From e7dc402d9e6013d3e21e263e63bdf9dcb856a0c3 Mon Sep 17 00:00:00 2001
From: jenstandstad <jens.tandstad@gmail.com>
Date: Sat, 25 Jul 2026 21:33:51 +0200
Subject: [PATCH] Adding fixes to build

---
 example/media/videos/videos.json |  2 +-
 gnommo/cli.py                    |  8 ++++----
 gnommo/scaffold.py               | 30 +++++++++++++++++++++++++++---
 3 files changed, 32 insertions(+), 8 deletions(-)

diff --git a/example/media/videos/videos.json b/example/media/videos/videos.json
index 44f3270..a4a634d 100644
--- a/example/media/videos/videos.json
+++ b/example/media/videos/videos.json
@@ -25,7 +25,7 @@
     "source_file": "Logo.mov",
     "is_shared": true,
     "cutout": "fullscreen",
-    "pause_narration": 17,
+    "pause_narration": 14,
     "take": 25,
     "skip": 0
   },
diff --git a/gnommo/cli.py b/gnommo/cli.py
index 35264a6..c8e15c7 100644
--- a/gnommo/cli.py
+++ b/gnommo/cli.py
@@ -4924,10 +4924,10 @@ def _cmd_render_impl(
             # Override path: the marker_timings the plan used were EFFECTIVE
             # narration (narration_time + adjustment). narration_time itself is
             # owned by events.json — restore it so the effective value doesn't leak
-            # into the stored narration_time.
-            _by_id = {e["id"]: e for e in _existing_events}
-            for e in _events:
-                _old = _by_id.get(e["id"])
+            # into the stored narration_time. Pair by ordinal (not id) so a marker
+            # reused several times keeps each occurrence's own narration_time
+            # instead of collapsing onto the last occurrence's value.
+            for e, _old in _scaffold.pair_events_by_ordinal(_events, _existing_events):
                 if _old is not None and _old.get("narration_time") is not None:
                     e["narration_time"] = _old["narration_time"]
         else:
diff --git a/gnommo/scaffold.py b/gnommo/scaffold.py
index 811e934..2db1fe3 100644
--- a/gnommo/scaffold.py
+++ b/gnommo/scaffold.py
@@ -236,17 +236,41 @@ def reinterpolate_events(events: list[dict]) -> None:
 
 # ── merge: human tweaks survive re-align ──────────────────────────────────────
 
+def pair_events_by_ordinal(fresh: list[dict], existing: Optional[list[dict]]):
+    """Yield (fresh_event, matching_existing_event_or_None) pairs.
+
+    Both lists are in deterministic manuscript order, so the Nth occurrence of a
+    given id in `fresh` corresponds to the Nth occurrence in `existing`. Keying by
+    id alone would collapse legitimately-repeated markers (e.g. the same video
+    reused at two points in the script) onto a single old entry and cross-
+    contaminate their timings/tweaks.
+    """
+    from collections import defaultdict
+
+    buckets: dict = defaultdict(list)
+    for e in existing or []:
+        buckets[e.get("id")].append(e)
+    counters: dict = defaultdict(int)
+    for e in fresh:
+        mid = e.get("id")
+        idx = counters[mid]
+        counters[mid] += 1
+        bucket = buckets.get(mid, [])
+        yield e, (bucket[idx] if idx < len(bucket) else None)
+
+
 def merge_events(fresh: list[dict], existing: Optional[list[dict]]) -> list[dict]:
     """Carry each id's `adjustment` (the human tweak) from the existing events.json
     onto the freshly-derived events. narration_time and mapping come from `fresh`
     (aligner-owned); the tweak is relative so it stays meaningful even when the
     alignment shifts. New ids are added; ids gone from the manuscript are dropped.
+
+    Matching is by ordinal (Nth occurrence to Nth occurrence), not by id, so a
+    marker reused several times keeps each occurrence's own tweak.
     """
     if not existing:
         return fresh
-    by_id = {e.get("id"): e for e in existing}
-    for e in fresh:
-        old = by_id.get(e["id"])
+    for e, old in pair_events_by_ordinal(fresh, existing):
         if old is not None and old.get("adjustment"):
             e["adjustment"] = old["adjustment"]
     return fresh