feat(collect): let --force ignore the re-collect cooldown

--collect 1 <blog> returned an empty worklist whenever the periodic
re-queue branch was still inside its 3-day window, with no way to ask
for the re-collect early. GetPosts now composes that age predicate
conditionally, and the existing global --force flag - already "ignore
cooldown" for --likes - drives it.

Only the age gate drops: NotFound = 0, the IsActive filter and the blog
scoping still apply. The flag is a no-op for mode 0, which re-collects
every post regardless, and says so rather than pretending to act.

Co-Authored-By: Claude Opus 5 <[email protected]>

.github/copilot-instructions.md

@@ -31,7 +31,7 @@ dotnet run -- --test [blogname] [postID]  # Test API for specific post
 - `--test [blogname] [postID]`: Test API note collection
 - `--posts`: Export post blogs to file
 - `--blogs`: Export blog list to file
-- `--collect [0|1] [datetime] [blogname]`: Collect notes for posts in DB. Optional `blogname` restricts the run to one blog (exact match), e.g. `--collect 1 zomb-eh`
+- `--collect [0|1] [datetime] [blogname]`: Collect notes for posts in DB. Optional `blogname` restricts the run to one blog (exact match), e.g. `--collect 1 zomb-eh`. Add `--force` to ignore the periodic re-collect cooldown so already-collected posts are re-queued immediately (mode 1 only)
 - `--blogsR`: Export reply blogs to file
 - `--blogsO [start] [stop]`: Export blogs within range
 

RERUN.sqbpro

@@ -9,8 +9,8 @@ WHERE (BlogName, PostID) IN (
         SELECT 1 
         FROM Notes n 
         WHERE n.PostID = p.PostID 
-          AND n.RootBlogName = p.BlogName
+          AND n.RootBlogId = (SELECT BlogId FROM BlogNames WHERE BlogName = p.BlogName)
-          --AND n.Type NOT IN ('reblog', 'reply')
+          --AND n.TypeId NOT IN (SELECT TypeId FROM NoteTypes WHERE Type IN ('reblog', 'reply'))
     )
     ORDER BY P.PostDate ASC
     --LIMIT 500
@@ -29,10 +29,14 @@ blogname in
 'nudenymph',
 'caylachief'
 
