feat: add APIEmbedder for remote embedding with multi-endpoint support

- Introduced APIEmbedder class to handle embeddings via a remote HTTP API. - Implemented token packing to optimize batch sizes based on token limits. - Added support for multiple API endpoints with round-robin dispatching. - Included retry logic for API calls with exponential backoff on failures. - Enhanced indexing pipeline with file exclusion checks and smart chunking strategies. - Updated tests to cover new APIEmbedder functionality and ensure robustness.
2026-03-19 18:58:47 +08:00 · 2026-03-17 17:17:24 +08:00
parent 34749d2fad
commit f37189dc64
18 changed files with 1633 additions and 476 deletions
--- a/ccw/frontend/src/components/codexlens/OverviewTab.tsx
+++ b/ccw/frontend/src/components/codexlens/OverviewTab.tsx
@@ -16,7 +16,6 @@ import { cn } from '@/lib/utils';
 import type { CodexLensVenvStatus, CodexLensConfig } from '@/lib/api';
 import { IndexOperations } from './IndexOperations';
 import { FileWatcherCard } from './FileWatcherCard';
-import { LspServerCard } from './LspServerCard';

 interface OverviewTabProps {
  installed: boolean;
@@ -145,9 +144,8 @@ export function OverviewTab({ installed, status, config, isLoading, onRefresh }:
      </div>

      {/* Service Management */}
-      <div className="grid grid-cols-1 md:grid-cols-2 gap-4">
+      <div className="grid grid-cols-1 gap-4">
        <FileWatcherCard disabled={!isReady} />
-        <LspServerCard disabled={!isReady} />
      </div>

      {/* Index Operations */}
--- a/ccw/frontend/src/components/codexlens/SchemaFormRenderer.tsx
+++ b/ccw/frontend/src/components/codexlens/SchemaFormRenderer.tsx
@@ -11,7 +11,6 @@ import {
  ArrowUpDown,
  Cpu,
  GitBranch,
-  Scissors,
  type LucideIcon,
 } from 'lucide-react';
 import { Label } from '@/components/ui/Label';
@@ -41,7 +40,6 @@ const iconMap: Record<string, LucideIcon> = {
  'arrow-up-down': ArrowUpDown,
  cpu: Cpu,
  'git-branch': GitBranch,
-  scissors: Scissors,
 };

 interface SchemaFormRendererProps {
@@ -214,12 +212,12 @@ function FieldRenderer({

    case 'model-select': {
      // Determine backend type from related backend env var
-      const isEmbedding = field.key.includes('EMBEDDING');
+      const isEmbedding = field.key.includes('EMBED');
      const backendKey = isEmbedding
        ? 'CODEXLENS_EMBEDDING_BACKEND'
        : 'CODEXLENS_RERANKER_BACKEND';
      const backendValue = allValues[backendKey];
-      const backendType = (backendValue === 'api' || backendValue === 'litellm') ? 'api' : 'local';
+      const backendType = backendValue === 'api' ? 'api' : 'local';

      return (
        <div className="flex items-center gap-2">
@@ -241,6 +239,27 @@ function FieldRenderer({
      );
    }

+    case 'password':
+      return (
+        <div className="flex items-center gap-2">
+          <Label
+            className="text-xs text-muted-foreground w-28 flex-shrink-0"
+            title={field.key}
+          >
+            {label}
+          </Label>
+          <Input
+            type="password"
+            className="flex-1 h-8 text-xs"
+            value={value}
+            onChange={(e) => onChange(e.target.value)}
+            placeholder={field.placeholder}
+            disabled={disabled}
+            autoComplete="off"
+          />
+        </div>
+      );
+
    case 'text':
    default:
      return (
--- a/ccw/frontend/src/components/codexlens/envVarSchema.ts
+++ b/ccw/frontend/src/components/codexlens/envVarSchema.ts
@@ -1,8 +1,8 @@
 // ========================================
-// CodexLens Environment Variable Schema
+// CodexLens v2 Environment Variable Schema
 // ========================================
-// TypeScript port of ENV_VAR_GROUPS from codexlens-manager.js
-// Defines structured groups for CodexLens configuration
+// Defines structured groups for codexlens-search v2 configuration.
+// Env var names match what the Python bridge CLI reads.

