Model providers: OpenAI/xAI/Ollama + run several at once (registry)

Extends the #215 abstraction:
- OpenAICompatibleLLMProvider / OpenAICompatibleEmbeddingProvider — one impl (via
  the official openai SDK) covers OpenAI, xAI (api.x.ai/v1), Ollama
  (…:11434/v1), OpenRouter, etc.; they differ only by base_url, key, and model.
- Registry factory: build_llm_providers() / build_embedding_providers() return
  every provider whose credentials are configured, so you can run several
  concurrently. get_llm_provider(name)/get_embedding_provider(name) select by
  name, falling back to default_*_provider, then Null.
- Per-provider env config (ANTHROPIC_*, OPENAI_*, XAI_*, OLLAMA_*) +
  DEFAULT_LLM_PROVIDER / DEFAULT_EMBEDDING_PROVIDER; documented in .env.example.
  Defaults keep AI off (empty registry).

Embeddings now have real backends (OpenAI/Ollama), still separate from the LLM
since Anthropic offers no embeddings endpoint. Tests cover multi-provider
selection, default resolution, disabled-without-credentials, and null fail-loud.
Full suite 87 passed.

Relates to #215.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Signed-off-by: Justin Paul <justin@jpaul.me>

backend/app/integrations/models/openai_compat.py

@@ -0,0 +1,40 @@
+"""OpenAI-compatible providers (one implementation, many vendors).
+
+OpenAI, xAI (api.x.ai/v1), Ollama (…:11434/v1), OpenRouter, Together, vLLM, etc.
+all speak the OpenAI Chat Completions / Embeddings API — they differ only by
+base URL, key, and model name. So a single class, parameterized by those, plugs
+in every one of them via the official `openai` SDK.
+"""
+
+from openai import AsyncOpenAI
+
+from app.integrations.models.base import EmbeddingProvider, LLMProvider
+
+
+class OpenAICompatibleLLMProvider(LLMProvider):
+    def __init__(self, *, api_key: str | None, base_url: str, model: str, max_tokens: int = 4096) -> None:
+        # Local backends (Ollama) ignore the key but the SDK requires a non-empty one.
+        self._client = AsyncOpenAI(api_key=api_key or "not-needed", base_url=base_url)
+        self._model = model
+        self._max_tokens = max_tokens
+
+    async def complete(self, *, prompt: str, system: str | None = None) -> str:
+        messages: list[dict] = []
+        if system:
+            messages.append({"role": "system", "content": system})
+        messages.append({"role": "user", "content": prompt})
+        resp = await self._client.chat.completions.create(
+            model=self._model, max_tokens=self._max_tokens, messages=messages
+        )
+        return resp.choices[0].message.content or ""
+
+
+class OpenAICompatibleEmbeddingProvider(EmbeddingProvider):
+    def __init__(self, *, api_key: str | None, base_url: str, model: str, dimensions: int) -> None:
+        self._client = AsyncOpenAI(api_key=api_key or "not-needed", base_url=base_url)
+        self._model = model
+        self.dimensions = dimensions
+
+    async def embed(self, texts: list[str]) -> list[list[float]]:
+        resp = await self._client.embeddings.create(model=self._model, input=texts)
+        return [d.embedding for d in resp.data]