@oh-my-pi/pi-ai 17.3.1 → 17.3.3

package/CHANGELOG.md

@@ -2,6 +2,24 @@
 
 ## [Unreleased]
 
+## [17.3.3] - 2026-08-14
+
+### Fixed
+
+- Distinguished Gemini thought-only `STOP` responses from empty transports, avoiding repeated identical reasoning requests and duplicate Antigravity endpoint streams while surfacing the missing final output for session-level recovery.
+
+## [17.3.2] - 2026-08-13
+
+### Fixed
+
+- Dropped unsigned thinking blocks from Antigravity Claude requests instead of sending them without a signature, preventing HTTP 400 responses when resuming sessions or switching models.
+- Classified Antigravity HTTP 429 responses from structured `google.rpc.ErrorInfo` reasons (`QUOTA_EXHAUSTED`, `RATE_LIMIT_EXCEEDED`, and `INSUFFICIENT_G1_CREDITS_BALANCE`), using retry delays of five minutes or longer to distinguish rotatable quota windows from transient throttling instead of relying only on message regexes.
+
+### Removed
+
+- Removed the Antigravity identity-prompt injection (`ANTIGRAVITY_SYSTEM_INSTRUCTION` and `shouldInjectAntigravitySystemInstruction`): Cloud Code Assist accepts arbitrary system instructions on gemini-3.x and Claude routes (verified live), and the injected stub never matched the real client's system prompt anyway. User system prompts are now sent unmodified (still tagged `role: "user"`).
+- Fixed Antigravity `auto` mode not failing over to the sandbox endpoint when the daily endpoint returned a thinking-only `STOP`, which caused Advisor turns to be falsely recorded as empty-response failures ([#8480](https://github.com/can1357/oh-my-pi/issues/8480)).
+
 ## [17.3.0] - 2026-08-13
 
 ### Breaking Changes

package/dist/types/error/flags.d.ts

@@ -8,6 +8,7 @@ export declare const Flag: {
     readonly StaleResponsesItem: 1048576;
     readonly MalformedFunctionCall: 2097152;
     readonly ProviderFinishError: 4194304;
+    readonly EmptyResponse: 8192;
     readonly ContentBlocked: 32768;
     /** Account-scoped provider policy denial that may succeed with another credential. */
     readonly AccountPolicy: 16384;

package/dist/types/error/provider.d.ts

@@ -7,6 +7,8 @@ export type ProviderResponseErrorKind =
  | "output"
 /** Response body was empty/missing when content was required. */
  | "empty-body"
+/** Response completed without actionable output (for example, thoughts only). */
+ | "empty-output"
 /** Malformed wire envelope (unexpected message ordering / shape). */
  | "envelope"
 /** Content was blocked by a provider safety filter. */

package/dist/types/error/rate-limit.d.ts

@@ -2,7 +2,7 @@
  * Rate limit reason classification and backoff calculation utilities.
  * Ported from opencode-antigravity-auth plugin for consistency.
  */
-export type RateLimitReason = "QUOTA_EXHAUSTED" | "RATE_LIMIT_EXCEEDED" | "CONCURRENT_LIMIT" | "MODEL_CAPACITY_EXHAUSTED" | "SERVER_ERROR" | "UNKNOWN";
+export type RateLimitReason = "QUOTA_EXHAUSTED" | "INSUFFICIENT_G1_CREDITS_BALANCE" | "RATE_LIMIT_EXCEEDED" | "CONCURRENT_LIMIT" | "MODEL_CAPACITY_EXHAUSTED" | "SERVER_ERROR" | "UNKNOWN";
 /**
  * Classify a rate-limit error message into a reason category.
  * Priority order: explicit details in a resource-exhausted error > QUOTA

package/dist/types/providers/google-gemini-cli.d.ts

@@ -69,7 +69,6 @@ export interface AntigravityProviderSessionState extends ProviderSessionState {
     lastExecutionId?: string;
 }
 export declare function getAntigravityProviderSessionState(providerSessionState: Map<string, ProviderSessionState> | undefined): AntigravityProviderSessionState | undefined;
-export { ANTIGRAVITY_SYSTEM_INSTRUCTION, getAntigravityUserAgent, getGeminiCliHeaders, getGeminiCliUserAgent, } from "@oh-my-pi/pi-catalog/wire/gemini-headers";
 interface ParsedGeminiCliCredentials {
     accessToken: string;
     projectId: string;

