going to test deep reply branch merge.

2026-08-24 23:26:44 -04:00
1 parent dc635997a9
commit 8741077173
@@ -131,3 +131,7 @@ Quartz remotes live in `site/` (`cd site; git pull`). After a Quartz pull, re-co
 Current major is **Quartz 5**. Edit `publish/quartz.config.yaml`, not the clone. Canvas uses `@quartz-community/canvas-page`. Drafts use `@quartz-community/remove-draft`.

 Engine license: MIT (Quartz). Vault content: Unlicense (`LICENSE`).
+
+## Notice
+
+I'm not a web dev. Look away at the scripts this is just done because it doesn't exist, so it was done badly.
@@ -7,8 +7,8 @@ author: "0x44"
 handle: 0x44_
 post_id: "1951048949667619280"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Matthew Rusch"
 handle: 2Sexy4MyGPU
 post_id: "1950935584714654191"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Nicholas Wilt"
 handle: CUDAHandbook
 post_id: "1951018231856312578"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Nick Tasios"
 handle: Karyuutensei
 post_id: "1950905493053923408"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "vulkan tamer"
 handle: NickDrisc0ll
 post_id: "1950899486059851961"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "PunteroCrudo"
 handle: PunteroCrudo
 post_id: "1950929528131326083"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Robert William Cummings"
 handle: SquaredApe
 post_id: "1950915633811534012"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Sterence"
 handle: Stererence
 post_id: "1950970860694913461"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "VicThor Dev"
 handle: VicThorDev6
 post_id: "1950927812401004774"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Naf 👨🏽‍💻"
 handle: _naf_90
 post_id: "1950948334002159684"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "David Sena"
 handle: biovf
 post_id: "1950863824522739861"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "D J"
 handle: cyberbemon
 post_id: "1950940978229236154"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Ian Hanschen"
 handle: furan
 post_id: "1950955895351083303"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Ian Hanschen"
 handle: furan
 post_id: "1950956007737463015"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "NEOAethyr"
 handle: konigssohne
 post_id: "1950961762419044639"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Arnaud Carré"
 handle: leonard_coder
 post_id: "1950889332375470135"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Manuel Montoto"
 handle: m6502
 post_id: "1950913023851278616"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "𝖒𝖒𝖆𝖑𝖊𝖝"
 handle: mmalex
 post_id: "1950886322341630045"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Chrinovic Mukanya"
 handle: mu_chrinovic
 post_id: "1950864277624979480"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Michael Spector"
 handle: nullspector
 post_id: "1950865695140364456"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Boga"
 handle: o__boga
 post_id: "1950939824183001106"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "opdroid1234"
 handle: opdroid1234
 post_id: "1950902422362046528"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "PlasmaBitcoin"
 handle: plasmabitcoin
 post_id: "1950963702569771336"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "unevenprankster"
 handle: pranksterware
 post_id: "1950872517700206902"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "᠌᠌ ᠌ ᠌"
 handle: roasted6read
 post_id: "1950914379412566114"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Rúben Cabaço"
 handle: ruben_cabaco
 post_id: "1950894646881611793"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Simplex"
 handle: simplex_fx
 post_id: "1951011391827010009"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Vlad Erium 🇯🇵"
 handle: ssh4net
 post_id: "1950870099809681578"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Mark Coleman"
 handle: thecolemanthe
 post_id: "1950956186783895852"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Alonne"
 handle: totalwert
 post_id: "1950900720770625916"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -31,6 +31,7 @@ parent_post_id: "1950860870818439202"
@NOTimothyLottes

 <video controls src="https://video.twimg.com/tweet_video/GxL93LLW8AA-5hM.mp4"></video>
+
 ## Related

