backend/planning_exercise_form_context.py

@@ -6,7 +6,7 @@ Wird als ``planning_context_json`` in Übungs-Prompts (summary, skills, instruct
 from __future__ import annotations
 
 import json
-from typing import Any, Dict, Mapping, Optional
+from typing import Any, Dict, List, Mapping, Optional
 
 _MAX_JSON_CHARS = 6000
 _MAX_STRING = 800
@@ -85,6 +85,73 @@ def planning_context_prompt_variables(
     }
 
 
+def build_progression_gap_snapshot(
+    *,
+    goal_analysis: Optional[Mapping[str, Any]] = None,
+    resolved_structured: Optional[Mapping[str, Any]] = None,
+    stage_spec: Optional[Mapping[str, Any]] = None,
+    semantic_brief: Optional[Mapping[str, Any]] = None,
+) -> Dict[str, Any]:
+    """Kompakter Roadmap-Kontext für Lücken-Übungen (Start, Ziel, Stufe, Fähigkeiten-Hinweise)."""
+    ga = dict(goal_analysis or {})
+    rs = dict(resolved_structured or {})
+    spec = dict(stage_spec or {})
+    brief = dict(semantic_brief or {})
+
+    start = _trim_str(rs.get("start_situation") or ga.get("start_assumption"))
+    target = _trim_str(rs.get("target_state") or ga.get("target_state"))
+    notes = _trim_str(rs.get("roadmap_notes"))
+    topic = _trim_str(ga.get("primary_topic") or brief.get("primary_topic"))
+
+    skill_hints: List[str] = []
+    for item in (brief.get("must_phrases") or [])[:4]:
+        t = _trim_str(item, limit=120)
+        if t:
+            skill_hints.append(t)
+    arc = brief.get("development_arc")
+    if isinstance(arc, list) and arc:
+        skill_hints.append(f"Entwicklungsbogen: {' → '.join(str(x) for x in arc[:5])}")
+
+    success_path = [
+        _trim_str(x, limit=200)
+        for x in (ga.get("success_criteria") or [])
+        if _trim_str(x, limit=200)
+    ][:4]
+    stage_success = [
+        _trim_str(x, limit=200)
+        for x in (spec.get("success_criteria") or [])
+        if _trim_str(x, limit=200)
+    ][:4]
+    load_profile = [
+        _trim_str(x, limit=80)
+        for x in (spec.get("load_profile") or [])
+        if _trim_str(x, limit=80)
+    ][:6]
+    anti_patterns = [
+        _trim_str(x, limit=200)
+        for x in (spec.get("anti_patterns") or [])
+        if _trim_str(x, limit=200)
+    ][:3]
+
+    snap: Dict[str, Any] = {
+        "primary_topic": topic,
+        "start_situation": start,
+        "target_state": target,
+        "roadmap_notes": notes,
+        "stage_learning_goal": _trim_str(
+            spec.get("learning_goal"), limit=1200
+        ),
+        "stage_phase": _trim_str(spec.get("phase")),
+        "stage_exercise_type": _trim_str(spec.get("exercise_type")),
+        "stage_load_profile": load_profile or None,
+        "stage_success_criteria": stage_success or None,
+        "stage_anti_patterns": anti_patterns or None,
+        "path_success_criteria": success_path or None,
+        "skill_hints": skill_hints or None,
+    }
+    return {k: v for k, v in snap.items() if v is not None and v != "" and v != []}
+
+
 def build_progression_path_gap_planning_context(
     *,
     goal_query: str,
@@ -97,6 +164,10 @@ def build_progression_path_gap_planning_context(
     major_step_count: Optional[int] = None,
     roadmap_phase: Optional[str] = None,
     roadmap_learning_goal: Optional[str] = None,
+    goal_analysis: Optional[Mapping[str, Any]] = None,
+    resolved_structured: Optional[Mapping[str, Any]] = None,
+    stage_spec: Optional[Mapping[str, Any]] = None,
+    semantic_brief: Optional[Mapping[str, Any]] = None,
 ) -> Dict[str, Any]:
     """Kontext für KI-Neuanlage aus Progressionsgraph-Pfad-Lücke."""
     offer = offer or {}
@@ -127,10 +198,18 @@ def build_progression_path_gap_planning_context(
         "path_step_count": path_step_count,
         "major_step_count": major_step_count,
     }
+    snap = build_progression_gap_snapshot(
+        goal_analysis=goal_analysis,
+        resolved_structured=resolved_structured,
+        stage_spec=stage_spec,
+        semantic_brief=semantic_brief,
+    )
+    ctx.update(snap)
     return sanitize_planning_context_for_ai(ctx)
 
 
 __all__ = [
+    "build_progression_gap_snapshot",
     "build_progression_path_gap_planning_context",
     "compact_planning_context_json",
     "planning_context_prompt_variables",

backend/planning_exercise_path_ai_fill.py

@@ -12,7 +12,8 @@ from ai_prompt_job import run_exercise_form_ai_suggestion
 from exercise_ai import strip_html_to_plain
 
 from planning_exercise_path_qa import find_step_pair_index
-from planning_exercise_semantics import PlanningSemanticBrief
+from planning_exercise_form_context import build_progression_gap_snapshot
+from planning_exercise_semantics import PlanningSemanticBrief, brief_to_summary_dict
 
