feat(providers): add Mistral embedding provider, route registry through dynaconf

Adds a hosted Mistral embedding option (mistral-embed, 1024-dim) alongside
the existing Bedrock / OpenAI / Ollama / Simple providers. Implementation
mirrors OpenAIProvider: lazy dimension detection with a known-models lookup,
chunked batch requests, defensive index sort, and a 429-aware retry decorator.

In the same change, ProviderRegistry switches from os.getenv to the
dynaconf-backed Settings dataclass so all five providers share a single
configuration path. config.py gains the previously-uncovered Bedrock keys,
the new Mistral keys, the missing OPENAI_GENERATION_MODEL /
OLLAMA_GENERATION_MODEL, and SIMPLE_EMBEDDING_DIMENSION.

Auto-detection priority: Bedrock → OpenAI → Mistral → Ollama → Simple.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

pyproject.toml

@@ -43,6 +43,7 @@ dependencies = [
     "pymupdf4llm>=0.2.2",
     "openai>=2.8.1",
     "dynaconf>=3.2.13,<4.0",
+    "mistralai>=2.4.5",
 ]
 classifiers = [
     "Development Status :: 4 - Beta",