 - Spine: [[archive/threads/NOTimothyLottes/2025-07-31-people-claim-assembly-is-hard-a-good-counter-to]]
@@ -0,0 +1,35 @@
+---
+title: "@NOTimothyLottes I'm gonna start pretending I understood everything you said"
+type: archive
+source: twitter
+source_url: "https://x.com/AnshumanKhanna5/status/1951095609567617288"
+author: "Anshuman Khanna"
+handle: AnshumanKhanna5
+post_id: "1951095609567617288"
+date: 2025-08-01
+archived: 2026-08-24
+draft: false
+tags:
+  - archive
+  - twitter
+  - NOTimothyLottes
+description: "@NOTimothyLottes I'm gonna start pretending I understood everything you said"
+in_reply_to: ""
+parent_post_id: "1950868863836410096"
+---
+
+## Source
+
+- URL: https://x.com/AnshumanKhanna5/status/1951095609567617288
+- Author: Anshuman Khanna (@AnshumanKhanna5)
+- Posted: 2025-08-01 01:40:17
+
+## Branch
+
+**1/**
+
+@NOTimothyLottes I'm gonna start pretending I understood everything you said
+
+## Related
+
+- Spine: [[archive/threads/NOTimothyLottes/2025-07-31-people-claim-assembly-is-hard-a-good-counter-to]]
@@ -7,8 +7,8 @@ author: "Anshuman Khanna"
 handle: AnshumanKhanna5
 post_id: "1951095292377571395"
 date: 2025-08-01
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Ægis Stranding"
 handle: John31625320803
 post_id: "1951198394329829393"
 date: 2025-08-01
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Karthik Kumar Viswanathan"
 handle: _vkaku
 post_id: "1951170620542296537"
 date: 2025-08-01
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "Ben Schulz"
 handle: schulzb589
 post_id: "1951093394786361833"
 date: 2025-08-01
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -7,8 +7,8 @@ author: "NOTimothyLottes"
 handle: NOTimothyLottes
 post_id: "1950860870818439202"
 date: 2025-07-31
-archived: 2026-08-23
-draft: true
+archived: 2026-08-24
+draft: false
 tags:
  - archive
  - twitter
@@ -50,3 +50,5 @@ So Valve standardizing on Proton saves a lot of trouble with porting across ABIs
 **6/**

 Few probably remember the old Unix before pthreads and ELF. It was better then. Much easier to use fork and shm to do platform audio than today. And that holds for all the vintage workstations (which I did implement back in the day)
+
+Branches: [[archive/threads/NOTimothyLottes/2025-07-31-people-claim-assembly-is-hard-a-good-counter-to/2025-08-01-AnshumanKhanna5-im-gonna-start-pretending-i-understood-everything]]
@@ -9,6 +9,7 @@ python C:\projects\Threadwell\scripts\twitter\tw.py graph   --id <snowflake>
 python C:\projects\Threadwell\scripts\twitter\tw.py refresh --id <snowflake> --tip
 python C:\projects\Threadwell\scripts\twitter\tw.py refresh --id <spine-tip> --tip --branch <branch-tip>
 python C:\projects\Threadwell\scripts\twitter\tw.py add-branch --id <original-spine-tip> --from <reply-node>
+python C:\projects\Threadwell\scripts\twitter\tw.py emit --id <spine-tip> --tip --preserve-existing
 python C:\projects\Threadwell\scripts\twitter\tw.py audit-media --id <snowflake>
 python C:\projects\Threadwell\scripts\twitter\tw.py publish --id <snowflake>
 python C:\projects\Threadwell\scripts\twitter\tw.py sync    --handle <handle>
@@ -23,7 +24,9 @@ python C:\projects\Threadwell\scripts\twitter\tw.py migrate-media --all --apply

 `refresh` = refetch (cookies) + ingest + emit `--force` + media_merge. `--tip` treats `--id` as the tip and walks back to the OP regardless of handle. Repeatable `--branch <tip-id>` captures only those additional explicit tip paths and merges them into the same `thread_data.json`; it does not discover replies automatically. Captures run sequentially with gallery-dl retries disabled and five-second extractor/request pacing. Each thread emits exactly one archive directory owned by the OP (the post with `reply_to_id == None`); cross-author responders do not get a directory. Does not flip `draft`. Does not commit. Frozen ids abort.

