feat: add use_responses_api config to force Chat Completions for OpenAI relays (#105)

* feat(config): use_responses_api (#98)

langchain-openai auto-switches to the Responses API when reasoning
params are set, which breaks OpenAI-compatible relays that only support
Chat Completions. This adds a user-facing config option to override
that behavior:

  evosci config set use_responses_api false
  # or EVOSCIENTIST_USE_RESPONSES_API=false

* fix: propagate use_responses_api from config file and add normalization tests

Address PR #105 review comments:
- apply_config_to_env() now sets EVOSCIENTIST_USE_RESPONSES_API so
  config file values take effect (not just the env var directly)
- Add parametrized tests for case/whitespace normalization

---------

Co-authored-by: Xi Zhang <106144707+X-iZhang@users.noreply.github.com>

EvoScientist/config/settings.py

@@ -197,6 +197,9 @@ class EvoScientistConfig:
     # DM access control policy
     dm_policy: str = "allowlist"
 
+    # OpenAI API mode - "" = auto, "true" = force Responses, "false" = force Completions
+    use_responses_api: str = ""
+
     # ccproxy
     ccproxy_port: int = 8000
 
@@ -372,6 +375,7 @@ _ENV_MAPPINGS = {
     "default_workdir": "EVOSCIENTIST_WORKSPACE_DIR",
     "ui_backend": "EVOSCIENTIST_UI_BACKEND",
     "ccproxy_port": "EVOSCIENTIST_CCPROXY_PORT",
+    "use_responses_api": "EVOSCIENTIST_USE_RESPONSES_API",
 }
 
 
@@ -468,3 +472,7 @@ def apply_config_to_env(config: EvoScientistConfig) -> None:
         os.environ["OLLAMA_BASE_URL"] = config.ollama_base_url
     if config.tavily_api_key and not os.environ.get("TAVILY_API_KEY"):
         os.environ["TAVILY_API_KEY"] = config.tavily_api_key
+    if config.use_responses_api and not os.environ.get(
+        "EVOSCIENTIST_USE_RESPONSES_API"
+    ):
+        os.environ["EVOSCIENTIST_USE_RESPONSES_API"] = config.use_responses_api