common : refactor common_sampler + grammar logic changes (#17937)

* common : refactor common_sampler + grammar logic changes * tests : increase max_tokens to get needed response * batched : fix uninitialized samplers
2025-12-14 10:11:13 +02:00
parent 3238b1400c
commit 254098a279
27 changed files with 372 additions and 293 deletions
@@ -684,7 +684,7 @@ def test_anthropic_streaming_content_block_indices():
    # Request that might produce both text and tool use
    res = server.make_stream_request("POST", "/v1/messages", data={
        "model": "test",
-        "max_tokens": 200,
+        "max_tokens": 400,
        "stream": True,
        "tools": [{
            "name": "test_tool",