pi-model-fallback 0.3.3 → 0.3.4

package/CHANGELOG.md

@@ -2,6 +2,11 @@
 
 ## Unreleased
 
+### Changed
+
+- Bump package version to `0.3.4` for the next patch release.
+
+- Declare `@earendil-works/pi-agent-core` as a peerDependency to align with pi-extension-template.
 - Add Buy Me a Coffee sponsor button to README and native GitHub funding link via `.github/FUNDING.yml`.
 
 ## [0.3.3] - 2026-07-04

package/README.md

@@ -90,6 +90,15 @@ Rule fields:
 - `cooldownMs`: optional persistent fallback window
 - `fallback`: target model Pi should switch to
 
+### Cooldowns
+
+When a rule does not set `cooldownMs`, the extension uses these defaults:
+
+- `429` → 72 hours
+- `5xx` → 10 minutes
+
+When the provider response includes `Retry-After` or `x-ratelimit-reset*` headers, those values override `cooldownMs` and the defaults for the persisted fallback window.
+
 ## State and paths
 
 The extension stores:
@@ -103,7 +112,7 @@ If the package is installed project-locally and the current project references i
 
 - Successful responses do nothing.
 - Matching failures from `after_provider_response` can trigger fallback immediately.
-- Assistant error messages parsed at `turn_end` can also persist fallback state for SDK/provider failures that do not emit the normal response hook.
+- Assistant error messages parsed at `turn_end` can also persist fallback state for SDK/provider failures that do not emit the normal response hook. Status extraction looks for HTTP-style tokens (for example `status 429`, `HTTP 503`, or `rate limit`) rather than any bare 3-digit number in the message.
 - The failed request is not automatically replayed.
 
 ## Development

package/docs/usage.md

@@ -3,7 +3,7 @@
 Install:
 
 ```bash
-pi install git:github.com/eiei114/pi-model-fallback
+pi install npm:pi-model-fallback
 ```
 
