Enhance Progression Path Suggestion Logic and UI Feedback
Test Suite / pytest-backend (push) Successful in 41s
Test Suite / lint-backend (push) Successful in 0s
Test Suite / build-frontend (push) Successful in 13s
Test Suite / k6 /health Baseline (push) Successful in 33s
Test Suite / playwright-tests (push) Successful in 1m18s
Deploy Development / deploy (push) Successful in 44s

- Updated `suggest_progression_path` to include AI-generated gap fill offers when exercises are missing, improving the relevance of suggested paths.
- Introduced a match summary to provide insights on library matches and gap fill offers, enhancing user feedback in the `ProgressionGraphEditor`.
- Refined the `pick_best_path_hit` function to ensure proper handling of roadmap stage matches based on primary topics.
- Added tests to validate the new gap fill offer logic and match summary functionality, ensuring robustness in path suggestion features.
This commit is contained in:
Lars committed 2026-06-11 11:17:53 +02:00
1 parent 044ce2ee60
commit 8f1dad53ab
5 files changed
+121 -8

No files matched your search

+59 -1
View File
@@ -1414,7 +1414,10 @@ def suggest_progression_path(
anchor_id = eid
anchor_variant_id = step.get("variant_id")
if len(steps) < 2:
stage_spec_count = len(roadmap_ctx.stage_specs or []) if roadmap_ctx else 0
if roadmap_first and stage_spec_count >= 2:
pass
elif len(steps) < 2:
raise HTTPException(
status_code=422,
detail="Zu wenig passende Übungen für einen Pfad (mindestens 2 Schritte). Ziel präzisieren oder max_steps senken.",
@@ -1623,6 +1626,60 @@ def suggest_progression_path(
roadmap_ctx=roadmap_ctx,
max_steps=max_steps,
)
if body.include_ai_gap_fill:
seen_offer_ids = {o.get("offer_id") for o in gap_fill_offers}
for step in steps:
if step.get("exercise_id") is not None:
continue
try:
major_idx = int(step["roadmap_major_step_index"])
except (TypeError, ValueError, KeyError):
continue
stage_spec = next(
(
s
for s in (roadmap_ctx.stage_specs or [])
if int(s.major_step_index) == major_idx
),
None,
)
if stage_spec is None:
continue
spec = {
"source": "roadmap_unfilled",
"insert_after_index": max(major_idx - 1, -1),
"roadmap_major_step_index": major_idx,
"phase": (step.get("roadmap_phase") or "vertiefung").strip().lower(),
"title_hint": (stage_spec.learning_goal or step.get("title") or f"Slot {major_idx + 1}")[:120],
"sketch": (stage_spec.learning_goal or "").strip(),
"rationale": f"Slot {major_idx + 1} — keine passende Bibliotheks-Übung; KI-Entwurf für diese Stufe.",
}
offer = build_gap_fill_offer(
spec=spec,
steps=steps,
goal_query=goal_query,
brief=semantic_brief,
proposal=None,
roadmap_snapshot=_roadmap_gap_snapshot_for_spec(
cur,
roadmap_ctx,
spec,
goal_query=goal_query,
semantic_brief=semantic_brief,
),
)
if offer.get("offer_id") not in seen_offer_ids:
gap_fill_offers.append(offer)
seen_offer_ids.add(offer.get("offer_id"))
filled_library_steps = sum(1 for s in steps if s.get("exercise_id") is not None)
match_summary = {
"roadmap_first": roadmap_first,
"library_matches": filled_library_steps,
"slot_count": len(steps),
"gap_fill_offer_count": len(gap_fill_offers),
"roadmap_unfilled_count": len(roadmap_unfilled),
}
target_profile_summary = path_target_profile.to_summary_dict(cur)
retrieval_parts = ["profile_v1", "full_library", "path_builder", "semantics"]
@@ -1667,6 +1724,7 @@ def suggest_progression_path(
"roadmap_edited": roadmap_edited,
"roadmap_unfilled_count": len(roadmap_unfilled),
"path_skill_expectations": path_skill_expectations,
"match_summary": match_summary,
"retrieval_phase": "+".join(retrieval_parts),
}