-)</sql><sql name="New Notes">select P.slug, N.replyText, n.RootBlogName, n.PostID, NoteBlogName || '.tumblr.com' as NoteBlogName, DatetimeCrawled, TimeStamp, type, n.RootBlogName || '.tumblr.com/post/' || n.postid, datetime(timestamp, 'unixepoch')
+)</sql><sql name="New Notes">select P.slug, N.replyText, rbn.BlogName as RootBlogName, n.PostID, nbn.BlogName || '.tumblr.com' as NoteBlogName, DatetimeCrawled, TimeStamp, nt.Type, rbn.BlogName || '.tumblr.com/post/' || n.postid, datetime(timestamp, 'unixepoch')
-from Notes N inner join Posts P on p.PostID = n.PostID
+from Notes N
+inner join Posts P on p.PostID = n.PostID
+inner join BlogNames rbn on rbn.BlogId = n.RootBlogId
+inner join BlogNames nbn on nbn.BlogId = n.NoteBlogId
+inner join NoteTypes nt on nt.TypeId = n.TypeId
 where
-DatetimeCrawled &gt; '2026-08-07 11:47:22' and type like 'r%'
+DatetimeCrawled &gt; '2026-08-07 11:47:22' and nt.Type like 'r%'
 and P.IsActive = 1
 order by n.DatetimeCrawled</sql><sql name="Pull Blogs">SELECT distinct
 	'''' || blogname || ''',',
@@ -41,31 +45,36 @@ order by n.DatetimeCrawled</sql><sql name="Pull Blogs">SELECT distinct
 FROM
 	Blogs
 		inner JOIN
-	Notes on notes.noteBlogName = blogs.BlogName
+	Notes on notes.noteBlogId = blogs.BlogId
+		inner JOIN
+	NoteTypes on NoteTypes.TypeId = Notes.TypeId
 WHERE
-	HasBeenOutput = 0 and type = 'reblog'
+	HasBeenOutput = 0 and NoteTypes.Type = 'reblog'
 order by
-	Notes.Type desc,
+	NoteTypes.Type desc,
 	DateAdded desc
 LIMIT 100;</sql><sql name="SQL 7">WITH ReplyCounts AS (
     SELECT
-        NoteBlogName, 
+        NoteBlogId,
         COUNT(DISTINCT replyText) AS DistinctReplyCount
     FROM Notes
 	where replyText &lt;&gt; '.'
-    GROUP BY NoteBlogName
+    GROUP BY NoteBlogId
 )
 SELECT
-    n.RootBlogName || '.tumblr.com/post/' || n.PostID AS PostURL, postid,
+    rbn.BlogName || '.tumblr.com/post/' || n.PostID AS PostURL, postid,
-    n.NoteBlogName,
+    nbn.BlogName AS NoteBlogName,
     n.replyText,
     c.DistinctReplyCount
 FROM Notes n
-JOIN ReplyCounts c ON n.NoteBlogName = c.NoteBlogName
+JOIN ReplyCounts c ON n.NoteBlogId = c.NoteBlogId
-where replyText &lt;&gt; '.' and type &lt;&gt; 'reply'
+JOIN BlogNames rbn ON rbn.BlogId = n.RootBlogId
---AND N.NoteBlogName NOT IN ( 'roadblocker21', 'thesaddemon666', 'edwardabbeyhoffman', 'tattedsoldier20', 'zomb-eh', 'animalistic13', 'indken', 'maccloud1592',
+JOIN BlogNames nbn ON nbn.BlogId = n.NoteBlogId
+JOIN NoteTypes t ON t.TypeId = n.TypeId
+where replyText &lt;&gt; '.' and t.Type &lt;&gt; 'reply'
+--AND nbn.BlogName NOT IN ( 'roadblocker21', 'thesaddemon666', 'edwardabbeyhoffman', 'tattedsoldier20', 'zomb-eh', 'animalistic13', 'indken', 'maccloud1592',
 --'moss-wizard', 'supertrucker12682', 'exploringthrupics', 'padeyepete' )
-order by c.DistinctReplyCount desc, n.NoteBlogName, n.DateModified desc, replyText, RootBlogName, PostID</sql><sql name="Collect">WITH PostsWithCount AS ( SELECT P.BlogName, P.PostID, 1925013599 AS LatestNoteTimestamp, P.NotesGatheredDateTime, COUNT(P.PostID) OVER(PARTITION BY P.BlogName) AS CNT, P.HasNotesGathered, P.NotFound, P.PostDate FROM Posts P WHERE COALESCE(P.IsActive, 1) = 1 ), Unioned AS ( SELECT BlogName, PostID, LatestNoteTimestamp, NotesGatheredDateTime, CNT, PostDate FROM PostsWithCount WHERE NotFound = 0 AND HasNotesGathered = 0 UNION SELECT BlogName, PostID, LatestNoteTimestamp, NotesGatheredDateTime, CNT, PostDate FROM PostsWithCount WHERE BlogName = 'zomb-eh' AND NotFound = 0 AND NotesGatheredDateTime &lt; unixepoch('now', 'localtime', '-3 days') ) SELECT U.BlogName, U.PostID, U.LatestNoteTimestamp, U.NotesGatheredDateTime, U.CNT FROM Unioned U WHERE (U.NotesGatheredDateTime &lt; 1786134037 OR U.NotesGatheredDateTime IS NULL) ORDER BY U.NotesGatheredDateTime, U.PostDate DESC, U.BlogName, U.PostID;</sql><sql name="Del Posts">delete from posts where postid in 
+order by c.DistinctReplyCount desc, nbn.BlogName, n.DateModified desc, replyText, rbn.BlogName, PostID</sql><sql name="Collect">WITH PostsWithCount AS ( SELECT P.BlogName, P.PostID, 1925013599 AS LatestNoteTimestamp, P.NotesGatheredDateTime, COUNT(P.PostID) OVER(PARTITION BY P.BlogName) AS CNT, P.HasNotesGathered, P.NotFound, P.PostDate FROM Posts P WHERE COALESCE(P.IsActive, 1) = 1 ), Unioned AS ( SELECT BlogName, PostID, LatestNoteTimestamp, NotesGatheredDateTime, CNT, PostDate FROM PostsWithCount WHERE NotFound = 0 AND HasNotesGathered = 0 UNION SELECT BlogName, PostID, LatestNoteTimestamp, NotesGatheredDateTime, CNT, PostDate FROM PostsWithCount WHERE BlogName = 'zomb-eh' AND NotFound = 0 AND NotesGatheredDateTime &lt; unixepoch('now', 'localtime', '-3 days') ) SELECT U.BlogName, U.PostID, U.LatestNoteTimestamp, U.NotesGatheredDateTime, U.CNT FROM Unioned U WHERE (U.NotesGatheredDateTime &lt; 1786134037 OR U.NotesGatheredDateTime IS NULL) ORDER BY U.NotesGatheredDateTime, U.PostDate DESC, U.BlogName, U.PostID;</sql><sql name="Del Posts">delete from posts where postid in 
 (
 '741662499571728384',
 178892849664,

