Diagram generation: ref-arch-driven procedure + spec validator + KB enrichment

The diagram path now follows a documented standard procedure (lookup
the closest Oracle Architecture Center reference → confirm components
→ author absolute_layout → spec validator → render → visually verify)
and ships persistent guardrails so layout regressions can't recur.

Persistent procedure changes (apply to all users, all sessions):
- tools/diagram_spec_validator.py — geometry checks (CONTAINER_TOO_THIN,
  CONTAINER_PADDING_VIOLATION, LABEL_OVERFLOW_PARENT) run BEFORE either
  renderer (drawio + PPTX). Catches the subnet-collapse / label-overflow
  bugs that the post-render drawio validator missed.
- tools/oci_diagram_gen.py + tools/oci_pptx_diagram_gen.py — call the
  spec validator before emitting any output. Adds mysql / mysql_heatwave
  type aliases.
- tools/archcenter_pattern_lookup.py — scores against cached page
  descriptions (not just the 1-line summary), supports --queries for
  multi-fragment composition, and applies synonym expansion via
  kb/architecture-center/synonyms.yaml so "LB HA cross AD" matches
  "load balancer high availability availability domain".
- kb/architecture-center/synonyms.yaml — canonical synonym table
  (load balancer, autonomous database, data guard, …) used by the
  lookup scorer.

KB enrichment:
- tools/archcenter_description_fetcher.py + 121 cached _description.md
  under kb/diagram/assets/archcenter-refs/<slug>/. Removes the runtime
  dependency on docs.oracle.com when authoring specs and feeds the
  pattern-lookup scorer.
- 110+ cached .drawio / .svg / .png references for offline reuse,
  plus the OCI Toolkit v24.2 import (kb/diagram/assets/oci-toolkit-drawio).

Documentation:
- docs/skill/output-formats.md — new "Standard diagram-generation
  procedure (MANDATORY)" + geometry rules + the new validator entry.
- SKILL.md option 2 — references the mandatory procedure.
- README.md — describes the spec validator, archcenter_pattern_lookup
  and description fetcher, and updates the KB-health table.

Tooling that backs the procedure (cumulative across recent sessions):
tools/archcenter_case_runner.py, archcenter_batch_driver.py,
archcenter_zip_downloader.py, drawio_visual_validator.py,
drawio_fidelity_eval.py, harvest_drawio_icon.py, import_oci_library.py,
oci_pptx_diagram_gen.py, oci_pptx_render.py, refresh_pptx_icon_index.py.

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

kb/diagram/assets/archcenter-refs/genai-vector-opensearch/_description.md

@@ -0,0 +1,192 @@
+# Improve search results with Oracle Generative AI Agents, Vector Search, and OCI OpenSearch
+
+- Source: https://docs.oracle.com/en/solutions/genai-vector-opensearch/index.html
+- Date: 2024-12
+- Type: reference-architecture
+- Services: genai, opensearch, adb-s
+- Tags: ai-ml, autonomous
+
+## Summary (catalog)
+
+Hybrid search combining vector similarity (ADB-S) with keyword search (OpenSearch). GenAI for query understanding and result re-ranking. Suitable for enterprise knowledge bases and document search.
+
+## Architecture (fetched from source)
+
+Deploy an AI-powered enterprise search engine using Oracle Generative AI Agents, Oracle Database 23ai Vector, and OCI OpenSearch 
+ 
+ 
+ 
+ 
+- 
+ 
+- 
+ 
+ 
+ 
+ 
+ 
+- 
+ 
+ 
+ 
+ 
+ 
+ 
+ 
+ 
+ 
+- 
+ 
+ 
+ 
+ 
+ 
+ 
+ 
+ 
+ 
+- 
+ 
+- 
+ 
+- 
+ 
+- 
+ 
+- 
+ 
+- 
+ 
+- 
+ 
+- 
+ 
+- 
+ 
+- 
+ 
+- 
+ 
+- 
+ 
+ 
+ 
+ 
+
+ Previous 
+ Next 
+ JavaScript must be enabled to correctly display this content
+ 
+ 
+
+ 
+
+ 
+ 
+ 
+- Improve search results with Oracle Generative AI Agents, Vector Search, and OCI OpenSearch 
+ 
+- Deploy an AI-powered enterprise
+ search engine using Oracle Generative AI Agents, Oracle Database 23ai Vector, and OCI OpenSearch 
+ 
+ 
+ 
+ 
+Deploy an AI-powered enterprise
+ search engine using Oracle Generative AI Agents, Oracle Database 23ai Vector, and OCI OpenSearch
+ 
+
+ 
+ 
+
+ 
+
+ 
+
+ Search powered by artificial intelligence (AI) is intended to help
+ employees in every line of business get immediate answers to complex queries. But
+ writing programmatic queries using keywords or semantic search can be extremely
+ challenging if not impossible for anyone without technical expertise. 
+ 
+ 
+
+ 
+By using Oracle Generative AI services, anyone with a keyboard or voice
+ command interface can:
+
+ 
+ 
+- Quickly predict customer purchase behaviors by asking natural language questions 
+ 
+- Instantly retrieve information from a knowledge base, and provide contextually
+ relevant solutions to complex problems 
+ 
+- Access and synthesize technical manuals and support forums to instantly retrieve
+ step-by-step instructions 
+ 
+ 
+By combining Oracle Generative AI Retrieval-Augmented Generation (RAG)
+ Agents with a supported knowledge base, cloud engineers and enterprise architects can
+ quickly:
+
+ 
+ 
+- Build an intelligent search system that supports hybrid search (keyword
+ search and semantic search), advanced data retrieval, and reranking to provide the
+ most precise and relevant information 
+ 
+- Provide a chat interface where any authorized user, with or without
+ technical expertise, can use natural language to query enterprise data 
+ 
+- Provide a managed vector data store and automated data ingestion
+ pipeline to enable efficient storage and retrieval of complex data 
+ 
+ 
+
+ 
+ 
+Replay the Webinar
+
+ 
+
+ 
+Replay the webinar: 
+
+ 
+
+ 
+
+ 
+
+ 
+
+ 
+
+ 
+
+ 
+
+ 
+
+ 
+
+ 
+
+ 
+ Title and Copyright Information 
+
+ 
+
+ 
+Improve search results with Oracle Generative AI Agents, Vector Search, and OCI OpenSearch
+
+ 
+G19700-01
+
+ 
+December 2024
+
+ 
+ Copyright © 2024, 
+
+Oracle and/or its affiliates.