feat(sources): Wayback pass, automatic trimming, detention rule, ten cases re-sourced

Second and third rounds on the dossier pipeline, reviewed locally before commit.

Retrieval
- wayback_pass.py: retries every BLOCKED/DEAD/THIN/ERROR linked source through
  the Wayback Machine; blocks carry the snapshot date, archive URL and the live
  verdict. 143 slots retried: 93 fetched, 37 no snapshot, 12 script shells, 1 PDF.
- fetch_sources.py: fetch_wayback() helper.
- add_extra_sources.py: files staged extra_* finds (web search, not on the DB
  record) into the store with a provenance note.
- Cases re-sourced by web search: 248 (Oslo: Document.no, Avisa Oslo, NRK; the
  linked Le Parisien piece is case 242 and is marked OFF-CASE), 258 Kharkiv,
  260 Singapore, 358 Bangkok, 365 Las Vegas, 388 Verneuil-sur-Seine, 390 Zoersel,
  430 Homestead. 341 of 364 cases now hold a fetched article; 11, 66 and 399
  have no public text source (podcast, police video, direct victim report).

Trimming
- auto_trim.py: case-anchored furniture cut for UNTRIMMED blocks. Finds the body
  run that mentions the case, merges across subheadings and short furniture
  gaps, drops teasers, share bars, date/URL/caption lines and subscription
  pitches; refuses pages with no record term or almost no body. 302 blocks
  trimmed; 16 left on auto-trim-review.md (7 OFF-CASE suspects). Every cut is
  labelled AUTO-TRIMMED, UNREVIEWED in the dossier; the full extract stays in
  staging/. Decisions with anchors in trim-decisions-auto.json.
- build_cases.py / verify_all.py: banners for auto-trimmed and archived blocks,
  staged-file check extended to Wayback blocks, flag legend under the record.

Detention rule
- README "Definitions": the DB field `kidnappings` is the DETENTION violence
  type (victim, guard, staff or relative held to force submission or execute
  the theft), distinct from the Kidnapping scenario (taken away and held).
- detention-flag-review.md / detention-flag-corrections.json: 40 records
  reviewed with evidence; 30 set-to-1 proposals accepted by the owner on
  2026-09-06 (listed in corrections-approved.md), 10 still open.
- apply_detention_wording.py: "Violence Used" in the 70 reviewed summaries now
  names detention explicitly (62 of 70 labelled), supported by the summary's
  own text; idempotent; supersedes the batch scripts' wording.

Worklist and docs
- sofia-worklist.md: 248 decisions, detention rule item replacing the old
  "no abduction" item, fresh-search section for the textless cases.
- README-START-HERE.md: progress notes, run commands, next steps.
- Bug fixed in passing: Wayback blocks stored in-memory text with carriage
  returns; now stored as read back from disk.

verify_all.py PASSES (2321 checks).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GZZENdTLzNGsbNy4DyF1yt

merge-output/build_cases.py

@@ -296,7 +296,14 @@ def render_fetched(entries):
     for i, e in enumerate(keeps, 1):
         flag = {"PARTIAL": "  [PARTIAL — PAYWALLED]",
                 "UNTRIMMED": "  [RAW EXTRACT — NOT YET TRIMMED]"}.get(e["verdict"], "")
+        auto = e["verdict"] == "KEEP" and str(e.get("trimmed_by", "")).startswith("auto")
+        if auto:
+            flag = "  [AUTO-TRIMMED — UNREVIEWED]"
         L += ["", "-" * 96, f"FETCHED ARTICLE {i}{flag}"]
+        if auto:
+            L += ["  !! Furniture was cut by a script keyed on this case's record, not by a person.",
+                  "  !! It may still carry passages about OTHER cases from a round-up article.",
+                  "  !! The full page extract is kept in staging/ if a cut needs revisiting."]
         if e["verdict"] == "UNTRIMMED":
             L += ["  !! This is the whole page as extracted. It still contains site furniture,",
                   "  !! and may contain teaser headlines for UNRELATED cases. Trim on read-through.",
@@ -313,8 +320,14 @@ def render_fetched(entries):
             L.append(f"  Trimmed    {e['cut_note']}")
         if e.get("note"):
             L.append(f"  Note       {e['note']}")
-        L += ["  Caveat     retrieved from a live page on the date above. Unlike text copied",
-              "             from the spreadsheet, there is no second copy to hash it against.",
+        if e.get("archive_url"):
+            L += [f"  Archive    {e['archive_url']}"]
+            L += ["  Caveat     retrieved from a Wayback Machine snapshot, not the live page. The",
+                  "             snapshot date is in the method line; the live URL was unreadable."]
+        else:
+            L += ["  Caveat     retrieved from a live page on the date above. Unlike text copied",
+                  "             from the spreadsheet, there is no second copy to hash it against."]
+        L += [
               "-" * 96, "",
               f"ORIGINAL ({e['language']}, verbatim as retrieved)", "", e["text"]]
         if e.get("translation"):
@@ -331,6 +344,9 @@ def render(rec, arts, notes, fetched=()):
     L += ["=" * 96, hdr, "=" * 96, "", "DATABASE RECORD"]
     for f in FIELD_ORDER:
         L.append(f"  {f:<20}{rec.get(f) if rec.get(f) is not None else '(null)'}")
+    L += ["  (flag legend: 'kidnappings' is the DETENTION flag — 1 when the victim was held against",
+          "   their will at any point, tied, locked in, held at gunpoint or taken away; it is NOT the",
+          "   same as the 'Kidnapping' scenario, which means taken away and held. See README, Definitions.)"]
 
     ov = SUMMARY_OVERRIDES.get(str(rec["id"]))
     if ov: