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/pages/dataset/dataset-setting/form-schema.ts

@@ -42,11 +42,14 @@ export const formSchema = z
           .object({
             use_raptor: z.boolean().optional(),
             prompt: z.string().optional(),
-            max_token: z.number().optional(),
-            threshold: z.number().optional(),
-            max_cluster: z.number().optional(),
-            random_seed: z.number().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(),
+            ext: z.record(z.string(), z.any()).optional(),
           })
           .refine(
             (data) => {

web/src/pages/dataset/dataset-setting/index.tsx

@@ -95,6 +95,8 @@ export default function DatasetSettings() {
           max_cluster: 64,
           random_seed: 0,
           scope: 'file',
+          clustering_method: 'gmm',
+          tree_builder: 'raptor',
           prompt: t('knowledgeConfiguration.promptText'),
         },
         graphrag: {

web/src/pages/dataset/dataset/use-change-document-parser.ts

@@ -19,7 +19,7 @@ export const useChangeDocumentParser = () => {
       if (record?.id && record?.dataset_id) {
         const ret = await setDocumentParser({
           parserId: parserConfigInfo.parser_id,
-          pipelineId: parserConfigInfo.pipeline_id,
+          pipelineId: parserConfigInfo.pipeline_id || '',
           documentId: record?.id,
           datasetId: record?.dataset_id,
           parserConfig: parserConfigInfo.parser_config,