iomgaa
9474c76ab0
Give one logical call an optional hard wall-clock boundary (issue #22). Leaving it unset keeps 1.3.5 behaviour verbatim: the timeout context is never entered when deadline_s is None. - new deadline.py: ensure_call_deadline() range check (None or a finite positive number; bool/0/nan/inf and out-of-range ints are rejected as ValueError so OverflowError never leaks) plus with_call_deadline(), which distinguishes an expiry from a TimeoutError raised by the body or its cleanup via a local-variable identity comparison rather than cm.expired() alone - new CallDeadlineExceeded: deliberately outside the four categories and not a GatewayUnavailableError, and carries no retry_after_s - new {SCOPE}__CALL_DEADLINE_S key, guarded on the env, direct construction and dataclasses.replace paths - three clients take a call_deadline_s constructor argument and a keyword-only per-call override on chat/embed/recognize_text/ parse_layout; None inherits the assembled value - validation runs before the awaitable is created, so an illegal value cannot strand an un-awaited coroutine - one embed call shares a single deadline across all of its batches - import-linter gains a polygateway.deadline layer - cover where the deadline lands: backoff sleep, admission polling, the structured re-ask ladder and embedding's batch loop, plus the empty-texts early return that stays outside it - cover what an expiry costs: exactly one terminal_failure row carrying error_type=CallDeadlineExceeded, a cancelled attempt row sharing its logical_call_id, cleanup that outlives the deadline (lower bound only) and an already-billed success being discarded - pin the injected clock as orthogonal: a 10^6 second jump never expires a call, yet total_latency_ms still reads that clock
102 lines
2.6 KiB
Python
102 lines
2.6 KiB
Python
"""PolyGateway: 实验室统一的大语言模型(LLM/VLM/OCR)调度与中转库。
|
|
|
|
治理单位是一次模型调用: 多源选择、限流、错误分类与重试、熔断、响应缓存、
|
|
流式活性看门狗、遥测。架构单一事实源见 research-wiki/ARCHITECTURE.md。
|
|
顶层导出即公共 API 面: 错误四分类必须从这里引用(ARCH §5.1 约定②)。
|
|
"""
|
|
|
|
from polygateway.client import GatewayClient, gather_bounded
|
|
from polygateway.config import EmbeddingSettings, GatewaySettings, OcrSettings
|
|
from polygateway.embedding import EmbeddingClient
|
|
from polygateway.errors import (
|
|
AllSourcesExhausted,
|
|
CallDeadlineExceeded,
|
|
CircuitOpenError,
|
|
GatewayUnavailableError,
|
|
GovernanceBackendError,
|
|
PolyGatewayError,
|
|
RequestRejectedError,
|
|
ResultInvalidError,
|
|
SourceDeadError,
|
|
SourceNotConfiguredError,
|
|
TransientError,
|
|
)
|
|
from polygateway.ocr import OcrClient
|
|
from polygateway.pricing import ModelPrice, PricingTable
|
|
from polygateway.providers import (
|
|
DEFAULT_PROFILES,
|
|
ProviderProfile,
|
|
ThinkingWire,
|
|
register_provider,
|
|
)
|
|
from polygateway.telemetry.schema import telemetry_schema_sql
|
|
from polygateway.thinking import (
|
|
ThinkingCapability,
|
|
ThinkingResolution,
|
|
ThinkingUnsupportedError,
|
|
get_capability,
|
|
register_capability,
|
|
resolve_thinking,
|
|
)
|
|
from polygateway.types import (
|
|
EFFORT_ORDER,
|
|
CallStats,
|
|
Effort,
|
|
EmbeddingResponse,
|
|
LLMResponse,
|
|
OcrLayoutElement,
|
|
OcrLayoutResult,
|
|
OcrTextResult,
|
|
SourceConfig,
|
|
TelemetryStatus,
|
|
ThinkingObservation,
|
|
)
|
|
|
|
__version__ = "1.3.5"
|
|
|
|
__all__ = [
|
|
"DEFAULT_PROFILES",
|
|
"EFFORT_ORDER",
|
|
"Effort",
|
|
"AllSourcesExhausted",
|
|
"CallStats",
|
|
"CallDeadlineExceeded",
|
|
"CircuitOpenError",
|
|
"EmbeddingClient",
|
|
"EmbeddingResponse",
|
|
"EmbeddingSettings",
|
|
"GatewayClient",
|
|
"GatewaySettings",
|
|
"GatewayUnavailableError",
|
|
"GovernanceBackendError",
|
|
"LLMResponse",
|
|
"ModelPrice",
|
|
"OcrClient",
|
|
"OcrLayoutElement",
|
|
"OcrLayoutResult",
|
|
"OcrSettings",
|
|
"OcrTextResult",
|
|
"PolyGatewayError",
|
|
"PricingTable",
|
|
"ProviderProfile",
|
|
"RequestRejectedError",
|
|
"ResultInvalidError",
|
|
"SourceConfig",
|
|
"SourceDeadError",
|
|
"SourceNotConfiguredError",
|
|
"TelemetryStatus",
|
|
"ThinkingCapability",
|
|
"ThinkingObservation",
|
|
"ThinkingResolution",
|
|
"ThinkingUnsupportedError",
|
|
"ThinkingWire",
|
|
"TransientError",
|
|
"__version__",
|
|
"gather_bounded",
|
|
"get_capability",
|
|
"register_capability",
|
|
"register_provider",
|
|
"resolve_thinking",
|
|
"telemetry_schema_sql",
|
|
]
|