feat(gateway): streaming token delivery — StreamingConfig, GatewayStreamConsumer, already_sent

Stage 3 of streaming support. Gateway now streams tokens to messaging platforms:

- StreamingConfig dataclass (enabled, transport, edit_interval, buffer_threshold, cursor)
  on GatewayConfig with from_dict/to_dict serialization
- GatewayStreamConsumer: async queue-based consumer that progressively edits
  a single message on the target platform (edit transport)
- on_delta() → queue → run() async task → send_or_edit() with rate limiting
- already_sent propagation: when streaming delivered the response, handler
  returns None so base adapter skips duplicate send()
- stream_delta_callback wired into AIAgent constructor in _run_agent
- Consumer lifecycle: started as asyncio task, awaited with timeout in finally

Config (config.yaml):
  streaming:
    enabled: true
    transport: edit      # progressive editMessageText
    edit_interval: 0.3   # seconds between edits
    buffer_threshold: 40 # chars before forcing flush
    cursor: ' ▉'

Credit: jobless0x (#774, #1312), OutThisLife (#798), clicksingh (#697).
This commit is contained in:
teknium1 2026-03-16 05:52:42 -07:00
parent ac739e485f
commit 5479bb0e0c
3 changed files with 270 additions and 0 deletions

View file

@ -146,6 +146,37 @@ class PlatformConfig:
)
@dataclass
class StreamingConfig:
"""Configuration for real-time token streaming to messaging platforms."""
enabled: bool = True
transport: str = "edit" # "edit" (progressive editMessageText) or "off"
edit_interval: float = 0.3 # Seconds between message edits
buffer_threshold: int = 40 # Chars before forcing an edit
cursor: str = "" # Cursor shown during streaming
def to_dict(self) -> Dict[str, Any]:
return {
"enabled": self.enabled,
"transport": self.transport,
"edit_interval": self.edit_interval,
"buffer_threshold": self.buffer_threshold,
"cursor": self.cursor,
}
@classmethod
def from_dict(cls, data: Dict[str, Any]) -> "StreamingConfig":
if not data:
return cls()
return cls(
enabled=data.get("enabled", True),
transport=data.get("transport", "edit"),
edit_interval=float(data.get("edit_interval", 0.3)),
buffer_threshold=int(data.get("buffer_threshold", 40)),
cursor=data.get("cursor", ""),
)
@dataclass
class GatewayConfig:
"""
@ -179,6 +210,9 @@ class GatewayConfig:
# Session isolation in shared chats
group_sessions_per_user: bool = True # Isolate group/channel sessions per participant when user IDs are available
# Streaming configuration
streaming: StreamingConfig = field(default_factory=StreamingConfig)
def get_connected_platforms(self) -> List[Platform]:
"""Return list of platforms that are enabled and configured."""
connected = []
@ -244,6 +278,7 @@ class GatewayConfig:
"always_log_local": self.always_log_local,
"stt_enabled": self.stt_enabled,
"group_sessions_per_user": self.group_sessions_per_user,
"streaming": self.streaming.to_dict(),
}
@classmethod
@ -297,6 +332,7 @@ class GatewayConfig:
always_log_local=data.get("always_log_local", True),
stt_enabled=_coerce_bool(stt_enabled, True),
group_sessions_per_user=_coerce_bool(group_sessions_per_user, True),
streaming=StreamingConfig.from_dict(data.get("streaming", {})),
)