{"type":"queue-operation","operation":"enqueue","timestamp":"2026-05-20T17:20:02.206Z","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2","content":"Implementiere Idee #7: Papierkorb-Seite (Trash UI) für PrintVault.\\n\\nBACKEND (main.py unter /media/HDD_1TB/PrintVault/main.py):\\n- TRASH_DIR existiert bereits, Soft-Delete verschiebt .stl/.png nach /trash mit Timestamp\\n- Füge 3 neue API-Endpoints hinzu: GET /api/trash, POST /api/trash/{filename}/restore, DELETE /api/trash/{filename}\\n- GET listet Dateien mit Original-ID (aus Dateiname extrahiert), Name aus DB, Löschdatum\\n- POST restore verschiebt zurück nach STL_DIR/THUMB_DIR und erstellt DB-Eintrag neu\\n- DELETE löscht Datei endgültig von Platte\\n\\nFRONTEND (index.html unter /media/HDD_1TB/PrintVault/frontend/index.html):\\n- Trash-Icon-Button im Header neben Upload mit Badge (Anzahl)\\n- Trash-Ansicht mit Karten: Name, Löschdatum, Wiederherstellen, Endgültig-Löschen\\n- Bestätigungsdialog beim endgültigen Löschen\\n- Leerer-Zustand Meldung\\n- Zurück-zur-Bibliothek Button\\n- Toast-Benachrichtigungen\\n- Styling passend zum bestehenden Design (CSS-Variablen, Cards im Trash mit --red Akzent)\\n\\nÄndere die existierenden Dateien direkt. Keine neuen Dateien."} {"type":"queue-operation","operation":"dequeue","timestamp":"2026-05-20T17:20:02.206Z","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2"} {"parentUuid":null,"isSidechain":false,"promptId":"998409ec-ab4b-4227-8986-411c0f339ff3","type":"user","message":{"role":"user","content":"Implementiere Idee #7: Papierkorb-Seite (Trash UI) für PrintVault.\\n\\nBACKEND (main.py unter /media/HDD_1TB/PrintVault/main.py):\\n- TRASH_DIR existiert bereits, Soft-Delete verschiebt .stl/.png nach /trash mit Timestamp\\n- Füge 3 neue API-Endpoints hinzu: GET /api/trash, POST /api/trash/{filename}/restore, DELETE /api/trash/{filename}\\n- GET listet Dateien mit Original-ID (aus Dateiname extrahiert), Name aus DB, Löschdatum\\n- POST restore verschiebt zurück nach STL_DIR/THUMB_DIR und erstellt DB-Eintrag neu\\n- DELETE löscht Datei endgültig von Platte\\n\\nFRONTEND (index.html unter /media/HDD_1TB/PrintVault/frontend/index.html):\\n- Trash-Icon-Button im Header neben Upload mit Badge (Anzahl)\\n- Trash-Ansicht mit Karten: Name, Löschdatum, Wiederherstellen, Endgültig-Löschen\\n- Bestätigungsdialog beim endgültigen Löschen\\n- Leerer-Zustand Meldung\\n- Zurück-zur-Bibliothek Button\\n- Toast-Benachrichtigungen\\n- Styling passend zum bestehenden Design (CSS-Variablen, Cards im Trash mit --red Akzent)\\n\\nÄndere die existierenden Dateien direkt. Keine neuen Dateien."},"uuid":"bcb78c00-0ebb-4bf4-bb94-eea58b9f3c59","timestamp":"2026-05-20T17:20:02.251Z","permissionMode":"bypassPermissions","userType":"external","entrypoint":"sdk-cli","cwd":"/DATA","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2","version":"2.1.145","gitBranch":"HEAD"} {"parentUuid":"bcb78c00-0ebb-4bf4-bb94-eea58b9f3c59","isSidechain":false,"attachment":{"type":"skill_listing","content":"- update-config: Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.\n- keybindings-help: Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify ~/.claude/keybindings.json. Examples: \"rebind ctrl+s\", \"add a chord shortcut\", \"change the submit key\", \"customize keybindings\".\n- verify: Verify that a code change actually does what it's supposed to by running the app and observing behavior. Use when asked to verify a PR, confirm a fix works, test a change manually, check that a feature works, or validate local changes before pushing.\n- simplify: Review changed code for reuse, quality, and efficiency, then fix any issues found.\n- fewer-permission-prompts: Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.\n- loop: Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo, defaults to 10m) - When the user wants to set up a recurring task, poll for status, or run something repeatedly on an interval (e.g. \"check the deploy every 5 minutes\", \"keep running /babysit-prs\"). Do NOT invoke for one-off tasks.\n- claude-api: Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements).\nTRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project.\nSKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.\n- run: Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).\n- init: Initialize a new CLAUDE.md file with codebase documentation\n- review: Review a pull request\n- security-review: Complete a security review of the pending changes on the current branch","skillCount":11,"isInitial":true},"type":"attachment","uuid":"55c0a280-cdad-432e-8b13-9bc62219a096","timestamp":"2026-05-20T17:20:02.250Z","userType":"external","entrypoint":"sdk-cli","cwd":"/DATA","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2","version":"2.1.145","gitBranch":"HEAD"} {"type":"ai-title","aiTitle":"Add trash page and restore functionality","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2"} {"parentUuid":"55c0a280-cdad-432e-8b13-9bc62219a096","isSidechain":false,"message":{"id":"msg_1779297603574","type":"message","role":"assistant","content":[{"type":"tool_use","id":"functions.Read:0","name":"Read","input":{"file_path":"/media/HDD_1TB/PrintVault/main.py"}}],"model":"kimi-k2.6","stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":0,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":0,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":"","iterations":[],"speed":"standard"},"stop_details":null},"type":"assistant","uuid":"27681d28-e7cb-46b6-ab9f-9d6b68e40846","timestamp":"2026-05-20T17:20:05.699Z","userType":"external","entrypoint":"sdk-cli","cwd":"/DATA","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2","version":"2.1.145","gitBranch":"HEAD"} {"parentUuid":"27681d28-e7cb-46b6-ab9f-9d6b68e40846","isSidechain":false,"message":{"id":"msg_1779297603574","type":"message","role":"assistant","content":[{"type":"tool_use","id":"functions.Read:1","name":"Read","input":{"file_path":"/media/HDD_1TB/PrintVault/frontend/index.html"}}],"model":"kimi-k2.6","stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":0,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":0,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":"","iterations":[],"speed":"standard"},"stop_details":null},"type":"assistant","uuid":"e76fa159-98fb-485b-91ae-42a3c34a8fbc","timestamp":"2026-05-20T17:20:05.700Z","userType":"external","entrypoint":"sdk-cli","cwd":"/DATA","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2","version":"2.1.145","gitBranch":"HEAD"} {"parentUuid":"27681d28-e7cb-46b6-ab9f-9d6b68e40846","isSidechain":false,"promptId":"998409ec-ab4b-4227-8986-411c0f339ff3","type":"user","message":{"role":"user","content":[{"tool_use_id":"functions.Read:0","type":"tool_result","content":"1\t\"\"\"\n2\tPrintVault — STL-Bibliothek für ZimaOS\n3\tFastAPI Backend + Static Frontend\n4\t\"\"\"\n5\t\n6\timport json\n7\timport os\n8\timport io\n9\timport uuid\n10\timport shutil\n11\timport sqlite3\n12\timport zipfile\n13\timport tempfile\n14\timport time\n15\timport asyncio\n16\tfrom pathlib import Path\n17\tfrom datetime import datetime\n18\tfrom typing import Optional, List\n19\t\n20\tfrom fastapi import FastAPI, File, UploadFile, HTTPException, Query, Request, BackgroundTasks\n21\tfrom fastapi.responses import FileResponse, JSONResponse, HTMLResponse, StreamingResponse\n22\tfrom fastapi.staticfiles import StaticFiles\n23\tfrom fastapi.middleware.cors import CORSMiddleware\n24\timport trimesh\n25\timport numpy as np\n26\t\n27\t# ── Konfiguration ──────────────────────────────────────────\n28\t\n29\tBASE_DIR = Path(os.environ.get(\"DATA_DIR\", \"/data\"))\n30\tSTL_DIR = BASE_DIR / \"stls\"\n31\tTHUMB_DIR = BASE_DIR / \"thumbs\"\n32\tTRASH_DIR = BASE_DIR / \"trash\"\n33\tBACKUP_DIR = BASE_DIR / \"backups\"\n34\tMETA_FILE = BASE_DIR / \"metadata.json\" # Legacy\n35\tDB_FILE = BASE_DIR / \"printvault.db\"\n36\t\n37\tfor d in (BASE_DIR, STL_DIR, THUMB_DIR, TRASH_DIR, BACKUP_DIR):\n38\t d.mkdir(parents=True, exist_ok=True)\n39\t\n40\tMAX_BACKUPS = 10\n41\t\n42\tapp = FastAPI(title=\"PrintVault\", version=\"2.0.0\")\n43\t\n44\tapp.add_middleware(\n45\t CORSMiddleware,\n46\t allow_origins=[\"*\"],\n47\t allow_methods=[\"*\"],\n48\t allow_headers=[\"*\"],\n49\t)\n50\t\n51\t\n52\t@app.middleware(\"http\")\n53\tasync def add_frame_options(request: Request, call_next):\n54\t response = await call_next(request)\n55\t response.headers[\"X-Frame-Options\"] = \"ALLOWALL\"\n56\t response.headers[\"Content-Security-Policy\"] = \"frame-ancestors 'self' http://*:* https://*:*;\"\n57\t return response\n58\t\n59\t\n60\t# ── Atomic helpers ─────────────────────────────────────────\n61\t\n62\tdef atomic_write_bytes(path: Path, data: bytes):\n63\t tmp = path.with_suffix(path.suffix + \".tmp\")\n64\t tmp.write_bytes(data)\n65\t os.replace(tmp, path)\n66\t\n67\t\n68\tdef atomic_write_text(path: Path, text: str):\n69\t atomic_write_bytes(path, text.encode(\"utf-8\"))\n70\t\n71\t\n72\t# ── Database ───────────────────────────────────────────────\n73\t\n74\tdef db_connect() -> sqlite3.Connection:\n75\t conn = sqlite3.connect(DB_FILE, timeout=15.0)\n76\t conn.row_factory = sqlite3.Row\n77\t conn.execute(\"PRAGMA foreign_keys = ON\")\n78\t conn.execute(\"PRAGMA journal_mode = WAL\")\n79\t conn.execute(\"PRAGMA synchronous = NORMAL\")\n80\t return conn\n81\t\n82\t\n83\tdef init_db():\n84\t with db_connect() as conn:\n85\t conn.execute(\"\"\"\n86\t CREATE TABLE IF NOT EXISTS files (\n87\t id TEXT PRIMARY KEY,\n88\t name TEXT NOT NULL,\n89\t note TEXT NOT NULL DEFAULT '',\n90\t tags_json TEXT NOT NULL DEFAULT '[]',\n91\t analysis_json TEXT NOT NULL DEFAULT '{}',\n92\t analysis_status TEXT NOT NULL DEFAULT 'done',\n93\t uploaded_at REAL NOT NULL\n94\t )\n95\t \"\"\")\n96\t conn.execute(\"CREATE INDEX IF NOT EXISTS idx_files_uploaded_at ON files(uploaded_at DESC)\")\n97\t\n98\t\n99\tdef row_to_dict(row: sqlite3.Row, include_path_info: bool = True) -> dict:\n100\t d = {\n101\t \"id\": row[\"id\"],\n102\t \"name\": row[\"name\"],\n103\t \"note\": row[\"note\"],\n104\t \"tags\": json.loads(row[\"tags_json\"] or \"[]\"),\n105\t \"analysis\": json.loads(row[\"analysis_json\"] or \"{}\"),\n106\t \"analysis_status\": row[\"analysis_status\"],\n107\t \"uploaded_at\": datetime.fromtimestamp(row[\"uploaded_at\"]).isoformat(),\n108\t }\n109\t if include_path_info:\n110\t stl_path = STL_DIR / f\"{row['id']}.stl\"\n111\t d[\"size_kb\"] = round(stl_path.stat().st_size / 1024, 1) if stl_path.exists() else 0\n112\t d[\"has_thumb\"] = (THUMB_DIR / f\"{row['id']}.png\").exists()\n113\t d[\"original_name\"] = stl_path.name if stl_path.exists() else \"\"\n114\t return d\n115\t\n116\t\n117\t# ── Migration: metadata.json → SQLite ─────────────────────\n118\t\n119\tdef migrate_legacy_json():\n120\t if not META_FILE.exists():\n121\t return\n122\t try:\n123\t meta = json.loads(META_FILE.read_text() or \"{}\")\n124\t except Exception:\n125\t return\n126\t if not meta:\n127\t return\n128\t imported = 0\n129\t with db_connect() as conn:\n130\t existing = {r[\"id\"] for r in conn.execute(\"SELECT id FROM files\")}\n131\t for fid, entry in meta.items():\n132\t if fid in existing:\n133\t continue\n134\t stl_path = STL_DIR / f\"{fid}.stl\"\n135\t uploaded_at = stl_path.stat().st_mtime if stl_path.exists() else time.time()\n136\t conn.execute(\n137\t \"INSERT INTO files (id,name,note,tags_json,analysis_json,analysis_status,uploaded_at) \"\n138\t \"VALUES (?,?,?,?,?,?,?)\",\n139\t (\n140\t fid,\n141\t entry.get(\"name\", fid),\n142\t entry.get(\"note\", \"\"),\n143\t json.dumps(entry.get(\"tags\", [])),\n144\t json.dumps(entry.get(\"analysis\", {})),\n145\t \"done\" if entry.get(\"analysis\") else \"pending\",\n146\t uploaded_at,\n147\t ),\n148\t )\n149\t imported += 1\n150\t conn.commit()\n151\t archive = META_FILE.with_name(\"metadata.migrated.json\")\n152\t META_FILE.rename(archive)\n153\t print(f\"[migrate] {imported} Einträge aus metadata.json nach SQLite importiert. Original → {archive.name}\")\n154\t\n155\t\n156\tdef import_orphan_stls():\n157\t \"\"\"STLs auf der Platte ohne DB-Eintrag automatisch erfassen.\"\"\"\n158\t with db_connect() as conn:\n159\t existing = {r[\"id\"] for r in conn.execute(\"SELECT id FROM files\")}\n160\t for stl_file in STL_DIR.glob(\"*.stl\"):\n161\t fid = stl_file.stem\n162\t if fid in existing:\n163\t continue\n164\t conn.execute(\n165\t \"INSERT INTO files (id,name,tags_json,analysis_json,analysis_status,uploaded_at) \"\n166\t \"VALUES (?,?,?,?,?,?)