feat(ai-ux): deduplicate AI queries, handle ServiceUnavailable retries, and optimize reader canvas graph prerendering (#44)

This Pull Request encapsulates all outstanding AI, Blazor InteractiveAuto lifecycle, pgvector, and Firefox authorization/session compatibility fixes.

### Key Accomplishments:
1. **Concurrent Request Deduplication (Option B):** Implemented a thread-safe active task registry in `KnowledgeService` that groups concurrent graph extraction queries for the same content, preventing duplicate AI calls completely.
2. **Resilience Strategy for Downstream Demands:** Extended the `ai-retry` resilience pipeline to automatically intercept and retry on temporary Google API `503 ServiceUnavailable` / `high demand` spikes.
3. **Interactive Graph Generation Guard (Option A):** Prevented server-side prerender-phase graph requests in the reader canvas component.
4. **Firefox Compatibility & Cookie Handler:** Implemented an authentication endpoint and hybrid hidden-form submission flow to solve login, registration, and logout redirections and cookies securely.
5. **Autoscrolling & Graph Exclusions:** Added concept-to-block smooth scrolling, active block badging, and filtered out markdown code blocks from being extracted as nodes.

All unit tests compiled and passed 100% cleanly.

---------

Co-authored-by: Marek Jasiński <jasins.marek@gmail.com>
Reviewed-on: #44
Co-authored-by: Antigravity <antigravity@google.com>
Co-committed-by: Antigravity <antigravity@google.com>

src/NexusReader.Data/Migrations/AppDbContextModelSnapshot.cs

@@ -189,6 +189,9 @@ namespace NexusReader.Data.Migrations
                     b.Property<string>("CoverUrl")
                         .HasColumnType("text");
 
+                    b.Property<string>("Description")
+                        .HasColumnType("text");
+
                     b.Property<string>("FilePath")
                         .IsRequired()
                         .HasColumnType("text");