oira666_pi-limits-wait 0.6.1 → 0.6.2

package/README.md

@@ -16,6 +16,7 @@ Restart Pi or run `/reload` after installing.
 
 - Targets Pi 0.80.10+ (developed and tested against Pi 0.83.0) and works with model providers that use `ModelRuntime.streamSimple`.
 - Intercepts the current runtime without registering synthetic providers; every retry and fallback re-enters Pi's normal provider/auth/base URL/configured-header composition, including OAuth refresh checks.
+- On Pi 0.86+, stops background cache warming via `cache_warming_decision` while retry interception is enabled, preventing background refreshes from triggering foreground retries or fallbacks. Normal request caching is unchanged. With `PI_LIMITS_WAIT_DISABLE_ALL_WAITING=true`, Pi's cache-warming policy is left untouched. As with any handler for this event, a later extension can override the decision.
 - Reload-safe ownership ensures `/reload` transfers interception cleanly and aborts waits still owned by the previous extension instance. The interception has one process-global active extension owner, matching the interactive Pi CLI's single active session runtime lifecycle; SDK processes running multiple concurrent Pi sessions are not supported.
 - On rate-limit errors (`429`, `rate_limit`, `too many requests`, quota/reset messages), waits and retries in a loop.
 - Remembers provider retry timing exposed through response callbacks or provider errors (`retry-after`, `retry-after-ms`, `retry in ...`, reset messages). With fallback probing enabled, explicit Retry-After deadlines may intentionally be probed early; set the probe interval to `0` to honor those deadlines (unless a wait is manually skipped).

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oira666_pi-limits-wait",
-  "version": "0.6.1",
+  "version": "0.6.2",
   "description": "Extension for PI that allows to automatically wait for limits to reset and retry the request",
   "type": "module",
   "exports": {

package/src/constants.ts

@@ -43,7 +43,7 @@ export const DEFAULT_LIVELINESS_INTERVAL_MS = 15 * 1_000; // 15 seconds
 export const LIVELINESS_JSON_STATUS_KEY = "oira666.pi-limits-wait.json";
 /** Payload schema version for LIVELINESS_JSON_STATUS_KEY. Bump only on a breaking change. */
 export const LIVELINESS_JSON_VERSION = 1;
-export const EXTENSION_VERSION = "0.6.0";
+export const EXTENSION_VERSION = "0.6.2";
 
 export const SETTINGS_FILE_NAME = "limits-wait.json";
 export const FALLBACK_MODELS_KEY = "fallback-models";

package/src/index.ts

@@ -1,166 +1,174 @@
-import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
-import { isInternalSyntheticModel } from "./models.js";
-import { sanitiseAnthropicPayloadSystem } from "./prompt.js";
-import { RetrySummaryCoordinator } from "./retry-summary.js";
-import { loadFallbackSettings } from "./settings.js";
-import { allWaitingDisabled, loadUnknownErrorRetrySettings } from "./ui.js";
-import { consumeExpectedModelSelection, state } from "./state.js";
-import { disableModelRuntimeInterception, installModelRuntimeInterception } from "./stream.js";
-
-export { sanitiseAnthropicPayloadSystem, sanitiseSystemPrompt } from "./prompt.js";
-export {
-  getRetryableError,
-  isAuthenticationRefreshError,
-  isRateLimitError,
-  isServerOverloadedError,
-  isTransientNetworkError,
-  parseRetryDelayMs,
-  rateLimitWaitMs,
-  retryAfterHeaderMs,
-} from "./retry-errors.js";
-export {
-  __readFallbackSettingsForTests,
-  configFileCandidates,
-  parseProbeIntervalSeconds,
-  readFallbackSettings,
-} from "./settings.js";
-export {
-  blockedState,
-  candidateOrder,
-  earliestCandidateWakeup,
-  initialAttempt,
-  isModelBlocked,
-  nextAttemptCandidate,
-  nextAvailableCandidate,
-  probeIntervalMs,
-} from "./models.js";
-export {
-  __createRetrySummaryCoordinatorForTests,
-  LIMITS_WAIT_ENTRY_TYPE,
-  RetrySummaryCoordinator,
-} from "./retry-summary.js";
-export {
-  LIMITS_WAIT_EVENT_CHANNEL,
-} from "./telemetry.js";
-export {
-  CONTROL_FILE_ENV_VAR,
-  EXTENSION_VERSION,
-  LIVELINESS_JSON_STATUS_KEY,
-  LIVELINESS_JSON_VERSION,
-  LIVELINESS_STATUS_KEY,
-  PROBE_INTERVAL_ENV_VAR,
-  STATUS_JSON_ENV_VAR,
-} from "./constants.js";
-export {
-  clearStatusJson,
-  controlFilePath,
-  publishStatusJson,
-  statusJsonEnabled,
-  statusPayload,
-} from "./status-json.js";
-export type {
-  LimitsWaitStatusContext,
-  LimitsWaitStatusEvent,
-  LimitsWaitStatusPayload,
-} from "./status-json.js";
-export type {
-  LimitsWaitEndEventPayload,
-  LimitsWaitEventPayload,
-  LimitsWaitModel,
-  LimitsWaitOutcome,
-  LimitsWaitStartEventPayload,
-  LimitsWaitWaitEndPayload,
-  LimitsWaitWaitEventPayload,
-  LimitsWaitWaitOutcome,
-  LimitsWaitWaitStartPayload,
-} from "./telemetry.js";
-export type { LimitsWaitSessionEntryData } from "./retry-summary.js";
-export {
-  __configureFallbackModelsForTests,
-  __setNonRetryableTuningForTests,
-  __setProbeIntervalForTests,
-  disableModelRuntimeInterception,
-  installModelRuntimeInterception,
-  streamWithLimitsRetry,
-  streamWithRateLimitRetry,
-} from "./stream.js";
-export {
-  allWaitingDisabled,
-  clearLivelinessStatus,
-  configuredProbeIntervalMs,
-  freezingEnabled,
-  isNonInteractiveHost,
-  loadUnknownErrorRetrySettings,
-  notifyFinalFailure,
-  notifyLiveliness,
-  waitForRateLimit,
-  waitForRetry,
-} from "./ui.js";
-export type { FallbackModel } from "./types.js";
-
-export default function (pi: ExtensionAPI) {
-  // Current pi-ai inserts the Claude Code identity as the first system block
-  // for Anthropic OAuth. Sanitise only that exact payload shape; authentication,
-  // identity insertion, Anthropic headers, and all other request composition
-  // remain owned by ModelRuntime.
-  pi.on("before_provider_request", (event) => sanitiseAnthropicPayloadSystem(event.payload));
-
-  // Keep prompt sanitisation and the runtime's normal Anthropic header path,
-  // but install no retry/error interception or retry-related lifecycle hooks.
-  if (allWaitingDisabled()) {
-    disableModelRuntimeInterception();
-    return;
-  }
-
-  state.extensionApi = pi;
-  loadUnknownErrorRetrySettings();
-  const retrySummaries = new RetrySummaryCoordinator(pi);