 import type { EnvVarGroupsSchema } from '@/types/codexlens';

@@ -20,20 +20,38 @@ export const envVarGroupsSchema: EnvVarGroupsSchema = {
        default: 'local',
        settingsPath: 'embedding.backend',
      },
-      CODEXLENS_EMBEDDING_MODEL: {
-        key: 'CODEXLENS_EMBEDDING_MODEL',
+      CODEXLENS_EMBED_API_URL: {
+        key: 'CODEXLENS_EMBED_API_URL',
+        labelKey: 'codexlens.envField.apiUrl',
+        type: 'text',
+        placeholder: 'https://api.siliconflow.cn/v1',
+        default: '',
+        settingsPath: 'embedding.api_url',
+        showWhen: (env) => env['CODEXLENS_EMBEDDING_BACKEND'] === 'api',
+      },
+      CODEXLENS_EMBED_API_KEY: {
+        key: 'CODEXLENS_EMBED_API_KEY',
+        labelKey: 'codexlens.envField.apiKey',
+        type: 'password',
+        placeholder: 'sk-...',
+        default: '',
+        settingsPath: 'embedding.api_key',
+        showWhen: (env) => env['CODEXLENS_EMBEDDING_BACKEND'] === 'api',
+      },
+      CODEXLENS_EMBED_API_MODEL: {
+        key: 'CODEXLENS_EMBED_API_MODEL',
        labelKey: 'codexlens.envField.model',
        type: 'model-select',
        placeholder: 'Select or enter model...',
-        default: 'fast',
-        settingsPath: 'embedding.model',
-        localModels: [
-          {
-            group: 'FastEmbed Profiles',
-            items: ['fast', 'code', 'base', 'minilm', 'multilingual', 'balanced'],
-          },
-        ],
+        default: '',
+        settingsPath: 'embedding.api_model',
+        showWhen: (env) => env['CODEXLENS_EMBEDDING_BACKEND'] === 'api',
+        localModels: [],
        apiModels: [
+          {
+            group: 'SiliconFlow',
+            items: ['BAAI/bge-m3', 'BAAI/bge-large-zh-v1.5', 'BAAI/bge-large-en-v1.5'],
+          },
          {
            group: 'OpenAI',
            items: ['text-embedding-3-small', 'text-embedding-3-large', 'text-embedding-ada-002'],
@@ -44,66 +62,90 @@ export const envVarGroupsSchema: EnvVarGroupsSchema = {
          },
          {
            group: 'Voyage',
-            items: ['voyage-3', 'voyage-3-lite', 'voyage-code-3', 'voyage-multilingual-2'],
-          },
-          {
-            group: 'SiliconFlow',
-            items: ['BAAI/bge-m3', 'BAAI/bge-large-zh-v1.5', 'BAAI/bge-large-en-v1.5'],
+            items: ['voyage-3', 'voyage-3-lite', 'voyage-code-3'],
          },
          {
            group: 'Jina',
-            items: ['jina-embeddings-v3', 'jina-embeddings-v2-base-en', 'jina-embeddings-v2-base-zh'],
+            items: ['jina-embeddings-v3', 'jina-embeddings-v2-base-en'],
          },
        ],
      },
-      CODEXLENS_AUTO_EMBED_MISSING: {
-        key: 'CODEXLENS_AUTO_EMBED_MISSING',
-        labelKey: 'codexlens.envField.autoEmbedMissing',
-        type: 'checkbox',
-        default: 'true',
-        settingsPath: 'embedding.auto_embed_missing',
+      CODEXLENS_EMBED_API_ENDPOINTS: {
+        key: 'CODEXLENS_EMBED_API_ENDPOINTS',
+        labelKey: 'codexlens.envField.multiEndpoints',
+        type: 'text',
+        placeholder: 'url1|key1|model1,url2|key2|model2',
+        default: '',
+        settingsPath: 'embedding.api_endpoints',
+        showWhen: (env) => env['CODEXLENS_EMBEDDING_BACKEND'] === 'api',
+      },
+      CODEXLENS_EMBED_DIM: {
+        key: 'CODEXLENS_EMBED_DIM',
+        labelKey: 'codexlens.envField.embedDim',
+        type: 'number',
+        placeholder: '384',
+        default: '384',
+        settingsPath: 'embedding.dim',
+        min: 64,
+        max: 4096,
+        showWhen: (env) => env['CODEXLENS_EMBEDDING_BACKEND'] === 'api',
+      },
+      CODEXLENS_EMBED_API_CONCURRENCY: {
+        key: 'CODEXLENS_EMBED_API_CONCURRENCY',
+        labelKey: 'codexlens.envField.apiConcurrency',
+        type: 'number',
+        placeholder: '4',
+        default: '4',
+        settingsPath: 'embedding.api_concurrency',
