oira666_pi-limits-wait 0.4.11 → 0.4.12

package/README.md

@@ -1,87 +1,87 @@
-# Pi Limits Wait
-
-[![npm](https://img.shields.io/npm/v/oira666_pi-limits-wait?style=flat-square&logo=npm&logoColor=white&label=npm&color=7c3aed)](https://www.npmjs.com/package/oira666_pi-limits-wait) [![node](https://img.shields.io/badge/node-%3E%3D18-7c3aed?style=flat-square&logo=nodedotjs&logoColor=white)](https://nodejs.org)
-
-Pi extension that keeps requests alive when a provider rate-limits you or returns `server_is_overloaded`.
-
-## Install
-
-```bash
-pi install npm:oira666_pi-limits-wait
-```
-
-Restart Pi or run `/reload` after installing.
-
-## What it does
-
-- Works with all Pi model providers/APIs that use `streamSimple`.
-- On rate-limit errors (`429`, `rate_limit`, `too many requests`, quota/reset messages), waits and retries in a loop.
-- Uses provider retry timing when available (`retry-after`, `retry-after-ms`, `retry in ...`, reset messages).
-- If no retry timing is available for a rate limit, waits 30 minutes before retrying.
-- On `server_is_overloaded`, waits 5 minutes, then retries. If the provider is still overloaded after Pi's normal retries, it waits another 5 minutes and repeats.
-- On transient network/transport failures — including undici idle-timeout aborts (`UND_ERR_HEADERS_TIMEOUT` / `UND_ERR_BODY_TIMEOUT`), `fetch failed`, `terminated`, `ECONNRESET`, `ETIMEDOUT`, etc. — treats the error as retryable with a short backoff (default 15s, or the provider's `retry-after`) instead of giving up. This prevents a stalled streaming request from turning into a silent hang.
-- For any other (unclassified) non-retryable error, retries the same model a few times (default 3) before falling back / freezing it, so a one-off hiccup does not immediately sideline a model.
-- Reports retry/fallback waits in chat notifications without adding persistent TUI status lines.
-- Press Enter during a retry wait to skip the wait and retry immediately.
-- Optionally falls back to configured models when the current/default model is rate-limited.
-
-## Optional fallback models
-
-By default, if you do not configure fallback models, the extension behaves exactly as before: it waits for the current model's limit to reset and retries.
-
-To enable automatic model fallback, add `fallback-models` to a `limits-wait.json` file.
-
-The extension reads these files in order; later files override earlier ones:
-
-| Location | Scope |
-|----------|-------|
-| `~/.config/.pi/limits-wait.json` | Global defaults |
-| `<Pi agent dir>/limits-wait.json` (for example `~/.pi/agent/limits-wait.json`, or `PI_CODING_AGENT_DIR/limits-wait.json`) | Pi agent directory |
-| `.limits-wait.json` | Project root override |
-| `.pi/limits-wait.json` | Pi project override |
-
-Example:
-
-```json
-{
-  "fallback-models": [
-    {
-      "provider": "anthropic",
-      "modelname": "claude-sonnet-4-5",
-      "reasoning effort": "medium"
-    },
-    {
-      "provider": "openai",
-      "modelname": "gpt-5.1-codex"
-    }
-  ]
-}
-```
-
-Each `fallback-models` entry supports:
-
-- `provider` — required. The Pi provider name, for example `anthropic`, `openai`, `google`, etc.
-- `modelname` — required. The model id/name as Pi knows it.
-- `reasoning effort` — optional. One of `off`, `minimal`, `low`, `medium`, `high`, `xhigh`. If omitted, Pi's current/default reasoning level is used.
-
-Fallback behavior:
-
-1. Pi starts with the normal default or user-selected model.
-2. If that model is rate-limited, the extension tries models in this order:
-   - the original default/user-selected model;
-   - then every model from `fallback-models`, top to bottom.
-3. The first model that responds without a rate-limit becomes the active Pi model for the rest of the session/task.
-4. If that model later becomes rate-limited too, the extension starts again from the same ordered list.
-5. Rate-limit reset times are remembered only in memory, so known-limited models are skipped until their countdown expires. This memory is cleared when Pi restarts.
-
-When the settings are loaded, the extension shows the full usable fallback model list. When models become rate-limited, it reports the wait in chat notifications.
-
-## Environment variables
-
-| Variable | Default | Description |
-|----------|---------|-------------|
-| `PI_LIMITS_WAIT_FREEZING_ENABLED` | `true` | When a model keeps failing with a non-retryable error, it is normally "frozen" for 1 hour and skipped in favour of other configured models. Set this to `false` (also accepts `0`, `no`, `off`) to disable freezing entirely: the extension will instead try each configured candidate once (after the bounded retries) and then surface the error, never blocking on a long "model-frozen" wait. Useful for non-interactive / subagent runs where no one can press Enter to skip. |
