$ python test_import.py https://www.recipetineats.com --count=10 --job-id=81039067-def3-4abf-a13e-8adfb784e018 --new-count=1700
Working directory: /app
------------------------------------------------------------
📡 Fetching recipe URLs from sitemap...
Trying: https://www.recipetineats.com/sitemap.xml
Found sitemap index with 8 sitemaps
Processing: https://www.recipetineats.com/post-sitemap.xml
Processing: https://www.recipetineats.com/post-sitemap2.xml
Processing: https://www.recipetineats.com/post-sitemap3.xml
Processing: https://www.recipetineats.com/post-sitemap4.xml
Found 1700 total recipes
📋 Checking for existing recipes...
Checking existing recipes in Mealie...
2026-08-14 16:06:13,479 - mealie_client - INFO - MealieClient initialized in API mode
Found 0 existing recipes
1700 new recipes available (deduplicated)
============================================================
TEST IMPORT: 10 recipes (batched pipeline)
============================================================
2026-08-14 16:06:13,501 - mealie_client - INFO - MealieClient initialized in API mode
🔍 Checking existing recipes for duplicates (Mealie API)...
✅ Found 0 existing recipe URLs in Mealie
📥 Importing 10 new recipes in batches of 10
==================================================
BATCH 1/1 (10 recipes)
==================================================
📥 Phase 1: Importing...
Polling report 6c77c328-f617-400d-89f9-b2547f80a2c8...
[1] Status: in-progress | 0/10 succeeded | 0s elapsed
[2] Status: in-progress | 0/10 succeeded | 1s elapsed
[3] Status: in-progress | 0/10 succeeded | 2s elapsed
[4] Status: in-progress | 0/10 succeeded | 4s elapsed
[5] Status: in-progress | 0/10 succeeded | 5s elapsed
[6] Status: in-progress | 0/10 succeeded | 6s elapsed
[7] Status: in-progress | 0/10 succeeded | 7s elapsed
[8] Status: in-progress | 0/10 succeeded | 8s elapsed
[9] Status: in-progress | 0/10 succeeded | 10s elapsed
[10] Status: in-progress | 0/10 succeeded | 11s elapsed
[11] Status: in-progress | 0/10 succeeded | 12s elapsed
[12] Status: success | 10/10 succeeded | 13s elapsed
2026-08-14 16:06:26,798 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:26,816 - bulk_import_smart - INFO - Looked up 10/10 recipes by URL
✅ Imported 10 recipes
🔍 Phase 2: Parsing ingredients...
2026-08-14 16:06:26,816 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:35,952 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:36,806 - mealie_parse - INFO - Loaded 2681 canonical foods from Mealie
2026-08-14 16:06:36,815 - mealie_parse - INFO - Direct LLM parsed 11 ingredients, 6 matched to canonical
2026-08-14 16:06:36,816 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:36,840 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:36,860 - mealie_parse - INFO - Loaded 37 canonical units from Mealie
2026-08-14 16:06:36,861 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:36,882 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:36,900 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:36,922 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:36,944 - mealie_parse - ERROR - Unexpected error parsing easter-cake: [Errno 2] No such file or directory: '/app/data/runtime/last_payload.json'
❌ Parse failed: easter-cake
2026-08-14 16:06:36,945 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:46,478 - mealie_parse - INFO - Direct LLM parsed 13 ingredients, 10 matched to canonical
2026-08-14 16:06:46,478 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:46,501 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:46,521 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:46,538 - mealie_parse - WARNING - Couldn't create or find food 'boiling water': [POST] HTTP error: 409 Client Error: Conflict for url: http://mealie:9000/api/foods