+        min: 1,
+        max: 32,
+        showWhen: (env) => env['CODEXLENS_EMBEDDING_BACKEND'] === 'api',
+      },
+      CODEXLENS_EMBED_API_MAX_TOKENS: {
+        key: 'CODEXLENS_EMBED_API_MAX_TOKENS',
+        labelKey: 'codexlens.envField.maxTokensPerBatch',
+        type: 'number',
+        placeholder: '8192',
+        default: '8192',
+        settingsPath: 'embedding.api_max_tokens_per_batch',
+        min: 512,
+        max: 65536,
+        showWhen: (env) => env['CODEXLENS_EMBEDDING_BACKEND'] === 'api',
+      },
+      CODEXLENS_EMBEDDING_MODEL: {
+        key: 'CODEXLENS_EMBEDDING_MODEL',
+        labelKey: 'codexlens.envField.localModel',
+        type: 'model-select',
+        placeholder: 'Select local model...',
+        default: 'BAAI/bge-small-en-v1.5',
+        settingsPath: 'embedding.model',
+        showWhen: (env) => env['CODEXLENS_EMBEDDING_BACKEND'] !== 'api',
+        localModels: [
+          {
+            group: 'FastEmbed Profiles',
+            items: ['small', 'base', 'large', 'code'],
+          },
+        ],
+        apiModels: [],
      },
      CODEXLENS_USE_GPU: {
        key: 'CODEXLENS_USE_GPU',
        labelKey: 'codexlens.envField.useGpu',
        type: 'select',
-        options: ['true', 'false'],
-        default: 'true',
-        settingsPath: 'embedding.use_gpu',
-        showWhen: (env) => env['CODEXLENS_EMBEDDING_BACKEND'] === 'local',
+        options: ['auto', 'cuda', 'cpu'],
+        default: 'auto',
+        settingsPath: 'embedding.device',
+        showWhen: (env) => env['CODEXLENS_EMBEDDING_BACKEND'] !== 'api',
      },
-      CODEXLENS_EMBEDDING_POOL_ENABLED: {
-        key: 'CODEXLENS_EMBEDDING_POOL_ENABLED',
-        labelKey: 'codexlens.envField.highAvailability',
-        type: 'select',
-        options: ['true', 'false'],
-        default: 'false',
-        settingsPath: 'embedding.pool_enabled',
-        showWhen: (env) => env['CODEXLENS_EMBEDDING_BACKEND'] === 'api',
-      },
-      CODEXLENS_EMBEDDING_STRATEGY: {
-        key: 'CODEXLENS_EMBEDDING_STRATEGY',
-        labelKey: 'codexlens.envField.loadBalanceStrategy',
-        type: 'select',
-        options: ['round_robin', 'latency_aware', 'weighted_random'],
-        default: 'latency_aware',
-        settingsPath: 'embedding.strategy',
-        showWhen: (env) =>
-          env['CODEXLENS_EMBEDDING_BACKEND'] === 'api' &&
-          env['CODEXLENS_EMBEDDING_POOL_ENABLED'] === 'true',
-      },
-      CODEXLENS_EMBEDDING_COOLDOWN: {
-        key: 'CODEXLENS_EMBEDDING_COOLDOWN',
-        labelKey: 'codexlens.envField.rateLimitCooldown',
+      CODEXLENS_EMBED_BATCH_SIZE: {
+        key: 'CODEXLENS_EMBED_BATCH_SIZE',
+        labelKey: 'codexlens.envField.batchSize',
        type: 'number',
-        placeholder: '60',
-        default: '60',
-        settingsPath: 'embedding.cooldown',
-        min: 0,
-        max: 300,
-        showWhen: (env) =>
-          env['CODEXLENS_EMBEDDING_BACKEND'] === 'api' &&
-          env['CODEXLENS_EMBEDDING_POOL_ENABLED'] === 'true',
+        placeholder: '64',
+        default: '64',
+        settingsPath: 'embedding.batch_size',
+        min: 1,
+        max: 512,
      },
    },
  },
@@ -112,29 +154,64 @@ export const envVarGroupsSchema: EnvVarGroupsSchema = {
    labelKey: 'codexlens.envGroup.reranker',
    icon: 'arrow-up-down',
    vars: {
-      CODEXLENS_RERANKER_ENABLED: {
-        key: 'CODEXLENS_RERANKER_ENABLED',
-        labelKey: 'codexlens.envField.enabled',
-        type: 'select',
-        options: ['true', 'false'],
-        default: 'true',
-        settingsPath: 'reranker.enabled',
-      },
      CODEXLENS_RERANKER_BACKEND: {
        key: 'CODEXLENS_RERANKER_BACKEND',
        labelKey: 'codexlens.envField.backend',
        type: 'select',
-        options: ['onnx', 'api', 'litellm', 'legacy'],
-        default: 'onnx',
