refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

- Rename teacher -> optimizer, student -> target across all code, configs, docs, prompts
- CLI: --teacher_model -> --optimizer_model, --student_model -> --target_model
- Remove best_skill files, keep only initial skills
- Fix slow update gate (force write into skill)
- Fix SLOW_UPDATE marker stripping
- Remove deep_reflect and meta_reflect mechanisms
- Update .env.example with export prefix and azure_cli docs
- Add endpoint empty validation in azure_openai.py

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

skillopt/model/common.py

@@ -17,10 +17,10 @@ _RESPONSES_API_MODELS = {
 }
 
 _BACKEND_DEFAULT_MODELS = {
-    "azure_openai": "gpt-5.5",
-    "openai_chat": "gpt-5.5",
-    "codex": "gpt-5.5",
-    "codex_exec": "gpt-5.5",
+    "azure_openai": "gpt-4o",
+    "openai_chat": "gpt-4o",
+    "codex": "gpt-4o",
+    "codex_exec": "gpt-4o",
     "claude": "claude-sonnet-4-6",
     "claude_chat": "claude-sonnet-4-6",
     "claude_code_exec": "claude-sonnet-4-6",