Refactor Planning Exercise Path Logic and Enhance Semantic Gating

- Replaced the manual path selection logic with a new `pick_best_path_hit` function to streamline the process of selecting the best exercise based on semantic scores and gating criteria.
- Updated the semantic gating logic to apply a soft penalty for off-topic exercises, improving the flexibility of exercise selection.
- Enhanced the handling of title, summary, and goal parameters in semantic checks to ensure more accurate relevance assessments.
- Incremented version to 0.8.189 and updated changelog to reflect these improvements in planning AI functionality.

backend/planning_exercise_path_builder.py

@@ -28,6 +28,7 @@ from planning_exercise_semantics import (
     build_semantic_brief,
     enrich_target_with_semantic_expectations,
     exercise_passes_path_semantic_gate,
+    pick_best_path_hit,
     resolve_semantic_skill_weights,
     step_phase_for_index,
     step_retrieval_query,
@@ -62,25 +63,7 @@ def _pick_best_path_hit(
     *,
     semantic_brief: Optional[PlanningSemanticBrief] = None,
 ) -> Optional[Dict[str, Any]]:
-    best: Optional[Dict[str, Any]] = None
-    best_key: Tuple[float, float] = (-1.0, -1.0)
-    for hit in hits:
-        eid = int(hit["id"])
-        if eid in used_exercise_ids:
-            continue
-        sem = float(hit.get("semantic_score") or 0.0)
-        if semantic_brief and not exercise_passes_path_semantic_gate(
-            semantic_score=sem,
-            title=str(hit.get("title") or ""),
-            brief=semantic_brief,
-        ):
-            continue
-        score = float(hit.get("score") or 0.0)
-        key = (sem, score)
-        if key > best_key:
-            best_key = key
-            best = hit
-    return best
+    return pick_best_path_hit(hits, used_exercise_ids, semantic_brief=semantic_brief)
 
 
 def _build_path_target_profile(
@@ -327,10 +310,12 @@ def _make_bridge_search_fn(
             if exercise_passes_path_semantic_gate(
                 semantic_score=float(h.get("semantic_score") or 0.0),
                 title=str(h.get("title") or ""),
+                summary=str(h.get("summary") or ""),
                 brief=semantic_brief,
+                strict=False,
             )
         ]
-        return gated or hits[:8]
+        return gated or hits[:12]
 
     return _bridge_search
 

backend/planning_exercise_retrieval.py

@@ -286,10 +286,15 @@ def rank_visible_library_hits(
             and not exercise_passes_path_semantic_gate(
                 semantic_score=semantic_score,
                 title=str(row.get("title") or ""),
+                summary=str(row.get("summary") or ""),
+                goal=goals_by_ex.get(eid, ""),
                 brief=semantic_brief,
+                strict=True,
             )
         ):
-            continue
+            score_penalty = 0.42
+        else:
+            score_penalty = 0.0
 
         score = (
             weights.get("semantic", 0.0) * semantic_score
@@ -300,6 +305,7 @@ def rank_visible_library_hits(
             + weights["profile"] * profile_score
             + weights["repeat_unit"] * repeat_unit
             + weights["repeat_group"] * repeat_group
+            - score_penalty
         )
 
         reasons: List[str] = []

backend/planning_exercise_semantics.py

@@ -421,15 +421,22 @@ def _blob_from_fields(
     return " ".join(p for p in parts if p).lower()
 
 
+def _compact_alpha(text: str) -> str:
+    return re.sub(r"[^a-z0-9äöüß]+", "", (text or "").lower())
+
+
 def _phrase_in_blob(phrase: str, blob: str) -> bool:
     ph = _normalize_phrase(phrase)
     if not ph or not blob:
         return False
-    if ph in blob:
+    low = blob.lower()
+    if ph in low:
+        return True
+    if _compact_alpha(ph) and _compact_alpha(ph) in _compact_alpha(low):
         return True
     if " " not in ph:
-        return bool(re.search(rf"\b{re.escape(ph)}\b", blob))
-    return ph in blob
+        return bool(re.search(rf"\b{re.escape(ph)}\b", low))
+    return ph in low
 
 
 def score_exercise_semantic_relevance(
@@ -602,17 +609,95 @@ def exercise_passes_path_semantic_gate(
     semantic_score: float,
     title: str,
     brief: PlanningSemanticBrief,
+    summary: str = "",
+    goal: str = "",
+    strict: bool = True,
 ) -> bool:
     if brief.semantic_strength < 0.55:
         return True
-    if semantic_score >= 0.20:
+
+    blob = _blob_from_fields(title, summary, goal, [])
+    min_score = 0.18 if strict else 0.06
+    if semantic_score >= min_score:
         return True
+
     topic = brief.primary_topic or ""
-    if topic and _phrase_in_blob(topic, (title or "").lower()):
+    if topic and _phrase_in_blob(topic, blob):
         return True
+
+    if not strict:
+        # Mae Geri oft im Fließtext, nicht im Titel
+        if semantic_score >= 0.04 and topic and _phrase_in_blob(topic, blob):
+            return True
+        parts = topic.split()
+        if len(parts) >= 2 and all(_phrase_in_blob(p, blob) for p in parts):
+            return True
+
     return False
 
