refactor: make Settings UI the single source of truth for API provider

Remove legacy env-var-based provider/mode detection that caused misleading
UI badges (e.g., GLM badge showing when Settings was set to Claude).

Key changes:
- Remove _is_glm_mode() and _is_ollama_mode() env-var sniffing functions
  from server/routers/settings.py; derive glm_mode/ollama_mode purely from
  the api_provider setting
- Remove `import os` from settings router (no longer needed)
- Update schema comments to reflect settings-based derivation
- Remove "(configured via .env)" from badge tooltips in App.tsx
- Remove Kimi/GLM/Ollama/Playwright-headless sections from .env.example;
  add note pointing to Settings UI
- Update CLAUDE.md and README.md documentation to reference Settings UI
  for alternative provider configuration
- Update model IDs from claude-opus-4-5-20251101 to claude-opus-4-6
  across registry, client, chat sessions, tests, and UI defaults
- Add LEGACY_MODEL_MAP with auto-migration in get_all_settings()
- Show model ID subtitle in SettingsModal model selector
- Add Vertex passthrough test for claude-opus-4-6 (no date suffix)

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

server/schemas.py

@@ -411,8 +411,8 @@ class SettingsResponse(BaseModel):
     """Response schema for global settings."""
     yolo_mode: bool = False
     model: str = DEFAULT_MODEL
-    glm_mode: bool = False  # True if GLM API is configured via .env
-    ollama_mode: bool = False  # True if Ollama API is configured via .env
+    glm_mode: bool = False  # True when api_provider is "glm"
+    ollama_mode: bool = False  # True when api_provider is "ollama"
     testing_agent_ratio: int = 1  # Regression testing agents (0-3)
     playwright_headless: bool = True
     batch_size: int = 3  # Features per coding agent batch (1-3)