fixed retrieval

math-tutor/backend/app/deterministic_services/context_stores/context_store_base.py

@@ -196,5 +196,5 @@ def update_retrieval_context(
     sources: list[Source],
 ) -> None:
     merged = get_retrieval(sheet) + sources
-    merged_sorted = sorted(merged, key=lambda item: item.score, reverse=True)[:8]
+    merged_sorted = sorted(merged, key=lambda item: item.score, reverse=True)
     set_sources(sheet, merged_sorted)

math-tutor/backend/app/deterministic_services/orchestrators/orchestrator_task.py

@@ -4,7 +4,6 @@ from app.LLM_services import task_hint_LLM
 import app.config as config
 from app.deterministic_services import (
     context_store,
-    embedding_provider,
     retrieval_store,
     task_catalog,
 )
@@ -61,20 +60,14 @@ def _retrieve_context_for_task(state: base.ChatState, query_text: str) -> None:
         return
 
     def _retrieve() -> dict:
-        embedder, cache_hit = embedding_provider.get_embedder()
-        sources = retrieval_store.retrieve_with_subsections(
+        sources = retrieval_store.retrieve_for_subsections(
             pg_url=config.get_postgres_url(),
-            embedder=embedder,
-            query=query_text,
             subsection_refs=refs,
-            k=8,
-            expand_links=True,
         )
         context_store.update_retrieval_context(state.sheet, sources)
         return {
             "subsection_refs": refs,
             "source_count": len(sources),
-            "embedder_cache_hit": cache_hit,
         }
 
     base.log_timed_call(
@@ -98,7 +91,6 @@ def _on_bootstrap(state: base.ChatState, query_text: str) -> None:
 
 def _on_turn_logic(state: base.ChatState) -> None:
     _ensure_context_task_fields(state, state.last_user)
-    _retrieve_context_for_task(state, state.last_user)
 
 # Antwort generieren
 
@@ -126,22 +118,30 @@ def run_chat(
     draft: str | None = None,
     selected_task: dict | None = None,
 ) -> dict:
+    def _apply_selected_task(state: base.ChatState) -> None:
+        if not selected_task:
+            return
+        selected_file_id = str(selected_task.get("file_id", "")).strip()
+        selected_task_id = str(selected_task.get("task_id", "")).strip()
+        if selected_file_id and selected_task_id:
+            task_catalog.select_task_by_ids(
+                state.sheet,
+                selected_file_id,
+                selected_task_id,
+            )
+
+    def on_bootstrap(state: base.ChatState, query_text: str) -> None:
+        _apply_selected_task(state)
+        _on_bootstrap(state, query_text)
+
     def on_turn_logic(state: base.ChatState) -> None:
-        if selected_task:
-            selected_file_id = str(selected_task.get("file_id", "")).strip()
-            selected_task_id = str(selected_task.get("task_id", "")).strip()
-            if selected_file_id and selected_task_id:
-                task_catalog.select_task_by_ids(
-                    state.sheet,
-                    selected_file_id,
-                    selected_task_id,
-                )
+        _apply_selected_task(state)
         _on_turn_logic(state)
 
     return base.run_chat_common(
         messages=messages,
         draft=draft,
-        on_bootstrap=_on_bootstrap,
+        on_bootstrap=on_bootstrap,
         on_turn_logic=on_turn_logic,
         on_build_reply=_on_build_reply,
     )

math-tutor/backend/app/deterministic_services/retrieval_store.py

@@ -92,3 +92,13 @@ def retrieve_with_subsections(
         expand_links=expand_links,
         neighbor_expand=neighbor_expand,
     )
+
+
+def retrieve_for_subsections(
+    pg_url: str,
+    subsection_refs: list[vector_store.SubsectionRef] | None = None,
+) -> List[Source]:
+    return vector_store.load_children_for_subsections(
+        pg_url=pg_url,
+        subsection_refs=subsection_refs,
+    )