docs: align the stall window comments with the new metering

_validate_stall still guards stall_window_s >= max ttft_timeout_s, but its
stated reason no longer holds: TTFT waiting is productive time and never
reaches the stall account. The check is harmless and stays, so the
docstring now says why it is kept rather than implying a live hazard.
.env.example dropped the "must be >= max TTFT" advice for what the window
actually measures.
This commit is contained in:
2026-08-06 10:09:06 -04:00
parent 0477d9534b
commit d05114e895
2 changed files with 9 additions and 2 deletions
+1 -1
View File
@@ -38,7 +38,7 @@ LLM_CIRCUIT_BREAKER_COOLDOWN=60 # 或 LLM__BREAKER__COOLDOWN_S
# 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, 最大源超时+5);显式值须 ≥ 最大源超时+5
# LLM__BACKPRESSURE__STALL_WINDOW_S=300 # stall 双条件判死窗口;须 ≥ 最大源 TTFT
# LLM__BACKPRESSURE__STALL_WINDOW_S=300 # stall 双条件判死窗口;只计非生产性等待(429 退避/配额轮询/熔断冷却),与 TIMEOUT_S 无耦合,无需按 timeout×retries 放大
# LLM__BACKPRESSURE__POLL_INTERVAL_S=0.05
# LLM__SELECTOR=health_aware # health_aware(默认,M2.5) | round_robin | least_inflight
# ── M2.5 失败率熔断通道(可选,缺省即生产推荐值)──