Grayscale/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(anthropic): treat stream idle timeout as inactivity only, not total time

Browse Source
This commit is contained in:
shen0122
2026-08-14 23:18:13 +08:00
committed by chengyongru
parent 1437d1a75a
commit 4de728a555
2 changed files with 161 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nanobot/providers/anthropic_provider.py
+59 -58
View File
@@ -782,67 +782,68 @@ class AnthropicProvider(LLMProvider):
idle_timeout_s = resolve_stream_idle_timeout_s()
try:
async with self._client.messages.stream(**kwargs) as stream:
if on_content_delta or on_thinking_delta or on_tool_call_delta:
# Idle timeout must track *any* SSE chunk (thinking_delta,
# tool JSON deltas, etc.), not only text_stream tokens.
# Otherwise extended thinking can stall text_stream for minutes
# while the connection is healthy (e.g. MiniMax Anthropic).
tool_blocks: dict[int, dict[str, str]] = {}
while True:
try:
chunk = await asyncio.wait_for(
stream.__anext__(),
timeout=idle_timeout_s,
)
except StopAsyncIteration:
break
if chunk.type == "content_block_start":
block = getattr(chunk, "content_block", None)
if getattr(block, "type", None) == "tool_use":
index = int(getattr(chunk, "index", 0) or 0)
state = {
"call_id": str(getattr(block, "id", "") or ""),
"name": str(getattr(block, "name", "") or ""),
}
tool_blocks[index] = state
if on_tool_call_delta:
await on_tool_call_delta({
"index": index,
**state,
"arguments_delta": "",
})
elif (
chunk.type == "content_block_delta"
and getattr(chunk.delta, "type", None) == "thinking_delta"
):
piece = getattr(chunk.delta, "thinking", None) or ""
if piece and on_thinking_delta:
await on_thinking_delta(piece)
elif (
chunk.type == "content_block_delta"
and getattr(chunk.delta, "type", None) == "text_delta"
):
text = getattr(chunk.delta, "text", None) or ""
if text and on_content_delta:
await on_content_delta(text)
elif (
chunk.type == "content_block_delta"
and getattr(chunk.delta, "type", None) == "input_json_delta"
):
partial = getattr(chunk.delta, "partial_json", None) or ""
if partial and on_tool_call_delta:
index = int(getattr(chunk, "index", 0) or 0)
state = tool_blocks.get(index, {})
# Idle timeout must track *any* SSE chunk (thinking_delta,
# tool JSON deltas, etc.), not only text_stream tokens.
# Otherwise extended thinking can stall text_stream for minutes
# while the connection is healthy (e.g. MiniMax Anthropic).
# Drain the whole stream with per-chunk idle waits so the
# timeout measures inactivity, not total generation time: a
# long but continuously-active stream must never be killed.
# The SDK accumulates the final message snapshot during
# iteration, so get_final_message() below returns instantly.
tool_blocks: dict[int, dict[str, str]] = {}
while True:
try:
chunk = await asyncio.wait_for(
stream.__anext__(),
timeout=idle_timeout_s,
)
except StopAsyncIteration:
break
if chunk.type == "content_block_start":
block = getattr(chunk, "content_block", None)
if getattr(block, "type", None) == "tool_use":
index = int(getattr(chunk, "index", 0) or 0)
state = {
"call_id": str(getattr(block, "id", "") or ""),
"name": str(getattr(block, "name", "") or ""),
}
tool_blocks[index] = state
if on_tool_call_delta:
await on_tool_call_delta({
"index": index,
"call_id": state.get("call_id", ""),
"name": state.get("name", ""),
"arguments_delta": partial,
**state,
"arguments_delta": "",
})
response = await asyncio.wait_for(
stream.get_final_message(),
timeout=idle_timeout_s,
)
elif (
chunk.type == "content_block_delta"
and getattr(chunk.delta, "type", None) == "thinking_delta"
):
piece = getattr(chunk.delta, "thinking", None) or ""
if piece and on_thinking_delta:
await on_thinking_delta(piece)
elif (
chunk.type == "content_block_delta"
and getattr(chunk.delta, "type", None) == "text_delta"
):
text = getattr(chunk.delta, "text", None) or ""
if text and on_content_delta:
await on_content_delta(text)
elif (
chunk.type == "content_block_delta"
and getattr(chunk.delta, "type", None) == "input_json_delta"
):
partial = getattr(chunk.delta, "partial_json", None) or ""
if partial and on_tool_call_delta:
index = int(getattr(chunk, "index", 0) or 0)
state = tool_blocks.get(index, {})
await on_tool_call_delta({
"index": index,
"call_id": state.get("call_id", ""),
"name": state.get("name", ""),
"arguments_delta": partial,
})
response = await stream.get_final_message()
return self._parse_response(response)
except asyncio.TimeoutError:
return LLMResponse(