2026-08-14 16:06:46,539 - mealie_parse - ERROR - Unexpected error parsing lemon-pepper-pork: [Errno 2] No such file or directory: '/app/data/runtime/last_payload.json'
❌ Parse failed: lemon-pepper-pork
2026-08-14 16:06:46,539 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:50,692 - mealie_parse - INFO - Direct LLM parsed 10 ingredients, 9 matched to canonical
2026-08-14 16:06:50,693 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:50,716 - mealie_parse - ERROR - Unexpected error parsing bearnaise-sauce-fast-easy-foolproof-method: [Errno 2] No such file or directory: '/app/data/runtime/last_payload.json'
❌ Parse failed: bearnaise-sauce-fast-easy-foolproof-method
2026-08-14 16:06:50,716 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:06:56,167 - mealie_parse - INFO - Direct LLM parsed 11 ingredients, 11 matched to canonical
2026-08-14 16:06:56,168 - mealie_parse - ERROR - Unexpected error parsing cajun-blackened-fish-video: [Errno 2] No such file or directory: '/app/data/runtime/last_payload.json'
❌ Parse failed: cajun-blackened-fish-video
2026-08-14 16:06:56,168 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:01,863 - mealie_parse - INFO - Direct LLM parsed 8 ingredients, 8 matched to canonical
2026-08-14 16:07:01,864 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:01,909 - mealie_parse - INFO - Created new unit: punnet (id: 95cef627-b195-4769-a3e7-1532148fb4b1) - added to cache
2026-08-14 16:07:01,909 - mealie_parse - ERROR - Unexpected error parsing strawberry-nutella-french-toast-roll-ups: [Errno 2] No such file or directory: '/app/data/runtime/last_payload.json'
❌ Parse failed: strawberry-nutella-french-toast-roll-ups
2026-08-14 16:07:01,910 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:07,670 - mealie_parse - INFO - Direct LLM parsed 14 ingredients, 13 matched to canonical
2026-08-14 16:07:07,671 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:07,707 - mealie_parse - INFO - Created new unit: stalk (id: 132c7645-06df-4830-8006-8c363daa44ef) - added to cache
2026-08-14 16:07:07,708 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:07,724 - mealie_parse - ERROR - Unexpected error parsing sausage-stuffing: [Errno 2] No such file or directory: '/app/data/runtime/last_payload.json'
❌ Parse failed: sausage-stuffing
2026-08-14 16:07:07,724 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:08,811 - mealie_parse - WARNING - LLM returned 0 ingredients, expected 1
2026-08-14 16:07:08,813 - mealie_parse - ERROR - ❌ LLM parsing failed - SKIPPING RECIPE to maintain 100% quality
2026-08-14 16:07:08,813 - mealie_parse - ERROR - This recipe will remain unparsed rather than use unreliable NLP fallback
2026-08-14 16:07:08,813 - mealie_parse - ERROR - Parsing failed for buttercream-frosting-10-flavours - LLM parsing unsuccessful
❌ Parse failed: buttercream-frosting-10-flavours
2026-08-14 16:07:08,814 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:15,266 - mealie_parse - INFO - Direct LLM parsed 20 ingredients, 17 matched to canonical
2026-08-14 16:07:15,268 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:15,290 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:15,311 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:15,333 - mealie_parse - ERROR - Unexpected error parsing sausage-ragu-with-pappardelle-pasta: [Errno 2] No such file or directory: '/app/data/runtime/last_payload.json'
❌ Parse failed: sausage-ragu-with-pappardelle-pasta
2026-08-14 16:07:15,334 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:23,801 - mealie_parse - INFO - Direct LLM parsed 12 ingredients, 11 matched to canonical
2026-08-14 16:07:23,802 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:23,820 - mealie_parse - WARNING - Couldn't create or find food 'cooking salt': [POST] HTTP error: 409 Client Error: Conflict for url: http://mealie:9000/api/foods
