chore: 移除所有 Citations 相关逻辑，为后续重构做准备

- Backend: 删除 lead_agent / general_purpose 中的 citations_format 与引用相关 reminder；artifacts 下载不再对 markdown 做 citation 清洗，统一走 FileResponse，保留 Response 用于二进制 inline
- Frontend: 删除 core/citations 模块、inline-citation、safe-citation-content；新增 MarkdownContent 仅做 Markdown 渲染；消息/artifact 预览与复制均使用原始 content
- i18n: 移除 citations 命名空间（loadingCitations、loadingCitationsWithCount）
- 技能与 demo: 措辞改为 references，demo 数据去掉 <citations> 块
- 文档: 更新 CLAUDE/AGENTS/README 描述，新增按文件 diff 的代码变更总结

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/CLAUDE.md

@@ -156,7 +156,7 @@ FastAPI application on port 8001 with health check at `GET /health`.
 | **Skills** (`/api/skills`) | `GET /` - list skills; `GET /{name}` - details; `PUT /{name}` - update enabled; `POST /install` - install from .skill archive |
 | **Memory** (`/api/memory`) | `GET /` - memory data; `POST /reload` - force reload; `GET /config` - config; `GET /status` - config + data |
 | **Uploads** (`/api/threads/{id}/uploads`) | `POST /` - upload files (auto-converts PDF/PPT/Excel/Word); `GET /list` - list; `DELETE /{filename}` - delete |
-| **Artifacts** (`/api/threads/{id}/artifacts`) | `GET /{path}` - serve artifacts; `?download=true` for download with citation removal |
+| **Artifacts** (`/api/threads/{id}/artifacts`) | `GET /{path}` - serve artifacts; `?download=true` for file download |
 
 Proxied through nginx: `/api/langgraph/*` → LangGraph, all other `/api/*` → Gateway.
 

backend/src/agents/lead_agent/prompt.py

@@ -240,34 +240,8 @@ You have access to skills that provide optimized workflows for specific tasks. E
 - Action-Oriented: Focus on delivering results, not explaining processes
 </response_style>
 
-<citations_format>
-After web_search, ALWAYS include citations in your output:
-
-1. Start with a `<citations>` block in JSONL format listing all sources
-2. In content, use FULL markdown link format: [Short Title](full_url)
-
-**CRITICAL - Citation Link Format:**
-- CORRECT: `[TechCrunch](https://techcrunch.com/ai-trends)` - full markdown link with URL
-- WRONG: `[arXiv:2502.19166]` - missing URL, will NOT render as link
-- WRONG: `[Source]` - missing URL, will NOT render as link
-
-**Rules:**
-- Every citation MUST be a complete markdown link with URL: `[Title](https://...)`
-- Write content naturally, add citation link at end of sentence/paragraph
-- NEVER use bare brackets like `[arXiv:xxx]` or `[Source]` without URL
-
-**Example:**
-<citations>
-{{"id": "cite-1", "title": "AI Trends 2026", "url": "https://techcrunch.com/ai-trends", "snippet": "Tech industry predictions"}}
-{{"id": "cite-2", "title": "OpenAI Research", "url": "https://openai.com/research", "snippet": "Latest AI research developments"}}
-</citations>
-The key AI trends for 2026 include enhanced reasoning capabilities and multimodal integration [TechCrunch](https://techcrunch.com/ai-trends). Recent breakthroughs in language models have also accelerated progress [OpenAI](https://openai.com/research).
-</citations_format>
-
-
 <critical_reminders>
 - **Clarification First**: ALWAYS clarify unclear/missing/ambiguous requirements BEFORE starting work - never assume or guess
-- **Web search citations**: When you use web_search (or synthesize subagent results that used it), you MUST output the `<citations>` block and [Title](url) links as specified in citations_format so citations display for the user.
 {subagent_reminder}- Skill First: Always load the relevant skill before starting **complex** tasks.
 - Progressive Loading: Load resources incrementally as referenced in skills
 - Output Files: Final deliverables must be in `/mnt/user-data/outputs`
@@ -341,7 +315,6 @@ def apply_prompt_template(subagent_enabled: bool = False) -> str:
     # Add subagent reminder to critical_reminders if enabled
     subagent_reminder = (
         "- **Orchestrator Mode**: You are a task orchestrator - decompose complex tasks into parallel sub-tasks and launch multiple subagents simultaneously. Synthesize results, don't execute directly.\n"
-        "- **Citations when synthesizing**: When you synthesize subagent results that used web search or cite sources, you MUST include a consolidated `<citations>` block (JSONL format) and use [Title](url) markdown links in your response so citations display correctly.\n"
         if subagent_enabled
         else ""
     )

backend/src/gateway/routers/artifacts.py

@@ -1,12 +1,10 @@
-import json
 import mimetypes
-import re
 import zipfile
 from pathlib import Path
 from urllib.parse import quote
 
-from fastapi import APIRouter, HTTPException, Request, Response
+from fastapi import APIRouter, HTTPException, Request
-from fastapi.responses import FileResponse, HTMLResponse, PlainTextResponse
+from fastapi.responses import FileResponse, HTMLResponse, PlainTextResponse, Response
 
 from src.gateway.path_utils import resolve_thread_virtual_path
 
@@ -24,40 +22,6 @@ def is_text_file_by_content(path: Path, sample_size: int = 8192) -> bool:
         return False
 
 
-def _extract_citation_urls(content: str) -> set[str]:
-    """Extract URLs from <citations> JSONL blocks. Format must match frontend core/citations/utils.ts."""
-    urls: set[str] = set()
-    for match in re.finditer(r"<citations>([\s\S]*?)</citations>", content):
-        for line in match.group(1).split("\n"):
-            line = line.strip()
-            if line.startswith("{"):
-                try:
-                    obj = json.loads(line)
-                    if "url" in obj:
-                        urls.add(obj["url"])
-                except (json.JSONDecodeError, ValueError):
-                    pass
-    return urls
-
-
-def remove_citations_block(content: str) -> str:
-    """Remove ALL citations from markdown (blocks, [cite-N], and citation links). Used for downloads."""
-    if not content:
-        return content
-
-    citation_urls = _extract_citation_urls(content)
-
-    result = re.sub(r"<citations>[\s\S]*?</citations>", "", content)
-    if "<citations>" in result:
-        result = re.sub(r"<citations>[\s\S]*$", "", result)
-    result = re.sub(r"\[cite-\d+\]", "", result)
-
-    for url in citation_urls:
-        result = re.sub(rf"\[[^\]]+\]\({re.escape(url)}\)", "", result)
-
-    return re.sub(r"\n{3,}", "\n\n", result).strip()
-
-
 def _extract_file_from_skill_archive(zip_path: Path, internal_path: str) -> bytes | None:
     """Extract a file from a .skill ZIP archive.
 
@@ -173,23 +137,8 @@ async def get_artifact(thread_id: str, path: str, request: Request) -> FileRespo
     # Encode filename for Content-Disposition header (RFC 5987)
     encoded_filename = quote(actual_path.name)
 
-    # Check if this is a markdown file that might contain citations
-    is_markdown = mime_type == "text/markdown" or actual_path.suffix.lower() in [".md", ".markdown"]
-    
     # if `download` query parameter is true, return the file as a download
     if request.query_params.get("download"):
-        # For markdown files, remove citations block before download
-        if is_markdown:
-            content = actual_path.read_text()
-            clean_content = remove_citations_block(content)
-            return Response(
-                content=clean_content.encode("utf-8"),
-                media_type="text/markdown",
-                headers={
-                    "Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}",
-                    "Content-Type": "text/markdown; charset=utf-8"
-                }
-            )
         return FileResponse(path=actual_path, filename=actual_path.name, media_type=mime_type, headers={"Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}"})
 
     if mime_type and mime_type == "text/html":

backend/src/subagents/builtins/general_purpose.py

@@ -24,21 +24,10 @@ Do NOT use for simple, single-step operations.""",
 - Do NOT ask for clarification - work with the information provided
 </guidelines>
 
-<citations_format>
-If you used web_search (or similar) and cite sources, ALWAYS include citations in your output:
-1. Start with a `<citations>` block in JSONL format listing all sources (one JSON object per line)
-2. In content, use FULL markdown link format: [Short Title](full_url)
-- Every citation MUST be a complete markdown link with URL: [Title](https://...)
-- Example block:
-<citations>
-{"id": "cite-1", "title": "...", "url": "https://...", "snippet": "..."}
-</citations>
-</citations_format>
-
 <output_format>
 When you complete the task, provide:
 1. A brief summary of what was accomplished
-2. Key findings or results (with citation links when from web search)
+2. Key findings or results
 3. Any relevant file paths, data, or artifacts created
 4. Issues encountered (if any)
 </output_format>