+        options: ['local', 'api'],
+        default: 'local',
        settingsPath: 'reranker.backend',
      },
-      CODEXLENS_RERANKER_MODEL: {
-        key: 'CODEXLENS_RERANKER_MODEL',
+      CODEXLENS_RERANKER_API_URL: {
+        key: 'CODEXLENS_RERANKER_API_URL',
+        labelKey: 'codexlens.envField.apiUrl',
+        type: 'text',
+        placeholder: 'https://api.siliconflow.cn/v1',
+        default: '',
+        settingsPath: 'reranker.api_url',
+        showWhen: (env) => env['CODEXLENS_RERANKER_BACKEND'] === 'api',
+      },
+      CODEXLENS_RERANKER_API_KEY: {
+        key: 'CODEXLENS_RERANKER_API_KEY',
+        labelKey: 'codexlens.envField.apiKey',
+        type: 'password',
+        placeholder: 'sk-...',
+        default: '',
+        settingsPath: 'reranker.api_key',
+        showWhen: (env) => env['CODEXLENS_RERANKER_BACKEND'] === 'api',
+      },
+      CODEXLENS_RERANKER_API_MODEL: {
+        key: 'CODEXLENS_RERANKER_API_MODEL',
        labelKey: 'codexlens.envField.model',
        type: 'model-select',
        placeholder: 'Select or enter model...',
+        default: '',
+        settingsPath: 'reranker.api_model',
+        showWhen: (env) => env['CODEXLENS_RERANKER_BACKEND'] === 'api',
+        localModels: [],
+        apiModels: [
+          {
+            group: 'SiliconFlow',
+            items: ['BAAI/bge-reranker-v2-m3', 'BAAI/bge-reranker-large', 'BAAI/bge-reranker-base'],
+          },
+          {
+            group: 'Cohere',
+            items: ['rerank-english-v3.0', 'rerank-multilingual-v3.0'],
+          },
+          {
+            group: 'Jina',
+            items: ['jina-reranker-v2-base-multilingual'],
+          },
+        ],
+      },
+      CODEXLENS_RERANKER_MODEL: {
+        key: 'CODEXLENS_RERANKER_MODEL',
+        labelKey: 'codexlens.envField.localModel',
+        type: 'model-select',
+        placeholder: 'Select local model...',
        default: 'Xenova/ms-marco-MiniLM-L-6-v2',
        settingsPath: 'reranker.model',
+        showWhen: (env) => env['CODEXLENS_RERANKER_BACKEND'] !== 'api',
        localModels: [
          {
            group: 'FastEmbed/ONNX',
@@ -145,283 +222,128 @@ export const envVarGroupsSchema: EnvVarGroupsSchema = {
            ],
          },
        ],
-        apiModels: [
-          {
-            group: 'Cohere',
-            items: ['rerank-english-v3.0', 'rerank-multilingual-v3.0', 'rerank-english-v2.0'],
-          },
-          {
-            group: 'Voyage',
-            items: ['rerank-2', 'rerank-2-lite', 'rerank-1'],
-          },
-          {
-            group: 'SiliconFlow',
-            items: ['BAAI/bge-reranker-v2-m3', 'BAAI/bge-reranker-large', 'BAAI/bge-reranker-base'],
-          },
-          {
-            group: 'Jina',
-            items: ['jina-reranker-v2-base-multilingual', 'jina-reranker-v1-base-en'],
-          },
-        ],
+        apiModels: [],
      },
      CODEXLENS_RERANKER_TOP_K: {
        key: 'CODEXLENS_RERANKER_TOP_K',
        labelKey: 'codexlens.envField.topKResults',
        type: 'number',
-        placeholder: '50',
-        default: '50',
+        placeholder: '20',
+        default: '20',
        settingsPath: 'reranker.top_k',
        min: 5,
        max: 200,
      },
-      CODEXLENS_RERANKER_POOL_ENABLED: {
-        key: 'CODEXLENS_RERANKER_POOL_ENABLED',
-        labelKey: 'codexlens.envField.highAvailability',
-        type: 'select',
-        options: ['true', 'false'],
-        default: 'false',
-        settingsPath: 'reranker.pool_enabled',
-        showWhen: (env) => env['CODEXLENS_RERANKER_BACKEND'] === 'api' || env['CODEXLENS_RERANKER_BACKEND'] === 'litellm',
+      CODEXLENS_RERANKER_BATCH_SIZE: {
+        key: 'CODEXLENS_RERANKER_BATCH_SIZE',
+        labelKey: 'codexlens.envField.batchSize',
+        type: 'number',
+        placeholder: '32',
