Prefer batch CLI in playbooks, cap tool persistence, and steer getManagedNe failures.

Default scheduled CLI steps to ne_ids/ume_ne_ids batch, compact oversized tool chat_message/tool_log after turns, and on getManagedNe miss guide agents to listManagedNe/UME paths instead of blind retries.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
oliver 2026-08-11 00:46:46 +08:00
parent ae70d4b89a
commit e2fc72607e
16 changed files with 373 additions and 61 deletions

View file

@ -2296,7 +2296,8 @@ class SqliteStore(ScheduledJobStoreMixin):
raw_cap = str(self.get_setting("AIA_TOOL_LOG_MAX_CHARS") or "").strip()
if not raw_cap:
raw_cap = str(os.getenv("AIA_TOOL_LOG_MAX_CHARS") or "").strip()
cap = 200_000
# Default 64k: field ops rarely need multi-100k tool dumps in tool_log.
cap = 64_000
if raw_cap.isdigit():
cap = max(20_000, min(int(raw_cap), 2_000_000))
args_capped = self._cap_json_for_log(args, max_chars=cap, keep_keys=())