modal: mount leetcode data from image; correct 2873b37 hang claim

Data fix: the read-only LeetCode jsonls (44MB, tracked in the rl-rewardhacking
submodule) now mount from the local checkout into the image (add_local_dir,
copy=False) instead of the Volume. A Volume mount/reload race FileNotFound'd
them mid-sweep even though they were committed; versioning the dataset with the
code removes that failure mode. Volume now carries only mutable dirs. Verified:
both a vanilla warm and a routeV smoke load data fine on the new image.

Correction: 2873b37's message claimed "the smoke on pinned 5.10.2 clears the
deadlock point" -- it did NOT, the smoke hung. And transformers is not the cause:
on this exact 5.10.2 image, vanilla completes generate (warm, 6.8 min, exit 0)
while routeV deadlocks at its first rollout generate(). Same image, same attn,
same data -- the hang is routeV-specific (v_grad extraction's CUDA state x
flash-attn first-generate on torch 2.7.1; local box runs routeV fine on 2.8).
Known-issue section + corrected app.py comment record this. Local box produces
the canonical routeV runs; Modal is proven for vanilla.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

modal/README.md

@@ -86,6 +86,31 @@ python modal/fetch.py                 # all of out/runs + logs
 python modal/fetch.py <ts>_<slug>     # one run
 ```
 
+## Known issue — routeV deadlocks at first generate() on Modal
+
+**vanilla works, routeV hangs, on the identical image.** On the `transformers==5.10.2`
++ Dao flash-attn 2.8.3 (torch 2.7.1) image, a vanilla warm completes generate cleanly
+(6.8 min, exit 0, `per_mode_deploy.json` written), but a routeV smoke freezes at its
+first rollout `generate()` indefinitely (killed at ~11 min). Same image, same attn,
+same data, same delta_S init — the only difference is the arm.
+
+It is NOT: the data path (both arms load fine now), the attn backend (the other agent
+reproduced the hang under sdpa too, commit 2f91561), transformers version (vanilla
+runs on this exact 5.10.2), or the generate-time forward hook (routeV's `grad_probe`
+branch is skipped under `generate()`'s no_grad, so both arms run the identical
+`_delta_hook` else-path). What's left: routeV extracts `v_grad` fresh before the loop
+(forward+backward across 252 modules), and that CUDA/allocator state collides with
+flash-attn's first generate on torch 2.7.1. The **local box runs routeV fine on torch
+2.8** — so this is a torch-2.7-on-Modal deadlock, not a method bug.
+
+Correction to commit 2873b37: its message claimed "the smoke on pinned 5.10.2 clears
+the deadlock point." It does not — the smoke hung. transformers was never the cause.
+
+**Current call:** Modal is proven for vanilla; the local box produces the canonical
+routeV runs (jobs 134/135). Don't sink Modal $ into the routeV hang unless we
+specifically want the parallelism — the fix is a focused torch-2.7 generate debug
+(candidate: `torch.cuda.empty_cache()` at the extraction→loop boundary, unverified).
+
 ## Caveat — keep the inventory fresh
 
 `launch.py::JOBS` is copied verbatim from the 2026-06-06 manifest. The live plan

modal/app.py

@@ -37,6 +37,8 @@ from pathlib import Path
 
 import modal
 
+REPO = Path(__file__).parent.parent
+
 # ---------------------------------------------------------------------------
 # Image
 # ---------------------------------------------------------------------------
@@ -55,12 +57,13 @@ image = (
         index_url="https://download.pytorch.org/whl/cu126",
     )
     .pip_install(
-        # transformers: pinned released version, NOT floating `@ main` (a later main
+        # transformers: pinned released version, NOT floating `@ main`. uv.lock keeps
-        # commit is what hung generate() -- my v60 ran clean on an earlier main, the
+        # the exact 5.8.0.dev0 commit for the local box; the image uses a released
-        # other agent confirmed the hang is the transformers commit not the attn
+        # wheel (Qwen3-4B needs no main-only feature). NB: transformers is NOT the
-        # backend). 5.10.2 is the patch line of my verified v60 build (5.10.0.dev0).
+        # routeV generate() hang -- on this exact 5.10.2 image, vanilla completes
-        # uv.lock keeps the exact 5.8.0.dev0 commit for the local box's fine-grained
+        # generate fine (warm, 6.8 min, exit 0) while routeV deadlocks at its first
-        # repro; the image uses a released wheel. Qwen3-4B needs no main-only feature.
+        # rollout generate. The hang is routeV-specific (v_grad extraction's CUDA
+        # state x flash-attn first-generate on torch 2.7.1); see modal/README.md.
         "transformers==5.10.2",
         "einops>=0.8",
         "jaxtyping>=0.2",
@@ -81,9 +84,14 @@ image = (
     # flash-attn last, after torch is present (no build isolation -> uses the wheel).
     .pip_install(FLASH_ATTN_WHL)
     # Research code mounted at runtime so local edits sync without an image rebuild.
-    # Only src/ is needed on PYTHONPATH; data + caches live on the Volume. Anchored
+    # Only src/ is needed on PYTHONPATH; mutable caches (svd_cache/out/logs) live on
-    # to the repo (not CWD) so `modal run` works from any directory.
+    # the Volume. Anchored to the repo (not CWD) so `modal run` works from anywhere.
-    .add_local_dir(str(Path(__file__).parent.parent / "src"), "/root/src", copy=False)
+    .add_local_dir(str(REPO / "src"), "/root/src", copy=False)
+    # Read-only LeetCode dataset (44MB, 3 jsonls, tracked in the rl-rewardhacking
+    # submodule). Mount from the image, NOT the Volume: a Volume mount/reload race
+    # FileNotFound'd it mid-sweep even though the file was committed. Versioning it
+    # with the code makes the dataset deterministic and removes that failure mode.
+    .add_local_dir(str(REPO / "external/rl-rewardhacking/results/data"), "/root/leetcode_data", copy=False)
 )
 
 app = modal.App("vgrout", image=image)
@@ -118,13 +126,19 @@ def _prepare_workdir() -> str:
         Path(f"{CACHE}/{sub}").mkdir(parents=True, exist_ok=True)
     work = Path("/work")
     work.mkdir(exist_ok=True)
-    # external/ holds the read-only LeetCode dataset (uploaded to the Volume by
+    # Mutable dirs live on the Volume (model cache, svd basis, uploaded inputs in
-    # upload_inputs.py); train.py reads it via the relative path
+    # out/, written out/runs/*). Symlinked from the ephemeral /work cwd.
-    # external/rl-rewardhacking/results/data/*.jsonl.
+    for name in ("svd_cache", "out", "logs"):
-    for name in ("svd_cache", "out", "logs", "external"):
         link = work / name
         if not link.exists():
             link.symlink_to(f"{CACHE}/{name}")
+    # Read-only LeetCode dataset comes from the image mount (/root/leetcode_data),
+    # not the Volume -- train.py reads external/rl-rewardhacking/results/data/*.jsonl
+    # relative to cwd, so symlink that leaf dir onto the deterministic image copy.
+    data = work / "external/rl-rewardhacking/results/data"
+    data.parent.mkdir(parents=True, exist_ok=True)
+    if not data.exists():
+        data.symlink_to("/root/leetcode_data")
     return str(work)