docs/CODE_CHANGE_SUMMARY_BY_FILE.md

@@ -0,0 +1,939 @@
+# 代码更改总结（按文件 diff，细到每一行）
+
+基于 `git diff HEAD` 的完整 diff，按文件列出所有变更。删除/新增文件单独说明。
+
+---
+
+## 一、后端
+
+### 1. `backend/CLAUDE.md`
+
+```diff
+@@ -156,7 +156,7 @@ FastAPI application on port 8001 with health check at `GET /health`.
+ | **Skills** (`/api/skills`) | `GET /` - list skills; `GET /{name}` - details; `PUT /{name}` - update enabled; `POST /install` - install from .skill archive |
+ | **Memory** (`/api/memory`) | `GET /` - memory data; `POST /reload` - force reload; `GET /config` - config; `GET /status` - config + data |
+ | **Uploads** (`/api/threads/{id}/uploads`) | `POST /` - upload files (auto-converts PDF/PPT/Excel/Word); `GET /list` - list; `DELETE /{filename}` - delete |
+-| **Artifacts** (`/api/threads/{id}/artifacts`) | `GET /{path}` - serve artifacts; `?download=true` for download with citation removal |
++| **Artifacts** (`/api/threads/{id}/artifacts`) | `GET /{path}` - serve artifacts; `?download=true` for file download |
+
+ Proxied through nginx: `/api/langgraph/*` → LangGraph, all other `/api/*` → Gateway.
+```
+
+- **第 159 行**：表格中 Artifacts 描述由「download with citation removal」改为「file download」。
+
+---
+
+### 2. `backend/src/agents/lead_agent/prompt.py`
+
+```diff
+@@ -240,34 +240,8 @@ You have access to skills that provide optimized workflows for specific tasks. E
+ - Action-Oriented: Focus on delivering results, not explaining processes
+ </response_style>
+ 
+-<citations_format>
+-After web_search, ALWAYS include citations in your output:
+-
+-1. Start with a `<citations>` block in JSONL format listing all sources
+-2. In content, use FULL markdown link format: [Short Title](full_url)
+-
+-**CRITICAL - Citation Link Format:**
+-- CORRECT: `[TechCrunch](https://techcrunch.com/ai-trends)` - full markdown link with URL
+-- WRONG: `[arXiv:2502.19166]` - missing URL, will NOT render as link
+-- WRONG: `[Source]` - missing URL, will NOT render as link
+-
+-**Rules:**
+-- Every citation MUST be a complete markdown link with URL: `[Title](https://...)`
+-- Write content naturally, add citation link at end of sentence/paragraph
+-- NEVER use bare brackets like `[arXiv:xxx]` or `[Source]` without URL
+-
+-**Example:**
+-<citations>
+-{{"id": "cite-1", "title": "AI Trends 2026", "url": "https://techcrunch.com/ai-trends", "snippet": "Tech industry predictions"}}
+-{{"id": "cite-2", "title": "OpenAI Research", "url": "https://openai.com/research", "snippet": "Latest AI research developments"}}
+-</citations>
+-The key AI trends for 2026 include enhanced reasoning capabilities and multimodal integration [TechCrunch](https://techcrunch.com/ai-trends). Recent breakthroughs in language models have also accelerated progress [OpenAI](https://openai.com/research).
+-</citations_format>
+-
+-
+ <critical_reminders>
+ - **Clarification First**: ALWAYS clarify unclear/missing/ambiguous requirements BEFORE starting work - never assume or guess
+-- **Web search citations**: When you use web_search (or synthesize subagent results that used it), you MUST output the `<citations>` block and [Title](url) links as specified in citations_format so citations display for the user.
+ {subagent_reminder}- Skill First: Always load the relevant skill before starting **complex** tasks.
+```
+
+```diff
+@@ -341,7 +315,6 @@ def apply_prompt_template(subagent_enabled: bool = False) -> str:
+     # Add subagent reminder to critical_reminders if enabled
+     subagent_reminder = (
+         "- **Orchestrator Mode**: You are a task orchestrator - decompose complex tasks into parallel sub-tasks and launch multiple subagents simultaneously. Synthesize results, don't execute directly.\n"
+-        "- **Citations when synthesizing**: When you synthesize subagent results that used web search or cite sources, you MUST include a consolidated `<citations>` block (JSONL format) and use [Title](url) markdown links in your response so citations display correctly.\n"
+         if subagent_enabled
+         else ""
+     )
+```
+
+- **删除**：`<citations_format>...</citations_format>` 整段（原约 243–266 行）、critical_reminders 中「Web search citations」一条、`apply_prompt_template` 中「Citations when synthesizing」一行。
+
+---
+
+### 3. `backend/src/gateway/routers/artifacts.py`
+
+```diff
+@@ -1,12 +1,10 @@
+-import json
+ import mimetypes
+-import re
+ import zipfile
+ from pathlib import Path
+ from urllib.parse import quote
+ 
+-from fastapi import APIRouter, HTTPException, Request, Response
+-from fastapi.responses import FileResponse, HTMLResponse, PlainTextResponse
++from fastapi import APIRouter, HTTPException, Request
++from fastapi.responses import FileResponse, HTMLResponse, PlainTextResponse, Response
+ 
+ from src.gateway.path_utils import resolve_thread_virtual_path
+```
+
+- **第 1 行**：删除 `import json`。
+- **第 3 行**：删除 `import re`。
+- **第 6–7 行**：`fastapi` 中去掉 `Response`；`fastapi.responses` 中增加 `Response`（保留二进制 inline 返回用）。
+
+```diff
+@@ -24,40 +22,6 @@ def is_text_file_by_content(path: Path, sample_size: int = 8192) -> bool:
+         return False
+ 
+ 
+-def _extract_citation_urls(content: str) -> set[str]:
+-    """Extract URLs from <citations> JSONL blocks. Format must match frontend core/citations/utils.ts."""
+-    urls: set[str] = set()
+-    for match in re.finditer(r"<citations>([\s\S]*?)</citations>", content):
+-        for line in match.group(1).split("\n"):
+-            line = line.strip()
+-            if line.startswith("{"):
+-                try:
+-                    obj = json.loads(line)
+-                    if "url" in obj:
+-                        urls.add(obj["url"])
+-                except (json.JSONDecodeError, ValueError):
+-                    pass
+-    return urls
+-
+-
+-def remove_citations_block(content: str) -> str:
+-    """Remove ALL citations from markdown (blocks, [cite-N], and citation links). Used for downloads."""
+-    if not content:
+-        return content
+-
+-    citation_urls = _extract_citation_urls(content)
+-
+-    result = re.sub(r"<citations>[\s\S]*?</citations>", "", content)
+-    if "<citations>" in result:
+-        result = re.sub(r"<citations>[\s\S]*$", "", result)
+-    result = re.sub(r"\[cite-\d+\]", "", result)
+-
+-    for url in citation_urls:
+-        result = re.sub(rf"\[[^\]]+\]\({re.escape(url)}\)", "", result)
+-
+-    return re.sub(r"\n{3,}", "\n\n", result).strip()
+-
+-
+ def _extract_file_from_skill_archive(zip_path: Path, internal_path: str) -> bytes | None:
+```
+
+- **删除**：`_extract_citation_urls`、`remove_citations_block` 两个函数（约 25–62 行）。
+
+```diff
+@@ -172,24 +136,9 @@ async def get_artifact(thread_id: str, path: str, request: Request) -> FileRespo
+ 
+     # Encode filename for Content-Disposition header (RFC 5987)
+     encoded_filename = quote(actual_path.name)
+-    
+-    # Check if this is a markdown file that might contain citations
+-    is_markdown = mime_type == "text/markdown" or actual_path.suffix.lower() in [".md", ".markdown"]
+-    
++
+     # if `download` query parameter is true, return the file as a download
+     if request.query_params.get("download"):
+-        # For markdown files, remove citations block before download
+-        if is_markdown:
+-            content = actual_path.read_text()
+-            clean_content = remove_citations_block(content)
+-            return Response(
+-                content=clean_content.encode("utf-8"),
+-                media_type="text/markdown",
+-                headers={
+-                    "Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}",
+-                    "Content-Type": "text/markdown; charset=utf-8"
+-                }
+-            )
+         return FileResponse(path=actual_path, filename=actual_path.name, media_type=mime_type, headers={"Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}"})
+ 
+     if mime_type and mime_type == "text/html":
+```
+
+- **删除**：`is_markdown` 判断及「markdown 时读文件 + remove_citations_block + Response」分支；download 时统一走 `FileResponse`。
+
+---
+
+### 4. `backend/src/subagents/builtins/general_purpose.py`
+
+```diff
+@@ -24,21 +24,10 @@ Do NOT use for simple, single-step operations.""",
+ - Do NOT ask for clarification - work with the information provided
+ </guidelines>
+ 
+-<citations_format>
+-If you used web_search (or similar) and cite sources, ALWAYS include citations in your output:
+-1. Start with a `<citations>` block in JSONL format listing all sources (one JSON object per line)
+-2. In content, use FULL markdown link format: [Short Title](full_url)
+-- Every citation MUST be a complete markdown link with URL: [Title](https://...)
+-- Example block:
+-<citations>
+-{"id": "cite-1", "title": "...", "url": "https://...", "snippet": "..."}
+-</citations>
+-</citations_format>
+-
+ <output_format>
+ When you complete the task, provide:
+ 1. A brief summary of what was accomplished
+-2. Key findings or results (with citation links when from web search)
++2. Key findings or results
+ 3. Any relevant file paths, data, or artifacts created
+ 4. Issues encountered (if any)
+ </output_format>
+```
+
+- **删除**：`<citations_format>...</citations_format>` 整段。
+- **第 40 行**：第 2 条由「Key findings or results (with citation links when from web search)」改为「Key findings or results」。
+
+---
+
+## 二、前端文档与工具
+
+### 5. `frontend/AGENTS.md`
+
+```diff
+@@ -49,7 +49,6 @@ src/
+ ├── core/                   # Core business logic
+ │   ├── api/                # API client & data fetching
+ │   ├── artifacts/          # Artifact management
+-│   ├── citations/          # Citation handling
+ │   ├── config/              # App configuration
+ │   ├── i18n/               # Internationalization
+```
+
+- **第 52 行**：删除目录树中的 `citations/` 一行。
+
+---
+
+### 6. `frontend/CLAUDE.md`
+
+```diff
+@@ -30,7 +30,7 @@ Frontend (Next.js) ──▶ LangGraph SDK ──▶ LangGraph Backend (lead_age
+                                               └── Tools & Skills
+ ```
+ 
+-The frontend is a stateful chat application. Users create **threads** (conversations), send messages, and receive streamed AI responses. The backend orchestrates agents that can produce **artifacts** (files/code), **todos**, and **citations**.
++The frontend is a stateful chat application. Users create **threads** (conversations), send messages, and receive streamed AI responses. The backend orchestrates agents that can produce **artifacts** (files/code) and **todos**.
+ 
+ ### Source Layout (`src/`)
+```
+
+- **第 33 行**：「and **citations**」删除。
+
+---
+
+### 7. `frontend/README.md`
+
+```diff
+@@ -89,7 +89,6 @@ src/
+ ├── core/                   # Core business logic
+ │   ├── api/                # API client & data fetching
+ │   ├── artifacts/          # Artifact management
+-│   ├── citations/          # Citation handling
+ │   ├── config/              # App configuration
+ │   ├── i18n/               # Internationalization
+```
+
+- **第 92 行**：删除目录树中的 `citations/` 一行。
+
+---
+
+### 8. `frontend/src/lib/utils.ts`
+
+```diff
+@@ -8,5 +8,5 @@ export function cn(...inputs: ClassValue[]) {
+ /** Shared class for external links (underline by default). */
+ export const externalLinkClass =
