Merge remote-tracking branch 'origin/main' into canary

CHANGELOG.md

@@ -2,6 +2,33 @@
 
 # Changelog
 
+### [Version 2.1.43](https://github.com/lobehub/lobe-chat/compare/v2.1.42...v2.1.43)
+
+<sup>Released on **2026-03-16**</sup>
+
+#### 👷 Build System
+
+- **misc**: add BM25 indexes with ICU tokenizer for search optimization.
+- **misc**: add `agent_documents` table.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Build System
+
+- **misc**: add BM25 indexes with ICU tokenizer for search optimization, closes [#13032](https://github.com/lobehub/lobe-chat/issues/13032) ([70a74f4](https://github.com/lobehub/lobe-chat/commit/70a74f4))
+- **misc**: add `agent_documents` table, closes [#12944](https://github.com/lobehub/lobe-chat/issues/12944) ([93ee1e3](https://github.com/lobehub/lobe-chat/commit/93ee1e3))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 2.1.42](https://github.com/lobehub/lobe-chat/compare/v2.1.41...v2.1.42)
 
 <sup>Released on **2026-03-14**</sup>

changelog/v2.json

@@ -1,4 +1,14 @@
 [
+  {
+    "children": {
+      "improvements": [
+        "add BM25 indexes with ICU tokenizer for search optimization.",
+        "add agent_documents table."
+      ]
+    },
+    "date": "2026-03-16",
+    "version": "2.1.43"
+  },
   {
     "children": {},
     "date": "2026-03-14",

docs/development/database-schema.dbml

@@ -79,6 +79,7 @@ table agent_bot_providers {
   platform varchar(50) [not null]
   application_id varchar(255) [not null]
   credentials text
+  settings jsonb [default: `{}`]
   enabled boolean [not null, default: true]
   accessed_at "timestamp with time zone" [not null, default: `now()`]
   created_at "timestamp with time zone" [not null, default: `now()`]
@@ -123,6 +124,46 @@ table agent_cron_jobs {
   }
 }
 
+table agent_documents {
+  id uuid [pk, not null, default: `gen_random_uuid()`]
+  user_id text [not null]
+  agent_id text [not null]
+  document_id varchar(255) [not null]
+  template_id varchar(100)
+  access_self integer [not null, default: 31]
+  access_shared integer [not null, default: 0]
+  access_public integer [not null, default: 0]
+  policy_load varchar(30) [not null, default: 'always']
+  policy jsonb
+  policy_load_position varchar(50) [not null, default: 'before-first-user']
+  policy_load_format varchar(20) [not null, default: 'raw']
+  policy_load_rule varchar(50) [not null, default: 'always']
+  deleted_at "timestamp with time zone"
+  deleted_by_user_id text
+  deleted_by_agent_id text
+  delete_reason text
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    user_id [name: 'agent_documents_user_id_idx']
+    agent_id [name: 'agent_documents_agent_id_idx']
+    access_self [name: 'agent_documents_access_self_idx']
+    access_shared [name: 'agent_documents_access_shared_idx']
+    access_public [name: 'agent_documents_access_public_idx']
+    policy_load [name: 'agent_documents_policy_load_idx']
+    template_id [name: 'agent_documents_template_id_idx']
+    policy_load_position [name: 'agent_documents_policy_load_position_idx']
+    policy_load_format [name: 'agent_documents_policy_load_format_idx']
+    policy_load_rule [name: 'agent_documents_policy_load_rule_idx']
+    (agent_id, policy_load_position) [name: 'agent_documents_agent_load_position_idx']
+    deleted_at [name: 'agent_documents_deleted_at_idx']
+    (agent_id, deleted_at, policy_load) [name: 'agent_documents_agent_autoload_deleted_idx']
+    document_id [name: 'agent_documents_document_id_idx']
+    (agent_id, document_id, user_id) [name: 'agent_documents_agent_document_user_unique', unique]
+  }
+}
+
 table agent_eval_benchmarks {
   id text [pk, not null]
   identifier text [not null]

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/lobehub",
-  "version": "2.1.42",
+  "version": "2.1.43",
   "description": "LobeHub - an open-source,comprehensive AI Agent framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.",
   "keywords": [
     "framework",

packages/database/migrations/0094_agent_bot_providers_add_settings.sql

@@ -0,0 +1 @@
+ALTER TABLE "agent_bot_providers" ADD COLUMN IF NOT EXISTS "settings" jsonb DEFAULT '{}'::jsonb;

packages/database/migrations/meta/_journal.json

@@ -658,6 +658,13 @@
       "when": 1773653550268,
       "tag": "0093_add_bm25_indexes_with_icu",
       "breakpoints": true
+    },
+    {
+      "idx": 94,
+      "version": "7",
+      "when": 1773764776073,
+      "tag": "0094_agent_bot_providers_add_settings",
+      "breakpoints": true
     }
   ],
   "version": "6"

packages/database/src/schemas/agentBotProvider.ts

@@ -1,4 +1,13 @@
-import { boolean, index, pgTable, text, uniqueIndex, uuid, varchar } from 'drizzle-orm/pg-core';
+import {
+  boolean,
+  index,
+  jsonb,
+  pgTable,
+  text,
+  uniqueIndex,
+  uuid,
+  varchar,
+} from 'drizzle-orm/pg-core';
 import { createInsertSchema } from 'drizzle-zod';
 
 import { timestamps } from './_helpers';
@@ -33,12 +42,15 @@ export const agentBotProviders = pgTable(
     /** Encrypted credentials string (decrypted to JSON with botToken, publicKey, etc.) */
     credentials: text('credentials'),
 
+    /** User-configurable settings (dm policy, charLimit, debounce, etc.) */
+    settings: jsonb('settings').$type<Record<string, unknown>>().default({}),
+
     enabled: boolean('enabled').default(true).notNull(),
 
     ...timestamps,
   },
   (t) => [
-    // Fast webhook lookup: platform + applicationId → agent
+    // Fast lookup: platform + applicationId → agent
     uniqueIndex('agent_bot_providers_platform_app_id_unique').on(t.platform, t.applicationId),
     index('agent_bot_providers_platform_idx').on(t.platform),
     index('agent_bot_providers_agent_id_idx').on(t.agentId),