Initial public push: docs cosmos v4 + AI module + framework groundwork

This is the snapshot the production landing site (nibiru-framework.com) is
deployed from. Brings together the recent splash + docs migration to the v4
"Cosmos" design system, the new in-framework AI module, and the framework
groundwork that backs the framework-reference extraction.

What lands:
- docs/: Astro + Starlight site with the v4 dark cosmic palette, GalaxyHero
  canvas constellation, Mission Control chat (wired to /api/oracle →
  api.neuronetz.ai via providers.mjs Ollama), 5-panel MMVC stage
  (Model · AI · Module · Controller · View), translated EN/DE/JA/ES/FR
  content, PWA + sitemap + llms.txt + Umami analytics.
- docs/design-system/: canonical mockup bundle (source/index-v2.html for
  splash, source/docs-system.html + preview/ for docs, SPEC.md, tokens).
- docs/scripts/extraction/framework-reference-v2.md: deep framework
  reference (~1.6k lines, file:line citations, every public factory and
  idiom — basis for the LoRA training corpus.
- application/module/ai/: AI module with chat / embed / RAG / agent
  plugins, plus pdoQuery / httpGet / fileRead tools and Modelfile +
  smoke-test in training/.
- application/module/users/: user / ACL / form-factory traits used as the
  reference plugin pattern for the framework docs.
- application/settings/config/database/: schema + seed migrations
  including the AI module tables (200–203).
- Form factory + autogenerator changes the framework-reference-v2 covers.

Production secrets stay out: docs/.env, settings.production.ini and
ai.production.ini are all gitignored (.example files are in tree).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

application/settings/config/database/201-ai_rag_chunk.sql

@@ -0,0 +1,28 @@
+-- =============================================================================
+--  ai_rag_chunk
+--
+--  One row per text chunk in a RAG collection. The embedding column stores
+--  the vector as a base64-packed Float32Array (4 bytes/dim). Cosine search
+--  is done in PHP after fetching all chunks for the collection — fine up
+--  to ~10k chunks per collection. For larger sets, drop in a vector index
+--  extension (pgvector, MySQL HeatWave LakeHouse vector) and update
+--  Rag::search() accordingly.
+-- =============================================================================
+
+CREATE TABLE IF NOT EXISTS ai_rag_chunk (
+    ai_rag_chunk_id            INT(11)      NOT NULL AUTO_INCREMENT,
+    ai_rag_chunk_collection_id INT(11)      NOT NULL,
+    ai_rag_chunk_text          MEDIUMTEXT   NOT NULL,
+    ai_rag_chunk_metadata      JSON         NULL,
+    ai_rag_chunk_embedding     LONGTEXT     NOT NULL,    -- base64-packed Float32Array
+    ai_rag_chunk_token_count   INT(11)      NOT NULL DEFAULT 0,
+    ai_rag_chunk_source        VARCHAR(512) NULL,        -- denormalised from metadata for indexing
+    ai_rag_chunk_created_at    TIMESTAMP    NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    PRIMARY KEY (ai_rag_chunk_id),
+    KEY ai_rag_chunk_collection_idx (ai_rag_chunk_collection_id),
+    KEY ai_rag_chunk_source_idx (ai_rag_chunk_source),
+    CONSTRAINT ai_rag_chunk_collection_fk
+        FOREIGN KEY (ai_rag_chunk_collection_id)
+        REFERENCES ai_rag_collection (ai_rag_collection_id)
+        ON DELETE CASCADE
+) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4 COLLATE = utf8mb4_unicode_ci;