sampler : remove "full-context windows" from history-based samplers (#26524)

* Resolve -1 to 1024 instead of ctx-len for samplers

Because of backend-sampling we initialize samplers before the complete
llama_context is there. Therefore, we cannot infer the resolved context
length yet at the time we construct the samplers.

* Shared default of 64 for history-based samplers, remove context_size

tools/mtmd/tests/test-deepseek-ocr.py

@@ -215,7 +215,7 @@ def run_mtmd_cli(spec: "ModelSpec", model_path, mmproj_path, image_path, bin_pat
             "--dry-multiplier", "0.8",
             "--dry-base", "1.75",
             "--dry-allowed-length", "2",
-            "--dry-penalty-last-n", "-1",
+            "--dry-penalty-last-n", "64",
             "--dry-sequence-breaker", "none",
         ]
     if spec.n_ctx is not None: