docs: 补回被误删的架构节，许可段压缩，去掉重复

## 上一轮我把架构整节删掉了

用 `s.index()` 替换区间时，把「架构」到「下载」之间的内容一起吞了。
README 里「架构」出现 0 次 —— 最该详细写的部分没了。已补回：

- 内核/插件三层通道图（ASCII，按 CJK 宽度对齐到 39 列）
- 七阶段表（`on_input` … `after_output` 各自时机与插件能做什么）
- 内循环规则与三个退出条件
- 三层记忆与插件崩溃退避（1s/2s/3s，5 分钟内第 4 次停自动重启）

## 许可段 16 行 → 7 行

原文逐条拆：

| 原文 | 问题 |
|---|---|
| 「GPL 家族里**传染性最强**的一档」 | 比喻+最高级，许可段不需要修辞 |
| 「即：任何人把改过的……」 | 重复上一句，只是换了说法 |
| 「边界很清楚：」 | 过渡铺垫 |
| 「子进程隔离在这里不重要了」 | 反驳没人提的问题（humanizer §A.5） |
| 「第三方插件生态的安全与活跃正建立在这条之上」 | 纯空话 |

用户只需要知道三件事：改过的版本对外提供服务要开源；自己写的插件不受约束、
可以闭源商用；第三方组件保留原许可。

## 去掉重复与模板化开头

- 「内核不发 HTTP、不读文件」在架构段与「其余」里各出现一次，删掉后一处
- 开头原本连续四段 `**粗体断言。** + 三行解释` —— 同一个模板重复四遍就是排比。
  改成一句话开场 + 安装命令，设计细节另起 `## 几个设计`
- 全文破折号从 1 处降到 0

## 验证

- 两版链接无死链，代码块配对（6/6）
- 6 个二级标题中英对齐
- ASCII 图逐行按 east_asian_width 计算，框线全部 39 列

README_EN.md

@@ -4,27 +4,82 @@
 
 > **中文**: [README.md](./README.md)
 
-Self-hosted agent kernel. [Docs](assets/docs/en/ARCHITECTURE.md) · [中文](README.md)
-
-**Startup order is computed at build time, not guessed at runtime.** Twenty kernel modules each declare `Requires`/`Provides`. The build resolves a 6-layer dependency graph into `depgraph.bin` and injects the graph digest into the binary via `-ldflags`. At runtime the kernel reads the graph and does not recompute it. If the graph and the binary don't match, startup is refused rather than guessing which one is right.
+Self-hosted agent kernel. Runs on your own hardware; plugins attach as separate processes.
 
 ```bash
 make build build-cli
 ./build/homed -data /tmp/ha
 ```
 
-**Plugins start when their facilities are ready, not when the kernel finishes.** A plugin declaring `requires_facilities: [config]` launches as layer 1 completes instead of waiting for the agent layer. Measured saving: 35 seconds, which is how long the agent layer spends on dense backfill of 750 events plus rebuilding document and knowledge indexes.
+API keys go in the web UI at `http://localhost:8080`. Requires Linux.
 
-**Two input classes, four interrupt levels.** Queued input carries no level, so any interrupt can preempt it. Interrupts carry L1–L4; higher preempts lower and the preempted state is pushed onto a stack for later resume. Same level never preempts. L4 belongs to the kernel alone (panics, kernel events); a plugin declaring L4 gets clamped to L3. Preemption count can raise a task's level, but by at most two steps (`preemptPromotionCap = 2`), so low-priority work can't starve indefinitely.
+## Design notes
 
-**Memory is partitioned by scene, not by session.** A scene fingerprint is built from channel, conversation partner, tools, topic, and time of day, weighted 1.0 / 1.0 / 0.8 / 0.4 / 0.2. A scene only comes into being on the second occurrence (`minSceneEvidence = 2`); one-off interactions don't count. Join threshold is 0.5, recall threshold 0.35. Recall is looser than join on purpose: failing to recall is a loss, while recalling one extra scene costs a few lines of context.
+**Startup order is resolved at build time.** Twenty kernel modules declare `Requires`/`Provides`.
+The build computes a 6-layer graph into `depgraph.bin` and injects its digest into the binary via
+`-ldflags`. At runtime the kernel reads the graph rather than recomputing it. A mismatch between
+graph and binary refuses startup.
+
+**Plugins launch as soon as their facilities are ready.** A plugin declaring
+`requires_facilities: [config]` starts when layer 1 completes instead of waiting for the agent
+layer at layer 4. That saves a measured 35 seconds, which the agent layer spends on dense
+backfill of 750 events and reindexing.
+
+**Two input classes, four interrupt levels.** Queued input has no level, so any interrupt can
+preempt it. Interrupts carry L1–L4: higher preempts lower and pushes the preempted state onto a
+stack for later resume, same level never preempts. L4 is kernel-only; plugins declaring it get
+clamped to L3. Preemption count can raise a level by at most two steps
+(`preemptPromotionCap = 2`), so low-priority work can't starve indefinitely.
+
+**Memory is partitioned by scene.** A fingerprint is built from channel, partner, tools, topic,
+and time of day, weighted 1.0/1.0/0.8/0.4/0.2. A scene exists only after the second matching
+fingerprint (`minSceneEvidence = 2`). Join threshold 0.5, recall 0.35 — recall is looser because
+failing to recall loses information while an extra scene costs a few lines of context.
+
+## Architecture
+
+```
+                    homed (kernel)
+        LLM orchestration · memory · retrieval
+                       │
+        ┌──────────────┼──────────────┐
+        │              │              │
+   stdio RPC       shared mem     event ring
+     control       bulk data      notify
+        │              │              │
+        └──────────────┼──────────────┘
+                       │
+              plugins (separate processes)
+   web UI · QQ · CLI · files · browser
+```
+
+The kernel makes no HTTP calls and reads no files. Everything that touches the outside world is a
+plugin. A plugin crash leaves the kernel running; restart backs off 1s / 2s / 3s, and the 4th
+crash within 5 minutes stops automatic restarts for human intervention.
+
+**Seven stages after a message arrives** (`internal/agent/core/stages.go`):
+
+| Stage | When | Plugins can |
+|---|---|---|
+| `on_input` | message arrives | blocklist, rate limit, short-circuit reply |
+| `pre_action` | context ready, before LLM | inject external data |
+| `post_action` | LLM returns text and tool calls | filter, force redirect |
+| `before_toolcall` | before one tool runs | audit, deny, rewrite args |
+| `after_toolcall` | after one tool runs | redact, sort results |
+| `before_output` | final text ready | format adaptation |
+| `after_output` | already sent | statistics |
+
+`post_action → [before_toolcall → run → after_toolcall] → post_action` is the inner loop. It exits
+when the model stops calling tools, all calls are denied, or the limit is reached.
+
+**Three memory layers**: context (last 10 always protected) → documents (cold data sinks) → graph
+database (distilled into triples). Media are first-class graph nodes, not attachments.
 
 ## Everything else
 
 - **Channels**: web UI, CLI, QQ groups and DMs, A2A, ACP in your IDE
 - **Tools**: files, shell, code, browser (real Chrome), calendar, notes, RSS, music
 - **Modalities**: images, video, voice, screenshots, web pages
-- **Zero-IO kernel**: no HTTP calls, no file reads; every capability lives in a plugin
 
 28 built-in plugins, 89 model-callable tools. External plugins live one per repo under [github.com/HologramAgent](https://github.com/HologramAgent).