feat(auth): authentication module with multi-tenant isolation (RFC-001)

Introduce an always-on auth layer with auto-created admin on first boot, multi-tenant isolation for threads/stores, and a full setup/login flow. Backend - JWT access tokens with `ver` field for stale-token rejection; bump on password/email change - Password hashing, HttpOnly+Secure cookies (Secure derived from request scheme at runtime) - CSRF middleware covering both REST and LangGraph routes - IP-based login rate limiting (5 attempts / 5-min lockout) with bounded dict growth and X-Forwarded-For bypass fix - Multi-worker-safe admin auto-creation (single DB write, WAL once) - needs_setup + token_version on User model; SQLite schema migration - Thread/store isolation by owner; orphan thread migration on first admin registration - thread_id validated as UUID to prevent log injection - CLI tool to reset admin password - Decorator-based authz module extracted from auth core Frontend - Login and setup pages with SSR guard for needs_setup flow - Account settings page (change password / email) - AuthProvider + route guards; skips redirect when no users registered - i18n (en-US / zh-CN) for auth surfaces - Typed auth API client; parseAuthError unwraps FastAPI detail envelope Infra & tooling - Unified `serve.sh` with gateway mode + auto dep install - Public PyPI uv.toml pin for CI compatibility - Regenerated uv.lock with public index Tests - HTTP vs HTTPS cookie security tests - Auth middleware, rate limiter, CSRF, setup flow coverage
2026-05-25 01:15:58 +00:00 · 2026-04-08 00:31:43 +08:00
parent 636053fb6d
commit 27b66d6753
214 changed files with 18830 additions and 1065 deletions
@@ -182,6 +182,23 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):

        return None, False

+    @staticmethod
+    def _append_text(content: str | list | None, text: str) -> str | list:
+        """Append *text* to AIMessage content, handling str, list, and None.
+
+        When content is a list of content blocks (e.g. Anthropic thinking mode),
+        we append a new ``{"type": "text", ...}`` block instead of concatenating
+        a string to a list, which would raise ``TypeError``.
+        """
+        if content is None:
+            return text
+        if isinstance(content, list):
+            return [*content, {"type": "text", "text": f"\n\n{text}"}]
+        if isinstance(content, str):
+            return content + f"\n\n{text}"
+        # Fallback: coerce unexpected types to str to avoid TypeError
+        return str(content) + f"\n\n{text}"
+
    def _apply(self, state: AgentState, runtime: Runtime) -> dict | None:
        warning, hard_stop = self._track_and_check(state, runtime)

@@ -192,7 +209,7 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
            stripped_msg = last_msg.model_copy(
                update={
                    "tool_calls": [],
-                    "content": (last_msg.content or "") + f"\n\n{_HARD_STOP_MSG}",
+                    "content": self._append_text(last_msg.content, _HARD_STOP_MSG),
                }
            )
            return {"messages": [stripped_msg]}
@@ -29,6 +29,22 @@ _CORRECTION_PATTERNS = (
    re.compile(r"改用"),
 )

+_REINFORCEMENT_PATTERNS = (
+    re.compile(r"\byes[,.]?\s+(?:exactly|perfect|that(?:'s| is) (?:right|correct|it))\b", re.IGNORECASE),
+    re.compile(r"\bperfect(?:[.!?]|$)", re.IGNORECASE),
+    re.compile(r"\bexactly\s+(?:right|correct)\b", re.IGNORECASE),
+    re.compile(r"\bthat(?:'s| is)\s+(?:exactly\s+)?(?:right|correct|what i (?:wanted|needed|meant))\b", re.IGNORECASE),
+    re.compile(r"\bkeep\s+(?:doing\s+)?that\b", re.IGNORECASE),
+    re.compile(r"\bjust\s+(?:like\s+)?(?:that|this)\b", re.IGNORECASE),
+    re.compile(r"\bthis is (?:great|helpful)\b(?:[.!?]|$)", re.IGNORECASE),
+    re.compile(r"\bthis is what i wanted\b(?:[.!?]|$)", re.IGNORECASE),
+    re.compile(r"对[，,]?\s*就是这样(?:[。！？!?.]|$)"),
+    re.compile(r"完全正确(?:[。！？!?.]|$)"),
+    re.compile(r"(?:对[，,]?\s*)?就是这个意思(?:[。！？!?.]|$)"),
+    re.compile(r"正是我想要的(?:[。！？!?.]|$)"),
+    re.compile(r"继续保持(?:[。！？!?.]|$)"),
+)
+