 _logger = logging.getLogger("shinkan.planning_exercise_path_ai_fill")
 
@@ -265,27 +266,62 @@ def build_gap_fill_goal_text(
     spec: Mapping[str, Any],
     step_a: Optional[Mapping[str, Any]] = None,
     step_b: Optional[Mapping[str, Any]] = None,
+    roadmap_snapshot: Optional[Mapping[str, Any]] = None,
 ) -> str:
-    """Ausführlicher Zieltext für KI-Neuanlage aus dem Pfad-Kontext."""
+    """Ausführlicher Zieltext für KI-Neuanlage aus Pfad-, Roadmap- und Stufen-Kontext."""
     topic = (brief.primary_topic or "Technik").strip()
     phase = spec.get("phase") or "vertiefung"
     from_title = (step_a or {}).get("title") or spec.get("from_title") or "vorherigem Schritt"
     to_title = (step_b or {}).get("title") or spec.get("to_title") or "nächstem Schritt"
     arc = ", ".join(brief.development_arc or []) or "einstieg → grundlage → vertiefung → anwendung → perfektion"
+    snap = dict(roadmap_snapshot or {})
+    if not snap:
+        snap = build_progression_gap_snapshot(semantic_brief=brief_to_summary_dict(brief))
+
     parts = [
         f"Planungsziel (gesamter Pfad): {goal_query}",
-        f"Hauptthema: {topic}",
+        f"Hauptthema: {snap.get('primary_topic') or topic}",
-        f"Entwicklungsphase dieser Übung: {phase}",
+    ]
+    if snap.get("start_situation"):
+        parts.append(f"Voraussetzung / Ausgangslage (Progression): {snap['start_situation']}")
+    if snap.get("target_state"):
+        parts.append(f"Gesamtziel der Progression: {snap['target_state']}")
+    if snap.get("roadmap_notes"):
+        parts.append(f"Ergänzender Kontext: {snap['roadmap_notes']}")
+    stage_goal = snap.get("stage_learning_goal") or spec.get("title_hint")
+    if stage_goal:
+        parts.append(f"Lernziel dieser Roadmap-Stufe: {stage_goal}")
+    parts.extend(
+        [
+            f"Entwicklungsphase dieser Übung: {snap.get('stage_phase') or phase}",
             f"Erwarteter Entwicklungsbogen: {arc}",
             f"Einordnung: didaktische Zwischenstufe zwischen „{from_title}“ und „{to_title}“.",
         ]
+    )
+    if snap.get("stage_load_profile"):
+        parts.append(f"Belastungsschwerpunkte: {', '.join(snap['stage_load_profile'])}")
+    if snap.get("stage_success_criteria"):
+        parts.append(
+            "Erfolgskriterien dieser Stufe: "
+            + "; ".join(str(x) for x in snap["stage_success_criteria"][:4])
+        )
+    if snap.get("stage_anti_patterns"):
+        parts.append(
+            "Vermeiden: " + "; ".join(str(x) for x in snap["stage_anti_patterns"][:3])
+        )
+    if snap.get("skill_hints"):
+        parts.append(
+            "Fähigkeiten-/Fokus-Hinweise: "
+            + "; ".join(str(x) for x in snap["skill_hints"][:4])
+        )
     if spec.get("rationale"):
         parts.append(f"Qualitätsprüfung: {spec['rationale']}")
     if spec.get("sketch"):
         parts.append(f"Skizze: {spec['sketch']}")
     parts.append(
-        "Die Übung muss einen klaren, trainierbaren Bezug zum Hauptthema haben — "
+        "Die Übung muss die Stufe didaktisch erfüllen: klare Voraussetzungen, messbares Stufenziel, "
-        "keine generische Kraftübung ohne Technikbezug. Konkrete Durchführung, Ziel und Trainerhinweise ausformulieren."
+        "Bezug zum Gesamtpfad — keine generische Kraftübung ohne Technikbezug. "
+        "Konkrete Durchführung, Ziel und Trainerhinweise ausformulieren."
     )
     return "\n\n".join(parts)[:8000]
 
@@ -297,6 +333,7 @@ def build_gap_fill_offer(
     goal_query: str = "",
     brief: Optional[PlanningSemanticBrief] = None,
     proposal: Optional[Mapping[str, Any]] = None,
+    roadmap_snapshot: Optional[Mapping[str, Any]] = None,
 ) -> Dict[str, Any]:
     idx = int(spec.get("insert_after_index") or 0)
     offer_id = f"{spec.get('source')}-{idx}-{uuid.uuid4().hex[:8]}"
@@ -310,6 +347,7 @@ def build_gap_fill_offer(
             spec=spec,
             step_a=step_a,
             step_b=step_b,
+            roadmap_snapshot=roadmap_snapshot,
         )
     offer: Dict[str, Any] = {
         "offer_id": offer_id,
@@ -345,6 +383,7 @@ def apply_gap_fill_after_qa(
     include_ai_calls: bool = True,
     max_ai_proposals: int = 3,
     auto_insert_proposals: bool = False,
+    roadmap_snapshot: Optional[Mapping[str, Any]] = None,
 ) -> Tuple[List[Dict[str, Any]], List[Dict[str, Any]], List[Dict[str, Any]]]:
     """
     Erzeugt gap_fill_offers für die UI; optional KI-Vorschläge einfügen.
@@ -370,6 +409,7 @@ def apply_gap_fill_after_qa(
                 goal_query=goal_query,
                 brief=brief,
                 proposal=None,
+                roadmap_snapshot=roadmap_snapshot,
             )
             offers.append(offer)
             continue
@@ -397,6 +437,7 @@ def apply_gap_fill_after_qa(
             goal_query=goal_query,
             brief=brief,
             proposal=proposal,
+            roadmap_snapshot=roadmap_snapshot,
         )
         offers.append(offer)
 

