[Ingest] Persistent crawl run-log + per-source breakdown on admin queue

Each ingestion run now records an IngestionRun row (found/queued/published/flagged/spam/duplicates + a per-source detail string). Admin → صف آگهی‌ها shows a «تاریخچه جمع‌آوری» table of the last 15 runs (hover a row for the per-source breakdown), so admins can see how much each source found vs added over time. IngestionSummary gains TotalFetched. Migration: IngestionRuns table.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

src/JobsMedical.Web/Data/AppDbContext.cs

@@ -30,6 +30,7 @@ public class AppDbContext : DbContext, IDataProtectionKeyContext
     public DbSet<Report> Reports => Set<Report>();
     public DbSet<FacilityDocument> FacilityDocuments => Set<FacilityDocument>();
     public DbSet<JobAlert> JobAlerts => Set<JobAlert>();
+    public DbSet<IngestionRun> IngestionRuns => Set<IngestionRun>();
     public DbSet<Review> Reviews => Set<Review>();
 
     protected override void OnModelCreating(ModelBuilder b)

src/JobsMedical.Web/Migrations/20260608024637_IngestionRunLog.cs

@@ -0,0 +1,43 @@
+using System;
+using Microsoft.EntityFrameworkCore.Migrations;
+using Npgsql.EntityFrameworkCore.PostgreSQL.Metadata;
+
+#nullable disable
+
+namespace JobsMedical.Web.Migrations
+{
+    /// <inheritdoc />
+    public partial class IngestionRunLog : Migration
+    {
+        /// <inheritdoc />
+        protected override void Up(MigrationBuilder migrationBuilder)
+        {
+            migrationBuilder.CreateTable(
+                name: "IngestionRuns",
+                columns: table => new
+                {
+                    Id = table.Column<int>(type: "integer", nullable: false)
+                        .Annotation("Npgsql:ValueGenerationStrategy", NpgsqlValueGenerationStrategy.IdentityByDefaultColumn),
+                    RunAt = table.Column<DateTime>(type: "timestamp with time zone", nullable: false),
+                    Fetched = table.Column<int>(type: "integer", nullable: false),
+                    Queued = table.Column<int>(type: "integer", nullable: false),
+                    Published = table.Column<int>(type: "integer", nullable: false),
+                    Flagged = table.Column<int>(type: "integer", nullable: false),
+                    Spam = table.Column<int>(type: "integer", nullable: false),
+                    Duplicates = table.Column<int>(type: "integer", nullable: false),
+                    Detail = table.Column<string>(type: "character varying(2000)", maxLength: 2000, nullable: true)
+                },
+                constraints: table =>
+                {
+                    table.PrimaryKey("PK_IngestionRuns", x => x.Id);
+                });
+        }
+
+        /// <inheritdoc />
+        protected override void Down(MigrationBuilder migrationBuilder)
+        {
+            migrationBuilder.DropTable(
+                name: "IngestionRuns");
+        }
+    }
+}

src/JobsMedical.Web/Migrations/AppDbContextModelSnapshot.cs

@@ -421,6 +421,44 @@ namespace JobsMedical.Web.Migrations
                     b.ToTable("FacilityDocuments");
                 });
 
+            modelBuilder.Entity("JobsMedical.Web.Models.IngestionRun", b =>
+                {
+                    b.Property<int>("Id")
+                        .ValueGeneratedOnAdd()
+                        .HasColumnType("integer");
+
+                    NpgsqlPropertyBuilderExtensions.UseIdentityByDefaultColumn(b.Property<int>("Id"));
+
+                    b.Property<string>("Detail")
+                        .HasMaxLength(2000)
+                        .HasColumnType("character varying(2000)");
+
+                    b.Property<int>("Duplicates")
+                        .HasColumnType("integer");
+
+                    b.Property<int>("Fetched")
+                        .HasColumnType("integer");
+
+                    b.Property<int>("Flagged")
+                        .HasColumnType("integer");
+
+                    b.Property<int>("Published")
+                        .HasColumnType("integer");
+
+                    b.Property<int>("Queued")
+                        .HasColumnType("integer");
+
+                    b.Property<DateTime>("RunAt")
+                        .HasColumnType("timestamp with time zone");
+
+                    b.Property<int>("Spam")
+                        .HasColumnType("integer");
+
+                    b.HasKey("Id");
+
+                    b.ToTable("IngestionRuns");
+                });
+
             modelBuilder.Entity("JobsMedical.Web.Models.InterestEvent", b =>
                 {
                     b.Property<long>("Id")

src/JobsMedical.Web/Models/IngestionRun.cs

@@ -0,0 +1,21 @@
+using System.ComponentModel.DataAnnotations;
+
+namespace JobsMedical.Web.Models;
+
+/// <summary>One ingestion run's outcome — kept so admins see a history of what was crawled,
+/// how much was found, queued, published, flagged, etc. (with a per-source breakdown).</summary>
+public class IngestionRun
+{
+    public int Id { get; set; }
+    public DateTime RunAt { get; set; } = DateTime.UtcNow;
+
+    public int Fetched { get; set; }       // total items pulled from all sources
+    public int Queued { get; set; }        // sent to the review queue
+    public int Published { get; set; }     // auto-published
+    public int Flagged { get; set; }       // needs-review
+    public int Spam { get; set; }          // discarded as spam/irrelevant
+    public int Duplicates { get; set; }    // skipped (already seen)
+
+    /// <summary>Human-readable per-source breakdown, e.g. "دیوار: یافت ۱۲…؛ مدجابز: یافت ۴۰…".</summary>
+    [MaxLength(2000)] public string? Detail { get; set; }
+}