 class MemoryMiddlewareState(AgentState):
    """Compatible with the `ThreadState` schema."""
@@ -132,6 +148,29 @@ def detect_correction(messages: list[Any]) -> bool:
    return False


+def detect_reinforcement(messages: list[Any]) -> bool:
+    """Detect explicit positive reinforcement signals in recent conversation turns.
+
+    Complements detect_correction() by identifying when the user confirms the
+    agent's approach was correct. This allows the memory system to record what
+    worked well, not just what went wrong.
+
+    The queue keeps only one pending context per thread, so callers pass the
+    latest filtered message list. Checking only recent user turns keeps signal
+    detection conservative while avoiding stale signals from long histories.
+    """
+    recent_user_msgs = [msg for msg in messages[-6:] if getattr(msg, "type", None) == "human"]
+
+    for msg in recent_user_msgs:
+        content = _extract_message_text(msg).strip()
+        if not content:
+            continue
+        if any(pattern.search(content) for pattern in _REINFORCEMENT_PATTERNS):
+            return True
+
+    return False
+
+
 class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
    """Middleware that queues conversation for memory update after agent execution.

@@ -196,12 +235,14 @@ class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):

        # Queue the filtered conversation for memory update
        correction_detected = detect_correction(filtered_messages)
+        reinforcement_detected = not correction_detected and detect_reinforcement(filtered_messages)
        queue = get_memory_queue()
        queue.add(
            thread_id=thread_id,
            messages=filtered_messages,
            agent_name=self._agent_name,
            correction_detected=correction_detected,
+            reinforcement_detected=reinforcement_detected,
        )

        return None
@@ -101,44 +101,33 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
        return user_msg if user_msg else "New Conversation"

    def _generate_title_result(self, state: TitleMiddlewareState) -> dict | None:
-        """Synchronously generate a title. Returns state update or None."""
+        """Generate a local fallback title without blocking on an LLM call."""
        if not self._should_generate_title(state):
            return None

-        prompt, user_msg = self._build_title_prompt(state)
-        config = get_title_config()
-        model = create_chat_model(name=config.model_name, thinking_enabled=False)
-
-        try:
-            response = model.invoke(prompt)
-            title = self._parse_title(response.content)
-            if not title:
-                title = self._fallback_title(user_msg)
-        except Exception:
-            logger.exception("Failed to generate title (sync)")
-            title = self._fallback_title(user_msg)
-
-        return {"title": title}
+        _, user_msg = self._build_title_prompt(state)
+        return {"title": self._fallback_title(user_msg)}

    async def _agenerate_title_result(self, state: TitleMiddlewareState) -> dict | None:
-        """Asynchronously generate a title. Returns state update or None."""
+        """Generate a title asynchronously and fall back locally on failure."""
        if not self._should_generate_title(state):
            return None

-        prompt, user_msg = self._build_title_prompt(state)
        config = get_title_config()
-        model = create_chat_model(name=config.model_name, thinking_enabled=False)
+        prompt, user_msg = self._build_title_prompt(state)

        try:
+            if config.model_name:
+                model = create_chat_model(name=config.model_name, thinking_enabled=False)
+            else:
+                model = create_chat_model(thinking_enabled=False)
            response = await model.ainvoke(prompt)
            title = self._parse_title(response.content)
-            if not title:
-                title = self._fallback_title(user_msg)
+            if title:
+                return {"title": title}
        except Exception:
-            logger.exception("Failed to generate title (async)")
-            title = self._fallback_title(user_msg)
-
-        return {"title": title}
+            logger.debug("Failed to generate async title; falling back to local title", exc_info=True)
+        return {"title": self._fallback_title(user_msg)}