package/dist/types/registry/oauth/google-antigravity.d.ts

@@ -1,9 +1,13 @@
 import type { OAuthController, OAuthCredentials } from "./types.js";
 export declare const ANTIGRAVITY_LOAD_CODE_ASSIST_METADATA: Readonly<{
     ideType: "ANTIGRAVITY";
-    platform: "PLATFORM_UNSPECIFIED";
-    pluginType: "GEMINI";
 }>;
+export interface AntigravityOnboardMetadata {
+    ide_type: string;
+    ide_version: string;
+    ide_name: string;
+}
+export declare function getAntigravityOnboardMetadata(): AntigravityOnboardMetadata;
 export declare function loginAntigravity(ctrl: OAuthController): Promise<OAuthCredentials>;
 /**
  * Refresh Antigravity token

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-ai",
-	"version": "17.3.1",
+	"version": "17.3.3",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"homepage": "https://omp.sh",
 	"author": "Can Boluk",
@@ -38,10 +38,10 @@
 	},
 	"dependencies": {
 		"@bufbuild/protobuf": "^2.12.1",
-		"@oh-my-pi/omptype": "17.3.1",
-		"@oh-my-pi/pi-catalog": "17.3.1",
-		"@oh-my-pi/pi-utils": "17.3.1",
-		"@oh-my-pi/pi-wire": "17.3.1"
+		"@oh-my-pi/omptype": "17.3.3",
+		"@oh-my-pi/pi-catalog": "17.3.3",
+		"@oh-my-pi/pi-utils": "17.3.3",
+		"@oh-my-pi/pi-wire": "17.3.3"
 	},
 	"devDependencies": {
 		"@bufbuild/protoc-gen-es": "^2.12.1",

package/src/error/flags.ts

@@ -24,6 +24,7 @@ export const Flag = {
 	StaleResponsesItem: 0x0010_0000,
 	MalformedFunctionCall: 0x0020_0000,
 	ProviderFinishError: 0x0040_0000,
+	EmptyResponse: 0x0000_2000,
 	ContentBlocked: 0x0000_8000,
 	/** Account-scoped provider policy denial that may succeed with another credential. */
 	AccountPolicy: 0x0000_4000,
@@ -50,6 +51,7 @@ const KIND_MASK =
 	Flag.StaleResponsesItem |
 	Flag.MalformedFunctionCall |
 	Flag.ProviderFinishError |
+	Flag.EmptyResponse |
 	Flag.ContentBlocked |
 	Flag.AccountPolicy |
 	Flag.ContextOverflow |
@@ -62,7 +64,12 @@ const KIND_MASK =
 	Flag.OAuthExpiry;
 
 const RETRIABLE_KINDS =
-	Flag.Transient | Flag.UsageLimit | Flag.ThinkingLoop | Flag.StaleResponsesItem | Flag.ProviderFinishError;
+	Flag.Transient |
+	Flag.UsageLimit |
+	Flag.ThinkingLoop |
+	Flag.StaleResponsesItem |
+	Flag.ProviderFinishError |
+	Flag.EmptyResponse;
 
