Merge branch 'merge/pr-940'

package-lock.json

@@ -12,7 +12,8 @@
 				"packages/web-ui/example",
 				"packages/coding-agent/examples/extensions/with-deps",
 				"packages/coding-agent/examples/extensions/custom-provider-anthropic",
-				"packages/coding-agent/examples/extensions/custom-provider-gitlab-duo"
+				"packages/coding-agent/examples/extensions/custom-provider-gitlab-duo",
+				"packages/coding-agent/examples/extensions/custom-provider-qwen-cli"
 			],
 			"dependencies": {
 				"@mariozechner/jiti": "^2.6.5",
@@ -7136,6 +7137,10 @@
 			"resolved": "packages/coding-agent/examples/extensions/custom-provider-gitlab-duo",
 			"link": true
 		},
+		"node_modules/pi-extension-custom-provider-qwen-cli": {
+			"resolved": "packages/coding-agent/examples/extensions/custom-provider-qwen-cli",
+			"link": true
+		},
 		"node_modules/pi-extension-with-deps": {
 			"resolved": "packages/coding-agent/examples/extensions/with-deps",
 			"link": true
@@ -9020,6 +9025,10 @@
 			"name": "pi-extension-custom-provider-gitlab-duo",
 			"version": "1.1.7"
 		},
+		"packages/coding-agent/examples/extensions/custom-provider-qwen-cli": {
+			"name": "pi-extension-custom-provider-qwen-cli",
+			"version": "1.0.0"
+		},
 		"packages/coding-agent/examples/extensions/with-deps": {
 			"name": "pi-extension-with-deps",
 			"version": "1.14.7",

package.json

@@ -7,7 +7,8 @@
 		"packages/web-ui/example",
 		"packages/coding-agent/examples/extensions/with-deps",
 		"packages/coding-agent/examples/extensions/custom-provider-anthropic",
-		"packages/coding-agent/examples/extensions/custom-provider-gitlab-duo"
+		"packages/coding-agent/examples/extensions/custom-provider-gitlab-duo",
+		"packages/coding-agent/examples/extensions/custom-provider-qwen-cli"
 	],
 	"scripts": {
 		"clean": "npm run clean --workspaces",

packages/ai/CHANGELOG.md

@@ -5,6 +5,7 @@
 ### Added
 
 - Added `maxRetryDelayMs` option to `StreamOptions` to cap server-requested retry delays. When a provider (e.g., Google Gemini CLI) requests a delay longer than this value, the request fails immediately with an informative error instead of waiting silently. Default: 60000ms (60 seconds). Set to 0 to disable the cap. ([#1123](https://github.com/badlogic/pi-mono/issues/1123))
+- Added Qwen thinking format support for OpenAI-compatible completions via `enable_thinking`. ([#940](https://github.com/badlogic/pi-mono/pull/940) by [@4h9fbZ](https://github.com/4h9fbZ))
 
 ## [0.50.7] - 2026-01-31
 

packages/ai/README.md

@@ -732,7 +732,7 @@ interface OpenAICompletionsCompat {
   supportsDeveloperRole?: boolean;   // Whether provider supports `developer` role vs `system` (default: true)
   supportsReasoningEffort?: boolean; // Whether provider supports `reasoning_effort` (default: true)
   maxTokensField?: 'max_completion_tokens' | 'max_tokens';  // Which field name to use (default: max_completion_tokens)
-  thinkingFormat?: 'openai' | 'zai'; // Format for reasoning param: 'openai' uses reasoning_effort, 'zai' uses thinking: { type: "enabled" } (default: openai)
+  thinkingFormat?: 'openai' | 'zai' | 'qwen'; // Format for reasoning param: 'openai' uses reasoning_effort, 'zai' uses thinking: { type: "enabled" }, 'qwen' uses enable_thinking: boolean (default: openai)
 }
 
 interface OpenAIResponsesCompat {

packages/ai/src/providers/openai-completions.ts

@@ -442,6 +442,9 @@ function buildParams(model: Model<"openai-completions">, context: Context, optio
 		// Z.ai uses binary thinking: { type: "enabled" | "disabled" }
 		// Must explicitly disable since z.ai defaults to thinking enabled
 		(params as any).thinking = { type: options?.reasoningEffort ? "enabled" : "disabled" };
+	} else if (compat.thinkingFormat === "qwen" && model.reasoning) {
+		// Qwen uses enable_thinking: boolean
+		(params as any).enable_thinking = !!options?.reasoningEffort;
 	} else if (options?.reasoningEffort && model.reasoning && compat.supportsReasoningEffort) {
 		// OpenAI-style reasoning_effort
 		params.reasoning_effort = options.reasoningEffort;

