tracker download fix

docs/issues/44-tracker-shard-source-partial-download.md

@@ -38,6 +38,17 @@ What exists already (build on it, don't duplicate):
    subset (new) → HF `snapshot_download` with `allow_patterns` for the same
    subset (new — stop downloading the whole repo even from HF) → full snapshot
    (last resort).
+   - The `allow_patterns` subset must not depend on the tracker having a local
+     snapshot: when the tracker has no `--models-dir` match for a repo (or
+     hasn't cached it yet — the common case for a fresh public tracker),
+     `model_sources` comes back empty and `download_shard` falls straight to
+     `_download_huggingface_subset(..., allow_patterns=None)`, i.e. the full
+     repo. Reported 2026-07-06: a CPU node assigned layers 0–2 of
+     `unsloth/Qwen3.6-35B-A3B` (42 safetensor shards) sat downloading the
+     entire model unauthenticated because of this. Fix: fetch
+     `model.safetensors.index.json` + `config.json` directly from HF (a few
+     KB) and compute the same layer-scoped file subset client-side, so the
+     HF-fallback path is filtered even with an empty `model_sources`.
 4. **Partial LOAD (the hard half).** Downloading a subset is wasted unless the
    node stops instantiating the full model: build the model skeleton on the
    `meta` device, materialize only assigned layers (+embeddings/norm/head as
@@ -64,6 +75,11 @@ What exists already (build on it, don't duplicate):
 - [x] Node downloader keeps exact-shard peers first, then races tracker model
   sources against a HuggingFace `snapshot_download(..., allow_patterns=...)`
   subset download, using the first successful source.
+- [ ] When no tracker model source is available at all, the HuggingFace
+  fallback still computes `allow_patterns` from the repo's own
+  `model.safetensors.index.json` (fetched directly, not via the tracker) —
+  it never silently downloads the full model just because the tracker has
+  nothing cached.
 - [x] Real PyTorch model startup can use tracker `full_url` sources to fetch
   the full local snapshot over LAN before `from_pretrained`, so local-network
   testing no longer has to pull from HuggingFace first.