refactor(llm): validate AgentConfig in prod; spec-mock the client in tests

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

hate_crack/llm.py

@@ -111,7 +111,7 @@ def generate_candidates(
     prompt_generator = _TARGET_PROMPT if mode == "target" else _WORDLIST_PROMPT
 
     agent = AtomicAgent[GenerationInput, PasswordCandidatesOutput](
-        config=AgentConfig.model_construct(
+        config=AgentConfig(
             client=client,
             model=model,
             system_prompt_generator=prompt_generator,

tests/test_llm.py

@@ -3,6 +3,7 @@
 import os
 from unittest import mock
 
+import instructor
 import pytest
 
 os.environ["HATE_CRACK_SKIP_INIT"] = "1"
@@ -25,7 +26,7 @@ def _patch_agent(candidates):
     agent_cls.__getitem__.return_value.return_value = agent_instance
 
     return (
-        mock.patch("hate_crack.llm.instructor"),
+        mock.patch("hate_crack.llm.instructor.from_openai", return_value=mock.MagicMock(spec=instructor.Instructor)),
         mock.patch("hate_crack.llm.OpenAI"),
         mock.patch("hate_crack.llm.AtomicAgent", agent_cls),
         agent_cls,