\",\n167\t (\n168\t fid,\n169\t stl_file.stem.replace(\"_\", \" \"),\n170\t \"[]\", \"{}\", \"pending\",\n171\t stl_file.stat().st_mtime,\n172\t ),\n173\t )\n174\t conn.commit()\n175\t\n176\t\n177\t# ── Backups ────────────────────────────────────────────────\n178\t\n179\tdef snapshot_db(reason: str = \"auto\"):\n180\t if not DB_FILE.exists():\n181\t return\n182\t ts = datetime.now().strftime(\"%Y%m%d-%H%M%S\")\n183\t target = BACKUP_DIR / f\"printvault-{ts}-{reason}.db\"\n184\t try:\n185\t with db_connect() as src, sqlite3.connect(target) as dst:\n186\t src.backup(dst)\n187\t except Exception as e:\n188\t print(f\"[backup] Snapshot fehlgeschlagen: {e}\")\n189\t return\n190\t rotate_backups()\n191\t\n192\t\n193\tdef rotate_backups():\n194\t backups = sorted(BACKUP_DIR.glob(\"printvault-*.db\"))\n195\t for old in backups[:-MAX_BACKUPS]:\n196\t try:\n197\t old.unlink()\n198\t except Exception:\n199\t pass\n200\t\n201\t\n202\t# ── STL-Analyse ────────────────────────────────────────────\n203\t\n204\tdef analyze_stl(path: Path) -> dict:\n205\t try:\n206\t mesh = trimesh.load(str(path))\n207\t extent = mesh.bounding_box.extents\n208\t x, y, z = float(extent[0]), float(extent[1]), float(extent[2])\n209\t dims = sorted([x, y, z], reverse=True)\n210\t\n211\t volume_mm3 = float(mesh.volume) if hasattr(mesh, \"volume\") and mesh.volume else 0\n212\t volume_cm3 = volume_mm3 / 1000.0\n213\t filament_grams = round(volume_cm3 * 1.24, 1)\n214\t faces = len(mesh.faces) if hasattr(mesh, \"faces\") and mesh.faces is not None else 0\n215\t watertight = bool(mesh.is_watertight) if hasattr(mesh, \"is_watertight\") else False\n216\t\n217\t is_manifold = False\n218\t try:\n219\t from manifold3d import Manifold\n220\t Manifold(*trimesh_to_manifold(mesh))\n221\t is_manifold = True\n222\t except Exception:\n223\t is_manifold = watertight\n224\t\n225\t return {\n226\t \"width_mm\": round(dims[0], 1),\n227\t \"depth_mm\": round(dims[1], 1),\n228\t \"height_mm\": round(dims[2], 1),\n229\t \"volume_cm3\": round(volume_cm3, 2),\n230\t \"filament_grams\": filament_grams,\n231\t \"faces\": faces,\n232\t \"watertight\": watertight,\n233\t \"manifold\": is_manifold,\n234\t }\n235\t except Exception as e:\n236\t return {\n237\t \"width_mm\": 0, \"depth_mm\": 0, \"height_mm\": 0,\n238\t \"volume_cm3\": 0, \"faces\": 0,\n239\t \"watertight\": False, \"manifold\": False,\n240\t \"error\": str(e),\n241\t }\n242\t\n243\t\n244\tdef trimesh_to_manifold(mesh):\n245\t verts = np.array(mesh.vertices, dtype=np.float64)\n246\t faces = np.array(mesh.faces, dtype=np.int32)\n247\t return verts, faces\n248\t\n249\t\n250\tdef generate_thumbnail(stl_path: Path, thumb_path: Path) -> bool:\n251\t \"\"\"Schönes Diffuse-Shaded PNG mit transparentem Hintergrund.\"\"\"\n252\t try:\n253\t import matplotlib\n254\t matplotlib.use(\"Agg\")\n255\t import matplotlib.pyplot as plt\n256\t from mpl_toolkits.mplot3d.art3d import Poly3DCollection\n257\t\n258\t mesh = trimesh.load(str(stl_path))\n259\t\n260\t # Auf den Ursprung zentrieren\n261\t mesh.apply_translation(-mesh.centroid)\n262\t\n263\t verts = np.asarray(mesh.vertices, dtype=np.float32)\n264\t faces = np.asarray(mesh.faces, dtype=np.int32)\n265\t polys = verts[faces] # (N, 3, 3)\n266\t\n267\t # Face-Normalen für Diffuse-Lighting\n268\t normals = np.asarray(mesh.face_normals, dtype=np.float32)\n269\t light_dir = np.array([0.35, -0.55, 0.75], dtype=np.float32)\n270\t light_dir /= np.linalg.norm(light_dir)\n271\t\n272\t # Lambert-Shading + Ambient + sanfter Rim-Light\n273\t diffuse = np.clip(normals @ light_dir, 0.0, 1.0)\n274\t rim = np.clip(1.0 - np.abs(normals @ np.array([0, 0, 1], dtype=np.float32)), 0, 1) ** 3\n275\t shade = 0.28 + 0.72 * diffuse + 0.08 * rim\n276\t shade = np.clip(shade, 0.0, 1.05)\n277\t\n278\t # Markenfarbe (#3B82F6 → #60A5FA an hellen Stellen)\n279\t base = np.array([0.231, 0.510, 0.965], dtype=np.float32)\n280\t highlight = np.array([0.376, 0.647, 0.980], dtype=np.float32)\n281\t # Mix zwischen base und highlight je nach Helligkeit\n282\t mix = np.clip((shade - 0.4) / 0.6, 0, 1)[:, None]\n283\t colors = base * (1 - mix) + highlight * mix\n284\t colors *= shade[:, None]\n285\t colors = np.clip(colors, 0, 1)\n286\t face_colors = np.hstack([colors, np.full((len(colors), 1), 0.98, dtype=np.float32)])\n287\t\n288\t fig = plt.figure(figsize=(6, 6), dpi=140)\n289\t ax = fig.add_subplot(111, projection=\"3d\")\n290\t fig.patch.set_alpha(0.0)\n291\t ax.set_facecolor((1, 1, 1, 0))\n292\t\n293\t coll = Poly3DCollection(polys, facecolors=face_colors, edgecolors=\"none\", linewidths=0)\n294\t coll.set_zsort(\"average\")\n295\t ax.add_collection3d(coll)\n296\t\n297\t extent = float(mesh.extents.max()) * 0.58\n298\t ax.set_xlim(-extent, extent)\n299\t ax.set_ylim(-extent, extent)\n300\t ax.set_zlim(-extent, extent)\n301\t try:\n302\t ax.set_box_aspect((1, 1, 1))\n303\t except Exception:\n304\t pass\n305\t ax.view_init(elev=28, azim=-55)\n306\t ax.axis(\"off\")\n307\t ax.set_proj_type(\"ortho\")\n308\t for pane in (ax.xaxis, ax.yaxis, ax.zaxis):\n309\t pane.pane.fill = False\n310\t pane.pane.set_edgecolor((0, 0, 0, 0))\n311\t\n312\t buf = io.BytesIO()\n313\t plt.savefig(buf, format=\"png\", bbox_inches=\"tight\", pad_inches=0.05, transparent=True, dpi=140)\n314\t buf.seek(0)\n315\t atomic_write_bytes(thumb_path, buf.read())\n316\t plt.close(fig)\n317\t return True\n318\t except Exception as e:\n319\t print(f\"Thumbnail error: {e}\")\n320\t return False\n321\t\n322\t\n323\tdef process_stl_background(file_id: str):\n324\t \"\"\"Analyse + Thumbnail im Hintergrund.\"\"\"\n325\t stl_path = STL_DIR / f\"{file_id}.stl\"\n326\t if not stl_path.exists():\n327\t return\n328\t analysis = analyze_stl(stl_path)\n329\t thumb_path = THUMB_DIR / f\"{file_id}.png\"\n330\t generate_thumbnail(stl_path, thumb_path)\n331\t with db_connect() as conn:\n332\t conn.execute(\n333\t \"UPDATE files SET analysis_json = ?, analysis_status = ? WHERE id = ?\",\n334\t (json.dumps(analysis), \"error\" if \"error\" in analysis else \"done\", file_id),\n335\t )\n336\t conn.commit()\n337\t\n338\t\n339\t# ── API: Files ─────────────────────────────────────────────\n340\t\n341\t@app.get(\"/api/files\")\n342\tdef list_files(\n343\t sort: str = Query(\"date\", regex=\"^(name|date|size|volume)$\"),\n344\t search: str = Query(\"\"),\n345\t tags: str = Query(\"\"),\n346\t):\n347\t with db_connect() as conn:\n348\t rows = conn.execute(\"SELECT * FROM files\").fetchall()\n349\t\n350\t results = [row_to_dict(r) for r in rows]\n351\t\n352\t if search:\n353\t q = search.lower()\n354\t results = [\n355\t r for r in results\n356\t if q in r[\"name\"].lower()\n357\t or q in (r.get(\"note\") or \"\").lower()\n358\t or any(q in t.lower() for t in r.get(\"tags\", []))\n359\t ]\n360\t\n361\t if tags:\n362\t required = {t.strip().lower() for t in tags.split(\",\") if t.strip()}\n363\t if required:\n364\t results = [\n365\t r for r in results\n366\t if required.issubset({t.lower() for t in r.get(\"tags\", [])})\n367\t ]\n368\t\n369\t if sort == \"name\":\n370\t results.sort(key=lambda r: r[\"name\"].lower())\n371\t elif sort == \"size\":\n372\t results.sort(key=lambda r: r[\"size_kb\"], reverse=True)\n373\t elif sort == \"volume\":\n374\t results.sort(key=lambda r: r.get(\"analysis\", {}).get(\"volume_cm3\", 0), reverse=True)\n375\t else:\n376\t results.sort(key=lambda r: r[\"uploaded_at\"], reverse=True)\n377\t\n378\t return results\n379\t\n380\t\n381\t@app.get(\"/api/files/{file_id}\")\n382\tdef get_file_detail(file_id: str):\n383\t with db_connect() as conn:\n384\t row = conn.execute(\"SELECT * FROM files WHERE id = ?