+        default: '32',
+        settingsPath: 'reranker.batch_size',
+        min: 1,
+        max: 128,
      },
-      CODEXLENS_RERANKER_STRATEGY: {
-        key: 'CODEXLENS_RERANKER_STRATEGY',
-        labelKey: 'codexlens.envField.loadBalanceStrategy',
-        type: 'select',
-        options: ['round_robin', 'latency_aware', 'weighted_random'],
-        default: 'latency_aware',
-        settingsPath: 'reranker.strategy',
-        showWhen: (env) =>
-          (env['CODEXLENS_RERANKER_BACKEND'] === 'api' || env['CODEXLENS_RERANKER_BACKEND'] === 'litellm') &&
-          env['CODEXLENS_RERANKER_POOL_ENABLED'] === 'true',
+    },
+  },
+  search: {
+    id: 'search',
+    labelKey: 'codexlens.envGroup.search',
+    icon: 'git-branch',
+    vars: {
+      CODEXLENS_BINARY_TOP_K: {
+        key: 'CODEXLENS_BINARY_TOP_K',
+        labelKey: 'codexlens.envField.binaryTopK',
+        type: 'number',
+        placeholder: '200',
+        default: '200',
+        settingsPath: 'search.binary_top_k',
+        min: 10,
+        max: 1000,
      },
-      CODEXLENS_RERANKER_COOLDOWN: {
-        key: 'CODEXLENS_RERANKER_COOLDOWN',
-        labelKey: 'codexlens.envField.rateLimitCooldown',
+      CODEXLENS_ANN_TOP_K: {
+        key: 'CODEXLENS_ANN_TOP_K',
+        labelKey: 'codexlens.envField.annTopK',
+        type: 'number',
+        placeholder: '50',
+        default: '50',
+        settingsPath: 'search.ann_top_k',
+        min: 5,
+        max: 500,
+      },
+      CODEXLENS_FTS_TOP_K: {
+        key: 'CODEXLENS_FTS_TOP_K',
+        labelKey: 'codexlens.envField.ftsTopK',
+        type: 'number',
+        placeholder: '50',
+        default: '50',
+        settingsPath: 'search.fts_top_k',
+        min: 5,
+        max: 500,
+      },
+      CODEXLENS_FUSION_K: {
+        key: 'CODEXLENS_FUSION_K',
+        labelKey: 'codexlens.envField.fusionK',
        type: 'number',
        placeholder: '60',
        default: '60',
-        settingsPath: 'reranker.cooldown',
-        min: 0,
-        max: 300,
-        showWhen: (env) =>
-          (env['CODEXLENS_RERANKER_BACKEND'] === 'api' || env['CODEXLENS_RERANKER_BACKEND'] === 'litellm') &&
-          env['CODEXLENS_RERANKER_POOL_ENABLED'] === 'true',
-      },
-    },
-  },
-  concurrency: {
-    id: 'concurrency',
-    labelKey: 'codexlens.envGroup.concurrency',
-    icon: 'cpu',
-    vars: {
-      CODEXLENS_API_MAX_WORKERS: {
-        key: 'CODEXLENS_API_MAX_WORKERS',
-        labelKey: 'codexlens.envField.maxWorkers',
-        type: 'number',
-        placeholder: '4',
-        default: '4',
-        settingsPath: 'api.max_workers',
+        settingsPath: 'search.fusion_k',
        min: 1,
-        max: 32,
-      },
-      CODEXLENS_API_BATCH_SIZE: {
-        key: 'CODEXLENS_API_BATCH_SIZE',
-        labelKey: 'codexlens.envField.batchSize',
-        type: 'number',
-        placeholder: '8',
-        default: '8',
-        settingsPath: 'api.batch_size',
-        min: 1,
-        max: 64,
-        showWhen: (env) => env['CODEXLENS_API_BATCH_SIZE_DYNAMIC'] !== 'true',
-      },
-      CODEXLENS_API_BATCH_SIZE_DYNAMIC: {
-        key: 'CODEXLENS_API_BATCH_SIZE_DYNAMIC',
-        labelKey: 'codexlens.envField.dynamicBatchSize',
-        type: 'checkbox',
-        default: 'false',
-        settingsPath: 'api.batch_size_dynamic',
-      },
-      CODEXLENS_API_BATCH_SIZE_UTILIZATION: {
-        key: 'CODEXLENS_API_BATCH_SIZE_UTILIZATION',
-        labelKey: 'codexlens.envField.batchSizeUtilization',
-        type: 'number',
-        placeholder: '0.8',
-        default: '0.8',
-        settingsPath: 'api.batch_size_utilization_factor',
-        min: 0.1,
-        max: 0.95,
-        step: 0.05,
-        showWhen: (env) => env['CODEXLENS_API_BATCH_SIZE_DYNAMIC'] === 'true',
-      },
-      CODEXLENS_API_BATCH_SIZE_MAX: {
-        key: 'CODEXLENS_API_BATCH_SIZE_MAX',
