refactor: convert f-string logging to lazy %-style format (G004)

Sweep all 1676 G004 violations across 112 files, converting
`logger.<level>(f"…{x}…")` to `logger.<level>("…%s…", x)`.

Why: ruff rule G004 was added to pyproject.toml to enforce lazy
%-style logging — defers formatting until the log level is enabled
and lets structured log tooling match the unformatted template.

Conversion preserves rendered output byte-for-byte:
- `{x}` → `%s` + `x`
- `{x!r}` / `{x!s}` / `{x!a}` → `%r` / `%s` / `%a`
- Format specs (`{x:.2f}`, `{x:>10}`) → `%s` + `format(x, 'spec')`
  (printf-style specs aren't 1:1 with Python format specs, so we
  delegate to `format()` to keep identical output)
- Literal `%` → `%%`
- Concatenated f-strings (`f"a {x} " "b"`) flattened
- Trailing kwargs (`exc_info=True`) preserved

Verified:
- `uv run ruff check --select G004` → 0 violations
- `uv run ty check -- nextcloud_mcp_server` → passes
- `uv run pytest tests/unit/` → 1010 passed

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

nextcloud_mcp_server/vector/pca.py

@@ -92,9 +92,11 @@ class PCA:
             self.explained_variance_ratio_ = np.zeros(self.n_components)
 
         logger.debug(
-            f"PCA fit: {n_samples} samples, {n_features} features → "
-            f"{self.n_components} components, "
-            f"explained variance: {self.explained_variance_ratio_}"
+            "PCA fit: %s samples, %s features → %s components, explained variance: %s",
+            n_samples,
+            n_features,
+            self.n_components,
+            self.explained_variance_ratio_,
         )
 
         return self