iomgaa
7b9815f4bc
Includes config aggregation for multi-source env keys, from_env and from_settings factories with explicit shared-backend injection, gather_bounded, top-level exports, tightened import-linter layers with the gate removed from the Makefile, and the finalized .env.example.
55 lines
3.1 KiB
Bash
55 lines
3.1 KiB
Bash
# PolyGateway 工程配置模板(复制为 .env 使用;.env 不提交)。
|
|
# 键名清单 = M1 设计文档 §8 定稿;缺关键配置直接报错,不做默认值兜底。
|
|
|
|
# ══ 多源配置: {SCOPE}__{PROVIDER}__{N}__{FIELD} ══
|
|
# PROVIDER 必须是注册表键(qwen/deepseek/openai,或 register_provider 注册后经 registry 传入)。
|
|
# 必填: BASE_URL / API_KEY / MODEL / TIMEOUT_S(或用平铺 LLM_TIMEOUT 作缺省)。
|
|
LLM__QWEN__1__BASE_URL=
|
|
LLM__QWEN__1__API_KEY=
|
|
LLM__QWEN__1__MODEL=
|
|
LLM__QWEN__1__TIMEOUT_S=120
|
|
# 可选(0 = 该闸不启用;TPM > 0 时 EST_TOKENS 必填 > 0):
|
|
# LLM__QWEN__1__MAX_CONCURRENCY=8
|
|
# LLM__QWEN__1__RPM=60
|
|
# LLM__QWEN__1__TPM=100000
|
|
# LLM__QWEN__1__EST_TOKENS=2000
|
|
# LLM__QWEN__1__TTFT_TIMEOUT_S=30 # 须与 INTER_TOKEN 成对;0 < inter < ttft < timeout
|
|
# LLM__QWEN__1__INTER_TOKEN_TIMEOUT_S=15
|
|
# LLM__QWEN__1__ENABLE_THINKING=true # 三态: 缺省=不注入 / true=注入开启 / false=注入关闭
|
|
# LLM__QWEN__1__MISSING_DONE=retry # SSE 缺 [DONE]: retry(默认) | salvage
|
|
# LLM__QWEN__1__TRUST_ENV=true # false = 绕过本地代理(LAN 直连)
|
|
|
|
# ══ scope 级全局闸(跨源合计;0/缺省 = 不启用)══
|
|
# LLM__GLOBAL__MAX_CONCURRENCY=8
|
|
# LLM__GLOBAL__RPM=120
|
|
# LLM__GLOBAL__TPM=200000
|
|
|
|
# ══ 韧性参数(平铺键 = 单 scope 简写,沿用三项目习惯;scope 键优先)══
|
|
LLM_MAX_RETRIES=3 # 总尝试次数(含首次);或 LLM__RETRY__MAX_ATTEMPTS
|
|
LLM_RETRY_BASE_DELAY=2.0 # 或 LLM__RETRY__BACKOFF_BASE_S
|
|
LLM_RETRY_MAX_DELAY=30.0 # 或 LLM__RETRY__BACKOFF_MAX_S
|
|
LLM_CIRCUIT_BREAKER_THRESHOLD=5 # 有效阈值自动取 max(此值, 并发×2);或 LLM__BREAKER__FAIL_THRESHOLD
|
|
LLM_CIRCUIT_BREAKER_COOLDOWN=60 # 或 LLM__BREAKER__COOLDOWN_S
|
|
# LLM_TIMEOUT=120 # 源缺 TIMEOUT_S 时的缺省
|
|
# LLM_TTFT_TIMEOUT=30 # 平铺看门狗缺省(成对生效)
|
|
# LLM_INTER_TOKEN_TIMEOUT=15
|
|
# LLM__BREAKER__PROBE_TTL_S=240 # 缺省派生: max(2×最大源超时, cooldown)
|
|
# LLM__BACKPRESSURE__STALL_WINDOW_S=300 # M2 启用 stall 判定
|
|
# LLM__BACKPRESSURE__POLL_INTERVAL_S=0.05
|
|
# LLM__SELECTOR=round_robin # round_robin(默认) | least_inflight
|
|
# LLM__QUOTA_FULL=wait # wait(默认) | fail_fast
|
|
|
|
# ══ 装配选择(PGW_*)══
|
|
PGW_LIMITER_BACKEND=memory # M1 仅 memory;redis 随 M2
|
|
PGW_BREAKER_BACKEND=memory
|
|
PGW_CACHE_BACKEND=none # redis | memory | none(必填,显式优于隐式)
|
|
PGW_TELEMETRY_BACKEND=none # sqlite | none(postgres 随 M2)
|
|
# PGW_TELEMETRY_SQLITE_PATH=logs/telemetry.db # sqlite 时必填
|
|
# PGW_CACHE_NAMESPACE=<项目名或租户前缀> # 缓存启用时必填(防跨项目毒化)
|
|
# PGW_CACHE_TTL_S=604800 # 缓存启用时必填,须 > 0
|
|
# PGW_STRUCTURED_MAX_RETRIES=1 # 0 = 解析失败不重问(CHS 策略)
|
|
# PGW_LEASE_TTL_S=1500 # permit 租约;须 ≥ 最大源 timeout
|
|
|
|
# ══ Redis(缓存;M2 起亦供分布式限流/熔断)══
|
|
# REDIS_URL=redis://localhost:6379/0
|