+   "text-primary underline underline-offset-2 hover:no-underline";
+-/** For streaming / loading state when link may be a citation (no underline). */
++/** Link style without underline by default (e.g. for streaming/loading). */
+ export const externalLinkClassNoUnderline = "text-primary hover:underline";
+```
+
+- **第 11 行**：仅注释修改，导出值未变。
+
+---
+
+## 三、前端组件
+
+### 9. `frontend/src/components/workspace/artifacts/artifact-file-detail.tsx`
+
+```diff
+@@ -8,7 +8,6 @@ import {
+   SquareArrowOutUpRightIcon,
+   XIcon,
+ } from "lucide-react";
+-import * as React from "react";
+ import { useCallback, useEffect, useMemo, useState } from "react";
+ ...
+@@ -21,7 +20,6 @@ import (
+   ArtifactHeader,
+   ArtifactTitle,
+ } from "@/components/ai-elements/artifact";
+-import { createCitationMarkdownComponents } from "@/components/ai-elements/inline-citation";
+ import { Select, SelectItem } from "@/components/ui/select";
+ ...
+@@ -33,12 +31,6 @@ import { ToggleGroup, ToggleGroupItem } from "@/components/ui/toggle-group";
+ import { CodeEditor } from "@/components/workspace/code-editor";
+ import { useArtifactContent } from "@/core/artifacts/hooks";
+ import { urlOfArtifact } from "@/core/artifacts/utils";
+-import type { Citation } from "@/core/citations";
+-import {
+-  contentWithoutCitationsFromParsed,
+-  removeAllCitations,
+-  useParsedCitations,
+-} from "@/core/citations";
+ import { useI18n } from "@/core/i18n/hooks";
+ ...
+@@ -48,9 +40,6 @@ import { cn } from "@/lib/utils";
+ 
+ import { Tooltip } from "../tooltip";
+ 
+-import { SafeCitationContent } from "../messages/safe-citation-content";
+-import { useThread } from "../messages/context";
+-
+ import { useArtifacts } from "./context";
+```
+
+```diff
+@@ -92,22 +81,13 @@ export function ArtifactFileDetail({
+   const previewable = useMemo(() => {
+     return (language === "html" && !isWriteFile) || language === "markdown";
+   }, [isWriteFile, language]);
+-  const { thread } = useThread();
+   const { content } = useArtifactContent({
+     threadId,
+     filepath: filepathFromProps,
+     enabled: isCodeFile && !isWriteFile,
+   });
+ 
+-  const parsed = useParsedCitations(
+-    language === "markdown" ? (content ?? "") : "",
+-  );
+-  const cleanContent =
+-    language === "markdown" && content ? parsed.cleanContent : (content ?? "");
+-  const contentWithoutCitations =
+-    language === "markdown" && content
+-      ? contentWithoutCitationsFromParsed(parsed)
+-      : (content ?? "");
++  const displayContent = content ?? "";
+ 
+   const [viewMode, setViewMode] = useState<"code" | "preview">("code");
+```
+
+```diff
+@@ -219,7 +199,7 @@ export function ArtifactFileDetail({
+                 disabled={!content}
+                 onClick={async () => {
+                   try {
+-                    await navigator.clipboard.writeText(contentWithoutCitations ?? "");
++                    await navigator.clipboard.writeText(displayContent ?? "");
+                     toast.success(t.clipboard.copiedToClipboard);
+ ...
+@@ -255,27 +235,17 @@ export function ArtifactFileDetail({
+           viewMode === "preview" &&
+           language === "markdown" &&
+           content && (
+-            <SafeCitationContent
+-              content={content}
+-              isLoading={thread.isLoading}
+-              rehypePlugins={streamdownPlugins.rehypePlugins}
+-              className="flex size-full items-center justify-center p-4 my-0"
+-              renderBody={(p) => (
+-                <ArtifactFilePreview
+-                  filepath={filepath}
+-                  threadId={threadId}
+-                  content={content}
+-                  language={language ?? "text"}
+-                  cleanContent={p.cleanContent}
+-                  citationMap={p.citationMap}
+-                />
+-              )}
++            <ArtifactFilePreview
++              filepath={filepath}
++              threadId={threadId}
++              content={displayContent}
++              language={language ?? "text"}
+             />
+           )}
+         {isCodeFile && viewMode === "code" && (
+           <CodeEditor
+             className="size-full resize-none rounded-none border-none"
+-            value={cleanContent ?? ""}
++            value={displayContent ?? ""}
+             readonly
+           />
+         )}
+```
+
+```diff
+@@ -295,29 +265,17 @@ export function ArtifactFilePreview({
+   threadId,
+   content,
+   language,
+-  cleanContent,
+-  citationMap,
+ }: {
+   filepath: string;
+   threadId: string;
+   content: string;
+   language: string;
+-  cleanContent: string;
+-  citationMap: Map<string, Citation>;
+ }) {
+   if (language === "markdown") {
+-    const components = createCitationMarkdownComponents({
+-      citationMap,
+-      syntheticExternal: true,
+-    });
+     return (
+       <div className="size-full px-4">
+-        <Streamdown
+-          className="size-full"
+-          {...streamdownPlugins}
+-          components={components}
+-        >
+-          {cleanContent ?? ""}
++        <Streamdown className="size-full" {...streamdownPlugins}>
++          {content ?? ""}
+         </Streamdown>
+       </div>
+     );
+```
+
+- 删除：React 命名空间、inline-citation、core/citations、SafeCitationContent、useThread；parsed/cleanContent/contentWithoutCitations 及引用解析逻辑。
+- 新增：`displayContent = content ?? ""`；预览与复制、CodeEditor 均使用 `displayContent`；`ArtifactFilePreview` 仅保留 `content`/`language` 等，去掉 `cleanContent`/`citationMap` 与 `createCitationMarkdownComponents`。
+
+---
+
+### 10. `frontend/src/components/workspace/messages/message-group.tsx`
+
+```diff
+@@ -39,9 +39,7 @@ import { useArtifacts } from "../artifacts";
+ import { FlipDisplay } from "../flip-display";
+ import { Tooltip } from "../tooltip";
+ 
+-import { useThread } from "./context";
+-
+-import { SafeCitationContent } from "./safe-citation-content";
++import { MarkdownContent } from "./markdown-content";
+ 
+ export function MessageGroup({
+```
+
+```diff
+@@ -120,7 +118,7 @@ export function MessageGroup({
+                 <ChainOfThoughtStep
+                   key={step.id}
+                   label={
+-                    <SafeCitationContent
++                    <MarkdownContent
+                       content={step.reasoning ?? ""}
+                       isLoading={isLoading}
+                       rehypePlugins={rehypePlugins}
+@@ -128,12 +126,7 @@ export function MessageGroup({
+                   }
+                 ></ChainOfThoughtStep>
+               ) : (
+-                <ToolCall
+-                  key={step.id}
+-                  {...step}
+-                  isLoading={isLoading}
+-                  rehypePlugins={rehypePlugins}
+-                />
++                <ToolCall key={step.id} {...step} isLoading={isLoading} />
+               ),
+             )}
+           {lastToolCallStep && (
+@@ -143,7 +136,6 @@ export function MessageGroup({
+                 {...lastToolCallStep}
+                 isLast={true}
+                 isLoading={isLoading}
+-                rehypePlugins={rehypePlugins}
+               />
+             </FlipDisplay>
+           )}
+@@ -178,7 +170,7 @@ export function MessageGroup({
+               <ChainOfThoughtStep
+                 key={lastReasoningStep.id}
+                 label={
+-                  <SafeCitationContent
++                  <MarkdownContent
+                     content={lastReasoningStep.reasoning ?? ""}
+                     isLoading={isLoading}
+                     rehypePlugins={rehypePlugins}
+@@ -201,7 +193,6 @@ function ToolCall({
+   result,
+   isLast = false,
+   isLoading = false,
+-  rehypePlugins,
+ }: {
+   id?: string;
+   messageId?: string;
+@@ -210,15 +201,10 @@ function ToolCall({
+   result?: string | Record<string, unknown>;
+   isLast?: boolean;
+   isLoading?: boolean;
+-  rehypePlugins: ReturnType<typeof useRehypeSplitWordsIntoSpans>;
+ }) {
+   const { t } = useI18n();
+   const { setOpen, autoOpen, autoSelect, selectedArtifact, select } =
+     useArtifacts();
+-  const { thread } = useThread();
+-  const threadIsLoading = thread.isLoading;
+-
+-  const fileContent = typeof args.content === "string" ? args.content : "";
+ 
+   if (name === "web_search") {
+```
+
+```diff
+@@ -364,42 +350,27 @@ function ToolCall({
+       }, 100);
+     }
+ 
+-    const isMarkdown =
+-      path?.toLowerCase().endsWith(".md") ||
+-      path?.toLowerCase().endsWith(".markdown");
+-
+     return (
+-      <>
+-        <ChainOfThoughtStep
+-          key={id}
+-          className="cursor-pointer"
+-          label={description}
+-          icon={NotebookPenIcon}
+-          onClick={() => {
+-            select(
+-              new URL(
+-                `write-file:${path}?message_id=${messageId}&tool_call_id=${id}`,
+-              ).toString(),
+-            );
+-            setOpen(true);
+-          }}
+-        >
+-          {path && (
+-            <ChainOfThoughtSearchResult className="cursor-pointer">
+-              {path}
+-            </ChainOfThoughtSearchResult>
+-          )}
+-        </ChainOfThoughtStep>
+-        {isMarkdown && (
+-          <SafeCitationContent
+-            content={fileContent}
+-            isLoading={threadIsLoading && isLast}
+-            rehypePlugins={rehypePlugins}
+-            loadingOnly
+-            className="mt-2 ml-8"
+-          />
++      <ChainOfThoughtStep
++        key={id}
++        className="cursor-pointer"
++        label={description}
++        icon={NotebookPenIcon}
++        onClick={() => {
++          select(
++            new URL(
++              `write-file:${path}?message_id=${messageId}&tool_call_id=${id}`,
++            ).toString(),
++          );
++          setOpen(true);
++        }}
++      >
++        {path && (
++          <ChainOfThoughtSearchResult className="cursor-pointer">
++            {path}
++          </ChainOfThoughtSearchResult>
+         )}
+-      </>
++      </ChainOfThoughtStep>
+     );
+   } else if (name === "bash") {
+```
+
+- 两处 `SafeCitationContent` → `MarkdownContent`；ToolCall 去掉 `rehypePlugins` 及内部 `useThread`/`fileContent`；write_file 分支去掉 markdown 预览块（`isMarkdown` + `SafeCitationContent`），仅保留 `ChainOfThoughtStep` + path。
+
+---
+
+### 11. `frontend/src/components/workspace/messages/message-list-item.tsx`
+
+```diff
+@@ -12,7 +12,6 @@ import {
+ } from "@/components/ai-elements/message";
+ import { Badge } from "@/components/ui/badge";
+ import { resolveArtifactURL } from "@/core/artifacts/utils";
+-import { removeAllCitations } from "@/core/citations";
+ import {
+   extractContentFromMessage,
+   extractReasoningContentFromMessage,
+@@ -24,7 +23,7 @@ import { humanMessagePlugins } from "@/core/streamdown";
+ import { cn } from "@/lib/utils";
+ 
+ import { CopyButton } from "../copy-button";
+-import { SafeCitationContent } from "./safe-citation-content";
++import { MarkdownContent } from "./markdown-content";
+ ...
+@@ -54,11 +53,11 @@ export function MessageListItem({
+       >
+         <div className="flex gap-1">
+           <CopyButton
+-            clipboardData={removeAllCitations(