-        labelKey: 'codexlens.envField.batchSizeMax',
-        type: 'number',
-        placeholder: '2048',
-        default: '2048',
-        settingsPath: 'api.batch_size_max',
-        min: 1,
-        max: 4096,
-        showWhen: (env) => env['CODEXLENS_API_BATCH_SIZE_DYNAMIC'] === 'true',
-      },
-      CODEXLENS_CHARS_PER_TOKEN: {
-        key: 'CODEXLENS_CHARS_PER_TOKEN',
-        labelKey: 'codexlens.envField.charsPerToken',
-        type: 'number',
-        placeholder: '4',
-        default: '4',
-        settingsPath: 'api.chars_per_token_estimate',
-        min: 1,
-        max: 10,
-        showWhen: (env) => env['CODEXLENS_API_BATCH_SIZE_DYNAMIC'] === 'true',
-      },
-    },
-  },
-  cascade: {
-    id: 'cascade',
-    labelKey: 'codexlens.envGroup.cascade',
-    icon: 'git-branch',
-    vars: {
-      CODEXLENS_CASCADE_STRATEGY: {
-        key: 'CODEXLENS_CASCADE_STRATEGY',
-        labelKey: 'codexlens.envField.searchStrategy',
-        type: 'select',
-        options: ['binary', 'hybrid', 'binary_rerank', 'dense_rerank', 'staged'],
-        default: 'dense_rerank',
-        settingsPath: 'cascade.strategy',
-      },
-      CODEXLENS_CASCADE_COARSE_K: {
-        key: 'CODEXLENS_CASCADE_COARSE_K',
-        labelKey: 'codexlens.envField.coarseK',
-        type: 'number',
-        placeholder: '100',
-        default: '100',
-        settingsPath: 'cascade.coarse_k',
-        min: 10,
-        max: 500,
-      },
-      CODEXLENS_CASCADE_FINE_K: {
-        key: 'CODEXLENS_CASCADE_FINE_K',
-        labelKey: 'codexlens.envField.fineK',
-        type: 'number',
-        placeholder: '10',
-        default: '10',
-        settingsPath: 'cascade.fine_k',
-        min: 1,
-        max: 100,
-      },
-      CODEXLENS_STAGED_STAGE2_MODE: {
-        key: 'CODEXLENS_STAGED_STAGE2_MODE',
-        labelKey: 'codexlens.envField.stagedStage2Mode',
-        type: 'select',
-        options: ['precomputed', 'realtime', 'static_global_graph'],
-        default: 'precomputed',
-        settingsPath: 'staged.stage2_mode',
-        showWhen: (env) => env['CODEXLENS_CASCADE_STRATEGY'] === 'staged',
-      },
-      CODEXLENS_STAGED_CLUSTERING_STRATEGY: {
-        key: 'CODEXLENS_STAGED_CLUSTERING_STRATEGY',
-        labelKey: 'codexlens.envField.stagedClusteringStrategy',
-        type: 'select',
-        options: ['auto', 'hdbscan', 'dbscan', 'frequency', 'noop', 'score', 'dir_rr', 'path'],
-        default: 'auto',
-        settingsPath: 'staged.clustering_strategy',
-        showWhen: (env) => env['CODEXLENS_CASCADE_STRATEGY'] === 'staged',
-      },
-      CODEXLENS_STAGED_CLUSTERING_MIN_SIZE: {
-        key: 'CODEXLENS_STAGED_CLUSTERING_MIN_SIZE',
-        labelKey: 'codexlens.envField.stagedClusteringMinSize',
-        type: 'number',
-        placeholder: '3',
-        default: '3',
-        settingsPath: 'staged.clustering_min_size',
-        min: 1,
-        max: 50,
-        showWhen: (env) => env['CODEXLENS_CASCADE_STRATEGY'] === 'staged',
-      },
-      CODEXLENS_ENABLE_STAGED_RERANK: {
-        key: 'CODEXLENS_ENABLE_STAGED_RERANK',
-        labelKey: 'codexlens.envField.enableStagedRerank',
-        type: 'checkbox',
-        default: 'true',
-        settingsPath: 'staged.enable_rerank',
-        showWhen: (env) => env['CODEXLENS_CASCADE_STRATEGY'] === 'staged',
+        max: 200,
      },
    },
  },
  indexing: {
    id: 'indexing',
    labelKey: 'codexlens.envGroup.indexing',
-    icon: 'git-branch',
+    icon: 'cpu',
    vars: {
-      CODEXLENS_USE_ASTGREP: {
-        key: 'CODEXLENS_USE_ASTGREP',
-        labelKey: 'codexlens.envField.useAstGrep',
+      CODEXLENS_CODE_AWARE_CHUNKING: {
+        key: 'CODEXLENS_CODE_AWARE_CHUNKING',
+        labelKey: 'codexlens.envField.codeAwareChunking',
        type: 'checkbox',
-        default: 'false',
-        settingsPath: 'parsing.use_astgrep',