TL.sqbpro

@@ -9,16 +9,22 @@ WHERE
 ORDER BY
 	postdate desc</sql><sql name="SQL 2*">SELECT
 	datetime(TimeStamp, 'unixepoch'),
-	RootBlogName || '.tumblr.com/post/' || N.postid,
+	rbn.BlogName || '.tumblr.com/post/' || N.postid,
 	*,
-	NoteBlogName || '.tumblr.com'
+	nbn.BlogName || '.tumblr.com'
 FROM
 	Notes N
 	inner JOIN
-	Posts P on P.PostID = N.PostID and P.BlogName = N.RootBlogName
+	BlogNames rbn on rbn.BlogId = N.RootBlogId
-WHERE	RootBlogName NOT IN ('xlittle-ghost', 'glimmerin-darlin', 'vvenus-child')␍
+	inner JOIN
-		and type like 'r%'␍
+	BlogNames nbn on nbn.BlogId = N.NoteBlogId
-		and RootBlogName = 'zomb-eh'␍
+	inner JOIN
+	NoteTypes t on t.TypeId = N.TypeId
+	inner JOIN
+	Posts P on P.PostID = N.PostID and P.BlogName = rbn.BlogName
+WHERE	rbn.BlogName NOT IN ('xlittle-ghost', 'glimmerin-darlin', 'vvenus-child')
+		and t.Type like 'r%'
+		and rbn.BlogName = 'zomb-eh'
 		and P.HasImage = 1
 ORDER BY
 	TimeStamp desc</sql><current_tab id="1"/></tab_sql></sqlb_project>

URLNotesGrabberCORE/DataAccess.cs

@@ -858,9 +858,10 @@ namespace URLNotesGrabberCORE
         /// 
         /// </summary>
         /// <param name="withoutNotesOnly"></param>
+        /// <param name="ignoreRefreshCooldown">Drops the age gate on the periodic re-queue branch (--force).</param>
         /// <param name="DBPath"></param>
         /// <returns>blogName, postID, lastNoteTimestamp, notesGatheredTimestamp</returns>
-        public static List<Tuple<string, long, long, long>> GetPosts(bool withoutNotesOnly = false, DateTime? beforeDate = null, string? blogName = null, string? DBPath = null)
+        public static List<Tuple<string, long, long, long>> GetPosts(bool withoutNotesOnly = false, DateTime? beforeDate = null, string? blogName = null, bool ignoreRefreshCooldown = false, string? DBPath = null)
         {
             DBPath ??= GetDefaultDbPath();
             using SQLiteConnection connection = new SQLiteConnection("Data Source=" + DBPath);
@@ -895,6 +896,13 @@ namespace URLNotesGrabberCORE
                     // scoped, so it contributes its rows when the filter names zomb-eh and nothing otherwise.
                     // That keeps a filtered worklist a strict subset of the unfiltered one -- "--collect 1 X"
                     // returns exactly the rows "--collect 1" would have returned for X.
+                    //
+                    // --force drops the age gate only. NotFound = 0 and the IsActive/blog scoping above still
+                    // apply: the flag is "re-collect early", not "collect rows every other path excludes".
+                    string refreshCooldownClause = ignoreRefreshCooldown
+                        ? string.Empty
+                        : "      AND NotesGatheredDateTime < unixepoch('now', 'localtime', '-3 days')" + Environment.NewLine;
+
                     string refreshBranch =
                           "" + Environment.NewLine +
                           "    UNION " + Environment.NewLine +
@@ -909,7 +917,7 @@ namespace URLNotesGrabberCORE
                           "    FROM PostsWithCount" + Environment.NewLine +
                           "    WHERE BlogName = 'zomb-eh'" + Environment.NewLine +
                           "      AND NotFound = 0" + Environment.NewLine +
-                          "      AND NotesGatheredDateTime < unixepoch('now', 'localtime', '-3 days')" + Environment.NewLine;
+                          refreshCooldownClause;
 
                     sql = "WITH PostsWithCount AS" + Environment.NewLine +
                           "(" + Environment.NewLine +

URLNotesGrabberCORE/Program.cs

@@ -322,7 +322,12 @@ namespace URLNotesGrabberCORE
                             managedCollectRun = true;
                         }
 
