[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): soften injected reply-language line to a default, not ONLY

[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

[NOTICKET] fix(tools): coerce numeric-string columns before analyze_* compute

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

[NOTICKET] fix(tools): log swallowed analytics tool errors in AnalyticsToolInvoker

/fix report: group findings by analysis, dedup, code-span-safe MDX escaping

[NOTICKET] fix(planner): repair near-miss catalog ids in QueryIR before validation

/fix report: remove record_id hash citations, EDA (for future tool) change to data source, transform to mdx-safe

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

/fix check and help tool (#8)

/fix v2 chat stream api update to analyses_messages (#7)

/fix message_id for chat/stream Endpoint (#6)

feat/ Endpoint Restructure (#5)

feat/Analysis State & Report Rework (#4)

feat/Knowledge & Data Tools (#3)

/fix redis connection code for general redis connection

feat/Planner Agent (#2)

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

fix build error in importing packages langchain_postgres

Fix schema table langchain_pg_embedding

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

feat/Catalog Retrieval System (#1)

[KM-438][KM-439] Improve Retrieval and Querying feature (#15)

Make a query for tabular (XLSX and CSV) (#14)

Merge dev_new to main (improve retriever and add querying) (#13)

[NOTICKET] fixed single source into multiple sources (#12)

[NOTICKET] add updated_at metadata & prevent duplicate while adding new embedding (#10)

[NOTICKET] add total token logging (#9)

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

[NOTICKET] [document]: add doctypes endpoint (#7)

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

[KM-493] [DED][AI] Fix source extraction in chat

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

[NOTICKET] Init db_client endpoint

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