++            clipboardData={
+               extractContentFromMessage(message) ??
+               extractReasoningContentFromMessage(message) ??
+               ""
+-            )}
++            }
+           />
+         </div>
+       </MessageToolbar>
+@@ -154,7 +153,7 @@ function MessageContent_({
+   return (
+     <AIElementMessageContent className={className}>
+       {filesList}
+-      <SafeCitationContent
++      <MarkdownContent
+         content={contentToParse}
+         isLoading={isLoading}
+         rehypePlugins={[...rehypePlugins, [rehypeKatex, { output: "html" }]]}
+```
+
+- 删除 `removeAllCitations` 与 `SafeCitationContent` 引用；复制改为原始内容；渲染改为 `MarkdownContent`。
+
+---
+
+### 12. `frontend/src/components/workspace/messages/message-list.tsx`
+
+```diff
+@@ -26,7 +26,7 @@ import { StreamingIndicator } from "../streaming-indicator";
+ 
+ import { MessageGroup } from "./message-group";
+ import { MessageListItem } from "./message-list-item";
+-import { SafeCitationContent } from "./safe-citation-content";
++import { MarkdownContent } from "./markdown-content";
+ import { MessageListSkeleton } from "./skeleton";
+ ...
+@@ -69,7 +69,7 @@ export function MessageList({
+             const message = group.messages[0];
+             if (message && hasContent(message)) {
+               return (
+-                <SafeCitationContent
++                <MarkdownContent
+                   key={group.id}
+                   content={extractContentFromMessage(message)}
+                   isLoading={thread.isLoading}
+@@ -89,7 +89,7 @@ export function MessageList({
+             return (
+               <div className="w-full" key={group.id}>
+                 {group.messages[0] && hasContent(group.messages[0]) && (
+-                  <SafeCitationContent
++                  <MarkdownContent
+                     content={extractContentFromMessage(group.messages[0])}
+                     isLoading={thread.isLoading}
+                     rehypePlugins={rehypePlugins}
+```
+
+- 三处：import 与两处渲染均由 `SafeCitationContent` 改为 `MarkdownContent`，props 不变。
+
+---
+
+### 13. `frontend/src/components/workspace/messages/subtask-card.tsx`
+
+```diff
+@@ -29,7 +29,7 @@ import { cn } from "@/lib/utils";
+ 
+ import { FlipDisplay } from "../flip-display";
+ 
+-import { SafeCitationContent } from "./safe-citation-content";
++import { MarkdownContent } from "./markdown-content";
+ ...
+@@ -153,7 +153,7 @@ export function SubtaskCard({
+               <ChainOfThoughtStep
+                 label={
+                   task.result ? (
+-                    <SafeCitationContent
++                    <MarkdownContent
+                       content={task.result}
+                       isLoading={false}
+                       rehypePlugins={rehypePlugins}
+```
+
+- import 与一处渲染：`SafeCitationContent` → `MarkdownContent`。
+
+---
+
+### 14. 新增 `frontend/src/components/workspace/messages/markdown-content.tsx`
+
+（当前工作区新增，未在 git 中）
+
+```ts
+"use client";
+
+import type { ImgHTMLAttributes } from "react";
+import type { ReactNode } from "react";
+
+import {
+  MessageResponse,
+  type MessageResponseProps,
+} from "@/components/ai-elements/message";
+import { streamdownPlugins } from "@/core/streamdown";
+
+export type MarkdownContentProps = {
+  content: string;
+  isLoading: boolean;
+  rehypePlugins: MessageResponseProps["rehypePlugins"];
+  className?: string;
+  remarkPlugins?: MessageResponseProps["remarkPlugins"];
+  isHuman?: boolean;
+  img?: (props: ImgHTMLAttributes<HTMLImageElement> & { threadId?: string; maxWidth?: string }) => ReactNode;
+};
+
+/** Renders markdown content. */
+export function MarkdownContent({
+  content,
+  rehypePlugins,
+  className,
+  remarkPlugins = streamdownPlugins.remarkPlugins,
+  img,
+}: MarkdownContentProps) {
+  if (!content) return null;
+  const components = img ? { img } : undefined;
+  return (
+    <MessageResponse
+      className={className}
+      remarkPlugins={remarkPlugins}
+      rehypePlugins={rehypePlugins}
+      components={components}
+    >
+      {content}
+    </MessageResponse>
+  );
+}
+```
+
+- 纯 Markdown 渲染组件，无引用解析或 loading 占位逻辑。
+
+---
+
+### 15. 删除 `frontend/src/components/workspace/messages/safe-citation-content.tsx`
+
+- 原约 85 行；提供引用解析、loading、renderBody/loadingOnly、cleanContent/citationMap。已由 `MarkdownContent` 替代，整文件删除。
+
+---
+
+### 16. 删除 `frontend/src/components/ai-elements/inline-citation.tsx`
+
+- 原约 289 行；提供 `createCitationMarkdownComponents` 等，用于将 `[cite-N]`/URL 渲染为可点击引用。仅被 artifact 预览使用，已移除后整文件删除。
+
+---
+
+## 四、前端 core
+
+### 17. 删除 `frontend/src/core/citations/index.ts`
+
+- 原 13 行，导出：`contentWithoutCitationsFromParsed`、`extractDomainFromUrl`、`isExternalUrl`、`parseCitations`、`removeAllCitations`、`shouldShowCitationLoading`、`syntheticCitationFromLink`、`useParsedCitations`、类型 `Citation`/`ParseCitationsResult`/`UseParsedCitationsResult`。整文件删除。
+
+---
+
+### 18. 删除 `frontend/src/core/citations/use-parsed-citations.ts`
+
+- 原 28 行，`useParsedCitations(content)` 与 `UseParsedCitationsResult`。整文件删除。
+
+---
+
+### 19. 删除 `frontend/src/core/citations/utils.ts`
+
+- 原 226 行，解析 `<citations>`/`[cite-N]`、buildCitationMap、removeAllCitations、contentWithoutCitationsFromParsed 等。整文件删除。
+
+---
+
+### 20. `frontend/src/core/i18n/locales/types.ts`
+
+```diff
+@@ -115,12 +115,6 @@ export interface Translations {
+     startConversation: string;
+   };
+ 
+-  // Citations
+-  citations: {
+-    loadingCitations: string;
+-    loadingCitationsWithCount: (count: number) => string;
+-  };
+-
+   // Chats
+   chats: {
+```
+
+- 删除 `Translations.citations` 及其两个字段。
+
+---
+
+### 21. `frontend/src/core/i18n/locales/zh-CN.ts`
+
+```diff
+@@ -164,12 +164,6 @@ export const zhCN: Translations = {
+     startConversation: "开始新的对话以查看消息",
+   },
+ 
+-  // Citations
+-  citations: {
+-    loadingCitations: "正在整理引用...",
+-    loadingCitationsWithCount: (count: number) => `正在整理 ${count} 个引用...`,
+-  },
+-
+   // Chats
+   chats: {
+```
+
+- 删除 `citations` 命名空间。
+
+---
+
+### 22. `frontend/src/core/i18n/locales/en-US.ts`
+
+```diff
+@@ -167,13 +167,6 @@ export const enUS: Translations = {
+     startConversation: "Start a conversation to see messages here",
+   },
+ 
+-  // Citations
+-  citations: {
+-    loadingCitations: "Organizing citations...",
+-    loadingCitationsWithCount: (count: number) =>
+-      `Organizing ${count} citation${count === 1 ? "" : "s"}...`,
+-  },
+-
+   // Chats
+   chats: {
+```
+
+- 删除 `citations` 命名空间。
+
+---
+
+## 五、技能与 Demo
+
+### 23. `skills/public/github-deep-research/SKILL.md`
+
+```diff
+@@ -147,5 +147,5 @@ Save report as: `research_{topic}_{YYYYMMDD}.md`
+ 3. **Triangulate claims** - 2+ independent sources
+ 4. **Note conflicting info** - Don't hide contradictions
+ 5. **Distinguish fact vs opinion** - Label speculation clearly
+-6. **Cite inline** - Reference sources near claims
++6. **Reference sources** - Add source references near claims where applicable
+ 7. **Update as you go** - Don't wait until end to synthesize
+```
+
+- 第 150 行：一条措辞修改。
+
+---
+
+### 24. `skills/public/market-analysis/SKILL.md`
+
+```diff
+@@ -15,7 +15,7 @@ This skill generates professional, consulting-grade market analysis reports in M
+ - Follow the **"Visual Anchor → Data Contrast → Integrated Analysis"** flow per sub-chapter
+ - Produce insights following the **"Data → User Psychology → Strategy Implication"** chain
+ - Embed pre-generated charts and construct comparison tables
+-- Generate inline citations formatted per **GB/T 7714-2015** standards
++- Include references formatted per **GB/T 7714-2015** where applicable
+ - Output reports entirely in Chinese with professional consulting tone
+ ...
+@@ -36,7 +36,7 @@ The skill expects the following inputs from the upstream agentic workflow:
+ | **Analysis Framework Outline** | Defines the logic flow and general topics for the report | Yes |
+ | **Data Summary** | The source of truth containing raw numbers and metrics | Yes |
+ | **Chart Files** | Local file paths for pre-generated chart images | Yes |
+-| **External Search Findings** | URLs and summaries for inline citations | Optional |
++| **External Search Findings** | URLs and summaries for inline references | Optional |
+ ...
+@@ -87,7 +87,7 @@ The report **MUST NOT** stop after the Conclusion — it **MUST** include Refere
+ - **Tone**: McKinsey/BCG — Authoritative, Objective, Professional
+ - **Language**: All headings and content strictly in **Chinese**
+ - **Number Formatting**: Use English commas for thousands separators (`1,000` not `1，000`)
+-- **Data Citation**: **Bold** important viewpoints and key numbers
++- **Data emphasis**: **Bold** important viewpoints and key numbers
+ ...
+@@ -109,11 +109,9 @@ Every insight must connect **Data → User Psychology → Strategy Implication**
+    treating male audiences only as a secondary gift-giving segment."
+ ```
+ 
+-### Citations & References
+-- **Inline**: Use `[\[Index\]](URL)` format (e.g., `[\[1\]](https://example.com)`)
+-- **Placement**: Append citations at the end of sentences using information from External Search Findings
+-- **Index Assignment**: Sequential starting from **1** based on order of appearance
+-- **References Section**: Formatted strictly per **GB/T 7714-2015**
++### References
++- **Inline**: Use markdown links for sources (e.g. `[Source Title](URL)`) when using External Search Findings
++- **References section**: Formatted strictly per **GB/T 7714-2015**
+ ...
+@@ -183,7 +181,7 @@ Before considering the report complete, verify:
+ - [ ] All headings are in Chinese with proper numbering (no "Chapter/Part/Section")
+ - [ ] Charts are embedded with `![Description](path)` syntax
+ - [ ] Numbers use English commas for thousands separators
+-- [ ] Inline citations use `[\[N\]](URL)` format
++- [ ] Inline references use markdown links where applicable
+ - [ ] References section follows GB/T 7714-2015
+```
+
+- 多处：核心能力、输入表、Data Citation、Citations & References 小节与检查项，改为「references / 引用」表述并去掉 `[\[N\]](URL)` 格式要求。
+
+---
+
+### 25. `frontend/public/demo/threads/.../user-data/outputs/research_deerflow_20260201.md`
+
+```diff
+@@ -1,12 +1,3 @@
+-<citations>
+-{"id": "cite-1", "title": "DeerFlow GitHub Repository", "url": "https://github.com/bytedance/deer-flow", "snippet": "..."}
+-...（共 7 条 JSONL）
+-</citations>
+ # DeerFlow Deep Research Report
+ 
+ - **Research Date:** 2026-02-01
+```
+
+- 删除文件开头的 `<citations>...</citations>` 整块（9 行），正文从 `# DeerFlow Deep Research Report` 开始。
+
+---
+
+### 26. `frontend/public/demo/threads/.../thread.json`
+
+- **主要变更**：某条 `write_file` 的 `args.content` 中，将原来的「`<citations>...\n</citations>\n# DeerFlow Deep Research Report\n\n...`」改为「`# DeerFlow Deep Research Report\n\n...`」，即去掉 `<citations>...</citations>` 块，保留其后全文。
+- **其他**：一处 `present_files` 的 `filepaths` 由单行数组改为多行格式；文件末尾增加/统一换行。
+- 消息顺序、结构及其他字段未改。
+
+---
+
+## 六、统计
+
+| 项目 | 数量 |
+|------|------|
+| 修改文件 | 18 |
+| 新增文件 | 1（markdown-content.tsx） |
+| 删除文件 | 5（safe-citation-content.tsx, inline-citation.tsx, core/citations/* 共 3 个） |
+| 总行数变化 | +62 / -894（diff stat） |
+
+以上为按文件、细到每一行 diff 的代码更改总结。