-                        exitCode = CollectNotes(settings.GetValue<string>("PathOutput"), withoutNotesOnly, beforeDate, managedCollectRun, collectBlogName).GetAwaiter().GetResult();
+                        if (forceIgnoreCooldown)
+                            Console.WriteLine(withoutNotesOnly
+                                ? "--force: ignoring the periodic re-collect cooldown; already-collected posts in scope are re-queued now"
+                                : "--force: no effect in mode 0 - a full re-check already re-collects every post");
+
+                        exitCode = CollectNotes(settings.GetValue<string>("PathOutput"), withoutNotesOnly, beforeDate, managedCollectRun, collectBlogName, forceIgnoreCooldown).GetAwaiter().GetResult();
                         break;
 
                     case "--blogsR": //collect notes from all posts
@@ -454,7 +459,7 @@ namespace URLNotesGrabberCORE
 
             Console.WriteLine("--blogs\t For each Blog in DB, write blogname to file");
 
-            Console.WriteLine("--collect [0|1] [datetime] [blogname]\t Collect Notes from API. 1=only posts without notes. 0=full re-check of all posts: a single resumable pass (interrupt & relaunch to resume; stops when complete, retrigger for a new pass). Optional datetime overrides the cutoff and runs as a one-off (bypasses resume tracking). Optional blogname restricts the run to that blog (exact, case-sensitive match) and also runs as a one-off; e.g. \"--collect 1 zomb-eh\". datetime and blogname may be given in either order - use --blog=name if a blog name would otherwise parse as a date.");
+            Console.WriteLine("--collect [0|1] [datetime] [blogname]\t Collect Notes from API. 1=only posts without notes. 0=full re-check of all posts: a single resumable pass (interrupt & relaunch to resume; stops when complete, retrigger for a new pass). Optional datetime overrides the cutoff and runs as a one-off (bypasses resume tracking). Optional blogname restricts the run to that blog (exact, case-sensitive match) and also runs as a one-off; e.g. \"--collect 1 zomb-eh\". datetime and blogname may be given in either order - use --blog=name if a blog name would otherwise parse as a date. Add --force to ignore the periodic re-collect cooldown and re-queue already-collected posts immediately (mode 1 only).");
 
             Console.WriteLine("--blogsR\t For each Note that is a REPLY, write blogname to file ");
 
@@ -466,7 +471,7 @@ namespace URLNotesGrabberCORE
 
             Console.WriteLine("--likes\t Fetch likes: initial backfill for new blogs, incremental refresh for blogs past cooldown. Optional blog name forces single-blog run.");
 
-            Console.WriteLine("--force\t (with --likes) Ignore cooldown and refresh every fully-backfilled blog");
+            Console.WriteLine("--force\t Ignore refresh cooldowns: with --likes, refresh every fully-backfilled blog; with --collect 1, re-queue already-collected posts without waiting out their cooldown");
 
             Console.WriteLine("--urldump\t Scan all posts' text columns and extract suspected URLs to configured file");
 
@@ -1345,15 +1350,17 @@ if (shouldInsert)
         // blipping on one post. Past this, skipping post-by-post would just hammer a closed door.
         const int MaxConsecutiveTransient = 10;
 
-        static async Task<int> CollectNotes(string outPath, bool withoutNotesOnly = true, DateTime? beforeDate = null, bool managedRun = false, string? blogName = null)
+        static async Task<int> CollectNotes(string outPath, bool withoutNotesOnly = true, DateTime? beforeDate = null, bool managedRun = false, string? blogName = null, bool ignoreRefreshCooldown = false)
         {
-            List<Tuple<string, long, long, long>> posts = DataAccess.GetPosts(withoutNotesOnly, beforeDate, blogName);
+            List<Tuple<string, long, long, long>> posts = DataAccess.GetPosts(withoutNotesOnly, beforeDate, blogName, ignoreRefreshCooldown);
 
             if (posts.Count == 0 && !string.IsNullOrWhiteSpace(blogName))
             {
                 // BlogName is matched exactly, so a typo or a case mismatch looks identical to "nothing
                 // left to collect". Say so rather than reporting a silent, instant success.
                 Console.WriteLine($"No posts to collect for blog '{blogName}'. Either it is fully collected, or the name does not match a stored blog (the match is case-sensitive).");
+                if (withoutNotesOnly && !ignoreRefreshCooldown)
+                    Console.WriteLine("Already-collected posts are re-queued only once their cooldown elapses; add --force to re-collect them now.");
                 return 0;
             }
 
@@ -1451,7 +1458,7 @@ if (shouldInsert)
                         }
 
                         // Re-fetch the updated list after processing the current post
-                        posts = DataAccess.GetPosts(withoutNotesOnly, beforeDate, blogName);
+                        posts = DataAccess.GetPosts(withoutNotesOnly, beforeDate, blogName, ignoreRefreshCooldown);
                     }
                 }