-
-## License
-
-MIT
+# Pi Limits Wait
+
+[![npm](https://img.shields.io/npm/v/oira666_pi-limits-wait?style=flat-square&logo=npm&logoColor=white&label=npm&color=7c3aed)](https://www.npmjs.com/package/oira666_pi-limits-wait) [![node](https://img.shields.io/badge/node-%3E%3D18-7c3aed?style=flat-square&logo=nodedotjs&logoColor=white)](https://nodejs.org)
+
+Pi extension that keeps requests alive when a provider rate-limits you or returns `server_is_overloaded`.
+
+## Install
+
+```bash
+pi install npm:oira666_pi-limits-wait
+```
+
+Restart Pi or run `/reload` after installing.
+
+## What it does
+
+- Works with all Pi model providers/APIs that use `streamSimple`.
+- On rate-limit errors (`429`, `rate_limit`, `too many requests`, quota/reset messages), waits and retries in a loop.
+- Uses provider retry timing when available (`retry-after`, `retry-after-ms`, `retry in ...`, reset messages).
+- If no retry timing is available for a rate limit, waits 30 minutes before retrying.
+- On `server_is_overloaded`, waits 5 minutes, then retries. If the provider is still overloaded after Pi's normal retries, it waits another 5 minutes and repeats.
+- On transient network/transport failures — including undici idle-timeout aborts (`UND_ERR_HEADERS_TIMEOUT` / `UND_ERR_BODY_TIMEOUT`), `fetch failed`, `terminated`, `ECONNRESET`, `ETIMEDOUT`, etc. — treats the error as retryable with a short backoff (default 15s, or the provider's `retry-after`) instead of giving up. This prevents a stalled streaming request from turning into a silent hang.
+- For any other (unclassified) non-retryable error, retries the same model a few times (default 3) before falling back / freezing it, so a one-off hiccup does not immediately sideline a model.
+- Reports retry/fallback waits in chat notifications without adding persistent TUI status lines.
+- Press Enter during a retry wait to skip the wait and retry immediately.
+- Optionally falls back to configured models when the current/default model is rate-limited.
+
+## Optional fallback models
+
+By default, if you do not configure fallback models, the extension behaves exactly as before: it waits for the current model's limit to reset and retries.
+
+To enable automatic model fallback, add `fallback-models` to a `limits-wait.json` file.
+
+The extension reads these files in order; later files override earlier ones:
+
+| Location | Scope |
+|----------|-------|
+| `~/.config/.pi/limits-wait.json` | Global defaults |
+| `<Pi agent dir>/limits-wait.json` (for example `~/.pi/agent/limits-wait.json`, or `PI_CODING_AGENT_DIR/limits-wait.json`) | Pi agent directory |
+| `.limits-wait.json` | Project root override |
+| `.pi/limits-wait.json` | Pi project override |
+
+Example:
+
+```json
+{
+  "fallback-models": [
+    {
+      "provider": "anthropic",
+      "modelname": "claude-sonnet-4-5",
+      "reasoning effort": "medium"
+    },
+    {
+      "provider": "openai",
+      "modelname": "gpt-5.1-codex"
+    }
+  ]
+}
+```
+
+Each `fallback-models` entry supports:
+
+- `provider` — required. The Pi provider name, for example `anthropic`, `openai`, `google`, etc.
+- `modelname` — required. The model id/name as Pi knows it.
+- `reasoning effort` — optional. One of `off`, `minimal`, `low`, `medium`, `high`, `xhigh`. If omitted, Pi's current/default reasoning level is used.
+
+Fallback behavior:
+
+1. Pi starts with the normal default or user-selected model.
+2. If that model is rate-limited, the extension tries models in this order:
+   - the original default/user-selected model;
+   - then every model from `fallback-models`, top to bottom.
+3. The first model that responds without a rate-limit becomes the active Pi model for the rest of the session/task.
+4. If that model later becomes rate-limited too, the extension starts again from the same ordered list.
+5. Rate-limit reset times are remembered only in memory, so known-limited models are skipped until their countdown expires. This memory is cleared when Pi restarts.
+
+When the settings are loaded, the extension shows the full usable fallback model list. When models become rate-limited, it reports the wait in chat notifications.
+
+## Environment variables
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `PI_LIMITS_WAIT_FREEZING_ENABLED` | `true` | When a model keeps failing with a non-retryable error, it is normally "frozen" for 1 hour and skipped in favour of other configured models. Set this to `false` (also accepts `0`, `no`, `off`) to disable freezing entirely: the extension will instead try each configured candidate once (after the bounded retries) and then surface the error, never blocking on a long "model-frozen" wait. Useful for non-interactive / subagent runs where no one can press Enter to skip. |
+
+## License
+
+MIT