    @override
    def after_model(self, state: TitleMiddlewareState, runtime: Runtime) -> dict | None:
@@ -138,6 +138,6 @@ def build_subagent_runtime_middlewares(*, lazy_init: bool = True) -> list[AgentM
    """Middlewares shared by subagent runtime before subagent-only middlewares."""
    return _build_runtime_middlewares(
        include_uploads=False,
-        include_dangling_tool_call_patch=False,
+        include_dangling_tool_call_patch=True,
        lazy_init=lazy_init,
    )
@@ -10,10 +10,52 @@ from langchain_core.messages import HumanMessage
 from langgraph.runtime import Runtime

 from deerflow.config.paths import Paths, get_paths
+from deerflow.utils.file_conversion import extract_outline

 logger = logging.getLogger(__name__)


+_OUTLINE_PREVIEW_LINES = 5
+
+
+def _extract_outline_for_file(file_path: Path) -> tuple[list[dict], list[str]]:
+    """Return the document outline and fallback preview for *file_path*.
+
+    Looks for a sibling ``<stem>.md`` file produced by the upload conversion
+    pipeline.
+
+    Returns:
+        (outline, preview) where:
+        - outline: list of ``{title, line}`` dicts (plus optional sentinel).
+          Empty when no headings are found or no .md exists.
+        - preview: first few non-empty lines of the .md, used as a content
+          anchor when outline is empty so the agent has some context.
+          Empty when outline is non-empty (no fallback needed).
+    """
+    md_path = file_path.with_suffix(".md")
+    if not md_path.is_file():
+        return [], []
+
+    outline = extract_outline(md_path)
+    if outline:
+        logger.debug("Extracted %d outline entries from %s", len(outline), file_path.name)
+        return outline, []
+
+    # outline is empty — read the first few non-empty lines as a content preview
+    preview: list[str] = []
+    try:
+        with md_path.open(encoding="utf-8") as f:
+            for line in f:
+                stripped = line.strip()
+                if stripped:
+                    preview.append(stripped)
+                if len(preview) >= _OUTLINE_PREVIEW_LINES:
+                    break
+    except Exception:
+        logger.debug("Failed to read preview lines from %s", md_path, exc_info=True)
+    return [], preview
+
+
 class UploadsMiddlewareState(AgentState):
    """State schema for uploads middleware."""

@@ -39,12 +81,38 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
        super().__init__()
        self._paths = Paths(base_dir) if base_dir else get_paths()

+    def _format_file_entry(self, file: dict, lines: list[str]) -> None:
+        """Append a single file entry (name, size, path, optional outline) to lines."""
+        size_kb = file["size"] / 1024
+        size_str = f"{size_kb:.1f} KB" if size_kb < 1024 else f"{size_kb / 1024:.1f} MB"
+        lines.append(f"- {file['filename']} ({size_str})")
+        lines.append(f"  Path: {file['path']}")
+        outline = file.get("outline") or []
+        if outline:
+            truncated = outline[-1].get("truncated", False)
+            visible = [e for e in outline if not e.get("truncated")]
+            lines.append("  Document outline (use `read_file` with line ranges to read sections):")
+            for entry in visible:
+                lines.append(f"    L{entry['line']}: {entry['title']}")
+            if truncated:
+                lines.append(f"    ... (showing first {len(visible)} headings; use `read_file` to explore further)")
+        else:
+            preview = file.get("outline_preview") or []
+            if preview:
+                lines.append("  No structural headings detected. Document begins with:")
+                for text in preview:
+                    lines.append(f"    > {text}")
+            lines.append("  Use `grep` to search for keywords (e.g. `grep(pattern='keyword', path='/mnt/user-data/uploads/')`).")
+        lines.append("")
+
    def _create_files_message(self, new_files: list[dict], historical_files: list[dict]) -> str:
        """Create a formatted message listing uploaded files.