 const OVERFLOW_PATTERNS = [
 	/prompt is too long/i, // Anthropic
@@ -104,6 +111,7 @@ const AUTH_FAILURE_PATTERN =
 	/\b(?:401|403|unauthorized|forbidden|authentication|auth[_ ]?unavailable|no auth available|(?:invalid|no)[_ ]?api[_ ]?key)\b/i;
 const MALFORMED_FUNCTION_CALL_PATTERN = /\bmalformed.?function.?call\b/i;
 const PROVIDER_FINISH_ERROR_PATTERN = /\bProvider (?:returned error finish_reason|finish_reason:\s*error)\b/i;
+const EMPTY_RESPONSE_PATTERN = /\bthought-only response without final output\b/i;
 const CONTENT_FILTER_PATTERN = /\b(?:incomplete:\s*)?content_filter\b/i;
 const ACCOUNT_POLICY_PATTERN = /\bcyber_policy\b|trusted access for cyber/i;
 const STALE_RESPONSE_ITEM_PATTERNS = [/\bItem with id ['"][^'"]+['"] not found\.?/i, /previous[ _]?response/i] as const;
@@ -197,6 +205,7 @@ const ERROR_KIND_LABELS: readonly [Flag, string][] = [
 	[Flag.StaleResponsesItem, "stale-responses-item"],
 	[Flag.MalformedFunctionCall, "malformed-function-call"],
 	[Flag.ProviderFinishError, "provider-finish-error"],
+	[Flag.EmptyResponse, "empty-response"],
 	[Flag.ContentBlocked, "content-blocked"],
 	[Flag.AccountPolicy, "account-policy"],
 	[Flag.ContextOverflow, "context-overflow"],
@@ -340,6 +349,7 @@ function classifyText(errorMessage: string | undefined, errorStatus: number | un
 		if (matchesOverflowText(errorMessage)) kinds |= Flag.ContextOverflow;
 		if (isMalformedFunctionCallText(errorMessage)) kinds |= Flag.MalformedFunctionCall;
 		if (isProviderFinishErrorText(errorMessage)) kinds |= Flag.ProviderFinishError;
+		if (EMPTY_RESPONSE_PATTERN.test(errorMessage)) kinds |= Flag.EmptyResponse | Flag.Transient;
 		if (isContentBlockedText(errorMessage)) kinds |= Flag.ContentBlocked;
 		if (ACCOUNT_POLICY_PATTERN.test(errorMessage)) kinds |= Flag.AccountPolicy | Flag.ContentBlocked;
 		if (isAuthFailureText(errorMessage)) kinds |= Flag.AuthFailed;

package/src/error/provider.ts

@@ -9,6 +9,8 @@ export type ProviderResponseErrorKind =
 	| "output"
 	/** Response body was empty/missing when content was required. */
 	| "empty-body"
+	/** Response completed without actionable output (for example, thoughts only). */
+	| "empty-output"
 	/** Malformed wire envelope (unexpected message ordering / shape). */
 	| "envelope"
 	/** Content was blocked by a provider safety filter. */
@@ -38,11 +40,10 @@ export class ProviderResponseError extends Error {
 		this.kind = options.kind ?? "output";
 		// A safety filter block is terminal and intentionally non-retryable.
 		if (this.kind === "content-blocked") attach(this, create(Flag.ContentBlocked));
-		// An incomplete stream (connection dropped / truncated before any terminal
-		// event) or an empty body never produced any content — the request didn't
-		// complete, so it is safe to retry and eligible for model fallback. The
-		// retry layer's replay-unsafe guard still blocks a retry when partial tool
-		// output was already emitted.
+		// A logically empty completed output needs a session-level reminder that
+		// asks for the missing final answer. Empty bodies and incomplete streams
+		// stay on the generic transient retry/model-fallback path.
+		else if (this.kind === "empty-output") attach(this, create(Flag.Transient, Flag.EmptyResponse));
 		else if (this.kind === "incomplete-stream" || this.kind === "empty-body") attach(this, create(Flag.Transient));
 	}
 }

package/src/error/rate-limit.ts

@@ -1,3 +1,5 @@
+import { extractRetryHint } from "@oh-my-pi/pi-utils";
+
 /**
  * Rate limit reason classification and backoff calculation utilities.
  * Ported from opencode-antigravity-auth plugin for consistency.
@@ -5,6 +7,7 @@
 
 export type RateLimitReason =
 	| "QUOTA_EXHAUSTED"
+	| "INSUFFICIENT_G1_CREDITS_BALANCE"
 	| "RATE_LIMIT_EXCEEDED"
 	| "CONCURRENT_LIMIT"
 	| "MODEL_CAPACITY_EXHAUSTED"
@@ -67,6 +70,66 @@ const CN_TRANSIENT_CAP_PATTERN =
 // of rotating through the opaque-429 fallback.
 const CN_THROTTLE_PATTERN = /速率(?:限制|过快)|频率(?:过高|过快)|过于频繁|稍后[重再]试/;
 
