'
handler = getattr(self, f"_render_{node.type}", None)
if handler is not None:
return handler(node, warnings)
@@ -257,6 +267,8 @@ class HtmlExporter:
warnings.append(f"函数图像：解析或渲染失败，已回退占位（{exc}）")
return f'{html.escape(node.text)}'
warnings.extend(rendered.warnings)
+ from app.plot.render import theme_svg
+ rendered.content = theme_svg(rendered.content, self._options.theme_id)
return f''
t = node.type
if t == "text":
return _html.escape(node.text)
@@ -376,7 +394,7 @@ class PdfExporter:
if safe_href is None:
warnings.append(f"链接协议不安全，已降级为纯文本：{href!r}")
return inner
- return f'{inner}'
+ return f'{inner}'
if t == "image":
src = str(node.attributes.get("src") or "")
alt = str(node.attributes.get("alt") or "")
diff --git a/backend/app/export/fonts.py b/backend/app/export/fonts.py
new file mode 100644
index 0000000..d74243e
--- /dev/null
+++ b/backend/app/export/fonts.py
@@ -0,0 +1,23 @@
+"""嵌入可用的 CJK TrueType 字体，找不到时保留可移植的 CID 字体回退。"""
+import os
+from pathlib import Path
+from reportlab.pdfbase import pdfmetrics
+from reportlab.pdfbase.ttfonts import TTFont
+from reportlab.pdfbase.cidfonts import UnicodeCIDFont
+
+def register_font():
+ """按显式配置、系统字体、Linux 字体的顺序注册 PDF 中文字体。"""
+ candidates = [os.getenv('APP_EXPORT_FONT',''),
+ str(Path(os.getenv('WINDIR','C:/Windows'))/'Fonts/simsun.ttc'),
+ '/usr/share/fonts/truetype/arphic/uming.ttc']
+ for candidate in candidates:
+ if candidate and Path(candidate).is_file():
+ try:
+ pdfmetrics.registerFont(TTFont('NotesExportCJK',candidate,subfontIndex=0))
+ return 'NotesExportCJK', Path(candidate)
+ except Exception:
+ continue
+ pdfmetrics.registerFont(UnicodeCIDFont('STSong-Light'))
+ return 'STSong-Light', None
+
+FONT, FONT_PATH = register_font()
diff --git a/backend/app/export/markdown.py b/backend/app/export/markdown.py
index 436ebda..521fbf9 100644
--- a/backend/app/export/markdown.py
+++ b/backend/app/export/markdown.py
@@ -178,6 +178,9 @@ class _AstMapper:
type="link", node_id=self.next_id(), attributes=attributes,
children=self.map_inline(token.get("children", [])),
)
+ if kind == "inline_html":
+ # 保留行内 HTML 的来源标记，仅供 PDF 资源扫描识别 img；最终 HTML 仍由前端净化。
+ return DocumentNode(type="text", node_id=self.next_id(), text=token.get("raw", ""), attributes={"raw_html": True})
if kind == "codespan":
return DocumentNode(type="codespan", node_id=self.next_id(), text=token.get("raw", ""))
if kind == "image":
diff --git a/backend/app/export/service.py b/backend/app/export/service.py
index 10666eb..68bd4bc 100644
--- a/backend/app/export/service.py
+++ b/backend/app/export/service.py
@@ -146,7 +146,7 @@ def _evict_terminal() -> bool:
return True
-async def _resolve_source(source: ExportSource) -> tuple[str, str, dict | None]:
+async def _resolve_source(source: ExportSource, unlimited: bool = False) -> tuple[str, str, dict | None]:
"""把导出源解析为 (markdown, title, metadata)；metadata 仅 note 源提供。"""
if source.type == ExportSourceType.note:
note = await note_service.get_note(source.note_id)
@@ -157,7 +157,7 @@ async def _resolve_source(source: ExportSource) -> tuple[str, str, dict | None]:
"note not found",
{"note_id": source.note_id},
)
- if len(note.markdown) > MAX_MARKDOWN_CHARS:
+ if not unlimited and len(note.markdown) > MAX_MARKDOWN_CHARS:
raise ApiError(
400,
"EXPORT_OPTIONS_INVALID",
@@ -175,19 +175,22 @@ async def _resolve_source(source: ExportSource) -> tuple[str, str, dict | None]:
markdown = source.markdown or ""
if not markdown.strip():
raise ApiError(400, "EXPORT_OPTIONS_INVALID", "markdown source must not be empty")
- if len(markdown) > MAX_MARKDOWN_CHARS:
+ if not unlimited and len(markdown) > MAX_MARKDOWN_CHARS:
raise ApiError(
400,
"EXPORT_OPTIONS_INVALID",
f"markdown source exceeds {MAX_MARKDOWN_CHARS} characters",
{"size": len(markdown), "limit": MAX_MARKDOWN_CHARS},
)
- return markdown, "", None
+ return markdown, "", {"file_path": source.file_path} if source.file_path else None
async def create_export(request: ExportRequest) -> ExportJob:
"""创建导出任务，立即返回 queued 的 ExportJob，由后台 Task 渲染。"""
- markdown, title, metadata = await _resolve_source(request.source)
+ markdown, title, metadata = await _resolve_source(request.source, request.format == ExportFormat.pdf)
+ title = request.title or title
+ from app.export.assets import validate_assets
+ assets = await asyncio.to_thread(validate_assets, request.assets, request.format == ExportFormat.pdf)
if not _evict_terminal():
raise ApiError(
@@ -207,7 +210,7 @@ async def create_export(request: ExportRequest) -> ExportJob:
_jobs[job_id] = job
_cancel_flags[job_id] = asyncio.Event()
_tasks[job_id] = asyncio.create_task(
- _execute(job_id, request.format, markdown, title, metadata, request.options)
+ _execute(job_id, request.format, markdown, title, metadata, request.options, assets, request.print_html)
)
return job
@@ -245,6 +248,8 @@ async def _execute(
title: str,
metadata: dict | None,
options: ExportOptions,
+ assets: dict | None = None,
+ print_html: str | None = None,
) -> None:
"""后台渲染：排队 → 解析 → 导出 → 写文件 → 挂载产物元信息。"""
cancel_event = _cancel_flags[job_id]
@@ -271,15 +276,24 @@ async def _execute(
# 解析与渲染都是 CPU 密集的同步工作，放入线程执行避免阻塞事件循环，
# 使运行中的取消能在渲染边界生效；写文件前再次检查取消。
- document = await asyncio.to_thread(parse_document, markdown)
- document.attributes["title"] = title
- if metadata:
- document.attributes["metadata"] = metadata
+ if format == ExportFormat.pdf and print_html is not None:
+ from app.export.browser_pdf import render_snapshot
+ result = await asyncio.to_thread(render_snapshot, print_html, options.page_size)
+ else:
+ document = await asyncio.to_thread(parse_document, markdown)
+ document.attributes["title"] = title
+ from app.export.assets import attach_assets
+ attach_assets(document, assets or {})
+ if metadata:
+ document.attributes["metadata"] = metadata
- result = await asyncio.to_thread(_render_document, document, options, format)
+ from app.export.assets import enrich_document
+ resource_warnings = await asyncio.to_thread(enrich_document, document, (metadata or {}).get('file_path'), format == ExportFormat.pdf, options)
+ result = await asyncio.to_thread(_render_document, document, options, format)
+ result.warnings[:0] = resource_warnings
if cancel_event.is_set():
raise ExportCancelled()
- if len(result.content) > MAX_EXPORT_BYTES:
+ if format != ExportFormat.pdf and len(result.content) > MAX_EXPORT_BYTES:
raise ExportTooLarge()
ext = _extension_for(format)
@@ -389,3 +403,42 @@ async def wait_for_export(job_id: str) -> ExportJob | None:
if task is not None:
await task
return _jobs.get(job_id)
+
+
+async def preview_resources(request: ExportRequest):
+ """为浏览器渲染器准备通过 Vault 校验的图片和静态函数图。"""
+ import base64
+ from app.export.assets import enrich_document
+ from app.plot.parser import parse_source
+ from app.plot.render import render_svg
+ from app.export.document import Document, DocumentNode
+ from html.parser import HTMLParser
+ markdown, _, metadata = await _resolve_source(request.source, True)