-`add-branch` incrementally extends an already emitted thread. `--id` must be the original stored spine tip; repeatable `--from <reply-node>` values are each captured once. The command locally retains each node's missing attachment path and entire visible descendant subtree, merges only previously absent posts into the existing `thread_data.json`, downloads media for the new posts, and re-emits with the original spine unchanged. It preserves existing origin/local/fallback/derived/OCR media records and adds provider-origin plus local-copy records for new branch media. A visible leaf is only the deepest reply returned by that capture; the command does not query descendants individually or claim provider-wide completeness. Fallback upload remains a separate explicit action after origin unavailability is confirmed.
+`emit --preserve-existing` is the safe completion step after inspecting a fresh scratch capture. Fresh records win for ids the provider returned; posts present only in the existing emitted `thread_data.json` are retained after the command verifies both captures share a conversation root. This prevents an incomplete gallery-dl refresh from deleting archived replies. The merged scratch dataset keeps the requested `--id` as its stored spine tip before normal emission and media-manifest reconciliation.
+
+`add-branch` incrementally extends an already emitted thread. `--id` must be the original stored spine tip; repeatable `--from <reply-node>` values are each captured once. The command locally retains each node's missing attachment path and entire visible descendant subtree, merges only previously absent posts into the existing `thread_data.json`, downloads media for the new posts, and re-emits with the original spine unchanged. It preserves existing origin/local/fallback/derived/OCR media records and adds provider-origin plus local-copy records for new branch media. A visible leaf is only the deepest reply returned by that capture; the command does not query descendants individually or claim provider-wide completeness. Gallery-dl may return only the ancestor chain when replies are behind nested show-more cursors; then the command adds nothing and known reply/stream-tip ids must be supplied explicitly. Fallback upload remains a separate explicit action after origin unavailability is confirmed.

 Usual publish path after you like the note:

@@ -17,11 +17,13 @@ from twitter.tw import (
    _copy_selected_media,
    _gallery_base_args,
    _merge_branch_posts,
+    _merge_existing_capture,
    _merge_gallery_files,
    _select_branch_capture,
    _validate_capture_ids,
    build_parser,
    cmd_add_branch,
+    cmd_emit,
 )


@@ -333,6 +335,107 @@ class TwMediaCommandTests(unittest.TestCase):
                with self.assertRaisesRegex(SystemExit, "stored spine tip"):
                    cmd_add_branch(Namespace(id="200", from_ids=["300"]))

+    def test_merge_existing_capture_keeps_fresh_and_retains_missing(self) -> None:
+        old_100 = make_post("100", None)
+        old_200 = make_post("200", "100")
+        old_300 = make_post("300", "100")
+        existing = ThreadData(
+            root_post_id="100",
+            posts=(old_100, old_200, old_300),
+            source_url="https://x.com/i/status/100",
+        )
+        fresh_100 = replace(old_100, text="fresh root")
+        fresh_200 = replace(old_200, text="fresh tip")
+        fresh_400 = make_post("400", "200")
+        fresh = ThreadData(
+            root_post_id="200",
+            posts=(fresh_100, fresh_200, fresh_400),
+            source_url="https://x.com/i/status/200",
+        )
+        merged, retained = _merge_existing_capture(fresh, existing, "200")
+        self.assertEqual(
+            merged.posts,
+            (fresh_100, fresh_200, fresh_400, old_300),
+        )
+        self.assertEqual(merged.root_post_id, "200")
+        self.assertEqual(merged.source_url, fresh.source_url)
+        self.assertEqual(retained, ("300",))
+
+    def test_merge_existing_capture_rejects_different_conversation(self) -> None:
+        existing = ThreadData(
+            root_post_id="100",
+            posts=(make_post("100", None),),
+            source_url="https://x.com/i/status/100",
+        )
+        fresh = ThreadData(
+            root_post_id="200",
+            posts=(make_post("200", None),),
+            source_url="https://x.com/i/status/200",
+        )
+        with self.assertRaisesRegex(SystemExit, "different conversation"):
+            _merge_existing_capture(fresh, existing, "200")
+
+    def test_emit_and_refresh_accept_preserve_existing(self) -> None:
+        emit_args = build_parser().parse_args([
+            "emit", "--id", "200", "--tip", "--preserve-existing",
+        ])
+        refresh_args = build_parser().parse_args([
+            "refresh", "--id", "200", "--tip", "--preserve-existing",
+        ])
+        self.assertTrue(emit_args.preserve_existing)
+        self.assertTrue(refresh_args.preserve_existing)
+
+    def test_emit_preserve_existing_merges_before_running_emitter(self) -> None:
+        with TemporaryDirectory() as tmp:
+            root = Path(tmp)
+            scratch = root / "refetch_200"
+            assets = root / "assets"
+            notes = root / "notes"
+            notes.mkdir()
+            existing = ThreadData(
+                root_post_id="100",
+                posts=(
+                    make_post("100", None),
+                    make_post("200", "100"),
+                    make_post("300", "100"),
+                ),
+                source_url="https://x.com/i/status/100",
+            )
+            fresh = ThreadData(
+                root_post_id="200",
+                posts=(
+                    replace(make_post("100", None), text="fresh"),
+                    replace(make_post("200", "100"), text="fresh"),
+                    make_post("400", "200"),
+                ),
+                source_url="https://x.com/i/status/200",
+            )
+            write_test_thread(assets / "thread_data.json", existing)
+            write_test_thread(scratch / "thread_data.json", fresh)
+            with (
+                patch.object(tw_module, "scratch_dir", return_value=scratch),
+                patch.object(tw_module, "dump_dir", return_value=root / "dump"),
+                patch.object(tw_module, "locate", return_value=(assets, notes)),
+                patch.object(tw_module, "locate_all", return_value=[]),
+                patch.object(tw_module, "check_frozen"),
+                patch.object(tw_module, "run") as run,
+                redirect_stdout(StringIO()),
+            ):
+                result = cmd_emit(Namespace(
+                    id="200",
+                    tip=True,
+                    slug=None,
+                    preserve_existing=True,
+                ))
+            self.assertEqual(result, 0)
+            self.assertTrue(run.called)
+            merged = load_thread(scratch / "thread_data.json")
+            self.assertEqual(
+                tuple(post.post_id for post in merged.posts),
+                ("100", "200", "400", "300"),
+            )
+            self.assertEqual(merged.root_post_id, "200")
+
    def test_migrate_defaults_to_dry_run(self) -> None:
        args = build_parser().parse_args(["migrate-media", "--id", "100"])
        self.assertEqual(args.cmd, "migrate-media")
@@ -320,6 +320,25 @@ def _merge_branch_posts(
    )


