_send_json({
                             "type": "prompt_ready",
@@ -1148,6 +1180,21 @@ class SessionController:
                             "latency_ms": 0.0,
                         })
 
+                while not stop_event.is_set():
+                    try:
+                        submission = raw_prompt_queue.get_nowait()
+                    except asyncio.QueueEmpty:
+                        await asyncio.sleep(0.1)
+                        continue
+                    # Dequeue and increment without an await in between so the
+                    # generation loop never sees an empty queue with zero in flight
+                    # while this submission is still being enhanced.
+                    prompt_enhancement_inflight += 1
+                    try:
+                        await process_submission(submission)
+                    finally:
+                        prompt_enhancement_inflight -= 1
+
             def queue_snapshot() -> dict[str, object]:
                 return {
                     "user_ready": ready_prompt_queue.qsize(),
@@ -1300,6 +1347,7 @@ class SessionController:
                     _resolve_generation_segment_cap(
                         single_clip_mode=single_clip_mode,
                         cap=GENERATION_SEGMENT_CAP,
+                        manual_continuation_mode=manual_continuation_mode,
                     ),
                 })
                 await ws_send_json({
@@ -1359,6 +1407,7 @@ class SessionController:
                         _resolve_generation_segment_cap(
                             single_clip_mode=single_clip_mode,
                             cap=GENERATION_SEGMENT_CAP,
+                            manual_continuation_mode=manual_continuation_mode,
                         ),
                     })
                     if nonlocal_reason == "loop_restart":
@@ -1388,8 +1437,9 @@ class SessionController:
                     await raw_prompt_queue.put(pending_simple_prompt_submission)
                     pending_simple_prompt_submission = None
 
-                if (not single_clip_mode and not generation_cap_blocked and not rollout_waiting_for_rewrite
-                        and GENERATION_SEGMENT_CAP > 0 and generated_segment_count >= GENERATION_SEGMENT_CAP):
+                if (not single_clip_mode and not manual_continuation_mode and not generation_cap_blocked
+                        and not rollout_waiting_for_rewrite and GENERATION_SEGMENT_CAP > 0
+                        and generated_segment_count >= GENERATION_SEGMENT_CAP):
                     loop_generation_enabled = False
                     rollout_waiting_for_rewrite = True
                     _main_print(
@@ -1542,7 +1592,10 @@ class SessionController:
                     if single_clip_mode:
                         await asyncio.sleep(PROMPT_AUTO_SLEEP_MS / 1000.0)
                         continue
-                    if not prompt_sources_drained_logged:
+                    # A raw submission still queued or being enhanced will produce a
+                    # ready prompt shortly; that is not a drained/blocked state.
+                    enhancement_pending = (raw_prompt_queue.qsize() > 0 or prompt_enhancement_inflight > 0)
+                    if not prompt_sources_drained_logged and not enhancement_pending:
                         snapshot = queue_snapshot()
                         _main_print(
                             "WARN",
@@ -1581,6 +1634,24 @@ class SessionController:
                 total_segments_hint = max(segment_idx, len(curated_prompts))
                 prompt = selected.prompt
                 locked_segment_prompts.append(prompt)
+                if SEGMENT_PROMPT_LOG_PATH:
+                    _ts = time.strftime("%Y-%m-%d %H:%M:%S")
+                    _lines = [
+                        f"\n=== Segment {segment_idx} [{_ts}] source={selected.source} client={client_id[:8]} ===",
+                    ]
+                    if selected.raw_prompt and selected.raw_prompt != prompt:
+                        _lines.append(f"User:     {selected.raw_prompt}")
+                    _lines.append(f"Rewritten: {prompt}")
+                    try:
+                        await asyncio.to_thread(_append_segment_prompt_log, SEGMENT_PROMPT_LOG_PATH,
+                                                "\n".join(_lines) + "\n")
+                    except Exception as exc:
+                        if not segment_prompt_log_warned:
+                            segment_prompt_log_warned = True
+                            _main_print(
+                                "WARN",
+                                f"Failed to write segment prompt log {SEGMENT_PROMPT_LOG_PATH}: {exc}",
+                            )
                 if (auto_extension_blocked_segment_idx is not None
                         and auto_extension_blocked_segment_idx <= segment_idx):
                     auto_extension_blocked_segment_idx = None

apps/dreamverse/dreamverse/session/messages.py

@@ -19,3 +19,4 @@ class ReadyPrompt:
     fallback_used: bool = False
     seed_prompt_index: int | None = None
     loop_iteration: int | None = None
+    raw_prompt: str | None = None

apps/dreamverse/dreamverse/tests/test_config.py

@@ -150,12 +150,22 @@ def test_config_enables_prompt_safety_when_requested(monkeypatch):
 
 def test_config_uses_five_minute_session_timeout(monkeypatch):
     _set_required_prompt_keys(monkeypatch)
+    monkeypatch.delenv("DREAMVERSE_SESSION_TIMEOUT_SECONDS", raising=False)
 
     module = _load_config_module()
 
     assert module.SESSION_TIMEOUT_SECONDS == 300
 
 
+def test_config_session_timeout_env_override(monkeypatch):
+    _set_required_prompt_keys(monkeypatch)
+    monkeypatch.setenv("DREAMVERSE_SESSION_TIMEOUT_SECONDS", "1800")
+
+    module = _load_config_module()
+
+    assert module.SESSION_TIMEOUT_SECONDS == 1800
+
+
 def test_config_rejects_invalid_prompt_provider(monkeypatch):
     monkeypatch.setenv("FASTVIDEO_PROMPT_PROVIDER", "unsupported")
     _set_required_prompt_keys(monkeypatch)

apps/dreamverse/dreamverse/tests/test_entrypoints.py

@@ -75,12 +75,13 @@ def _run_cli(module, monkeypatch, argv: list[str]) -> list[dict[str, object]]:
     calls: list[dict[str, object]] = []
     uvicorn_stub = types.ModuleType("uvicorn")
 
-    def run(app, host: str, port: int) -> None:
+    def run(app, host: str, port: int, **kwargs) -> None:
         calls.append(
             {
                 "app": app,
                 "host": host,
                 "port": port,
+                **kwargs,
             }
         )
 
@@ -104,6 +105,7 @@ def test_server_cli_defaults_to_local_web_port(monkeypatch):
             "app": server_main.app,
             "host": "0.0.0.0",
             "port": 8009,
+            "ws_max_size": 32 * 1024 * 1024,
         }
     ]
 
@@ -121,6 +123,7 @@ def test_server_cli_allows_explicit_host_and_port(monkeypatch):
             "app": server_main.app,
             "host": "127.0.0.1",
             "port": 8123,
+            "ws_max_size": 32 * 1024 * 1024,
         }
     ]
 
@@ -147,6 +150,7 @@ def test_mock_server_cli_defaults_to_local_web_port(monkeypatch):
             "app": mock_server.app,
             "host": "0.0.0.0",
             "port": 8009,
+            "ws_max_size": 32 * 1024 * 1024,
         }
     ]
 
@@ -166,6 +170,7 @@ def test_mock_server_cli_updates_latency(monkeypatch):
                 "app": mock_server.app,
                 "host": "0.0.0.0",
                 "port": 8111,
+                "ws_max_size": 32 * 1024 * 1024,
             }
         ]
         assert mock_server.LATENCY_MS == 321

apps/dreamverse/dreamverse/tests/test_mock_server.py

@@ -290,6 +290,152 @@ def test_mock_server_supports_initial_custom_rollout_prompt():
         mock_server.LATENCY_MS = old_latency_ms
 
 
+def test_mock_server_manual_mode_streams_initial_prompt_without_rewrite_or_cap():
+    old_segment_bytes = mock_server.MOCK_SEGMENT_BYTES
+    old_latency_ms = mock_server.LATENCY_MS
+    old_generation_segment_cap = mock_server.GENERATION_SEGMENT_CAP
+    try:
+        mock_server.MOCK_SEGMENT_BYTES = b"mock-fmp4-bytes"
+        mock_server.LATENCY_MS = 1
+        mock_server.GENERATION_SEGMENT_CAP = 1
+
+        ws = _FakeWebSocket(
+            [
+                (
+                    0.0,
+                    {
+                        "type": "session_init_v2",
+                        "preset_id": "custom_editable",
+                        "preset_label": "Custom rollout",
+                        "curated_prompts": [],
+                        "initial_rollout_prompt": "A drone skims a neon canyon",
+                        "initial_rollout_prompt_id": "steer-prompt-1",
+                        "manual_continuation_mode": True,
+                        "enhancement_enabled": True,
+                        "auto_extension_enabled": False,
+                        "loop_generation_enabled": False,
+                    },
+                ),
+                (
+                    0.08,
+                    {
+                        "type": "append_prompt",
+                        "prompt": "The drone dives toward the river",
+                        "prompt_id": "steer-prompt-2",
+                    },
+                ),
+                (0.30, {"type": "leave"}),
+            ]
+        )
+
+        asyncio.run(mock_server.websocket_endpoint(ws))
+
+        message_types = [payload["type"] for payload in ws.sent_json]
+        assert "rewrite_seed_prompts_started" not in message_types
+        assert "rewrite_seed_prompts_complete" not in message_types
+        assert "ltx2_stream_start" in message_types
+        # cap=1 must not stop a manual-mode session after the first segment
+        assert "ltx2_stream_complete" not in message_types
+
+        prompt_ready_events = [
+            payload for payload in ws.sent_json if payload["type"] == "prompt_ready"
+        ]
+        assert [payload["prompt_id"] for payload in prompt_ready_events] == [
+            "steer-prompt-1",
+            "steer-prompt-2",
+        ]
+
+        segment_start_events = [
+            payload
+            for payload in ws.sent_json
+            if payload["type"] == "ltx2_segment_start"
+        ]
+        assert [payload["prompt"] for payload in segment_start_events] == [
+            "A drone skims a neon canyon",
+            "The drone dives toward the river",
+        ]
+        segment_source_events = [
+            payload
+            for payload in ws.sent_json
+            if payload["type"] == "segment_prompt_source"
+        ]
+        assert [payload["prompt_id"] for payload in segment_source_events] == [
+            "steer-prompt-1",
+            "steer-prompt-2",
+        ]
+    finally:
+        mock_server.MOCK_SEGMENT_BYTES = old_segment_bytes
+        mock_server.LATENCY_MS = old_latency_ms
+        mock_server.GENERATION_SEGMENT_CAP = old_generation_segment_cap
+
+
+def test_mock_server_project_init_manual_mode_streams_initial_prompt():
+    old_segment_bytes = mock_server.MOCK_SEGMENT_BYTES
+    old_latency_ms = mock_server.LATENCY_MS
+    try:
+        mock_server.MOCK_SEGMENT_BYTES = b"mock-fmp4-bytes"
+        mock_server.LATENCY_MS = 1
+
+        ws = _FakeWebSocket(
+            [
+                (
+                    0.0,
+                    {
+                        "type": "session_init_v2",
+                        "preset_id": "test_preset",
+                        "curated_prompts": ["segment one"],
+                        "enhancement_enabled": True,
+                        "auto_extension_enabled": False,
+                        "loop_generation_enabled": False,
+                    },
+                ),
+                (0.05, {"type": "end_project_keep_session"}),
+                (
+                    0.15,
+                    {
+                        "type": "project_init_v1",
+                        "preset_id": "custom_editable",
+                        "preset_label": "Custom rollout",
+                        "curated_prompts": [],
+                        "initial_rollout_prompt": "A drone skims a neon canyon",
+                        "initial_rollout_prompt_id": "steer-prompt-1",
+                        "manual_continuation_mode": True,
+                        "enhancement_enabled": True,
+                        "auto_extension_enabled": False,
+                        "loop_generation_enabled": False,
+                    },
+                ),
+                (0.45, {"type": "leave"}),
+            ]
+        )
+
+        asyncio.run(mock_server.websocket_endpoint(ws))
+
+        message_types = [payload["type"] for payload in ws.sent_json]
+        assert "project_idle" in message_types
+        project_idle_index = message_types.index("project_idle")
+        # manual-mode restart must not run the rewrite rollout
+        assert "rewrite_seed_prompts_started" not in message_types[project_idle_index:]
+        assert "ltx2_stream_start" in message_types[project_idle_index:]
+
+        prompt_ready_events = [
+            payload for payload in ws.sent_json if payload["type"] == "prompt_ready"
+        ]
+        assert [payload["prompt_id"] for payload in prompt_ready_events] == [
+            "steer-prompt-1",
+        ]
+
+        segment_start_events = [
+            payload
+            for payload in ws.sent_json
+            if payload["type"] == "ltx2_segment_start"
+        ]
+        assert segment_start_events[-1]["prompt"] == "A drone skims a neon canyon"
+    finally:
+        mock_server.MOCK_SEGMENT_BYTES = old_segment_bytes
+        mock_server.LATENCY_MS = old_latency_ms
+
+
 def test_mock_server_can_start_new_project_without_reconnecting():
     old_segment_bytes = mock_server.MOCK_SEGMENT_BYTES
     old_latency_ms = mock_server.LATENCY_MS

apps/dreamverse/dreamverse/tests/test_prompt_enhancer.py

@@ -6,6 +6,7 @@ import os
 import re
 import time
 
+import pytest
 
 os.environ.setdefault("CEREBRAS_API_KEY", "dummy")
 os.environ.setdefault("GROQ_API_KEY", "dummy")
@@ -205,6 +206,59 @@ def test_parse_json_response_extracts_first_embedded_object():
     assert parsed == {"segment_prompts": ["A", "B"]}
 
