fix(llm): skip Anthropic effort kwarg on non-supporting models (#831)

Haiku 4.5 rejects the effort parameter with 400. AnthropicClient.get_llm()
now drops effort when the model isn't in the supported set (Opus 4.5+,
Sonnet 4.5+, mythos-preview). Forward-compat regex catches future
claude-{opus,sonnet}-X-Y releases automatically; Haiku and unknown
models stay excluded conservatively.

14 tests cover Haiku exclusion, current Opus/Sonnet inclusion, future-
version inheritance via pattern, mythos-preview, unknown-default
exclusion, and other passthrough kwargs surviving the effort-skip path.

tradingagents/llm_clients/anthropic_client.py

@@ -1,3 +1,4 @@
+import re
 from typing import Any, Optional
 
 from langchain_anthropic import ChatAnthropic
@@ -10,6 +11,22 @@ _PASSTHROUGH_KWARGS = (
     "callbacks", "http_client", "http_async_client", "effort",
 )
 
+# Anthropic's extended-thinking ``effort`` parameter is accepted by Opus 4.5+
+# and Sonnet 4.5+ only. Haiku (any version shipped to date) 400s with
+# ``"This model does not support the effort parameter"`` (#831). Future
+# ``claude-{opus,sonnet}-X-Y`` releases inherit effort support via the
+# forward-compat pattern below; future Haiku stays excluded by default.
+_EFFORT_EXACT = {
+    "claude-mythos-preview",  # non-standard preview name; effort-capable
+}
+_EFFORT_PATTERN = re.compile(r"^claude-(opus|sonnet)-\d+-\d+$")
+
+
+def _supports_effort(model: str) -> bool:
+    """Whether Anthropic accepts the ``effort`` parameter for this model."""
+    model_lc = model.lower()
+    return model_lc in _EFFORT_EXACT or bool(_EFFORT_PATTERN.match(model_lc))
+
 
 class NormalizedChatAnthropic(ChatAnthropic):
     """ChatAnthropic with normalized content output.
@@ -38,8 +55,11 @@ class AnthropicClient(BaseLLMClient):
             llm_kwargs["base_url"] = self.base_url
 
         for key in _PASSTHROUGH_KWARGS:
-            if key in self.kwargs:
-                llm_kwargs[key] = self.kwargs[key]
+            if key not in self.kwargs:
+                continue
+            if key == "effort" and not _supports_effort(self.model):
+                continue
+            llm_kwargs[key] = self.kwargs[key]
 
         return NormalizedChatAnthropic(**llm_kwargs)