diff --git a/CHANGELOG.md b/CHANGELOG.md
index 7dc815cf6d5..d606b2ddf56 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -30,7 +30,7 @@ Docs: https://docs.openclaw.ai
- Git hooks: skip ignored staged paths when formatting and restaging pre-commit files, so merge commits no longer abort when `.gitignore` newly ignores staged merged content. Fixes #72744. Thanks @100yenadmin.
- Memory-core/dreaming: add a supported `dreaming.model` knob for Dream Diary narrative subagents, wired through phase config and the existing plugin subagent model-override trust gate. Refs #65963. Thanks @esqandil and @mjamiv.
- Agents/Anthropic: remove trailing assistant prefill payloads when extended thinking is enabled, so Opus 4.7/Sonnet 4.6 requests do not fail Anthropic's user-final-turn validation. Fixes #72739. Thanks @superandylin.
-- Agents/vLLM: honor `compat.thinkingFormat: "qwen-chat-template"` by sending Qwen chat-template thinking kwargs, including preserved thinking for agent loops, and support DashScope-style `qwen` top-level thinking flags. Fixes #72329. Thanks @stavrostzagadouris.
+- Agents/vLLM/Qwen: add plugin-owned Qwen thinking controls for vLLM chat-template kwargs and DashScope-style top-level `enable_thinking` flags, including preserved thinking for agent loops. Fixes #72329. Thanks @stavrostzagadouris.
- Memory-core/dreaming: treat request-scoped narrative fallback as expected, skip session cleanup when no subagent run was created, and remove duplicate phase-level cleanup so fallback no longer emits warning noise. Fixes #67152. Thanks @jsompis.
- Agents/exec: apply configured `tools.exec.timeoutSec` to background, `yieldMs`, and node `system.run` commands when no per-call timeout is set, preventing auto-backgrounded and remote node commands from running indefinitely. Fixes #67600; supersedes #67603. Thanks @dlmpx and @kagura-agent.
- Config/doctor: stop masking unknown-key validation diagnostics such as `agents.defaults.llm`, and have `openclaw doctor --fix` remove the retired `agents.defaults.llm` timeout block. Thanks @aidiffuser.
diff --git a/docs/gateway/config-agents.md b/docs/gateway/config-agents.md
index b6a2616c0fa..8e55d906d8b 100644
--- a/docs/gateway/config-agents.md
+++ b/docs/gateway/config-agents.md
@@ -371,7 +371,7 @@ Time format in system prompt. Default: `auto` (OS preference).
- `params`: global default provider parameters applied to all models. Set at `agents.defaults.params` (e.g. `{ cacheRetention: "long" }`).
- `params` merge precedence (config): `agents.defaults.params` (global base) is overridden by `agents.defaults.models["provider/model"].params` (per-model), then `agents.list[].params` (matching agent id) overrides by key. See [Prompt Caching](/reference/prompt-caching) for details.
- `params.extra_body`/`params.extraBody`: advanced pass-through JSON merged into `api: "openai-completions"` request bodies for OpenAI-compatible proxies. If it collides with generated request keys, the extra body wins; non-native completions routes still strip OpenAI-only `store` afterward.
-- `params.chat_template_kwargs`: vLLM/OpenAI-compatible chat-template arguments merged into top-level `api: "openai-completions"` request bodies. For `vllm/nemotron-3-*` with thinking off, OpenClaw automatically sends `enable_thinking: false` and `force_nonempty_content: true`; models with `compat.thinkingFormat: "qwen-chat-template"` map OpenClaw thinking controls to `chat_template_kwargs.enable_thinking` plus `preserve_thinking: true`; explicit `chat_template_kwargs` override generated defaults, and `extra_body.chat_template_kwargs` still has final precedence.
+- `params.chat_template_kwargs`: vLLM/OpenAI-compatible chat-template arguments merged into top-level `api: "openai-completions"` request bodies. For `vllm/nemotron-3-*` with thinking off, OpenClaw automatically sends `enable_thinking: false` and `force_nonempty_content: true`; explicit `chat_template_kwargs` override generated defaults, and `extra_body.chat_template_kwargs` still has final precedence. For vLLM Qwen thinking controls, set `params.qwenThinkingFormat` to `"chat-template"` or `"top-level"` on that model entry.
- `params.preserveThinking`: Z.AI-only opt-in for preserved thinking. When enabled and thinking is on, OpenClaw sends `thinking.clear_thinking: false` and replays prior `reasoning_content`; see [Z.AI thinking and preserved thinking](/providers/zai#thinking-and-preserved-thinking).
- `agentRuntime`: default low-level agent runtime policy. Omitted id defaults to OpenClaw Pi. Use `id: "pi"` to force the built-in PI harness, `id: "auto"` to let registered plugin harnesses claim supported models, a registered harness id such as `id: "codex"`, or a supported CLI backend alias such as `id: "claude-cli"`. Set `fallback: "none"` to disable automatic PI fallback. Explicit plugin runtimes such as `codex` fail closed by default unless you set `fallback: "pi"` in the same override scope. Keep model refs canonical as `provider/model`; select Codex, Claude CLI, Gemini CLI, and other execution backends through runtime config instead of legacy runtime provider prefixes. See [Agent runtimes](/concepts/agent-runtimes) for how this differs from provider/model selection.
- Config writers that mutate these fields (for example `/models set`, `/models set-image`, and fallback add/remove commands) save canonical object form and preserve existing fallback lists when possible.
diff --git a/docs/providers/qwen.md b/docs/providers/qwen.md
index beea2510e01..bf1e2a4b207 100644
--- a/docs/providers/qwen.md
+++ b/docs/providers/qwen.md
@@ -169,6 +169,13 @@ Availability can still vary by endpoint and billing plan even when a model is
present in the bundled catalog.
+## Thinking Controls
+
+For reasoning-enabled Qwen Cloud models, the bundled provider maps OpenClaw
+thinking levels to DashScope's top-level `enable_thinking` request flag. Disabled
+thinking sends `enable_thinking: false`; other thinking levels send
+`enable_thinking: true`.
+
## Multimodal add-ons
The `qwen` plugin also exposes multimodal capabilities on the **Standard**
diff --git a/docs/providers/vllm.md b/docs/providers/vllm.md
index d1efe226fed..0d7b9bc61b7 100644
--- a/docs/providers/vllm.md
+++ b/docs/providers/vllm.md
@@ -131,7 +131,7 @@ Use explicit config when:
For Qwen models served through vLLM, set
- `compat.thinkingFormat: "qwen-chat-template"` on the model entry when the
+ `params.qwenThinkingFormat: "chat-template"` on the model entry when the
server expects Qwen chat-template kwargs. OpenClaw maps `/think off` to:
```json
@@ -145,8 +145,8 @@ Use explicit config when:
Non-`off` thinking levels send `enable_thinking: true`. If your endpoint
expects DashScope-style top-level flags instead, use
- `compat.thinkingFormat: "qwen"` to send `enable_thinking` at the request
- root.
+ `params.qwenThinkingFormat: "top-level"` to send `enable_thinking` at the
+ request root. Snake-case `params.qwen_thinking_format` is also accepted.
