feat(raptor): add Psi tree builder with original-space ranking and safe migration (#14679)

### What problem does this PR solve?

Closes #14674.

This PR improves RAPTOR configuration and tree construction while
preserving the existing RAPTOR behavior as the default.

RAPTOR currently builds summary layers with the original UMAP + GMM
clustering path. This PR keeps that default path, and adds:

- A hidden backend tree-builder option:
  - `tree_builder="raptor"`: default, existing RAPTOR behavior.
- `tree_builder="psi"`: rank-aware Psi-style tree builder using original
embedding-space cosine ranking.
- A user-facing clustering method option for the default RAPTOR builder:
  - `clustering_method="gmm"`: existing default.
- `clustering_method="ahc"`: agglomerative hierarchical clustering path.
- A RAPTOR UI setting for `Clustering method` and `Max cluster`.

### What changed

#### Backend

- Added `tree_builder` support for RAPTOR/Psi.
- Added `clustering_method` support for GMM/AHC.
- Kept existing RAPTOR + GMM as the default.
- Added Psi tree building from original-space cosine similarity.
- Added bucketed Psi building controls for large inputs:
  - `raptor.ext.psi_exact_max_leaves`
  - `raptor.ext.psi_bucket_size`
- Added method-aware RAPTOR summary metadata using existing
`extra.raptor_method`.
- Avoided adding a dedicated DB schema field for experimental method
tracking.
- Added cleanup/migration logic to avoid mixing stale RAPTOR summary
trees.
- Added defensive checks for Psi tree construction and summary failures.

#### Frontend/UI

- Added `Clustering method` in RAPTOR settings with `GMM` and `AHC`.
- Added/kept `Max cluster` in RAPTOR settings.
- Enlarged max cluster UI limit to `1024`, matching backend validation.
- Kept AHC editable even when a RAPTOR task has already finished.
- Fixed the UI save payload so `clustering_method` and `tree_builder`
are serialized through `parser_config.raptor.ext`, avoiding backend
validation errors for extra top-level RAPTOR fields.

Example saved RAPTOR config:

```json
{
  "raptor": {
    "max_cluster": 317,
    "ext": {
      "clustering_method": "ahc",
      "tree_builder": "raptor"
    }
  }
}

Co-authored-by: CaptainTimon <CaptainTimon@users.noreply.github.com>

web/src/components/chunk-method-dialog/index.tsx

@@ -17,7 +17,7 @@ import { DocumentParserType, ParseType } from '@/constants/knowledge';
 import { useFetchKnowledgeBaseConfiguration } from '@/hooks/use-knowledge-request';
 import { IModalProps } from '@/interfaces/common';
 import { IParserConfig } from '@/interfaces/database/document';
-import { IChangeParserConfigRequestBody } from '@/interfaces/request/document';
+import { IChangeParserRequestBody } from '@/interfaces/request/document';
 import { MetadataType } from '@/pages/dataset/components/metedata/constant';
 import {
   AutoMetadata,
@@ -28,7 +28,6 @@ import {
 } from '@/pages/dataset/dataset-setting/configuration/common-item';
 import { zodResolver } from '@hookform/resolvers/zod';
 import omit from 'lodash/omit';
-import {} from 'module';
 import { useEffect, useMemo } from 'react';
 import { useForm, useWatch } from 'react-hook-form';
 import { useTranslation } from 'react-i18next';
@@ -56,10 +55,7 @@ import {
 
 const FormId = 'ChunkMethodDialogForm';
 
-interface IProps extends IModalProps<{
-  parserId: string;
-  parserConfig: IChangeParserConfigRequestBody;
-}> {
+interface IProps extends IModalProps<IChangeParserRequestBody> {
   loading: boolean;
   parserId: string;
   pipelineId?: string;
@@ -126,16 +122,19 @@ export function ChunkMethodDialog({
         mineru_formula_enable: z.boolean().optional(),
         mineru_table_enable: z.boolean().optional(),
         mineru_lang: z.string().optional(),
-        // raptor: z
-        //   .object({
-        //     use_raptor: z.boolean().optional(),
-        //     prompt: z.string().optional().optional(),
-        //     max_token: z.coerce.number().optional(),
-        //     threshold: z.coerce.number().optional(),
-        //     max_cluster: z.coerce.number().optional(),
-        //     random_seed: z.coerce.number().optional(),
-        //   })
-        //   .optional(),
+        raptor: z
+          .object({
+            use_raptor: z.boolean().optional(),
+            prompt: z.string().optional(),
+            max_token: z.coerce.number().optional(),
+            threshold: z.coerce.number().optional(),
+            max_cluster: z.coerce.number().optional(),
+            random_seed: z.coerce.number().optional(),
+            scope: z.string().optional(),
+            clustering_method: z.enum(['gmm', 'ahc']).optional(),
+            tree_builder: z.enum(['raptor', 'psi']).optional(),
+          })
+          .optional(),
         // graphrag: z.object({
         //   use_graphrag: z.boolean().optional(),
         // }),

web/src/components/chunk-method-dialog/use-default-parser-values.ts

@@ -23,14 +23,17 @@ export function useDefaultParserValues() {
       mineru_formula_enable: true,
       mineru_table_enable: true,
       mineru_lang: 'English',
-      // raptor: {
-      //   use_raptor: false,
-      //   prompt: t('knowledgeConfiguration.promptText'),
-      //   max_token: 256,
-      //   threshold: 0.1,
-      //   max_cluster: 64,
-      //   random_seed: 0,
-      // },
+      raptor: {
+        use_raptor: false,
+        prompt: t('knowledgeConfiguration.promptText'),
+        max_token: 256,
+        threshold: 0.1,
+        max_cluster: 64,
+        random_seed: 0,
+        scope: 'file',
+        clustering_method: 'gmm',
+        tree_builder: 'raptor',
+      },
       // graphrag: {
       //   use_graphrag: false,
       // },