Switch all generated diagrams from PNG to JPG for consistency

All architecture diagrams (01-10 + llm-supervised-concept) now use JPG format.
Updated README, Chinese README, and visualize_graph.py output path.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: Grivn

README.md

@@ -17,7 +17,7 @@ LLM agents forget everything between sessions. Context compaction drops critical
 Mnemon gives your agent persistent, cross-session memory — with a single binary and one setup command.
 
 <p align="center">
-  <img src="docs/diagrams/10-knowledge-graph.png" width="720" alt="Knowledge Graph — 87 insights connected by temporal, entity, semantic, and causal edges" />
+  <img src="docs/diagrams/10-knowledge-graph.jpg" width="720" alt="Knowledge Graph — 87 insights connected by temporal, entity, semantic, and causal edges" />
   <br />
   <sub>A real knowledge graph built by Mnemon — 87 insights, 2150 edges across four graph types.</sub>
 </p>
@@ -37,7 +37,7 @@ This means: **memory management logic moves from prompt to code — deterministi
 | **LLM-Supervised** | External supervisor of a standalone binary | Mnemon |
 
 <p align="center">
-  <img src="docs/diagrams/llm-supervised-concept.png" width="720" alt="LLM-Supervised Architecture — three patterns compared, with detailed Mnemon implementation showing hooks, brain/organ split, and sub-agent delegation" />
+  <img src="docs/diagrams/llm-supervised-concept.jpg" width="720" alt="LLM-Supervised Architecture — three patterns compared, with detailed Mnemon implementation showing hooks, brain/organ split, and sub-agent delegation" />
   <br />
   <sub>The LLM-Supervised pattern: hooks drive the lifecycle, the host LLM makes judgment calls, the binary handles deterministic computation.</sub>
 </p>

docs/diagrams/10-knowledge-graph.jpg

@@ -17,7 +17,7 @@ LLM 智能体在会话之间会遗忘一切。上下文压缩丢失关键决策
 Mnemon 为你的 LLM 提供持久的跨会话记忆 — 只需一个 Go 二进制文件和一条 setup 命令。
 
 <p align="center">
-  <img src="../diagrams/10-knowledge-graph.png" width="720" alt="知识图谱 — 87 条洞察通过时序、实体、语义和因果边连接" />
+  <img src="../diagrams/10-knowledge-graph.jpg" width="720" alt="知识图谱 — 87 条洞察通过时序、实体、语义和因果边连接" />
   <br />
   <sub>Mnemon 构建的真实知识图谱 — 87 条洞察，2150 条边，横跨四种图类型。</sub>
 </p>

docs/diagrams/10-knowledge-graph.png

@@ -13,7 +13,7 @@
 import numpy as np
 
 DB_PATH = Path.home() / ".mnemon" / "mnemon.db"
-OUT_PATH = Path(__file__).resolve().parent.parent / "docs" / "diagrams" / "10-knowledge-graph.png"
+OUT_PATH = Path(__file__).resolve().parent.parent / "docs" / "diagrams" / "10-knowledge-graph.jpg"
 
 # ── colour palette ──────────────────────────────────────────────────
 CATEGORY_COLOURS = {