朱子纯 / xlyNewAi

…i_op_queue staging cols + ai_skill registry

- proposeCreate tool -> ai_op_queue draft(payload) -> confirm executes addBusinessData
- ai_op_queue: add sPayload/sSourceRef/bAutoExecute/sResultBillId/sErrorMsg/tExecutedDate/tExpireAt (create/examine/auto-flow ready)
- ai_skill registry table + seed playbooks (Skills §6)
- QueryTool: self-repair retry (feed SQL error back to model, up to 3x)
- TracingChatModelListener: per-call LLM latency/token/error trace (Langfuse hook point)

- AuthzService: form-level allowlist ported from backend getsAuthsIdNew (sysjurisdiction sKey set); sysadmin=all; wired into Read/lookupRecord/proposeUpdate/proposeDelete (admin dev-login => all-access; enforces per-user once prod passes through user token)
- proposeDelete + ErpClient.deleteForm (handleType=del) + OpController branches op type; HITL-gated like update
- docs/security-findings.md: report of the 5 current-system vulns (backend form-perm off, read-API-can-write, NL2SQL no-tenant/over-privilege/partial-SQL-safety/cache-skips-validation) for the business
- Verified end-to-end: read after authz = 93; propose-delete card -> confirm -> row actually deleted; audit rows written.

…nce) vs deferred (authz/create-delete-审核/FormCollect/staging-executor/Langfuse/NL2SQL)

- FormResolverService: shared KG resolution (entity->master table excl. viw_*, field 中文->column, name field, labels)
- ErpReadTool.lookupRecord(entity, record): reliably resolves the master table + returns a single record's full labelled fields — fixes the 'specific field of a specific record' case (e.g. 必胜客的销售员 -> 马艺祖)
- AuditService + ai_audit_log: immutable audit of propose/confirm/cancel/query (who/when/action/target/result)
- QueryTool.queryData(question): read-only SQL escape hatch — coder-model NL2SQL grounded on 字段字典, jsqlparser single-SELECT guard, blocks OUTFILE/LOAD_FILE/information_schema/SLEEP, forced LIMIT, audited. SAFE by construction; NL2SQL table/join accuracy for complex questions is limited (architecture-flagged, deferred).

Verified: lookupRecord works; audit rows written; Query guards + LIMIT + audit work (NL2SQL grounding still mis-picks entity master on multi-table questions).

- ai_op_queue: staging table for AI write ops (draft|confirmed|executed|failed|cancelled)
- ProposeWriteTool.proposeUpdate(entity, record, field, newValue): self-resolves the entity master table (excludes viw_* report views), resolves field via 字段字典, locates the unique record + old value, stages a DRAFT to ai_op_queue — DOES NOT execute; returns a proposal
- ErpClient.updateForm: executes via ERP addUpdateDelBusinessData with the frontend-compatible payload {data:[{sTable,name:master,column:[{handleType:update,sId,field:value}]}]}
- OpController: deterministic (non-LLM) POST /op/{id}/confirm (executes + writes back status) / cancel / GET pending
- AgentChatController.onToolExecuted: on proposeUpdate, attach conversation + push write_proposal SSE
- chat.html: confirm/cancel card + result echo
- system prompt: proposeUpdate flow; never claim a write is done before confirm

Verified end-to-end: '把必胜客简称改成必胜客中国' -> proposal card -> confirm -> ERP update -> DB changed; cancel -> DB unchanged. Nothing executes without explicit user confirm.

- ErpReadTool: optional keyword -> LIKE filter on the form's resolved name field (viw_kg_field_dict, *Name); keyword doc clarified (only for locating a named record, empty for counts)
- ErpClient.readForm: accepts filterField/filterValue -> bFilter
- KgQueryTool.findForms: rank by bAiTool(curated) + table + flow-connectivity + name length so the top hit is usually the canonical form
- SystemPromptService: hard 'always Simplified Chinese, no other language' rule (kills qwen language drift); prefer top form; read directly instead of over-asking
- AgentConfig: qwen3 think(false)/returnThinking(false) -> fast + disciplined tool-calling, no leaked chain-of-thought
- application-saaslocal.yml: chat model -> qwen3:14b

Verified: no more foreign-language leaks; '多少客户'->92; keyword lookup finds 必胜客; proc-backed stock forms readable; greeting 2s, form lookup ~6s. Known limit: which form/columns get picked for a specific-field-of-specific-record query still varies (deferred KgSearch).

- RedisChatMemoryStore (ChatMemoryStore): persist per-conversation messages to Redis (chat:mem:{convId}, 30d TTL) -> survives restart; agent memory now Redis-backed via MessageWindowChatMemory.builder().chatMemoryStore(...)
- ConversationService: per-user conversation metadata (chat:convs:{userId} hash), title from first message, list/create/delete/history
- ConversationController: GET/POST/DELETE /api/agent/conversations + GET /{id}/messages
- AgentChatController: touch conversation on each turn
- chat.html: conversation sidebar (list/switch/new/delete), load history on switch, refresh on send

Verified: multi-turn memory recalls facts; after full restart, conversation list + history + memory all persist (agent still recalls prior-turn facts).