 
+def test_parse_json_response_returns_outer_object_not_nested_value():
+    parsed = _parse_json_response(
+        "Final answer: {\"next_prompt\": \"a scene\", \"style\": {\"mood\": \"noir\"}} done."
+    )
+    assert parsed == {"next_prompt": "a scene", "style": {"mood": "noir"}}
+
+
+def test_parse_json_response_returns_last_of_multiple_objects():
+    parsed = _parse_json_response(
+        "Draft: {\"next_prompt\": \"draft\"}\nRefined: {\"next_prompt\": \"final\"}"
+    )
+    assert parsed == {"next_prompt": "final"}
+
+
+def test_parse_json_response_ignores_fragments_of_truncated_trailing_object():
+    # finish_reason=length cut the refined object short; the complete draft must
+    # win over a nested fragment of the truncated object.
+    parsed = _parse_json_response(
+        '{"next_prompt": "draft"} refined: {"next_prompt": "final", "style": {"mood": "noir"}'
+    )
+    assert parsed == {"next_prompt": "draft"}
+
+
+def test_parse_json_response_ignores_fragments_of_mid_string_truncated_object():
+    # Unterminated-string truncation reports the error at the opening quote,
+    # not end-of-text; nested fragments still must not win over the draft.
+    parsed = _parse_json_response(
+        '{"next_prompt": "draft"} refined: {"style": {"mood": "noir"}, "next_prompt": "cut off'
+    )
+    assert parsed == {"next_prompt": "draft"}
+
+
+def test_parse_json_response_ignores_fragments_of_malformed_object_with_trailing_prose():
+    parsed = _parse_json_response(
+        '{"next_prompt": "draft"} {"final": {"mood": "noir"}, "x": 1 and then some prose'
+    )
+    assert parsed == {"next_prompt": "draft"}
+
+
+def test_parse_json_response_raises_when_only_object_is_truncated():
+    with pytest.raises(ValueError):
+        _parse_json_response('{"style": {"mood": "noir"}, "next_prompt": "cut off')
+
+
+def test_parse_json_response_returns_outer_rollout_dict():
+    parsed = _parse_json_response(
+        "{\"rollout\": {\"segment_prompts\": [{\"prompt\": \"a\"}, {\"prompt\": \"b\"}]}}"
+    )
+    assert parsed == {
+        "rollout": {"segment_prompts": [{"prompt": "a"}, {"prompt": "b"}]}
+    }
+
+
 def test_load_prompt_required_falls_back_to_default_path(tmp_path):
     fallback_path = tmp_path / "next_segment_system_prompt.md"
     fallback_path.write_text("fallback prompt\n", encoding="utf-8")

apps/dreamverse/dreamverse/utils.py

@@ -15,5 +15,6 @@ def _utc_now_iso() -> str:
 PROMPT_EXTENSION_FAILURE_USER_MESSAGE = ("Prompt extension failed for this request.")
 
 
-def _resolve_generation_segment_cap(*, single_clip_mode: bool, cap: int) -> int:
-    return 0 if single_clip_mode else cap
+def _resolve_generation_segment_cap(*, single_clip_mode: bool, cap: int, manual_continuation_mode: bool = False) -> int:
+    # Steering (manual continuation) lets the user keep going indefinitely, like single-clip mode.
+    return 0 if (single_clip_mode or manual_continuation_mode) else cap

apps/dreamverse/dreamverse/video_generation.py

@@ -489,7 +489,7 @@ class VideoGenerationWorker:
             num_inference_steps=NUM_INFERENCE_STEPS,
             guidance_scale=1.0,
             seed=10,
-            ltx2_image_crf=0.0,
+            ltx2_image_crf=(33.0 if image_path and segment_idx == 1 else 0.0),
             image_path=image_path if segment_idx == 1 else None,
             return_continuation_state=False,
         )

apps/dreamverse/pyproject.toml

@@ -29,6 +29,9 @@ test = [
 dreamverse-server = "dreamverse.server_entry:cli"
 dreamverse-mock-server = "dreamverse.mock_server:cli"
 
+[tool.setuptools.packages.find]
+include = ["dreamverse*"]
+
 [tool.uv]
 package = false
 

apps/dreamverse/scripts/launch-dreamverse.sh

@@ -0,0 +1,67 @@
+#!/usr/bin/env bash
+# launch-dreamverse.sh — launch dreamverse-server on a compute node.
+#
+# Usage (from repo root):
+#   bash apps/dreamverse/scripts/launch-dreamverse.sh                          # GPUs 0-3, SP_SIZE=4
+#   CUDA_VISIBLE_DEVICES=0 bash apps/dreamverse/scripts/launch-dreamverse.sh   # single GPU, SP_SIZE=1
+
+set -euo pipefail
+
+CONDA_PREFIX="$HOME/miniconda3/envs/dreamverse"
+CUDA_RT_DIR="$CONDA_PREFIX/lib/python3.11/site-packages/nvidia/cuda_runtime/lib"
+GXX="$CONDA_PREFIX/bin/aarch64-conda-linux-gnu-g++"
+
+
+export CUDA_HOME="$CONDA_PREFIX"
+export FASTVIDEO_ENABLE_STARTUP_WARMUP=true
+export FASTVIDEO_ENABLE_PROMPT_SAFETY=false
+export DREAMVERSE_MAX_AUTOTUNE=true
+export LTX2_USE_DISTILLED_SIGMAS=0
+export LTX2_VIDEO_CONDITIONING_NUM_FRAMES=1
+export AUDIO_CONDITIONING_NUM_FRAMES=41
+export DREAMVERSE_SESSION_TIMEOUT_SECONDS="${DREAMVERSE_SESSION_TIMEOUT_SECONDS:-1800}"
+# GB200 max-autotune warmup compiles can run for hours; keep the watchdog generous here
+export FASTVIDEO_STARTUP_WARMUP_TIMEOUT_SECONDS="${FASTVIDEO_STARTUP_WARMUP_TIMEOUT_SECONDS:-24000}"
+export CEREBRAS_API_KEY="${CEREBRAS_API_KEY:-}"  # set this in your env or ~/.env
+export FASTVIDEO_PROMPT_CEREBRAS_MODEL="gpt-oss-120b"
+export TORCHINDUCTOR_CACHE_DIR="$HOME/.cache/torchinductor"
+export TRITON_CACHE_DIR="$HOME/.triton/cache"
+export TORCH_CUDA_ARCH_LIST="10.0a"
+
+# Compiler env (needed for flashinfer JIT compilation at server startup)
+export CXX="$CONDA_PREFIX/compiler_compat/g++"
+export CC="$CONDA_PREFIX/compiler_compat/gcc"
+export CUDAHOSTCXX="$GXX"
+export NVCC_PREPEND_FLAGS="-ccbin $GXX -allow-unsupported-compiler"
+
+# Link against libcudart.so.12 at JIT compile time; stubs for libcuda.so
+# cuda-compat has libcudart.so -> libcudart.so.12 (linker needs unversioned name)
+export LIBRARY_PATH="$CONDA_PREFIX/lib/cuda-compat:$CONDA_PREFIX/lib/stubs"
+
+# Only libcudart.so.12 at runtime — prevents cuDNN from seeing .so.13
+export LD_LIBRARY_PATH="$CUDA_RT_DIR"
+
+CUDA_VISIBLE_DEVICES="${CUDA_VISIBLE_DEVICES:-0,1,2,3}"
+export FASTVIDEO_GPU_COUNT="${FASTVIDEO_GPU_COUNT:-all}"
+# Default SP size to the usable GPU count so single-GPU invocations work.
+# A numeric FASTVIDEO_GPU_COUNT caps the pool below the visible count, and an
+# SP size above the pool size fails GPUPool startup with "Not enough GPUs".
+IFS=',' read -ra _VISIBLE_GPUS <<< "$CUDA_VISIBLE_DEVICES"
+# Count only non-empty tokens, matching gpu_pool.get_available_gpus (e.g. ",0,1" is 2 GPUs).
+_USABLE_GPU_COUNT=0
+for _gpu in "${_VISIBLE_GPUS[@]}"; do
+    [[ -n "${_gpu//[[:space:]]/}" ]] && _USABLE_GPU_COUNT=$((_USABLE_GPU_COUNT + 1))
+done
+if [[ "$FASTVIDEO_GPU_COUNT" =~ ^[0-9]+$ ]] && (( FASTVIDEO_GPU_COUNT < _USABLE_GPU_COUNT )); then
+    _USABLE_GPU_COUNT="$FASTVIDEO_GPU_COUNT"
+fi
+export DREAMVERSE_SP_SIZE="${DREAMVERSE_SP_SIZE:-$_USABLE_GPU_COUNT}"
+PORT="${DREAMVERSE_PORT:-8009}"
+
+FFMPEG_ENV="$(dirname "$0")/ffmpeg-env.sh"
+# shellcheck source=ffmpeg-env.sh
+[[ -f "$FFMPEG_ENV" ]] && source "$FFMPEG_ENV"
+
+echo "==> Launching dreamverse-server on GPU $CUDA_VISIBLE_DEVICES port $PORT"
+CUDA_VISIBLE_DEVICES="$CUDA_VISIBLE_DEVICES" \
+    "$CONDA_PREFIX/bin/dreamverse-server" --host 0.0.0.0 --port "$PORT"

apps/dreamverse/scripts/launch-frontend.sh

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+# launch-frontend.sh — start the Dreamverse Next.js dev server and ngrok tunnel.
+#
+# Usage (from repo root):
+#   bash apps/dreamverse/scripts/launch-frontend.sh
+#
+# Override backend or ngrok URL via env:
+#   BACKEND_HOST=1.2.3.4 bash apps/dreamverse/scripts/launch-frontend.sh
+
+set -euo pipefail
+
+CONDA_PREFIX="$HOME/miniconda3/envs/dreamverse"
+BACKEND_HOST="${BACKEND_HOST:-10.244.18.228}"
+BACKEND_PORT="${BACKEND_PORT:-8009}"
+NGROK_URL="${NGROK_URL:-ltx23.ngrok.app}"
+WEB_DIR="$(git rev-parse --show-toplevel)/apps/dreamverse/web"
+
+cleanup() {
+    echo "==> Shutting down..."
+    kill "$FRONTEND_PID" 2>/dev/null || true
+}
+trap cleanup EXIT
+
+echo "==> Starting frontend (backend: $BACKEND_HOST:$BACKEND_PORT)"
+BACKEND_HOST="$BACKEND_HOST" BACKEND_PORT="$BACKEND_PORT" \
+    npm run --prefix "$WEB_DIR" dev &
+FRONTEND_PID=$!
+
+echo "==> Starting ngrok tunnel -> $NGROK_URL"
+"$CONDA_PREFIX/bin/ngrok" http --url="$NGROK_URL" 5299

