From 71b7a310ce938f072fe20f27eeeadd40685f1ad1 Mon Sep 17 00:00:00 2001
From: Christophe Besson <cbesson@gmail.com>
Date: Sat, 29 Aug 2026 14:58:30 +0200
Subject: fix(node): correct TMDB movie matching, per-file overrides, rematch

A batch of wrong poster-grid matches found live on a real library
(2026-08-29): a two-volume film's second part matched the first; a
numbered sequel matched a same-year making-of documentary; several
entries of one franchise matched a single early entry whose localized
TMDB title is the franchise name; one matched nothing. One mechanism:
_tmdb_search returned the first candidate query whose title-similarity
ratio merely cleared 0.6, before alternative_title / the Roman-numeral
variant was ever tried.

Matching:
- title_parse: fold guessit's volume/part number back into display_title
  so the parts of a multi-part film stay distinct in the query, the card
  and the override.
- _tmdb_search: keep a strong PASS 1 fast path (ratio >= 0.85, one
  request), otherwise score every candidate query and pick the best. A
  year-exact rescue lifts a sub-0.6 top hit to the confidence floor only
  when TMDB's own year-filtered result lands exactly on the filename's
  year. No local re-ranking of any single result list; no tmdb.py change.

Fix match / rematch:
- _admin_exec_tmdb_override: a movie override touches its own file only
  (guessit gives a whole franchise one display_title); a show override
  still fans out. Corrected files are marked in media_cache.tmdb_override.
- media_cache: tmdb_override table; clear_file_tmdb / clear_tmdb_matches
  drop auto-resolved matches while sparing manual corrections.
- ops.rematch_video + `meshbay-node video rematch` (loopback endpoint +
  CLI verb): re-resolve a group's video matches after a matcher fix.
  file_tmdb is keyed by content hash and otherwise only pruned on
  deletion, so nothing dislodged a cached match before.
- a rename now drops the stale auto match too (daemon
  _reenrich_renamed_video_entries).

UI:
- VideoDetailModal shows the source filename and resolved TMDB id; an
  unmatched poster gets a badge (3 new video.* i18n keys x 10 locales).
  So a wrong match can actually be identified before hitting Fix match.

docs/mediacenter.md 10.1 records this and the V8-V13 follow-up backlog
(show-branch ladder, year-aware _best_match, wider sequel_variants, the
0.6-0.85 extra calls, movie grid merge, per-card rematch).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018BMLQjqFGCize2KtNBT79v
---
 packages/meshbay-node/src/meshbay_node/ops.py | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'packages/meshbay-node/src/meshbay_node/ops.py')

diff --git a/packages/meshbay-node/src/meshbay_node/ops.py b/packages/meshbay-node/src/meshbay_node/ops.py
index cb8e01e..c921b05 100644
--- a/packages/meshbay-node/src/meshbay_node/ops.py
+++ b/packages/meshbay-node/src/meshbay_node/ops.py
@@ -974,6 +974,31 @@ async def prune_index_cache(state: dict) -> dict:
     return {"status": "pruned", "removed": len(stale), "kept": len(paths) - len(stale)}
 
 
+# ── Videos: force TMDB re-matching ───────────────────────────────────────────
+#
+# `media_cache.file_tmdb` is keyed by a file's content hash and is otherwise
+# only pruned on deletion, so a fixed matcher/parser never dislodges a match
+# already in cache. This drops a group's *auto-resolved* mappings so the
+# next `media_meta_req` for each poster tile re-resolves against the current
+# code. Re-resolution is lazy and calls TMDB once per unique title — real
+# API budget — so this is an explicit operator action, never a background job.
+# Manual "Fix match" corrections (media_cache.tmdb_override) are kept.
+
+async def rematch_video(state: dict, group_id: str) -> dict:
+    media_cache = state.get("media_cache")
+    if media_cache is None:
+        raise OpError("No media cache in this process", status=503)
+    indexer = (state.get("indexers") or {}).get(group_id)
+    if indexer is None:
+        raise OpError("Unknown group", status=404)
+    file_ids = [e.id for e in indexer.index.entries if e.type == "video"]
+    removed = await media_cache.clear_tmdb_matches(file_ids)
+    log.info("Video rematch for group %s: %d auto match(es) cleared across %d video file(s)",
+             group_id[:8], removed, len(file_ids))
+    return {"status": "cleared", "removed": removed, "videos": len(file_ids),
+            "group_id": group_id}
+
+
 # ── Reload ──────────────────────────────────────────────────────────────────
 
 async def reload_config(state: dict) -> dict:
-- 
cgit v1.2.3