@oh-my-pi/pi-ai 17.3.2 → 17.3.3

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 ## [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

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/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-ai",
-	"version": "17.3.2",
+	"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": "17.3.2",
-		"@oh-my-pi/pi-catalog": "17.3.2",
-		"@oh-my-pi/pi-utils": "17.3.2",
-		"@oh-my-pi/pi-wire": "17.3.2"
+		"@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/providers/google-gemini-cli.ts

@@ -622,11 +622,8 @@ export const streamGoogleGeminiCli: StreamFunction<"google-gemini-cli"> = (
 			const isFlashLeakModel = model.id.includes("flash");
 
 			let started = false;
-			// Tracks whether *visible* content (text delta or tool call) has been
-			// pushed downstream. `started` alone is a poor failover guard because a
-			// hidden thought part also flips it (via `ensureStarted`); a thinking-only
-			// STOP must still fail over to the alternate Antigravity endpoint (#8480).
-			let emittedVisibleContent = 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 = () => {
@@ -705,7 +702,6 @@ export const streamGoogleGeminiCli: StreamFunction<"google-gemini-cli"> = (
 
 				const emitVisibleText = (delta: string, thoughtSignature?: string): void => {
 					if (!delta) return;
-					emittedVisibleContent = true;
 					const block = startTextBlock();
 					block.text += delta;
 					block.textSignature = retainThoughtSignature(block.textSignature, thoughtSignature);
@@ -864,7 +860,6 @@ export const streamGoogleGeminiCli: StreamFunction<"google-gemini-cli"> = (
 								};
 
 								output.content.push(toolCall);
-								emittedVisibleContent = true;
 								ensureStarted();
 								pushToolCallEvents(toolCall, blockIndex(), output, stream);
 							}
@@ -932,13 +927,17 @@ 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];
 				const isLastEndpoint = i === endpoints.length - 1;
 				try {
 					started = false;
-					emittedVisibleContent = false;
 					resetOutput();
 
 					// Per attempt: arm a pre-response (TTFT) timer, cleared the instant
@@ -1022,17 +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();
 						}
@@ -1046,10 +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) {
@@ -1081,7 +1095,7 @@ export const streamGoogleGeminiCli: StreamFunction<"google-gemini-cli"> = (
 					const status = extractHttpStatusFromError(error);
 					if (
 						!isLastEndpoint &&
-						!emittedVisibleContent &&
+						!started &&
 						(AIError.isTransientStatus(status) ||
 							(status === undefined &&
 								!(error instanceof AIError.ProviderResponseError && error.kind === "output") &&