fix: lower reweave threshold 0.70→0.55, increase batch 50→200

Orphan ratio at 39.6% (443/1118 claims) vs <15% target. Root cause:
reweave threshold 0.70 too strict for text-embedding-3-small — 56% of
orphans found "no neighbors." At 0.55, dry-run shows 0% no-neighbor
skips. Batch size 200 clears backlog in ~3-4 nights at ~$0.20/run.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

reweave.py

@@ -50,7 +50,7 @@ EDGE_FIELDS = ("supports", "challenges", "challenged_by", "depends_on", "related
 WIKI_LINK_RE = re.compile(r"\[\[([^\]]+)\]\]")
 
 # Thresholds (from calibration data — Mar 28)
-DEFAULT_THRESHOLD = 0.70       # Elbow in score distribution
+DEFAULT_THRESHOLD = 0.55       # Lowered from 0.70 — text-embedding-3-small scores 0.50-0.60 on conceptual matches
 DEFAULT_MAX_ORPHANS = 50       # Keep PRs reviewable
 DEFAULT_MAX_NEIGHBORS = 3      # Don't over-connect
 HAIKU_CONFIDENCE_FLOOR = 0.85  # Below this → default to "related"

scripts/nightly-reweave.sh

@@ -14,8 +14,8 @@ REWEAVE_SCRIPT="${PIPELINE_DIR}/reweave.py"
 LOG_DIR="/opt/teleo-eval/logs"
 LOCK_FILE="/opt/teleo-eval/workspaces/.reweave-nightly.lock"
 
-# Batch size per night — 50 orphans is ~$0.05 in Haiku calls
-BATCH_SIZE=50
+# Batch size per night — 200 orphans is ~$0.20 in Haiku calls
+BATCH_SIZE=200
 
 echo "=== Nightly reweave started at $(date -u +%Y-%m-%dT%H:%M:%SZ) ==="