apps/dreamverse/scripts/setup-dreamverse-env.sh

@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+# setup-dreamverse-env.sh — create and configure the dreamverse conda env
+# from scratch on this aarch64 NFS Slurm cluster.
+#
+# Run from the login node (from the repo root):
+#   bash apps/dreamverse/scripts/setup-dreamverse-env.sh
+#
+# After this script completes, use launch-dreamverse.sh on a compute node.
+
+set -euo pipefail
+
+REPO_ROOT="$(git rev-parse --show-toplevel)"
+ENV_NAME="dreamverse"
+LOCAL_DIR="/mnt/local/hal-kevin"       # cache/pkgs — keep on local disk
+CONDA_PREFIX="$HOME/miniconda3/envs/$ENV_NAME"  # env — on shared NFS so it survives node changes
+
+echo "==> Removing existing env if present"
+conda env remove -p "$CONDA_PREFIX" -y 2>/dev/null || true
+rm -rf "$CONDA_PREFIX" 2>/dev/null || true
+
+echo "==> Creating conda env at $CONDA_PREFIX"
+CONDA_PKGS_DIRS="$LOCAL_DIR/conda/pkgs" conda create -p "$CONDA_PREFIX" python=3.11 -y
+
+GXX="$CONDA_PREFIX/bin/aarch64-conda-linux-gnu-g++"
+GCC="$CONDA_PREFIX/bin/aarch64-conda-linux-gnu-gcc"
+
+echo "==> Installing compiler"
+CONDA_PKGS_DIRS="$LOCAL_DIR/conda/pkgs" conda install -p "$CONDA_PREFIX" gxx_linux-aarch64 -y
+
+echo "==> Installing CUDA toolkit (nvcc + headers)"
+CONDA_PKGS_DIRS="$LOCAL_DIR/conda/pkgs" conda install -p "$CONDA_PREFIX" -c nvidia cuda-toolkit -y
+
+echo "==> Hiding conflicting libcudart.so.13 immediately"
+mkdir -p "$CONDA_PREFIX/lib/hidden"
+mv "$CONDA_PREFIX"/lib/libcudart.so* "$CONDA_PREFIX/lib/hidden/" 2>/dev/null || true
+
+echo "==> Fixing compiler_compat symlinks"
+mkdir -p "$CONDA_PREFIX/compiler_compat"
+ln -sf "$GXX" "$CONDA_PREFIX/compiler_compat/g++"
+ln -sf "$GCC" "$CONDA_PREFIX/compiler_compat/gcc"
+
+echo "==> Symlinking CUDA headers to standard location"
+for f in "$CONDA_PREFIX/targets/sbsa-linux/include/"*; do
+    ln -sf "$f" "$CONDA_PREFIX/include/$(basename "$f")" 2>/dev/null || true
+done
+
+echo "==> Installing ffmpeg (native build with x264 + NVENC)"
+CUDA_PREFIX="$CONDA_PREFIX" bash "$REPO_ROOT/apps/dreamverse/scripts/install_native_ffmpeg.sh"
+
+echo "==> Installing pip and uv"
+CONDA_PKGS_DIRS="$LOCAL_DIR/conda/pkgs" conda install -p "$CONDA_PREFIX" pip -y
+"$CONDA_PREFIX/bin/pip" install uv
+
+echo "==> Setting compiler env vars"
+export UV_CACHE_DIR="$LOCAL_DIR/cache"
+export UV_LINK_MODE=copy
+export CXX="$CONDA_PREFIX/compiler_compat/g++"
+export CC="$CONDA_PREFIX/compiler_compat/gcc"
+export CUDAHOSTCXX="$GXX"
+export NVCC_PREPEND_FLAGS="-ccbin $GXX -allow-unsupported-compiler"
+export CUDA_HOME="$CONDA_PREFIX"
+# Only build for GB200 (sm_100a); CUDA 13 dropped support for older archs
+export TORCH_CUDA_ARCH_LIST="10.0a"
+
+echo "==> Installing torch with CUDA 12.8"
+UV_CACHE_DIR="$LOCAL_DIR/cache" "$CONDA_PREFIX/bin/uv" pip install torch==2.11.0 torchvision \
+    --index-url https://download.pytorch.org/whl/cu128
+
+echo "==> Hiding any newly introduced libcudart.so.13"
+mv "$CONDA_PREFIX"/lib/libcudart.so* "$CONDA_PREFIX/lib/hidden/" 2>/dev/null || true
+
+# Set paths now that torch (and its nvidia packages) are installed
+CUDA_RT_DIR="$CONDA_PREFIX/lib/python3.11/site-packages/nvidia/cuda_runtime/lib"
+CUDA_RT_SO="$(ls "$CUDA_RT_DIR"/libcudart.so.* 2>/dev/null | head -1)"
+
+# The pip nvidia package only has libcudart.so.12 (versioned), not libcudart.so.
+# The linker needs the unversioned name to satisfy -lcudart. Create a compat dir.
+mkdir -p "$CONDA_PREFIX/lib/cuda-compat"
+ln -sf "$CUDA_RT_SO" "$CONDA_PREFIX/lib/cuda-compat/libcudart.so"
+
+export LIBRARY_PATH="$CONDA_PREFIX/lib/cuda-compat:$CONDA_PREFIX/lib/stubs"
+export CMAKE_ARGS="-DCUDA_CUDART_LIBRARY=$CUDA_RT_SO -DCUDA_INCLUDE_DIRS=$CONDA_PREFIX/targets/sbsa-linux/include"
+
+echo "==> Installing build tools"
+"$CONDA_PREFIX/bin/pip" install scikit-build-core cmake ninja
+
+echo "==> Initializing git submodules"
+cd "$REPO_ROOT"
+git submodule update --init fastvideo-kernel/include/cutlass fastvideo-kernel/include/tk
+
+echo "==> Building fastvideo-kernel from local source"
+UV_CACHE_DIR="$LOCAL_DIR/cache" "$CONDA_PREFIX/bin/uv" pip install \
+    -e "./fastvideo-kernel" --no-build-isolation
+
+echo "==> Installing fastvideo + dreamverse extras"
+UV_CACHE_DIR="$LOCAL_DIR/cache" "$CONDA_PREFIX/bin/uv" pip install \
+    -e ".[dreamverse]" --no-build-isolation
+
+echo "==> Installing flashinfer-python (pinned, must be last)"
+UV_CACHE_DIR="$LOCAL_DIR/cache" "$CONDA_PREFIX/bin/uv" pip install \
+    https://github.com/flashinfer-ai/flashinfer/releases/download/v0.6.11.post3/flashinfer_python-0.6.11.post3-py3-none-any.whl
+
+echo ""
+echo "Done. On a compute node run (GPUs 0-3 by default; set CUDA_VISIBLE_DEVICES to restrict):"
+echo "  bash apps/dreamverse/scripts/launch-dreamverse.sh"

apps/dreamverse/serve_configs/streaming_demo.yaml

@@ -110,7 +110,7 @@ default_request:
     fps: 24                  # internal: gpu_pool.py:85 TARGET_FPS
 
 streaming:
-  # internal: config.py:33 SESSION_TIMEOUT_SECONDS = 300
+  # internal: config.py SESSION_TIMEOUT_SECONDS (env DREAMVERSE_SESSION_TIMEOUT_SECONDS, default 300)
   session_timeout_seconds: 300
   # internal: config.py:282-284 GENERATION_SEGMENT_CAP default 6
   generation_segment_cap: 6

apps/dreamverse/web/src/app/page.tsx

@@ -9,7 +9,7 @@ import SessionTimeoutModal from "@/components/SessionTimeoutModal";
 import Sidebar from "@/components/Sidebar";
 import Header from "@/components/Header";
 import VideoPlayer from "@/components/VideoPlayer";
-import Workspace from "@/components/Workspace";
+import Workspace, { SceneHistoryList } from "@/components/Workspace";
 import { saveProject, saveProjectMetadata, listProjects, loadProjectClips, deleteProject, pruneOldProjects, type StoredProject, type StoredClip } from "@/lib/projectStorage";
 import { isInfrastructureError } from "@/lib/ws/reducer";
 import { useStore } from "@/hooks/useStore";
@@ -31,7 +31,7 @@ import { applyNormalizedSocketEvent } from "@/lib/ws/reducer";
 import { createPromptWindowStore } from "@/stores/promptWindow";
 import { createRewriteStore } from "@/stores/rewrite";
 import { createSessionStore } from "@/stores/session";
-import { createStreamStore } from "@/stores/stream";
+import { createStreamStore, USER_PROMPT_SOURCES } from "@/stores/stream";
 import { createUiStore } from "@/stores/ui";
 import { Button } from "@/components/ui/button";
 
@@ -80,7 +80,7 @@ function yieldToEventLoop(): Promise<void> {
 
 const HERO_WAVE_LIGHT = ["#2A4A98", "#4878E5", "#6FA0F2", "#B0BCC8", "#E8D99E", "#D8C844", "#C2A620"];
 const HERO_WAVE_DARK = ["#143468", "#1E58B8", "#3892F0", "#80B8E8", "#B8D0EA", "#E2D498", "#DABB50"];
-const HERO_TEXT = "Direct scenes in seconds";
+const HERO_TEXT = "Direct scenes in seconds with";
 
 function HeroTagline() {
 	const ref = useRef<HTMLHeadingElement>(null);
@@ -166,6 +166,8 @@ function HeroTagline() {
 					</span>
 				</Fragment>
 			))}
+			<span data-char className="transition-[color,filter] duration-150">{" "}</span>
+			<img src="/logo.svg" alt="FastVideo" className="inline-block h-[1.1em] w-auto align-middle" />
 		</h1>
 	);
 }
@@ -237,6 +239,7 @@ export default function Page() {
 		enhancementEnabled,
 		promptExtensionError,
 		autoExtensionEnabled,
+		manualContinuationMode,
 		autoExtensionTimeoutHint,
 		loopGenerationEnabled,
 		generationPaused,
@@ -249,6 +252,8 @@ export default function Page() {
 		livePromptRewriteMode,
 		sessionExpired,
 		projectResetPending,
+		waitingForSegmentPrompt,
+		generatingNextScene,
 	} = sessionState;
 
 	const {
@@ -323,6 +328,11 @@ export default function Page() {
 	const [ttffValueMs, setTtffValueMs] = useState<number | null>(null);
 	const ttffIntervalRef = useRef<ReturnType<typeof setInterval> | null>(null);
 	const pendingInitialPromptRef = useRef("");
+	// Prompt id the opening scene is recorded under; sent as initial_rollout_prompt_id
+	// so the backend's pre-seeded opening PromptSubmission emits status updates
+	// (prompt_enhancing/prompt_ready/prompt_fallback_used) against the same id.
+	const pendingInitialPromptIdRef = useRef("");
+	const [initialImageDataUrl, setInitialImageDataUrl] = useState("");
 	const lastArchivedReplayKeyRef = useRef("");
 	const [sidebarOpen, setSidebarOpen] = useState(false);
 	const [currentThumbnail, setCurrentThumbnail] = useState<string | null>(null);
@@ -422,6 +432,11 @@ export default function Page() {
 			if (String(e?.source || "") === "user_rewrite" && typeof e?.text === "string" && e.text.trim()) {
 				return e.text.trim();
 			}
+			// Steering opening: the backend overwrites text/source with the enhanced
+			// prompt once ready, so fall back to the stable rawText record.
+			if (e?.steeringUserPrompt && typeof e?.rawText === "string" && e.rawText.trim()) {
+				return e.rawText.trim();
+			}
 		}
 		return "Untitled project";
 	}, [selectedPreset, promptEvents]);
@@ -432,11 +447,39 @@ export default function Page() {
 	const canDownloadVideo = useMemo(() => {
 		const currentActiveClip = activeClip as Record<string, any> | null;
 		if (currentActiveClip?.blob instanceof Blob) return true;
-		return (completedClips as Record<string, any>[]).some((clip) => clip?.blob instanceof Blob);
-	}, [activeClip, completedClips]);
+		if ((completedClips as Record<string, any>[]).some((clip) => clip?.blob instanceof Blob)) return true;
+		// Steering only: once playback has started the live AV pipeline holds playable segments, so
+		// the user can download the in-progress video at any time (handleDownloadVideo remuxes live
+		// segments). Auto mode keeps its original blob-gated behavior.
+		return Boolean(manualContinuationMode) && Boolean(avPlaybackStarted);
+	}, [activeClip, completedClips, avPlaybackStarted, manualContinuationMode]);
+
+	// Steering mode scene list (oldest first). Primary source is the user's own words, captured
+	// stably at submit time as `rawText` (the backend later overwrites text/source with the
+	// enhanced prompt, so we never read those). A segment with no user prompt — e.g. a preset's
+	// opening scene — falls back to promptHistory (the actual prompt that drove that segment).
+	const steeringScenes = useMemo(() => {
+		if (!manualContinuationMode) return [] as Record<string, any>[];
+		const userScenes = (promptEvents as Record<string, any>[])
+			.filter((e) => e?.steeringUserPrompt && !e?.steeringFailed && typeof e?.rawText === "string" && e.rawText.trim())
+			.slice()
+			.reverse() // oldest -> newest
+			.map((e) => ({ id: e.promptId, prompt: e.rawText as string }));
+		const scenes: Record<string, any>[] = [];
+		// Preset opening segments: curated seeds with no user prompt of their own.
+		const curatedHists = (promptHistory as Record<string, any>[])
+			.slice()
+			.reverse() // oldest first
+			.filter((h) => !USER_PROMPT_SOURCES.has(String(h?.source || "")) && typeof h?.prompt === "string" && (h.prompt as string).trim());
+		scenes.push(...curatedHists.map((h) => ({ id: h.id || "scene_open", prompt: h.prompt })));
+		scenes.push(...userScenes);
+		return scenes;
+	}, [manualContinuationMode, promptEvents, promptHistory]);
 
 	const hasEdits = useMemo(
-		() => Boolean(sessionStarted) && (promptEvents as Record<string, any>[]).some((e) => typeof e?.text === "string" && e.text.trim() && String(e?.source || "").trim() === "user_rewrite"),
+		() => Boolean(sessionStarted) && (
+			(promptEvents as Record<string, any>[]).some((e) => typeof e?.text === "string" && e.text.trim() && String(e?.source || "").trim() === "user_rewrite")
+		),
 		[sessionStarted, promptEvents],
 	);
 
