mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-06-10 09:25:57 +00:00
Huixin615
88e36d9686
* fix(#3189): prevent write_file streaming timeout on long reports Adds a layered defense against StreamChunkTimeoutError caused by oversized single-shot write_file tool calls: - factory: default stream_chunk_timeout to 240s for OpenAI-compatible clients (overridable via ModelConfig.stream_chunk_timeout in config.yaml) - sandbox/tools: server-side 80 KB length guard on non-append write_file calls (configurable via DEERFLOW_WRITE_FILE_MAX_BYTES env var, 0 disables); rejects oversized payloads with a structured error pointing the model at str_replace or append=True - middleware: classify StreamChunkTimeoutError as transient but cap retries at 1 via per-exception _RETRY_BUDGET_OVERRIDES (same-payload retry on a chunk-gap timeout buffers the same way upstream; full 3-attempt loop would stack 6-12 min of dead air) - middleware: surface an actionable user-facing message for stream-drop exceptions instead of leaking the raw langchain stack - prompts: add a routing-style File Editing Workflow hint to both lead_agent and general_purpose subagent prompts, pointing the model at str_replace for incremental edits (mirrors Claude Code's Edit / Codex's apply_patch) - tests: behavioural coverage for size guard, retry budget override, stream-drop user message, factory default injection Refs #3189 * fix(#3189): drop stream_chunk_timeout for non-OpenAI providers Address CR feedback on PR #3195: - factory: pop `stream_chunk_timeout` from kwargs for any model_use_path other than `langchain_openai:ChatOpenAI` instead of returning early. `ModelConfig.stream_chunk_timeout` is part of the shared schema, so a user-supplied value on a non-OpenAI provider would otherwise be forwarded to its constructor and raise `TypeError: unexpected keyword argument`. - factory: rewrite docstring to describe the actual `exclude_none=True` behaviour (explicit null is excluded and falls back to the default) instead of the misleading "None falling out via exclude_none=True keeps its value". - tests: add regression coverage asserting the kwarg is stripped before reaching a non-OpenAI provider's constructor. Refs: bytedance#3189 * fix(#3189): restrict stream-drop user copy to StreamChunkTimeoutError only Per CR on #3195: narrow _STREAM_DROP_EXCEPTIONS to StreamChunkTimeoutError. Generic httpx RemoteProtocolError / ReadError fall back to the standard 'temporarily unavailable' copy, since they routinely fire on transient network blips where the 'split the output' guidance is misleading. Retry/backoff classification is unchanged — both remain transient/retriable. Tests updated to reflect new copy, plus a symmetric regression test for ReadError. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
52 lines
2.6 KiB
Python
52 lines
2.6 KiB
Python
from pydantic import BaseModel, ConfigDict, Field
|
|
|
|
|
|
class ModelConfig(BaseModel):
|
|
"""Config section for a model"""
|
|
|
|
name: str = Field(..., description="Unique name for the model")
|
|
display_name: str | None = Field(..., default_factory=lambda: None, description="Display name for the model")
|
|
description: str | None = Field(..., default_factory=lambda: None, description="Description for the model")
|
|
use: str = Field(
|
|
...,
|
|
description="Class path of the model provider(e.g. langchain_openai.ChatOpenAI)",
|
|
)
|
|
model: str = Field(..., description="Model name")
|
|
model_config = ConfigDict(extra="allow")
|
|
use_responses_api: bool | None = Field(
|
|
default=None,
|
|
description="Whether to route OpenAI ChatOpenAI calls through the /v1/responses API",
|
|
)
|
|
output_version: str | None = Field(
|
|
default=None,
|
|
description="Structured output version for OpenAI responses content, e.g. responses/v1",
|
|
)
|
|
supports_thinking: bool = Field(default_factory=lambda: False, description="Whether the model supports thinking")
|
|
supports_reasoning_effort: bool = Field(default_factory=lambda: False, description="Whether the model supports reasoning effort")
|
|
when_thinking_enabled: dict | None = Field(
|
|
default_factory=lambda: None,
|
|
description="Extra settings to be passed to the model when thinking is enabled",
|
|
)
|
|
when_thinking_disabled: dict | None = Field(
|
|
default_factory=lambda: None,
|
|
description="Extra settings to be passed to the model when thinking is disabled",
|
|
)
|
|
supports_vision: bool = Field(default_factory=lambda: False, description="Whether the model supports vision/image inputs")
|
|
stream_chunk_timeout: float | None = Field(
|
|
default=None,
|
|
description=(
|
|
"Maximum seconds to wait between successive streaming chunks before "
|
|
"langchain-openai raises StreamChunkTimeoutError. None means use the "
|
|
"factory default (240s for OpenAI-compatible clients). Tune higher for "
|
|
"reasoning models with long thinking pauses; lower for latency-sensitive "
|
|
"interactive endpoints. Has no effect on non-OpenAI-compatible providers."
|
|
),
|
|
)
|
|
thinking: dict | None = Field(
|
|
default_factory=lambda: None,
|
|
description=(
|
|
"Thinking settings for the model. If provided, these settings will be passed to the model when thinking is enabled. "
|
|
"This is a shortcut for `when_thinking_enabled` and will be merged with `when_thinking_enabled` if both are provided."
|
|
),
|
|
)
|