backend/planning_exercise_path_builder.py

@@ -6,7 +6,7 @@ planning_progression_roadmap.py und PLANNING_PROGRESSION_ROADMAP_SPEC.md.
 """
 from __future__ import annotations
 
-from typing import Any, Callable, Dict, List, Optional, Set, Tuple
+from typing import Any, Callable, Dict, List, Mapping, Optional, Set, Tuple
 
 from fastapi import HTTPException
 from pydantic import BaseModel, Field
@@ -50,6 +50,7 @@ from planning_exercise_suggest import (
     _normalize_query,
     resolve_planning_exercise_intent,
 )
+from planning_exercise_form_context import build_progression_gap_snapshot
 from planning_progression_roadmap import (
     MajorStep,
     ProgressionRoadmapContext,
@@ -61,6 +62,7 @@ from planning_progression_roadmap import (
     resolve_step_exercise_kind_filter,
     roadmap_context_from_override,
     run_progression_roadmap_pipeline,
+    run_start_target_resolve_only,
     stage_spec_retrieval_query,
 )
 from routers.training_planning import _has_planning_role
@@ -79,6 +81,7 @@ class ProgressionPathSuggestRequest(BaseModel):
     include_llm_start_target: bool = True
     roadmap_first: bool = False
     roadmap_only: bool = False
+    start_target_only: bool = False
     roadmap_override: Optional[RoadmapOverridePayload] = None
     start_situation: Optional[str] = Field(default=None, max_length=2000)
     target_state: Optional[str] = Field(default=None, max_length=2000)
@@ -87,6 +90,44 @@ class ProgressionPathSuggestRequest(BaseModel):
     exercise_kind_any: Optional[List[str]] = None
 
 
+def _roadmap_gap_snapshot_for_spec(
+    roadmap_ctx: Optional[ProgressionRoadmapContext],
+    spec: Mapping[str, Any],
+    *,
+    semantic_brief: PlanningSemanticBrief,
+) -> Dict[str, Any]:
+    """Roadmap-Kontext für KI-Lücken-Übung (Start, Ziel, Stufenspec)."""
+    major_idx = spec.get("roadmap_major_step_index")
+    stage_spec_dict: Optional[Dict[str, Any]] = None
+    if roadmap_ctx and major_idx is not None:
+        for s in roadmap_ctx.stage_specs or []:
+            if int(s.major_step_index) == int(major_idx):
+                stage_spec_dict = s.model_dump()
+                if roadmap_ctx.roadmap:
+                    for m in roadmap_ctx.roadmap.major_steps:
+                        if m.index == int(major_idx):
+                            stage_spec_dict["phase"] = m.phase
+                            break
+                break
+    ga = roadmap_ctx.goal_analysis.model_dump() if roadmap_ctx and roadmap_ctx.goal_analysis else None
+    rs = (
+        roadmap_ctx.resolved_structured.model_dump()
+        if roadmap_ctx and roadmap_ctx.resolved_structured
+        else None
+    )
+    brief_summary = (
+        roadmap_ctx.semantic_brief
+        if roadmap_ctx and roadmap_ctx.semantic_brief
+        else brief_to_summary_dict(semantic_brief)
+    )
+    return build_progression_gap_snapshot(
+        goal_analysis=ga,
+        resolved_structured=rs,
+        stage_spec=stage_spec_dict,
+        semantic_brief=brief_summary,
+    )
+
+
 def _roadmap_structured_from_body(body: ProgressionPathSuggestRequest) -> Optional[RoadmapStructuredInput]:
     start = (body.start_situation or "").strip() or None
     target = (body.target_state or "").strip() or None
@@ -516,7 +557,10 @@ def suggest_progression_path(
 
     roadmap_first = bool(body.roadmap_first)
     roadmap_only = bool(body.roadmap_only)
-    include_roadmap = roadmap_first or body.include_roadmap_preview or roadmap_only
+    start_target_only = bool(body.start_target_only)
+    include_roadmap = (
+        roadmap_first or body.include_roadmap_preview or roadmap_only or start_target_only
+    )
     progression_roadmap: Optional[Dict[str, Any]] = None
     roadmap_ctx: Optional[ProgressionRoadmapContext] = None
     roadmap_edited = False
@@ -538,6 +582,15 @@ def suggest_progression_path(
         roadmap_edited = True
         max_steps = int(roadmap_ctx.max_steps)
         roadmap_first = True
+    elif start_target_only:
+        roadmap_ctx = run_start_target_resolve_only(
+            goal_query,
+            semantic_brief=semantic_brief,
+            cur=cur,
+            include_llm_start_target=body.include_llm_start_target,
+            structured=roadmap_structured,
+        )
+        progression_roadmap = progression_roadmap_to_api_dict(roadmap_ctx)
     elif include_roadmap:
         roadmap_ctx = run_progression_roadmap_pipeline(
             goal_query,
@@ -550,6 +603,28 @@ def suggest_progression_path(
         )
         progression_roadmap = progression_roadmap_to_api_dict(roadmap_ctx)
 
