stage 2 builder: scrub of other runs' leftover objects, drop of foreign reads; rebuild (36 train + 4 valid), doc generator, HF dataset updated

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

train/build_stage2.py

@@ -14,6 +14,7 @@ nothing of the system turn (tool schemas), the user turn or the tool results is
 """
 import argparse
 import importlib
+import re
 import json
 import os
 import random
@@ -33,6 +34,55 @@ from transformers import AutoTokenizer  # noqa: E402
 POOL = os.path.join(ROOT, "tasks_gen", "train")
 
 
+START_PREFIX = re.compile(r"^(Z\d[0-9A-Z]{6}_)", re.I)
+MID_PREFIX = re.compile(r"^[A-Z]{1,5}_(Z\d[0-9A-Z]{6}_)", re.I)
+LIST_TOOLS = ("sap_inactive_objects", "sap_search_object", "sap_usage_references")
+READ_TOOLS = ("sap_pull_source", "sap_object_structure", "sap_object_members", "sap_element_info", "sap_run_unit_test", "sap_check_object",
+              "sap_syntax_check", "sap_atc_run")
+
+
+def foreign_name(name, own):
+    n = (name or "").upper()
+    m = START_PREFIX.match(n) or MID_PREFIX.match(n)
+    return bool(m) and m.group(1).upper() != own.upper()
+
+
+def scrub_foreign(msgs, own_prefix):
+    """Remove other runs' leftover objects from list results (the proxy hides them since 2026-10-06; the older records still have them).
+    Returns (messages, removed list entries, number of reads of a foreign object)."""
+    tool_of = {}
+    for m in msgs:
+        if m["role"] == "assistant":
+            for c in m.get("tool_calls") or []:
+                a = c["function"].get("arguments") or "{}"
+                try:
+                    a = json.loads(a) if isinstance(a, str) else a
+                except ValueError:
+                    a = {}
+                tool_of[c.get("id")] = (c["function"]["name"], a)
+    removed = reads = 0
+    out = []
+    for m in msgs:
+        if m["role"] == "tool":
+            name, args = tool_of.get(m.get("tool_call_id"), ("", {}))
+            if name in READ_TOOLS and foreign_name(args.get("objectName"), own_prefix):
+                reads += 1
+            if name in LIST_TOOLS:
+                body = m["content"]
+                prefix = "ERROR: " if body.startswith("ERROR: ") else ""
+                try:
+                    data = json.loads(body[len(prefix):])
+                except ValueError:
+                    data = None
+                if isinstance(data, list):
+                    keep = [d for d in data if not (isinstance(d, dict) and foreign_name(d.get("name"), own_prefix))]
+                    if len(keep) != len(data):
+                        removed += len(data) - len(keep)
+                        m = dict(m, content=prefix + json.dumps(keep))
+        out.append(m)
+    return out, removed, reads
+
+
 def pct(v, p):
     v = sorted(v)
     return v[min(len(v) - 1, int(p * len(v)))] if v else None
@@ -65,6 +115,8 @@ def main():
     ap.add_argument("--min-score", type=float, default=80)
     ap.add_argument("--valid-frac", type=float, default=0.10)
     ap.add_argument("--seed", type=int, default=20261006)
+    ap.add_argument("--no-scrub", action="store_true", help="keep other runs' leftover objects in list results (default: removed)")
+    ap.add_argument("--keep-foreign-reads", action="store_true", help="keep trajectories in which the model read another run's object (default: dropped)")
     ap.add_argument("--hook", help="module:function; function(row) -> None to drop, or a float weight (repeat factor), or a dict "
                                    "{'keep': bool, 'weight': float, 'extra': {...}} (for example the own-test mutation score)")
     a = ap.parse_args()
@@ -90,7 +142,14 @@ def main():
         if not ok:
             continue
         msgs, removed = acc.trim_loops(rec["messages"])
-        cand.append({"rec": rec, "msgs": msgs, "removed": removed, "row": r, "repair": acc.has_repair(msgs)})
+        scrubbed = freads = 0
+        if not a.no_scrub:
+            msgs, scrubbed, freads = scrub_foreign(msgs, rec["prefix"])
+        if freads and not a.keep_foreign_reads:
+            kind0 = mix.kind_of_task_dir(r["task"])
+            report["dropped"][kind0]["read_of_another_runs_object"] += 1
+            continue
+        cand.append({"rec": rec, "msgs": msgs, "removed": removed, "row": r, "repair": acc.has_repair(msgs), "scrubbed": scrubbed, "freads": freads})
     report["steps"]["accepted_trajectories"] = len(cand)
 
     # 2 eval overlap at build time (the task against every eval task)
@@ -127,7 +186,7 @@ def main():
         t = c["rec"]["task"]
         samples.append({"id": f"{c['row']['task']}_r{c['row']['run']}", "task": c["row"]["task"], "family": family_of(c["row"]["task"]),
                         "kind": c["kind"], "category": t.get("category"), "object_type": t.get("object_type"),
-                        "attempt": c["row"]["attempt"], "repair": c["repair"], "loop_pairs_removed": c["removed"],
+                        "attempt": c["row"]["attempt"], "repair": c["repair"], "loop_pairs_removed": c["removed"], "foreign_entries_removed": c["scrubbed"],
                         "score": c["rec"]["metadata"].get("score"), "teacher": c["rec"]["teacher"], "weight": 1.0,
                         "n_tokens": n, "assistant_tokens": nl, "text": text, "assistant_spans": spans})
     report["steps"]["after_token_limit"] = len(samples)
@@ -250,6 +309,7 @@ Samples over {r['settings']['max_tokens']} tokens are dropped, never cut. CLAS i
 
 ## Known limits
 - Small data (see the table); kinds marked short have fewer than the minimum samples.
+- Until 2026-10-06 the test system still held leftover objects of earlier runs (the model's own `ZCL_<prefix>_...` classes). Their names are removed from list results (`sap_inactive_objects`, searches) in these samples; trajectories in which the model read such an object are dropped.
 - The proxy added local abaplint messages (`syntaxCheck`) to some failed writes; the EPOD server does not do this itself.
 - The teacher sees only the tool results of its own runs; a run that repaired an error is kept with its error (60 to 65 % of the samples).
 - Validation split is by task family; do not mix valid samples into the training set.