packages/ai/src/types.ts

@@ -222,8 +222,8 @@ export interface OpenAICompletionsCompat {
 	requiresThinkingAsText?: boolean;
 	/** Whether tool call IDs must be normalized to Mistral format (exactly 9 alphanumeric chars). Default: auto-detected from URL. */
 	requiresMistralToolIds?: boolean;
-	/** Format for reasoning/thinking parameter. "openai" uses reasoning_effort, "zai" uses thinking: { type: "enabled" }. Default: "openai". */
-	thinkingFormat?: "openai" | "zai";
+	/** Format for reasoning/thinking parameter. "openai" uses reasoning_effort, "zai" uses thinking: { type: "enabled" }, "qwen" uses enable_thinking: boolean. Default: "openai". */
+	thinkingFormat?: "openai" | "zai" | "qwen";
 	/** OpenRouter-specific routing preferences. Only used when baseUrl points to OpenRouter. */
 	openRouterRouting?: OpenRouterRouting;
 	/** Vercel AI Gateway routing preferences. Only used when baseUrl points to Vercel AI Gateway. */

packages/coding-agent/CHANGELOG.md

@@ -7,6 +7,8 @@
 - Added `newSession`, `tree`, and `fork` keybinding actions for `/new`, `/tree`, and `/fork` commands. All unbound by default. ([#1114](https://github.com/badlogic/pi-mono/pull/1114) by [@juanibiapina](https://github.com/juanibiapina))
 - Added `retry.maxDelayMs` setting to cap maximum server-requested retry delay. When a provider requests a longer delay (e.g., Google's "quota will reset after 5h"), the request fails immediately with an informative error instead of waiting silently. Default: 60000ms (60 seconds). ([#1123](https://github.com/badlogic/pi-mono/issues/1123))
 - `/resume` session picker: new "Threaded" sort mode (now default) displays sessions in a tree structure based on fork relationships. Compact one-line format with message count and age on the right. ([#1124](https://github.com/badlogic/pi-mono/pull/1124) by [@pasky](https://github.com/pasky))
+- Added Qwen CLI OAuth provider extension example. ([#940](https://github.com/badlogic/pi-mono/pull/940) by [@4h9fbZ](https://github.com/4h9fbZ))
+- Added OAuth `modifyModels` hook support for extension-registered providers at registration time. ([#940](https://github.com/badlogic/pi-mono/pull/940) by [@4h9fbZ](https://github.com/4h9fbZ))
 
 ### Fixed
 

packages/coding-agent/docs/custom-provider.md

@@ -135,6 +135,7 @@ models: [{
     maxTokensField: "max_tokens",      // instead of "max_completion_tokens"
     requiresToolResultName: true,      // tool results need name field
     requiresMistralToolIds: true       // tool IDs must be 9 alphanumeric chars
+    thinkingFormat: "qwen"             // uses enable_thinking: true
   }
 }]
 ```
@@ -532,7 +533,7 @@ interface ProviderModelConfig {
     requiresAssistantAfterToolResult?: boolean;
     requiresThinkingAsText?: boolean;
     requiresMistralToolIds?: boolean;
-    thinkingFormat?: "openai" | "zai";
+    thinkingFormat?: "openai" | "zai" | "qwen";
   };
 }
 ```

packages/coding-agent/examples/extensions/README.md

@@ -108,6 +108,7 @@ cp permission-gate.ts ~/.pi/agent/extensions/
 |-----------|-------------|
 | `custom-provider-anthropic/` | Custom Anthropic provider with OAuth support and custom streaming implementation |
 | `custom-provider-gitlab-duo/` | GitLab Duo provider using pi-ai's built-in Anthropic/OpenAI streaming via proxy |
+| `custom-provider-qwen-cli/` | Qwen CLI provider with OAuth device flow and OpenAI-compatible models |
 