+const GOOGLE_RPC_ERROR_INFO_TYPE = "type.googleapis.com/google.rpc.ErrorInfo";
+const LONG_RATE_LIMIT_DELAY_MS = 5 * 60 * 1000;
+
+function asRecord(value: unknown): Record<string, unknown> | undefined {
+	return typeof value === "object" && value !== null && !Array.isArray(value)
+		? (value as Record<string, unknown>)
+		: undefined;
+}
+
+function parseJsonBody(errorMessage: string): Record<string, unknown> | undefined {
+	const start = errorMessage.indexOf("{");
+	const end = errorMessage.lastIndexOf("}");
+	if (start < 0 || end < start) return undefined;
+	try {
+		const parsed: unknown = JSON.parse(errorMessage.slice(start, end + 1));
+		return asRecord(parsed);
+	} catch {
+		return undefined;
+	}
+}
+
+/**
+ * Classify structured Google RESOURCE_EXHAUSTED bodies before consulting text.
+ * Cloud Code Assist prefixes the JSON with its HTTP error label, so accept an
+ * embedded top-level object as well as a raw JSON body.
+ */
+function parseGoogleRpcRateLimitReason(errorMessage: string): RateLimitReason | undefined {
+	const body = parseJsonBody(errorMessage);
+	const error = asRecord(body?.error);
+	if (typeof error?.status !== "string" || error.status.trim().toUpperCase() !== "RESOURCE_EXHAUSTED") {
+		return undefined;
+	}
+	if (!Array.isArray(error.details)) return undefined;
+
+	for (const value of error.details) {
+		const detail = asRecord(value);
+		if (detail?.["@type"] !== GOOGLE_RPC_ERROR_INFO_TYPE || typeof detail.reason !== "string") continue;
+		const reason = detail.reason.trim().toUpperCase();
+		switch (reason) {
+			case "QUOTA_EXHAUSTED":
+				return "QUOTA_EXHAUSTED";
+			case "INSUFFICIENT_G1_CREDITS_BALANCE":
+				// Keep Google's specific credit-balance reason available to logs
+				// and callers while treating it as credential-rotatable below.
+				return "INSUFFICIENT_G1_CREDITS_BALANCE";
+			case "RATE_LIMIT_EXCEEDED": {
+				const retryDelayMs = extractRetryHint(undefined, errorMessage);
+				return retryDelayMs !== undefined && retryDelayMs >= LONG_RATE_LIMIT_DELAY_MS
+					? "QUOTA_EXHAUSTED"
+					: "RATE_LIMIT_EXCEEDED";
+			}
+		}
+	}
+	return undefined;
+}
+
+function isQuotaExhaustedReason(reason: RateLimitReason): boolean {
+	return reason === "QUOTA_EXHAUSTED" || reason === "INSUFFICIENT_G1_CREDITS_BALANCE";
+}
+
 /**
  * Classify a rate-limit error message into a reason category.
  * Priority order: explicit details in a resource-exhausted error > QUOTA
@@ -77,6 +140,8 @@ const CN_THROTTLE_PATTERN = /速率(?:限制|过快)|频率(?:过高|过快)|过
  * Explicit details such as "quota exceeded" retain their normal classification.
  */
 export function parseRateLimitReason(errorMessage: string): RateLimitReason {
+	const structuredReason = parseGoogleRpcRateLimitReason(errorMessage);
+	if (structuredReason !== undefined) return structuredReason;
 	const lowerWithStatus = errorMessage.toLowerCase();
 	const lower = lowerWithStatus.replace(RESOURCE_EXHAUSTED_PATTERN, "");
 	const hasResourceExhaustedStatus = lower !== lowerWithStatus;
@@ -162,6 +227,7 @@ export function parseRateLimitReason(errorMessage: string): RateLimitReason {
  */
 export function calculateRateLimitBackoffMs(reason: RateLimitReason): number {
 	switch (reason) {
+		case "INSUFFICIENT_G1_CREDITS_BALANCE":
 		case "QUOTA_EXHAUSTED":
 			return QUOTA_EXHAUSTED_BACKOFF_MS;
 		case "RATE_LIMIT_EXCEEDED":
@@ -215,6 +281,8 @@ export function isUsageLimitStatus(status: number | undefined): boolean {
  *     credentials.
  */
 export function isUsageLimitOutcome(status: number | undefined, message: string | undefined): boolean {
+	const structuredReason = message ? parseGoogleRpcRateLimitReason(message) : undefined;
+	if (structuredReason !== undefined) return isQuotaExhaustedReason(structuredReason);
 	// Concurrency caps are shed-and-backoff, not credential-rotatable — but only
 	// for quota-worded 429 / other statuses. HTTP 402 is categorically an
 	// account-billing cap, so a 402 whose body happens to mention concurrency is
@@ -235,7 +303,7 @@ export function isUsageLimitOutcome(status: number | undefined, message: string
 	const reason = parseRateLimitReason(message);
 	// For the categorical 402 billing cap a concurrency-worded body is still an
 	// exhausted cap (rotate); for 429 / other only QUOTA_EXHAUSTED rotates.
-	return reason === "QUOTA_EXHAUSTED" || (isBillingCapStatus && reason === "CONCURRENT_LIMIT");
+	return isQuotaExhaustedReason(reason) || (isBillingCapStatus && reason === "CONCURRENT_LIMIT");
 }
 
