Prevent + net the unescaped-quote bug in the durable prompts/pipeline
The escape-ASCII-quote rule previously lived only in ephemeral Agent-call strings. Bake it into the durable artifacts so the next session doesn't re-derive it: - SUBAGENT_PROMPT.md + ENRICHMENT_PROMPT.md: explicit rule to escape any ASCII " inside JSON string values (Romanian „cuvânt" is the trap). - run_enrichment.py collect_enrichment: repair malformed parts with escape_stray_quotes instead of dropping them — the enrichment path had no repair net (bad parts were silently dropped, losing that activity's enrichment). Extraction already had one; now both do. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -49,6 +49,7 @@ from import_common import ( # noqa: E402
|
||||
find_chunk_text,
|
||||
normalize_name,
|
||||
)
|
||||
from repair_extractions import escape_stray_quotes # noqa: E402
|
||||
|
||||
ENRICHMENT_PROMPT = SCRIPT_DIR / "ENRICHMENT_PROMPT.md"
|
||||
|
||||
@@ -169,11 +170,26 @@ def collect_enrichment(parts_dir: Path, out_path: Path) -> dict:
|
||||
"""Merge data/enrichment_parts/*.json into one flat content_key map."""
|
||||
merged: dict = {}
|
||||
bad: list[str] = []
|
||||
repaired: list[str] = []
|
||||
if parts_dir.is_dir():
|
||||
for part in sorted(parts_dir.glob("*.json")):
|
||||
raw = part.read_text(encoding="utf-8")
|
||||
try:
|
||||
data = json.loads(part.read_text(encoding="utf-8"))
|
||||
except (json.JSONDecodeError, OSError):
|
||||
data = json.loads(raw)
|
||||
except json.JSONDecodeError:
|
||||
# Enrichment subagents hit the same unescaped-ASCII-quote bug as
|
||||
# extraction (description_ro is full of Romanian „…"). Repair by
|
||||
# escaping rather than dropping the activity's enrichment.
|
||||
try:
|
||||
data = json.loads(escape_stray_quotes(raw))
|
||||
repaired.append(part.name)
|
||||
except json.JSONDecodeError:
|
||||
bad.append(part.name)
|
||||
continue
|
||||
except OSError:
|
||||
bad.append(part.name)
|
||||
continue
|
||||
if not isinstance(data, dict):
|
||||
bad.append(part.name)
|
||||
continue
|
||||
key = data.get("content_key") or part.stem
|
||||
@@ -182,7 +198,8 @@ def collect_enrichment(parts_dir: Path, out_path: Path) -> dict:
|
||||
out_path.write_text(
|
||||
json.dumps(merged, ensure_ascii=False, indent=2), encoding="utf-8"
|
||||
)
|
||||
return {"entries": len(merged), "bad_parts": bad, "out": str(out_path)}
|
||||
return {"entries": len(merged), "repaired": repaired,
|
||||
"bad_parts": bad, "out": str(out_path)}
|
||||
|
||||
|
||||
def run_emit(
|
||||
@@ -235,6 +252,8 @@ def main(argv: Optional[list[str]] = None) -> int:
|
||||
if args.collect:
|
||||
result = collect_enrichment(Path(args.parts), Path(args.out))
|
||||
print(f"collected : {result['entries']} entries -> {result['out']}")
|
||||
if result["repaired"]:
|
||||
print(f"repaired : {len(result['repaired'])} parts (unescaped-quote fix)")
|
||||
if result["bad_parts"]:
|
||||
print(f"bad parts : {len(result['bad_parts'])} (skipped)")
|
||||
for name in result["bad_parts"]:
|
||||
|
||||
Reference in New Issue
Block a user