mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-29 01:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

fix(api-server): keep chat-completions SSE alive

Browse source
This commit is contained in:
helix4u 2026-04-11 12:42:01 -06:00 • committed by Teknium
parent cac6178104
commit 39da23a129
2 changed files with 54 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

18
gateway/platforms/api_server.py
View file

@ -53,6 +53,7 @@ DEFAULT_HOST = "127.0.0.1"
DEFAULT_PORT = 8642
MAX_STORED_RESPONSES = 100
MAX_REQUEST_BYTES = 1_000_000 # 1 MB default limit for POST bodies
CHAT_COMPLETIONS_SSE_KEEPALIVE_SECONDS = 30.0
def check_api_server_requirements() -> bool:
@ -762,7 +763,11 @@ class APIServerAdapter(BasePlatformAdapter):
"""
import queue as _q
sse_headers = {"Content-Type": "text/event-stream", "Cache-Control": "no-cache"}
sse_headers = {
"Content-Type": "text/event-stream",
"Cache-Control": "no-cache",
"X-Accel-Buffering": "no",
}
# CORS middleware can't inject headers into StreamResponse after
# prepare() flushes them, so resolve CORS headers up front.
origin = request.headers.get("Origin", "")
@ -775,6 +780,8 @@ class APIServerAdapter(BasePlatformAdapter):
await response.prepare(request)
try:
last_activity = time.monotonic()
# Role chunk
role_chunk = {
"id": completion_id, "object": "chat.completion.chunk",
@ -782,6 +789,7 @@ class APIServerAdapter(BasePlatformAdapter):
"choices": [{"index": 0, "delta": {"role": "assistant"}, "finish_reason": None}],
}
await response.write(f"data: {json.dumps(role_chunk)}\n\n".encode())
last_activity = time.monotonic()
# Helper — route a queue item to the correct SSE event.
async def _emit(item):
@ -805,6 +813,7 @@ class APIServerAdapter(BasePlatformAdapter):
"choices": [{"index": 0, "delta": {"content": item}, "finish_reason": None}],
}
await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
return time.monotonic()
# Stream content chunks as they arrive from the agent
loop = asyncio.get_event_loop()
@ -819,16 +828,19 @@ class APIServerAdapter(BasePlatformAdapter):
delta = stream_q.get_nowait()
if delta is None:
break
await _emit(delta)
last_activity = await _emit(delta)
except _q.Empty:
break
break
if time.monotonic() - last_activity >= CHAT_COMPLETIONS_SSE_KEEPALIVE_SECONDS:
await response.write(b": keepalive\n\n")
last_activity = time.monotonic()
continue
if delta is None: # End of stream sentinel
break
await _emit(delta)
last_activity = await _emit(delta)
# Get usage from completed agent
usage = {"input_tokens": 0, "output_tokens": 0, "total_tokens": 0}