feat: fix RAG pipelines, Beep Graph branding, PWA, and ambient glow UI

Pipeline fixes:
- Fix agent getting empty response from graph-rag by combining answer +
  explain data in single message (RequestResponse returns first msg)
- Fix Doc RAG pipeline: add content field to Qdrant doc payload, seed 10
  document chunks, fix type mismatches across base/flow/client
- Forward explainability events from agent's KnowledgeQuery to client
- Add "agent" to TERM_BEARING_RESPONSE_SERVICES for triple translation
- Fix embeddings env var (OLLAMA_URL), user/collection threading, edge
  scoring threshold, and various protocol mismatches

Branding:
- Rename TrustGraph → Beep Graph (title, sidebar, settings, about)
- Custom lambda + ThugLife pixel glasses SVG logo component
- Forest green color palette (brand-50 through brand-900)
- SVG favicon + PNG icons (16/32/180/192/512)
- PWA manifest with service worker for offline shell caching
- Splash screen with animated logo pulse on app load
- Ambient glow background with drifting green radial blobs

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

ts/packages/flow/src/retrieval/document-rag.ts

@@ -13,6 +13,8 @@ import type {
   TextCompletionResponse,
   EmbeddingsRequest,
   EmbeddingsResponse,
+  DocumentEmbeddingsRequest,
+  DocumentEmbeddingsResponse,
   PromptRequest,
   PromptResponse,
 } from "@trustgraph/base";
@@ -20,7 +22,7 @@ import type {
 export interface DocumentRagClients {
   llm: RequestResponse<TextCompletionRequest, TextCompletionResponse>;
   embeddings: RequestResponse<EmbeddingsRequest, EmbeddingsResponse>;
-  docEmbeddings: RequestResponse<unknown, unknown>; // Doc embedding query
+  docEmbeddings: RequestResponse<DocumentEmbeddingsRequest, DocumentEmbeddingsResponse>;
   prompt: RequestResponse<PromptRequest, PromptResponse>;
 }
 
@@ -31,22 +33,31 @@ export class DocumentRag {
 
   async query(
     queryText: string,
-    _options?: {
+    options?: {
       collection?: string;
       streaming?: boolean;
       chunkCallback?: ChunkCallback;
     },
   ): Promise<string> {
+    const collection = options?.collection ?? "default";
+
     // Step 1: Embed the query
     const embResp = await this.clients.embeddings.request({ text: [queryText] });
     const vectors = (embResp as EmbeddingsResponse).vectors;
 
     // Step 2: Find similar document chunks
-    const docResp = await this.clients.docEmbeddings.request({ vectors, limit: 10 });
-    const chunks = docResp as { chunks: Array<{ content: string; document: string }> };
+    const docResp = await this.clients.docEmbeddings.request({
+      vectors,
+      limit: 10,
+      collection,
+      user: "default",
+    });
+    const chunks = (docResp as DocumentEmbeddingsResponse).chunks ?? [];
+    console.log(`[DocumentRag] Found ${chunks.length} matching chunks`);
 
     // Step 3: Build context from chunks
-    const context = (chunks.chunks ?? [])
+    const context = chunks
+      .filter((c) => c.content)
       .map((c) => c.content)
       .join("\n\n---\n\n");