- ErpClient: thin HTTP client to ERP xlyEntry; dev-login (/checklogin admin) mints+caches a real session token, auto re-login on session expiry (code=-2); reads getBusinessDataByFormcustomId (read-only params only, never bUpdate)
- ErpReadTool.readFormData(formId,moduleId): reads a form's real rows, renders Chinese column labels from viw_kg_field_dict, first 10 rows + total count
- wired into the agent (tools = findForms + readFormData); system prompt now describes the findForms->readFormData flow (still read-only, writes still 'under development')
- application-saaslocal.yml: erp.baseurl -> local xlyEntry :8697 + dev-login creds

Verified: '我们有多少客户' -> agent finds the form, reads 92 real customers, renders a clean Chinese table (name/category/salesperson/tax).

- ReActAgent: AiServices streaming tool-loop (replaces 8-scene SceneSelector path)
- AgentConfig: single agent = streaming Ollama(qwen2.5:14b) + KgQueryTool + per-conversation memory + L1-domain system prompt
- SystemPromptService: injects L1 domain map (viw_kg_domain) into system prompt; degrades gracefully if KG views missing
- KgQueryTool.findForms: read-only form-catalog lookup over local viw_ai_useful_forms (global metadata, no tenant) — interim formId resolver
- AgentChatController: POST /api/agent/chat SSE stream ({type:token|reset|done|error}); reset drops pre-tool-call narration
- chat.html: consume the new SSE endpoint (streamed), per-page conversationId, drop TTS-borrow path
- application-saaslocal.yml: add to worktree (was master-only untracked -> profile silently hit remote DB)

Verified running (saaslocal, :8099): streaming chat, tool loop returns real forms, write requests correctly report 'under development'.

…tions, standalone chat page, always user-present, designated model cloud/local, shared-DB multi-brand); backups recorded; formId deferred; refresh open-items

…rminal + reconcile on reconnect; manual stays sync

… terminal (no chaining), validate-only

…oposeWrite ends turn on draft

…nistic /op/{id}/confirm endpoint (not a tool)

…lt); ERP real-time exec via /ai/execStaging + two link modes

…on dropped, form-level only via sAuthsId; Query security simplified

…Ai authorization layer; Read not permission-safe + param whitelist; invoke not backend-safe

…oseWrite covers mutating button-actions

… ERP procs, Query = ad-hoc-only

…; NL2SQL security pending investigation

Roll L2 flow up to domain->domain adjacency (11 domains) with anchor
forms, form/tool counts, and the matching AI-agent scene. This is the
coarse L1 tier meant to live in the agent system prompt for routing;
L2/L3 stay as on-demand tools. Domains align to ai_agent's 8 business
智能体 (+ 基础资料/设备/其他 -> ERP代理人).

Materialize each form's L2 neighbors (upstream/downstream documents) and
L3 neighbors (referenced entity tables) so the retriever can expand a
vector-recalled form-card into a subgraph context via a single JOIN.
702 forms have downstream, 476 upstream, 1467 reference entity tables.

Map 业务中文名 -> real column -> table (38342 mappings, 6075 terms, 539
tables), ranked by form-usage for same-name disambiguation, with FK target
(sFkTable/sFkKey) attached from viw_kg_edge_ref so NL2SQL knows the join.
This is the field-dictionary half of the GraphRAG package.

Assemble one structured, embeddable text card per form (1748) merging
node metadata, upstream/downstream document names, and the field 中文名
list. export_form_cards.sh emits JSONL for vector-store ingestion
(group_concat_max_len raised to avoid truncating 269-field forms).
Generated corpus is gitignored — regenerate deterministically via script.

Parse gdsconfigformslave.sRelation (comma-separated field&table&pk&display
hops) into FK edges: src_table.field -> tgt_table.pk, with the set of
display columns each FK surfaces aggregated per edge. 1597 distinct FK
edges / 368 source tables / 109 target tables (mostly ele*/sis* master
data). Provides the join dictionary for NL2SQL grounding.

One row per useful form enriched with business domain (L1, derived from
normalized data-source prefix + AI-scene override), data source/exec type,
and upstream/downstream flow counts from viw_kg_edge_flow. 857 forms
participate in document flow; 63 back an AI tool; 92% domain-classified.

Materialize source-form -->generate--> target-form flow edges from the
low-code config. Resolves BtnCopyTo.<Action>.sActiveId to the target
gdsmodule exactly as Sp_Ai_AddCommonAfterNew does (sActiveId is the real
target; the .ActXxx suffix is only a label).

411 distinct edges / 405 (src,tgt) pairs / 51 self-loops; 404 endpoints
hit viw_ai_useful_forms. Captures full order-to-cash and procure-to-pay
chains plus cross-domain (order->workorder, quote->process-card).