Phase 5: AI provider system with local and cloud support

- Implement AIProvider base interface with chat() and is_available()
- Add LocalProvider connecting to bundled llama-server via OpenAI SDK
- Add OpenAIProvider for direct OpenAI API access
- Add AnthropicProvider for Anthropic Claude API
- Add LiteLLMProvider for multi-provider gateway
- Build AIProviderService with provider routing, auto-selection,
  and transcript context injection
- Add ai.chat IPC handler supporting chat, list_providers, set_provider,
  and configure actions
- Add ai_chat, ai_list_providers, ai_configure Tauri commands
- Build interactive AIChatPanel with message history, quick actions
  (Summarize, Action Items), and transcript context awareness
- Tests: 30 Python, 6 Rust, 0 Svelte errors

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

python/voice_to_notes/providers/openai_provider.py

@@ -2,4 +2,52 @@
 
 from __future__ import annotations
 
-# TODO: Implement OpenAI provider
+import os
+from typing import Any
+
+from voice_to_notes.providers.base import AIProvider
+
+
+class OpenAIProvider(AIProvider):
+    """Connects to the OpenAI API."""
+
+    def __init__(
+        self,
+        api_key: str | None = None,
+        model: str = "gpt-4o-mini",
+    ) -> None:
+        self._api_key = api_key or os.environ.get("OPENAI_API_KEY", "")
+        self._model = model
+        self._client: Any = None
+
+    def _ensure_client(self) -> Any:
+        if self._client is not None:
+            return self._client
+
+        if not self._api_key:
+            raise RuntimeError("OpenAI API key not configured. Set OPENAI_API_KEY or provide it in settings.")
+
+        try:
+            from openai import OpenAI
+
+            self._client = OpenAI(api_key=self._api_key)
+        except ImportError:
+            raise RuntimeError("openai package is required. Install with: pip install openai")
+        return self._client
+
+    def chat(self, messages: list[dict[str, str]], **kwargs: Any) -> str:
+        client = self._ensure_client()
+        response = client.chat.completions.create(
+            model=kwargs.get("model", self._model),
+            messages=messages,
+            temperature=kwargs.get("temperature", 0.7),
+            max_tokens=kwargs.get("max_tokens", 2048),
+        )
+        return response.choices[0].message.content or ""
+
+    def is_available(self) -> bool:
+        return bool(self._api_key)
+
+    @property
+    def name(self) -> str:
+        return "OpenAI"