\", (file_id,)).fetchone()\n385\t if not row:\n386\t raise HTTPException(404, \"Datei nicht gefunden\")\n387\t return row_to_dict(row)\n388\t\n389\t\n390\t@app.post(\"/api/upload\")\n391\tasync def upload_stl(background: BackgroundTasks, file: UploadFile = File(...)):\n392\t if not file.filename.lower().endswith(\".stl\"):\n393\t raise HTTPException(400, \"Nur .stl-Dateien erlaubt\")\n394\t\n395\t fid = str(uuid.uuid4())[:8]\n396\t stl_path = STL_DIR / f\"{fid}.stl\"\n397\t content = await file.read()\n398\t if not content:\n399\t raise HTTPException(400, \"Leere Datei\")\n400\t atomic_write_bytes(stl_path, content)\n401\t\n402\t name = file.filename.rsplit(\".\", 1)[0].replace(\"_\", \" \")\n403\t uploaded_at = time.time()\n404\t\n405\t with db_connect() as conn:\n406\t conn.execute(\n407\t \"INSERT INTO files (id,name,tags_json,analysis_json,analysis_status,uploaded_at) \"\n408\t \"VALUES (?,?,?,?,?,?)\",\n409\t (fid, name, \"[]\", \"{}\", \"pending\", uploaded_at),\n410\t )\n411\t conn.commit()\n412\t\n413\t background.add_task(process_stl_background, fid)\n414\t\n415\t return {\n416\t \"id\": fid,\n417\t \"name\": name,\n418\t \"size_kb\": round(stl_path.stat().st_size / 1024, 1),\n419\t \"analysis\": {},\n420\t \"analysis_status\": \"pending\",\n421\t \"has_thumb\": False,\n422\t }\n423\t\n424\t\n425\t@app.patch(\"/api/files/{file_id}\")\n426\tasync def update_file(file_id: str, body: dict):\n427\t with db_connect() as conn:\n428\t row = conn.execute(\"SELECT * FROM files WHERE id = ?\", (file_id,)).fetchone()\n429\t if not row:\n430\t raise HTTPException(404, \"Datei nicht gefunden\")\n431\t\n432\t fields, values = [], []\n433\t if \"name\" in body:\n434\t fields.append(\"name = ?\"); values.append(str(body[\"name\"]))\n435\t if \"note\" in body:\n436\t fields.append(\"note = ?\"); values.append(str(body[\"note\"]))\n437\t if \"tags\" in body:\n438\t tags = body[\"tags\"] if isinstance(body[\"tags\"], list) else []\n439\t tags = [str(t).strip() for t in tags if str(t).strip()]\n440\t fields.append(\"tags_json = ?\"); values.append(json.dumps(tags))\n441\t\n442\t if not fields:\n443\t return {\"ok\": True}\n444\t\n445\t values.append(file_id)\n446\t conn.execute(f\"UPDATE files SET {', '.join(fields)} WHERE id = ?\", values)\n447\t conn.commit()\n448\t return {\"ok\": True}\n449\t\n450\t\n451\t@app.delete(\"/api/files/{file_id}\")\n452\tdef delete_file(file_id: str):\n453\t \"\"\"Soft-Delete: STL + Thumbnail in /trash verschieben, DB-Eintrag löschen.\"\"\"\n454\t stl_path = STL_DIR / f\"{file_id}.stl\"\n455\t thumb_path = THUMB_DIR / f\"{file_id}.png\"\n456\t\n457\t ts = datetime.now().strftime(\"%Y%m%d-%H%M%S\")\n458\t if stl_path.exists():\n459\t shutil.move(str(stl_path), str(TRASH_DIR / f\"{file_id}-{ts}.stl\"))\n460\t if thumb_path.exists():\n461\t shutil.move(str(thumb_path), str(TRASH_DIR / f\"{file_id}-{ts}.png\"))\n462\t\n463\t with db_connect() as conn:\n464\t conn.execute(\"DELETE FROM files WHERE id = ?\", (file_id,))\n465\t conn.commit()\n466\t\n467\t return {\"ok\": True}\n468\t\n469\t\n470\t@app.get(\"/api/thumbs/{file_id}.png\")\n471\tdef get_thumbnail(file_id: str):\n472\t thumb_path = THUMB_DIR / f\"{file_id}.png\"\n473\t if not thumb_path.exists():\n474\t stl_path = STL_DIR / f\"{file_id}.stl\"\n475\t if not stl_path.exists():\n476\t raise HTTPException(404, \"Kein Thumbnail\")\n477\t generate_thumbnail(stl_path, thumb_path)\n478\t return FileResponse(thumb_path, media_type=\"image/png\")\n479\t\n480\t\n481\t@app.get(\"/api/stats\")\n482\tdef get_stats():\n483\t with db_connect() as conn:\n484\t rows = conn.execute(\"SELECT analysis_json FROM files\").fetchall()\n485\t total = len(rows)\n486\t watertight = 0\n487\t total_volume = 0.0\n488\t total_filament = 0.0\n489\t for r in rows:\n490\t try:\n491\t a = json.loads(r[\"analysis_json\"] or \"{}\")\n492\t except Exception:\n493\t a = {}\n494\t if a.get(\"watertight\"):\n495\t watertight += 1\n496\t total_volume += float(a.get(\"volume_cm3\") or 0)\n497\t total_filament += float(a.get(\"filament_grams\") or 0)\n498\t\n499\t total_size = sum(f.stat().st_size for f in STL_DIR.glob(\"*.stl\"))\n500\t\n501\t return {\n502\t \"total_files\": total,\n503\t \"total_size_mb\": round(total_size / 1024 / 1024, 1),\n504\t \"watertight\": watertight,\n505\t \"not_watertight\": total - watertight,\n506\t \"total_volume_cm3\": round(total_volume, 1),\n507\t \"total_filament_grams\": round(total_filament, 1),\n508\t }\n509\t\n510\t\n511\t@app.get(\"/api/tags\")\n512\tdef list_tags():\n513\t with db_connect() as conn:\n514\t rows = conn.execute(\"SELECT tags_json FROM files\").fetchall()\n515\t counts: dict = {}\n516\t for r in rows:\n517\t try:\n518\t for t in json.loads(r[\"tags_json\"] or \"[]\"):\n519\t counts[t] = counts.get(t, 0) + 1\n520\t except Exception:\n521\t pass\n522\t return [{\"tag\": t, \"count\": c} for t, c in sorted(counts.items(), key=lambda x: -x[1])]\n523\t\n524\t\n525\t@app.get(\"/api/download/{file_id}\")\n526\tdef download_stl(file_id: str):\n527\t stl_path = STL_DIR / f\"{file_id}.stl\"\n528\t if not stl_path.exists():\n529\t raise HTTPException(404, \"Datei nicht gefunden\")\n530\t with db_connect() as conn:\n531\t row = conn.execute(\"SELECT name FROM files WHERE id = ?\", (file_id,)).fetchone()\n532\t name = (row[\"name\"] if row else file_id).replace(\" \", \"_\") + \".stl\"\n533\t return FileResponse(stl_path, media_type=\"application/octet-stream\", filename=name)\n534\t\n535\t\n536\t# ── Backup / Restore ──────────────────────────────────────\n537\t\n538\t@app.get(\"/api/backup\")\n539\tdef backup_zip():\n540\t \"\"\"Komplette Bibliothek als ZIP herunterladen (DB + STLs + Thumbnails).