 
+def pick_best_path_hit(
+    hits: List[Dict[str, Any]],
+    used_exercise_ids: Set[int],
+    *,
+    semantic_brief: Optional[PlanningSemanticBrief] = None,
+) -> Optional[Dict[str, Any]]:
+    """Gestufte Auswahl: strikt → relaxed → bester Semantik-Score."""
+    if not hits:
+        return None
+
+    def _scan(*, strict: bool) -> Optional[Dict[str, Any]]:
+        best: Optional[Dict[str, Any]] = None
+        best_key: Tuple[float, float] = (-1.0, -1.0)
+        for hit in hits:
+            eid = int(hit["id"])
+            if eid in used_exercise_ids:
+                continue
+            sem = float(hit.get("semantic_score") or 0.0)
+            if semantic_brief and not exercise_passes_path_semantic_gate(
+                semantic_score=sem,
+                title=str(hit.get("title") or ""),
+                summary=str(hit.get("summary") or ""),
+                goal="",
+                brief=semantic_brief,
+                strict=strict,
+            ):
+                continue
+            score = float(hit.get("score") or 0.0)
+            key = (sem, score)
+            if key > best_key:
+                best_key = key
+                best = hit
+        return best
+
+    chosen = _scan(strict=True)
+    if chosen:
+        return chosen
+    chosen = _scan(strict=False)
+    if chosen:
+        return chosen
+
+    # Notfall: bester verbleibender Treffer mit Semantik > 0 (Thema trotzdem priorisieren)
+    fallback: Optional[Dict[str, Any]] = None
+    fallback_key: Tuple[float, float] = (-1.0, -1.0)
+    for hit in hits:
+        eid = int(hit["id"])
+        if eid in used_exercise_ids:
+            continue
+        sem = float(hit.get("semantic_score") or 0.0)
+        score = float(hit.get("score") or 0.0)
+        if sem <= 0 and semantic_brief and semantic_brief.primary_topic:
+            topic = semantic_brief.primary_topic
+            blob = (str(hit.get("title") or "") + " " + str(hit.get("summary") or "")).lower()
+            if not _phrase_in_blob(topic, blob):
+                continue
+        key = (sem, score)
+        if key > fallback_key:
+            fallback_key = key
+            fallback = hit
+    return fallback
+
+
 __all__ = [
     "PlanningSemanticBrief",
     "apply_dynamic_retrieval_weights",
@@ -622,6 +707,7 @@ __all__ = [
     "enrich_target_with_semantic_expectations",
     "exercise_passes_path_semantic_gate",
     "merge_semantic_brief_llm",
+    "pick_best_path_hit",
     "resolve_semantic_skill_weights",
     "score_exercise_semantic_relevance",
     "semantic_core_phrases",

backend/tests/test_planning_exercise_path_qa.py

@@ -14,10 +14,36 @@ def test_pick_best_path_hit_prefers_semantic_score():
     assert chosen["id"] == 2
 
 
-def test_pick_best_path_hit_skips_off_topic_when_gate():
-    brief = build_semantic_brief("Mae Geri")
-    hits = [{"id": 1, "title": "Kumite Grundstellung", "score": 0.9, "semantic_score": 0.05}]
-    assert _pick_best_path_hit(hits, set(), semantic_brief=brief) is None
+def test_phrase_compact_match_maegeri():
+    from planning_exercise_semantics import _phrase_in_blob
+
+    assert _phrase_in_blob("mae geri", "Erlernen des Mae-Geri aus Einzelbewegungen")
+    assert _phrase_in_blob("mae geri", "Maegeri Kihon")
+
+
+def test_pick_best_path_hit_fallback_title_only_in_summary():
+    from planning_exercise_semantics import pick_best_path_hit
+
+    brief = build_semantic_brief("Mae Geri Perfektion")
+    hits = [
+        {
+            "id": 1,
+            "title": "Kumite Stellungen",
+            "summary": "",
+            "score": 0.9,
+            "semantic_score": 0.02,
+        },
+        {
+            "id": 2,
+            "title": "Einzelbewegungen",
+            "summary": "Schrittweise Erlernen des Mae Geri",
+            "score": 0.5,
+            "semantic_score": 0.08,
+        },
+    ]
+    chosen = pick_best_path_hit(hits, set(), semantic_brief=brief)
+    assert chosen is not None
+    assert int(chosen["id"]) == 2
 
 
 def test_pick_best_path_hit_skips_used():

backend/version.py

@@ -1,6 +1,6 @@
 # Shinkan Jinkendo Version Information
 
-APP_VERSION = "0.8.188"
+APP_VERSION = "0.8.189"
 BUILD_DATE = "2026-05-23"
 DB_SCHEMA_VERSION = "20260531074"
 
@@ -29,7 +29,7 @@ MODULE_VERSIONS = {
     "skill_profiles": "1.0.0",  # Phase 3: gewichtetes Fähigkeiten-Profil + skill-discovery/suggestions
     "methods": "0.1.0",
     "exercises": "2.37.0",  # Planungs-KI P1: Szenario-Pipeline + Query-Intent-Overlay
-    "planning_exercise_suggest": "0.15.1",  # Pfad: fixes Semantik-Gate + Skill-Erwartungsprofil
+    "planning_exercise_suggest": "0.15.2",  # Pfad-Gate: soft penalty + gestufter Fallback
     "training_units": "0.4.0",  # POST .../publish-to-framework: Ablauf aus geplanter Einheit → Rahmen-Slot-Blueprint
     "training_programs": "0.1.0",
     "planning": "0.15.0",  # Vorlagen: Strukturvorschau, Bearbeiten inkl. Split-Sessions + Beschreibung
@@ -44,6 +44,14 @@ MODULE_VERSIONS = {
 }
 
 CHANGELOG = [
+    {
+        "version": "0.8.189",
+        "date": "2026-05-23",
+        "changes": [
+            "Fix Pfad-Builder: Semantik-Gate zu strikt — soft penalty statt Hard-Filter, gestufter Fallback.",
+            "Mae-Geri-Matching: Titel/Summary/Goal, Mae-Geri/Maegeri-Schreibweisen.",
+        ],
+    },
     {
         "version": "0.8.188",
         "date": "2026-05-23",