 /**
@@ -272,6 +340,8 @@ export function isOpaqueStatusBody(message: string): boolean {
  * {@link isUsageLimitOutcome} uses it for the account-rotation decision.
  */
 export function matchesUsageLimitText(errorMessage: string): boolean {
+	const structuredReason = parseGoogleRpcRateLimitReason(errorMessage);
+	if (structuredReason !== undefined) return isQuotaExhaustedReason(structuredReason);
 	return (
 		USAGE_LIMIT_PATTERN.test(errorMessage) ||
 		(CN_QUOTA_EXHAUSTED_PATTERN.test(errorMessage) && !CN_TRANSIENT_CAP_PATTERN.test(errorMessage)) ||

package/src/providers/google-gemini-cli.ts

@@ -8,7 +8,6 @@ import { scheduler } from "node:timers/promises";
 import { type } from "@oh-my-pi/omptype";
 import { calculateCost } from "@oh-my-pi/pi-catalog/models";
 import {
-	ANTIGRAVITY_SYSTEM_INSTRUCTION,
 	getAntigravityModelWireProfile,
 	getAntigravityUserAgent,
 	getGeminiCliHeaders,
@@ -316,13 +315,6 @@ const ANTIGRAVITY_DAILY_ENDPOINT = "https://daily-cloudcode-pa.googleapis.com";
 const ANTIGRAVITY_SANDBOX_ENDPOINT = "https://daily-cloudcode-pa.sandbox.googleapis.com";
 const ANTIGRAVITY_ENDPOINT_FALLBACKS = [ANTIGRAVITY_DAILY_ENDPOINT, ANTIGRAVITY_SANDBOX_ENDPOINT] as const;
 
-export {
-	ANTIGRAVITY_SYSTEM_INSTRUCTION,
-	getAntigravityUserAgent,
-	getGeminiCliHeaders,
-	getGeminiCliUserAgent,
-} from "@oh-my-pi/pi-catalog/wire/gemini-headers";
-
 // Retry configuration
 const MAX_RETRIES = 3;
 const BASE_DELAY_MS = 1000;
@@ -342,11 +334,6 @@ function needsClaudeThinkingBetaHeader(model: Model<"google-gemini-cli">): boole
 	return model.provider === "google-antigravity" && model.id.startsWith("claude-") && model.reasoning;
 }
 
-function shouldInjectAntigravitySystemInstruction(modelId: string): boolean {
-	const normalized = modelId.toLowerCase();
-	return normalized.includes("claude") || normalized.includes("gemini-3");
-}
-
 const optionalCredentialString = type("unknown").pipe(raw => {
 	const out = type("string")(raw);
 	return out instanceof type.errors ? undefined : out;
@@ -635,6 +622,8 @@ export const streamGoogleGeminiCli: StreamFunction<"google-gemini-cli"> = (
 			const isFlashLeakModel = model.id.includes("flash");
 
 			let started = false;
+			// Once any stream event starts, the endpoint is committed downstream.
+			// Failover remains safe only while `started` is false.
 			let sawFinishReason = false;
 			let lastResponseId: string | undefined;
 			const ensureStarted = () => {
@@ -938,6 +927,11 @@ export const streamGoogleGeminiCli: StreamFunction<"google-gemini-cli"> = (
 			};
 
 			let receivedContent = false;
+			const hasThinkingOutput = () =>
+				output.content.some(
+					block =>
+						block.type === "thinking" && (block.thinking.trim().length > 0 || Boolean(block.thinkingSignature)),
+				);
 
 			for (let i = 0; i < endpoints.length; i++) {
 				const endpoint = endpoints[i];
@@ -1027,17 +1021,26 @@ export const streamGoogleGeminiCli: StreamFunction<"google-gemini-cli"> = (
 						}
 
