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>

nextcloud_mcp_server/providers/mistral.py

@@ -6,6 +6,10 @@ can be added later if needed; see ADR-015.
 
 import logging
 
+# mistralai 2.x ships no top-level __init__.py, so `from mistralai import …`
+# raises ImportError. The canonical public paths are `mistralai.client` (which
+# re-exports the SDK class via `client/__init__.py`) and `mistralai.client.errors`
+# (which lazy-loads SDKError). There is no `mistralai.models` subpackage either.
 from mistralai.client import Mistral
 from mistralai.client.errors import SDKError