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oira666_pi-limits-wait",
-  "version": "0.4.11",
+  "version": "0.4.12",
   "description": "Extension for PI that allows to automatically wait for limits to reset and retry the request",
   "type": "module",
   "license": "MIT",

package/src/constants.ts

@@ -1,23 +1,26 @@
-export const CLAUDE_CODE_IDENTITY =
-  "You are Claude Code, Anthropic's official CLI for Claude.";
-
-export const PI_REMOVAL_ANCHORS = [
-  "pi-coding-agent",
-  "@mariozechner/pi-coding-agent",
-  "badlogic/pi-mono",
-] as const;
-
-export const PI_IDENTITY_SENTENCE_PATTERN =
-  /(?:^|\n)\s*You are pi\b[^.!?\n]*(?:[.!?](?=\s|$)|(?=\n|$))/gi;
-
-export const DEFAULT_RATE_LIMIT_WAIT_MS = 30 * 60 * 1_000; // 30 minutes
-export const DEFAULT_OVERLOADED_WAIT_MS = 5 * 60 * 1_000; // 5 minutes
-export const DEFAULT_NETWORK_WAIT_MS = 15 * 1_000; // 15 seconds
-export const DEFAULT_NON_RETRYABLE_FREEZE_MS = 10 * 60 * 1_000; // 10 minutes
-
-export const NON_RETRYABLE_MAX_ATTEMPTS = 3;
-export const NON_RETRYABLE_RETRY_DELAY_MS = 5 * 1_000; // 5 seconds
-
-export const SETTINGS_FILE_NAME = "limits-wait.json";
-export const FALLBACK_MODELS_KEY = "fallback-models";
-export const FREEZING_ENV_VAR = "PI_LIMITS_WAIT_FREEZING_ENABLED";
+export const CLAUDE_CODE_IDENTITY =
+  "You are Claude Code, Anthropic's official CLI for Claude.";
+
+export const PI_REMOVAL_ANCHORS = [
+  "pi-coding-agent",
+  "@mariozechner/pi-coding-agent",
+  "badlogic/pi-mono",
+] as const;
+
+export const PI_IDENTITY_SENTENCE_PATTERN =
+  /(?:^|\n)\s*You are pi\b[^.!?\n]*(?:[.!?](?=\s|$)|(?=\n|$))/gi;
+
+export const CLAUDE_CODE_IDENTITY_PATTERN =
+  /(?:^|\n)\s*You are Claude Code, Anthropic's official CLI for Claude\.\s*/gi;
+
+export const DEFAULT_RATE_LIMIT_WAIT_MS = 30 * 60 * 1_000; // 30 minutes
+export const DEFAULT_OVERLOADED_WAIT_MS = 5 * 60 * 1_000; // 5 minutes
+export const DEFAULT_NETWORK_WAIT_MS = 15 * 1_000; // 15 seconds
+export const DEFAULT_NON_RETRYABLE_FREEZE_MS = 10 * 60 * 1_000; // 10 minutes
+
+export const NON_RETRYABLE_MAX_ATTEMPTS = 3;
+export const NON_RETRYABLE_RETRY_DELAY_MS = 5 * 1_000; // 5 seconds
+
+export const SETTINGS_FILE_NAME = "limits-wait.json";
+export const FALLBACK_MODELS_KEY = "fallback-models";
+export const FREEZING_ENV_VAR = "PI_LIMITS_WAIT_FREEZING_ENABLED";