 ### External Dependencies
 

packages/coding-agent/examples/extensions/custom-provider-qwen-cli/.gitignore

@@ -0,0 +1 @@
+node_modules/

packages/coding-agent/examples/extensions/custom-provider-qwen-cli/index.ts

@@ -0,0 +1,345 @@
+/**
+ * Qwen CLI Provider Extension
+ *
+ * Provides access to Qwen models via OAuth authentication with chat.qwen.ai.
+ * Uses device code flow with PKCE for secure browser-based authentication.
+ *
+ * Usage:
+ *   pi -e ./packages/coding-agent/examples/extensions/custom-provider-qwen-cli
+ *   # Then /login qwen-cli, or set QWEN_CLI_API_KEY=...
+ */
+
+import type { OAuthCredentials, OAuthLoginCallbacks } from "@mariozechner/pi-ai";
+import type { ExtensionAPI } from "@mariozechner/pi-coding-agent";
+
+// =============================================================================
+// Constants
+// =============================================================================
+
+const QWEN_DEVICE_CODE_ENDPOINT = "https://chat.qwen.ai/api/v1/oauth2/device/code";
+const QWEN_TOKEN_ENDPOINT = "https://chat.qwen.ai/api/v1/oauth2/token";
+const QWEN_CLIENT_ID = "f0304373b74a44d2b584a3fb70ca9e56";
+const QWEN_SCOPE = "openid profile email model.completion";
+const QWEN_GRANT_TYPE = "urn:ietf:params:oauth:grant-type:device_code";
+const QWEN_DEFAULT_BASE_URL = "https://dashscope.aliyuncs.com/compatible-mode/v1";
+const QWEN_POLL_INTERVAL_MS = 2000;
+
+// =============================================================================
+// PKCE Helpers
+// =============================================================================
+
+async function generatePKCE(): Promise<{ verifier: string; challenge: string }> {
+	const array = new Uint8Array(32);
+	crypto.getRandomValues(array);
+	const verifier = btoa(String.fromCharCode(...array))
+		.replace(/\+/g, "-")
+		.replace(/\//g, "_")
+		.replace(/=+$/, "");
+
+	const encoder = new TextEncoder();
+	const data = encoder.encode(verifier);
+	const hash = await crypto.subtle.digest("SHA-256", data);
+	const challenge = btoa(String.fromCharCode(...new Uint8Array(hash)))
+		.replace(/\+/g, "-")
+		.replace(/\//g, "_")
+		.replace(/=+$/, "");
+
+	return { verifier, challenge };
+}
+
+// =============================================================================
+// OAuth Implementation
+// =============================================================================
+
+interface DeviceCodeResponse {
+	device_code: string;
+	user_code: string;
+	verification_uri: string;
+	verification_uri_complete?: string;
+	expires_in: number;
+	interval?: number;
+}
+
+interface TokenResponse {
+	access_token: string;
+	refresh_token?: string;
+	token_type: string;
+	expires_in: number;
+	resource_url?: string;
+}
+
+function abortableSleep(ms: number, signal?: AbortSignal): Promise<void> {
+	return new Promise((resolve, reject) => {
+		if (signal?.aborted) {
+			reject(new Error("Login cancelled"));
+			return;
+		}
+		const timeout = setTimeout(resolve, ms);
+		signal?.addEventListener(
+			"abort",
+			() => {
+				clearTimeout(timeout);
+				reject(new Error("Login cancelled"));
+			},
+			{ once: true },
+		);
+	});
+}
+
+async function startDeviceFlow(): Promise<{ deviceCode: DeviceCodeResponse; verifier: string }> {
+	const { verifier, challenge } = await generatePKCE();
+
+	const body = new URLSearchParams({
+		client_id: QWEN_CLIENT_ID,
+		scope: QWEN_SCOPE,
+		code_challenge: challenge,
+		code_challenge_method: "S256",
+	});
+
+	const headers: Record<string, string> = {
+		"Content-Type": "application/x-www-form-urlencoded",
+		Accept: "application/json",
+	};
+	const requestId = globalThis.crypto?.randomUUID?.();
+	if (requestId) headers["x-request-id"] = requestId;
+
+	const response = await fetch(QWEN_DEVICE_CODE_ENDPOINT, {
+		method: "POST",
+		headers,
+		body: body.toString(),
+	});
+
+	if (!response.ok) {
+		const text = await response.text();
+		throw new Error(`Device code request failed: ${response.status} ${text}`);
+	}
+
+	const data = (await response.json()) as DeviceCodeResponse;
+
+	if (!data.device_code || !data.user_code || !data.verification_uri) {
+		throw new Error("Invalid device code response: missing required fields");
+	}
+
+	return { deviceCode: data, verifier };
+}
+
+async function pollForToken(
+	deviceCode: string,
+	verifier: string,
+	intervalSeconds: number | undefined,
+	expiresIn: number,
+	signal?: AbortSignal,
+): Promise<TokenResponse> {
+	const deadline = Date.now() + expiresIn * 1000;
+	const resolvedIntervalSeconds =
+		typeof intervalSeconds === "number" && Number.isFinite(intervalSeconds) && intervalSeconds > 0
+			? intervalSeconds
+			: QWEN_POLL_INTERVAL_MS / 1000;
+	let intervalMs = Math.max(1000, Math.floor(resolvedIntervalSeconds * 1000));
+
+	const handleTokenError = async (error: string, description?: string): Promise<boolean> => {
+		switch (error) {
+			case "authorization_pending":
+				await abortableSleep(intervalMs, signal);
+				return true;
+			case "slow_down":
+				intervalMs = Math.min(intervalMs + 5000, 10000);
+				await abortableSleep(intervalMs, signal);
+				return true;
+			case "expired_token":
+				throw new Error("Device code expired. Please restart authentication.");
+			case "access_denied":
+				throw new Error("Authorization denied by user.");
+			default:
+				throw new Error(`Token request failed: ${error} - ${description || ""}`);
