oira666_pi-limits-wait 0.5.9 → 0.6.2

package/package.json

@@ -1,52 +1,52 @@
-{
-  "name": "oira666_pi-limits-wait",
-  "version": "0.5.9",
-  "description": "Extension for PI that allows to automatically wait for limits to reset and retry the request",
-  "type": "module",
-  "exports": {
-    ".": "./src/index.ts"
-  },
-  "license": "MIT",
-  "files": [
-    "src",
-    "!src/__tests__",
-    "README.md",
-    "LICENSE"
-  ],
-  "engines": {
-    "node": ">=22.19.0"
-  },
-  "repository": {
-    "type": "git",
-    "url": "https://github.com/gee666/pi-limits-wait.git"
-  },
-  "bugs": {
-    "url": "https://github.com/gee666/pi-limits-wait/issues"
-  },
-  "homepage": "https://github.com/gee666/pi-limits-wait#readme",
-  "publishConfig": {
-    "access": "public"
-  },
-  "scripts": {
-    "check": "tsc -p tsconfig.json --noEmit",
-    "test": "tsx src/__tests__/test-extension.ts",
-    "pack:check": "npm pack --dry-run",
-    "prepublishOnly": "npm run check && npm test && npm run pack:check"
-  },
-  "pi": {
-    "extensions": [
-      "./src/index.ts"
-    ]
-  },
-  "dependencies": {},
-  "peerDependencies": {
-    "@earendil-works/pi-ai": ">=0.80.10",
-    "@earendil-works/pi-coding-agent": ">=0.80.10"
-  },
-  "devDependencies": {
-    "@earendil-works/pi-ai": "0.83.0",
-    "@earendil-works/pi-coding-agent": "0.83.0",
-    "tsx": "^4.20.6",
-    "typescript": "^5.9.3"
-  }
-}
+{
+  "name": "oira666_pi-limits-wait",
+  "version": "0.6.2",
+  "description": "Extension for PI that allows to automatically wait for limits to reset and retry the request",
+  "type": "module",
+  "exports": {
+    ".": "./src/index.ts"
+  },
+  "license": "MIT",
+  "files": [
+    "src",
+    "!src/__tests__",
+    "README.md",
+    "LICENSE"
+  ],
+  "engines": {
+    "node": ">=22.19.0"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/gee666/pi-limits-wait.git"
+  },
+  "bugs": {
+    "url": "https://github.com/gee666/pi-limits-wait/issues"
+  },
+  "homepage": "https://github.com/gee666/pi-limits-wait#readme",
+  "publishConfig": {
+    "access": "public"
+  },
+  "scripts": {
+    "check": "tsc -p tsconfig.json --noEmit",
+    "test": "tsx src/__tests__/test-extension.ts",
+    "pack:check": "npm pack --dry-run",
+    "prepublishOnly": "npm run check && npm test && npm run pack:check"
+  },
+  "pi": {
+    "extensions": [
+      "./src/index.ts"
+    ]
+  },
+  "dependencies": {},
+  "peerDependencies": {
+    "@earendil-works/pi-ai": ">=0.80.10",
+    "@earendil-works/pi-coding-agent": ">=0.80.10"
+  },
+  "devDependencies": {
+    "@earendil-works/pi-ai": "0.83.0",
+    "@earendil-works/pi-coding-agent": "0.83.0",
+    "tsx": "^4.20.6",
+    "typescript": "^5.9.3"
+  }
+}

package/src/constants.ts

@@ -1,55 +1,62 @@
-export const CLAUDE_CODE_IDENTITY =
-  "You are Claude Code, Anthropic's official CLI for Claude.";
-
-export const PI_REMOVAL_ANCHORS = [
-  "pi-coding-agent",
-  "@earendil-works/pi-coding-agent",
-  "badlogic/pi-mono",
-] as const;
-
-export const PI_IDENTITY_SENTENCE_PATTERN =
-  /(?:^|\n)\s*You are pi\b[^.!?\n]*(?:[.!?](?=\s|$)|(?=\n|$))/gi;
-
-// Strips the host-harness identity clause pi prepends to its system prompt, e.g.
-// "You are an expert coding assistant operating inside pi, a coding agent harness."
-// The Claude Code identity block already establishes who the assistant is, so
-// leaving this clause in tells the model (and Anthropic) it is running inside pi.
-export const PI_HARNESS_IDENTITY_PATTERN =
-  /\s+operating inside pi,\s*a coding agent harness/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
-
-// Unknown provider errors are retried separately from rate-limit, overload,
-// authentication, and network failures.
-export const DEFAULT_UNKNOWN_ERROR_MAX_RETRIES = 999_999;
-export const DEFAULT_UNKNOWN_ERROR_RETRY_INTERVAL_MS = 5 * 1_000; // 5 seconds
-
-// Non-interactive hosts (RPC/JSON) cannot render the TUI countdown, so retry
-// progress is published as periodic liveliness notifications instead.
-export const LIVELINESS_STATUS_KEY = "oira666.pi-limits-wait";
-export const DEFAULT_LIVELINESS_INTERVAL_MS = 15 * 1_000; // 15 seconds
-
-/** Machine-readable sibling of LIVELINESS_STATUS_KEY. Compact JSON, never prose. */
-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 = "0.5.7";
-
-export const SETTINGS_FILE_NAME = "limits-wait.json";
-export const FALLBACK_MODELS_KEY = "fallback-models";
-export const DISABLE_ALL_WAITING_ENV_VAR = "PI_LIMITS_WAIT_DISABLE_ALL_WAITING";
-export const FREEZING_ENV_VAR = "PI_LIMITS_WAIT_FREEZING_ENABLED";
-export const DEFAULT_WAITING_ENV_VAR = "PI_LIMITS_WAIT_DEFAULT_WAITING";
-export const MAX_RETRY_ENV_VAR = "PI_LIMITS_WAIT_MAX_RETRY";
-export const RETRY_INTERVAL_ENV_VAR = "PI_LIMITS_WAIT_RETRY_INTERVAL";
-export const LIVELINESS_INTERVAL_ENV_VAR = "PI_LIMITS_WAIT_LIVELINESS_INTERVAL";
-/** Set to false/0/no/off to suppress the structured status channel. */
-export const STATUS_JSON_ENV_VAR = "PI_LIMITS_WAIT_STATUS_JSON";
-/** Absolute path of the out-of-band control file polled while waiting. Unset => no control. */
-export const CONTROL_FILE_ENV_VAR = "PI_LIMITS_WAIT_CONTROL_FILE";
+export const CLAUDE_CODE_IDENTITY =
+  "You are Claude Code, Anthropic's official CLI for Claude.";
+
+export const PI_REMOVAL_ANCHORS = [
+  "pi-coding-agent",
+  "@earendil-works/pi-coding-agent",
+  "badlogic/pi-mono",
+] as const;
+
+export const PI_IDENTITY_SENTENCE_PATTERN =
+  /(?:^|\n)\s*You are pi\b[^.!?\n]*(?:[.!?](?=\s|$)|(?=\n|$))/gi;
+
+// Strips the host-harness identity clause pi prepends to its system prompt, e.g.
+// "You are an expert coding assistant operating inside pi, a coding agent harness."
+// The Claude Code identity block already establishes who the assistant is, so
+// leaving this clause in tells the model (and Anthropic) it is running inside pi.
+export const PI_HARNESS_IDENTITY_PATTERN =
+  /\s+operating inside pi,\s*a coding agent harness/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
+
+// A model that is currently limited/frozen is re-probed this often, so a
+// higher-priority model can be reclaimed long before its remembered deadline.
+export const DEFAULT_PROBE_INTERVAL_MS = 60 * 1_000; // 1 minute
+
+// Unknown provider errors are retried separately from rate-limit, overload,
+// authentication, and network failures.
+export const DEFAULT_UNKNOWN_ERROR_MAX_RETRIES = 999_999;
+export const DEFAULT_UNKNOWN_ERROR_RETRY_INTERVAL_MS = 5 * 1_000; // 5 seconds
+
+// Non-interactive hosts (RPC/JSON) cannot render the TUI countdown, so retry
+// progress is published as periodic liveliness notifications instead.
+export const LIVELINESS_STATUS_KEY = "oira666.pi-limits-wait";
+export const DEFAULT_LIVELINESS_INTERVAL_MS = 15 * 1_000; // 15 seconds
+
+/** Machine-readable sibling of LIVELINESS_STATUS_KEY. Compact JSON, never prose. */
+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 = "0.6.2";
+
+export const SETTINGS_FILE_NAME = "limits-wait.json";
+export const FALLBACK_MODELS_KEY = "fallback-models";
+export const PROBE_INTERVAL_KEY = "probe-interval-seconds";
+export const DISABLE_ALL_WAITING_ENV_VAR = "PI_LIMITS_WAIT_DISABLE_ALL_WAITING";
+export const FREEZING_ENV_VAR = "PI_LIMITS_WAIT_FREEZING_ENABLED";
+export const DEFAULT_WAITING_ENV_VAR = "PI_LIMITS_WAIT_DEFAULT_WAITING";
+export const MAX_RETRY_ENV_VAR = "PI_LIMITS_WAIT_MAX_RETRY";
+/** Seconds between re-probes of a higher-priority limited/frozen model. 0 disables probing. */
+export const PROBE_INTERVAL_ENV_VAR = "PI_LIMITS_WAIT_PROBE_INTERVAL";
+export const RETRY_INTERVAL_ENV_VAR = "PI_LIMITS_WAIT_RETRY_INTERVAL";
+export const LIVELINESS_INTERVAL_ENV_VAR = "PI_LIMITS_WAIT_LIVELINESS_INTERVAL";
+/** Set to false/0/no/off to suppress the structured status channel. */
+export const STATUS_JSON_ENV_VAR = "PI_LIMITS_WAIT_STATUS_JSON";
+/** Absolute path of the out-of-band control file polled while waiting. Unset => no control. */
+export const CONTROL_FILE_ENV_VAR = "PI_LIMITS_WAIT_CONTROL_FILE";

package/src/index.ts

@@ -1,152 +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,
-  readFallbackSettings,
-} from "./settings.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,
-  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,
-  disableModelRuntimeInterception,
-  installModelRuntimeInterception,
-  streamWithLimitsRetry,
-  streamWithRateLimitRetry,
-} from "./stream.js";
-export {
-  allWaitingDisabled,
-  clearLivelinessStatus,
-  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;
+  });
+}