package/src/fetch-observer.ts

@@ -1,49 +1,49 @@
-import { DEFAULT_RATE_LIMIT_WAIT_MS } from "./constants.js";
-import { retryAfterHeaderMs } from "./retry-errors.js";
-import { state } from "./state.js";
-import { formatErrorDetail, showAmbientRetryStatus, clearAmbientRetryStatus } from "./ui.js";
-
-async function responseErrorMessage(response: Response): Promise<string> {
-  const retryAfterMs = retryAfterHeaderMs(response.headers);
-  const retryAfter = retryAfterMs !== undefined ? ` retry-after-ms ${retryAfterMs}` : "";
-  let body = "";
-  try {
-    body = await response.clone().text();
-  } catch {
-    // Ignore body read failures; status and retry headers are enough.
-  }
-  const detail = body.trim() ? ` ${formatErrorDetail(body)}` : "";
-  return `HTTP ${response.status}${response.statusText ? ` ${response.statusText}` : ""}${retryAfter}${detail}`;
-}
-
-export function installFetchRateLimitObserver(): void {
-  if (state.restoreFetch || typeof globalThis.fetch !== "function") return;
-
-  const originalFetch = globalThis.fetch.bind(globalThis);
-  globalThis.fetch = (async (...args: Parameters<typeof fetch>) => {
-    const response = await originalFetch(...args);
-
-    if (state.activeProviderRequests > 0) {
-      if (!response.ok) {
-        const message = await responseErrorMessage(response);
-        state.lastObservedHttpError = { at: Date.now(), message };
-        if (response.status === 429) {
-          const waitMs = retryAfterHeaderMs(response.headers) ?? DEFAULT_RATE_LIMIT_WAIT_MS;
-          showAmbientRetryStatus("rate-limit", waitMs);
-          if (state.activeFallbackProviderRequests > 0) {
-            throw new Error(message);
-          }
-        }
-      } else if (state.ambientStatusCleanup && response.ok) {
-        clearAmbientRetryStatus();
-      }
-    }
-
-    return response;
-  }) as typeof fetch;
-
-  state.restoreFetch = () => {
-    globalThis.fetch = originalFetch as typeof fetch;
-    state.restoreFetch = undefined;
-  };
-}
+import { DEFAULT_RATE_LIMIT_WAIT_MS } from "./constants.js";
+import { retryAfterHeaderMs } from "./retry-errors.js";
+import { state } from "./state.js";
+import { formatErrorDetail, showAmbientRetryStatus, clearAmbientRetryStatus } from "./ui.js";
+
+async function responseErrorMessage(response: Response): Promise<string> {
+  const retryAfterMs = retryAfterHeaderMs(response.headers);
+  const retryAfter = retryAfterMs !== undefined ? ` retry-after-ms ${retryAfterMs}` : "";
+  let body = "";
+  try {
+    body = await response.clone().text();
+  } catch {
+    // Ignore body read failures; status and retry headers are enough.
+  }
+  const detail = body.trim() ? ` ${formatErrorDetail(body)}` : "";
+  return `HTTP ${response.status}${response.statusText ? ` ${response.statusText}` : ""}${retryAfter}${detail}`;
+}
+
+export function installFetchRateLimitObserver(): void {
+  if (state.restoreFetch || typeof globalThis.fetch !== "function") return;
+
+  const originalFetch = globalThis.fetch.bind(globalThis);
+  globalThis.fetch = (async (...args: Parameters<typeof fetch>) => {
+    const response = await originalFetch(...args);
+
+    if (state.activeProviderRequests > 0) {
+      if (!response.ok) {
+        const message = await responseErrorMessage(response);
+        state.lastObservedHttpError = { at: Date.now(), message };
+        if (response.status === 429) {
+          const waitMs = retryAfterHeaderMs(response.headers) ?? DEFAULT_RATE_LIMIT_WAIT_MS;
+          showAmbientRetryStatus("rate-limit", waitMs);
+          if (state.activeFallbackProviderRequests > 0) {
+            throw new Error(message);
+          }
+        }
+      } else if (state.ambientStatusCleanup && response.ok) {
+        clearAmbientRetryStatus();
+      }
+    }
+
+    return response;
+  }) as typeof fetch;
+
+  state.restoreFetch = () => {
+    globalThis.fetch = originalFetch as typeof fetch;
+    state.restoreFetch = undefined;
+  };
+}