2026-08-14 16:07:23,821 - mealie_parse - ERROR - Unexpected error parsing slow-roast-leg-of-lamb: [Errno 2] No such file or directory: '/app/data/runtime/last_payload.json'
❌ Parse failed: slow-roast-leg-of-lamb
2026-08-14 16:07:23,821 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:27,578 - mealie_parse - INFO - Direct LLM parsed 12 ingredients, 11 matched to canonical
2026-08-14 16:07:27,579 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:27,616 - mealie_parse - INFO - Created new unit: third cup (id: 8adc4a7d-efd7-49c5-aff8-d3dab495a9ad) - added to cache
2026-08-14 16:07:27,616 - mealie_client - INFO - MealieClient initialized in API mode
2026-08-14 16:07:27,637 - mealie_parse - ERROR - Unexpected error parsing apple-and-rhubarb-crumble: [Errno 2] No such file or directory: '/app/data/runtime/last_payload.json'
❌ Parse failed: apple-and-rhubarb-crumble
⚠️ 10 recipes failed parsing - skipping from pipeline
2026-08-14 16:07:27,638 - mealie_client - INFO - MealieClient initialized in API mode
🗑️ Deleted failed recipe: easter-cake
2026-08-14 16:07:27,700 - bulk_import_smart - INFO - Deleted failed recipe easter-cake from Mealie
🗑️ Deleted failed recipe: lemon-pepper-pork
2026-08-14 16:07:27,753 - bulk_import_smart - INFO - Deleted failed recipe lemon-pepper-pork from Mealie
🗑️ Deleted failed recipe: bearnaise-sauce-fast-easy-foolproof-method
2026-08-14 16:07:27,810 - bulk_import_smart - INFO - Deleted failed recipe bearnaise-sauce-fast-easy-foolproof-method from Mealie
🗑️ Deleted failed recipe: cajun-blackened-fish-video
2026-08-14 16:07:27,862 - bulk_import_smart - INFO - Deleted failed recipe cajun-blackened-fish-video from Mealie
🗑️ Deleted failed recipe: strawberry-nutella-french-toast-roll-ups
2026-08-14 16:07:27,910 - bulk_import_smart - INFO - Deleted failed recipe strawberry-nutella-french-toast-roll-ups from Mealie
🗑️ Deleted failed recipe: sausage-stuffing
2026-08-14 16:07:27,955 - bulk_import_smart - INFO - Deleted failed recipe sausage-stuffing from Mealie
🗑️ Deleted failed recipe: buttercream-frosting-10-flavours
2026-08-14 16:07:28,611 - bulk_import_smart - INFO - Deleted failed recipe buttercream-frosting-10-flavours from Mealie
🗑️ Deleted failed recipe: sausage-ragu-with-pappardelle-pasta
2026-08-14 16:07:28,658 - bulk_import_smart - INFO - Deleted failed recipe sausage-ragu-with-pappardelle-pasta from Mealie
🗑️ Deleted failed recipe: slow-roast-leg-of-lamb
2026-08-14 16:07:28,707 - bulk_import_smart - INFO - Deleted failed recipe slow-roast-leg-of-lamb from Mealie
🗑️ Deleted failed recipe: apple-and-rhubarb-crumble
2026-08-14 16:07:28,754 - bulk_import_smart - INFO - Deleted failed recipe apple-and-rhubarb-crumble from Mealie
⚠️ No recipes to process after parsing
==================================================
✅ IMPORT COMPLETE
==================================================
Total imported: 10
Completed: 0
Failed: 10
🔍 Verifying RAG index...
🔧 Initializing USearch ANN index with dimension 4096
✅ USearch index initialized for cosine similarity search
2026-08-14 16:07:28,884 - recipe_rag - WARNING - ⚠️ No ANN index found. Run migration to build index.
🗑️ 10 non-recipes correctly filtered out
📄 Results saved to: /app/data/import_tests/81039067-def3-4abf-a13e-8adfb784e018.json
============================================================
TEST RESULTS: 0 recipes imported, 10 non-recipes filtered
RAG INDEX: 0/0 verified ✅
============================================================
⏱️ Timing:
Total test time: 75.3 seconds
Average per recipe: 7.5 seconds
✅ Test passed - pipeline is working
📎 View imported recipes:
------------------------------------------------------------
✅ Completed successfully