        Args:
            new_files: Files uploaded in the current message.
            historical_files: Files uploaded in previous messages.
+                Each file dict may contain an optional ``outline`` key — a list of
+                ``{title, line}`` dicts extracted from the converted Markdown file.

        Returns:
            Formatted string inside <uploaded_files> tags.
@@ -55,25 +123,24 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
        lines.append("")
        if new_files:
            for file in new_files:
-                size_kb = file["size"] / 1024
-                size_str = f"{size_kb:.1f} KB" if size_kb < 1024 else f"{size_kb / 1024:.1f} MB"
-                lines.append(f"- {file['filename']} ({size_str})")
-                lines.append(f"  Path: {file['path']}")
-                lines.append("")
+                self._format_file_entry(file, lines)
        else:
            lines.append("(empty)")
+            lines.append("")

        if historical_files:
            lines.append("The following files were uploaded in previous messages and are still available:")
            lines.append("")
            for file in historical_files:
-                size_kb = file["size"] / 1024
-                size_str = f"{size_kb:.1f} KB" if size_kb < 1024 else f"{size_kb / 1024:.1f} MB"
-                lines.append(f"- {file['filename']} ({size_str})")
-                lines.append(f"  Path: {file['path']}")
-                lines.append("")
+                self._format_file_entry(file, lines)

-        lines.append("You can read these files using the `read_file` tool with the paths shown above.")
+        lines.append("To work with these files:")
+        lines.append("- Read from the file first — use the outline line numbers and `read_file` to locate relevant sections.")
+        lines.append("- Use `grep` to search for keywords when you are not sure which section to look at")
+        lines.append("  (e.g. `grep(pattern='revenue', path='/mnt/user-data/uploads/')`).")
+        lines.append("- Use `glob` to find files by name pattern")
+        lines.append("  (e.g. `glob(pattern='**/*.md', path='/mnt/user-data/uploads/')`).")
+        lines.append("- Only fall back to web search if the file content is clearly insufficient to answer the question.")
        lines.append("</uploaded_files>")

        return "\n".join(lines)
@@ -147,6 +214,13 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):

        # Resolve uploads directory for existence checks
        thread_id = (runtime.context or {}).get("thread_id")
+        if thread_id is None:
+            try:
+                from langgraph.config import get_config
+
+                thread_id = get_config().get("configurable", {}).get("thread_id")
+            except RuntimeError:
+                pass  # get_config() raises outside a runnable context (e.g. unit tests)
        uploads_dir = self._paths.sandbox_uploads_dir(thread_id) if thread_id else None

        # Get newly uploaded files from the current message's additional_kwargs.files
@@ -159,15 +233,26 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
            for file_path in sorted(uploads_dir.iterdir()):
                if file_path.is_file() and file_path.name not in new_filenames:
                    stat = file_path.stat()
+                    outline, preview = _extract_outline_for_file(file_path)
                    historical_files.append(
                        {
                            "filename": file_path.name,
                            "size": stat.st_size,
                            "path": f"/mnt/user-data/uploads/{file_path.name}",
                            "extension": file_path.suffix,
+                            "outline": outline,
+                            "outline_preview": preview,
                        }
                    )

+        # Attach outlines to new files as well
+        if uploads_dir:
+            for file in new_files:
+                phys_path = uploads_dir / file["filename"]
+                outline, preview = _extract_outline_for_file(phys_path)
+                file["outline"] = outline
+                file["outline_preview"] = preview
+
        if not new_files and not historical_files:
            return None