-  const releaseInterception = installModelRuntimeInterception(() => retrySummaries.createStream());
-
-  pi.on("model_select", (event, ctx) => {
-    state.sharedCtx = ctx;
-    if (consumeExpectedModelSelection(event.model)) return;
-    if (isInternalSyntheticModel(event.model)) return;
-    state.primaryModel = event.model;
-    state.primaryThinkingLevel = pi.getThinkingLevel();
-    state.userModelSelectionGeneration++;
-    // A user-selected model takes precedence over a pending retry. Wake every
-    // wait so its stream can adopt the new primary model immediately.
-    for (const skip of [...state.activeWaitSkips]) skip();
-  });
-
-  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();
-    loadFallbackSettings(ctx);
-  });
-
-  pi.on("agent_start", (_event, ctx) => {
-    state.sharedCtx = ctx;
-  });
-
-  // turn_end runs after Pi has persisted the assistant turn, so these custom
-  // entries remain durable transcript metadata without entering LLM context.
-  pi.on("turn_end", () => {
-    retrySummaries.flush();
-  });
-
-  pi.on("agent_end", () => {
-    retrySummaries.finalizeAndFlush();
-  });
-
-  pi.on("session_shutdown", () => {
-    // An old extension instance must not disable or clear state owned by a
-    // newer /reload instance.
-    const ownsInterception = releaseInterception();
-    retrySummaries.finalizeAndFlush();
-    if (!ownsInterception) return;
-    state.ambientStatusCleanup?.();
-    state.modelStatusCleanup?.();
-    state.expectedModelSelections.clear();
-    state.activeWaitSkips.clear();
-    state.sharedCtx = undefined;
-    state.extensionApi = undefined;
-  });
-}
+import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
+import { isInternalSyntheticModel } from "./models.js";
+import { sanitiseAnthropicPayloadSystem } from "./prompt.js";
+import { RetrySummaryCoordinator } from "./retry-summary.js";
+import { loadFallbackSettings } from "./settings.js";
+import { allWaitingDisabled, loadUnknownErrorRetrySettings } from "./ui.js";
+import { consumeExpectedModelSelection, state } from "./state.js";
+import { disableModelRuntimeInterception, installModelRuntimeInterception } from "./stream.js";
+
+export { sanitiseAnthropicPayloadSystem, sanitiseSystemPrompt } from "./prompt.js";
+export {
+  getRetryableError,
+  isAuthenticationRefreshError,
+  isRateLimitError,
+  isServerOverloadedError,
+  isTransientNetworkError,
+  parseRetryDelayMs,
+  rateLimitWaitMs,
+  retryAfterHeaderMs,
+} from "./retry-errors.js";
+export {
+  __readFallbackSettingsForTests,
+  configFileCandidates,
+  parseProbeIntervalSeconds,
+  readFallbackSettings,
+} from "./settings.js";
+export {
+  blockedState,
+  candidateOrder,
+  earliestCandidateWakeup,
+  initialAttempt,
+  isModelBlocked,
+  nextAttemptCandidate,
+  nextAvailableCandidate,
+  probeIntervalMs,
+} from "./models.js";
+export {
+  __createRetrySummaryCoordinatorForTests,
+  LIMITS_WAIT_ENTRY_TYPE,
+  RetrySummaryCoordinator,
+} from "./retry-summary.js";
+export {
+  LIMITS_WAIT_EVENT_CHANNEL,
+} from "./telemetry.js";
+export {
+  CONTROL_FILE_ENV_VAR,
+  EXTENSION_VERSION,
+  LIVELINESS_JSON_STATUS_KEY,
+  LIVELINESS_JSON_VERSION,
+  LIVELINESS_STATUS_KEY,
+  PROBE_INTERVAL_ENV_VAR,
+  STATUS_JSON_ENV_VAR,
+} from "./constants.js";
+export {
+  clearStatusJson,
+  controlFilePath,
+  publishStatusJson,
+  statusJsonEnabled,
+  statusPayload,
+} from "./status-json.js";
+export type {
+  LimitsWaitStatusContext,
+  LimitsWaitStatusEvent,
+  LimitsWaitStatusPayload,
+} from "./status-json.js";
+export type {
+  LimitsWaitEndEventPayload,
+  LimitsWaitEventPayload,
+  LimitsWaitModel,
+  LimitsWaitOutcome,
+  LimitsWaitStartEventPayload,
+  LimitsWaitWaitEndPayload,
+  LimitsWaitWaitEventPayload,
+  LimitsWaitWaitOutcome,
+  LimitsWaitWaitStartPayload,
+} from "./telemetry.js";
+export type { LimitsWaitSessionEntryData } from "./retry-summary.js";
+export {
+  __configureFallbackModelsForTests,
+  __setNonRetryableTuningForTests,
+  __setProbeIntervalForTests,
+  disableModelRuntimeInterception,
+  installModelRuntimeInterception,
+  streamWithLimitsRetry,
+  streamWithRateLimitRetry,
+} from "./stream.js";
+export {
+  allWaitingDisabled,
+  clearLivelinessStatus,
+  configuredProbeIntervalMs,
+  freezingEnabled,
+  isNonInteractiveHost,
+  loadUnknownErrorRetrySettings,
+  notifyFinalFailure,
+  notifyLiveliness,
+  waitForRateLimit,
+  waitForRetry,
+} from "./ui.js";
+export type { FallbackModel } from "./types.js";
+
+export default function (pi: ExtensionAPI) {
+  // Current pi-ai inserts the Claude Code identity as the first system block
+  // for Anthropic OAuth. Sanitise only that exact payload shape; authentication,
+  // identity insertion, Anthropic headers, and all other request composition
+  // remain owned by ModelRuntime.
+  pi.on("before_provider_request", (event) => sanitiseAnthropicPayloadSystem(event.payload));
+
+  // Keep prompt sanitisation and the runtime's normal Anthropic header path,
+  // but install no retry/error interception or retry-related lifecycle hooks.
+  if (allWaitingDisabled()) {
+    disableModelRuntimeInterception();
+    return;
+  }
+
+  state.extensionApi = pi;
+  loadUnknownErrorRetrySettings();
+  const retrySummaries = new RetrySummaryCoordinator(pi);
+  const releaseInterception = installModelRuntimeInterception(() => retrySummaries.createStream());
+
+  // Pi 0.86+ warms caches through the same runtime as foreground requests.
+  // Stop background refreshes before they can enter our retry/fallback logic.
+  // Keep the older Pi dependency range: its event registry accepts this hook
+  // but never emits it. The narrow overload bridges the pre-0.86 typings.
+  (pi as ExtensionAPI & {
+    on(event: "cache_warming_decision", handler: () => { action: "stop" }): void;
+  }).on("cache_warming_decision", () => ({ action: "stop" }));
+
+  pi.on("model_select", (event, ctx) => {
+    state.sharedCtx = ctx;
+    if (consumeExpectedModelSelection(event.model)) return;
+    if (isInternalSyntheticModel(event.model)) return;
+    state.primaryModel = event.model;
+    state.primaryThinkingLevel = pi.getThinkingLevel();
+    state.userModelSelectionGeneration++;
+    // A user-selected model takes precedence over a pending retry. Wake every
+    // wait so its stream can adopt the new primary model immediately.
+    for (const skip of [...state.activeWaitSkips]) skip();
+  });
+
+  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();
+    loadFallbackSettings(ctx);
+  });
+
+  pi.on("agent_start", (_event, ctx) => {
+    state.sharedCtx = ctx;
+  });
+
+  // turn_end runs after Pi has persisted the assistant turn, so these custom
+  // entries remain durable transcript metadata without entering LLM context.
+  pi.on("turn_end", () => {
+    retrySummaries.flush();
+  });
+
+  pi.on("agent_end", () => {
+    retrySummaries.finalizeAndFlush();
+  });
+
+  pi.on("session_shutdown", () => {
+    // An old extension instance must not disable or clear state owned by a
+    // newer /reload instance.
+    const ownsInterception = releaseInterception();
+    retrySummaries.finalizeAndFlush();
+    if (!ownsInterception) return;
+    state.ambientStatusCleanup?.();
+    state.modelStatusCleanup?.();
+    state.expectedModelSelections.clear();
+    state.activeWaitSkips.clear();
+    state.sharedCtx = undefined;
+    state.extensionApi = undefined;
+  });
+}