 						const streamed = await streamResponse(currentResponse);
-						// Only accept an empty STOP as valid silence once every fallback
-						// endpoint is exhausted: an earlier endpoint returning empty
-						// successful streams must still fail over (Antigravity auto mode)
-						// rather than be recorded as a real silent review.
+						// Eventless silence may fail over to the alternate Antigravity
+						// endpoint. Once thinking has streamed, the endpoint is already
+						// committed downstream; Advisor mode may accept that silence,
+						// while normal sessions surface it to final-output recovery.
+						const thoughtOnly = hasThinkingOutput();
 						const acceptedSilence =
-							options?.acceptEmptyResponse === true && !streamed.strippedPlanningLeak && isLastEndpoint;
+							options?.acceptEmptyResponse === true &&
+							!streamed.strippedPlanningLeak &&
+							(isLastEndpoint || thoughtOnly);
 						if (output.stopReason !== "stop" || streamed.meaningful || acceptedSilence) {
 							receivedContent = streamed.meaningful || acceptedSilence;
 							break;
 						}
 
+						// A thought-only STOP is a complete provider response, not a
+						// transiently empty transport. Replaying the identical request
+						// burns another full reasoning pass; let session recovery add
+						// an explicit final-output reminder instead.
+						if (thoughtOnly) break;
+
 						if (emptyAttempt < MAX_EMPTY_STREAM_RETRIES) {
 							resetOutput();
 						}
@@ -1051,10 +1054,16 @@ export const streamGoogleGeminiCli: StreamFunction<"google-gemini-cli"> = (
 					}
 
 					if (!receivedContent) {
-						throw new AIError.ProviderResponseError("Cloud Code Assist API returned an empty response", {
-							provider: model.provider,
-							kind: "empty-body",
-						});
+						const thoughtOnly = hasThinkingOutput();
+						throw new AIError.ProviderResponseError(
+							thoughtOnly
+								? "Cloud Code Assist API returned a thought-only response without final output"
+								: "Cloud Code Assist API returned an empty response",
+							{
+								provider: model.provider,
+								kind: thoughtOnly ? "empty-output" : "empty-body",
+							},
+						);
 					}
 
 					if (options?.signal?.aborted) {
@@ -1320,14 +1329,6 @@ export function buildRequest(
 		};
 	}
 
-	if (isAntigravity && shouldInjectAntigravitySystemInstruction(model.id)) {
-		const existingParts = request.systemInstruction?.parts ?? [];
-		request.systemInstruction = {
-			role: "user",
-			parts: [{ text: ANTIGRAVITY_SYSTEM_INSTRUCTION }, ...existingParts],
-		};
-	}
-
 	if (context.tools && context.tools.length > 0) {
 		const convertedTools = convertTools(context.tools, model);
 		request.tools = isAntigravity ? normalizeAntigravityTools(convertedTools) : convertedTools;

package/src/providers/google-shared.ts

@@ -233,6 +233,8 @@ export function convertMessages<T extends GoogleApiType>(model: Model<T>, contex
 			const parts: Part[] = [];
 			// Check if message is from same provider and model - only then keep thinking blocks
 			const isSameProviderAndModel = msg.provider === model.provider && msg.model === model.id;
+			const dropsUnsignedThinking =
+				model.provider === "google-antigravity" && model.id.toLowerCase().includes("claude");
 
 			for (const block of msg.content) {
 				if (block.type === "text") {
@@ -247,6 +249,7 @@ export function convertMessages<T extends GoogleApiType>(model: Model<T>, contex
 					// Skip empty thinking blocks
 					if (!block.thinking || block.thinking.trim() === "") continue;
 					const thoughtSignature = resolveThoughtSignature(isSameProviderAndModel, block.thinkingSignature);
+					if (dropsUnsignedThinking && !thoughtSignature) continue;
 					if (thoughtSignature) {
 						parts.push({
 							thought: true,