+    if start_target_only:
+        return {
+            "goal_query": goal_query,
+            "max_steps_requested": max_steps,
+            "steps": [],
+            "step_count": 0,
+            "target_profile_summary": None,
+            "semantic_brief_summary": brief_to_summary_dict(semantic_brief),
+            "semantic_llm_applied": semantic_llm_applied,
+            "query_intent_summary": {},
+            "progression_graph_id": body.progression_graph_id,
+            "path_qa": None,
+            "gap_fill_offers": [],
+            "progression_roadmap": progression_roadmap,
+            "roadmap_first": False,
+            "roadmap_only": False,
+            "start_target_only": True,
+            "roadmap_edited": False,
+            "roadmap_unfilled_count": 0,
+            "retrieval_phase": "start_target_only",
+        }
+
     if roadmap_only:
         return {
             "goal_query": goal_query,
@@ -615,6 +690,8 @@ def suggest_progression_path(
                 steps=steps,
                 brief=semantic_brief,
                 goal_query=goal_query,
+                goal_analysis=roadmap_ctx.goal_analysis if roadmap_ctx else None,
+                resolved_structured=roadmap_ctx.resolved_structured if roadmap_ctx else None,
             )
             for spec in roadmap_gap_specs:
                 roadmap_gap_offers.append(
@@ -624,6 +701,9 @@ def suggest_progression_path(
                         goal_query=goal_query,
                         brief=semantic_brief,
                         proposal=None,
+                        roadmap_snapshot=_roadmap_gap_snapshot_for_spec(
+                            roadmap_ctx, spec, semantic_brief=semantic_brief
+                        ),
                     )
                 )
     else:
@@ -760,6 +840,21 @@ def suggest_progression_path(
                 brief=semantic_brief,
                 goal_query=goal_query,
             )
+            path_roadmap_snapshot = None
+            if roadmap_ctx:
+                path_roadmap_snapshot = build_progression_gap_snapshot(
+                    goal_analysis=(
+                        roadmap_ctx.goal_analysis.model_dump()
+                        if roadmap_ctx.goal_analysis
+                        else None
+                    ),
+                    resolved_structured=(
+                        roadmap_ctx.resolved_structured.model_dump()
+                        if roadmap_ctx.resolved_structured
+                        else None
+                    ),
+                    semantic_brief=roadmap_ctx.semantic_brief or brief_to_summary_dict(semantic_brief),
+                )
             steps, ai_proposals, gap_fill_offers = apply_gap_fill_after_qa(
                 cur,
                 steps,
@@ -769,6 +864,7 @@ def suggest_progression_path(
                 include_ai_calls=False,
                 max_ai_proposals=0,
                 auto_insert_proposals=False,
+                roadmap_snapshot=path_roadmap_snapshot,
             )
 
     if roadmap_gap_offers:

backend/planning_progression_roadmap.py

@@ -794,6 +794,8 @@ def build_roadmap_unfilled_gap_specs(
     steps: Sequence[Mapping[str, Any]],
     brief: PlanningSemanticBrief,
     goal_query: str,
+    goal_analysis: Optional[GoalAnalysisArtifact] = None,
+    resolved_structured: Optional[RoadmapStructuredInput] = None,
 ) -> List[Dict[str, Any]]:
     """Gap-Fill-Angebote für Roadmap-Stufen ohne Bibliothekstreffer."""
     topic = (brief.primary_topic or "Technik").strip()
@@ -807,8 +809,18 @@ def build_roadmap_unfilled_gap_specs(
             f"Planungsziel: {goal_query}",
             f"Roadmap-Stufe {stage_spec.major_step_index + 1} ({phase}): {stage_spec.learning_goal}",
         ]
+        if resolved_structured and (resolved_structured.start_situation or "").strip():
+            sketch_parts.append(f"Ausgangslage (Pfad): {resolved_structured.start_situation.strip()}")
+        elif goal_analysis and (goal_analysis.start_assumption or "").strip():
+            sketch_parts.append(f"Ausgangslage (Pfad): {goal_analysis.start_assumption.strip()}")
+        if resolved_structured and (resolved_structured.target_state or "").strip():
+            sketch_parts.append(f"Gesamtziel (Pfad): {resolved_structured.target_state.strip()}")
+        elif goal_analysis and (goal_analysis.target_state or "").strip():
+            sketch_parts.append(f"Gesamtziel (Pfad): {goal_analysis.target_state.strip()}")
         if stage_spec.success_criteria:
             sketch_parts.append(f"Erfolgskriterien: {', '.join(stage_spec.success_criteria[:3])}")
+        if stage_spec.load_profile:
+            sketch_parts.append(f"Belastung: {', '.join(stage_spec.load_profile[:4])}")
         specs.append(
             {
                 "source": "roadmap_unfilled",
@@ -960,6 +972,48 @@ def _merge_structured_into_goal_analysis(
     )
 
