@monotykamary/pi-retry 0.8.1 → 0.8.2

package/README.md

@@ -167,7 +167,7 @@ Exhausted quotas, session limits, and budgets are auto-detected and stop the ret
 - **Usage / session limits with reset windows** — "You've hit your limit · resets …" and "5-hour limit reached" (Claude Code), "You've hit your usage limit" / "You've exceeded your usage limit" (Codex), "You have hit your ChatGPT usage limit (plus plan)" (ChatGPT subscription caps via the Codex backend, also `usage_limit_reached`)
 - **Plan / billing quotas** — OpenAI `insufficient_quota`, "You exceeded your current quota, please check your plan and billing details" (OpenAI, Gemini — reached only after pi's built-in 429 retry gives up)
 - **Google subscription caps** — "You have exhausted your capacity on this model. Your quota will reset after …" (Gemini Code Assist), "You have reached the quota limit for …" / "You can resume using this model at …" (Antigravity)
-- **Hard allotments** — OpenRouter `free-models-per-day`, Alibaba "Allocated quota exceeded" (`Throttling.AllocationQuota`), GitHub Copilot "premium request allowance", z.ai GLM Coding Plan "Usage limit reached for 5 hour" / "no resource package"
+- **Hard allotments** — OpenRouter `free-models-per-day`, Alibaba Coding Plan window quotas "hour/week/month allocated quota exceeded" and free-quota exhaustion "free allocated quota exceeded" (the bare "Allocated quota exceeded" is TPM rate limiting and stays retryable), GitHub Copilot "premium request allowance", z.ai GLM Coding Plan "Usage limit reached for 5 hour" / "no resource package"
 - **Budget exhaustion** — "out of budget", "Budget has been exceeded" (LiteLLM-style proxies), max/spending/monthly limits
 - **Suspended accounts** — "Your account … is suspended" (Kimi `exceeded_current_quota_error`)
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@monotykamary/pi-retry",
-  "version": "0.8.1",
+  "version": "0.8.2",
   "description": "Extension suite for pi coding agent that handles 400/413 errors and connection errors with automatic retry",
   "type": "module",
   "author": "Tom X Nguyen",

package/src/error-patterns.ts

@@ -157,8 +157,11 @@ const SILENCED_PATTERNS = [
 //     (Thinking). You can resume using this model at …" (Antigravity)
 // - OpenRouter:   "Rate limit exceeded: free-models-per-day. ..."
 // - Alibaba:      "Allocated quota exceeded, please increase your quota limit"
-//                 (Throttling.AllocationQuota — hard cap; RateQuota is
-//                 transient and stays retryable)
+//                 (429 Throttling.AllocationQuota / insufficient_quota) — TPM
+//                 token rate limiting, transient, auto-recovers in minutes;
+//                 stays retryable. Matched only when prefixed by a hard-cap
+//                 window: "hour|week|month allocated quota exceeded" (Coding
+//                 Plan) and "free allocated quota exceeded" (free quota drained)
 // - Copilot:      "You have exceeded your premium request allowance"
 // - LiteLLM:      "Budget has been exceeded! Current cost: …, Max budget: …"
 // - Kimi:         "Your account {org}<{ak}> is suspended, please check your
@@ -171,8 +174,9 @@ const SILENCED_PATTERNS = [
 //
 // Deliberately retryable (verified, kept out): DeepSeek 402 "Insufficient
 // Balance" and 429 "Rate Limit Reached" (concurrency), Kimi TPD org limits
-// and "exceeded your current token quota" (balance). See the note on
-// hasQuotaExhaustedError below.
+// and "exceeded your current token quota" (balance), Alibaba "Allocated quota
+// exceeded" (429 Throttling.AllocationQuota — TPM rate limiting, recovers in
+// minutes). See the note on hasQuotaExhaustedError below.
 export const QUOTA_EXHAUSTED_PATTERNS = [
   // Session / usage limits with reset windows (Claude, Codex, ChatGPT plans)
   /hit your (?:[a-z]+ )?usage limit/i, // "…hit your usage limit", "…hit your ChatGPT usage limit (plus plan)" — the optional word is the provider name; "hit your rate limit" intentionally NOT matched (burst limit stays retryable)
@@ -188,7 +192,14 @@ export const QUOTA_EXHAUSTED_PATTERNS = [
   /exceeded your current quota/i, // Kimi's "...current token quota" (balance, retryable) intentionally not matched
   // Hard allotments
   /free.models.per.day/i, // OpenRouter free-tier daily pool
-  /allocated\s*quota/i, // Alibaba Throttling.AllocationQuota
+  // Alibaba: bare "Allocated quota exceeded" (429 Throttling.AllocationQuota /
+  // insufficient_quota) is TPM token rate limiting — transient, auto-recovers
+  // in minutes, retryable — NOT matched here. Only the Coding Plan window
+  // quotas (hour/week/month) and free-quota exhaustion are true hard caps.
+  /hour\s*allocated\s*quota/i, // "hour allocated quota exceeded" (Coding Plan)
+  /week\s*allocated\s*quota/i, // "week allocated quota exceeded" (Coding Plan)
+  /month\s*allocated\s*quota/i, // "month allocated quota exceeded" (Coding Plan)
+  /free\s*allocated\s*quota/i, // "free allocated quota exceeded" (free quota drained)
   /premium\s*request\s*allowance/i, // GitHub Copilot monthly allowance
   /monthly\s*(limit|quota|budget|allowance)/i,
   // Budget exhaustion (LiteLLM and similar proxies/gateways)