mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-09-16 17:46:20 +00:00
ae82f426bf
* fix(summarization): resolve fraction triggers from declared context_window, degrade instead of crashing the agent build A fraction trigger/keep clause requires profile["max_input_tokens"], which any third-party OpenAI-compatible model lacks, so SummarizationMiddleware construction raised ValueError out of create_summarization_middleware and failed the whole agent build (#3103). - factory: translate a declared model context_window into the langchain profile (metadata-only, never reaches the provider payload); explicit caller/override profiles win - summarization factory: drop unusable fraction trigger clauses (absolute clauses survive), fall a fraction keep back to the messages default, and disable compaction with an actionable warning only when no usable trigger clause remains — the agent build never dies from summarization config - docs: config.example.yaml, ModelConfig.context_window, summarization.md * refactor(summarization): share the default keep constant with the fraction fallback The fraction-keep degradation fallback hardcoded ("messages", 20), duplicating SummarizationConfig.keep's default_factory literal. Move the value to a shared DEFAULT_KEEP constant so the two cannot drift apart. * fix(summarization): keep trigger-null + fraction-keep constructing after degradation A trigger of None with a fraction keep hit the all-clauses-dropped branch (has_usable_trigger=False) and disabled compaction, and the accompanying warning claimed configured triggers were all fraction-based when none were configured. Only report nothing-usable when trigger clauses actually existed; trigger:null keeps constructing the never-firing middleware with the degraded keep, matching its behavior outside the degradation path. * fix(summarization): address review — keep manual compaction, validate ContextSize, pin wiring Review follow-ups on #4901: - When every configured trigger is a dropped fraction clause, keep constructing the never-firing middleware (trigger=None) instead of returning None: manual /compact runs with force=True and never consults trigger clauses, so it must keep working for a profile-less model rather than reporting 'compaction is disabled'. The warning now says auto-compaction will not fire while manual compaction remains. - ContextSize gains a config-load validator: fraction values must be in (0,1] (a percent-style 80 instead of 0.8 previously produced a threshold the context could never reach — a silently inert trigger), absolute values must be positive. - New un-monkeypatched integration test pins the shipped wiring (context_window declared -> real factory attaches profile -> fraction clause survives -> middleware constructs), which the stubbed middleware-side tests and kwarg-capturing factory-side tests each stopped short of. - Docs (summarization.md + config.example.yaml) clarify that the fraction resolves against the summary/anchor model's context_window (summarization.model_name when set, else the run model), including the mismatch caveat for a larger-window summary model. * fix(summarization): reject non-finite ContextSize values at config load YAML .nan / .inf pass pydantic's float parsing, and nan <= 0 is False, so the positivity check alone let them through as dead thresholds (count >= nan is always False) — the same silent-inert-trigger class the range validator was added to close. Guard with math.isfinite first, consistent with the existing non-finite guards on mem0 timeout_seconds and poll_after_seconds. * fix(summarization): merge context_window into inferred profile, require whole message counts - construct the model first, then merge max_input_tokens into the provider-inferred langchain profile: passing profile= to the constructor replaced the whole inferred metadata (tool_calling, structured_output, io capabilities, output limits) with the single key. An explicitly configured profile is still never clobbered. - reject non-integral ContextSize values for type=messages at config load: langchain slices the message list with them, so a float index raised TypeError mid-compaction. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
64 lines
3.3 KiB
Python
64 lines
3.3 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")
|
|
context_window: int | None = Field(
|
|
default=None,
|
|
gt=0,
|
|
description=(
|
|
"Positive total context window size in tokens (prompt + completion). Used to compute the real-time "
|
|
"context usage percentage displayed in the chat UI, and attached to the model's langchain profile "
|
|
"(`max_input_tokens`) so fraction-based summarization triggers can resolve their thresholds for "
|
|
"third-party OpenAI-compatible models that carry no built-in profile. Distinct from `max_tokens`, "
|
|
"which is the per-call output cap passed to the provider. Leave unset if unknown; the UI will hide "
|
|
"the percentage and fraction summarization clauses will degrade with a warning."
|
|
),
|
|
)
|
|
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."
|
|
),
|
|
)
|