[NOTICKET] fix(planner): reject analyze_* fed from metadata/documents tools

[NOTICKET] fix(agents): analysis answer reply-language + number formatting

[NOTICKET] fix(intent): route bagaimana by object + honest out_of_scope eval scoring

[NOTICKET] fix(help): reply language default + explicit-request exception (mirror chat)

[NOTICKET] fix(agents): lock analysis answer language to the user's turn

feat(guardrails): add input guard, out_of_scope intent, and refusal handling

fix(planner): correct top-N guidance — in-query ranking IS supported

fix(planner): harden plan validation to reduce retry thrash on structured questions

/fix analysis + report_inputs and storage update (#9)

/fix check and help tool (#8)

feat/Analysis State & Report Rework (#4)

feat/Knowledge & Data Tools (#3)

feat/Planner Agent (#2)

[KM-582][DED][AI] Fix Retrieval in Agentic Service

[NOTICKET] fix: add SKIP_INIT_DB flag and remove pymongo dependency

feat/Catalog Retrieval System (#1)

[KM-496] [DED][AI] Fix Response data structure for field sources (db flow)

[NOTICKET][DB] add endpoints for dbtypes (#6)

[KM-436][KM-437] add and modify for database and document pipeline (#3)

[KM-467] [DED][AI] Orchestration Agent - Init