package/src/index.ts

@@ -1,7 +1,5 @@
 import type { ExtensionAPI } from "@mariozechner/pi-coding-agent";
-import { CLAUDE_CODE_IDENTITY } from "./constants.js";
 import { isInternalSyntheticModel } from "./models.js";
-import { isAnthropicOAuthSession, sanitiseSystemPrompt } from "./prompt.js";
 import { loadFallbackSettings } from "./settings.js";
 import { state } from "./state.js";
 import { registerWrappedApi } from "./stream.js";
@@ -44,7 +42,7 @@ export default function (pi: ExtensionAPI) {
     state.primaryThinkingLevel = pi.getThinkingLevel();
   });
 
-  pi.on("before_agent_start", (event, ctx) => {
+  pi.on("before_agent_start", (_event, ctx) => {
     state.sharedCtx = ctx;
     if (!state.primaryModel && ctx.model && !isInternalSyntheticModel(ctx.model)) state.primaryModel = ctx.model;
     state.primaryThinkingLevel ??= pi.getThinkingLevel();
@@ -57,14 +55,9 @@ export default function (pi: ExtensionAPI) {
     }
     if (ctx.model && !isInternalSyntheticModel(ctx.model)) registerWrappedApi(pi, ctx.model.api);
 
-    // Anthropic subscription/OAuth requests identify as Claude Code, not Pi.
-    if (!isAnthropicOAuthSession(ctx)) return;
-
-    const sanitised = sanitiseSystemPrompt(event.systemPrompt);
-    return {
-      systemPrompt: sanitised
-        ? `${CLAUDE_CODE_IDENTITY}\n\n${sanitised}`
-        : CLAUDE_CODE_IDENTITY,
-    };
+    // Anthropic subscription/OAuth identity is applied per provider request in
+    // streamWithLimitsRetry(). Doing it there ensures every retry/fallback
+    // attempt gets the right prompt for its actual target model, while
+    // non-Anthropic providers never inherit the Claude Code identity.
   });
 }