+ def prepare():
+ document = parse_document(markdown)
+ images, plots = [], []
+ class HtmlImages(HTMLParser):
+ # 原始 HTML 只提取 img.src；路径、扩展名和图片格式仍交给 enrich_document 校验。
+ # 行内代码和代码块在 AST 中不是 HTML 节点，因此不会误当作图片资源。
+ def handle_starttag(self, tag, attrs):
+ if tag == 'img':
+ src = dict(attrs).get('src')
+ if src:
+ visit(DocumentNode(type='image', node_id='html-image', attributes={'src':src}))
+ def visit(node):
+ if node.type == 'html_block' or node.attributes.get('raw_html'):
+ parser = HtmlImages(convert_charrefs=True)
+ parser.feed(node.text)
+ parser.close()
+ if node.type == 'image':
+ warnings = enrich_document(Document(node_id='pdf-resources', children=[node]), (metadata or {}).get('file_path'), True, request.options, preserve_alpha=True)
+ raw = node.attributes.get('static_png')
+ images.append({'source': node.attributes.get('src',''), 'data': 'data:image/png;base64,'+base64.b64encode(raw).decode() if raw else None, 'warnings': warnings})
+ if node.type == 'function_plot':
+ parsed = parse_source(node.text, unlimited=True)
+ result = render_svg(parsed.plot, request.options.theme_id, unlimited=True) if parsed.plot else None
+ plots.append({'source':node.text, 'svg':result.content if result else '', 'warnings':[d.message for d in parsed.diagnostics]+(result.warnings if result else [])})
+ for child in node.children: visit(child)
+ for child in document.children: visit(child)
+ return {'images':images,'plots':plots}
+ return await asyncio.to_thread(prepare)
diff --git a/backend/app/export/themes.py b/backend/app/export/themes.py
index 94e07ee..42dde44 100644
--- a/backend/app/export/themes.py
+++ b/backend/app/export/themes.py
@@ -1,5 +1,6 @@
"""Export palettes are fixed data; arbitrary theme CSS is never executed."""
PALETTES = {
+ 'ocean-blue': ('#edf5fa','#ffffff','#183a50','#46667a','#e6f1f8','#a6c5d9','#086b9c'),
'light': ('#f6f7f9','#ffffff','#1f2328','#57606a','#eaeef2','#d0d7de','#0969da'),
'dark': ('#010409','#0d1117','#e6edf3','#b1bac4','#21262d','#57606a','#79c0ff'),
'sepia': ('#eee5d2','#faf4e6','#463b2d','#6b5943','#eae0cd','#b5a58b','#80532a'),
@@ -31,3 +32,13 @@ ALIASES = {'summary':'abstract','tldr':'abstract','hint':'tip',
'check':'success','done':'success','help':'question','faq':'question',
'caution':'warning','attention':'warning','fail':'failure','missing':'failure',
'error':'danger','cite':'quote'}
+
+
+def pdf_palette(options, warnings):
+ if options.palette is not None:
+ return options.palette.model_dump()
+ theme_id = options.theme_id
+ if theme_id not in PALETTES:
+ warnings.append(f'PDF 不支持主题 {theme_id}，已使用 light 导出配色')
+ theme_id = 'light'
+ return dict(zip(('page','surface','text','muted','code','border','accent'), PALETTES[theme_id]))
diff --git a/backend/app/local_models/runtime.py b/backend/app/local_models/runtime.py
index 7bcb7e2..3c941ca 100644
--- a/backend/app/local_models/runtime.py
+++ b/backend/app/local_models/runtime.py
@@ -5,6 +5,8 @@ import asyncio
import json
import os
import time
+import hashlib
+from collections import OrderedDict
from contextlib import closing
from contextvars import ContextVar
from functools import wraps
@@ -239,6 +241,11 @@ class Runtime:
runtime = Runtime()
+# 对确定性的单文本本地向量做有界内存复用。键包含模型目录、不可变版本和冻结运行配置；
+# 远程 API 响应以及模型不可用时的回退结果都不进入缓存。
+_embedding_cache = OrderedDict()
+_EMBEDDING_CACHE_TTL = 600
+
class LocalEmbedding:
dim = 384
@@ -264,9 +271,24 @@ class LocalEmbedding:
async def embed_documents(self, texts):