 
+def run_start_target_resolve_only(
+    goal_query: str,
+    *,
+    semantic_brief: Optional[PlanningSemanticBrief] = None,
+    cur=None,
+    include_llm_start_target: bool = True,
+    structured: Optional[RoadmapStructuredInput] = None,
+) -> ProgressionRoadmapContext:
+    """Nur Start/Ziel/Ergänzungen auflösen — ohne Roadmap-Stufen (Review vor Major Steps)."""
+    brief = semantic_brief or build_semantic_brief(goal_query)
+    resolved, resolve_meta, llm_extract = resolve_roadmap_structured_input(
+        goal_query,
+        structured,
+        brief=brief,
+        cur=cur,
+        include_llm=include_llm_start_target,
+    )
+    topic_override = None
+    if llm_extract and (llm_extract.primary_topic or "").strip():
+        topic_override = llm_extract.primary_topic.strip()
+    goal_analysis = build_goal_analysis(
+        goal_query,
+        brief,
+        structured=resolved,
+        topic_override=topic_override,
+    )
+    ctx = ProgressionRoadmapContext(
+        goal_query=goal_query.strip(),
+        max_steps=2,
+        semantic_brief=brief_to_summary_dict(brief),
+        resolved_structured=resolved,
+        start_target_extract=llm_extract,
+        start_target_resolve=resolve_meta,
+        goal_analysis=goal_analysis,
+        llm_start_target_applied=resolve_meta.llm_start_target_applied,
+        pipeline_phase="start_target_only",
+    )
+    if resolve_meta.llm_start_target_applied:
+        ctx.prompt_slugs.append(PROMPT_SLUG_START_TARGET)
+    return ctx
+
+
 def run_progression_roadmap_pipeline(
     goal_query: str,
     *,
@@ -1135,6 +1189,7 @@ __all__ = [
     "consolidate_micro_to_major",
     "develop_micro_objectives",
     "progression_roadmap_to_api_dict",
+    "run_start_target_resolve_only",
     "run_progression_roadmap_pipeline",
     "try_llm_start_target_extract",
     "try_llm_goal_analysis",

backend/routers/planning_exercise_suggest.py

@@ -73,6 +73,7 @@ def post_progression_path_suggest(
         or body.include_ai_gap_fill
         or body.include_llm_roadmap
         or body.include_llm_start_target
+        or (body.start_target_only and body.include_llm_start_target)
     )
     club_id = resolve_club_id_for_probe(tenant) if uses_ai else None
     if uses_ai:

backend/tests/test_planning_exercise_form_context.py

@@ -1,5 +1,6 @@
 """Tests Planungs-KI Phase D — planning_context für suggestExerciseAi."""
 from planning_exercise_form_context import (
+    build_progression_gap_snapshot,
     build_progression_path_gap_planning_context,
     planning_context_prompt_variables,
     sanitize_planning_context_for_ai,
@@ -44,3 +45,36 @@ def test_build_progression_path_gap_context():
 def test_sanitize_truncates_long_strings():
     ctx = sanitize_planning_context_for_ai({"goal_query": "x" * 900})
     assert len(ctx["goal_query"]) <= 800
+
+
+def test_build_progression_gap_snapshot_includes_start_target_and_stage():
+    snap = build_progression_gap_snapshot(
+        goal_analysis={
+            "primary_topic": "Kumite Beinarbeit",
+            "start_assumption": "gleichförmige Steppbewegung",
+            "target_state": "explosiver Angriff mit Ausweichen",
+            "success_criteria": ["nachvollziehbarer Übergang"],
+        },
+        resolved_structured={"roadmap_notes": "Kindergruppe"},
+        stage_spec={
+            "learning_goal": "variable Rhythmen",
+            "load_profile": ["timing", "distanz"],
+            "success_criteria": ["Reaktion unter Druck"],
+            "anti_patterns": ["statisches Stehen"],
+        },
+        semantic_brief={"must_phrases": ["Beinarbeit"], "development_arc": ["grundlage", "anwendung"]},
+    )
+    assert snap["start_situation"] == "gleichförmige Steppbewegung"
+    assert snap["stage_learning_goal"] == "variable Rhythmen"
+    assert "timing" in snap["stage_load_profile"]
+    assert snap["roadmap_notes"] == "Kindergruppe"
+
+
+def test_gap_planning_context_carries_snapshot_fields():
+    ctx = build_progression_path_gap_planning_context(
+        goal_query="Kumite Beinarbeit",
+        goal_analysis={"start_assumption": "Start", "target_state": "Ziel"},
+        stage_spec={"learning_goal": "Stufenziel", "load_profile": ["koordination"]},
+    )
+    assert ctx["start_situation"] == "Start"
+    assert ctx["stage_learning_goal"] == "Stufenziel"

