pi-ccswitch-auto-switch 0.3.13 → 0.3.15

package/README.md

@@ -144,7 +144,7 @@ The state machine waits for Pi's native retry cycle to settle before switching.
 | Failure | Scope | Initial cooldown |
 | --- | --- | --- |
 | `401`, `403`, quota, billing | Provider | 30 minutes |
-| `429` | Provider | `Retry-After` when present; otherwise 5 minutes |
+| `429` | Provider | quota/billing body (e.g. `AccountQuotaExceeded`) → 30 minutes; otherwise `Retry-After` when present, else 5 minutes |
 | DNS, network, `408`, `5xx`, interrupted stream | Endpoint | 2 minutes |
 | `404`, invalid model, incompatible parameters | Model | 15 minutes |
 | Content-policy or sensitive-content rejection | Current model + learned model-family constraint | 2-minute model cooldown; family evidence is session-scoped (cleared at `session_start`) |

package/README.zh-CN.md

@@ -132,7 +132,7 @@ CCS v0.3.5 ✓70/131 · ⏳61 · ⛔0 · 🔄3 · provider/model-id
 | 失败类型 | 熔断范围 | 初始冷却 |
 | --- | --- | --- |
 | `401`、`403`、额度或账单问题 | Provider | 30 分钟 |
-| `429` | Provider | 优先使用 `Retry-After`，否则 5 分钟 |
+| `429` | Provider | 配额/余额正文（如 `AccountQuotaExceeded`）→ 30 分钟；否则优先使用 `Retry-After`，无则 5 分钟 |
 | DNS、网络、`408`、`5xx`、流中断 | 端点 | 2 分钟 |
 | `404`、模型不存在、参数不兼容 | 模型 | 15 分钟 |
 | 内容审查/敏感拦截 | 当前模型 + 模型系列约束 | 模型冷却 2 分钟；系列约束按 session 隔离（`session_start` 时清除） |

package/classify.ts

@@ -25,7 +25,13 @@ export function classifyFailure(observation: FailureObservation): Classification
   if (content.test(text)) return { kind: 'content_policy', scope: 'model', roundOnly: false }
   if (context.test(text)) return { kind: 'context_overflow', roundOnly: true }
   if (status === 413) return { kind: 'context_overflow', roundOnly: true }
-  if (status === 429) return { kind: 'rate_limit', scope: 'provider', roundOnly: false, retryAfterMs: observation.retryAfterMs }
+  // 账户级配额耗尽常以 429 上报（如 AccountQuotaExceeded + "exceeded the 5-hour usage quota"）。
+  // quota 文本必须优先于瞬时 rate_limit：否则死 provider 只按 5min 冷却停放，
+  // 在数小时后才重置的配额窗口内被放回健康池重试。
+  if (status === 429) {
+    if (quota.test(text)) return { kind: 'quota', scope: 'provider', roundOnly: false }
+    return { kind: 'rate_limit', scope: 'provider', roundOnly: false, retryAfterMs: observation.retryAfterMs }
+  }
   if (status === 402) return { kind: 'quota', scope: 'provider', roundOnly: false }
   if (status === 403 && quota.test(text)) return { kind: 'quota', scope: 'provider', roundOnly: false }
   if (status === 401 || status === 403) return { kind: 'auth', scope: 'provider', roundOnly: false }

package/index.ts

@@ -17,7 +17,7 @@ const roundLimitMs = (): number => {
   return Number.isFinite(override) && override > 0 ? override : ROUND_LIMIT_DEFAULT
 }
 const RPC_PROTOCOL_VERSION = 1
-const EXTENSION_VERSION = '0.3.13'
+const EXTENSION_VERSION = '0.3.15'
 // 同端点（BaseURL 相同）连续失败达到该次数即隔离该端点，避免同一个平台的多个模型逐个试错耗尽本轮切换
 const ENDPOINT_FAIL_THRESHOLD = 3
 
@@ -309,9 +309,11 @@ export default function (pi: ExtensionAPI) {
     // 下一轮还会重试同一个刚失败的模型/provider
     if (!classification.roundOnly && classification.scope) health.recordFailure(classification.scope, classification.scope === 'model' ? failedKey : classification.scope === 'provider' ? round.model.provider : endpointKey(round.model), classification.kind, round.observation.message, classification.retryAfterMs)
     await health.flush()
-    // 窗口从上一次成功切换（或本轮开始）起算：供应商内部重试耗时不应消耗整轮限额
+    // 窗口从上一次成功切换（或本轮开始）起算：供应商内部重试耗时不应消耗整轮限额。
+    // 仅在本轮已成功切换过（attempts > 0）后才生效：窗口的本意是限制连续切换 churn，
+    // 长健康轮末尾的第一次失败也必须拿到兜底切换，否则轮时限会拦掉唯一一次 fallback。
     const windowStart = Math.max(round.startedAt, round.lastSwitchAt ?? 0)
-    if (Date.now() - windowStart >= roundLimitMs()) return exhaust(ctx, '超过本轮时间限制')
+    if (round.attempts > 0 && Date.now() - windowStart >= roundLimitMs()) return exhaust(ctx, '超过本轮时间限制')
     await refresh(ctx)
     const candidates = effectiveCandidates(ctx.scopedModels, ctx.modelRegistry.getAvailable())
     const candidateOptions = () => ({

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-ccswitch-auto-switch",
-  "version": "0.3.13",
+  "version": "0.3.15",
   "description": "Provider-first automatic model failover extension for Pi and CC Switch",
   "license": "MIT",
   "keywords": [

package/runner.mjs

@@ -376,5 +376,6 @@ export async function main(argv = process.argv.slice(2)) {
   }
 }
 
-const invoked = process.argv[1] && resolve(process.argv[1]) === fileURLToPath(import.meta.url)
+const invokedPath = process.argv[1] && await realpath(resolve(process.argv[1])).catch(() => undefined)
+const invoked = invokedPath === fileURLToPath(import.meta.url)
 if (invoked) main().then(code => { process.exitCode = code })