src/JobsMedical.Web/Pages/Admin/Index.cshtml

@@ -62,6 +62,40 @@
         </aside>
 
         <div>
+            @if (Model.Runs.Count > 0)
+            {
+                <h2 style="font-size:20px; margin-top:0;">تاریخچه جمع‌آوری</h2>
+                <div class="card card-pad" style="margin-bottom:18px; overflow-x:auto;">
+                    <table style="width:100%; border-collapse:collapse; font-size:13px; white-space:nowrap;">
+                        <thead>
+                            <tr style="text-align:start; color:var(--muted);">
+                                <th style="padding:6px 8px;">زمان</th>
+                                <th style="padding:6px 8px;">یافت‌شده</th>
+                                <th style="padding:6px 8px;">صف</th>
+                                <th style="padding:6px 8px;">منتشر</th>
+                                <th style="padding:6px 8px;">پرچم</th>
+                                <th style="padding:6px 8px;">اسپم</th>
+                                <th style="padding:6px 8px;">تکراری</th>
+                            </tr>
+                        </thead>
+                        <tbody>
+                            @foreach (var run in Model.Runs)
+                            {
+                                <tr style="border-top:1px solid var(--line);" title="@run.Detail">
+                                    <td style="padding:6px 8px;">@JalaliDate.ToLongDate(DateOnly.FromDateTime(run.RunAt)) @run.RunAt.ToString("HH:mm")</td>
+                                    <td style="padding:6px 8px;">@JalaliDate.ToPersianDigits(run.Fetched.ToString())</td>
+                                    <td style="padding:6px 8px;">@JalaliDate.ToPersianDigits(run.Queued.ToString())</td>
+                                    <td style="padding:6px 8px; color:var(--primary-dark); font-weight:700;">@JalaliDate.ToPersianDigits(run.Published.ToString())</td>
+                                    <td style="padding:6px 8px;">@JalaliDate.ToPersianDigits(run.Flagged.ToString())</td>
+                                    <td style="padding:6px 8px;">@JalaliDate.ToPersianDigits(run.Spam.ToString())</td>
+                                    <td style="padding:6px 8px;">@JalaliDate.ToPersianDigits(run.Duplicates.ToString())</td>
+                                </tr>
+                            }
+                        </tbody>
+                    </table>
+                    <p class="muted" style="font-size:11px; margin:8px 0 0;">جزئیات هر منبع را با نگه‌داشتن نشانگر روی هر ردیف ببین. لاگ کامل: <code dir="ltr">docker logs hamkadr_api</code></p>
+                </div>
+            }
             <h2 style="font-size:20px; margin-top:0;">صف بررسی</h2>
             @if (Model.Queue.Count == 0)
             {

src/JobsMedical.Web/Pages/Admin/Index.cshtml.cs

@@ -25,6 +25,7 @@ public class IndexModel : PageModel
     public IReadOnlyList<string> SourceNames { get; private set; } = new List<string>();
     public int PublishedShifts { get; private set; }
     public int PublishedJobs { get; private set; }
+    public List<IngestionRun> Runs { get; private set; } = new();
 
     [BindProperty] public string? SourceChannel { get; set; }
     [BindProperty] public string? RawText { get; set; }
@@ -67,5 +68,6 @@ public class IndexModel : PageModel
         SourceNames = _ingest.SourceNames;
         PublishedShifts = await _db.Shifts.CountAsync(s => s.Source != ShiftSource.Direct);
         PublishedJobs = await _db.JobOpenings.CountAsync();
+        Runs = await _db.IngestionRuns.OrderByDescending(r => r.RunAt).Take(15).ToListAsync();
     }
 }

src/JobsMedical.Web/Services/Scraping/IngestionService.cs

@@ -11,6 +11,7 @@ public record SourceResult(string Source, int Fetched, int Queued, int Published
 
 public record IngestionSummary(List<SourceResult> Sources)
 {
+    public int TotalFetched => Sources.Sum(s => s.Fetched);
     public int TotalQueued => Sources.Sum(s => s.Queued);
     public int TotalPublished => Sources.Sum(s => s.Published);
     public int TotalFlagged => Sources.Sum(s => s.Flagged);
@@ -108,7 +109,27 @@ public class IngestionService
                 source.Name, fetched, queued, published, flagged, spam, dupes);
         }
 
-        return new IngestionSummary(results);
+        var summary = new IngestionSummary(results);
+
+        // Persist a run-log row so admins get a crawl history (with a per-source breakdown).
+        if (results.Count > 0)
+        {
+            var detail = string.Join("؛ ", results.Select(r =>
+                $"{r.Source}: یافت {r.Fetched}، صف {r.Queued}، منتشر {r.Published}، پرچم {r.Flagged}، اسپم {r.Spam}، تکراری {r.Duplicates}"));
+            _db.IngestionRuns.Add(new IngestionRun
+            {
+                Fetched = summary.TotalFetched,
+                Queued = summary.TotalQueued,
+                Published = summary.TotalPublished,
+                Flagged = summary.TotalFlagged,
+                Spam = summary.TotalSpam,
+                Duplicates = summary.TotalDuplicates,
+                Detail = detail.Length > 2000 ? detail[..2000] : detail,
+            });
+            await _db.SaveChangesAsync(ct);
+        }
+
+        return summary;
     }
 
     private static (RawListingStatus status, string? reason, int confidence) Decide(