backend/tests/test_planning_exercise_path_ai_fill.py

@@ -91,3 +91,25 @@ def test_build_gap_fill_goal_text_includes_topic():
     assert "Mae Geri" in text or "mae geri" in text.lower()
     assert "anwendung" in text
     assert "Kihon" in text
+
+
+def test_build_gap_fill_goal_text_includes_roadmap_snapshot():
+    brief = build_semantic_brief("Kumite Beinarbeit")
+    text = build_gap_fill_goal_text(
+        goal_query="Kumite Beinarbeit",
+        brief=brief,
+        spec={"phase": "vertiefung", "title_hint": "variable Rhythmen"},
+        step_a={"title": "Schritt A"},
+        step_b={"title": "Schritt B"},
+        roadmap_snapshot={
+            "start_situation": "gleichförmige Steppbewegung",
+            "target_state": "explosiver Angriff",
+            "stage_learning_goal": "variable Rhythmen und multidirektionale Kontrolle",
+            "stage_load_profile": ["timing", "distanz"],
+            "skill_hints": ["Beinarbeit"],
+        },
+    )
+    assert "gleichförmige Steppbewegung" in text
+    assert "explosiver Angriff" in text
+    assert "variable Rhythmen" in text
+    assert "timing" in text

backend/tests/test_planning_progression_roadmap.py

@@ -16,6 +16,7 @@ from planning_progression_roadmap import (
     resolve_roadmap_structured_input,
     resolve_step_exercise_kind_filter,
     run_progression_roadmap_pipeline,
+    run_start_target_resolve_only,
     stage_spec_exercise_kind_filter,
     stage_spec_retrieval_query,
     normalize_major_steps_for_override,
@@ -173,6 +174,15 @@ def test_resolve_structured_regex_fallback_without_llm():
     assert "dynamischen" in (resolved.target_state or "")
 
 
+def test_run_start_target_resolve_only_no_major_steps():
+    ctx = run_start_target_resolve_only(KUMITE_GOAL, include_llm_start_target=False)
+    assert ctx.pipeline_phase == "start_target_only"
+    assert ctx.roadmap is None
+    assert ctx.goal_analysis is not None
+    assert "Steppbewegung" in ctx.goal_analysis.start_assumption
+    assert ctx.resolved_structured is not None
+
+
 def test_resolve_structured_merges_user_and_llm_notes():
     brief = build_semantic_brief("Kumite Beinarbeit")
     structured = RoadmapStructuredInput(roadmap_notes="Kindergruppe 10–12")

backend/version.py

@@ -1,6 +1,6 @@
 # Shinkan Jinkendo Version Information
 
-APP_VERSION = "0.8.211"
+APP_VERSION = "0.8.212"
 BUILD_DATE = "2026-06-07"
 DB_SCHEMA_VERSION = "20260607087"
 
@@ -38,7 +38,7 @@ MODULE_VERSIONS = {
     "skill_profiles": "1.0.0",  # Phase 3: gewichtetes Fähigkeiten-Profil + skill-discovery/suggestions
     "methods": "0.1.0",
     "exercises": "2.37.1",  # KI-Endpoints: feature_usage nach ai_calls consume
-    "planning_exercise_suggest": "0.21.0",  # LLM Start/Ziel-Extraktion (planning_progression_start_target)
+    "planning_exercise_suggest": "0.21.1",  # start_target_only + reicher gap-fill planning_context
     "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

frontend/src/components/ExerciseProgressionPathBuilder.jsx

@@ -201,8 +201,10 @@ export default function ExerciseProgressionPathBuilder({
   const [editableMajorSteps, setEditableMajorSteps] = useState([])
   const [roadmapDirty, setRoadmapDirty] = useState(false)
   const [loadingRoadmap, setLoadingRoadmap] = useState(false)
+  const [loadingStartTarget, setLoadingStartTarget] = useState(false)
   const [loadingMatch, setLoadingMatch] = useState(false)
-  const loading = loadingRoadmap || loadingMatch
+  const [startTargetAnalyzed, setStartTargetAnalyzed] = useState(false)
+  const loading = loadingRoadmap || loadingStartTarget || loadingMatch
   const [focusAreas, setFocusAreas] = useState([])
   const [skillsCatalog, setSkillsCatalog] = useState([])
   const [generatingOfferId, setGeneratingOfferId] = useState(null)
@@ -397,6 +399,9 @@ export default function ExerciseProgressionPathBuilder({
       pathSteps,
       editableMajorSteps,
       progressionRoadmap,
+      startSituation,
+      targetState,
+      roadmapNotes,
     })
     try {
       const aiRes = await api.suggestExerciseAi({
@@ -531,6 +536,60 @@ export default function ExerciseProgressionPathBuilder({
     if (!segmentNotes.trim() && q) setSegmentNotes(q.slice(0, 400))
   }
 