frontend/AGENTS.md

@@ -49,7 +49,6 @@ src/
 ├── core/                   # Core business logic
 │   ├── api/                # API client & data fetching
 │   ├── artifacts/          # Artifact management
-│   ├── citations/          # Citation handling
 │   ├── config/              # App configuration
 │   ├── i18n/               # Internationalization
 │   ├── mcp/                # MCP integration

frontend/CLAUDE.md

@@ -30,7 +30,7 @@ Frontend (Next.js) ──▶ LangGraph SDK ──▶ LangGraph Backend (lead_age
                                               └── Tools & Skills
 ```
 
-The frontend is a stateful chat application. Users create **threads** (conversations), send messages, and receive streamed AI responses. The backend orchestrates agents that can produce **artifacts** (files/code), **todos**, and **citations**.
+The frontend is a stateful chat application. Users create **threads** (conversations), send messages, and receive streamed AI responses. The backend orchestrates agents that can produce **artifacts** (files/code) and **todos**.
 
 ### Source Layout (`src/`)
 

frontend/README.md

@@ -89,7 +89,6 @@ src/
 ├── core/                   # Core business logic
 │   ├── api/                # API client & data fetching
 │   ├── artifacts/          # Artifact management
-│   ├── citations/          # Citation handling
 │   ├── config/              # App configuration
 │   ├── i18n/               # Internationalization
 │   ├── mcp/                # MCP integration

frontend/public/demo/threads/fe3f7974-1bcb-4a01-a950-79673baafefd/user-data/outputs/research_deerflow_20260201.md

@@ -1,12 +1,3 @@
-<citations>
-{"id": "cite-1", "title": "DeerFlow GitHub Repository", "url": "https://github.com/bytedance/deer-flow", "snippet": "Community-driven Deep Research framework combining language models with tools like web search, crawling, and Python execution"}
-{"id": "cite-2", "title": "Create Your Own Deep Research Agent with DeerFlow", "url": "https://thesequence.substack.com/p/the-sequence-engineering-661-create", "snippet": "Open-source multi-agent research automation framework developed by ByteDance"}
-{"id": "cite-3", "title": "DeerFlow: A Game-Changer for Automated Research and Content Creation", "url": "https://medium.com/@mingyang.heaven/deerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a", "snippet": "Open-source multi-agent framework revolutionizing research and content creation"}
-{"id": "cite-4", "title": "ByteDance DeerFlow - (Deep Research Agents with a LOCAL LLM!)", "url": "https://www.youtube.com/watch?v=Ui0ovCVDYGs", "snippet": "Video demonstration of DeerFlow capabilities and local LLM integration"}
-{"id": "cite-5", "title": "DeerFlow Official Website", "url": "https://deerflow.tech/", "snippet": "Official platform showcasing DeerFlow features, case studies, and architecture"}
-{"id": "cite-6", "title": "Navigating the Landscape of Deep Research Frameworks", "url": "https://www.oreateai.com/blog/navigating-the-landscape-of-deep-research-frameworks-a-comprehensive-comparison/0dc13e48eb8c756650112842c8d1a184", "snippet": "Comparative analysis of deep research frameworks including DeerFlow"}
-{"id": "cite-7", "title": "DeerFlow: Multi-Agent AI For Research Automation 2025", "url": "https://firexcore.com/blog/what-is-deerflow/", "snippet": "Overview of DeerFlow features and capabilities for research automation"}
-</citations>
 # DeerFlow Deep Research Report
 
 - **Research Date:** 2026-02-01

frontend/src/components/ai-elements/inline-citation.tsx

@@ -1,289 +0,0 @@
-"use client";
-
-import { Badge } from "@/components/ui/badge";
-import {
-  HoverCard,
-  HoverCardContent,
-  HoverCardTrigger,
-} from "@/components/ui/hover-card";
-import {
-  cn,
-  externalLinkClass,
-  externalLinkClassNoUnderline,
-} from "@/lib/utils";
-import { ExternalLinkIcon } from "lucide-react";
-import {
-  type AnchorHTMLAttributes,
-  type ComponentProps,
-  type ImgHTMLAttributes,
-  type ReactElement,
-  type ReactNode,
-  Children,
-} from "react";
-import type { Citation } from "@/core/citations";
-import {
-  extractDomainFromUrl,
-  isExternalUrl,
-  syntheticCitationFromLink,
-} from "@/core/citations";
-import { Shimmer } from "./shimmer";
-import { useI18n } from "@/core/i18n/hooks";
-
-type InlineCitationCardProps = ComponentProps<typeof HoverCard>;
-
-const InlineCitationCard = (props: InlineCitationCardProps) => (
-  <HoverCard closeDelay={0} openDelay={0} {...props} />
-);
-
-const InlineCitationCardBody = ({
-  className,
-  ...props
-}: ComponentProps<"div">) => (
-  <HoverCardContent className={cn("relative w-80 p-0", className)} {...props} />
-);
-
-const InlineCitationSource = ({
-  title,
-  url,
-  description,
-  className,
-  children,
-  ...props
-}: ComponentProps<"div"> & {
-  title?: string;
-  url?: string;
-  description?: string;
-}) => (
-  <div className={cn("space-y-1", className)} {...props}>
-    {title && (
-      <h4 className="truncate font-medium text-sm leading-tight">{title}</h4>
-    )}
-    {url && (
-      <p className="truncate break-all text-muted-foreground text-xs">{url}</p>
-    )}
-    {description && (
-      <p className="line-clamp-3 text-muted-foreground text-sm leading-relaxed">
-        {description}
-      </p>
-    )}
-    {children}
-  </div>
-);
-
-/**
- * Shared CitationLink component that renders a citation as a hover card badge
- * Used across message-list-item, artifact-file-detail, and message-group
- * 
- * When citation is provided, displays title and snippet from the citation.
- * When citation is omitted, falls back to displaying the domain name extracted from href.
- */
-export type CitationLinkProps = {
-  citation?: Citation;
-  href: string;
-  children: React.ReactNode;
-};
-
-export const CitationLink = ({
-  citation,
-  href,
-  children,
-}: CitationLinkProps) => {
-  const domain = extractDomainFromUrl(href);
-  
-  // Priority: citation.title > children (if meaningful) > domain
-  // - citation.title: from parsed <citations> block, most accurate
-  // - children: from markdown link text [Text](url), used when no citation data
-  // - domain: fallback when both above are unavailable
-  // Skip children if it's a generic placeholder like "Source"
-  const childrenText = typeof children === "string" ? children : null;
-  const isGenericText = childrenText === "Source" || childrenText === "来源";
-  const displayText = citation?.title || (!isGenericText && childrenText) || domain;
-
-  return (
-    <InlineCitationCard>
-      <HoverCardTrigger asChild>
-        <a
-          href={href}
-          target="_blank"
-          rel="noopener noreferrer"
-          className="inline-flex items-center"
-          onClick={(e) => e.stopPropagation()}
-        >
-          <Badge
-            variant="secondary"
-            className="hover:bg-secondary/80 mx-0.5 cursor-pointer gap-1 rounded-full px-2 py-0.5 text-xs font-normal"
-          >
-            {displayText}
-            <ExternalLinkIcon className="size-3" />
-          </Badge>
-        </a>
-      </HoverCardTrigger>
-      <InlineCitationCardBody>
-        <div className="p-3">
-          <InlineCitationSource
-            title={citation?.title || domain}
-            url={href}
-            description={citation?.snippet}
-          />
-          <a
-            href={href}
-            target="_blank"
-            rel="noopener noreferrer"
-            className="text-primary mt-2 inline-flex items-center gap-1 text-xs hover:underline"
-          >
-            Visit source
-            <ExternalLinkIcon className="size-3" />
-          </a>
-        </div>
-      </InlineCitationCardBody>
-    </InlineCitationCard>
-  );
-};
-
-/**
- * Renders a link with optional citation badge. Use in markdown components (message + artifact).
- * - citationMap: URL -> Citation; links in map render as CitationLink.
- * - isHuman: when true, never render as CitationLink (plain link).
- * - isLoadingCitations: when true and not human, non-citation links use no-underline style.
- * - syntheticExternal: when true, external URLs not in citationMap render as CitationLink with synthetic citation.
- */
-export type CitationAwareLinkProps = ComponentProps<"a"> & {
-  citationMap: Map<string, Citation>;
-  isHuman?: boolean;
-  isLoadingCitations?: boolean;
-  syntheticExternal?: boolean;
-};
-
-export const CitationAwareLink = ({
-  href,
-  children,
-  citationMap,
-  isHuman = false,
-  isLoadingCitations = false,
-  syntheticExternal = false,
-  className,
-  ...rest
-}: CitationAwareLinkProps) => {
-  if (!href) return <span>{children}</span>;
-
-  const citation = citationMap.get(href);
-
-  if (citation && !isHuman) {
-    return (
-      <CitationLink citation={citation} href={href}>
-        {children}
-      </CitationLink>
-    );
-  }
-
-  if (syntheticExternal && isExternalUrl(href)) {
-    const linkText =
-      typeof children === "string"
-        ? children
-        : String(Children.toArray(children).join("")).trim() || href;
-    return (
-      <CitationLink
-        citation={syntheticCitationFromLink(href, linkText)}
-        href={href}
-      >
-        {children}
-      </CitationLink>
-    );
-  }
-
-  const noUnderline = !isHuman && isLoadingCitations;
-  return (
-    <a
-      href={href}
-      target="_blank"
-      rel="noopener noreferrer"
-      className={cn(noUnderline ? externalLinkClassNoUnderline : externalLinkClass, className)}
-      {...rest}
-    >
-      {children}
-    </a>
-  );
-};
-
-/**
- * Options for creating markdown components that render links as citations.
- * Used by message list (all modes: Flash/Thinking/Pro/Ultra), artifact preview, and CoT.
- */
-export type CreateCitationMarkdownComponentsOptions = {
-  citationMap: Map<string, Citation>;
-  isHuman?: boolean;
-  isLoadingCitations?: boolean;
-  syntheticExternal?: boolean;
-  /** Optional custom img component (e.g. MessageImage with threadId). Omit for artifact. */
-  img?: (props: ImgHTMLAttributes<HTMLImageElement> & { threadId?: string; maxWidth?: string }) => ReactNode;
-};
-
-/**
- * Create markdown `components` (a, optional img) that use CitationAwareLink.
- * Reused across message-list-item (all modes), artifact-file-detail, and any CoT markdown.
- */
-export function createCitationMarkdownComponents(
-  options: CreateCitationMarkdownComponentsOptions,
-): {
-  a: (props: AnchorHTMLAttributes<HTMLAnchorElement>) => ReactElement;
-  img?: (props: ImgHTMLAttributes<HTMLImageElement> & { threadId?: string; maxWidth?: string }) => ReactNode;