package/src/registry/oauth/google-antigravity.ts

@@ -2,7 +2,7 @@
  * Antigravity OAuth flow (Gemini 3, Claude, GPT-OSS via Google Cloud)
  * Uses different OAuth credentials than google-gemini-cli for access to additional models.
  */
-import { getAntigravityUserAgent } from "@oh-my-pi/pi-catalog/wire/gemini-headers";
+import { getAntigravityUserAgent, getAntigravityVersion } from "@oh-my-pi/pi-catalog/wire/gemini-headers";
 import * as AIError from "../../error";
 import { oauthFetch, runGoogleOAuthLogin, throwIfLoginCancelled } from "./google-oauth-shared";
 import type { OAuthController, OAuthCredentials } from "./types";
@@ -26,10 +26,12 @@ const SCOPES = [
 const AUTH_URL = "https://accounts.google.com/o/oauth2/v2/auth";
 const TOKEN_URL = "https://oauth2.googleapis.com/token";
 const CLOUD_CODE_ENDPOINT = "https://cloudcode-pa.googleapis.com";
-const TIER_LEGACY = "legacy-tier";
+const DAILY_CLOUD_CODE_ENDPOINT = "https://daily-cloudcode-pa.googleapis.com";
+const NODE_API_CLIENT_USER_AGENT = "google-api-nodejs-client/10.3.0";
+const GOOG_API_CLIENT_HEADER = "gl-node/22.21.1";
+const TIER_FREE = "free-tier";
 const PROJECT_ONBOARD_MAX_ATTEMPTS = 5;
 const PROJECT_ONBOARD_INTERVAL_MS = 2000;
-
 interface LoadCodeAssistPayload {
 	cloudaicompanionProject?: string | { id?: string };
 	currentTier?: { id?: string };
@@ -45,35 +47,65 @@ interface LongRunningOperationResponse {
 
 export const ANTIGRAVITY_LOAD_CODE_ASSIST_METADATA = Object.freeze({
 	ideType: "ANTIGRAVITY",
-	platform: "PLATFORM_UNSPECIFIED",
-	pluginType: "GEMINI",
 });
 
-function readProjectId(value: string | { id?: string } | undefined): string | undefined {
+export interface AntigravityOnboardMetadata {
+	ide_type: string;
+	ide_version: string;
+	ide_name: string;
+}
+
+export function getAntigravityOnboardMetadata(): AntigravityOnboardMetadata {
+	return {
+		ide_type: "ANTIGRAVITY",
+		ide_version: getAntigravityVersion(),
+		ide_name: "antigravity",
+	};
+}
+
+function readProjectId(value: unknown): string | undefined {
 	if (typeof value === "string" && value.length > 0) {
-		return value;
+		return value.trim();
+	}
+	if (value && typeof value === "object" && "id" in value && typeof (value as { id?: unknown }).id === "string") {
+		const id = (value as { id: string }).id.trim();
+		if (id.length > 0) return id;
 	}
-	if (value && typeof value === "object" && typeof value.id === "string" && value.id.length > 0) {
-		return value.id;
+	return undefined;
+}
+
+function extractProjectId(payload: unknown): string | undefined {
+	if (!payload || typeof payload !== "object") return undefined;
+	const record = payload as Record<string, unknown>;
+	for (const key of ["cloudaicompanionProject", "projectId", "project"]) {
+		const id = readProjectId(record[key]);
+		if (id) return id;
 	}
 	return undefined;
 }
 
-function getDefaultTierId(allowedTiers?: Array<{ id?: string; isDefault?: boolean }>): string {
-	if (!allowedTiers || allowedTiers.length === 0) {
-		return TIER_LEGACY;
+function getDefaultTierId(
+	allowedTiers?: Array<{ id?: string; isDefault?: boolean }>,
+	currentTier?: { id?: string },
+): string {
+	if (allowedTiers && allowedTiers.length > 0) {
+		const defaultTier = allowedTiers.find(
+			tier => tier.isDefault && typeof tier.id === "string" && tier.id.trim().length > 0,
+		);
+		if (defaultTier?.id) {
+			return defaultTier.id.trim();
+		}
 	}
-	const defaultTier = allowedTiers.find(tier => tier.isDefault && typeof tier.id === "string" && tier.id.length > 0);
-	if (defaultTier?.id) {
-		return defaultTier.id;
+	if (currentTier && typeof currentTier.id === "string" && currentTier.id.trim().length > 0) {
+		return currentTier.id.trim();
 	}
-	return TIER_LEGACY;
+	return TIER_FREE;
 }
 
 async function onboardProjectWithRetries(
 	endpoint: string,
 	headers: Record<string, string>,
-	onboardBody: { tierId: string; metadata: typeof ANTIGRAVITY_LOAD_CODE_ASSIST_METADATA },
+	onboardBody: { tier_id: string; metadata: AntigravityOnboardMetadata },
 	signal: AbortSignal | undefined,
 	onProgress?: (message: string) => void,
 ): Promise<string> {
@@ -104,7 +136,7 @@ async function onboardProjectWithRetries(
 			continue;
 		}
 