+		}
+	};
+
+	while (Date.now() < deadline) {
+		if (signal?.aborted) {
+			throw new Error("Login cancelled");
+		}
+
+		const body = new URLSearchParams({
+			grant_type: QWEN_GRANT_TYPE,
+			client_id: QWEN_CLIENT_ID,
+			device_code: deviceCode,
+			code_verifier: verifier,
+		});
+
+		const response = await fetch(QWEN_TOKEN_ENDPOINT, {
+			method: "POST",
+			headers: {
+				"Content-Type": "application/x-www-form-urlencoded",
+				Accept: "application/json",
+			},
+			body: body.toString(),
+		});
+
+		const responseText = await response.text();
+		let data: (TokenResponse & { error?: string; error_description?: string }) | null = null;
+		if (responseText) {
+			try {
+				data = JSON.parse(responseText) as TokenResponse & { error?: string; error_description?: string };
+			} catch {
+				data = null;
+			}
+		}
+
+		const error = data?.error;
+		const errorDescription = data?.error_description;
+
+		if (!response.ok) {
+			if (error && (await handleTokenError(error, errorDescription))) {
+				continue;
+			}
+			throw new Error(`Token request failed: ${response.status} ${response.statusText}. Response: ${responseText}`);
+		}
+
+		if (data?.access_token) {
+			return data;
+		}
+
+		if (error && (await handleTokenError(error, errorDescription))) {
+			continue;
+		}
+
+		throw new Error("Token request failed: missing access token in response");
+	}
+
+	throw new Error("Authentication timed out. Please try again.");
+}
+
+async function loginQwen(callbacks: OAuthLoginCallbacks): Promise<OAuthCredentials> {
+	const { deviceCode, verifier } = await startDeviceFlow();
+
+	// Show verification URL and user code to user
+	const authUrl = deviceCode.verification_uri_complete || deviceCode.verification_uri;
+	const instructions = deviceCode.verification_uri_complete
+		? undefined // Code is already embedded in the URL
+		: `Enter code: ${deviceCode.user_code}`;
+	callbacks.onAuth({ url: authUrl, instructions });
+
+	// Poll for token
+	const tokenResponse = await pollForToken(
+		deviceCode.device_code,
+		verifier,
+		deviceCode.interval,
+		deviceCode.expires_in,
+		callbacks.signal,
+	);
+
+	// Calculate expiry with 5-minute buffer
+	const expiresAt = Date.now() + tokenResponse.expires_in * 1000 - 5 * 60 * 1000;
+
+	return {
+		refresh: tokenResponse.refresh_token || "",
+		access: tokenResponse.access_token,
+		expires: expiresAt,
+		// Store resource_url for API base URL if provided
+		enterpriseUrl: tokenResponse.resource_url,
+	};
+}
+
+async function refreshQwenToken(credentials: OAuthCredentials): Promise<OAuthCredentials> {
+	const body = new URLSearchParams({
+		grant_type: "refresh_token",
+		refresh_token: credentials.refresh,
+		client_id: QWEN_CLIENT_ID,
+	});
+
+	const response = await fetch(QWEN_TOKEN_ENDPOINT, {
+		method: "POST",
+		headers: {
+			"Content-Type": "application/x-www-form-urlencoded",
+			Accept: "application/json",
+		},
+		body: body.toString(),
+	});
+
+	if (!response.ok) {
+		const text = await response.text();
+		throw new Error(`Token refresh failed: ${response.status} ${text}`);
+	}
+
+	const data = (await response.json()) as TokenResponse;
+
+	if (!data.access_token) {
+		throw new Error("Token refresh failed: no access token in response");
+	}
+
+	const expiresAt = Date.now() + data.expires_in * 1000 - 5 * 60 * 1000;
+
+	return {
+		refresh: data.refresh_token || credentials.refresh,
+		access: data.access_token,
+		expires: expiresAt,
+		enterpriseUrl: data.resource_url ?? credentials.enterpriseUrl,
+	};
+}
+
+function getQwenBaseUrl(resourceUrl?: string): string {
+	if (!resourceUrl) {
+		return QWEN_DEFAULT_BASE_URL;
+	}
+
+	let url = resourceUrl.startsWith("http") ? resourceUrl : `https://${resourceUrl}`;
+	if (!url.endsWith("/v1")) {
+		url = `${url}/v1`;
+	}
+	return url;
+}
+
+// =============================================================================
+// Extension Entry Point
+// =============================================================================
+
+export default function (pi: ExtensionAPI) {
+	pi.registerProvider("qwen-cli", {
+		baseUrl: QWEN_DEFAULT_BASE_URL,
+		apiKey: "QWEN_CLI_API_KEY",
+		api: "openai-completions",
+
+		models: [
+			{
+				id: "qwen3-coder-plus",
+				name: "Qwen3 Coder Plus",
+				reasoning: false,
+				input: ["text"],
+				cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+				contextWindow: 1000000,
+				maxTokens: 65536,
+			},
+			{
+				id: "qwen3-coder-flash",
+				name: "Qwen3 Coder Flash",
+				reasoning: false,
+				input: ["text"],
+				cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+				contextWindow: 1000000,
+				maxTokens: 65536,
+			},
+			{
+				id: "vision-model",
+				name: "Qwen3 VL Plus",
+				reasoning: true,
+				input: ["text", "image"],
+				cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+				contextWindow: 262144,
+				maxTokens: 32768,
+				compat: { supportsDeveloperRole: false, thinkingFormat: "qwen" },
+			},
+		],
+
+		oauth: {
+			name: "Qwen CLI",
+			login: loginQwen,
+			refreshToken: refreshQwenToken,
+			getApiKey: (cred) => cred.access,
+			modifyModels: (models, cred) => {
+				const baseUrl = getQwenBaseUrl(cred.enterpriseUrl as string | undefined);
+				return models.map((m) => (m.provider === "qwen-cli" ? { ...m, baseUrl } : m));
+			},
+		},
+	});
+}

