feat(job-search): extract keywords from LLM match call instead of heuristics

Piggybacks keyword extraction onto the existing CV-to-job LLM call —
no extra API calls. The system prompt now instructs the model to return
8-12 English job-search terms (job titles, technologies, skills, domains)
in a new `keywords` field alongside the existing score/summary fields.

Keywords flow: LLM JSON → JobMatchResponse.Keywords → CreateJobSearchTokenRequest →
JobSearchTokenEntity.Keywords (stored comma-separated) → JobSearchSessionEntity.Keywords
(copied at session-creation time, no RAG call needed).

Changes:
- Add Keywords to JobMatchResponse, CreateJobSearchTokenRequest, JobSearchTokenEntity
- IJobTokenService.CreateTokenAsync now accepts IReadOnlyList<string> keywords
- JobTokenService: store keywords on token; TriggerStartAsync reads token.Keywords
  instead of fetching CV text from RAG — removes IRagApiClient dependency
- Remove heuristic ExtractKeywords method
- Migration AddKeywordsToJobSearchTokens: adds Keywords column to cvSearch.JobSearchTokens
- Migration UpdateCvMatchSystemPromptKeywords: updates ai.cv-match.system-prompt seed
  to include keywords in the JSON shape

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Apis/cv-search-data/Migrations/CvSearchDbContextModelSnapshot.cs

@@ -197,6 +197,13 @@ namespace CvSearch.Data.Migrations
                     b.Property<DateTime>("ExpiresAt")
                         .HasColumnType("datetime2");
 
+                    b.Property<string>("Keywords")
+                        .IsRequired()
+                        .ValueGeneratedOnAdd()
+                        .HasMaxLength(1000)
+                        .HasColumnType("nvarchar(1000)")
+                        .HasDefaultValue("");
+
                     b.Property<string>("Language")
                         .IsRequired()
                         .ValueGeneratedOnAdd()