refactor: Prettier 格式化全量前端、Library 服务端分页筛选、Agent 工具输出可视化与 .agent 目录统一

代码质量：
  - 新增 .prettierrc + eslint-plugin-prettier，全量格式化所有 TSX/TS/CSS 文件
  - npm scripts 新增 format / format:check / lint:fix

  Logo 重设计：
  - SVG logo 从简单星月改为望远镜+轨道+三角架+星光，favicon 同步更新

  Library 服务端分页与多维筛选：
  - LibraryQueryParams 支持 q(全局搜索)/status(下载状态)/doctype/author/year/journal/sort_by
  - API 返回 {items, total}，默认每页 12 条
  - 前端新增筛选面板：搜索栏、状态下拉、文献类型、排序、分页控件

  Agent 工具输出可视化：
  - 新增 SpecialToolRenderers.tsx：query_target 天体参数卡片(含 SIMBAD/VizieR 链接)、search_papers
  文献列表(内嵌下载/阅读/星系跳转按钮)
  - 系统内部工具(compress_context 等)无错误时自动隐藏，减少时间线噪音
  - ToolCallCard 与 Reader/Citation 打通：可在工具输出中直接打开文献或跳转引用星系

  .agent 目录统一：
  - memory/tool-results/trajectories/images 全部归入 library/.agent/ 子目录

  PDF 加载修复：
  - BilingualViewer 改用 fetch → blob:// URL 加载 PDF，绕过 iframe SameSite Cookie 限制

CLAUDE.md

@@ -46,6 +46,9 @@ cargo test test_name
 npm run dev       # HMR dev server on :5173, proxies /api to :8000
 npm run build     # TypeScript check + Vite production build → dashboard/dist/
 npm run lint      # ESLint
+npm run lint:fix  # ESLint with auto-fix
+npm run format    # Prettier format all source files
+npm run format:check  # Check formatting without modifying files
 ```
 
 ## Architecture Overview
@@ -169,13 +172,14 @@ Session-level modes configure the agent's identity, tool access, step limits, th
 
 Three built-in modes (registered in `ModeRegistry::builtins()`):
 
-| Mode | ID | Tools | Max Steps | Thinking | Permission Profile |
-|------|-----|-------|-----------|----------|---------------------|
-| 通用科研助手 | `default` | All (unrestricted) | 8 (default) | user-controlled | none |
-| 深度研究 | `deep-research` | All | 16 | forced on | `research` |
-| 文献阅读助手 | `literature-reader` | Allowlist (read-only + literature) | 6 | forced off | `readonly` |
+| Mode         | ID                    | Tools                              | Max Steps   | Thinking        | Permission Profile |
+| ------------ | --------------------- | ---------------------------------- | ----------- | --------------- | ------------------ |
+| 通用科研助手 | `default`           | All (unrestricted)                 | 8 (default) | user-controlled | none               |
+| 深度研究     | `deep-research`     | All                                | 16          | forced on       | `research`       |
+| 文献阅读助手 | `literature-reader` | Allowlist (read-only + literature) | 6           | forced off      | `readonly`       |
 
 Key types in `modes/mod.rs`:
+
 - **`AgentMode`** — static definition struct: id, name, description, icon, identity/principles overrides, extra sections, `ToolSet`, `ModeConfig`
 - **`ToolSet`** — `All`, `Allowlist(&[&str])`, or `Except(&[&str])` — constrains which tools are available
 - **`ModeConfig`** — optional overrides for `max_steps`, `enable_thinking`, `tool_timeout_secs`, `permission_profile`
@@ -190,6 +194,7 @@ The mode is stored in the `agent_sessions.mode` column (migration `2026062400000
 Tool execution is gated by a priority-ordered rule chain: **Deny > Allow > Ask** (first match wins). Rules support content-level pattern matching (e.g., `run_bash(rm *)`).
 
 **Permission modes** (set via `AGENT_PERMISSION_MODE` env or mode's `permission_profile`):
+
 - `default` — full rule chain evaluation
 - `accept_edits` — auto-allow `file_write`/`file_edit` within the working directory
 - `bypass` — skip all Ask checks (Deny rules still enforced)
@@ -198,6 +203,7 @@ Tool execution is gated by a priority-ordered rule chain: **Deny > Allow > Ask**
 **Permission profiles** (`src/agent/runtime/permission_profile.rs`) are named presets loaded by `AGENT_PERMISSION_MODE` or a mode's `permission_profile` field. Profiles `research` and `readonly` are used by deep-research and literature-reader modes respectively.
 
 **Configuration** (in `.env`):
+
 - `AGENT_PERMISSIONS_DENY` — comma-separated deny rules (e.g., `run_bash(rm *),run_bash(sudo *)`)
 - `AGENT_PERMISSIONS_ALLOW` — comma-separated allow rules
 - `AGENT_PERMISSIONS_ASK` — comma-separated ask rules
@@ -207,11 +213,11 @@ Tool execution is gated by a priority-ordered rule chain: **Deny > Allow > Ask**
 
 The system supports three LLM tiers with cascade fallback:
 
-| Tier | Env Prefix | Purpose | Fallback |
-|------|-----------|---------|----------|
-| Primary | `LLM_` | Main agent reasoning | — |
-| Medium | `LLM_MEDIUM_` | Translation, RAG | Primary LLM config |
-| Fast | `LLM_FAST_` | Memory extraction, background tasks | Medium LLM config |
+| Tier    | Env Prefix      | Purpose                             | Fallback           |
+| ------- | --------------- | ----------------------------------- | ------------------ |
+| Primary | `LLM_`        | Main agent reasoning                | —                 |
+| Medium  | `LLM_MEDIUM_` | Translation, RAG                    | Primary LLM config |
+| Fast    | `LLM_FAST_`   | Memory extraction, background tasks | Medium LLM config  |
 
 Each tier has `_API_KEY`, `_API_BASE`, `_MODEL` variants. Unset tiers cascade to the next tier down.
 
@@ -224,6 +230,7 @@ When `LLM_VISION_MODEL` env is set, the `analyze_image` tool (`src/agent/tools/a
 ### Auto Memory Extraction
 
 Controlled by env vars:
+
 - `EXTRACT_MEMORY_ENABLED` (default `false`) — enables automatic memory extraction at session end and during compaction
 - `EXTRACT_MEMORY_THROTTLE_TURNS` (default `3`) — extract every N turns
 - `EXTRACT_MEMORY_MAX_STEPS` (default `3`) — sub-agent max steps for extraction