refactor(ml): DRY pass — shared sweep helpers + table-driven settings (#161)

Consolidate duplication accrued across the ML tagging + settings backend,
behavior-preserving (over-DRY guard applied — the three auto-apply sweep
BODIES stay separate; only their shared inner helpers are extracted).

- _sigmoid / _conflict_scores / _insert_presentation_review (heads.py): the
  score→prob transform (6 inlined sites), the presentation conflict signal
  (2 sites), and the ring-loud PresentationReview insert (2 sites, single-
  sourced so the mode column can't drift on the shared composite PK).
- _applied_or_rejected (training_data.py): the per-tag "applied ∪ rejected"
  skip-set, byte-identical at 3 sweep sites (heads.py x2, tasks/ml.py ccip).
- ccip sweep divergence fixes: import ccip._FIGURE_KINDS + training_data._l2norm
  instead of local copies that silently drift when the canonical changes.
- MLSettings.load / .load_sync classmethods (mirror ImportSettings); route all
  8 scalar_one singleton reads through them (the session.get None-path stays).
- GET serializers for MLSettings + ImportSettings are now table-driven off the
  same _EDITABLE tuples PATCH writes, so a new field can't be silently absent
  from GET (the split that historically dropped fields).
- AUTO_APPLY_THRESHOLD_MIN/MAX constant single-sources the [0.5,0.999] operating
  range across the service clamp + the 5 API validators.
- test_ml_dry_helpers.py pins _applied_or_rejected + _sigmoid.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NsmJSQxnNxGgtM5Yz4GAqi

backend/app/api/ml_admin.py

@@ -4,6 +4,7 @@ from quart import Blueprint, jsonify, request
 
 from ..extensions import get_session
 from ..models import MLSettings
+from ..services.ml.heads import AUTO_APPLY_THRESHOLD_MAX, AUTO_APPLY_THRESHOLD_MIN
 
 ml_admin_bp = Blueprint("ml_admin", __name__, url_prefix="/api/ml")
 
@@ -83,48 +84,21 @@ async def embedder_models():
 
 @ml_admin_bp.route("/settings", methods=["GET"])
 async def get_settings():
-    from sqlalchemy import select
-
     async with get_session() as session:
-        s = (
-            await session.execute(select(MLSettings).where(MLSettings.id == 1))
-        ).scalar_one()
-    return jsonify(
-        {
-            "cpu_embed_enabled": s.cpu_embed_enabled,
-            "video_frame_interval_seconds": s.video_frame_interval_seconds,
-            "video_max_frames": s.video_max_frames,
-            "embedder_model_version": s.embedder_model_version,
-            "head_min_positives": s.head_min_positives,
-            "head_auto_apply_precision": s.head_auto_apply_precision,
-            "head_auto_apply_enabled": s.head_auto_apply_enabled,
-            "head_auto_apply_min_positives": s.head_auto_apply_min_positives,
-            "ccip_match_threshold": s.ccip_match_threshold,
-            "ccip_auto_apply_enabled": s.ccip_auto_apply_enabled,
-            "ccip_auto_apply_threshold": s.ccip_auto_apply_threshold,
-            "presentation_auto_apply_enabled": s.presentation_auto_apply_enabled,
-            "presentation_auto_apply_threshold": s.presentation_auto_apply_threshold,
-            "presentation_conflict_threshold": s.presentation_conflict_threshold,
-            "process_auto_apply_enabled": s.process_auto_apply_enabled,
-            "process_auto_apply_threshold": s.process_auto_apply_threshold,
-            "process_conflict_threshold": s.process_conflict_threshold,
-            "embedder_model_name": s.embedder_model_name,
-            **{f: getattr(s, f) for f in _DETECTOR_FIELDS},
-        }
-    )
+        s = await MLSettings.load(session)
+    # Table-driven off _EDITABLE (which PATCH also writes) so a new settings field
+    # can never be silently absent from GET — the split that historically dropped
+    # fields. _EDITABLE already includes *_DETECTOR_FIELDS.
+    return jsonify({f: getattr(s, f) for f in _EDITABLE})
 
 
 @ml_admin_bp.route("/settings", methods=["PATCH"])
 async def patch_settings():
-    from sqlalchemy import select
-
     body = await request.get_json()
     if not isinstance(body, dict):
         return jsonify({"error": "body must be an object"}), 400
     async with get_session() as session:
-        s = (
-            await session.execute(select(MLSettings).where(MLSettings.id == 1))
-        ).scalar_one()
+        s = await MLSettings.load(session)
 
         # Merge the patch over current values, then validate the result as a
         # whole — the store-floor invariant couples three fields, so they
@@ -154,24 +128,24 @@ def _validate(p: dict) -> str | None:
     # Head training (#114).
     if int(p["head_min_positives"]) < 1:
         return "head_min_positives must be >= 1"
-    if not (0.5 <= float(p["head_auto_apply_precision"]) <= 0.999):
-        return "head_auto_apply_precision must be between 0.5 and 0.999"
+    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["head_auto_apply_precision"]) <= AUTO_APPLY_THRESHOLD_MAX):
+        return f"head_auto_apply_precision must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
     if int(p["head_auto_apply_min_positives"]) < 1:
         return "head_auto_apply_min_positives must be >= 1"
-    if not (0.5 <= float(p["ccip_match_threshold"]) <= 0.999):
-        return "ccip_match_threshold must be between 0.5 and 0.999"
-    if not (0.5 <= float(p["ccip_auto_apply_threshold"]) <= 0.999):
-        return "ccip_auto_apply_threshold must be between 0.5 and 0.999"
+    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["ccip_match_threshold"]) <= AUTO_APPLY_THRESHOLD_MAX):
+        return f"ccip_match_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
+    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["ccip_auto_apply_threshold"]) <= AUTO_APPLY_THRESHOLD_MAX):
+        return f"ccip_auto_apply_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
     # Presentation chrome auto-hide (#141). Auto-apply runs high (hiding is
     # consequential); the conflict cut is a plain probability [0,1].
-    if not (0.5 <= float(p["presentation_auto_apply_threshold"]) <= 0.999):
-        return "presentation_auto_apply_threshold must be between 0.5 and 0.999"
+    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["presentation_auto_apply_threshold"]) <= AUTO_APPLY_THRESHOLD_MAX):
+        return f"presentation_auto_apply_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
     if not (0.0 <= float(p["presentation_conflict_threshold"]) <= 1.0):
         return "presentation_conflict_threshold must be between 0 and 1"
     # Process auto-apply (#1464). wip/editor stay VISIBLE so a false apply is
     # low-harm (excludes-from-training + a review flag), but keep the same bar.
-    if not (0.5 <= float(p["process_auto_apply_threshold"]) <= 0.999):
-        return "process_auto_apply_threshold must be between 0.5 and 0.999"
+    if not (AUTO_APPLY_THRESHOLD_MIN <= float(p["process_auto_apply_threshold"]) <= AUTO_APPLY_THRESHOLD_MAX):
+        return f"process_auto_apply_threshold must be between {AUTO_APPLY_THRESHOLD_MIN} and {AUTO_APPLY_THRESHOLD_MAX}"
     if not (0.0 <= float(p["process_conflict_threshold"]) <= 1.0):
         return "process_conflict_threshold must be between 0 and 1"
     # Embedder model swap (#1190): both must be non-empty. Changing them means a