Harness: runner, generator, tasks T01 T13 T14 T15, CLAUDE.md

harness/pilot.py

@@ -0,0 +1,48 @@
+"""Pilot: generate and validate a list of tasks, one after the other."""
+import json
+import os
+import sys
+
+from .adt_client import load_env
+from .generator import ROOT, generate
+from .ledger import BudgetExceeded, spent
+
+PLAN = [
+    ("CLAS", "A"), ("CLAS", "B"), ("CLAS", "C"), ("CLAS", "D"), ("CLAS", "E"),
+    ("CLAS", "F"), ("CLAS", "G"), ("CLAS", "I"), ("CLAS", "C"),
+    ("FUNC", "A"), ("FUNC", "F"), ("FUNC", "I"),
+    ("PROG", "B"), ("PROG", "B"), ("PROG", "E"),
+    ("DDLS", "B"), ("DDLS", "B"), ("DDLS", "B"), ("DDLS", "B"), ("DDLS", "B"),
+]
+DDLS_TOPICS = ["join of two tables and a calculated element", "association and path expression",
+               "aggregation with CASE and GROUP BY", "view with input parameters",
+               "UNION of two tables with a literal source element"]
+
+
+def main():
+    load_env(os.path.join(ROOT, ".env"))
+    first = int(sys.argv[1]) if len(sys.argv) > 1 else 2
+    results = []
+    d = 0
+    for k, (otype, cat) in enumerate(PLAN):
+        tid = f"G{first + k:04d}"
+        topic = None
+        if otype == "DDLS":
+            topic, d = DDLS_TOPICS[d], d + 1
+        try:
+            log = generate(tid, "eval", otype, cat, 2, "deepseek-v4.1-flash:cloud",
+                           os.environ.get("LLM_BASE_URL", "http://127.0.0.1:11434/v1"),
+                           1100 + 10 * k, topic)
+        except BudgetExceeded as e:
+            print("BUDGET", e, flush=True)
+            break
+        except Exception as e:  # noqa: BLE001
+            log = {"id": tid, "error": str(e)[:500]}
+        log["spent_total"] = spent()
+        results.append(log)
+        print(json.dumps(log), flush=True)
+        json.dump(results, open(os.path.join(ROOT, "runs", "gen", "pilot.json"), "w"), indent=1)
+
+
+if __name__ == "__main__":
+    main()