From eef1c2e7d3e454932b593fcae02a2b64ef4d0ea6 Mon Sep 17 00:00:00 2001
From: Benjamin Admin <benjaminadmin@MacBookPro.fritz.box>
Date: Thu, 12 Mar 2026 13:37:57 +0100
Subject: [PATCH] fix(rag): Use docker cp to inject checked-out scripts

The runner container can't access host paths directly, so the
deploy dir scripts were always stale. Now uses docker create +
docker cp + docker start to copy the freshly checked-out scripts
into the ingestion container before starting it.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 .gitea/workflows/rag-ingest.yaml | 34 ++++++++++++++++++++------------
 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/.gitea/workflows/rag-ingest.yaml b/.gitea/workflows/rag-ingest.yaml
index 9c4258f..9d23040 100644
--- a/.gitea/workflows/rag-ingest.yaml
+++ b/.gitea/workflows/rag-ingest.yaml
@@ -35,7 +35,6 @@ jobs:
         run: |
           set -euo pipefail
           PHASE="${{ github.event.inputs.phase }}"
-          DEPLOY_DIR="/opt/breakpilot-compliance"
 
           echo "=== RAG Ingestion: Phase ${PHASE} ==="
           echo ""
@@ -48,7 +47,6 @@ jobs:
           # Netzwerk finden in dem die bp-Services laufen
           BP_NETWORK=$(docker inspect bp-core-rag-service --format '{{range $k,$v := .NetworkSettings.Networks}}{{$k}}{{end}}' 2>/dev/null || echo "")
           if [ -z "$BP_NETWORK" ]; then
-            # Fallback: Netzwerk vom Compliance-Backend nehmen
             BP_NETWORK=$(docker inspect bp-compliance-backend --format '{{range $k,$v := .NetworkSettings.Networks}}{{$k}}{{end}}' 2>/dev/null || echo "")
           fi
 
@@ -67,16 +65,12 @@ jobs:
           echo "BreakPilot Netzwerk: $BP_NETWORK"
           echo ""
 
-          # Scripts aus dem Deploy-Dir aktualisieren (git pull)
-          # damit die neuesten Fixes verfuegbar sind
-          cd "${DEPLOY_DIR}" && git pull --no-rebase origin main 2>/dev/null || true
-          cd -
-
-          # Ingestion in einem Container auf dem BP-Netzwerk ausfuehren,
-          # mit Zugriff auf die Scripts aus dem Deploy-Dir
-          docker run --rm \
+          # Ingestion-Container erstellen (noch nicht starten),
+          # dann Scripts aus dem Checkout per docker cp hineinkopieren.
+          # So verwenden wir IMMER die neueste Version der Scripts,
+          # unabhaengig vom Deploy-Dir auf dem Host.
+          CONTAINER_ID=$(docker create \
             --network "$BP_NETWORK" \
-            -v "${DEPLOY_DIR}/scripts:/workspace/scripts:ro" \
             -e "WORK_DIR=/tmp/rag-ingestion" \
             -e "RAG_URL=http://bp-core-rag-service:8097/api/v1/documents/upload" \
             -e "QDRANT_URL=https://qdrant-dev.breakpilot.ai" \
@@ -92,14 +86,28 @@ jobs:
               elif [ '${PHASE}' = 'download' ]; then
                 bash scripts/ingest-legal-corpus.sh --only download
               else
-                # Download-Phase muss immer zuerst laufen (erstellt Textdateien)
                 echo '=== Running download phase first ==='
                 bash scripts/ingest-legal-corpus.sh --only download
                 echo ''
                 echo '=== Running phase: ${PHASE} ==='
                 bash scripts/ingest-legal-corpus.sh --only '${PHASE}'
               fi
-            "
+            ")
+
+          echo "Container: $CONTAINER_ID"
+
+          # Scripts aus dem Git-Checkout in den Container kopieren
+          docker cp scripts/. "${CONTAINER_ID}:/workspace/scripts/"
+          echo "Scripts kopiert (aus Git-Checkout)"
+
+          # Container starten und Output streamen
+          docker start -a "${CONTAINER_ID}" || EXITCODE=$?
+
+          # Container aufraeumen
+          docker rm -f "${CONTAINER_ID}" 2>/dev/null || true
 
           echo ""
           echo "=== Ingestion abgeschlossen ==="
+
+          # Exit mit dem Original-Exitcode
+          exit ${EXITCODE:-0}