@@ -1421,7 +1464,8 @@ export default function Page() {
 		if (!prompt) return;
 		lastSubmitTimeRef.current = now;
 		const rCAR = !uiStore.get().devtoolsMode && !uiStore.get().demoMode;
-		if (rCAR || (sessionStore.get().livePromptRewriteMode && !uiStore.get().demoMode)) {
+		const inManualMode = sessionStore.get().manualContinuationMode;
+		if (!inManualMode && (rCAR || (sessionStore.get().livePromptRewriteMode && !uiStore.get().demoMode))) {
 			if (rewriteStore.get().rewritingSeedPrompts) return;
 			const rewriteSourcePromptWindowPrompts = getActivePromptWindowPrompts();
 			const nextPendingClip = {
@@ -1462,6 +1506,11 @@ export default function Page() {
 			status: "submitted",
 			source: "user_raw",
 			text: prompt,
+			// Stable record of the user's own words for the steering scene list. The backend
+			// later overwrites `text`/`source` with the enhanced prompt via prompt/ready, but
+			// these two fields are never touched by trackPromptEvent.
+			steeringUserPrompt: true,
+			rawText: prompt,
 		});
 		ws.send(
 			JSON.stringify({
@@ -1475,7 +1524,14 @@ export default function Page() {
 			activeClipId: shouldUseArchivedPlaybackFallback() ? streamStore.get().activeClipId : "",
 			activePlaybackStartTime: shouldUseArchivedPlaybackFallback() ? streamStore.get().activePlaybackStartTime : 0,
 		});
-		sessionStore.patch({ livePromptDraft: "" });
+		sessionStore.patch({
+			livePromptDraft: "",
+			waitingForSegmentPrompt: false,
+			sessionNotice: "",
+			// Light the "Generating next scene" overlay immediately on a real submit;
+			// stream/media_init (or a fallback/error) clears it.
+			...(inManualMode ? { generatingNextScene: true } : {}),
+		});
 	}
 
 	function setLivePromptRewriteMode(enabled: boolean) {
@@ -1550,6 +1606,14 @@ export default function Page() {
 		);
 	}
 
+	// Steering (manual continuation) vs the automatic 6-segment rollout — a pre-session
+	// preference honored when the session starts.
+	function handleManualContinuationToggle(event: any) {
+		sessionStore.patch({
+			manualContinuationMode: Boolean(event.currentTarget.checked),
+		});
+	}
+
 	function handleLoopGenerationToggle(event: any) {
 		sessionStore.patch({
 			loopGenerationEnabled: Boolean(event.currentTarget.checked),
@@ -1725,6 +1789,9 @@ export default function Page() {
 			sessionNotice: preserveSessionNotice ? sessionStore.get().sessionNotice : "",
 			sessionExpired: preserveSessionNotice ? sessionStore.get().sessionExpired : false,
 			projectResetPending: false,
+			manualContinuationMode: true,
+			waitingForSegmentPrompt: false,
+			generatingNextScene: false,
 		});
 		rewriteStore.resetSessionState();
 		streamStore.resetSessionState();
@@ -1737,6 +1804,7 @@ export default function Page() {
 	function resetToProjectLobbyState() {
 		setVideoMuted(true);
 		pendingInitialPromptRef.current = "";
+		pendingInitialPromptIdRef.current = "";
 		sessionStore.patch({
 			sessionStarted: false,
 			livePromptDraft: "",
@@ -1750,6 +1818,9 @@ export default function Page() {
 			sessionNotice: "",
 			sessionExpired: false,
 			projectResetPending: false,
+			manualContinuationMode: true,
+			waitingForSegmentPrompt: false,
+			generatingNextScene: false,
 		});
 		rewriteStore.resetSessionState();
 		streamStore.resetSessionState();
@@ -1760,7 +1831,14 @@ export default function Page() {
 	}
 
 	function buildProjectInitPayload(type: "session_init_v2" | "project_init_v1") {
-		const segmentPrompts = getSessionInitPrompts();
+		const manualMode = Boolean(sessionStore.get().manualContinuationMode);
+		let segmentPrompts = getSessionInitPrompts();
+		// Steering mode: seed the first 2 segments from the preset so there's no
+		// gap between segment 1 and 2; the user drives every subsequent segment.
+		// Force auto/loop off so the backend waits after the seeded prompts run out.
+		if (manualMode) {
+			segmentPrompts = segmentPrompts.slice(0, 2);
+		}
 		setSeedPrompts(segmentPrompts);
 		return {
 			type,
@@ -1768,11 +1846,17 @@ export default function Page() {
 			preset_label: getInitialPresetLabel(),
 			curated_prompts: segmentPrompts,
 			initial_rollout_prompt: normalizeInitialPrompt(pendingInitialPromptRef.current),
-			initial_image: null,
+			// Ties the backend's pre-seeded opening PromptSubmission to the prompt event
+			// recorded in beginProjectLocally so its status updates land on that record.
+			initial_rollout_prompt_id: pendingInitialPromptIdRef.current,
+			initial_image: initialImageDataUrl
+				? { data_url: initialImageDataUrl, mime_type: initialImageDataUrl.split(";")[0].split(":")[1] || "image/png", name: "upload.png" }
+				: null,
 			single_clip_mode: false,
 			enhancement_enabled: sessionStore.get().enhancementEnabled,
-			auto_extension_enabled: sessionStore.get().autoExtensionEnabled,
-			loop_generation_enabled: sessionStore.get().loopGenerationEnabled,
+			auto_extension_enabled: manualMode ? false : sessionStore.get().autoExtensionEnabled,
+			loop_generation_enabled: manualMode ? false : sessionStore.get().loopGenerationEnabled,
+			manual_continuation_mode: manualMode,
 		};
 	}
 
@@ -1951,7 +2035,11 @@ export default function Page() {
 		setCurrentThumbnail(null);
 		const initialPrompt = normalizeInitialPrompt(sessionStore.get().livePromptDraft as string);
 		pendingInitialPromptRef.current = initialPrompt;
+		setInitialImageDataUrl("");
 		const rCAR = !uiStore.get().devtoolsMode && !uiStore.get().demoMode;
+		// The "Steering mode" toggle is authoritative: checked = manual per-segment steering,
+		// unchecked = automatic 6-segment rollout (default).
+		const nextManualContinuationMode = Boolean(sessionStore.get().manualContinuationMode);
 		sessionStore.patch({
 			sessionNotice: "",
 			sessionExpired: false,
@@ -1966,6 +2054,9 @@ export default function Page() {
 			autoExtensionTimeoutHint: "",
 			generationPaused: false,
 			projectResetPending: false,
+			manualContinuationMode: nextManualContinuationMode,
+			waitingForSegmentPrompt: false,
+			generatingNextScene: false,
 		});
 		resetPlaybackState();
 		streamStore.patch({
@@ -1979,12 +2070,15 @@ export default function Page() {
 			selectedHistoryId: "",
 		});
 		rewriteStore.resetSessionState();
+		pendingInitialPromptIdRef.current = initialPrompt ? makePromptId() : "";
 		if (initialPrompt) {
 			addPromptEvent({
-				promptId: makePromptId(),
+				promptId: pendingInitialPromptIdRef.current,
 				status: "rewrite_requested",
 				source: "user_rewrite",
 				text: initialPrompt,
+				// In steering mode the typed opening is the user's Scene 1 — record it stably.
+				...(nextManualContinuationMode ? { steeringUserPrompt: true, rawText: initialPrompt } : {}),
 			});
 		}
 		setSeedPrompts(getSessionInitPrompts());
@@ -2500,6 +2594,7 @@ export default function Page() {
 				selectedPresetId={selectedPresetId as string}
 				enhancementEnabled={enhancementEnabled as boolean}
 				autoExtensionEnabled={autoExtensionEnabled as boolean}
+				manualContinuationEnabled={manualContinuationMode as boolean}
 				loopGenerationEnabled={loopGenerationEnabled as boolean}
 				canJoinSession={canJoinSession as boolean}
 				canSubmitContinuation={canSubmitContinuation}
@@ -2512,6 +2607,7 @@ export default function Page() {
 				onEnhancementToggle={handleEnhancementToggle}
 				onCuratedPromptLimitChange={handleCuratedPromptLimitChange}
 				onAutoExtensionToggle={handleAutoExtensionToggle}
+				onManualContinuationToggle={handleManualContinuationToggle}
 				onLoopToggle={handleLoopGenerationToggle}
 				onJoin={joinSession}
 				onLeave={leaveSession}
@@ -2641,6 +2737,7 @@ export default function Page() {
 			/>
 			<Header timeLeft={headerTimeLeft} formatTime={formatTime} onToggleSidebar={() => setSidebarOpen((prev) => !prev)} />
 
+			<div className={cn("flex flex-1 min-h-0 flex-col", sessionStarted && "pb-16 sm:pb-28")}>
 			<div className="relative flex flex-1 min-h-0 flex-col justify-center px-4 pb-2 sm:px-6 sm:pb-12">
 				{isViewingMode && (
 					<>
@@ -2724,6 +2821,8 @@ export default function Page() {
 									showLivePlayback={showLivePlayback}
 									defaultMuted={videoMuted}
 									canDownload={canDownloadVideo}
+									waitingForSegmentPrompt={waitingForSegmentPrompt as boolean}
+									generatingNextScene={generatingNextScene as boolean}
 									onPlaying={markFirstFrameRendered}
 									onDownload={handleDownloadVideo}
 								/>
@@ -2734,6 +2833,7 @@ export default function Page() {
 					<section className={cn("mx-auto w-full max-w-2xl", hasEdits && "flex-1 min-h-0 overflow-y-auto")}>
 						<Workspace
 							promptEvents={promptEvents as any[]}
+							manualMode={manualContinuationMode as boolean}
 							currentThumbnail={currentThumbnail}
 							originalLabel={pendingInitialPromptRef.current || (selectedPreset as Record<string, any>)?.label || ""}
 							sessionStarted={sessionStarted as boolean}
@@ -2780,11 +2880,17 @@ export default function Page() {
 							isGenerating={loadingAnimation as boolean}
 							storyPresets={storyPresets as any[]}
 							continuationDraft={livePromptDraft as string}
+							manualContinuationEnabled={manualContinuationMode as boolean}
+							onModeChange={(manual) => sessionStore.patch({ manualContinuationMode: manual })}
+							initialImageDataUrl={initialImageDataUrl}
+							onImageUpload={(dataUrl) => setInitialImageDataUrl(dataUrl)}
+							onImageClear={() => setInitialImageDataUrl("")}
 							canJoinSession={canStartSession}
 							canSubmitContinuation={canSubmitContinuation}
 							sessionExpired={sessionExpired as boolean}
 							sessionNotice={sessionNotice as string}
 							projectResetPending={projectResetPending as boolean}
+							waitingForSegmentPrompt={waitingForSegmentPrompt as boolean}
 							onPresetGenerate={handlePresetGenerate}
 							onContinuationInput={handleLivePromptInput}
 							onContinuationKeydown={handleLivePromptKeydown}
@@ -2798,6 +2904,12 @@ export default function Page() {
 					</motion.div>
 				</div>
 			</div>
+			{manualContinuationMode && (
+				<div className="px-4 sm:px-6">
+					<SceneHistoryList sceneHistory={steeringScenes as any[]} />
+				</div>
+			)}
+			</div>
 		</main>
 	);
 }

apps/dreamverse/web/src/components/ChatBar.tsx

@@ -2,13 +2,16 @@
 
 import React, { useRef, useState, useCallback, useEffect } from "react";
 import Image from "next/image";
-import { Film, ArrowUp, X, Loader2, ArrowLeft } from "lucide-react";
+import { Film, ArrowUp, X, Loader2, ArrowLeft, ImagePlus } from "lucide-react";
 import { Button } from "@/components/ui/button";
 import LeaveSessionModal, { shouldShowLeaveWarning } from "@/components/LeaveSessionModal";
 import SpeechToTextButton from "@/components/SpeechToTextButton";
 import { cn } from "@/lib/utils";
 
 const PROMPT_MAX_LENGTH = 500;
+// Must match backend session_init_image.py: MAX_SESSION_INIT_IMAGE_BYTES / SUPPORTED_SESSION_INIT_IMAGE_MIME_TYPES.
+const IMAGE_MAX_BYTES = 15 * 1024 * 1024;
+const IMAGE_ALLOWED_TYPES = ["image/png", "image/jpeg", "image/webp"];
 
 interface Props {
 	sessionStarted?: boolean;
@@ -22,6 +25,12 @@ interface Props {
 	sessionNotice?: string;
 	projectResetPending?: boolean;
 	viewingReadOnly?: boolean;
+	waitingForSegmentPrompt?: boolean;
+	manualContinuationEnabled?: boolean;
+	onModeChange?: (manual: boolean) => void;
+	initialImageDataUrl?: string;
+	onImageUpload?: (dataUrl: string, mimeType: string, name: string) => void;
+	onImageClear?: () => void;
 	onPresetGenerate?: (presetId: string) => void;
 	onContinuationInput?: (e: React.ChangeEvent<HTMLTextAreaElement>) => void;
 	onContinuationKeydown?: (e: React.KeyboardEvent<HTMLTextAreaElement>) => void;
@@ -46,6 +55,12 @@ export default function ChatBar({
 	sessionNotice = "",
 	projectResetPending = false,
 	viewingReadOnly = false,
+	waitingForSegmentPrompt = false,
+	manualContinuationEnabled = false,
+	onModeChange = () => {},
+	initialImageDataUrl = "",
+	onImageUpload = () => {},
+	onImageClear = () => {},
 	onPresetGenerate = () => {},
 	onContinuationInput = () => {},
 	onContinuationKeydown = () => {},
@@ -59,15 +74,51 @@ export default function ChatBar({
 }: Props) {
 	const [sttBusy, setSttBusy] = useState(false);
 	const [leaveModalOpen, setLeaveModalOpen] = useState(false);
+	const [imageError, setImageError] = useState("");
+	const fileInputRef = useRef<HTMLInputElement>(null);
+
+	const processImageFile = useCallback((file: File) => {
+		if (!IMAGE_ALLOWED_TYPES.includes(file.type)) {
+			setImageError("Unsupported image type. Use a PNG, JPEG, or WebP image.");
+			return;
+		}
+		if (file.size > IMAGE_MAX_BYTES) {
+			setImageError("Image is too large. The maximum size is 15MB.");
+			return;
+		}
+		const reader = new FileReader();
+		reader.onload = (e) => {
+			const dataUrl = e.target?.result as string;
+			if (dataUrl) {
+				setImageError("");
+				onImageUpload(dataUrl, file.type, file.name);
+			}
+		};
+		reader.onerror = () => {
+			setImageError("Could not read the image file. Please try again.");
+		};
+		reader.readAsDataURL(file);
+	}, [onImageUpload]);
+
+	const handleImagePaste = useCallback((e: React.ClipboardEvent) => {
+		if (sessionStarted) return;
+		const items = Array.from(e.clipboardData?.items ?? []);
+		const imageItem = items.find((item) => item.type.startsWith("image/"));
+		if (!imageItem) return;
+		const file = imageItem.getAsFile();
+		if (file) processImageFile(file);
+	}, [sessionStarted, processImageFile]);
 	const showSpinner = isGenerating || rewritingSeedPrompts;
 	const isBusy = isGenerating || rewritingSeedPrompts || projectResetPending;
 	const messagePlaceholder = projectResetPending
 		? "Starting new project\u2026"
 		: isBusy
 			? "Generating video\u2026"
-			: !sessionStarted
-				? "What video are you imagining?"
-				: "What do you want to edit?";
+			: waitingForSegmentPrompt
+				? "Describe the next scene\u2026"
+				: !sessionStarted
+					? "What video are you imagining?"
+					: "What do you want to edit?";
 	const actionLabel = !sessionStarted ? "Generate" : "Rewrite rollout";
 
 	const inputRef = useRef<HTMLTextAreaElement>(null);
@@ -267,9 +318,9 @@ export default function ChatBar({
 						<Button onClick={onStartNewProject} size="sm" className="rounded-full px-5">
 							New Project
 						</Button>
-						<a href="https://docs.google.com/forms/d/e/1FAIpQLSe5zpO1iD8Ds-Ih-fOLm64qd7YZVvuvAyHuJaAfw1hkRHTe_A/viewform?usp=publish-editor" target="_blank" rel="noopener noreferrer">
+						<a href="https://haoailab.com/blogs/dreamverse/" target="_blank" rel="noopener noreferrer">
 							<Button variant="outline" size="sm" className="rounded-full px-5">
-								Join Waitlist
+								Blog
 							</Button>
 						</a>
 					</div>
@@ -346,6 +397,31 @@ export default function ChatBar({
 				</div>
 			)}
 
+
+			{!sessionStarted && imageError && (
+				<div className="rounded-xl border border-rose-500/20 bg-rose-500/10 px-4 py-2.5 text-center text-xs text-rose-700 dark:text-rose-300">
+					{imageError}
+				</div>
+			)}
+
+			{!sessionStarted && initialImageDataUrl && (
+				<div className="flex items-center gap-2 rounded-2xl border border-input bg-card/65 px-3 py-2">
+					<img src={initialImageDataUrl} alt="Initial frame" className="h-12 w-12 rounded-lg object-cover" />
+					<span className="flex-1 truncate text-xs text-muted-foreground">Starting image set</span>
+					<button type="button" onClick={() => { setImageError(""); onImageClear(); }} className="text-muted-foreground hover:text-foreground transition-colors">
+						<X className="size-4" />
+					</button>
+				</div>
+			)}
+
+			<input
+				ref={fileInputRef}
+				type="file"
+				accept={IMAGE_ALLOWED_TYPES.join(",")}
+				className="hidden"
+				onChange={(e) => { const f = e.target.files?.[0]; if (f) processImageFile(f); e.target.value = ""; }}
+			/>
+
 			<div
 				className={cn(
 					"flex min-w-0 items-center gap-1.5 rounded-4xl border py-2.5 pl-5 pr-2.5 shadow-md backdrop-blur-sm transition-all duration-200",
@@ -359,6 +435,7 @@ export default function ChatBar({
 					value={continuationDraft}
 					onChange={onContinuationInput}
 					onKeyDown={handleKeyDown}
+					onPaste={handleImagePaste}
 					placeholder={sttBusy ? "Listening\u2026" : messagePlaceholder}
 					maxLength={PROMPT_MAX_LENGTH}
 					disabled={isBusy || sttBusy}
@@ -369,6 +446,19 @@ export default function ChatBar({
 					)}
 				/>
 				{onSpeechTranscript && <SpeechToTextButton disabled={isBusy} onTranscript={onSpeechTranscript} onInterimChange={onSpeechInterimChange} onBusyChange={setSttBusy} />}
+				{!sessionStarted && (
+					<Button
+						type="button"
+						variant="ghost"
+						size="icon-sm"
+						title="Add starting image"
+						onClick={() => fileInputRef.current?.click()}
+						disabled={isBusy}
+						className="shrink-0 rounded-full text-muted-foreground hover:text-foreground"
+					>
+						<ImagePlus className="size-4" />
+					</Button>
+				)}
 				{!sessionStarted ? (
 					<Button
 						aria-label={actionLabel}

apps/dreamverse/web/src/components/Header.tsx

@@ -8,7 +8,6 @@ import { Badge } from "@/components/ui/badge";
 import { Button } from "@/components/ui/button";
 import { ThemeToggle } from "@/components/ui/theme-toggle";
 
-const FASTVIDEO_REPO_URL = "https://haoailab.com/blogs/dreamverse/";
 const FASTVIDEO_BLOG_URL = "https://haoailab.com/blogs/dreamverse/";
 
 interface Props {
@@ -29,13 +28,13 @@ export default function Header({ timeLeft = null, formatTime = (seconds) => `${s
 							<SidePanelOpenFilled size={20} />
 						</Button>
 					)}
-					<a href={FASTVIDEO_REPO_URL} target="_blank" rel="noopener noreferrer" title="FastVideo on GitHub">
+					<a href="/" title="FastVideo home">
 						<Image src="/logo.svg" alt="FastVideo" width={32} height={32} className="h-8 w-auto sm:h-9 transition-opacity hover:opacity-70" />
 					</a>
 					<div className="hidden sm:flex items-center gap-3">
-						<a href="https://docs.google.com/forms/d/e/1FAIpQLSe5zpO1iD8Ds-Ih-fOLm64qd7YZVvuvAyHuJaAfw1hkRHTe_A/viewform?usp=publish-editor" target="_blank" rel="noopener noreferrer">
+						<a href={FASTVIDEO_BLOG_URL} target="_blank" rel="noopener noreferrer">
 							<Button variant="outline" size="sm" className="gap-1.5 rounded-full px-3 text-xs">
-								Join Waitlist
+								Blog
 								<ExternalLink className="size-3 opacity-60" />
 							</Button>
 						</a>
@@ -53,9 +52,9 @@ export default function Header({ timeLeft = null, formatTime = (seconds) => `${s
 			</div>
 
 			<div className="flex sm:hidden items-center gap-2 px-4 pb-3">
-				<a href="https://docs.google.com/forms/d/e/1FAIpQLSe5zpO1iD8Ds-Ih-fOLm64qd7YZVvuvAyHuJaAfw1hkRHTe_A/viewform?usp=publish-editor" target="_blank" rel="noopener noreferrer">
+				<a href={FASTVIDEO_BLOG_URL} target="_blank" rel="noopener noreferrer">
 					<Button variant="outline" size="sm" className="gap-1.5 rounded-full px-3 text-xs">
-						Join Waitlist
+						Blog
 						<ExternalLink className="size-3 opacity-60" />
 					</Button>
 				</a>

apps/dreamverse/web/src/components/VideoPlayer.tsx

@@ -3,7 +3,7 @@
 import React, { useState, useEffect, useRef, useCallback } from "react";
 import { cn } from "@/lib/utils";
 import { PlayFilledAlt } from "@carbon/icons-react";
-import { Download, Loader2, Share } from "lucide-react";
+import { Check, ChevronDown, Download, Loader2, Share } from "lucide-react";
 import { Button } from "@/components/ui/button";
 interface VideoPlayerProps {
 	videoRef?: React.RefCallback<HTMLVideoElement>;
@@ -21,6 +21,8 @@ interface VideoPlayerProps {
 	showLivePlayback?: boolean;
 	defaultMuted?: boolean;
 	rewritePending?: boolean;
+	waitingForSegmentPrompt?: boolean;
+	generatingNextScene?: boolean;
 	onPlaying?: () => void;
 	onDownload?: () => void;
 }
@@ -57,6 +59,8 @@ export default function VideoPlayer({
 	showLivePlayback = true,
 	defaultMuted = true,
 	rewritePending = false,
+	waitingForSegmentPrompt = false,
+	generatingNextScene = false,
 	onPlaying = () => {},
 	onDownload,
 }: VideoPlayerProps) {
@@ -88,6 +92,137 @@ export default function VideoPlayer({
 		setCanShare(typeof navigator.canShare === "function" && window.matchMedia("(pointer: coarse)").matches);
 	}, []);
 
