fix: strip MEDIA: directives from streamed gateway messages (#5152)

When streaming is enabled, the GatewayStreamConsumer sends raw text
chunks directly to the platform without post-processing. This causes
MEDIA:/path/to/file tags and [[audio_as_voice]] directives to appear
as visible text in the user's chat instead of being stripped.

The non-streaming path already handles this correctly via
extract_media() in base.py, but the streaming path was missing
equivalent cleanup.

Add _clean_for_display() to GatewayStreamConsumer that strips MEDIA:
tags and internal markers before any text reaches the platform. The
actual media file delivery is unaffected — _deliver_media_from_response()
in gateway/run.py still extracts files from the agent's final_response
(separate from the stream consumer's display text).

Reported by Ao [FotM] on Discord.
This commit is contained in:
Teknium
2026-04-04 19:05:27 -07:00
committed by GitHub
parent ff544526cd
commit c8220e69a1
2 changed files with 211 additions and 0 deletions

View File

@@ -18,6 +18,7 @@ from __future__ import annotations
import asyncio
import logging
import queue
import re
import time
from dataclasses import dataclass
from typing import Any, Optional
@@ -156,8 +157,39 @@ class GatewayStreamConsumer:
except Exception as e:
logger.error("Stream consumer error: %s", e)
# Pattern to strip MEDIA:<path> tags (including optional surrounding quotes).
# Matches the simple cleanup regex used by the non-streaming path in
# gateway/platforms/base.py for post-processing.
_MEDIA_RE = re.compile(r'''[`"']?MEDIA:\s*\S+[`"']?''')
@staticmethod
def _clean_for_display(text: str) -> str:
"""Strip MEDIA: directives and internal markers from text before display.
The streaming path delivers raw text chunks that may include
``MEDIA:<path>`` tags and ``[[audio_as_voice]]`` directives meant for
the platform adapter's post-processing. The actual media files are
delivered separately via ``_deliver_media_from_response()`` after the
stream finishes — we just need to hide the raw directives from the
user.
"""
if "MEDIA:" not in text and "[[audio_as_voice]]" not in text:
return text
cleaned = text.replace("[[audio_as_voice]]", "")
cleaned = GatewayStreamConsumer._MEDIA_RE.sub("", cleaned)
# Collapse excessive blank lines left behind by removed tags
cleaned = re.sub(r'\n{3,}', '\n\n', cleaned)
# Strip trailing whitespace/newlines but preserve leading content
return cleaned.rstrip()
async def _send_or_edit(self, text: str) -> None:
"""Send or edit the streaming message."""
# Strip MEDIA: directives so they don't appear as visible text.
# Media files are delivered as native attachments after the stream
# finishes (via _deliver_media_from_response in gateway/run.py).
text = self._clean_for_display(text)
if not text.strip():
return
try:
if self._message_id is not None:
if self._edit_supported: