@oh-my-pi/pi-ai 18.6.3 → 18.8.0

package/CHANGELOG.md

@@ -2,6 +2,40 @@
 
 ## [Unreleased]
 
+## [18.8.0] - 2026-10-07
+
+### Breaking Changes
+
+- The environment API-key helpers (`getEnvApiKey`, `getEnvApiKeyName`, and `listProvidersWithEnvKey`) are no longer exported from `@oh-my-pi/pi-ai/stream`; import them from `@oh-my-pi/pi-ai` or `@oh-my-pi/pi-ai/env-api-key` instead.
+- `TranscriptionRequest.audio` now accepts `Uint8Array | Blob`. Consumers must handle `Blob` values when reading transcription requests.
+
+### Changed
+
+- Improved CPU and memory efficiency across streamed model responses, including Cursor, Devin, Codex, OpenAI Responses, and GitLab Duo Workflow.
+- Improved request and authentication performance, including account ranking, OAuth preflight, credential rate-limit checks, credential synchronization, and auth gateway requests.
+- Improved tool-call parsing performance for long calls and Apple Foundation Models requests.
+- Improved Cloudflare AI Gateway request performance and AWS credential-source detection.
+- Reduced memory usage when handling generated images and usage reports.
+
+### Fixed
+
+- Fixed false thinking-loop detections for Gemini, DeepSeek, and Grok when responses contain repetitive code or markup such as VRML, SVG, or JSON; valid output is no longer discarded and retried.
+- Fixed the Cursor provider retaining request resources after requests completed.
+- Fixed session-affinity pins growing without bound in long-lived gateways; pins are now capped at 256 sessions per provider.
+- Fixed Anthropic sessions failing every request with HTTP 400 ("role 'system' must precede an 'assistant' message") after a tool change coincided with compaction or an interrupted or failed reply; sessions already stuck this way recover on the next message ([#14746](https://github.com/can1357/oh-my-pi/issues/14746)).
+
+## [18.7.0] - 2026-10-06
+
+### Added
+
+- Added `getOAuthCredentialProvider()` to resolve login aliases, such as `openai-codex-device`, to the provider where their credentials are stored.
+
+### Fixed
+
+- Fixed Ultrafast service-tier billing and usage accounting: GPT-6 Astra now applies its published premium rates—6× on the OpenAI API and 8× included usage on Codex—and is counted toward the premium-request limit.
+- Fixed Vertex AI authentication on Windows when credentials are created with `gcloud auth application-default login`.
+- Fixed selecting Cursor accounts by email through `auth.accountPolicies` and `/session pin`; newly refreshed and existing accounts now retain the account email.
+
 ## [18.6.3] - 2026-10-06
 
 ### Added

package/dist/types/auth/sqlite-credential-store.d.ts

@@ -60,6 +60,7 @@ export declare class SqliteAuthCredentialStore implements AuthCredentialStore {
     deleteCachePrefix(prefix: string): void;
     cleanExpiredCache(): void;
     getCredentialBlock(credentialId: number, providerKey: string, blockScope: string): number | undefined;
+    getCredentialBlockScopes(credentialId: number, providerKey: string): Map<string, number>;
     getCredentialBlockReconcileAfter(credentialId: number, providerKey: string, blockScope: string): number | undefined;
     upsertCredentialBlock(block: StoredCredentialBlock): void;
     deleteCredentialBlock(credentialId: number, providerKey: string, blockScope: string): void;

package/dist/types/auth/store.d.ts

@@ -71,6 +71,12 @@ export interface CredentialCacheStore {
 export interface CredentialBlockStore {
     /** Non-expired block for one (credential, providerKey, scope) key, or undefined. */
     getCredentialBlock(credentialId: number, providerKey: string, blockScope: string): number | undefined;
+    /**
+     * Non-expired blocks for one credential and providerKey, keyed by block
+     * scope (`""` is unscoped), in one read. Optional: selectors fall back to
+     * {@link CredentialBlockStore.getCredentialBlock} per scope when absent.
+     */
+    getCredentialBlockScopes?(credentialId: number, providerKey: string): ReadonlyMap<string, number>;
     /** Earliest time a shared-store block should be eligible for live-usage reconciliation. */
     getCredentialBlockReconcileAfter(credentialId: number, providerKey: string, blockScope: string): number | undefined;
     /** Upsert with MAX semantics: keep the later blockedUntilMs on conflict. */