\"\"\"\n541\t snapshot_db(\"manual\")\n542\t\n543\t buf = io.BytesIO()\n544\t with zipfile.ZipFile(buf, \"w\", zipfile.ZIP_DEFLATED) as zf:\n545\t if DB_FILE.exists():\n546\t zf.write(DB_FILE, \"printvault.db\")\n547\t for p in STL_DIR.glob(\"*.stl\"):\n548\t zf.write(p, f\"stls/{p.name}\")\n549\t for p in THUMB_DIR.glob(\"*.png\"):\n550\t zf.write(p, f\"thumbs/{p.name}\")\n551\t manifest = {\n552\t \"version\": \"2.0.0\",\n553\t \"created_at\": datetime.now().isoformat(),\n554\t \"files\": len(list(STL_DIR.glob(\"*.stl\"))),\n555\t }\n556\t zf.writestr(\"manifest.json\", json.dumps(manifest, indent=2))\n557\t buf.seek(0)\n558\t\n559\t fname = f\"printvault-backup-{datetime.now().strftime('%Y%m%d-%H%M%S')}.zip\"\n560\t return StreamingResponse(\n561\t buf,\n562\t media_type=\"application/zip\",\n563\t headers={\"Content-Disposition\": f'attachment; filename=\"{fname}\"'},\n564\t )\n565\t\n566\t\n567\t@app.post(\"/api/restore\")\n568\tasync def restore_zip(file: UploadFile = File(...)):\n569\t \"\"\"Backup-ZIP einspielen. Vorher wird automatisch ein Sicherheits-Snapshot angelegt.\"\"\"\n570\t if not file.filename.lower().endswith(\".zip\"):\n571\t raise HTTPException(400, \"Nur .zip erlaubt\")\n572\t\n573\t snapshot_db(\"pre-restore\")\n574\t\n575\t data = await file.read()\n576\t with tempfile.TemporaryDirectory() as tmpdir:\n577\t tmp = Path(tmpdir)\n578\t try:\n579\t with zipfile.ZipFile(io.BytesIO(data)) as zf:\n580\t # Validierung\n581\t names = zf.namelist()\n582\t if \"printvault.db\" not in names:\n583\t raise HTTPException(400, \"ZIP enthält keine printvault.db\")\n584\t zf.extractall(tmp)\n585\t except zipfile.BadZipFile:\n586\t raise HTTPException(400, \"Ungültige ZIP-Datei\")\n587\t\n588\t # DB validieren bevor wir sie übernehmen\n589\t try:\n590\t test_conn = sqlite3.connect(tmp / \"printvault.db\")\n591\t test_conn.execute(\"SELECT COUNT(*) FROM files\").fetchone()\n592\t test_conn.close()\n593\t except Exception as e:\n594\t raise HTTPException(400, f\"DB im Backup ungültig: {e}\")\n595\t\n596\t # STL & Thumbs einspielen (überschreiben)\n597\t if (tmp / \"stls\").exists():\n598\t for src in (tmp / \"stls\").glob(\"*.stl\"):\n599\t atomic_write_bytes(STL_DIR / src.name, src.read_bytes())\n600\t if (tmp / \"thumbs\").exists():\n601\t for src in (tmp / \"thumbs\").glob(\"*.png\"):\n602\t atomic_write_bytes(THUMB_DIR / src.name, src.read_bytes())\n603\t\n604\t # DB atomar ersetzen\n605\t atomic_write_bytes(DB_FILE, (tmp / \"printvault.db\").read_bytes())\n606\t\n607\t return {\"ok\": True}\n608\t\n609\t\n610\t@app.get(\"/api/backups\")\n611\tdef list_backups():\n612\t return [\n613\t {\n614\t \"name\": p.name,\n615\t \"size_kb\": round(p.stat().st_size / 1024, 1),\n616\t \"created_at\": datetime.fromtimestamp(p.stat().st_mtime).isoformat(),\n617\t }\n618\t for p in sorted(BACKUP_DIR.glob(\"printvault-*.db\"), reverse=True)\n619\t ]\n620\t\n621\t\n622\t# ── Static Frontend ────────────────────────────────────────\n623\t\n624\tFRONTEND_DIR = Path(__file__).parent / \"frontend\"\n625\tFRONTEND_DIR.mkdir(exist_ok=True)\n626\t\n627\t\n628\t@app.get(\"/\")\n629\tdef serve_frontend():\n630\t return FileResponse(FRONTEND_DIR / \"index.html\")\n631\t\n632\t\n633\tif (FRONTEND_DIR / \"assets\").exists():\n634\t app.mount(\"/assets\", StaticFiles(directory=FRONTEND_DIR / \"assets\"), name=\"assets\")\n635\t\n636\t\n637\t@app.get(\"/icon.svg\")\n638\tdef serve_icon():\n639\t return FileResponse(FRONTEND_DIR / \"icon.svg\", media_type=\"image/svg+xml\")\n640\t\n641\t\n642\t# ── Startup ────────────────────────────────────────────────\n643\t\n644\t@app.on_event(\"startup\")\n645\tdef on_startup():\n646\t init_db()\n647\t migrate_legacy_json()\n648\t import_orphan_stls()\n649\t snapshot_db(\"startup\")\n650\t\n651\t\n652\tif __name__ == \"__main__\":\n653\t import uvicorn\n654\t uvicorn.run(app, host=\"0.0.0.0\", port=3001)\n655\t"}]},"uuid":"114554a9-b83d-4784-b379-000502f6ed48","timestamp":"2026-05-20T17:20:05.959Z","toolUseResult":{"type":"text","file":{"filePath":"/media/HDD_1TB/PrintVault/main.py","content":"\"\"\"\nPrintVault — STL-Bibliothek für ZimaOS\nFastAPI Backend + Static Frontend\n\"\"\"\n\nimport json\nimport os\nimport io\nimport uuid\nimport shutil\nimport sqlite3\nimport zipfile\nimport tempfile\nimport time\nimport asyncio\nfrom pathlib import Path\nfrom datetime import datetime\nfrom typing import Optional, List\n\nfrom fastapi import FastAPI, File, UploadFile, HTTPException, Query, Request, BackgroundTasks\nfrom fastapi.responses import FileResponse, JSONResponse, HTMLResponse, StreamingResponse\nfrom fastapi.staticfiles import StaticFiles\nfrom fastapi.middleware.cors import CORSMiddleware\nimport trimesh\nimport numpy as np\n\n# ── Konfiguration ──────────────────────────────────────────\n\nBASE_DIR = Path(os.environ.get(\"DATA_DIR\", \"/data\"))\nSTL_DIR = BASE_DIR / \"stls\"\nTHUMB_DIR = BASE_DIR / \"thumbs\"\nTRASH_DIR = BASE_DIR / \"trash\"\nBACKUP_DIR = BASE_DIR / \"backups\"\nMETA_FILE = BASE_DIR / \"metadata.json\" # Legacy\nDB_FILE = BASE_DIR / \"printvault.db\"\n\nfor d in (BASE_DIR, STL_DIR, THUMB_DIR, TRASH_DIR, BACKUP_DIR):\n d.mkdir(parents=True, exist_ok=True)\n\nMAX_BACKUPS = 10\n\napp = FastAPI(title=\"PrintVault\", version=\"2.0.0\")\n\napp.add_middleware(\n CORSMiddleware,\n allow_origins=[\"*\"],\n allow_methods=[\"*\"],\n allow_headers=[\"*\"],\n)\n\n\n@app.middleware(\"http\")\nasync def add_frame_options(request: Request, call_next):\n response = await call_next(request)\n response.headers[\"X-Frame-Options\"] = \"ALLOWALL\"\n response.headers[\"Content-Security-Policy\"] = \"frame-ancestors 'self' http://*:* https://*:*;\"\n return response\n\n\n# ── Atomic helpers ─────────────────────────────────────────\n\ndef atomic_write_bytes(path: Path, data: bytes):\n tmp = path.with_suffix(path.suffix + \".tmp\")\n tmp.write_bytes(data)\n os.replace(tmp, path)\n\n\ndef atomic_write_text(path: Path, text: str):\n atomic_write_bytes(path, text.encode(\"utf-8\"))\n\n\n# ── Database ───────────────────────────────────────────────\n\ndef db_connect() -> sqlite3.Connection:\n conn = sqlite3.connect(DB_FILE, timeout=15.0)\n conn.row_factory = sqlite3.Row\n conn.execute(\"PRAGMA foreign_keys = ON\")\n conn.execute(\"PRAGMA journal_mode = WAL\")\n conn.execute(\"PRAGMA synchronous = NORMAL\")\n return conn\n\n\ndef init_db():\n with db_connect() as conn:\n conn.execute(\"\"\"\n CREATE TABLE IF NOT EXISTS files (\n id TEXT PRIMARY KEY,\n name TEXT NOT NULL,\n note TEXT NOT NULL DEFAULT '',\n tags_json TEXT NOT NULL DEFAULT '[]',\n analysis_json TEXT NOT NULL DEFAULT '{}',\n analysis_status TEXT NOT NULL DEFAULT 'done',\n uploaded_at REAL NOT NULL\n )\n \"\"\")\n conn.execute(\"CREATE INDEX IF NOT EXISTS idx_files_uploaded_at ON files(uploaded_at DESC)\")\n\n\ndef row_to_dict(row: sqlite3.Row, include_path_info: bool = True) -> dict:\n d = {\n \"id\": row[\"id\"],\n \"name\": row[\"name\"],\n \"note\": row[\"note\"],\n \"tags\": json.loads(row[\"tags_json\"] or \"[]\"),\n \"analysis\": json.loads(row[\"analysis_json\"] or \"{}\"),\n \"analysis_status\": row[\"analysis_status\"],\n \"uploaded_at\": datetime.fromtimestamp(row[\"uploaded_at\"]).isoformat(),\n }\n if include_path_info:\n stl_path = STL_DIR / f\"{row['id']}.stl\"\n d[\"size_kb\"] = round(stl_path.stat().st_size / 1024, 1) if stl_path.exists() else 0\n d[\"has_thumb\"] = (THUMB_DIR / f\"{row['id']}.png\").exists()\n d[\"original_name\"] = stl_path.name if stl_path.exists() else \"\"\n return d\n\n\n# ── Migration: metadata.json → SQLite ─────────────────────\n\ndef migrate_legacy_json():\n if not META_FILE.exists():\n return\n try:\n meta = json.loads(META_FILE.read_text() or \"{}\")\n except Exception:\n return\n if not meta:\n return\n imported = 0\n with db_connect() as conn:\n existing = {r[\"id\"] for r in conn.execute(\"SELECT id FROM files\")}\n for fid, entry in meta.items():\n if fid in existing:\n continue\n stl_path = STL_DIR / f\"{fid}.stl\"\n uploaded_at = stl_path.stat().st_mtime if stl_path.exists() else time.time()\n conn.execute(\n \"INSERT INTO files (id,name,note,tags_json,analysis_json,analysis_status,uploaded_at) \"\n \"VALUES (?,?,?,?,?,?,?)\",\n (\n fid,\n entry.get(\"name\", fid),\n entry.get(\"note\", \"\"),\n json.dumps(entry.get(\"tags\", [])),\n json.dumps(entry.get(\"analysis\", {})),\n \"done\" if entry.get(\"analysis\") else \"pending\",\n uploaded_at,\n ),\n )\n imported += 1\n conn.commit()\n archive = META_FILE.with_name(\"metadata.migrated.json\")\n META_FILE.rename(archive)\n print(f\"[migrate] {imported} Einträge aus metadata.json nach SQLite importiert. Original → {archive.name}\")\n\n\ndef import_orphan_stls():\n \"\"\"STLs auf der Platte ohne DB-Eintrag automatisch erfassen.\"\"\"\n with db_connect() as conn:\n existing = {r[\"id\"] for r in conn.execute(\"SELECT id FROM files\")}\n for stl_file in STL_DIR.glob(\"*.stl\"):\n fid = stl_file.stem\n if fid in existing:\n continue\n conn.execute(\n \"INSERT INTO files (id,name,tags_json,analysis_json,analysis_status,uploaded_at) \"\n \"VALUES (?,?,?,?,?,?)\",\n (\n fid,\n stl_file.stem.replace(\"_\", \" \"),\n \"[]\", \"{}\", \"pending\",\n stl_file.stat().st_mtime,\n ),\n )\n conn.commit()\n\n\n# ── Backups ────────────────────────────────────────────────\n\ndef snapshot_db(reason: str = \"auto\"):\n if not DB_FILE.exists():\n return\n ts = datetime.now().strftime(\"%Y%m%d-%H%M%S\")\n target = BACKUP_DIR / f\"printvault-{ts}-{reason}.db\"\n try:\n with db_connect() as src, sqlite3.connect(target) as dst:\n src.backup(dst)\n except Exception as e:\n print(f\"[backup] Snapshot fehlgeschlagen: {e}\")\n return\n rotate_backups()\n\n\ndef rotate_backups():\n backups = sorted(BACKUP_DIR.glob(\"printvault-*.db\"))\n for old in backups[:-MAX_BACKUPS]:\n try:\n old.unlink()\n except Exception:\n pass\n\n\n# ── STL-Analyse ────────────────────────────────────────────\n\ndef analyze_stl(path: Path) -> dict:\n try:\n mesh = trimesh.load(str(path))\n extent = mesh.bounding_box.extents\n x, y, z = float(extent[0]), float(extent[1]), float(extent[2])\n dims = sorted([x, y, z], reverse=True)\n\n volume_mm3 = float(mesh.volume) if hasattr(mesh, \"volume\") and mesh.volume else 0\n volume_cm3 = volume_mm3 / 1000.0\n filament_grams = round(volume_cm3 * 1.24, 1)\n faces = len(mesh.faces) if hasattr(mesh, \"faces\") and mesh.faces is not None else 0\n watertight = bool(mesh.is_watertight) if hasattr(mesh, \"is_watertight\") else False\n\n is_manifold = False\n try:\n from manifold3d import Manifold\n Manifold(*trimesh_to_manifold(mesh))\n is_manifold = True\n except Exception:\n is_manifold = watertight\n\n return {\n \"width_mm\": round(dims[0], 1),\n \"depth_mm\": round(dims[1], 1),\n \"height_mm\": round(dims[2], 1),\n \"volume_cm3\": round(volume_cm3, 2),\n \"filament_grams\": filament_grams,\n \"faces\": faces,\n \"watertight\": watertight,\n \"manifold\": is_manifold,\n }\n except Exception as e:\n return {\n \"width_mm\": 0, \"depth_mm\": 0, \"height_mm\": 0,\n \"volume_cm3\": 0, \"faces\": 0,\n \"watertight\": False, \"manifold\": False,\n \"error\": str(e),\n }\n\n\ndef trimesh_to_manifold(mesh):\n verts = np.array(mesh.vertices, dtype=np.float64)\n faces = np.array(mesh.faces, dtype=np.int32)\n return verts, faces\n\n\ndef generate_thumbnail(stl_path: Path, thumb_path: Path) -> bool:\n \"\"\"Schönes Diffuse-Shaded PNG mit transparentem Hintergrund.\"\"\"\n try:\n import matplotlib\n matplotlib.use(\"Agg\")\n import matplotlib.pyplot as plt\n from mpl_toolkits.mplot3d.art3d import Poly3DCollection\n\n mesh = trimesh.load(str(stl_path))\n\n # Auf den Ursprung zentrieren\n mesh.apply_translation(-mesh.centroid)\n\n verts = np.asarray(mesh.vertices, dtype=np.float32)\n faces = np.asarray(mesh.faces, dtype=np.int32)\n polys = verts[faces] # (N, 3, 3)\n\n # Face-Normalen für Diffuse-Lighting\n normals = np.asarray(mesh.face_normals, dtype=np.float32)\n light_dir = np.array([0.35, -0.55, 0.75], dtype=np.float32)\n light_dir /= np.linalg.norm(light_dir)\n\n # Lambert-Shading + Ambient + sanfter Rim-Light\n diffuse = np.clip(normals @ light_dir, 0.0, 1.0)\n rim = np.clip(1.0 - np.abs(normals @ np.array([0, 0, 1], dtype=np.float32)), 0, 1) ** 3\n shade = 0.28 + 0.72 * diffuse + 0.08 * rim\n shade = np.clip(shade, 0.0, 1.05)\n\n # Markenfarbe (#3B82F6 → #60A5FA an hellen Stellen)\n base = np.array([0.231, 0.510, 0.965], dtype=np.float32)\n highlight = np.array([0.376, 0.647, 0.980], dtype=np.float32)\n # Mix zwischen base und highlight je nach Helligkeit\n mix = np.clip((shade - 0.4) / 0.6, 0, 1)[:, None]\n colors = base * (1 - mix) + highlight * mix\n colors *= shade[:, None]\n colors = np.clip(colors, 0, 1)\n face_colors = np.hstack([colors, np.full((len(colors), 1), 0.98, dtype=np.float32)])\n\n fig = plt.figure(figsize=(6, 6), dpi=140)\n ax = fig.add_subplot(111, projection=\"3d\")\n fig.patch.set_alpha(0.0)\n ax.set_facecolor((1, 1, 1, 0))\n\n coll = Poly3DCollection(polys, facecolors=face_colors, edgecolors=\"none\", linewidths=0)\n coll.set_zsort(\"average\")\n ax.add_collection3d(coll)\n\n extent = float(mesh.extents.max()) * 0.58\n ax.set_xlim(-extent, extent)\n ax.set_ylim(-extent, extent)\n ax.set_zlim(-extent, extent)\n try:\n ax.set_box_aspect((1, 1, 1))\n except Exception:\n pass\n ax.view_init(elev=28, azim=-55)\n ax.axis(\"off\")\n ax.set_proj_type(\"ortho\")\n for pane in (ax.xaxis, ax.yaxis, ax.zaxis):\n pane.pane.fill = False\n pane.pane.set_edgecolor((0, 0, 0, 0))\n\n buf = io.BytesIO()\n plt.savefig(buf, format=\"png\", bbox_inches=\"tight\", pad_inches=0.05, transparent=True, dpi=140)\n buf.seek(0)\n atomic_write_bytes(thumb_path, buf.read())\n plt.close(fig)\n return True\n except Exception as e:\n print(f\"Thumbnail error: {e}\")\n return False\n\n\ndef process_stl_background(file_id: str):\n \"\"\"Analyse + Thumbnail im Hintergrund.