-} {
-  const {
-    citationMap,
-    isHuman = false,
-    isLoadingCitations = false,
-    syntheticExternal = false,
-    img,
-  } = options;
-  const a = (props: AnchorHTMLAttributes<HTMLAnchorElement>) => (
-    <CitationAwareLink
-      {...props}
-      citationMap={citationMap}
-      isHuman={isHuman}
-      isLoadingCitations={isLoadingCitations}
-      syntheticExternal={syntheticExternal}
-    />
-  );
-  return img ? { a, img } : { a };
-}
-
-/**
- * Shared CitationsLoadingIndicator component
- * Used across message-list-item and message-group to show loading citations
- */
-export type CitationsLoadingIndicatorProps = {
-  citations: Citation[];
-  className?: string;
-};
-
-export const CitationsLoadingIndicator = ({
-  citations,
-  className,
-}: CitationsLoadingIndicatorProps) => {
-  const { t } = useI18n();
-
-  return (
-    <div className={cn("flex flex-col gap-2", className)}>
-      <Shimmer duration={2.5} className="text-sm">
-        {citations.length > 0
-          ? t.citations.loadingCitationsWithCount(citations.length)
-          : t.citations.loadingCitations}
-      </Shimmer>
-      {citations.length > 0 && (
-        <div className="flex flex-wrap gap-2">
-          {citations.map((citation) => (
-            <Badge
-              key={citation.id}
-              variant="secondary"
-              className="animate-fade-in gap-1 rounded-full px-2.5 py-1 text-xs font-normal"
-            >
-              <Shimmer duration={2} as="span">
-                {citation.title || extractDomainFromUrl(citation.url)}
-              </Shimmer>
-            </Badge>
-          ))}
-        </div>
-      )}
-    </div>
-  );
-};

frontend/src/components/workspace/artifacts/artifact-file-detail.tsx

@@ -8,7 +8,6 @@ import {
   SquareArrowOutUpRightIcon,
   XIcon,
 } from "lucide-react";
-import * as React from "react";
 import { useCallback, useEffect, useMemo, useState } from "react";
 import { toast } from "sonner";
 import { Streamdown } from "streamdown";
@@ -21,7 +20,6 @@ import {
   ArtifactHeader,
   ArtifactTitle,
 } from "@/components/ai-elements/artifact";
-import { createCitationMarkdownComponents } from "@/components/ai-elements/inline-citation";
 import { Select, SelectItem } from "@/components/ui/select";
 import {
   SelectContent,
@@ -33,12 +31,6 @@ import { ToggleGroup, ToggleGroupItem } from "@/components/ui/toggle-group";
 import { CodeEditor } from "@/components/workspace/code-editor";
 import { useArtifactContent } from "@/core/artifacts/hooks";
 import { urlOfArtifact } from "@/core/artifacts/utils";
-import type { Citation } from "@/core/citations";
-import {
-  contentWithoutCitationsFromParsed,
-  removeAllCitations,
-  useParsedCitations,
-} from "@/core/citations";
 import { useI18n } from "@/core/i18n/hooks";
 import { installSkill } from "@/core/skills/api";
 import { streamdownPlugins } from "@/core/streamdown";
@@ -48,9 +40,6 @@ import { cn } from "@/lib/utils";
 
 import { Tooltip } from "../tooltip";
 
-import { SafeCitationContent } from "../messages/safe-citation-content";
-import { useThread } from "../messages/context";
-
 import { useArtifacts } from "./context";
 
 export function ArtifactFileDetail({
@@ -92,22 +81,13 @@ export function ArtifactFileDetail({
   const previewable = useMemo(() => {
     return (language === "html" && !isWriteFile) || language === "markdown";
   }, [isWriteFile, language]);
-  const { thread } = useThread();
   const { content } = useArtifactContent({
     threadId,
     filepath: filepathFromProps,
     enabled: isCodeFile && !isWriteFile,
   });
 
-  const parsed = useParsedCitations(
+  const displayContent = content ?? "";
-    language === "markdown" ? (content ?? "") : "",
-  );
-  const cleanContent =
-    language === "markdown" && content ? parsed.cleanContent : (content ?? "");
-  const contentWithoutCitations =
-    language === "markdown" && content
-      ? contentWithoutCitationsFromParsed(parsed)
-      : (content ?? "");
 
   const [viewMode, setViewMode] = useState<"code" | "preview">("code");
   const [isInstalling, setIsInstalling] = useState(false);
@@ -219,7 +199,7 @@ export function ArtifactFileDetail({
                 disabled={!content}
                 onClick={async () => {
                   try {
-                    await navigator.clipboard.writeText(contentWithoutCitations ?? "");
+                    await navigator.clipboard.writeText(displayContent ?? "");
                     toast.success(t.clipboard.copiedToClipboard);
                   } catch (error) {
                     toast.error("Failed to copy to clipboard");
@@ -255,27 +235,17 @@ export function ArtifactFileDetail({
           viewMode === "preview" &&
           language === "markdown" &&
           content && (
-            <SafeCitationContent
-              content={content}
-              isLoading={thread.isLoading}
-              rehypePlugins={streamdownPlugins.rehypePlugins}
-              className="flex size-full items-center justify-center p-4 my-0"
-              renderBody={(p) => (
             <ArtifactFilePreview
               filepath={filepath}
               threadId={threadId}
-                  content={content}
+              content={displayContent}
               language={language ?? "text"}
-                  cleanContent={p.cleanContent}
-                  citationMap={p.citationMap}
-                />
-              )}
             />
           )}
         {isCodeFile && viewMode === "code" && (
           <CodeEditor
             className="size-full resize-none rounded-none border-none"
-            value={cleanContent ?? ""}
+            value={displayContent ?? ""}
             readonly
           />
         )}
@@ -295,29 +265,17 @@ export function ArtifactFilePreview({
   threadId,
   content,
   language,
-  cleanContent,
-  citationMap,
 }: {
   filepath: string;
   threadId: string;
   content: string;
   language: string;
-  cleanContent: string;
-  citationMap: Map<string, Citation>;
 }) {
   if (language === "markdown") {
-    const components = createCitationMarkdownComponents({
-      citationMap,
-      syntheticExternal: true,
-    });
     return (
       <div className="size-full px-4">
-        <Streamdown
+        <Streamdown className="size-full" {...streamdownPlugins}>
-          className="size-full"
+          {content ?? ""}
-          {...streamdownPlugins}
-          components={components}
-        >
-          {cleanContent ?? ""}
         </Streamdown>
       </div>
     );

frontend/src/components/workspace/messages/markdown-content.tsx

@@ -0,0 +1,42 @@
+"use client";
+
+import type { ImgHTMLAttributes } from "react";
+import type { ReactNode } from "react";
+
+import {
+  MessageResponse,
+  type MessageResponseProps,
+} from "@/components/ai-elements/message";
+import { streamdownPlugins } from "@/core/streamdown";
+
+export type MarkdownContentProps = {
+  content: string;
+  isLoading: boolean;
+  rehypePlugins: MessageResponseProps["rehypePlugins"];
+  className?: string;
+  remarkPlugins?: MessageResponseProps["remarkPlugins"];
+  isHuman?: boolean;
+  img?: (props: ImgHTMLAttributes<HTMLImageElement> & { threadId?: string; maxWidth?: string }) => ReactNode;
+};
+
+/** Renders markdown content. */
+export function MarkdownContent({
+  content,
+  rehypePlugins,
+  className,
+  remarkPlugins = streamdownPlugins.remarkPlugins,
+  img,
+}: MarkdownContentProps) {
+  if (!content) return null;
+  const components = img ? { img } : undefined;
+  return (
+    <MessageResponse
+      className={className}
+      remarkPlugins={remarkPlugins}
+      rehypePlugins={rehypePlugins}
+      components={components}
+    >
+      {content}
+    </MessageResponse>
+  );
+}

frontend/src/components/workspace/messages/message-group.tsx

@@ -39,9 +39,7 @@ import { useArtifacts } from "../artifacts";
 import { FlipDisplay } from "../flip-display";
 import { Tooltip } from "../tooltip";
 
-import { useThread } from "./context";
+import { MarkdownContent } from "./markdown-content";
-
-import { SafeCitationContent } from "./safe-citation-content";
 
 export function MessageGroup({
   className,
@@ -120,7 +118,7 @@ export function MessageGroup({
                 <ChainOfThoughtStep
                   key={step.id}
                   label={
-                    <SafeCitationContent
+                    <MarkdownContent
                       content={step.reasoning ?? ""}
                       isLoading={isLoading}
                       rehypePlugins={rehypePlugins}
@@ -128,12 +126,7 @@ export function MessageGroup({
                   }
                 ></ChainOfThoughtStep>
               ) : (
-                <ToolCall
+                <ToolCall key={step.id} {...step} isLoading={isLoading} />
-                  key={step.id}
-                  {...step}
-                  isLoading={isLoading}
-                  rehypePlugins={rehypePlugins}
-                />
               ),
             )}
           {lastToolCallStep && (
@@ -143,7 +136,6 @@ export function MessageGroup({
                 {...lastToolCallStep}
                 isLast={true}
                 isLoading={isLoading}
-                rehypePlugins={rehypePlugins}
               />
             </FlipDisplay>
           )}
@@ -178,7 +170,7 @@ export function MessageGroup({
               <ChainOfThoughtStep
                 key={lastReasoningStep.id}
                 label={
-                  <SafeCitationContent
+                  <MarkdownContent
                     content={lastReasoningStep.reasoning ?? ""}
                     isLoading={isLoading}
                     rehypePlugins={rehypePlugins}
@@ -201,7 +193,6 @@ function ToolCall({
   result,
   isLast = false,
   isLoading = false,
-  rehypePlugins,
 }: {
   id?: string;
   messageId?: string;
@@ -210,15 +201,10 @@ function ToolCall({
   result?: string | Record<string, unknown>;
   isLast?: boolean;
   isLoading?: boolean;
-  rehypePlugins: ReturnType<typeof useRehypeSplitWordsIntoSpans>;
 }) {
   const { t } = useI18n();
   const { setOpen, autoOpen, autoSelect, selectedArtifact, select } =
     useArtifacts();
-  const { thread } = useThread();
-  const threadIsLoading = thread.isLoading;
-
-  const fileContent = typeof args.content === "string" ? args.content : "";
 
   if (name === "web_search") {
     let label: React.ReactNode = t.toolCalls.searchForRelatedInfo;
@@ -364,12 +350,7 @@ function ToolCall({
