oliver e2fc72607e 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>		2026-08-11 00:46:46 +08:00
..
db	feat(persistence): PostgreSQL assistant store, chat persist fixes, gateway scripts	2026-05-14 09:33:50 +08:00
ddl	feat(persistence): PostgreSQL assistant store, chat persist fixes, gateway scripts	2026-05-14 09:33:50 +08:00
sa_repos	fix(chat): allow administrator to delete channel-only sessions	2026-07-21 16:55:51 +08:00
__init__.py	refactor: root-package imports (svc/runtime/interfaces) and fix PYTHONPATH	2026-05-13 14:51:17 +08:00
assistant_store.py	fix: harden assistant SQLite/PostgreSQL dual-backend (singleton, timeouts, warnings)	2026-05-14 10:24:23 +08:00
assistant_store_protocol.py	fix(chat): allow administrator to delete channel-only sessions	2026-07-21 16:55:51 +08:00
pg_adapter.py	fix: harden assistant SQLite/PostgreSQL dual-backend (singleton, timeouts, warnings)	2026-05-14 10:24:23 +08:00
pg_compat.py	fix(chat,channels): admin session delete, weixin inbound, PG and docs	2026-06-03 01:36:45 +08:00
scheduled_job_store.py	Skip overlapping scheduled runs and surface playbook status in job lists.	2026-08-11 00:07:42 +08:00
sqlite_retention.py	Add dry-run sqlite retention prune for tool/trace bloat.	2026-08-11 00:22:26 +08:00
sqlite_store.py	Prefer batch CLI in playbooks, cap tool persistence, and steer getManagedNe failures.	2026-08-11 00:46:46 +08:00