packages/coding-agent/examples/extensions/custom-provider-qwen-cli/package.json

@@ -0,0 +1,16 @@
+{
+  "name": "pi-extension-custom-provider-qwen-cli",
+  "private": true,
+  "version": "1.0.0",
+  "type": "module",
+  "scripts": {
+    "clean": "echo 'nothing to clean'",
+    "build": "echo 'nothing to build'",
+    "check": "echo 'nothing to check'"
+  },
+  "pi": {
+    "extensions": [
+      "./index.ts"
+    ]
+  }
+}

packages/coding-agent/src/core/model-registry.ts

@@ -48,7 +48,7 @@ const OpenAICompletionsCompatSchema = Type.Object({
 	requiresAssistantAfterToolResult: Type.Optional(Type.Boolean()),
 	requiresThinkingAsText: Type.Optional(Type.Boolean()),
 	requiresMistralToolIds: Type.Optional(Type.Boolean()),
-	thinkingFormat: Type.Optional(Type.Union([Type.Literal("openai"), Type.Literal("zai")])),
+	thinkingFormat: Type.Optional(Type.Union([Type.Literal("openai"), Type.Literal("zai"), Type.Literal("qwen")])),
 	openRouterRouting: Type.Optional(OpenRouterRoutingSchema),
 	vercelGatewayRouting: Type.Optional(VercelGatewayRoutingSchema),
 });
@@ -544,6 +544,14 @@ export class ModelRegistry {
 					compat: modelDef.compat,
 				} as Model<Api>);
 			}
+
+			// Apply OAuth modifyModels if credentials exist (e.g., to update baseUrl)
+			if (config.oauth?.modifyModels) {
+				const cred = this.authStorage.get(providerName);
+				if (cred?.type === "oauth") {
+					this.models = config.oauth.modifyModels(this.models, cred);
+				}
+			}
 		} else if (config.baseUrl) {
 			// Override-only: update baseUrl/headers for existing models
 			const resolvedHeaders = resolveHeaders(config.headers);