-      },
-      CODEXLENS_STATIC_GRAPH_ENABLED: {
-        key: 'CODEXLENS_STATIC_GRAPH_ENABLED',
-        labelKey: 'codexlens.envField.staticGraphEnabled',
-        type: 'checkbox',
-        default: 'false',
-        settingsPath: 'indexing.static_graph_enabled',
-      },
-      CODEXLENS_STATIC_GRAPH_RELATIONSHIP_TYPES: {
-        key: 'CODEXLENS_STATIC_GRAPH_RELATIONSHIP_TYPES',
-        labelKey: 'codexlens.envField.staticGraphRelationshipTypes',
-        type: 'text',
-        placeholder: 'imports,inherits,calls',
-        default: 'imports,inherits',
-        settingsPath: 'indexing.static_graph_relationship_types',
-        showWhen: (env) => env['CODEXLENS_STATIC_GRAPH_ENABLED'] === 'true',
-      },
-    },
-  },
-  chunking: {
-    id: 'chunking',
-    labelKey: 'codexlens.envGroup.chunking',
-    icon: 'scissors',
-    vars: {
-      CHUNK_STRIP_COMMENTS: {
-        key: 'CHUNK_STRIP_COMMENTS',
-        labelKey: 'codexlens.envField.stripComments',
-        type: 'select',
-        options: ['true', 'false'],
        default: 'true',
-        settingsPath: 'chunking.strip_comments',
+        settingsPath: 'indexing.code_aware_chunking',
      },
-      CHUNK_STRIP_DOCSTRINGS: {
-        key: 'CHUNK_STRIP_DOCSTRINGS',
-        labelKey: 'codexlens.envField.stripDocstrings',
-        type: 'select',
-        options: ['true', 'false'],
-        default: 'true',
-        settingsPath: 'chunking.strip_docstrings',
-      },
-      RERANKER_TEST_FILE_PENALTY: {
-        key: 'RERANKER_TEST_FILE_PENALTY',
-        labelKey: 'codexlens.envField.testFilePenalty',
+      CODEXLENS_INDEX_WORKERS: {
+        key: 'CODEXLENS_INDEX_WORKERS',
+        labelKey: 'codexlens.envField.indexWorkers',
        type: 'number',
-        placeholder: '0.0',
-        default: '0.0',
-        settingsPath: 'reranker.test_file_penalty',
-        min: 0,
-        max: 1,
-        step: 0.1,
+        placeholder: '2',
+        default: '2',
+        settingsPath: 'indexing.workers',
+        min: 1,
+        max: 16,
      },
-      RERANKER_DOCSTRING_WEIGHT: {
-        key: 'RERANKER_DOCSTRING_WEIGHT',
-        labelKey: 'codexlens.envField.docstringWeight',
+      CODEXLENS_MAX_FILE_SIZE: {
+        key: 'CODEXLENS_MAX_FILE_SIZE',
+        labelKey: 'codexlens.envField.maxFileSize',
        type: 'number',
-        placeholder: '1.0',
-        default: '1.0',
-        settingsPath: 'reranker.docstring_weight',
-        min: 0,
-        max: 1,
-        step: 0.1,
+        placeholder: '1000000',
+        default: '1000000',
+        settingsPath: 'indexing.max_file_size_bytes',
+        min: 10000,
+        max: 10000000,
+      },
+      CODEXLENS_HNSW_EF: {
+        key: 'CODEXLENS_HNSW_EF',
+        labelKey: 'codexlens.envField.hnswEf',
+        type: 'number',
+        placeholder: '150',
+        default: '150',
+        settingsPath: 'indexing.hnsw_ef',
+        min: 10,
+        max: 500,
+      },
+      CODEXLENS_HNSW_M: {
+        key: 'CODEXLENS_HNSW_M',
+        labelKey: 'codexlens.envField.hnswM',
+        type: 'number',
+        placeholder: '32',
+        default: '32',
+        settingsPath: 'indexing.hnsw_M',
+        min: 4,
+        max: 128,
      },
    },
  },
--- a/ccw/frontend/src/locales/en/codexlens.json
+++ b/ccw/frontend/src/locales/en/codexlens.json
@@ -290,41 +290,31 @@
  "envGroup": {
    "embedding": "Embedding",
    "reranker": "Reranker",
-    "concurrency": "Concurrency",
-    "cascade": "Cascade Search",
-    "indexing": "Indexing",
-    "chunking": "Chunking"
+    "search": "Search Pipeline",
+    "indexing": "Indexing"
  },
  "envField": {
    "backend": "Backend",
    "model": "Model",
-    "autoEmbedMissing": "Auto Build Missing Vectors",
-    "useGpu": "Use GPU",
-    "highAvailability": "High Availability",
-    "loadBalanceStrategy": "Load Balance Strategy",