config = (self._config or configuration()).model_copy(deep=True)
+ from app.retrieval.provenance import record_embedding
+ cache_key = None
+ if len(texts) == 1 and read_state(config.embedding_model)['status'] == 'installed' and interpreter(config).is_file():
+ cache_key = (str(model_path(config.embedding_model).resolve()), config.model_dump_json(),
+ hashlib.sha256(texts[0].encode()).hexdigest())
+ cached = _embedding_cache.get(cache_key)
+ if cached and time.monotonic() - cached[0] < _EMBEDDING_CACHE_TTL:
+ _embedding_cache.move_to_end(cache_key)
+ record_embedding(query_embedding_cache='hit')
+ return [list(cached[1])]
+ record_embedding(query_embedding_cache='miss')
token = runtime_context.set(config)
try:
- return await runtime.infer(config.embedding_model, "embedding", {"texts": texts}, priority=embedding_priority.get())
+ vectors = await runtime.infer(config.embedding_model, "embedding", {"texts": texts}, priority=embedding_priority.get())
+ if cache_key and len(vectors) == 1:
+ _embedding_cache[cache_key] = (time.monotonic(), tuple(vectors[0]))
+ while len(_embedding_cache) > 128: _embedding_cache.popitem(last=False)
+ return vectors
finally:
runtime_context.reset(token)
diff --git a/backend/app/main.py b/backend/app/main.py
index c9e0651..6426954 100644
--- a/backend/app/main.py
+++ b/backend/app/main.py
@@ -35,6 +35,8 @@ async def lifespan(_: FastAPI):
try:
yield
finally:
+ from app.benchmarks import service as benchmark_service
+ await benchmark_service.shutdown()
await container.agent.shutdown()
from app.services import index_service
await index_service.shutdown()
@@ -75,6 +77,8 @@ app.include_router(local_model_router)
app.include_router(usage_router)
app.include_router(provider_preview_router)
app.include_router(log_router)
+from app.plot_routes import router as plot_router
+app.include_router(plot_router)
@app.middleware('http')
diff --git a/backend/app/plot/model.py b/backend/app/plot/model.py
index f11273e..63ba52e 100644
--- a/backend/app/plot/model.py
+++ b/backend/app/plot/model.py
@@ -1,7 +1,7 @@
"""Function Plot 内部数据模型。
-契约 §12.2 的 FunctionPlot 结构与 §10.4 的 StaticRenderResult 只在导出链路的后端内部
-流转，不进入 HTTP 契约，因此与 Document AST 一样放在独立包内，不进 contracts.py。
+FunctionPlot 供预览和导出共享；StaticRenderResult 同时是交互预览端点的响应内容。
+模型保留在独立包内，由 plot_routes 中的请求与响应类型注册 OpenAPI。
"""
from __future__ import annotations
diff --git a/backend/app/plot/parser.py b/backend/app/plot/parser.py
index 4dab231..f9dcf8c 100644
--- a/backend/app/plot/parser.py
+++ b/backend/app/plot/parser.py
@@ -143,7 +143,7 @@ def _preprocess(expr: str) -> str:
return _insert_implicit_multiplication(expr.replace("^", "**"))
-def _check_node(node: ast.AST, depth: int = 0, counter: list[int] | None = None) -> None:
+def _check_node(node: ast.AST, depth: int = 0, counter: list[int] | None = None, unlimited: bool = False) -> None:
"""白名单校验：任何越界节点都抛 FUNCTION_PLOT_EXPRESSION_UNSAFE。
同时限制 AST 深度与节点总数，避免超长/超深表达式在递归校验或求值时触发
@@ -151,10 +151,10 @@ def _check_node(node: ast.AST, depth: int = 0, counter: list[int] | None = None)
"""
if counter is None:
counter = [0]
- if depth > _MAX_AST_DEPTH:
+ if not unlimited and depth > _MAX_AST_DEPTH:
_unsafe(f"表达式嵌套过深（超过 {_MAX_AST_DEPTH} 层）")
counter[0] += 1
- if counter[0] > _MAX_AST_NODES:
+ if not unlimited and counter[0] > _MAX_AST_NODES:
_unsafe(f"表达式过于复杂（节点数超过 {_MAX_AST_NODES}）")
if isinstance(node, ast.Constant):
if isinstance(node.value, bool) or not isinstance(node.value, (int, float)):
