Bump default n_ctx 8192 → 32768

8K filled up after one month of activity (~200 MB state) and the next
`memwalk update` crashed with llama_decode returned 1 because new
tokens didn't fit. Nemotron 3 Nano 4B is trained for 1M context so
32K is well within model capacity and leaves headroom for several
more months of ingest before rotation matters.

Note: existing users need to delete current.memb after upgrading,
since state files are tied to the n_ctx they were created with.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

memwalk/config.py

@@ -49,7 +49,7 @@ class BashConfig:
 class Config:
     model_path: Path
     n_gpu_layers: int = -1
-    n_ctx: int = 8192
+    n_ctx: int = 32768
     state_dir: Path = HOME_DIR
     git: GitConfig = field(default_factory=GitConfig)
     bash: BashConfig = field(default_factory=BashConfig)