package/dist/types/auth-broker/remote-store.d.ts

@@ -73,6 +73,7 @@ export declare class RemoteAuthCredentialStore implements AuthCredentialStore {
     /** Broker-backed disabled tombstones; empty against brokers predating the endpoint. */
     listDisabledCredentials(provider?: string, signal?: AbortSignal): Promise<DisabledCredentialSummary[]>;
     getCredentialBlock(credentialId: number, providerKey: string, blockScope: string): number | undefined;
+    getCredentialBlockScopes(credentialId: number, providerKey: string): Map<string, number>;
     getCredentialBlockReconcileAfter(credentialId: number, providerKey: string, blockScope: string): number | undefined;
     listCredentialBlocks(credentialIds: readonly number[]): StoredCredentialBlock[];
     upsertCredentialBlock(block: StoredCredentialBlock): void;

package/dist/types/auth-broker/snapshot-cache.d.ts

@@ -15,3 +15,15 @@ export interface WriteAuthBrokerSnapshotCacheOptions {
 }
 export declare function readAuthBrokerSnapshotCache(opts: ReadAuthBrokerSnapshotCacheOptions): Promise<SnapshotResponse | null>;
 export declare function writeAuthBrokerSnapshotCache(opts: WriteAuthBrokerSnapshotCacheOptions): Promise<void>;
+/**
+ * Fire-and-forget cache write for snapshot callbacks. The first snapshot after
+ * a quiet period is written immediately; later ones within
+ * {@link WRITE_COALESCE_MS} collapse into a single trailing write of the
+ * newest. A snapshot whose generation and credential content match the last
+ * write is skipped (see {@link UNCHANGED_REWRITE_MS}). Pending writes are
+ * flushed on process shutdown and by {@link flushAuthBrokerSnapshotCacheWrites};
+ * failures are logged, never thrown.
+ */
+export declare function scheduleAuthBrokerSnapshotCacheWrite(opts: WriteAuthBrokerSnapshotCacheOptions): void;
+/** Write every pending scheduled snapshot now and wait for in-flight writes to settle. */
+export declare function flushAuthBrokerSnapshotCacheWrites(): Promise<void>;

package/dist/types/auth-gateway/session-state.d.ts

@@ -63,6 +63,12 @@ export interface AuthGatewaySessionStateRequest {
      * continues.
      */
     context: Context;
+    /**
+     * `JSON.stringify(context.tools)` when the caller already serialized it
+     * (the gateway derives its `sessionId` from the same string). Recomputed
+     * from `context` when absent.
+     */
+    toolsJson?: string;
     /**
      * Stable identity of the account this request's credential resolved to.
      * A change means the gateway switched the session to a sibling credential,

package/dist/types/dialect/terminator-wait.d.ts

@@ -0,0 +1,19 @@
+/**
+ * Fast path for in-band scanners that sit inside a body waiting for one fixed
+ * terminator (a tool-call close tag) and emit nothing until it arrives.
+ *
+ * Appending each delta to the scanner's string buffer and calling `indexOf` on
+ * it flattens the growing rope on every delta, so a long in-band tool call cost
+ * O(n²) copying and scanning. While armed, deltas are set aside and only the new
+ * text plus the terminator-length overlap with what came before is searched;
+ * the buffer is rebuilt once, when the terminator shows up or the stream ends.
+ */
+export declare class TerminatorWait {
+    #private;
+    /** Start deferring; `buffered` is the scanner's pending body, known not to contain `terminator`. */
+    arm(terminator: string, buffered: string): void;
+    /** Take `text` while the terminator is still absent; false means the caller must {@link release} and scan. */
+    absorb(text: string): boolean;
+    /** Stop deferring and return `buffered` with every absorbed delta appended. */
+    release(buffered: string): string;
+}

package/dist/types/env-api-key.d.ts

@@ -0,0 +1,21 @@
+/**
+ * Get API key for provider from known environment variables, e.g. OPENAI_API_KEY.
+ *
+ * Will not return API keys for providers that require OAuth tokens.
+ * Checks Bun.env, then cwd/.env, then ~/.env.
+ */
+export declare function getEnvApiKey(provider: string): string | undefined;
+/**
+ * Name of the environment variable that backs `getEnvApiKey` for a provider,
+ * when that provider maps to a single named variable (e.g. `github-copilot` →
+ * `COPILOT_GITHUB_TOKEN`). Returns undefined for providers whose env fallback
+ * is computed (multi-var pickers, Vertex ADC / Bedrock probes, …) since no
+ * single variable name describes the source.
+ */
+export declare function getEnvApiKeyName(provider: string): string | undefined;
+/**
+ * Enumerate every provider that has an env-var fallback for `getEnvApiKey`.
+ * Used by `omp auth-broker migrate --include-env` to discover env-sourced keys
+ * that should be uploaded to the broker.
+ */
+export declare function listProvidersWithEnvKey(): string[];

package/dist/types/images/index.d.ts

@@ -1,4 +1,4 @@
-import type { Api, Model } from "@oh-my-pi/pi-catalog/types";
+import { type Api, type ImageGenerationApi, type Model } from "@oh-my-pi/pi-catalog/types";
 import type { ImageGenerationOptions, ImageGenerationRequest, ImageGenerationResult } from "./types.js";
 export * from "./google-antigravity.js";
 export * from "./google-generative-ai.js";
@@ -6,8 +6,7 @@ export * from "./openai-hosted.js";
 export * from "./openai-images.js";
 export * from "./openrouter-images.js";
 export * from "./types.js";
-/** Catalog APIs {@link generateImage} serves; the hosted Responses pair needs an explicit carrier model. */
-export type ImageGenerationApi = "openai-images" | "openrouter-images" | "google-generative-ai" | "google-gemini-cli" | "openai-responses" | "openai-codex-responses";
+export type { ImageGenerationApi } from "@oh-my-pi/pi-catalog/types";
 /** Whether a catalog API generates images through one of the pi-ai image clients. */
 export declare function isImageGenerationApi(api: Api): api is ImageGenerationApi;
 /** Generate (or edit, when `request.inputImages` is set) images through the transport selected by the model's `api`. */

package/dist/types/images/shared.d.ts

@@ -32,6 +32,12 @@ export declare function decodeImageResponse(value: unknown, fetch: FetchImpl, si
     images: GeneratedImage[];
     usage: Usage;
 }>;
+/**
+ * Mime type of a base64 image, read from its header only. 64 base64 chars
+ * decode to 48 bytes, past every magic number `parseImageMetadata` checks, so
+ * multi-MB payloads are never fully decoded just to be labelled.
+ */
+export declare function sniffBase64ImageMimeType(base64: string): string | undefined;
 export declare function toDataUrl(image: GeneratedImage): string;
 export declare function resolveOpenAIImageSize(aspectRatio?: string, imageSize?: string): string | undefined;
 export {};

package/dist/types/index.d.ts

@@ -39,6 +39,7 @@ export type * from "./providers/openai-responses.js";
 export type * from "./providers/synthetic.js";
 export * from "./registry/index.js";
 export { resolveCacheRetention } from "./utils.js";
+export * from "./env-api-key.js";
 export * from "./stream.js";
 export * from "./types.js";
 export * from "./usage.js";

package/dist/types/providers/connect-frame.d.ts

@@ -0,0 +1,44 @@
+/**
+ * Connect-protocol streaming envelope shared by the Cursor and Devin
+ * transports: 1 flag byte + 4-byte big-endian payload length + payload.
+ */
+/** Flag bit: payload is compressed with the negotiated encoding (gzip). */
+export declare const CONNECT_COMPRESSED_FLAG = 1;
+/** Flag bit: payload is the end-of-stream JSON trailer. */
+export declare const CONNECT_END_STREAM_FLAG = 2;
+/** Wrap one Connect-protocol message: 1 flag byte + 4-byte big-endian length + payload. */
+export declare function frameConnectMessage(data: Uint8Array, flags?: number): Buffer;
+/** One decoded Connect envelope. */
+export interface ConnectFrame {
+    flags: number;
+    payload: Buffer;
+}
+/** Options for {@link ConnectFrameDecoder}. */
+export interface ConnectFrameDecoderOptions {
+    /**
+     * Payload cap: a length prefix above `maxPayloadBytes` throws `error(length)`
+     * before any of that payload is buffered. Uncapped when omitted.
+     */
+    limit?: {
+        maxPayloadBytes: number;
+        error: (length: number) => Error;
+    };
+}
+/**
+ * Incremental Connect frame decoder. Incoming chunks are kept as-is and a frame
+ * spanning several chunks is joined once, when the length the header announced
+ * has fully arrived — re-concatenating the pending bytes on every chunk made a
+ * multi-MB frame cost O(size × chunks).
+ *
+ * Payloads alias the chunk they came from whenever a frame fits in one chunk,
+ * so callers must not reuse chunk buffers they hand in.
+ */
+export declare class ConnectFrameDecoder {
+    #private;
+    constructor(options?: ConnectFrameDecoderOptions);
+    /**
+     * Buffer `chunk` (if any) and yield every frame now complete, in wire order.
+     * An oversize length prefix throws after the frames that precede it.
+     */
+    decode(chunk?: Uint8Array): Generator<ConnectFrame, void, undefined>;
+}

package/dist/types/providers/cursor/interaction-query.d.ts

@@ -7,8 +7,6 @@ type ProtoUnknownField = {
 interface CursorInteractionWriter {
     write(frame: Uint8Array): void;
 }
-/** Wrap one Connect-protocol message: 1 flag byte + 4-byte big-endian length + payload. */
-export declare function frameConnectMessage(data: Uint8Array, flags?: number): Buffer;
 /** Well-formed protobuf-es `$unknown` entries on `message`; anything else on the bag is ignored. */
 export declare function protoUnknownFields(message: object): ProtoUnknownField[];
 /**

package/dist/types/providers/google-auth.d.ts

@@ -5,13 +5,16 @@
  * Sources, in priority order:
  *   1. `GOOGLE_APPLICATION_CREDENTIALS` env → file with `type: "service_account"` (RS256 JWT exchange)
  *     or `type: "authorized_user"` (refresh-token exchange).
- *   2. `~/.config/gcloud/application_default_credentials.json` (user ADC, same authorized_user flow).
+ *   2. gcloud user ADC: `%APPDATA%\gcloud\application_default_credentials.json` on Windows,
+ *     `~/.config/gcloud/application_default_credentials.json` elsewhere (authorized_user flow).
  *   3. GCE / Cloud Run metadata server (`metadata.google.internal`).
  *
  * Tokens are cached per source key and refreshed `GOOGLE_VERTEX_REFRESH_SKEW_MS` before expiry
  * (default 60s). Concurrent callers waiting on a refresh share the same in-flight promise.
  */
 import type { FetchImpl } from "../types.js";
+/** gcloud's user ADC file: `%APPDATA%\gcloud\…` on Windows, `~/.config/gcloud/…` elsewhere. */
+export declare function userAdcPath(platform?: typeof process.platform, appData?: string | undefined): string;
 /**
  * Returns a Bearer access token suitable for the `Authorization` header on Vertex AI calls.
  * The token is cached in module scope and refreshed `GOOGLE_VERTEX_REFRESH_SKEW_MS` ms before it expires.

package/dist/types/providers/mock.d.ts

@@ -41,7 +41,7 @@
  *   // Inspect calls afterwards.
  *   expect(mock.calls).toHaveLength(2);
  */
-import type { AnthropicFallbackCreditHandle, Api, Context, Model, SimpleStreamOptions, StopDetails, StopReason, Usage } from "../types.js";
+import type { AnthropicFallbackCreditHandle, Api, Context, Model, ServiceTier, SimpleStreamOptions, StopDetails, StopReason, Usage } from "../types.js";
 import { AssistantMessageEventStream } from "../utils/event-stream.js";
 /** The API string this provider serves. */
 export declare const MOCK_API: "mock";
@@ -78,6 +78,8 @@ export interface MockResponse {
     usage?: Partial<Omit<Usage, "cost">> & {
         cost?: Partial<Usage["cost"]>;
     };
+    /** Service tier the mock reports serving the turn, as a real provider's response echo would. */
+    serviceTier?: ServiceTier;
     /** Pre-set responseId. */
     responseId?: string;
     /** If set, the stream emits a terminal error event instead of completing. */

package/dist/types/providers/openai-responses-wire.d.ts

@@ -906,60 +906,6 @@ export declare namespace Response {
              */
             type: "error";
         }
-        /**
-         * A moderation result produced for the response input or output.
-         */
-        interface ModerationResult {
-            /**
-             * A dictionary of moderation categories to booleans, True if the input is flagged
-             * under this category.
-             */
-            categories: {
-                [key: string]: boolean;
-            };
-            /**
-             * Which modalities of input are reflected by the score for each category.
-             */
-            category_applied_input_types: {
-                [key: string]: Array<"text" | "image">;
-            };
-            /**
-             * A dictionary of moderation categories to scores.
-             */
-            category_scores: {
-                [key: string]: number;
-            };
-            /**
-             * A boolean indicating whether the content was flagged by any category.
-             */
-            flagged: boolean;
-            /**
-             * The moderation model that produced this result.
-             */
-            model: string;
-            /**
-             * The object type, which was always `moderation_result` for successful moderation
-             * results.
-             */
-            type: "moderation_result";
-        }
-        /**
-         * An error produced while attempting moderation for the response input or output.
-         */
-        interface Error {
-            /**
-             * The error code.
-             */
-            code: string;
-            /**
-             * The error message.
-             */
-            message: string;
-            /**
-             * The object type, which was always `error` for moderation failures.
-             */
-            type: "error";
-        }
     }
 }
 /**

package/dist/types/providers/openai-shared.d.ts

@@ -76,8 +76,11 @@ export declare function applyOpenAIServiceTier(params: {
  * resolved request tier. Scoped to `provider: "openai"` (the only standard
  * Responses biller) so an echoed `service_tier` from an Azure/OpenRouter/Copilot
  * proxy can never skew those costs.
+ *
+ * Returns the tier the turn ran on for the caller to record on the message, and
+ * counts the premium request the tier bills.
  */
-export declare function applyOpenAIResponsesServiceTierCost(model: Pick<Model, "provider" | "serviceTierCost">, usage: AssistantMessage["usage"], responseServiceTier: unknown, requestServiceTier: ServiceTier | null | undefined): void;
+export declare function applyOpenAIResponsesServiceTierCost(model: Pick<Model, "provider" | "serviceTierCost" | "api" | "identity">, usage: AssistantMessage["usage"], responseServiceTier: unknown, requestServiceTier: ServiceTier | null | undefined): ServiceTier | undefined;
 /**
  * Reconcile token-price estimates with a gateway's authoritative account charge.
  * BYOK turns (`is_byok: true`) price from the provider spend in

package/dist/types/registry/oauth/cursor.d.ts

@@ -1,3 +1,4 @@
+import type { FetchImpl } from "../../types.js";
 import type { OAuthController, OAuthCredentials } from "./types.js";
 export interface CursorAuthParams {
     verifier: string;
@@ -13,6 +14,13 @@ export declare function pollCursorAuth(uuid: string, verifier: string): Promise<
 export declare function loginCursor(onAuthUrl: (url: string) => void, onPollStart?: () => void): Promise<OAuthCredentials>;
 export declare function loginCursorHook(callbacks: OAuthController): Promise<OAuthCredentials>;
 export declare function refreshCursorToken(apiKeyOrRefreshToken: string): Promise<OAuthCredentials>;
-export declare function refreshCursorHook(credentials: OAuthCredentials): Promise<OAuthCredentials>;
+export declare function refreshCursorHook(credentials: OAuthCredentials, signal?: AbortSignal): Promise<OAuthCredentials>;
+/** Request headers that present `accessToken` to cursor.com as its user's web session. */
+export declare function cursorSessionHeaders(userId: string, accessToken: string): Record<string, string>;
+/**
+ * Email of the Cursor account that owns `accessToken`, read from its cursor.com
+ * profile. Undefined when the token names no user or the profile names another.
+ */
+export declare function fetchCursorAccountEmail(accessToken: string, fetchImpl?: FetchImpl, signal?: AbortSignal): Promise<string | undefined>;
 export declare function extractCursorAccessTokenUserId(accessToken: string): string | undefined;
 export declare function isCursorTokenExpiringSoon(token: string, thresholdSeconds?: number): boolean;