+  const applyStartTargetResponse = (res) => {
+    const roadmap = res?.progression_roadmap || null
+    setProgressionRoadmap((prev) => ({
+      ...(prev || {}),
+      ...roadmap,
+      roadmap: prev?.roadmap || roadmap?.roadmap || null,
+      stage_specs: prev?.stage_specs || roadmap?.stage_specs || [],
+    }))
+    applyResolvedStructuredFromRoadmap(roadmap, {
+      setStartSituation,
+      setTargetState,
+      setRoadmapNotes,
+    })
+    setSemanticBrief(res?.semantic_brief_summary || null)
+    setStartTargetAnalyzed(true)
+  }
+
+  const analyzeStartTarget = async () => {
+    const q = (goalQuery || '').trim()
+    if (q.length < 3) {
+      alert('Ziel-Anfrage: mindestens 3 Zeichen.')
+      return
+    }
+    if (!graphId) {
+      alert('Zuerst einen Graphen wählen.')
+      return
+    }
+    setLoadingStartTarget(true)
+    setError('')
+    try {
+      const res = await api.suggestProgressionPath({
+        query: q,
+        max_steps: Number(maxSteps),
+        include_llm_intent: false,
+        include_path_qa: false,
+        include_llm_path_qa: false,
+        include_path_reorder: false,
+        include_ai_gap_fill: false,
+        include_roadmap_preview: false,
+        include_llm_roadmap: false,
+        include_llm_start_target: true,
+        start_target_only: true,
+        progression_graph_id: Number(graphId),
+        ...roadmapStructuredPayload(startSituation, targetState, roadmapNotes),
+      })
+      applyStartTargetResponse(res)
+    } catch (e) {
+      console.error(e)
+      setError(e.message || 'Start/Ziel-Analyse fehlgeschlagen')
+    } finally {
+      setLoadingStartTarget(false)
+    }
+  }
+
   const suggestRoadmap = async () => {
     const q = (goalQuery || '').trim()
     if (q.length < 3) {
@@ -541,6 +600,7 @@ export default function ExerciseProgressionPathBuilder({
       alert('Zuerst einen Graphen wählen.')
       return
     }
+    const fieldsEmpty = !startSituation.trim() && !targetState.trim()
     setLoadingRoadmap(true)
     setError('')
     try {
@@ -554,7 +614,7 @@ export default function ExerciseProgressionPathBuilder({
         include_ai_gap_fill: false,
         include_roadmap_preview: true,
         include_llm_roadmap: true,
-        include_llm_start_target: true,
+        include_llm_start_target: fieldsEmpty,
         roadmap_only: true,
         progression_graph_id: Number(graphId),
         ...roadmapStructuredPayload(startSituation, targetState, roadmapNotes),
@@ -567,11 +627,14 @@ export default function ExerciseProgressionPathBuilder({
       setMaxSteps(majors.length)
       const roadmap = res?.progression_roadmap || null
       setProgressionRoadmap(roadmap)
+      if (fieldsEmpty) {
         applyResolvedStructuredFromRoadmap(roadmap, {
           setStartSituation,
           setTargetState,
           setRoadmapNotes,
         })
+        setStartTargetAnalyzed(true)
+      }
       setSemanticBrief(res?.semantic_brief_summary || null)
       setPathSteps([])
       setTargetSummary(null)
@@ -767,18 +830,37 @@ export default function ExerciseProgressionPathBuilder({
         </div>
       </div>
       <p style={{ fontSize: '11px', color: 'var(--text3)', margin: '6px 0 0', lineHeight: 1.4 }}>
-        Leer gelassen: Start/Ziel werden per KI aus dem Zieltext verstanden und formuliert (Fallback: Muster
+        Optional zuerst „Start/Ziel analysieren“, anpassen, dann Roadmap-Stufen. Sind Start und Ziel leer,
-        „von … bis …“). Manuelle Eingaben haben Vorrang.
+        geschieht die Analyse beim Roadmap-Vorschlag automatisch mit. Manuelle Eingaben haben immer Vorrang.
       </p>
       <div style={{ display: 'flex', flexWrap: 'wrap', gap: '10px', alignItems: 'flex-end', marginTop: '10px' }}>
+        <button
+          type="button"
+          className="btn btn-secondary"
+          disabled={disabled || loading || saving || !graphId}
+          onClick={analyzeStartTarget}
+          title="Nur Ausgangslage, Zielzustand und Ergänzungen per KI — ohne Roadmap-Stufen"
+        >
+          {loadingStartTarget ? 'Analyse …' : 'Start/Ziel analysieren'}
+        </button>
         <button
           type="button"
           className="btn btn-primary"
           disabled={disabled || loading || saving || !graphId}
           onClick={suggestRoadmap}
+          title={
+            startSituation.trim() && targetState.trim()
+              ? 'Roadmap-Stufen aus den gesetzten Start/Ziel-Feldern'
+              : 'Start/Ziel-Analyse und Roadmap-Stufen in einem Schritt'
+          }
         >
           {loadingRoadmap ? 'Roadmap …' : 'Roadmap vorschlagen'}
         </button>
+        {startTargetAnalyzed && !editableMajorSteps.length ? (
+          <span className="exercise-tag" style={{ borderColor: 'var(--accent)' }}>
+            Start/Ziel bereit — Roadmap als Nächstes
+          </span>
+        ) : null}
         <button
           type="button"
           className="btn btn-secondary"
@@ -808,7 +890,8 @@ export default function ExerciseProgressionPathBuilder({
         </p>
       ) : null}
 