+	// Steering mode: the backend may signal "waiting for next prompt" while the current
+	// segment is still PLAYING (it generates ahead). Only surface the "Segment complete"
+	// overlay once the playhead actually reaches the end of the buffered segment.
+	const [playbackReachedEnd, setPlaybackReachedEnd] = useState(false);
+	// Steering mode: when the user submits the next scene, the segment is generated
+	// (a few seconds of latency) before frames stream. Show a "Generating next scene…"
+	// indicator across that gap so the frozen frame isn't silent. Driven by the explicit
+	// generatingNextScene state (set on scene submit / prompt selection), never inferred
+	// from waitingForSegmentPrompt edges.
+	const [generatingNext, setGeneratingNext] = useState(false);
+	// End of the buffered timeline captured the moment generation starts; the freshly
+	// generated segment extends the buffer past this, which is how we know it landed.
+	const genBoundaryRef = useRef(0);
+
+	// Steering mode: the backend may signal "waiting for next prompt" while the current
+	// segment is still PLAYING (it generates ahead). Track whether the playhead has reached
+	// the end of the buffered segment so end-overlays only show there. Keep tracking through
+	// the generating phase too, so scrubbing back and replaying to the end re-shows them.
+	useEffect(() => {
+		if (!waitingForSegmentPrompt && !generatingNext) {
+			setPlaybackReachedEnd(false);
+			return;
+		}
+		const el = liveVideoEl.current;
+		if (!el) return;
+		const check = () => {
+			try {
+				const buffered = el.buffered;
+				if (buffered.length === 0) return;
+				const end = buffered.end(buffered.length - 1);
+				// Track proximity both ways: scrubbing back off the end hides the overlay,
+				// playing forward to the end re-shows it.
+				setPlaybackReachedEnd(el.ended || end - el.currentTime <= 0.2);
+			} catch {
+				/* buffered access can throw mid-append */
+			}
+		};
+		check();
+		el.addEventListener("timeupdate", check);
+		el.addEventListener("ended", check);
+		el.addEventListener("waiting", check);
+		el.addEventListener("stalled", check);
+		el.addEventListener("pause", check);
+		el.addEventListener("seeking", check);
+		el.addEventListener("seeked", check);
+		el.addEventListener("playing", check);
+		el.addEventListener("progress", check);
+		return () => {
+			el.removeEventListener("timeupdate", check);
+			el.removeEventListener("ended", check);
+			el.removeEventListener("waiting", check);
+			el.removeEventListener("stalled", check);
+			el.removeEventListener("pause", check);
+			el.removeEventListener("seeking", check);
+			el.removeEventListener("seeked", check);
+			el.removeEventListener("playing", check);
+			el.removeEventListener("progress", check);
+		};
+	}, [waitingForSegmentPrompt, generatingNext]);
+
+	useEffect(() => {
+		if (waitingForSegmentPrompt || !sessionStarted) {
+			// Back to waiting (or session over): nothing is generating.
+			setGeneratingNext(false);
+			return;
+		}
+		if (!generatingNextScene) return;
+		// Snapshot the current end of the buffered timeline; the generated segment will
+		// extend the buffer past this boundary.
+		const el = liveVideoEl.current;
+		let boundary = el?.currentTime ?? 0;
+		try {
+			const b = el?.buffered;
+			if (b && b.length) boundary = Math.max(boundary, b.end(b.length - 1));
+		} catch {
+			/* buffered access can throw mid-append */
+		}
+		genBoundaryRef.current = boundary;
+		setGeneratingNext(true);
+	}, [generatingNextScene, waitingForSegmentPrompt, sessionStarted]);
+
+	useEffect(() => {
+		if (!generatingNext) return;
+		if (!sessionStarted) {
+			setGeneratingNext(false);
+			return;
+		}
+		const el = liveVideoEl.current;
+		if (!el) return;
+		// Clear the instant the freshly generated segment lands: the buffer grows past the
+		// boundary captured at generation start (or the playhead advances into the new
+		// frames). Deliberately NOT a bare "playing" handler — scrubbing back and replaying
+		// the EXISTING segment must keep "Generating" up until the new frames actually arrive.
+		const check = () => {
+			try {
+				const b = el.buffered;
+				const end = b.length ? b.end(b.length - 1) : 0;
+				if (end > genBoundaryRef.current + 0.25 || el.currentTime > genBoundaryRef.current + 0.1) {
+					setGeneratingNext(false);
+				}
+			} catch {
+				/* buffered access can throw mid-append */
+			}
+		};
+		check();
+		el.addEventListener("progress", check);
+		el.addEventListener("timeupdate", check);
+		el.addEventListener("durationchange", check);
+		return () => {
+			el.removeEventListener("progress", check);
+			el.removeEventListener("timeupdate", check);
+			el.removeEventListener("durationchange", check);
+		};
+	}, [generatingNext, sessionStarted]);
+
+	// Drive a ~10.5s progress bar during generation so the wait has a visible ETA.
+	const GEN_DURATION_MS = 10500;
+	const [genProgress, setGenProgress] = useState(0);
+	useEffect(() => {
+		if (!generatingNext) {
+			setGenProgress(0);
+			return;
+		}
+		const start = performance.now();
+		setGenProgress(0);
+		const id = setInterval(() => {
+			setGenProgress(Math.min((performance.now() - start) / GEN_DURATION_MS, 1));
+		}, 50);
+		return () => clearInterval(id);
+	}, [generatingNext]);
+
 	return (
 		<div className="mx-auto w-full max-w-3xl mb-2 sm:mb-6">
 			<div className="rounded-2xl border border-border bg-card/50 p-2 shadow-lg backdrop-blur-md">
@@ -104,7 +239,7 @@ export default function VideoPlayer({
 								<PlayFilledAlt className="size-10 text-white/25" />
 								<p className="text-sm text-white/50">Your video will appear here</p>
 							</div>
-						) : !avPlaybackStarted && !mediaAppendError && !inQueue && loadingAnimation ? (
+						) : !avPlaybackStarted && !mediaAppendError && !inQueue && !waitingForSegmentPrompt && loadingAnimation ? (
 							<div className="absolute inset-0 flex flex-col items-center justify-center gap-4 bg-slate-900/60 p-4 backdrop-blur-[2px]">
 								<div className="pointer-events-none absolute inset-0 overflow-hidden">
 									<div className="absolute inset-0 -translate-x-full animate-[shimmer_3s_ease-in-out_infinite] bg-gradient-to-r from-transparent via-white/[0.04] to-transparent" />
@@ -114,6 +249,35 @@ export default function VideoPlayer({
 							</div>
 						) : null}
 
+						{/* Steering mode: this segment finished — wait gracefully for the user's next scene
+							instead of spinning. The last frame stays visible behind a soft bottom gradient. */}
+						{sessionStarted && waitingForSegmentPrompt && playbackReachedEnd && !mediaAppendError && !inQueue && (
+							<div className="pointer-events-none absolute inset-0 flex flex-col items-center justify-end gap-2 bg-gradient-to-t from-slate-950/85 via-slate-950/15 to-transparent p-5 pb-6 text-center">
+								<div className="flex size-9 items-center justify-center rounded-full border border-white/25 bg-white/10 shadow-lg backdrop-blur-md">
+									<Check className="size-4 text-white/90" />
+								</div>
+								<div className="space-y-0.5">
+									<p className="text-sm font-medium text-white/95">Segment complete</p>
+									<p className="text-xs text-white/65">Describe the next scene below to keep going</p>
+								</div>
+								<ChevronDown className="size-4 animate-bounce text-white/45" />
+							</div>
+						)}
+
+						{/* Steering mode: generating the next segment — show a ~10.5s progress bar so the wait has an ETA.
+							Gated on playbackReachedEnd like "Segment complete": scrubbing back hides it, playing to the end re-shows it. */}
+						{sessionStarted && generatingNext && playbackReachedEnd && !mediaAppendError && !inQueue && (
+							<div className="pointer-events-none absolute inset-0 flex flex-col items-center justify-end gap-3 bg-gradient-to-t from-slate-950/85 via-slate-950/15 to-transparent p-5 pb-7 text-center">
+								<p className="text-sm font-medium text-white/95">Generating next scene&hellip;</p>
+								<div className="h-1.5 w-48 overflow-hidden rounded-full bg-white/15 shadow-sm">
+									<div
+										className="h-full rounded-full bg-white/85 transition-[width] duration-100 ease-linear"
+										style={{ width: `${Math.round(genProgress * 100)}%` }}
+									/>
+								</div>
+							</div>
+						)}
+
 						{rewritePending && avPlaybackStarted && (
 							<div className="absolute inset-x-0 bottom-0 z-10 flex items-center justify-center gap-2 bg-gradient-to-t from-black/60 to-transparent px-4 pb-12 pt-8 pointer-events-none">
 								<Loader2 className="size-4 animate-spin text-white/90" />

apps/dreamverse/web/src/components/Workspace.tsx

@@ -3,11 +3,90 @@ import React, { useRef, useMemo, useEffect, useCallback, useState } from "react"
 import { motion, useAnimationControls } from "framer-motion";
 import { Badge } from "@/components/ui/badge";
 import { cn } from "@/lib/utils";
-import { Check, Lightbulb, Pencil } from "lucide-react";
+import { Check, Clapperboard, Lightbulb, Pencil } from "lucide-react";
 
 export const WORKSPACE_ORIGINAL_SELECTION_KEY = "original";
 export const WORKSPACE_CURRENT_SELECTION_KEY = "current";
 
+export function SceneHistoryList({ sceneHistory = [] }: { sceneHistory?: Record<string, any>[] }) {
+	const bottomSentinelRef = useRef<HTMLDivElement>(null);
+	const topSentinelRef = useRef<HTMLDivElement>(null);
+	const [showTopFade, setShowTopFade] = useState(false);
+
+	const scenes = useMemo(
+		() => (sceneHistory || []).filter((s) => normalizeText(s?.prompt)),
+		[sceneHistory],
+	);
+
+	const scrollToBottom = useCallback(() => {
+		setTimeout(() => {
+			bottomSentinelRef.current?.scrollIntoView({ block: "end", behavior: "smooth" });
+		}, 60);
+	}, []);
+
+	useEffect(() => {
+		if (scenes.length > 0) scrollToBottom();
+	}, [scenes.length, scrollToBottom]);
+
+	useEffect(() => {
+		const sentinel = bottomSentinelRef.current;
+		if (!sentinel || typeof ResizeObserver === "undefined") return;
+		let container: HTMLElement | null = sentinel.parentElement;
+		while (container) {
+			const oy = getComputedStyle(container).overflowY;
+			if (oy === "auto" || oy === "scroll") break;
+			container = container.parentElement;
+		}
+		if (!container) return;
+		const ro = new ResizeObserver(() => {
+			const nearBottom = container!.scrollHeight - container!.scrollTop - container!.clientHeight < 96;
+			if (nearBottom) scrollToBottom();
+		});
+		ro.observe(container);
+		return () => ro.disconnect();
+	}, [scenes.length, scrollToBottom]);
+
+	useEffect(() => {
+		const el = topSentinelRef.current;
+		if (!el) return;
+		const observer = new IntersectionObserver(([entry]) => setShowTopFade(!entry.isIntersecting), { threshold: 0.1 });
+		observer.observe(el);
+		return () => observer.disconnect();
+	}, [scenes.length]);
+
+	if (scenes.length === 0) return null;
+
+	return (
+		<section className="relative z-10 flex flex-col mx-auto w-full max-w-2xl max-h-32 overflow-y-auto">
+			<div
+				className={cn(
+					"pointer-events-none sticky top-0 z-20 -mb-12 h-12 bg-linear-to-b from-background to-transparent transition-opacity duration-200",
+					showTopFade ? "opacity-100" : "opacity-0",
+				)}
+				aria-hidden="true"
+			/>
+			<div ref={topSentinelRef} className="h-0 w-0" aria-hidden="true" />
+			<div className="flex flex-col gap-2 pt-12 pb-4">
+				{scenes.map((scene, index) => (
+					<div
+						key={scene.id || index}
+						className="flex items-start gap-3 rounded-xl p-3 transition-colors duration-200 hover:bg-slate-200/50 hover:dark:bg-slate-800/30"
+					>
+						<div className="flex min-w-0 flex-1 flex-col gap-2">
+							<Badge variant="secondary" className="horizontal gap-2 items-center w-fit">
+								<Clapperboard className="size-3 opacity-70" />
+								{`Scene ${index + 1}`}
+							</Badge>
+							<p className="line-clamp-2 text-sm leading-5 text-muted-foreground">{scene.prompt}</p>
+						</div>
+					</div>
+				))}
+			</div>
+			<div ref={bottomSentinelRef} className="h-0 w-0" aria-hidden="true" />
+		</section>
+	);
+}
+
 interface WorkspaceProps {
 	promptEvents?: Record<string, any>[];
 	currentThumbnail?: string | null;
@@ -19,6 +98,7 @@ interface WorkspaceProps {
 	selectedClipId?: string;
 	selectedEntryKey?: string;
 	originalClipId?: string;
+	manualMode?: boolean;
 }
 
 function normalizeText(value: any): string {
@@ -218,7 +298,7 @@ function ChromaGradient({ sessionStarted = false }: { sessionStarted?: boolean }
 	);
 }
 
