fix: reduce vLLM default max_tokens to 4096, update model to AxionML/Qwen3.5-9B-NVFP4

The model's max_model_len is 16384 — requesting 32768 output tokens
caused HTTP 400 from vLLM. 4096 is a safe default for extraction output.

services/shared/config.py

@@ -61,13 +61,13 @@ class VLLMConfig:
     Requirements: 3.1, 3.2
     """
     base_url: str = "http://192.168.42.254:8000"
-    model: str = "RedHatAI/Qwen3.6-35B-A3B-NVFP4"
+    model: str = "AxionML/Qwen3.5-9B-NVFP4"
     timeout: int = 120
     max_retries: int = 2
     retry_base_delay: float = 1.0
     retry_max_delay: float = 10.0
     retry_backoff_multiplier: float = 2.0
-    max_tokens: int = 32768
+    max_tokens: int = 4096
     temperature: float = 0.7
     api_key: str = ""  # Optional, for authenticated vLLM deployments
 
@@ -287,7 +287,7 @@ def load_config() -> AppConfig:
             retry_base_delay=float(os.getenv("VLLM_RETRY_BASE_DELAY", "1.0")),
             retry_max_delay=float(os.getenv("VLLM_RETRY_MAX_DELAY", "10.0")),
             retry_backoff_multiplier=float(os.getenv("VLLM_RETRY_BACKOFF_MULTIPLIER", "2.0")),
-            max_tokens=int(os.getenv("VLLM_MAX_TOKENS", "32768")),
+            max_tokens=int(os.getenv("VLLM_MAX_TOKENS", "4096")),
             temperature=float(os.getenv("VLLM_TEMPERATURE", "0.7")),
             api_key=os.getenv("VLLM_API_KEY", ""),
         ),

tests/test_vllm_client.py

@@ -386,11 +386,11 @@ def test_appconfig_vllm_defaults():
     assert hasattr(cfg, "vllm")
     assert isinstance(cfg.vllm, VLLMConfig)
     assert cfg.vllm.base_url == "http://192.168.42.254:8000"
-    assert cfg.vllm.model == "RedHatAI/Qwen3.6-35B-A3B-NVFP4"
+    assert cfg.vllm.model == "AxionML/Qwen3.5-9B-NVFP4"
     assert cfg.vllm.timeout == 120
     assert cfg.vllm.max_retries == 2
     assert cfg.vllm.temperature == 0.7
-    assert cfg.vllm.max_tokens == 32768
+    assert cfg.vllm.max_tokens == 4096
     assert cfg.vllm.api_key == ""