 Default behavior: when a `zai/*` model receives `429`, `500`, `502`, `503`, or `504`, Pi switches to `deepseek/deepseek-v4-flash` for the next prompt.
@@ -15,4 +15,11 @@ Commands:
 /model-fallback:reset
 ```
 
-The failed provider response is not automatically replayed in v0.1.0.
+Cooldown defaults when a rule omits `cooldownMs`:
+
+- `429` → 72 hours
+- `5xx` → 10 minutes
+
+`Retry-After` and `x-ratelimit-reset*` response headers override `cooldownMs` and those defaults.
+
+The failed request is not automatically replayed.

package/extensions/index.ts

@@ -1,4 +1,5 @@
 import { existsSync, readFileSync } from "node:fs";
+import { readFile } from "node:fs/promises";
 import { dirname, join, resolve } from "node:path";
 import { fileURLToPath } from "node:url";
 import { getAgentDir, type ExtensionAPI, type ExtensionContext } from "@earendil-works/pi-coding-agent";
@@ -12,7 +13,8 @@ import {
   type ModelFallbackConfig,
   type ModelRef,
 } from "../lib/config.js";
-import { findActiveStateEntry, readState, upsertStateEntry, writeState, type FallbackState } from "../lib/state.js";
+import { parseStatusFromErrorMessage } from "../lib/error-status.js";
+import { emptyState, findActiveStateEntry, pruneExpiredState, readState, upsertStateEntry, validateStateShape, writeState, type FallbackState } from "../lib/state.js";
 import { modelFallbackPaths, readConfig, writeConfig, type ModelFallbackPaths } from "../lib/storage.js";
 
 const PACKAGE_ROOT = dirname(dirname(fileURLToPath(import.meta.url)));
@@ -22,6 +24,7 @@ const DEFAULT_5XX_COOLDOWN_MS = 10 * 60 * 1000;
 
 export default function modelFallback(pi: ExtensionAPI) {
   let paths: ModelFallbackPaths = modelFallbackPaths(getAgentDir());
+  let pathsResolvedForCwd: string | undefined;
   let config: ModelFallbackConfig | undefined;
   let state: FallbackState | undefined;
   let originalModelKey: string | undefined;
@@ -29,6 +32,8 @@ export default function modelFallback(pi: ExtensionAPI) {
   let lastFallbackReason: string | undefined;
 
   function syncPaths(ctx: ExtensionContext): void {
+    if (pathsResolvedForCwd === ctx.cwd) return;
+    pathsResolvedForCwd = ctx.cwd;
     paths = shouldUseProjectLocalState(ctx) ? modelFallbackPaths(join(ctx.cwd, ".pi")) : modelFallbackPaths(getAgentDir());
   }
 
@@ -46,8 +51,18 @@ export default function modelFallback(pi: ExtensionAPI) {
   async function loadState(ctx: ExtensionContext): Promise<FallbackState | undefined> {
     try {
       syncPaths(ctx);
-      state = await readState(paths.state);
-      await writeState(paths.state, state);
+      const statePath = paths.state;
+      if (!existsSync(statePath)) {
+        state = emptyState();
+        return state;
+      }
+
+      const before = validateStateShape(JSON.parse(await readFile(statePath, "utf8")));
+      const after = pruneExpiredState(before);
+      state = after;
+      if (JSON.stringify(before) !== JSON.stringify(after)) {
+        await writeState(statePath, after);
+      }
       return state;
     } catch (error) {
       ctx.ui.notify(`Model fallback state error: ${errorMessage(error)}`, "warning");
@@ -343,7 +358,7 @@ function parseRetryAfter(value: string | undefined): number | undefined {
   return undefined;
 }
 
-function parseResetHeader(value: string | undefined): number | undefined {
+function parseResetHeader(value: string | undefined): number | undefined {
   if (!value) return undefined;
   const trimmed = value.trim();
   const numeric = Number(trimmed);
@@ -354,17 +369,10 @@ function parseResetHeader(value: string | undefined): number | undefined {
   }
   const dateMs = Date.parse(trimmed);
   if (!Number.isNaN(dateMs) && dateMs > Date.now()) return dateMs - Date.now();
-  return undefined;
-}
-
-function parseStatusFromErrorMessage(message: string): number | undefined {
-  const match = message.match(/\b([1-5][0-9]{2})\b/);
-  if (!match) return undefined;
-  const status = Number(match[1]);
-  return Number.isInteger(status) ? status : undefined;
-}
-
-function modelToRef(model: { provider: string; id: string }): ModelRef {
+  return undefined;
+}
+
+function modelToRef(model: { provider: string; id: string }): ModelRef {
   return { provider: model.provider, model: model.id };
 }
 

package/lib/error-status.ts

@@ -0,0 +1,18 @@
+export function parseStatusFromErrorMessage(message: string): number | undefined {
+  const patterns: RegExp[] = [
+    /\b(?:status|code|http)\s*[:\s]?\s*([1-5][0-9]{2})\b/i,
+    /\bHTTP\/\d(?:\.\d)?\s+([1-5][0-9]{2})\b/,
+    /\b(?:rate[\s-]?limit(?:ed)?|too many requests)[^0-9]{0,40}([45][0-9]{2})\b/i,
+    /\b([45][0-9]{2})\s+(?:error|too many requests|service unavailable|bad gateway|gateway timeout|internal server error)\b/i,
+    /\berror\s+([45][0-9]{2})\b/i,
+  ];
+
+  for (const pattern of patterns) {
+    const match = message.match(pattern);
+    if (!match) continue;
+    const status = Number(match[1]);
+    if (Number.isInteger(status) && status >= 100 && status <= 599) return status;
+  }
+
+  return undefined;
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-model-fallback",
-  "version": "0.3.3",
+  "version": "0.3.4",
   "description": "Pi extension that switches to a fallback model after provider failures such as 429 rate limits.",
   "type": "module",
   "license": "MIT",
@@ -43,15 +43,17 @@
     "access": "public"
   },
   "peerDependencies": {
+    "@earendil-works/pi-agent-core": "*",
     "@earendil-works/pi-ai": "*",
     "@earendil-works/pi-coding-agent": "*",
     "@earendil-works/pi-tui": "*",
     "typebox": "*"
   },
   "devDependencies": {
-    "@earendil-works/pi-ai": "latest",
-    "@earendil-works/pi-coding-agent": "latest",
-    "@earendil-works/pi-tui": "latest",
+    "@earendil-works/pi-agent-core": "^0.80.6",
+    "@earendil-works/pi-ai": "^0.80.6",
+    "@earendil-works/pi-coding-agent": "^0.80.6",
+    "@earendil-works/pi-tui": "^0.80.6",
     "typebox": "latest",
     "@types/node": "^26.0.0",
     "typescript": "^6.0.3"