config: retire the last process-global config field reads (#33338)

`get_server_args().<field>` reads one process's startup record. Nine sites still
did that for a value that has a namespace: the attention backend (5),
`skip_tokenizer_init` (2), the draft-aware `load_format`, and a chunked-prefill
size in `sglang.kernels`. They now read `get_exec().kernel` / `get_serving()` /
`get_model()` / `get_schedule()`, so they see the resolved value including
post-publish overrides.

The multimodal processor's device selection moves to the instance it was
constructed with rather than to a namespace: `base_gpu_id` differs per worker (the
encode-server DP workers each specialise their own copy), so no process-global
value can stand in for it, and engines sharing a tokenizer process each need their
own. Branch order, the NPU preprocess patches, and the case that leaves "device"
unset are unchanged.

What stays on `get_server_args()` is the derived API — `@property` and method
members computed from several fields plus the HF config
(`mamba_cache_chunk_size`, `get_model_config()`, `enable_mamba_extra_buffer*`) —
plus three config-intent reads of live-shadowed sizes, each of which needs an
answer the live topology property cannot give (the DSA indexer's PP gate must
short-circuit before touching the PP group, `allocation`'s DCP gate asks whether
DCP was configured at all, and the CUDA-IPC recycler runs where no group exists).

A new AST ratchet pins both shapes it can see — the direct call and an alias
bound from it in the same function — at 0 and 12 respectively, exempting the
derived APIs and those three sites by name. The alias-form baseline is not zero:
those reads are mostly per-runner fields in model code, and lowering them is the
next slice.

Two fixtures stopped faking config: `test_dllm_fdfo_kv_reuse` rebound
`allocation.get_server_args` to a SimpleNamespace, which silently stops
intercepting the moment a reader migrates; it publishes a real config instead.

.claude/skills/sglang-runtime-context/SKILL.md

@@ -69,10 +69,10 @@ resolved configuration lives in the namespace bags.**
 - **Per-instance boundaries** — the tokenizer-manager family, everything under
   `entrypoints/`, and the tokenizer-process multimodal processors read
   `self.server_args`: several `Engine`s can share one process, and the process-global
-  bags are last-publish-wins across engines. (The mm-processor boundary is not yet
-  airtight: `BaseMultimodalProcessor.process_mm_data` still reads `base_gpu_id` /
-  `rl_on_policy_target` through `get_server_args()` — a known last-publish-wins gap,
-  not a pattern to copy.)
+  bags are last-publish-wins across engines. `base_gpu_id` also differs per worker
+  (the encode-server DP workers each specialize their own copy), so no process-global
+  value can stand in for it — `BaseMultimodalProcessor._fast_image_processor_device`
+  is the shape to copy.
 - **Whole-object passes** (`f(server_args)` handing the instance along) keep the
   supplied-instance contract; don't rewrite the parameter reads to bag reads unless the
   field is runtime-mutated (see the elastic-EP `ep_size` case in