fix floating stream empty responses with sanitizer-safe fallbacks

app/core/deep_agent.py

@@ -42,6 +42,7 @@ _HOME_SINGLE_AGENT_SYSTEM = (
 _FLOATING_SINGLE_AGENT_SYSTEM = (
     "You are the floating assistant with direct access to all tools: tasks, projects, notes, timelines, and memory tools. "
     "Stay focused on the floating scope in context.scope and answer concisely. "
+    "Return plain text only. Do not output XML/HTML-like tags such as <task>, <project>, <note>, <timeline>, or any bracketed id tag wrappers. "
     "Always use tools for factual data retrieval before answering. "
     "When the user asks to remember, forget, or update what you know about them, use memory tools. "
     "If context.context.resolved_project_id exists, use it as project_id for scoped list calls. "
@@ -221,6 +222,70 @@ def _normalize_tagged_list_lines(text: str, message: str) -> str:
     return "\n".join(output_lines)
 
 
+_GENERIC_TAG_RE = re.compile(r"</?(task|project|note|timeline|chart)>", re.IGNORECASE)
+_BRACKETED_ID_RE = re.compile(r"\[(?:[0-9a-fA-F-]{8,}|[A-Za-z0-9_-]{8,})\]")
+_FLOATING_EMPTY_FALLBACK = "No results found."
+
+
+def _strip_floating_markup_fragment(text: str) -> str:
+    if not text:
+        return text
+    cleaned = _GENERIC_TAG_RE.sub("", text)
+    return _BRACKETED_ID_RE.sub("", cleaned)
+
+
+def _strip_floating_markup(text: str) -> str:
+    """Ensure floating responses stay plain text with no XML-like tag wrappers."""
+    if not text:
+        return text
+
+    cleaned = _strip_floating_markup_fragment(text)
+    # Collapse excessive spaces introduced by tag/id removal while preserving lines.
+    lines = [re.sub(r"[ \t]{2,}", " ", line).strip() for line in cleaned.splitlines()]
+    return "\n".join(line for line in lines if line)
+
+
+def _fallback_from_raw_floating_text(raw_text: str) -> str:
+    fallback = _strip_floating_markup_fragment(raw_text or "")
+    fallback = re.sub(r"[ \t]{2,}", " ", fallback).strip()
+    return fallback or _FLOATING_EMPTY_FALLBACK
+
+
+class _FloatingStreamSanitizer:
+    """Streaming sanitizer that removes floating markup without buffering the full answer."""
+
+    def __init__(self) -> None:
+        self._pending = ""
+
+    @staticmethod
+    def _split_safe_boundary(text: str) -> tuple[str, str]:
+        boundary = len(text)
+
+        last_lt = text.rfind("<")
+        if last_lt != -1 and ">" not in text[last_lt:]:
+            boundary = min(boundary, last_lt)
+
+        last_lb = text.rfind("[")
+        if last_lb != -1 and "]" not in text[last_lb:]:
+            boundary = min(boundary, last_lb)
+
+        if boundary == len(text):
+            return text, ""
+        return text[:boundary], text[boundary:]
+
+    def feed(self, chunk: str) -> str:
+        combined = f"{self._pending}{chunk}"
+        safe_text, self._pending = self._split_safe_boundary(combined)
+        return _strip_floating_markup_fragment(safe_text)
+
+    def finalize(self) -> str:
+        # Drop dangling unfinished wrappers at the very end.
+        tail = re.sub(r"<[^>\n]*$", "", self._pending)
+        tail = re.sub(r"\[[^\]\n]*$", "", tail)
+        self._pending = ""
+        return _strip_floating_markup_fragment(tail)
+
+
 def _normalize_memory_label(path_or_label: str) -> str:
     value = path_or_label.strip()
     if value.startswith("/memories/"):
@@ -618,11 +683,20 @@ async def _run_single_agent_stream(
             messages.append(response)
 
             if not response.tool_calls:
+                emitted_any = False
                 async for chunk in llm.astream(messages):
                     token = _as_text(getattr(chunk, "content", ""))
                     if token:
                         streamed_chars += len(token)
+                        emitted_any = True
                         yield "token", token
+
+                # Some providers return final text in `response.content` but stream no chunks.
+                if not emitted_any:
+                    fallback_text = _as_text(response.content)
+                    if fallback_text:
+                        streamed_chars += len(fallback_text)
+                        yield "token", fallback_text
                 logger.info(
                     "deep_agent: run_single_agent_stream_end trace=%s user=%s tool_calls=%d response_chars=%d",
                     trace_id or "-",
@@ -696,7 +770,10 @@ async def run_floating(user_id: str, message: str, context: dict[str, Any]) -> t
         message=message,
         context=prepared_context,
     )
-    return response, domain
+    sanitized = _strip_floating_markup(response)
+    if not sanitized and response:
+        sanitized = _fallback_from_raw_floating_text(response)
+    return sanitized, domain
 
 
 async def run_home_stream(
@@ -732,13 +809,34 @@ async def run_floating_stream(
     domain = await _infer_floating_domain(message, prepared_context)
     yield "floating_domain", domain
 
+    sanitizer = _FloatingStreamSanitizer()
+    emitted_sanitized = False
+    raw_chunks: list[str] = []
     async for event in _run_single_agent_stream(
         user_id=user_id,
         system_prompt=_FLOATING_SINGLE_AGENT_SYSTEM,
         message=message,
         context=prepared_context,
     ):
-        yield event
+        event_type, data = event
+        if event_type != "token":
+            yield event
+            continue
+
+        raw_chunk = str(data or "")
+        raw_chunks.append(raw_chunk)
+        sanitized_chunk = sanitizer.feed(raw_chunk)
+        if sanitized_chunk:
+            emitted_sanitized = True
+            yield "token", sanitized_chunk
+
+    tail = sanitizer.finalize()
+    if tail:
+        emitted_sanitized = True
+        yield "token", tail
+
+    if not emitted_sanitized and raw_chunks:
+        yield "token", _fallback_from_raw_floating_text("".join(raw_chunks))
 
 
 async def update_core_memory(user_id: str, key: str, value: str) -> None: