chore: update changelog and docs for qwen extension

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",

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/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";
   };
 }
 ```