live: EXTERNAL_SERVICE_TOKEN precedence, baked A/B candidates, model|gpu ledger from task/page modelId+gpuType, string total fix, Iluvatar/MTT enums (59 tests)

scripts/bake_ledger.py

@@ -0,0 +1,39 @@
+"""Extract only model/GPU identities from local evidence; never copy raw fields."""
+import json
+import re
+import sys
+from pathlib import Path
+sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
+from src.config_params import GPU_ENUMS
+from src.live_queue import model_key
+from src.pending_pool import load_do_not_resubmit
+
+
+def extract(value, source, pairs):
+    if isinstance(value, dict):
+        model = value.get('modelId') or value.get('model') or value.get('model_address')
+        gpu = value.get('gpuType') or value.get('gpu_code') or value.get('gpu') or value.get('gpuLabel')
+        if isinstance(model, str) and re.fullmatch(r'[\w.-]+/[\w.\-/]+', model) and isinstance(gpu, str) and gpu in GPU_ENUMS:
+            pairs.setdefault((model_key(model), GPU_ENUMS[gpu]), source)
+        for child in value.values():
+            extract(child, source, pairs)
+    elif isinstance(value, list):
+        for child in value:
+            extract(child, source, pairs)
+
+
+def main():
+    base = Path('/workspace/modelhub-adapt')
+    files = [base / 'logs/task-page-snapshot-2026-10-17.json', *sorted((base / 'logs').glob('submit-session-*.json')), *sorted((base / 'logs').glob('submit-batch-*.json'))]
+    pairs = {}
+    for path in files:
+        extract(json.loads(path.read_text()), path.name, pairs)
+    blocks = sorted(map(model_key, load_do_not_resubmit(base / 'do-not-resubmit.md')))
+    output = Path(__file__).resolve().parents[1] / 'src/data/submitted-ledger.json'
+    output.parent.mkdir(exist_ok=True)
+    output.write_text(json.dumps(dict(pairs=[dict(model=m, gpu=g, source=s) for (m,g),s in sorted(pairs.items())], blocked_models=blocks), indent=2) + '\n')
+    print('baked pairs', len(pairs), 'blocked models', len(blocks))
+
+
+if __name__ == '__main__':
+    main()