+def _merge_existing_capture(
+    fresh: ThreadData,
+    existing: ThreadData,
+    tip_id: str,
+) -> tuple[ThreadData, tuple[str, ...]]:
+    """Keep fresh post data while retaining archived posts it omitted."""
+    if tip_id not in {post.post_id for post in fresh.posts}:
+        raise SystemExit(f"spine tip {tip_id} missing from fresh capture")
+    fresh_roots = {
+        post.post_id for post in fresh.posts if post.reply_to_id is None
+    }
+    existing_roots = {
+        post.post_id for post in existing.posts if post.reply_to_id is None
+    }
+    if not fresh_roots or fresh_roots.isdisjoint(existing_roots):
+        raise SystemExit("fresh and existing captures are a different conversation")
+    return _merge_branch_posts(fresh, [existing.posts])
+
+
 def _copy_selected_media(
    source: Path,
    destination: Path,
@@ -447,7 +466,12 @@ def cmd_add_branch(args: argparse.Namespace) -> int:
        }
        _copy_selected_media(capture_dir, output_dir, selected_added)
    _write_thread(output_dir / "thread_data.json", merged)
-    cmd_emit(argparse.Namespace(id=post_id, tip=True, slug=None))
+    cmd_emit(argparse.Namespace(
+        id=post_id,
+        tip=True,
+        slug=None,
+        preserve_existing=False,
+    ))

    added_text = ",".join(added_ids) if added_ids else "-"
    leaf_text = ";".join(
@@ -469,6 +493,23 @@ def cmd_emit(args: argparse.Namespace) -> int:
        src = dump_dir(post_id)
    if not (src / "thread_data.json").is_file():
        raise SystemExit(f"no thread_data.json for {post_id}")
+    if args.preserve_existing:
+        assets, _notes = locate(post_id)
+        if assets is None:
+            raise SystemExit(f"no existing emitted thread for {post_id}")
+        existing_path = assets / "thread_data.json"
+        if not existing_path.is_file():
+            raise SystemExit(f"missing {existing_path}")
+        fresh = load_thread(src / "thread_data.json")
+        existing = load_thread(existing_path)
+        merged, retained_ids = _merge_existing_capture(
+            fresh,
+            existing,
+            post_id,
+        )
+        _write_thread(src / "thread_data.json", merged)
+        retained = ",".join(retained_ids) if retained_ids else "-"
+        print(f"preserve-existing retained={retained}")
    cmd = [
        sys.executable,
        str(HERE / "emit_archive.py"),
@@ -795,6 +836,11 @@ def build_parser() -> argparse.ArgumentParser:
        if name in ("emit", "refresh"):
            p.add_argument("--tip", action="store_true", help="use --id as tip")
            p.add_argument("--slug", default=None)
+            p.add_argument(
+                "--preserve-existing",
+                action="store_true",
+                help="retain archived posts omitted by the fresh capture",
+            )
        if name == "lift":
            p.add_argument("--orig", action="store_true")
        if name == "ocr":