-      {progressionRoadmap?.goal_analysis ? (
+      {(progressionRoadmap?.goal_analysis ||
+        progressionRoadmap?.pipeline_phase === 'start_target_only') ? (
         <div
           style={{
             marginTop: '12px',

frontend/src/utils/planningContextForExerciseAi.js

@@ -30,6 +30,18 @@ export function buildPickerPlanningContextForAi({
   return Object.fromEntries(Object.entries(ctx).filter(([, v]) => v != null && v !== ''))
 }
 
+function stageSpecForMajorIndex(progressionRoadmap, majorIdx) {
+  if (majorIdx == null || !progressionRoadmap) return null
+  const specs = progressionRoadmap?.stage_specs
+  if (!Array.isArray(specs)) return null
+  const hit = specs.find((s) => Number(s.major_step_index) === Number(majorIdx))
+  if (!hit) return null
+  const majors = progressionRoadmap?.roadmap?.major_steps
+  const major =
+    Array.isArray(majors) && majors.find((m) => Number(m.index) === Number(majorIdx))
+  return major ? { ...hit, phase: hit.phase || major.phase } : hit
+}
+
 export function buildPathGapPlanningContextForAi({
   goalQuery = '',
   semanticBrief = null,
@@ -38,6 +50,9 @@ export function buildPathGapPlanningContextForAi({
   pathSteps = [],
   editableMajorSteps = [],
   progressionRoadmap = null,
+  startSituation = '',
+  targetState = '',
+  roadmapNotes = '',
 } = {}) {
   const afterIdx = Number(offer?.insert_after_index)
   const stepA = Number.isFinite(afterIdx) && afterIdx >= 0 ? pathSteps[afterIdx] : null
@@ -49,19 +64,63 @@ export function buildPathGapPlanningContextForAi({
     majorIdxRaw != null && Number.isFinite(Number(majorIdxRaw)) ? Number(majorIdxRaw) : null
   const majorStep =
     majorIdx != null && editableMajorSteps[majorIdx] ? editableMajorSteps[majorIdx] : null
+  const stageSpec = stageSpecForMajorIndex(progressionRoadmap, majorIdx)
+  const ga = progressionRoadmap?.goal_analysis || null
+  const rs = progressionRoadmap?.resolved_structured || null
+
+  const start =
+    (startSituation || '').trim() ||
+    rs?.start_situation ||
+    ga?.start_assumption ||
+    null
+  const target =
+    (targetState || '').trim() || rs?.target_state || ga?.target_state || null
+  const notes = (roadmapNotes || '').trim() || rs?.roadmap_notes || null
+
+  const skillHints = []
+  if (Array.isArray(semanticBrief?.must_phrases)) {
+    semanticBrief.must_phrases.slice(0, 4).forEach((p) => {
+      const s = String(p || '').trim()
+      if (s) skillHints.push(s)
+    })
+  }
+  if (Array.isArray(semanticBrief?.development_arc) && semanticBrief.development_arc.length) {
+    skillHints.push(
+      `Entwicklungsbogen: ${semanticBrief.development_arc.slice(0, 5).join(' → ')}`,
+    )
+  }
 
   const ctx = {
     source: 'progression_path_gap_fill',
     goal_query: (goalQuery || '').trim() || null,
-    primary_topic: semanticBrief?.primary_topic || null,
+    primary_topic: ga?.primary_topic || semanticBrief?.primary_topic || null,
     progression_graph_id: graphId != null ? Number(graphId) : null,
     gap_source: offer?.source || null,
     gap_phase: offer?.phase || offer?.gap?.expected_phase || null,
     roadmap_major_step_index: majorIdx,
-    roadmap_phase: majorStep?.phase || offer?.phase || null,
+    roadmap_phase: majorStep?.phase || stageSpec?.phase || offer?.phase || null,
     roadmap_learning_goal:
       (majorStep?.learning_goal || offer?.title_hint || offer?.gap?.learning_goal || '').trim() ||
       null,
+    start_situation: start,
+    target_state: target,
+    roadmap_notes: notes,
+    stage_learning_goal: stageSpec?.learning_goal || null,
+    stage_phase: stageSpec?.phase || majorStep?.phase || null,
+    stage_exercise_type: stageSpec?.exercise_type || null,
+    stage_load_profile: Array.isArray(stageSpec?.load_profile)
+      ? stageSpec.load_profile.slice(0, 6)
+      : null,
+    stage_success_criteria: Array.isArray(stageSpec?.success_criteria)
+      ? stageSpec.success_criteria.slice(0, 4)
+      : null,
+    stage_anti_patterns: Array.isArray(stageSpec?.anti_patterns)
+      ? stageSpec.anti_patterns.slice(0, 3)
+      : null,
+    path_success_criteria: Array.isArray(ga?.success_criteria)
+      ? ga.success_criteria.slice(0, 4)
+      : null,
+    skill_hints: skillHints.length ? skillHints : null,
     neighbor_before_title: stepA?.exerciseTitle || offer?.from_title || null,
     neighbor_after_title: stepB?.exerciseTitle || offer?.to_title || null,
     path_step_count: Array.isArray(pathSteps) ? pathSteps.length : 0,