-    "rateLimitCooldown": "Rate Limit Cooldown",
-    "enabled": "Enabled",
+    "localModel": "Local Model",
+    "apiUrl": "API URL",
+    "apiKey": "API Key",
+    "multiEndpoints": "Multi-Endpoint",
+    "embedDim": "Embed Dimension",
+    "apiConcurrency": "Concurrency",
+    "maxTokensPerBatch": "Max Tokens/Batch",
+    "useGpu": "Device",
    "topKResults": "Top K Results",
-    "maxWorkers": "Max Workers",
    "batchSize": "Batch Size",
-    "dynamicBatchSize": "Dynamic Batch Size",
-    "batchSizeUtilization": "Utilization Factor",
-    "batchSizeMax": "Max Batch Size",
-    "charsPerToken": "Chars Per Token",
-    "searchStrategy": "Search Strategy",
-    "coarseK": "Coarse K",
-    "fineK": "Fine K",
-    "stagedStage2Mode": "Stage-2 Mode",
-    "stagedClusteringStrategy": "Clustering Strategy",
-    "stagedClusteringMinSize": "Cluster Min Size",
-    "enableStagedRerank": "Enable Rerank",
-    "useAstGrep": "Use ast-grep",
-    "staticGraphEnabled": "Static Graph",
-    "staticGraphRelationshipTypes": "Relationship Types",
-    "stripComments": "Strip Comments",
-    "stripDocstrings": "Strip Docstrings",
-    "testFilePenalty": "Test File Penalty",
-    "docstringWeight": "Docstring Weight"
+    "binaryTopK": "Binary Top K",
+    "annTopK": "ANN Top K",
+    "ftsTopK": "FTS Top K",
+    "fusionK": "Fusion K",
+    "codeAwareChunking": "Code-Aware Chunking",
+    "indexWorkers": "Index Workers",
+    "maxFileSize": "Max File Size (bytes)",
+    "hnswEf": "HNSW ef",
+    "hnswM": "HNSW M"
  },
  "install": {
    "title": "Install CodexLens",
--- a/ccw/frontend/src/locales/zh/codexlens.json
+++ b/ccw/frontend/src/locales/zh/codexlens.json
@@ -290,41 +290,31 @@
  "envGroup": {
    "embedding": "嵌入模型",
    "reranker": "重排序",
-    "concurrency": "并发",
-    "cascade": "级联搜索",
-    "indexing": "索引与解析",
-    "chunking": "分块"
+    "search": "搜索流水线",
+    "indexing": "索引"
  },
  "envField": {
    "backend": "后端",
    "model": "模型",
-    "autoEmbedMissing": "缺失向量时自动构建",
-    "useGpu": "使用 GPU",
-    "highAvailability": "高可用",
-    "loadBalanceStrategy": "负载均衡策略",
-    "rateLimitCooldown": "限流冷却时间",
-    "enabled": "启用",
+    "localModel": "本地模型",
+    "apiUrl": "API 地址",
+    "apiKey": "API 密钥",
+    "multiEndpoints": "多端点",
+    "embedDim": "向量维度",
+    "apiConcurrency": "并发数",
+    "maxTokensPerBatch": "每批最大Token数",
+    "useGpu": "设备",
    "topKResults": "Top K 结果数",
-    "maxWorkers": "最大工作线程",
    "batchSize": "批次大小",
-    "dynamicBatchSize": "动态批次大小",
-    "batchSizeUtilization": "利用率因子",
-    "batchSizeMax": "最大批次大小",
-    "charsPerToken": "每 Token 字符数",
-    "searchStrategy": "搜索策略",
-    "coarseK": "粗筛 K 值",
-    "fineK": "精筛 K 值",
-    "stagedStage2Mode": "Stage-2 模式",
-    "stagedClusteringStrategy": "聚类策略",
-    "stagedClusteringMinSize": "最小聚类大小",
-    "enableStagedRerank": "启用重排序",
-    "useAstGrep": "使用 ast-grep",
-    "staticGraphEnabled": "启用静态图",
-    "staticGraphRelationshipTypes": "关系类型",
-    "stripComments": "去除注释",
-    "stripDocstrings": "去除文档字符串",
-    "testFilePenalty": "测试文件惩罚",
-    "docstringWeight": "文档字符串权重"
+    "binaryTopK": "二值粗筛 K",
+    "annTopK": "ANN 精筛 K",
+    "ftsTopK": "全文搜索 K",
+    "fusionK": "融合 K",
+    "codeAwareChunking": "代码感知分块",
+    "indexWorkers": "索引线程数",
+    "maxFileSize": "最大文件大小(字节)",
+    "hnswEf": "HNSW ef",
+    "hnswM": "HNSW M"
  },
  "install": {
    "title": "安装 CodexLens",
--- a/ccw/frontend/src/types/codexlens.ts
+++ b/ccw/frontend/src/types/codexlens.ts
@@ -20,7 +20,7 @@ export interface EnvVarFieldSchema {
  /** i18n label key */
  labelKey: string;
  /** Field type determines which control to render */
-  type: 'select' | 'model-select' | 'number' | 'checkbox' | 'text';
+  type: 'select' | 'model-select' | 'number' | 'checkbox' | 'text' | 'password';
  /** Options for select type */
  options?: string[];
  /** Default value */