@@ -167,13 +167,13 @@ def _check_node(node: ast.AST, depth: int = 0, counter: list[int] | None = None)
if isinstance(node, ast.BinOp):
if not isinstance(node.op, _ALLOWED_BINOPS):
_unsafe(f"不支持的运算符 {type(node.op).__name__}")
- _check_node(node.left, depth + 1, counter)
- _check_node(node.right, depth + 1, counter)
+ _check_node(node.left, depth + 1, counter, unlimited)
+ _check_node(node.right, depth + 1, counter, unlimited)
return
if isinstance(node, ast.UnaryOp):
if not isinstance(node.op, _ALLOWED_UNARY):
_unsafe(f"不支持的运算符 {type(node.op).__name__}")
- _check_node(node.operand, depth + 1, counter)
+ _check_node(node.operand, depth + 1, counter, unlimited)
return
if isinstance(node, ast.Call):
if not isinstance(node.func, ast.Name) or node.func.id not in _FUNCTIONS:
@@ -184,12 +184,12 @@ def _check_node(node: ast.AST, depth: int = 0, counter: list[int] | None = None)
if len(node.args) != 1:
_unsafe(f"{node.func.id} 需要 1 个参数，实际 {len(node.args)} 个")
for arg in node.args:
- _check_node(arg, depth + 1, counter)
+ _check_node(arg, depth + 1, counter, unlimited)
return
_unsafe(f"不支持的语法 {type(node).__name__}")
-def parse_expression(expr: str) -> ast.Expression:
+def parse_expression(expr: str, unlimited: bool = False) -> ast.Expression:
"""把数学表达式解析为已通过白名单校验的 AST（可直接交给 evaluate）。"""
preprocessed = _preprocess(expr)
try:
@@ -211,7 +211,7 @@ def parse_expression(expr: str) -> ast.Expression:
message="表达式嵌套过深，无法解析",
)
) from exc
- _check_node(tree.body)
+ _check_node(tree.body, unlimited=unlimited)
return tree
@@ -279,7 +279,7 @@ def _parse_directive(line: str) -> tuple[str, str] | None:
return key, value.strip()
-def parse_source(source: str) -> FunctionPlotParseResult:
+def parse_source(source: str, unlimited: bool = False) -> FunctionPlotParseResult:
"""把 function-plot fenced block 源码解析为 FunctionPlot + 诊断。"""
diagnostics: list[PlotDiagnostic] = []
expressions: list[FunctionPlotExpression] = []
@@ -371,7 +371,7 @@ def parse_source(source: str) -> FunctionPlotParseResult:
continue
try:
- tree = parse_expression(expr_text)
+ tree = parse_expression(expr_text, unlimited=unlimited)
except PlotParseError as exc:
exc.diagnostic.line = lineno
diagnostics.append(exc.diagnostic)
@@ -380,7 +380,7 @@ def parse_source(source: str) -> FunctionPlotParseResult:
total_nodes += _count_nodes(tree.body)
expressions.append(FunctionPlotExpression(expression=expr_text))
# 表达式数量超限：整块回退并提前终止，避免对海量表达式做采样求值
- if len(expressions) > _MAX_EXPRESSIONS:
+ if not unlimited and len(expressions) > _MAX_EXPRESSIONS:
diagnostics.append(
PlotDiagnostic(
severity="error",
diff --git a/backend/app/plot/render.py b/backend/app/plot/render.py
index baee2be..fa79112 100644
--- a/backend/app/plot/render.py
+++ b/backend/app/plot/render.py
@@ -339,7 +339,7 @@ def _sample_segments(
return clipped
-def compute_geometry(plot: FunctionPlot) -> PlotGeometry:
+def compute_geometry(plot: FunctionPlot, unlimited: bool = False) -> PlotGeometry:
"""解析并计算几何，供 SVG 与 reportlab 后端复用。"""
warnings: list[str] = []
xmin, xmax = plot.domain
@@ -351,7 +351,7 @@ def compute_geometry(plot: FunctionPlot) -> PlotGeometry:
fns: list[tuple[object, object]] = []
for expr in plot.expressions:
try:
- tree = parse_expression(expr.expression)
+ tree = parse_expression(expr.expression, unlimited=unlimited)
except PlotParseError as exc:
warnings.append(f"表达式无法渲染，已跳过：{expr.expression}（{exc.diagnostic.message}）")
continue
@@ -413,12 +413,12 @@ def _grid_svg(geo: PlotGeometry) -> str:
for x in geo.xticks:
parts.append(
f'