refactor(providers): address PR #772 review round 2 — guard, naming, docs, tests

- _retry.py: replace `assert last_error is not None` with explicit
  `if last_error is None: raise RuntimeError(...)` so the original
  rate-limit error is preserved under `python -O`.
- openai.py: drop the `_retry_factory` alias chain; rename the bound
  decorator to `_retry_429` to match the pattern in mistral.py.
- mistral.py: comment the imports so future reviewers understand why
  `from mistralai.client import …` is the canonical path on 2.x (no
  top-level `__init__.py`; no `mistralai.models` subpackage either).
- docs/configuration.md: add `OPENAI_GENERATION_MODEL` and
  `OLLAMA_GENERATION_MODEL` rows to the env-var reference table.
- test_mistral.py: add direct unit test for the `_is_rate_limit`
  predicate (429 → True, 500 → False, missing-attr → False).
- test_registry.py: stub `mistralai.client.Mistral` in the registry
  picker test, mirroring the Ollama sibling, so the test doesn't
  depend on the SDK accepting arbitrary keys.

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

tests/unit/providers/test_registry.py

@@ -69,8 +69,11 @@ def test_registry_picks_simple_with_custom_dimension(clean_provider_env):
 
 
 @pytest.mark.unit
-def test_registry_picks_mistral_when_api_key_set(clean_provider_env):
+def test_registry_picks_mistral_when_api_key_set(clean_provider_env, mocker):
     """MISTRAL_API_KEY alone is enough to select MistralProvider."""
+    # MistralProvider eagerly constructs the SDK client in __init__; stub it
+    # so the test doesn't depend on the SDK accepting arbitrary keys.
+    mocker.patch("nextcloud_mcp_server.providers.mistral.Mistral")
     clean_provider_env.setenv("MISTRAL_API_KEY", "test-key")
     _reload_config()