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.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
 
@@ -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.
 
@@ -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":

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>