\"\"\"\n stl_path = STL_DIR / f\"{file_id}.stl\"\n if not stl_path.exists():\n return\n analysis = analyze_stl(stl_path)\n thumb_path = THUMB_DIR / f\"{file_id}.png\"\n generate_thumbnail(stl_path, thumb_path)\n with db_connect() as conn:\n conn.execute(\n \"UPDATE files SET analysis_json = ?, analysis_status = ? WHERE id = ?\",\n (json.dumps(analysis), \"error\" if \"error\" in analysis else \"done\", file_id),\n )\n conn.commit()\n\n\n# ── API: Files ─────────────────────────────────────────────\n\n@app.get(\"/api/files\")\ndef list_files(\n sort: str = Query(\"date\", regex=\"^(name|date|size|volume)$\"),\n search: str = Query(\"\"),\n tags: str = Query(\"\"),\n):\n with db_connect() as conn:\n rows = conn.execute(\"SELECT * FROM files\").fetchall()\n\n results = [row_to_dict(r) for r in rows]\n\n if search:\n q = search.lower()\n results = [\n r for r in results\n if q in r[\"name\"].lower()\n or q in (r.get(\"note\") or \"\").lower()\n or any(q in t.lower() for t in r.get(\"tags\", []))\n ]\n\n if tags:\n required = {t.strip().lower() for t in tags.split(\",\") if t.strip()}\n if required:\n results = [\n r for r in results\n if required.issubset({t.lower() for t in r.get(\"tags\", [])})\n ]\n\n if sort == \"name\":\n results.sort(key=lambda r: r[\"name\"].lower())\n elif sort == \"size\":\n results.sort(key=lambda r: r[\"size_kb\"], reverse=True)\n elif sort == \"volume\":\n results.sort(key=lambda r: r.get(\"analysis\", {}).get(\"volume_cm3\", 0), reverse=True)\n else:\n results.sort(key=lambda r: r[\"uploaded_at\"], reverse=True)\n\n return results\n\n\n@app.get(\"/api/files/{file_id}\")\ndef get_file_detail(file_id: str):\n with db_connect() as conn:\n row = conn.execute(\"SELECT * FROM files WHERE id = ?\", (file_id,)).fetchone()\n if not row:\n raise HTTPException(404, \"Datei nicht gefunden\")\n return row_to_dict(row)\n\n\n@app.post(\"/api/upload\")\nasync def upload_stl(background: BackgroundTasks, file: UploadFile = File(...)):\n if not file.filename.lower().endswith(\".stl\"):\n raise HTTPException(400, \"Nur .stl-Dateien erlaubt\")\n\n fid = str(uuid.uuid4())[:8]\n stl_path = STL_DIR / f\"{fid}.stl\"\n content = await file.read()\n if not content:\n raise HTTPException(400, \"Leere Datei\")\n atomic_write_bytes(stl_path, content)\n\n name = file.filename.rsplit(\".\", 1)[0].replace(\"_\", \" \")\n uploaded_at = time.time()\n\n with db_connect() as conn:\n conn.execute(\n \"INSERT INTO files (id,name,tags_json,analysis_json,analysis_status,uploaded_at) \"\n \"VALUES (?,?,?,?,?,?)\",\n (fid, name, \"[]\", \"{}\", \"pending\", uploaded_at),\n )\n conn.commit()\n\n background.add_task(process_stl_background, fid)\n\n return {\n \"id\": fid,\n \"name\": name,\n \"size_kb\": round(stl_path.stat().st_size / 1024, 1),\n \"analysis\": {},\n \"analysis_status\": \"pending\",\n \"has_thumb\": False,\n }\n\n\n@app.patch(\"/api/files/{file_id}\")\nasync def update_file(file_id: str, body: dict):\n with db_connect() as conn:\n row = conn.execute(\"SELECT * FROM files WHERE id = ?\", (file_id,)).fetchone()\n if not row:\n raise HTTPException(404, \"Datei nicht gefunden\")\n\n fields, values = [], []\n if \"name\" in body:\n fields.append(\"name = ?\"); values.append(str(body[\"name\"]))\n if \"note\" in body:\n fields.append(\"note = ?\"); values.append(str(body[\"note\"]))\n if \"tags\" in body:\n tags = body[\"tags\"] if isinstance(body[\"tags\"], list) else []\n tags = [str(t).strip() for t in tags if str(t).strip()]\n fields.append(\"tags_json = ?\"); values.append(json.dumps(tags))\n\n if not fields:\n return {\"ok\": True}\n\n values.append(file_id)\n conn.execute(f\"UPDATE files SET {', '.join(fields)} WHERE id = ?\", values)\n conn.commit()\n return {\"ok\": True}\n\n\n@app.delete(\"/api/files/{file_id}\")\ndef delete_file(file_id: str):\n \"\"\"Soft-Delete: STL + Thumbnail in /trash verschieben, DB-Eintrag löschen.\"\"\"\n stl_path = STL_DIR / f\"{file_id}.stl\"\n thumb_path = THUMB_DIR / f\"{file_id}.png\"\n\n ts = datetime.now().strftime(\"%Y%m%d-%H%M%S\")\n if stl_path.exists():\n shutil.move(str(stl_path), str(TRASH_DIR / f\"{file_id}-{ts}.stl\"))\n if thumb_path.exists():\n shutil.move(str(thumb_path), str(TRASH_DIR / f\"{file_id}-{ts}.png\"))\n\n with db_connect() as conn:\n conn.execute(\"DELETE FROM files WHERE id = ?\", (file_id,))\n conn.commit()\n\n return {\"ok\": True}\n\n\n@app.get(\"/api/thumbs/{file_id}.png\")\ndef get_thumbnail(file_id: str):\n thumb_path = THUMB_DIR / f\"{file_id}.png\"\n if not thumb_path.exists():\n stl_path = STL_DIR / f\"{file_id}.stl\"\n if not stl_path.exists():\n raise HTTPException(404, \"Kein Thumbnail\")\n generate_thumbnail(stl_path, thumb_path)\n return FileResponse(thumb_path, media_type=\"image/png\")\n\n\n@app.get(\"/api/stats\")\ndef get_stats():\n with db_connect() as conn:\n rows = conn.execute(\"SELECT analysis_json FROM files\").fetchall()\n total = len(rows)\n watertight = 0\n total_volume = 0.0\n total_filament = 0.0\n for r in rows:\n try:\n a = json.loads(r[\"analysis_json\"] or \"{}\")\n except Exception:\n a = {}\n if a.get(\"watertight\"):\n watertight += 1\n total_volume += float(a.get(\"volume_cm3\") or 0)\n total_filament += float(a.get(\"filament_grams\") or 0)\n\n total_size = sum(f.stat().st_size for f in STL_DIR.glob(\"*.stl\"))\n\n return {\n \"total_files\": total,\n \"total_size_mb\": round(total_size / 1024 / 1024, 1),\n \"watertight\": watertight,\n \"not_watertight\": total - watertight,\n \"total_volume_cm3\": round(total_volume, 1),\n \"total_filament_grams\": round(total_filament, 1),\n }\n\n\n@app.get(\"/api/tags\")\ndef list_tags():\n with db_connect() as conn:\n rows = conn.execute(\"SELECT tags_json FROM files\").fetchall()\n counts: dict = {}\n for r in rows:\n try:\n for t in json.loads(r[\"tags_json\"] or \"[]\"):\n counts[t] = counts.get(t, 0) + 1\n except Exception:\n pass\n return [{\"tag\": t, \"count\": c} for t, c in sorted(counts.items(), key=lambda x: -x[1])]\n\n\n@app.get(\"/api/download/{file_id}\")\ndef download_stl(file_id: str):\n stl_path = STL_DIR / f\"{file_id}.stl\"\n if not stl_path.exists():\n raise HTTPException(404, \"Datei nicht gefunden\")\n with db_connect() as conn:\n row = conn.execute(\"SELECT name FROM files WHERE id = ?