-export default function Workspace({ promptEvents = [], currentThumbnail = null, originalLabel = "", sessionStarted = false, onSelectOriginal, onSelectEvent, onSelectCurrent, selectedClipId, selectedEntryKey: selectedEntryKeyProp, originalClipId = "" }: WorkspaceProps) {
+export default function Workspace({ promptEvents = [], currentThumbnail = null, originalLabel = "", sessionStarted = false, onSelectOriginal, onSelectEvent, onSelectCurrent, selectedClipId, selectedEntryKey: selectedEntryKeyProp, originalClipId = "", manualMode = false }: WorkspaceProps) {
 	const bottomSentinelRef = useRef<HTMLDivElement>(null);
 	const topSentinelRef = useRef<HTMLDivElement>(null);
 	const [showTopFade, setShowTopFade] = useState(false);
@@ -259,6 +339,14 @@ export default function Workspace({ promptEvents = [], currentThumbnail = null,
 		return () => observer.disconnect();
 	}, [conversationEvents.length]);
 
+	if (manualMode) {
+		return (
+			<div className="mt-auto flex flex-col">
+				<ChromaGradient sessionStarted={sessionStarted} />
+			</div>
+		);
+	}
+
 	return (
 		<div className="mt-auto flex flex-col">
 			<ChromaGradient sessionStarted={sessionStarted} />

apps/dreamverse/web/src/components/devtools/DevtoolsComposer.tsx

@@ -34,6 +34,7 @@ interface DevtoolsComposerProps {
   demoMode?: boolean;
   enhancementEnabled?: boolean;
   autoExtensionEnabled?: boolean;
+  manualContinuationEnabled?: boolean;
   loopGenerationEnabled?: boolean;
   curatedPromptLimit?: number;
   maxCuratedPromptCount?: number;
@@ -49,6 +50,7 @@ interface DevtoolsComposerProps {
   onEnhancementToggle?: (e: React.ChangeEvent<HTMLInputElement>) => void;
   onCuratedPromptLimitChange?: (e: React.ChangeEvent<HTMLInputElement>) => void;
   onAutoExtensionToggle?: (e: React.ChangeEvent<HTMLInputElement>) => void;
+  onManualContinuationToggle?: (e: React.ChangeEvent<HTMLInputElement>) => void;
   onLoopToggle?: (e: React.ChangeEvent<HTMLInputElement>) => void;
   onLivePromptModeToggle?: (e: React.ChangeEvent<HTMLInputElement>) => void;
   onSpeechTranscript?: (text: string) => void;
@@ -71,6 +73,7 @@ export default function DevtoolsComposer({
   demoMode = false,
   enhancementEnabled = true,
   autoExtensionEnabled = false,
+  manualContinuationEnabled = false,
   loopGenerationEnabled = false,
   curatedPromptLimit = 0,
   maxCuratedPromptCount = 0,
@@ -86,6 +89,7 @@ export default function DevtoolsComposer({
   onEnhancementToggle = () => {},
   onCuratedPromptLimitChange = () => {},
   onAutoExtensionToggle = () => {},
+  onManualContinuationToggle = () => {},
   onLoopToggle = () => {},
   onLivePromptModeToggle = () => {},
   onSpeechTranscript,
@@ -328,6 +332,28 @@ export default function DevtoolsComposer({
                   </div>
                 </div>
 
+                <div className="flex items-start gap-3">
+                  <Checkbox
+                    id="devtools-steering-mode"
+                    checked={manualContinuationEnabled}
+                    onCheckedChange={(checked) =>
+                      onManualContinuationToggle({
+                        target: { checked: Boolean(checked) },
+                        currentTarget: { checked: Boolean(checked) },
+                      } as React.ChangeEvent<HTMLInputElement>)
+                    }
+                  />
+                  <div className="space-y-1">
+                    <Label htmlFor="devtools-steering-mode">
+                      Steering mode
+                    </Label>
+                    <p className="text-sm text-muted-foreground">
+                      Drive each segment manually — type the next scene to
+                      continue (vs the automatic 6-segment rollout).
+                    </p>
+                  </div>
+                </div>
+
                 <div className="flex items-start gap-3">
                   <Checkbox
                     id="devtools-loop-generation"

apps/dreamverse/web/src/components/devtools/DevtoolsShell.tsx

@@ -21,6 +21,7 @@ interface DevtoolsShellProps {
   selectedPresetId?: string;
   enhancementEnabled?: boolean;
   autoExtensionEnabled?: boolean;
+  manualContinuationEnabled?: boolean;
   loopGenerationEnabled?: boolean;
   canJoinSession?: boolean;
   canSubmitContinuation?: boolean;
@@ -34,6 +35,7 @@ interface DevtoolsShellProps {
   onEnhancementToggle?: (e: React.ChangeEvent<HTMLInputElement>) => void;
   onCuratedPromptLimitChange?: (e: React.ChangeEvent<HTMLInputElement>) => void;
   onAutoExtensionToggle?: (e: React.ChangeEvent<HTMLInputElement>) => void;
+  onManualContinuationToggle?: (e: React.ChangeEvent<HTMLInputElement>) => void;
   onLoopToggle?: (e: React.ChangeEvent<HTMLInputElement>) => void;
   onJoin?: () => void;
   onLeave?: () => void;
@@ -128,6 +130,7 @@ export default function DevtoolsShell({
   selectedPresetId = '',
   enhancementEnabled = true,
   autoExtensionEnabled = false,
+  manualContinuationEnabled = false,
   loopGenerationEnabled = false,
   canJoinSession = false,
   canSubmitContinuation = false,
@@ -141,6 +144,7 @@ export default function DevtoolsShell({
   onEnhancementToggle = () => {},
   onCuratedPromptLimitChange = () => {},
   onAutoExtensionToggle = () => {},
+  onManualContinuationToggle = () => {},
   onLoopToggle = () => {},
   onJoin = () => {},
   onLeave = () => {},
@@ -284,6 +288,7 @@ export default function DevtoolsShell({
           demoMode={demoMode}
           enhancementEnabled={enhancementEnabled}
           autoExtensionEnabled={autoExtensionEnabled}
+          manualContinuationEnabled={manualContinuationEnabled}
           loopGenerationEnabled={loopGenerationEnabled}
           curatedPromptLimit={curatedPromptLimit}
           maxCuratedPromptCount={maxCuratedPromptCount}
@@ -299,6 +304,7 @@ export default function DevtoolsShell({
           onEnhancementToggle={onEnhancementToggle}
           onCuratedPromptLimitChange={onCuratedPromptLimitChange}
           onAutoExtensionToggle={onAutoExtensionToggle}
+          onManualContinuationToggle={onManualContinuationToggle}
           onLoopToggle={onLoopToggle}
           onLivePromptModeToggle={onLivePromptModeToggle}
           onSpeechTranscript={onSpeechTranscript}

apps/dreamverse/web/src/lib/promptEvents.test.ts

@@ -57,4 +57,32 @@ describe('prependPromptEvent', () => {
     expect(next[0].promptId).toBe('new');
     expect(next.some((item: any) => item.promptId === 'p-23')).toBe(false);
   });
+
+  it('never drops steering scene events when capping', () => {
+    // 30 scenes interleaved with 30 other events — well past the cap.
+    let events: Record<string, any>[] = [];
+    for (let i = 0; i < 30; i += 1) {
+      events = prependPromptEvent(events, {
+        promptId: `scene-${i}`,
+        status: 'submitted',
+        steeringUserPrompt: true,
+        rawText: `scene ${i}`,
+      });
+      events = prependPromptEvent(events, {
+        promptId: `other-${i}`,
+        status: 'submitted',
+      });
+    }
+
+    const scenes = events.filter((e) => e.steeringUserPrompt);
+    expect(scenes).toHaveLength(30);
+    // Oldest-first scene order (and therefore numbering) is stable and complete.
+    expect(scenes[scenes.length - 1].promptId).toBe('scene-0');
+    expect(scenes[0].promptId).toBe('scene-29');
+    // Non-scene events are still capped, oldest dropped first.
+    const others = events.filter((e) => !e.steeringUserPrompt);
+    expect(others.length).toBeLessThanOrEqual(24);
+    expect(others.some((e) => e.promptId === 'other-0')).toBe(false);
+    expect(others[0].promptId).toBe('other-29');
+  });
 });

apps/dreamverse/web/src/lib/promptEvents.ts

@@ -16,5 +16,19 @@ export function prependPromptEvent(
   events: Record<string, any>[],
   event: Record<string, any>,
 ): Record<string, any>[] {
-  return [event, ...events].slice(0, MAX_PROMPT_EVENTS);
+  const next = [event, ...events];
+  if (next.length <= MAX_PROMPT_EVENTS) {
+    return next;
+  }
+  // Steering scene events (steeringUserPrompt) are exempt from the cap: the
+  // scene list is derived from them and must stay complete and stably numbered
+  // for long sessions. Only the oldest non-scene events are dropped.
+  let nonSceneKept = 0;
+  return next.filter((e) => {
+    if (e?.steeringUserPrompt) {
+      return true;
+    }
+    nonSceneKept += 1;
+    return nonSceneKept <= MAX_PROMPT_EVENTS;
+  });
 }

apps/dreamverse/web/src/lib/ws/reducer.test.ts

@@ -1,6 +1,11 @@
 import { describe, expect, it } from 'vitest';
 
-import { resolveSessionErrorMessage } from './reducer';
+import { applyNormalizedSocketEvent, resolveSessionErrorMessage } from './reducer';
+import { createSessionStore } from '../../stores/session';
+import { createRewriteStore } from '../../stores/rewrite';
+import { createStreamStore } from '../../stores/stream';
+import { createUiStore } from '../../stores/ui';
+import { createPromptWindowStore } from '../../stores/promptWindow';
 
