mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(streaming): surface dropped tool-call on mid-stream stall (#12072)

Browse source 
When streaming died after text was already delivered to the user but
before a tool-call's arguments finished streaming, the partial-stream
stub at the end of _interruptible_streaming_api_call silently set
`tool_calls=None` on the returned message and kept `finish_reason=stop`.
The agent treated the turn as complete, the session exited cleanly with
code 0, and the attempted action was lost with zero user-facing signal.

Live-observed Apr 2026 with MiniMax M2.7 on a ~6-minute audit task:
agent streamed 'Let me write the audit:', started emitting a write_file
tool call, MiniMax stalled for 240s mid-arguments, the stale-stream
detector killed the connection, the stub fired, session ended, no file
written, no error shown.

Fix: the streaming accumulator now records each tool-call's name into
`result['partial_tool_names']` as soon as the name is known. When the
stub builder fires after a partial delivery and finds any recorded tool
names, it appends a human-visible warning to the stub's content — and
also fires it as a live stream delta so the user sees it immediately,
not only in the persisted transcript. The next turn's model also sees
the warning in conversation history and can retry on its own. Text-only
partial streams keep the original bare-recovery behaviour (no warning).

Validation:
| Scenario                                    | Before                    | After                                       |
|---------------------------------------------|---------------------------|---------------------------------------------|
| Stream dies mid tool-call, text already sent | Silent exit, no indication | User sees ⚠ warning naming the dropped tool |
| Text-only partial stream                     | Bare recovered text       | Unchanged                                   |
| tests/run_agent/test_streaming.py            | 24 passed                 | 26 passed (2 new)                           |
This commit is contained in:
Teknium 2026-04-18 01:52:06 -07:00 • committed by GitHub
parent 285bb2b915
commit 8322b42c6c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 182 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

55
run_agent.py
View file

@ -5579,7 +5579,7 @@ class AIAgent:
raise result["error"]
return result["response"]
result = {"response": None, "error": None}
result = {"response": None, "error": None, "partial_tool_names": []}
request_client_holder = {"client": None}
first_delta_fired = {"done": False}
deltas_were_sent = {"yes": False} # Track if any deltas were fired (for fallback)
@ -5751,6 +5751,14 @@ class AIAgent:
tool_gen_notified.add(idx)
_fire_first_delta()
self._fire_tool_gen_started(name)
# Record the partial tool-call name so the outer
# stub-builder can surface a user-visible warning
# if streaming dies before this tool's arguments
# are fully delivered. Without this, a stall
# during tool-call JSON generation lets the stub
# at line ~6107 return `tool_calls=None`, silently
# discarding the attempted action.
result["partial_tool_names"].append(name)
if chunk.choices[0].finish_reason:
finish_reason = chunk.choices[0].finish_reason
@ -6117,13 +6125,44 @@ class AIAgent:
_partial_text = (
getattr(self, "_current_streamed_assistant_text", "") or ""
).strip() or None
logger.warning(
"Partial stream delivered before error; returning stub "
"response with %s chars of recovered content to prevent "
"duplicate messages: %s",
len(_partial_text or ""),
result["error"],
)
# If the stream died while the model was emitting a tool call,
# the stub below will silently set `tool_calls=None` and the
# agent loop will treat the turn as complete — the attempted
# action is lost with no user-facing signal. Append a
# human-visible warning to the stub content so (a) the user
# knows something failed, and (b) the next turn's model sees
# in conversation history what was attempted and can retry.
_partial_names = list(result.get("partial_tool_names") or [])
if _partial_names:
_name_str = ", ".join(_partial_names[:3])
if len(_partial_names) > 3:
_name_str += f", +{len(_partial_names) - 3} more"
_warn = (
f"\n\n⚠ Stream stalled mid tool-call "
f"({_name_str}); the action was not executed. "
f"Ask me to retry if you want to continue."
)
_partial_text = (_partial_text or "") + _warn
# Also fire as a streaming delta so the user sees it now
# instead of only in the persisted transcript.
try:
self._fire_stream_delta(_warn)
except Exception:
pass
logger.warning(
"Partial stream dropped tool call(s) %s after %s chars "
"of text; surfaced warning to user: %s",
_partial_names, len(_partial_text or ""), result["error"],
)
else:
logger.warning(
"Partial stream delivered before error; returning stub "
"response with %s chars of recovered content to prevent "
"duplicate messages: %s",
len(_partial_text or ""),
result["error"],
)
_stub_msg = SimpleNamespace(
role="assistant", content=_partial_text, tool_calls=None,
reasoning_content=None,