       }, 100);
     }
 
-    const isMarkdown =
-      path?.toLowerCase().endsWith(".md") ||
-      path?.toLowerCase().endsWith(".markdown");
-
     return (
-      <>
       <ChainOfThoughtStep
         key={id}
         className="cursor-pointer"
@@ -390,16 +371,6 @@ function ToolCall({
           </ChainOfThoughtSearchResult>
         )}
       </ChainOfThoughtStep>
-        {isMarkdown && (
-          <SafeCitationContent
-            content={fileContent}
-            isLoading={threadIsLoading && isLast}
-            rehypePlugins={rehypePlugins}
-            loadingOnly
-            className="mt-2 ml-8"
-          />
-        )}
-      </>
     );
   } else if (name === "bash") {
     const description: string | undefined = (args as { description: string })

frontend/src/components/workspace/messages/message-list-item.tsx

@@ -12,7 +12,6 @@ import {
 } from "@/components/ai-elements/message";
 import { Badge } from "@/components/ui/badge";
 import { resolveArtifactURL } from "@/core/artifacts/utils";
-import { removeAllCitations } from "@/core/citations";
 import {
   extractContentFromMessage,
   extractReasoningContentFromMessage,
@@ -24,7 +23,7 @@ import { humanMessagePlugins } from "@/core/streamdown";
 import { cn } from "@/lib/utils";
 
 import { CopyButton } from "../copy-button";
-import { SafeCitationContent } from "./safe-citation-content";
+import { MarkdownContent } from "./markdown-content";
 
 export function MessageListItem({
   className,
@@ -54,11 +53,11 @@ export function MessageListItem({
       >
         <div className="flex gap-1">
           <CopyButton
-            clipboardData={removeAllCitations(
+            clipboardData={
               extractContentFromMessage(message) ??
               extractReasoningContentFromMessage(message) ??
               ""
-            )}
+            }
           />
         </div>
       </MessageToolbar>
@@ -154,7 +153,7 @@ function MessageContent_({
   return (
     <AIElementMessageContent className={className}>
       {filesList}
-      <SafeCitationContent
+      <MarkdownContent
         content={contentToParse}
         isLoading={isLoading}
         rehypePlugins={[...rehypePlugins, [rehypeKatex, { output: "html" }]]}

frontend/src/components/workspace/messages/message-list.tsx

@@ -26,7 +26,7 @@ import { StreamingIndicator } from "../streaming-indicator";
 
 import { MessageGroup } from "./message-group";
 import { MessageListItem } from "./message-list-item";
-import { SafeCitationContent } from "./safe-citation-content";
+import { MarkdownContent } from "./markdown-content";
 import { MessageListSkeleton } from "./skeleton";
 import { SubtaskCard } from "./subtask-card";
 
@@ -69,7 +69,7 @@ export function MessageList({
             const message = group.messages[0];
             if (message && hasContent(message)) {
               return (
-                <SafeCitationContent
+                <MarkdownContent
                   key={group.id}
                   content={extractContentFromMessage(message)}
                   isLoading={thread.isLoading}
@@ -89,7 +89,7 @@ export function MessageList({
             return (
               <div className="w-full" key={group.id}>
                 {group.messages[0] && hasContent(group.messages[0]) && (
-                  <SafeCitationContent
+                  <MarkdownContent
                     content={extractContentFromMessage(group.messages[0])}
                     isLoading={thread.isLoading}
                     rehypePlugins={rehypePlugins}

frontend/src/components/workspace/messages/safe-citation-content.tsx

@@ -1,85 +0,0 @@
-"use client";
-
-import type { ImgHTMLAttributes } from "react";
-import type { ReactNode } from "react";
-import { useMemo } from "react";
-
-import {
-  CitationsLoadingIndicator,
-  createCitationMarkdownComponents,
-} from "@/components/ai-elements/inline-citation";
-import {
-  MessageResponse,
-  type MessageResponseProps,
-} from "@/components/ai-elements/message";
-import {
-  shouldShowCitationLoading,
-  useParsedCitations,
-  type UseParsedCitationsResult,
-} from "@/core/citations";
-import { streamdownPlugins } from "@/core/streamdown";
-import { cn } from "@/lib/utils";
-
-export type SafeCitationContentProps = {
-  content: string;
-  isLoading: boolean;
-  rehypePlugins: MessageResponseProps["rehypePlugins"];
-  className?: string;
-  remarkPlugins?: MessageResponseProps["remarkPlugins"];
-  isHuman?: boolean;
-  img?: (props: ImgHTMLAttributes<HTMLImageElement> & { threadId?: string; maxWidth?: string }) => ReactNode;
-  /** When true, only show loading indicator or null (e.g. write_file step). */
-  loadingOnly?: boolean;
-  /** When set, use instead of default MessageResponse (e.g. artifact preview). */
-  renderBody?: (parsed: UseParsedCitationsResult) => ReactNode;
-};
-
-/** Single place for citation-aware body: shows loading until citations complete (no half-finished refs), else body. */
-export function SafeCitationContent({
-  content,
-  isLoading,
-  rehypePlugins,
-  className,
-  remarkPlugins = streamdownPlugins.remarkPlugins,
-  isHuman = false,
-  img,
-  loadingOnly = false,
-  renderBody,
-}: SafeCitationContentProps) {
-  const parsed = useParsedCitations(content);
-  const { citations, cleanContent, citationMap } = parsed;
-  const showLoading = shouldShowCitationLoading(content, cleanContent, isLoading);
-  const components = useMemo(
-    () =>
-      createCitationMarkdownComponents({
-        citationMap,
-        isHuman,
-        isLoadingCitations: false,
-        img,
-      }),
-    [citationMap, isHuman, img],
-  );
-
-  if (showLoading) {
-    return (
-      <CitationsLoadingIndicator
-        citations={citations}
-        className={cn("my-2", className)}
-      />
-    );
-  }
-  if (loadingOnly) return null;
-  if (renderBody) return renderBody(parsed);
-  if (!cleanContent) return null;
-
-  return (
-    <MessageResponse
-      className={className}
-      remarkPlugins={remarkPlugins}
-      rehypePlugins={rehypePlugins}
-      components={components}
-    >
-      {cleanContent}
-    </MessageResponse>
-  );
-}

frontend/src/components/workspace/messages/subtask-card.tsx

@@ -29,7 +29,7 @@ import { cn } from "@/lib/utils";
 
 import { FlipDisplay } from "../flip-display";
 
-import { SafeCitationContent } from "./safe-citation-content";
+import { MarkdownContent } from "./markdown-content";
 
 export function SubtaskCard({
   className,
@@ -153,7 +153,7 @@ export function SubtaskCard({
               <ChainOfThoughtStep
                 label={
                   task.result ? (
-                    <SafeCitationContent
+                    <MarkdownContent
                       content={task.result}
                       isLoading={false}
                       rehypePlugins={rehypePlugins}

frontend/src/core/citations/index.ts

@@ -1,13 +0,0 @@
-export {
-  contentWithoutCitationsFromParsed,
-  extractDomainFromUrl,
-  isExternalUrl,
-  parseCitations,
-  removeAllCitations,
-  shouldShowCitationLoading,
-  syntheticCitationFromLink,
-} from "./utils";
-
-export { useParsedCitations } from "./use-parsed-citations";
-export type { UseParsedCitationsResult } from "./use-parsed-citations";
-export type { Citation, ParseCitationsResult } from "./utils";

frontend/src/core/citations/use-parsed-citations.ts

@@ -1,28 +0,0 @@
-"use client";
-
-import { useMemo } from "react";
-
-import { parseCitations } from "./utils";
-import type { Citation } from "./utils";
-
-export interface UseParsedCitationsResult {
-  citations: Citation[];
-  cleanContent: string;
-  citationMap: Map<string, Citation>;
-}
-
-/**
- * Parse content for citations and build citation map. Memoized by content.
- */
-export function useParsedCitations(content: string): UseParsedCitationsResult {
-  return useMemo(() => {
-    const parsed = parseCitations(content ?? "");
-    const citationMap = new Map<string, Citation>();
-    for (const c of parsed.citations) citationMap.set(c.url, c);
-    return {
-      citations: parsed.citations,
-      cleanContent: parsed.cleanContent,
-      citationMap,
-    };
-  }, [content]);
-}

frontend/src/core/citations/utils.ts

@@ -1,226 +0,0 @@
-/**
- * Citation parsing and display helpers.
- * Display rule: never show half-finished citations. Use shouldShowCitationLoading
- * and show only the loading indicator until the block is complete and all
- * [cite-N] refs are replaced.
- */
-
-/**
- * Citation data structure representing a source reference
- */
-export interface Citation {
-  id: string;
-  title: string;
-  url: string;
-  snippet: string;
-}
-
-/**
- * Result of parsing citations from content
- */
-export interface ParseCitationsResult {
-  citations: Citation[];
-  cleanContent: string;
-}
-
-/**
- * Parse citation lines (one JSON object per line) into Citation array.
- * Deduplicates by URL. Used for both complete and incomplete (streaming) blocks.
- */
-function parseCitationLines(
-  blockContent: string,
-  seenUrls: Set<string>,
-): Citation[] {
-  const out: Citation[] = [];
-  const lines = blockContent.split("\n");
-  for (const line of lines) {
-    const trimmed = line.trim();
-    if (!trimmed?.startsWith("{")) continue;
-    try {
-      const citation = JSON.parse(trimmed) as Citation;
-      if (citation.id && citation.url && !seenUrls.has(citation.url)) {
-        seenUrls.add(citation.url);
-        out.push({
-          id: citation.id,
-          title: citation.title || "",
-          url: citation.url,
-          snippet: citation.snippet || "",
-        });
-      }
-    } catch {
-      // Skip invalid JSON lines - can happen during streaming
-    }
-  }
-  return out;
-}
-
-/**
- * Parse citations block from message content.
- * Shared by all modes (Flash / Thinking / Pro / Ultra); supports incomplete
- * <citations> blocks during SSE streaming (parses whatever complete JSON lines
- * have arrived so far so [cite-N] can be linked progressively).
- *
- * The citations block format:
- * <citations>
- * {"id": "cite-1", "title": "Page Title", "url": "https://example.com", "snippet": "Description"}
- * {"id": "cite-2", "title": "Another Page", "url": "https://example2.com", "snippet": "Description"}
- * </citations>
- *
- * @param content - The raw message content that may contain a citations block
- * @returns Object containing parsed citations array and content with citations block removed
- */
-export function parseCitations(content: string): ParseCitationsResult {
