feat(analysis): vision client + system prompt + AnalysisConfig

The OpenAI-compatible vision client and the bounded prompt/output handling
for the analysis worker (no DB, fully unit-tested):

- analysis::prompt: terse system prompt carrying the JSON schema, the OCR
  kind / content-warning vocabularies, and the output-size caps.
- analysis::vision: VisionClient (downscale via the new `image` dep →
  base64 data-URL → chat/completions with an image_url part), plus pure
  parse_chat_completion (fence/prose-tolerant) and sanitize (drop empty
  OCR, truncate, clamp tags to 10 via the shared page-tag normalizer,
  filter unknown warnings).
- config::AnalysisConfig extended with endpoint/model/api_key/timeouts/
  max_tokens/max_image_dim/max_image_bytes + from_env.
- Deps: add `image` (jpeg/png/webp), reqwest `json` feature. Expose
  api::page_tags::normalize_tag as pub(crate) for reuse.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

backend/src/api/page_tags.rs

@@ -115,7 +115,7 @@ fn is_invisible_format(c: char) -> bool {
     )
 }
 
-fn normalize_tag(input: &str) -> AppResult<String> {
+pub(crate) fn normalize_tag(input: &str) -> AppResult<String> {
     // Fast-fail on absurd input before allocating in lowercase /
     // whitespace passes. Cheap and bounds worst-case work.
     if input.len() > MAX_TAG_BYTES {