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/local_provider.py

@@ -2,8 +2,57 @@
 
 from __future__ import annotations
 
+import sys
+from typing import Any
 
-# TODO: Implement local provider
-# - Connect to llama-server on localhost:{port}
-# - Use openai SDK with custom base_url
-# - Support chat and streaming
+from voice_to_notes.providers.base import AIProvider
+
+
+class LocalProvider(AIProvider):
+    """Connects to bundled llama-server via its OpenAI-compatible API."""
+
+    def __init__(self, base_url: str = "http://localhost:8080", model: str = "local") -> None:
+        self._base_url = base_url.rstrip("/")
+        self._model = model
+        self._client: Any = None
+
+    def _ensure_client(self) -> Any:
+        if self._client is not None:
+            return self._client
+
+        try:
+            from openai import OpenAI
+
+            self._client = OpenAI(
+                base_url=f"{self._base_url}/v1",
+                api_key="not-needed",  # llama-server doesn't require an API key
+            )
+        except ImportError:
+            raise RuntimeError(
+                "openai package is required for local AI. 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=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:
+        try:
+            import urllib.request
+
+            req = urllib.request.Request(f"{self._base_url}/health", method="GET")
+            with urllib.request.urlopen(req, timeout=2) as resp:
+                return resp.status == 200
+        except Exception:
+            return False
+
+    @property
+    def name(self) -> str:
+        return "Local (llama-server)"