 describe('resolveSessionErrorMessage', () => {
   it('returns a dedicated message for IP session limit errors', () => {
@@ -19,3 +24,162 @@ describe('resolveSessionErrorMessage', () => {
     })).toBe('Backend replica unavailable. Rejoin session.');
   });
 });
+
+function buildContext(overrides: Record<string, unknown> = {}) {
+  const sessionStore = createSessionStore();
+  const rewriteStore = createRewriteStore();
+  const streamStore = createStreamStore();
+  const uiStore = createUiStore();
+  const promptWindowStore = createPromptWindowStore();
+  const avPipeline = {
+    reset: () => {},
+    setStreamCompleted: () => {},
+    noteSegmentInit: () => {},
+    noteSegmentComplete: () => {},
+    maybeStartPlayback: () => {},
+    ensurePipeline: async () => {},
+  };
+  return {
+    sessionStore,
+    promptWindowStore,
+    rewriteStore,
+    streamStore,
+    uiStore,
+    avPipeline,
+    tick: async () => {},
+    defaultAvMime: 'video/mp4',
+    fixedRewriteModel: 'model',
+    parseLatencyMs: () => null,
+    formatPromptWindowEventText: () => '',
+    makePromptId: () => 'generated-id',
+    buildClipLabel: () => 'clip',
+    startSessionCountdown: () => {},
+    clearCountdownInterval: () => {},
+    resetTtffTimer: () => {},
+    startTtffTimer: () => {},
+    preserveArchivedPlaybackSelection: false,
+    finalizeStreamCompletion: async () => {},
+    ...overrides,
+  };
+}
+
+describe('steering generatingNextScene flow', () => {
+  it('sets generatingNextScene on prompt/sources_resumed in manual mode', async () => {
+    const context = buildContext();
+    await applyNormalizedSocketEvent(
+      { type: 'prompt/sources_resumed', payload: { segment_idx: 2 } },
+      context,
+    );
+    expect(context.sessionStore.get().generatingNextScene).toBe(true);
+    expect(context.sessionStore.get().waitingForSegmentPrompt).toBe(false);
+  });
+
+  it('does NOT set generatingNextScene on session/auto_extension_updated', async () => {
+    const context = buildContext();
+    await applyNormalizedSocketEvent(
+      { type: 'session/auto_extension_updated', payload: { enabled: true } },
+      context,
+    );
+    expect(context.sessionStore.get().generatingNextScene).toBe(false);
+    expect(context.sessionStore.get().waitingForSegmentPrompt).toBe(false);
+  });
+
+  it('clears generatingNextScene when segment media arrives', async () => {
+    const context = buildContext();
+    context.sessionStore.patch({ generatingNextScene: true });
+    await applyNormalizedSocketEvent(
+      {
+        type: 'stream/media_init',
+        payload: { segment_idx: 2, stream_id: 's', mime: 'video/mp4' },
+      },
+      context,
+    );
+    expect(context.sessionStore.get().generatingNextScene).toBe(false);
+  });
+
+  it('clears generatingNextScene and returns to waiting on prompt/sources_blocked', async () => {
+    const context = buildContext();
+    context.sessionStore.patch({ generatingNextScene: true });
+    await applyNormalizedSocketEvent(
+      { type: 'prompt/sources_blocked', payload: { segment_idx: 3 } },
+      context,
+    );
+    expect(context.sessionStore.get().generatingNextScene).toBe(false);
+    expect(context.sessionStore.get().waitingForSegmentPrompt).toBe(true);
+  });
+
+  it('clears generatingNextScene when the opening prompt falls back', async () => {
+    const context = buildContext();
+    context.sessionStore.patch({ generatingNextScene: true });
+    await applyNormalizedSocketEvent(
+      {
+        type: 'prompt/fallback_used',
+        payload: { prompt_id: 'p1', prompt: '', source: 'user_enhancement_failed' },
+      },
+      context,
+    );
+    expect(context.sessionStore.get().generatingNextScene).toBe(false);
+    expect(context.sessionStore.get().waitingForSegmentPrompt).toBe(true);
+  });
+});
+
+describe('opening prompt id tracking', () => {
+  it('routes prompt lifecycle updates to the frontend-recorded opening event', async () => {
+    // The frontend records the opening scene under its own prompt id and sends it
+    // as initial_rollout_prompt_id; the backend echoes it in status updates.
+    const context = buildContext();
+    context.rewriteStore.addPromptEvent({
+      promptId: 'opening-id',
+      status: 'rewrite_requested',
+      source: 'user_rewrite',
+      text: 'a castle at dawn',
+      steeringUserPrompt: true,
+      rawText: 'a castle at dawn',
+    });
+
+    await applyNormalizedSocketEvent(
+      { type: 'prompt/enhancing', payload: { prompt_id: 'opening-id' } },
+      context,
+    );
+    let opening = (context.rewriteStore.get().promptEvents as Record<string, any>[])
+      .find((e) => e.promptId === 'opening-id');
+    expect(opening?.status).toBe('enhancing');
+
+    await applyNormalizedSocketEvent(
+      {
+        type: 'prompt/fallback_used',
+        payload: { prompt_id: 'opening-id', prompt: '', source: 'user_enhancement_failed' },
+      },
+      context,
+    );
+    opening = (context.rewriteStore.get().promptEvents as Record<string, any>[])
+      .find((e) => e.promptId === 'opening-id');
+    expect(opening?.status).toBe('ready_fallback');
+    // A failed opening is dropped from the steering scene list instead of
+    // lingering as a ghost "Scene 1".
+    expect(opening?.steeringFailed).toBe(true);
+  });
+
+  it('marks a prompt-scoped session/error (e.g. safety block) as steeringFailed', async () => {
+    const context = buildContext();
+    context.rewriteStore.addPromptEvent({
+      promptId: 'blocked-id',
+      status: 'queued',
+      source: 'user_raw',
+      text: 'a blocked prompt',
+      steeringUserPrompt: true,
+      rawText: 'a blocked prompt',
+    });
+
+    await applyNormalizedSocketEvent(
+      {
+        type: 'session/error',
+        payload: { message: 'Prompt blocked by safety filter.', prompt_id: 'blocked-id' },
+      },
+      context,
+    );
+    const blocked = (context.rewriteStore.get().promptEvents as Record<string, any>[])
+      .find((e) => e.promptId === 'blocked-id');
+    expect(blocked?.steeringFailed).toBe(true);
+  });
+});

apps/dreamverse/web/src/lib/ws/reducer.ts

@@ -99,7 +99,19 @@ export async function applyNormalizedSocketEvent(event: any, context: any): Prom
 				status: "ready_fallback",
 				source: payload.source || "user_raw",
 				text: payload.prompt,
+				// Steering: this prompt produced no segment — drop it from the scene list.
+				steeringFailed: true,
 			});
+			// Steering recovery: enhancement failed so the backend enqueued nothing AND won't
+			// re-emit prompt_sources_blocked (its drained flag is still set). Put the user back to
+			// "describe the next scene" ourselves so the generating overlay clears and they can retry.
+			if (!uiStore.get().simpleMode && sessionStore.get().manualContinuationMode) {
+				sessionStore.patch({
+					waitingForSegmentPrompt: true,
+					generatingNextScene: false,
+					sessionNotice: "Couldn't continue from that prompt — try rephrasing the next scene.",
+				});
+			}
 			console.warn("[PromptEnhanceFallback] Prompt extension failed for this request.");
 			return;
 
@@ -243,19 +255,32 @@ export async function applyNormalizedSocketEvent(event: any, context: any): Prom
 		}
 
 		case "prompt/sources_blocked":
-			sessionStore.patch({
-				autoExtensionTimeoutHint: uiStore.get().simpleMode ? "" : "blocked on user input, increase prompt count for smoother experience",
-			});
+			if (sessionStore.get().manualContinuationMode) {
+				sessionStore.patch({ waitingForSegmentPrompt: true, generatingNextScene: false, autoExtensionTimeoutHint: "" });
+			} else {
+				sessionStore.patch({
+					autoExtensionTimeoutHint: uiStore.get().simpleMode ? "" : "blocked on user input, increase prompt count for smoother experience",
+				});
+			}
 			return;
 
 		case "prompt/sources_resumed":
+			sessionStore.patch({
+				autoExtensionTimeoutHint: "",
+				waitingForSegmentPrompt: false,
+				// A real prompt was just selected for the next segment; media arriving
+				// (stream/media_init) clears this again.
+				...(sessionStore.get().manualContinuationMode ? { generatingNextScene: true } : {}),
+			});
+			return;
+
 		case "session/auto_extension_updated":
-			sessionStore.patch({ autoExtensionTimeoutHint: "" });
-			if (event.type === "session/auto_extension_updated") {
-				console.log("[AutoExtensionUpdated]", {
-					enabled: sessionStore.get().autoExtensionEnabled,
-				});
-			}
+			// Deliberately does NOT touch generatingNextScene: toggling auto extension
+			// starts no generation.
+			sessionStore.patch({ autoExtensionTimeoutHint: "", waitingForSegmentPrompt: false });
+			console.log("[AutoExtensionUpdated]", {
+				enabled: sessionStore.get().autoExtensionEnabled,
+			});
 			return;
 
 		case "segment/step_complete":
@@ -277,6 +302,7 @@ export async function applyNormalizedSocketEvent(event: any, context: any): Prom
 				projectResetPending: false,
 				sessionExpired: true,
 				sessionNotice: "",
+				generatingNextScene: false,
 			});
 			console.log("Session timed out");
 			clearCountdownInterval();
@@ -354,6 +380,8 @@ export async function applyNormalizedSocketEvent(event: any, context: any): Prom
 			return;
 
 		case "stream/media_init":
+			// Segment media is arriving — the "Generating next scene" phase is over.
+			sessionStore.patch({ generatingNextScene: false });
 			streamStore.patch({
 				mediaAppendError: null,
 				loadingAnimation: streamStore.get().avPlaybackStarted ? streamStore.get().loadingAnimation : true,
@@ -471,17 +499,30 @@ export async function applyNormalizedSocketEvent(event: any, context: any): Prom
 			sessionStore.patch({
 				generationCapReached: false,
 				sessionNotice: "",
+				generatingNextScene: false,
 			});
 			await finalizeStreamCompletion();
 			return;
 
 		case "session/error": {
 			const errorMessage = resolveSessionErrorMessage(payload);
+			if (payload?.prompt_id) {
+				// Prompt-scoped error (e.g. safety-blocked): the prompt produced no
+				// segment, so drop it from the steering scene list.
+				rewriteStore.trackPromptEvent(payload.prompt_id, {
+					steeringFailed: true,
+				});
+			}
 			sessionStore.patch({
 				generationCapReached: false,
 				preservePlaybackOnClose: false,
 				promptExtensionError: "",
 				sessionNotice: errorMessage,
+				// Steering: a blocked/failed prompt produced no segment and the backend won't re-emit
+				// prompt_sources_blocked, so recover the "describe the next scene" state ourselves.
+				...(!uiStore.get().simpleMode && sessionStore.get().manualContinuationMode
+					? { waitingForSegmentPrompt: true, generatingNextScene: false }
+					: {}),
 			});
 			rewriteStore.patch({
 				rewritingSeedPrompts: false,

apps/dreamverse/web/src/stores/session.ts

@@ -24,6 +24,9 @@ export interface SessionState {
   livePromptRewriteMode: boolean;
   sessionExpired: boolean;
   projectResetPending: boolean;
+  manualContinuationMode: boolean;
+  waitingForSegmentPrompt: boolean;
+  generatingNextScene: boolean;
 }
 
 const DEFAULT_SESSION_STATE: SessionState = {
@@ -49,6 +52,12 @@ const DEFAULT_SESSION_STATE: SessionState = {
   livePromptRewriteMode: false,
   sessionExpired: false,
   projectResetPending: false,
+  // Steering-only product: every session drives scenes manually. There is no
+  // auto-rollout mode and no UI selector, so this stays true throughout.
+  manualContinuationMode: true,
+  waitingForSegmentPrompt: false,
+  // True from scene submit / prompt selection until the segment's media arrives.
+  generatingNextScene: false,
 };
 
 export type SessionStore = ManagedStore<SessionState> & {

apps/dreamverse/web/src/stores/stream.ts

@@ -1,5 +1,18 @@
 import { createManagedStore, type ManagedStore } from "./createManagedStore";
 
+// Prompt-history sources driven by the user's own submissions. Curated (non-user)
+// entries — e.g. a preset's opening scene — feed the steering scene list and are
+// exempt from the history cap so Scene 1 survives long sessions.
+export const USER_PROMPT_SOURCES = new Set([
+	"user_raw",
+	"user",
+	"user_enhanced",
+	"user_rewrite",
+	"user_enhancement_failed",
+]);
+
+const PROMPT_HISTORY_CAP = 120;
+
 export interface StreamState {
 	playingSeedPromptIndex: number | null;
 	generatingSeedPromptIndex: number | null;
@@ -159,10 +172,14 @@ export function createStreamStore(initialState: Partial<StreamState> = {}): Stre
 					loopIteration: typeof loopIteration === "number" ? loopIteration : null,
 				};
 
+				const nextHistory = [entry, ...state.promptHistory];
 				return {
 					...state,
 					promptHistoryCounter: nextCounter,
-					promptHistory: [entry, ...state.promptHistory].slice(0, 120),
+					promptHistory: nextHistory.length > PROMPT_HISTORY_CAP
+						? nextHistory.filter((item, index) =>
+							index < PROMPT_HISTORY_CAP || !USER_PROMPT_SOURCES.has(String(item.source || "")))
+						: nextHistory,
 					selectedHistoryId: state.selectedHistoryId || (entry.id as string),
 				};
 			});

fastvideo/entrypoints/streaming/server.py

@@ -191,10 +191,13 @@ def run_server(serve_config: ServeConfig, *, generator: _GeneratorProto | None =
 
         generator = VideoGenerator.from_pretrained(config=serve_config.generator)
     app = build_app(serve_config, generator)
+    # A 15MB init image is ~20MB as a base64 ws message, above uvicorn's
+    # default 16MiB frame cap.
     uvicorn.run(
         app,
         host=serve_config.server.host,
         port=serve_config.server.port,
+        ws_max_size=32 * 1024 * 1024,
     )