package/dist/types/registry/oauth/index.d.ts

@@ -43,3 +43,5 @@ export declare function getOAuthApiKey(provider: OAuthProvider, credentials: Rec
  * Get list of OAuth providers.
  */
 export declare function getOAuthProviders(): OAuthProviderInfo[];
+/** Provider id that stores `providerId`'s credentials: login aliases (`openai-codex-device`) map to their target (`openai-codex`). */
+export declare function getOAuthCredentialProvider(providerId: string): string;

package/dist/types/stream.d.ts

@@ -31,27 +31,6 @@ export declare const __providerInFlightForTesting: {
     captureStaleLockRelease(provider: string): Promise<(() => Promise<void>) | null>;
     captureLockDirRelease(provider: string): Promise<(() => Promise<void>) | null>;
 };
-/**
- * Get API key for provider from known environment variables, e.g. OPENAI_API_KEY.
- *
- * Will not return API keys for providers that require OAuth tokens.
- * Checks Bun.env, then cwd/.env, then ~/.env.
- */
-export declare function getEnvApiKey(provider: string): string | undefined;
-/**
- * Name of the environment variable that backs `getEnvApiKey` for a provider,
- * when that provider maps to a single named variable (e.g. `github-copilot` →
- * `COPILOT_GITHUB_TOKEN`). Returns undefined for providers whose env fallback
- * is computed (multi-var pickers, Vertex ADC / Bedrock probes, …) since no
- * single variable name describes the source.
- */
-export declare function getEnvApiKeyName(provider: string): string | undefined;
-/**
- * Enumerate every provider that has an env-var fallback for `getEnvApiKey`.
- * Used by `omp auth-broker migrate --include-env` to discover env-sourced keys
- * that should be uploaded to the broker.
- */
-export declare function listProvidersWithEnvKey(): string[];
 export declare function stream<TApi extends Api>(model: Model<TApi>, context: Context, options?: OptionsForApi<TApi>): AssistantMessageEventStream;
 export declare function complete<TApi extends Api>(model: Model<TApi>, context: Context, options?: OptionsForApi<TApi>): Promise<AssistantMessage>;
 export declare function streamSimple<TApi extends Api>(model: Model<TApi>, context: Context, options?: SimpleStreamOptions): AssistantMessageEventStream;

package/dist/types/transcription/types.d.ts

@@ -2,7 +2,8 @@ import type { Usage } from "@oh-my-pi/pi-catalog/types";
 export type TranscriptionResponseFormat = "json" | "verbose_json";
 export type TranscriptionTimestampGranularity = "word" | "segment";
 export interface TranscriptionRequest {
-    audio: Uint8Array;
+    /** Audio bytes. A `Blob`/`File` (e.g. a parsed multipart upload) is sent without copying. */
+    audio: Uint8Array | Blob;
     mimeType: string;
     fileName?: string;
     language?: string;

package/dist/types/types.d.ts

@@ -157,18 +157,31 @@ export declare function shouldSendServiceTier(serviceTier: ServiceTier | null |
  */
 export declare function realizesPriorityServiceTier(serviceTier: ServiceTier | null | undefined, model: ServiceTierModel): boolean;
 /**
- * Premium-request weight contributed by a priority request to a provider that
- * realizes it and bills extra. Mirrors GitHub Copilot's `premiumRequests`
- * accounting so the "premium requests" stat aggregates priority traffic across
- * the OpenAI family, direct Anthropic fast mode, and Google priority.
+ * Premium-request weight contributed by a request a provider bills above
+ * standard. Priority (Fast mode) counts 1 on every provider that realizes it;
+ * `ultrafast` counts 1 on the OpenAI family, where it is a premium serving tier
+ * (its cost premium is recorded separately in `usage.cost`). Mirrors GitHub
+ * Copilot's `premiumRequests` accounting so the "premium requests" stat
+ * aggregates premium traffic across the OpenAI family, direct Anthropic fast
+ * mode, and Google priority.
  *
- * Returns 1 only when priority is actually realized on the wire for `model`
- * (see {@link realizesPriorityServiceTier}) and the provider bills it as a
- * premium request. OpenRouter is excluded — it bills per its own pricing, not
- * Copilot-premium semantics — as are Bedrock/Vertex Claude, where priority is
- * silently dropped.
+ * Returns 1 only when the tier is actually realized on the wire for `model`
+ * (see {@link realizesPriorityServiceTier} and {@link shouldSendServiceTier})
+ * and the provider bills it as a premium request. OpenRouter is excluded — it
+ * bills per its own pricing, not Copilot-premium semantics — as are
+ * Bedrock/Vertex Claude, where priority is silently dropped.
+ *
+ * Pass `served: true` when the tier is the one the provider reported serving
+ * (an assistant message's {@link AssistantMessage.serviceTier}) rather than a
+ * requested setting: realization is then already proven, so the wire gate is
+ * skipped and a model without discovery metadata (a stats-backfill row) still
+ * counts.
  */
-export declare function getPriorityPremiumRequests(serviceTier: ServiceTier | null | undefined, model: ServiceTierModel): number;
+export declare function getPremiumServiceTierRequests(serviceTier: ServiceTier | null | undefined, model: ServiceTierModel, options?: {
+    served?: boolean;
+}): number;
+/** Parse a provider-reported `service_tier` echo into a known tier, or `undefined` for anything else. */
+export declare function parseServiceTier(value: unknown): ServiceTier | undefined;
 /**
  * Coerce a persisted service-tier value to a {@link ServiceTierByFamily}. Newer
  * sessions store the family map directly; legacy sessions stored a single
@@ -965,6 +978,15 @@ export interface AssistantMessage {
      * other than what was requested.
      */
     upstreamModel?: string;
+    /**
+     * Service tier the provider reported serving this turn, when the API echoes
+     * one (`response.service_tier`), falling back to the tier the request carried
+     * when the response omits the echo. Absent when the provider reports no tier
+     * or the echo cannot be trusted (proxies). This is the tier the turn actually
+     * ran on, which is what cost, premium-request, and speed accounting key on —
+     * the session's live setting may already have changed.
+     */
+    serviceTier?: ServiceTier;
     usage: Usage;
     stopReason: StopReason;
     stopDetails?: StopDetails | null;

package/dist/types/utils/aws-profile.d.ts

@@ -9,6 +9,11 @@ export declare function resolveAwsProfile(profile?: string): string;
  * the AWS SDK's `AWS_SDK_LOAD_CONFIG` opt-in.
  */
 export declare function shouldLoadAwsSharedConfig(profile?: string): boolean;
+/** Shared credentials and config file locations, honoring their env overrides. */
+export declare function awsSharedFilePaths(): {
+    credentialsPath: string;
+    configPath: string;
+};
 export declare function resolveAwsProfileRegion(profile?: string): string | undefined;
 /** Region selected by the environment or active shared-config profile. */
 export declare function resolveAwsAmbientRegion(profile?: string): string | undefined;

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@oh-my-pi/pi-ai",
-	"version": "18.6.3",
+	"version": "18.8.0",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"keywords": [
 		"ai",
@@ -155,11 +155,11 @@
 		"fmt": "oxfmt --no-error-on-unmatched-pattern 'src/**/*.{ts,tsx}' '{test,bench,examples,scripts}/**/*.ts' '*.ts'"
 	},
 	"dependencies": {
-		"@oh-my-pi/omptype": "18.6.3",
-		"@oh-my-pi/pi-catalog": "18.6.3",
-		"@oh-my-pi/pi-natives": "18.6.3",
-		"@oh-my-pi/pi-utils": "18.6.3",
-		"@oh-my-pi/pi-wire": "18.6.3"
+		"@oh-my-pi/omptype": "18.8.0",
+		"@oh-my-pi/pi-catalog": "18.8.0",
+		"@oh-my-pi/pi-natives": "18.8.0",
+		"@oh-my-pi/pi-utils": "18.8.0",
+		"@oh-my-pi/pi-wire": "18.8.0"
 	},
 	"devDependencies": {
 		"@types/bun": "^1.3.14"