-  if (!content) {
-    return { citations: [], cleanContent: content };
-  }
-
-  const citations: Citation[] = [];
-  const seenUrls = new Set<string>();
-
-  // 1) Complete blocks: <citations>...</citations>
-  const citationsRegex = /<citations>([\s\S]*?)<\/citations>/g;
-  let match;
-  while ((match = citationsRegex.exec(content)) !== null) {
-    citations.push(...parseCitationLines(match[1] ?? "", seenUrls));
-  }
-
-  // 2) Incomplete block during streaming: <citations>... (no closing tag yet)
-  if (content.includes("<citations>") && !content.includes("</citations>")) {
-    const openMatch = content.match(/<citations>([\s\S]*)$/);
-    if (openMatch?.[1] != null) {
-      citations.push(...parseCitationLines(openMatch[1], seenUrls));
-    }
-  }
-
-  let cleanContent = removeCitationsBlocks(content);
-
-  // Convert [cite-N] references to markdown links
-  // Example: [cite-1] -> [Title](url)
-  if (citations.length > 0) {
-    // Build a map from citation id to citation object
-    const idMap = new Map<string, Citation>();
-    for (const citation of citations) {
-      idMap.set(citation.id, citation);
-    }
-
-    // Replace all [cite-N] patterns with markdown links
-    cleanContent = cleanContent.replace(/\[cite-(\d+)\]/g, (match, num) => {
-      const citeId = `cite-${num}`;
-      const citation = idMap.get(citeId);
-      if (citation) {
-        // Use title if available, otherwise use domain
-        const linkText = citation.title || extractDomainFromUrl(citation.url);
-        return `[${linkText}](${citation.url})`;
-      }
-      // If citation not found, keep the original text
-      return match;
-    });
-  }
-
-  return { citations, cleanContent };
-}
-
-/**
- * Whether the URL is external (http/https).
- */
-export function isExternalUrl(url: string): boolean {
-  return url.startsWith("http://") || url.startsWith("https://");
-}
-
-/**
- * Build a synthetic Citation from a link (e.g. in artifact markdown without <citations> block).
- */
-export function syntheticCitationFromLink(href: string, title: string): Citation {
-  return {
-    id: `artifact-cite-${href}`,
-    title: title || href,
-    url: href,
-    snippet: "",
-  };
-}
-
-/**
- * Extract the domain name from a URL for display
- *
- * @param url - Full URL string
- * @returns Domain name or the original URL if parsing fails
- */
-export function extractDomainFromUrl(url: string): string {
-  try {
-    const urlObj = new URL(url);
-    // Remove 'www.' prefix if present
-    return urlObj.hostname.replace(/^www\./, "");
-  } catch {
-    return url;
-  }
-}
-
-/**
- * Remove all <citations> blocks from content (complete and incomplete).
- * Does not remove [cite-N] or markdown links; use removeAllCitations for that.
- */
-export function removeCitationsBlocks(content: string): string {
-  if (!content) return content;
-  let result = content.replace(/<citations>[\s\S]*?<\/citations>/g, "").trim();
-  if (result.includes("<citations>")) {
-    result = result.replace(/<citations>[\s\S]*$/g, "").trim();
-  }
-  return result;
-}
-
-/**
- * Whether content contains a <citations> block (open tag).
- */
-export function hasCitationsBlock(content: string): boolean {
-  return Boolean(content?.includes("<citations>"));
-}
-
-/** Pattern for [cite-1], [cite-2], ... that should be replaced by parseCitations. */
-const UNREPLACED_CITE_REF = /\[cite-\d+\]/;
-
-/**
- * Whether cleanContent still contains unreplaced [cite-N] refs (half-finished citations).
- * When true, callers must not render this content and should show loading instead.
- */
-export function hasUnreplacedCitationRefs(cleanContent: string): boolean {
-  return Boolean(cleanContent && UNREPLACED_CITE_REF.test(cleanContent));
-}
-
-/**
- * Single source of truth: true when body must not be rendered (show loading instead).
- * Use after parseCitations: pass raw content, parsed cleanContent, and isLoading.
- * Never show body when cleanContent still has [cite-N] (e.g. refs arrived before
- * <citations> block in stream); also show loading while streaming with citation block.
- */
-export function shouldShowCitationLoading(
-  rawContent: string,
-  cleanContent: string,
-  isLoading: boolean,
-): boolean {
-  if (hasUnreplacedCitationRefs(cleanContent)) return true;
-  return isLoading && hasCitationsBlock(rawContent);
-}
-
-/**
- * Strip citation markdown links from already-cleaned content (from parseCitations).
- * Use when you already have ParseCitationsResult to avoid parsing twice.
- */
-export function contentWithoutCitationsFromParsed(
-  parsed: ParseCitationsResult,
-): string {
-  const citationUrls = new Set(parsed.citations.map((c) => c.url));
-  const withoutLinks = parsed.cleanContent.replace(
-    /\[([^\]]+)\]\(([^)]+)\)/g,
-    (fullMatch, _text, url) => (citationUrls.has(url) ? "" : fullMatch),
-  );
-  return withoutLinks.replace(/\n{3,}/g, "\n\n").trim();
-}
-
-/**
- * Remove ALL citations from content (blocks, [cite-N], and citation links).
- * Used for copy/download. For display you typically use parseCitations/useParsedCitations.
- */
-export function removeAllCitations(content: string): string {
-  if (!content) return content;
-  return contentWithoutCitationsFromParsed(parseCitations(content));
-}

frontend/src/core/i18n/locales/en-US.ts

@@ -167,13 +167,6 @@ export const enUS: Translations = {
     startConversation: "Start a conversation to see messages here",
   },
 
-  // Citations
-  citations: {
-    loadingCitations: "Organizing citations...",
-    loadingCitationsWithCount: (count: number) =>
-      `Organizing ${count} citation${count === 1 ? "" : "s"}...`,
-  },
-
   // Chats
   chats: {
     searchChats: "Search chats",

frontend/src/core/i18n/locales/types.ts

@@ -115,12 +115,6 @@ export interface Translations {
     startConversation: string;
   };
 
-  // Citations
-  citations: {
-    loadingCitations: string;
-    loadingCitationsWithCount: (count: number) => string;
-  };
-
   // Chats
   chats: {
     searchChats: string;

frontend/src/core/i18n/locales/zh-CN.ts

@@ -164,12 +164,6 @@ export const zhCN: Translations = {
     startConversation: "开始新的对话以查看消息",
   },
 
-  // Citations
-  citations: {
-    loadingCitations: "正在整理引用...",
-    loadingCitationsWithCount: (count: number) => `正在整理 ${count} 个引用...`,
-  },
-
   // Chats
   chats: {
     searchChats: "搜索对话",

frontend/src/lib/utils.ts

@@ -8,5 +8,5 @@ export function cn(...inputs: ClassValue[]) {
 /** Shared class for external links (underline by default). */
 export const externalLinkClass =
   "text-primary underline underline-offset-2 hover:no-underline";
-/** For streaming / loading state when link may be a citation (no underline). */
+/** Link style without underline by default (e.g. for streaming/loading). */
 export const externalLinkClassNoUnderline = "text-primary hover:underline";

skills/public/github-deep-research/SKILL.md

@@ -147,5 +147,5 @@ Save report as: `research_{topic}_{YYYYMMDD}.md`
 3. **Triangulate claims** - 2+ independent sources
 4. **Note conflicting info** - Don't hide contradictions
 5. **Distinguish fact vs opinion** - Label speculation clearly
-6. **Cite inline** - Reference sources near claims
+6. **Reference sources** - Add source references near claims where applicable
 7. **Update as you go** - Don't wait until end to synthesize

skills/public/market-analysis/SKILL.md

@@ -15,7 +15,7 @@ This skill generates professional, consulting-grade market analysis reports in M
 - Follow the **"Visual Anchor → Data Contrast → Integrated Analysis"** flow per sub-chapter
 - Produce insights following the **"Data → User Psychology → Strategy Implication"** chain
 - Embed pre-generated charts and construct comparison tables
-- Generate inline citations formatted per **GB/T 7714-2015** standards
+- Include references formatted per **GB/T 7714-2015** where applicable
 - Output reports entirely in Chinese with professional consulting tone
 
 ## When to Use This Skill
@@ -36,7 +36,7 @@ The skill expects the following inputs from the upstream agentic workflow:
 | **Analysis Framework Outline** | Defines the logic flow and general topics for the report | Yes |
 | **Data Summary** | The source of truth containing raw numbers and metrics | Yes |
 | **Chart Files** | Local file paths for pre-generated chart images | Yes |
-| **External Search Findings** | URLs and summaries for inline citations | Optional |
+| **External Search Findings** | URLs and summaries for inline references | Optional |
 
 ## Workflow
 
@@ -87,7 +87,7 @@ The report **MUST NOT** stop after the Conclusion — it **MUST** include Refere
 - **Tone**: McKinsey/BCG — Authoritative, Objective, Professional
 - **Language**: All headings and content strictly in **Chinese**
 - **Number Formatting**: Use English commas for thousands separators (`1,000` not `1，000`)
-- **Data Citation**: **Bold** important viewpoints and key numbers
+- **Data emphasis**: **Bold** important viewpoints and key numbers
 
 ### Titling Constraints
 - **Numbering**: Use standard numbering (`1.`, `1.1`) or Chinese numbering (`一、`) directly followed by the title
@@ -109,11 +109,9 @@ Every insight must connect **Data → User Psychology → Strategy Implication**
    treating male audiences only as a secondary gift-giving segment."
 ```
 
-### Citations & References
+### References
-- **Inline**: Use `[\[Index\]](URL)` format (e.g., `[\[1\]](https://example.com)`)
+- **Inline**: Use markdown links for sources (e.g. `[Source Title](URL)`) when using External Search Findings
-- **Placement**: Append citations at the end of sentences using information from External Search Findings
+- **References section**: Formatted strictly per **GB/T 7714-2015**
-- **Index Assignment**: Sequential starting from **1** based on order of appearance
-- **References Section**: Formatted strictly per **GB/T 7714-2015**
 
 ### Markdown Rules
 - **Immediate Start**: Begin directly with `# Report Title` — no introductory text
@@ -183,7 +181,7 @@ Before considering the report complete, verify:
 - [ ] All headings are in Chinese with proper numbering (no "Chapter/Part/Section")
 - [ ] Charts are embedded with `![Description](path)` syntax
 - [ ] Numbers use English commas for thousands separators
-- [ ] Inline citations use `[\[N\]](URL)` format
+- [ ] Inline references use markdown links where applicable
 - [ ] References section follows GB/T 7714-2015
 - [ ] No horizontal rules (`---`) in the document
 - [ ] Conclusion uses flowing prose — no bullet points