\", (file_id,)).fetchone()\n name = (row[\"name\"] if row else file_id).replace(\" \", \"_\") + \".stl\"\n return FileResponse(stl_path, media_type=\"application/octet-stream\", filename=name)\n\n\n# ── Backup / Restore ──────────────────────────────────────\n\n@app.get(\"/api/backup\")\ndef backup_zip():\n \"\"\"Komplette Bibliothek als ZIP herunterladen (DB + STLs + Thumbnails).\"\"\"\n snapshot_db(\"manual\")\n\n buf = io.BytesIO()\n with zipfile.ZipFile(buf, \"w\", zipfile.ZIP_DEFLATED) as zf:\n if DB_FILE.exists():\n zf.write(DB_FILE, \"printvault.db\")\n for p in STL_DIR.glob(\"*.stl\"):\n zf.write(p, f\"stls/{p.name}\")\n for p in THUMB_DIR.glob(\"*.png\"):\n zf.write(p, f\"thumbs/{p.name}\")\n manifest = {\n \"version\": \"2.0.0\",\n \"created_at\": datetime.now().isoformat(),\n \"files\": len(list(STL_DIR.glob(\"*.stl\"))),\n }\n zf.writestr(\"manifest.json\", json.dumps(manifest, indent=2))\n buf.seek(0)\n\n fname = f\"printvault-backup-{datetime.now().strftime('%Y%m%d-%H%M%S')}.zip\"\n return StreamingResponse(\n buf,\n media_type=\"application/zip\",\n headers={\"Content-Disposition\": f'attachment; filename=\"{fname}\"'},\n )\n\n\n@app.post(\"/api/restore\")\nasync def restore_zip(file: UploadFile = File(...)):\n \"\"\"Backup-ZIP einspielen. Vorher wird automatisch ein Sicherheits-Snapshot angelegt.\"\"\"\n if not file.filename.lower().endswith(\".zip\"):\n raise HTTPException(400, \"Nur .zip erlaubt\")\n\n snapshot_db(\"pre-restore\")\n\n data = await file.read()\n with tempfile.TemporaryDirectory() as tmpdir:\n tmp = Path(tmpdir)\n try:\n with zipfile.ZipFile(io.BytesIO(data)) as zf:\n # Validierung\n names = zf.namelist()\n if \"printvault.db\" not in names:\n raise HTTPException(400, \"ZIP enthält keine printvault.db\")\n zf.extractall(tmp)\n except zipfile.BadZipFile:\n raise HTTPException(400, \"Ungültige ZIP-Datei\")\n\n # DB validieren bevor wir sie übernehmen\n try:\n test_conn = sqlite3.connect(tmp / \"printvault.db\")\n test_conn.execute(\"SELECT COUNT(*) FROM files\").fetchone()\n test_conn.close()\n except Exception as e:\n raise HTTPException(400, f\"DB im Backup ungültig: {e}\")\n\n # STL & Thumbs einspielen (überschreiben)\n if (tmp / \"stls\").exists():\n for src in (tmp / \"stls\").glob(\"*.stl\"):\n atomic_write_bytes(STL_DIR / src.name, src.read_bytes())\n if (tmp / \"thumbs\").exists():\n for src in (tmp / \"thumbs\").glob(\"*.png\"):\n atomic_write_bytes(THUMB_DIR / src.name, src.read_bytes())\n\n # DB atomar ersetzen\n atomic_write_bytes(DB_FILE, (tmp / \"printvault.db\").read_bytes())\n\n return {\"ok\": True}\n\n\n@app.get(\"/api/backups\")\ndef list_backups():\n return [\n {\n \"name\": p.name,\n \"size_kb\": round(p.stat().st_size / 1024, 1),\n \"created_at\": datetime.fromtimestamp(p.stat().st_mtime).isoformat(),\n }\n for p in sorted(BACKUP_DIR.glob(\"printvault-*.db\"), reverse=True)\n ]\n\n\n# ── Static Frontend ────────────────────────────────────────\n\nFRONTEND_DIR = Path(__file__).parent / \"frontend\"\nFRONTEND_DIR.mkdir(exist_ok=True)\n\n\n@app.get(\"/\")\ndef serve_frontend():\n return FileResponse(FRONTEND_DIR / \"index.html\")\n\n\nif (FRONTEND_DIR / \"assets\").exists():\n app.mount(\"/assets\", StaticFiles(directory=FRONTEND_DIR / \"assets\"), name=\"assets\")\n\n\n@app.get(\"/icon.svg\")\ndef serve_icon():\n return FileResponse(FRONTEND_DIR / \"icon.svg\", media_type=\"image/svg+xml\")\n\n\n# ── Startup ────────────────────────────────────────────────\n\n@app.on_event(\"startup\")\ndef on_startup():\n init_db()\n migrate_legacy_json()\n import_orphan_stls()\n snapshot_db(\"startup\")\n\n\nif __name__ == \"__main__\":\n import uvicorn\n uvicorn.run(app, host=\"0.0.0.0\", port=3001)\n","numLines":655,"startLine":1,"totalLines":655}},"sourceToolAssistantUUID":"27681d28-e7cb-46b6-ab9f-9d6b68e40846","userType":"external","entrypoint":"sdk-cli","cwd":"/DATA","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2","version":"2.1.145","gitBranch":"HEAD"} {"parentUuid":"e76fa159-98fb-485b-91ae-42a3c34a8fbc","isSidechain":false,"promptId":"998409ec-ab4b-4227-8986-411c0f339ff3","type":"user","message":{"role":"user","content":[{"tool_use_id":"functions.Read:1","type":"tool_result","content":"1\t\n2\t\n3\t\n4\t\n5\t\n6\tPrintVault\n7\t\n8\t\n9\t\n10\t\n18\t\n884\t\n885\t\n886\t\n887\t
\n888\t
\n889\t
\n890\t
\n891\t \n892\t \n893\t \n894\t \n895\t \n896\t
\n897\t
\n898\t

PrintVault

\n899\t
STL-Bibliothek
\n900\t
\n901\t
\n902\t
\n903\t
\n904\t 0 druckbar\n905\t 0 Modelle\n906\t ≈ 0,00 €\n907\t
\n908\t \n913\t \n918\t
\n919\t
\n920\t
\n921\t\n922\t
\n923\t
Deine Modelle
\n924\t
Suche, organisiere und drucke deine STL-Sammlung.
\n925\t\n926\t
\n927\t
\n928\t \n929\t \n930\t
\n931\t \n937\t
\n938\t\n939\t
\n940\t
\n941\t\n942\t
\n943\t \n951\t
\n952\t\n953\t
\n954\t\n955\t
\n956\t
\n957\t\n958\t\n1081\t\n1082\t\n1583\t\n1584\t\n1585\t"}]},"uuid":"851dd2e6-7960-41fc-8821-8d0b690bf64b","timestamp":"2026-05-20T17:20:06.007Z","toolUseResult":{"type":"text","file":{"filePath":"/media/HDD_1TB/PrintVault/frontend/index.html","content":"\n\n\n\n\nPrintVault\n\n\n\n\n\n\n\n\n
\n
\n
\n
\n \n \n \n \n \n
\n
\n

PrintVault

\n
STL-Bibliothek
\n
\n
\n
\n
\n 0 druckbar\n 0 Modelle\n ≈ 0,00 €\n
\n \n \n
\n
\n
\n\n
\n
Deine Modelle
\n
Suche, organisiere und drucke deine STL-Sammlung.
\n\n
\n
\n \n \n
\n \n
\n\n
\n
\n\n
\n \n
\n\n
\n\n
\n
\n\n\n\n\n\n\n","numLines":1585,"startLine":1,"totalLines":1585}},"sourceToolAssistantUUID":"e76fa159-98fb-485b-91ae-42a3c34a8fbc","userType":"external","entrypoint":"sdk-cli","cwd":"/DATA","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2","version":"2.1.145","gitBranch":"HEAD"} {"type":"last-prompt","lastPrompt":"Implementiere Idee #7: Papierkorb-Seite (Trash UI) für PrintVault.\\n\\nBACKEND (main.py unter /media/HDD_1TB/PrintVault/main.py):\\n- TRASH_DIR existiert bereits, Soft-Delete verschiebt .stl/.png nach /…","leafUuid":"851dd2e6-7960-41fc-8821-8d0b690bf64b","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2"} {"type":"ai-title","aiTitle":"Add trash page and restore functionality","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2"} {"type":"last-prompt","lastPrompt":"Implementiere Idee #7: Papierkorb-Seite (Trash UI) für PrintVault.\\n\\nBACKEND (main.py unter /media/HDD_1TB/PrintVault/main.py):\\n- TRASH_DIR existiert bereits, Soft-Delete verschiebt .stl/.png nach /…","leafUuid":"851dd2e6-7960-41fc-8821-8d0b690bf64b","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2"} {"type":"ai-title","aiTitle":"Add trash page and restore functionality","sessionId":"58e15d46-8cfa-4bcd-9455-8bf6c0e667a2"}