-		const projectId = readProjectId(operation.response?.cloudaicompanionProject);
+		const projectId = extractProjectId(operation.response);
 		if (projectId) {
 			return projectId;
 		}
@@ -128,42 +160,65 @@ async function discoverProject(
 	};
 
 	onProgress?.("Checking for existing project...");
-	const endpoint = CLOUD_CODE_ENDPOINT;
 	try {
-		throwIfLoginCancelled(signal);
-		const loadResponse = await oauthFetch(
-			`${endpoint}/v1internal:loadCodeAssist`,
-			{
-				method: "POST",
-				headers,
-				body: JSON.stringify({
-					metadata: ANTIGRAVITY_LOAD_CODE_ASSIST_METADATA,
-				}),
-			},
-			{ provider: "google-antigravity", signal },
-		);
+		let lastErrorText: string | undefined;
+		let lastStatus: number | undefined;
+		let fallbackTierId = TIER_FREE;
+		let loadedSuccessfully = false;
 
-		if (!loadResponse.ok) {
-			const errorText = await loadResponse.text();
-			throw new AIError.OAuthError(
-				`loadCodeAssist failed: ${loadResponse.status} ${loadResponse.statusText}: ${errorText}`,
-				{ kind: "discovery", status: loadResponse.status },
+		for (const endpoint of [DAILY_CLOUD_CODE_ENDPOINT, CLOUD_CODE_ENDPOINT]) {
+			throwIfLoginCancelled(signal);
+			const loadResponse = await oauthFetch(
+				`${endpoint}/v1internal:loadCodeAssist`,
+				{
+					method: "POST",
+					headers,
+					body: JSON.stringify({
+						metadata: ANTIGRAVITY_LOAD_CODE_ASSIST_METADATA,
+					}),
+				},
+				{ provider: "google-antigravity", signal },
 			);
+
+			if (!loadResponse.ok) {
+				lastStatus = loadResponse.status;
+				lastErrorText = await loadResponse.text();
+				continue;
+			}
+
+			loadedSuccessfully = true;
+			const loadPayload = (await loadResponse.json()) as LoadCodeAssistPayload;
+			const existingProject = extractProjectId(loadPayload);
+			if (existingProject) {
+				return existingProject;
+			}
+			fallbackTierId = getDefaultTierId(loadPayload.allowedTiers, loadPayload.currentTier);
 		}
 
-		const loadPayload = (await loadResponse.json()) as LoadCodeAssistPayload;
-		const existingProject = readProjectId(loadPayload.cloudaicompanionProject);
-		if (existingProject) {
-			return existingProject;
+		if (!loadedSuccessfully && lastStatus !== undefined) {
+			throw new AIError.OAuthError(`loadCodeAssist failed: ${lastStatus}: ${lastErrorText || "unknown error"}`, {
+				kind: "discovery",
+				status: lastStatus,
+			});
 		}
 
-		const tierId = getDefaultTierId(loadPayload.allowedTiers);
 		onProgress?.("Provisioning project...");
 		const onboardBody = {
-			tierId,
-			metadata: ANTIGRAVITY_LOAD_CODE_ASSIST_METADATA,
+			tier_id: fallbackTierId,
+			metadata: getAntigravityOnboardMetadata(),
 		};
-		const provisionedProject = await onboardProjectWithRetries(endpoint, headers, onboardBody, signal, onProgress);
+		const onboardHeaders: Record<string, string> = {
+			...headers,
+			"User-Agent": `${headers["User-Agent"]} ${NODE_API_CLIENT_USER_AGENT}`,
+			"X-Goog-Api-Client": GOOG_API_CLIENT_HEADER,
+		};
+		const provisionedProject = await onboardProjectWithRetries(
+			DAILY_CLOUD_CODE_ENDPOINT,
+			onboardHeaders,
+			onboardBody,
+			signal,
+			onProgress,
+		);
 		return provisionedProject;
 	} catch (error) {
 		if (error instanceof AIError.LoginCancelledError || error instanceof AIError.OAuthError) {

package/src/usage/gemini.ts

@@ -1,4 +1,4 @@
-import { getGeminiCliHeaders } from "../providers/google-gemini-cli";
+import { getGeminiCliHeaders } from "@oh-my-pi/pi-catalog/wire/gemini-headers";
 import type {
 	UsageAmount,
 	UsageFetchContext,