feat(config): TRADINGAGENTS_* env-var overlay for DEFAULT_CONFIG

Adds a single _ENV_OVERRIDES table in default_config.py with type-aware
coercion (str/int/bool), so users can switch llm_provider, deep/quick
models, backend URL, output language, debate rounds, and the checkpoint
flag purely via .env. Centralizes load_dotenv in the package __init__
so the overlay applies for every entry point (CLI, main.py, programmatic).
Drops the hardcoded model assignments and duplicate dotenv loads in
main.py and cli/main.py. Verified live with OpenAI and Gemini.

#602

.env.example

@@ -11,3 +11,16 @@ ZHIPU_CN_API_KEY=
 MINIMAX_API_KEY=
 MINIMAX_CN_API_KEY=
 OPENROUTER_API_KEY=
+
+# Optional: override DEFAULT_CONFIG without editing code.
+# Any TRADINGAGENTS_* variable below, when set, replaces the matching key
+# in tradingagents/default_config.py. Values are coerced to the type of
+# the existing default (bool / int / str), so "true"/"3" work as expected.
+#TRADINGAGENTS_LLM_PROVIDER=openai
+#TRADINGAGENTS_DEEP_THINK_LLM=gpt-5.4
+#TRADINGAGENTS_QUICK_THINK_LLM=gpt-5.4-mini
+#TRADINGAGENTS_LLM_BACKEND_URL=
+#TRADINGAGENTS_OUTPUT_LANGUAGE=English
+#TRADINGAGENTS_MAX_DEBATE_ROUNDS=1
+#TRADINGAGENTS_MAX_RISK_ROUNDS=1
+#TRADINGAGENTS_CHECKPOINT_ENABLED=false