diff --git a/extensions/qwen/api.ts b/extensions/qwen/api.ts
index 08f87897da1..0117bad9128 100644
--- a/extensions/qwen/api.ts
+++ b/extensions/qwen/api.ts
@@ -31,3 +31,4 @@ export {
MODELSTUDIO_MODEL_CATALOG,
} from "./models.js";
export { buildModelStudioProvider, buildQwenProvider } from "./provider-catalog.js";
+export { createQwenThinkingWrapper, wrapQwenProviderStream } from "./stream.js";
diff --git a/extensions/qwen/index.ts b/extensions/qwen/index.ts
index e7cfd093b11..3b9bce7f8cd 100644
--- a/extensions/qwen/index.ts
+++ b/extensions/qwen/index.ts
@@ -10,6 +10,7 @@ import {
QWEN_DEFAULT_MODEL_REF,
} from "./onboard.js";
import { buildQwenProvider } from "./provider-catalog.js";
+import { wrapQwenProviderStream } from "./stream.js";
import { buildQwenVideoGenerationProvider } from "./video-generation-provider.js";
const PROVIDER_ID = "qwen";
@@ -165,6 +166,7 @@ export default defineSingleProviderPluginEntry({
},
applyNativeStreamingUsageCompat: ({ providerConfig }) =>
applyQwenNativeStreamingUsageCompat(providerConfig),
+ wrapStreamFn: wrapQwenProviderStream,
normalizeConfig: ({ providerConfig }) => {
if (!isQwenCodingPlanBaseUrl(providerConfig.baseUrl)) {
return undefined;
diff --git a/extensions/qwen/stream.test.ts b/extensions/qwen/stream.test.ts
new file mode 100644
index 00000000000..596fca552b3
--- /dev/null
+++ b/extensions/qwen/stream.test.ts
@@ -0,0 +1,94 @@
+import type { StreamFn } from "@mariozechner/pi-agent-core";
+import type { Context, Model } from "@mariozechner/pi-ai";
+import { describe, expect, it } from "vitest";
+import { createQwenThinkingWrapper, wrapQwenProviderStream } from "./stream.js";
+
+function capturePayload(params: {
+ thinkingLevel?: "off" | "low" | "medium" | "high" | "xhigh" | "max";
+ reasoning?: unknown;
+ initialPayload?: Record;
+ model?: Partial>;
+}): Record {
+ let captured: Record = {};
+ const baseStreamFn: StreamFn = (_model, _context, options) => {
+ const payload = { ...params.initialPayload };
+ options?.onPayload?.(payload, _model);
+ captured = payload;
+ return {} as ReturnType;
+ };
+
+ const wrapped = createQwenThinkingWrapper(baseStreamFn, params.thinkingLevel ?? "high");
+ void wrapped(
+ {
+ api: "openai-completions",
+ provider: "qwen",
+ id: "qwen3.6-plus",
+ reasoning: true,
+ ...params.model,
+ } as Model<"openai-completions">,
+ { messages: [] } as Context,
+ params.reasoning === undefined ? {} : ({ reasoning: params.reasoning } as never),
+ );
+
+ return captured;
+}
+
+describe("createQwenThinkingWrapper", () => {
+ it("maps disabled thinking to Qwen top-level enable_thinking", () => {
+ const payload = capturePayload({
+ reasoning: "none",
+ initialPayload: {
+ reasoning_effort: "high",
+ reasoning: { effort: "high" },
+ reasoningEffort: "high",
+ },
+ });
+
+ expect(payload).toEqual({ enable_thinking: false });
+ });
+
+ it("maps enabled thinking to Qwen top-level enable_thinking", () => {
+ expect(capturePayload({ reasoning: "medium" })).toEqual({ enable_thinking: true });
+ });
+
+ it("falls back to the session thinking level", () => {
+ expect(capturePayload({ thinkingLevel: "off" })).toEqual({ enable_thinking: false });
+ expect(capturePayload({ thinkingLevel: "high" })).toEqual({ enable_thinking: true });
+ });
+
+ it("skips non-reasoning and non-completions models", () => {
+ expect(capturePayload({ model: { reasoning: false } })).toEqual({});
+ expect(capturePayload({ model: { api: "openai-responses" as never } })).toEqual({});
+ });
+});
+
+describe("wrapQwenProviderStream", () => {
+ it("only registers for Qwen-family OpenAI-compatible providers", () => {
+ expect(
+ wrapQwenProviderStream({
+ provider: "qwencloud",
+ modelId: "qwen3.6-plus",
+ model: {
+ api: "openai-completions",
+ provider: "qwen",
+ id: "qwen3.6-plus",
+ reasoning: true,
+ } as Model<"openai-completions">,
+ streamFn: undefined,
+ } as never),
+ ).toBeTypeOf("function");
+
+ expect(
+ wrapQwenProviderStream({
+ provider: "openai",
+ modelId: "gpt-5.4",
+ model: {
+ api: "openai-completions",
+ provider: "openai",
+ id: "gpt-5.4",
+ } as Model<"openai-completions">,
+ streamFn: undefined,
+ } as never),
+ ).toBeUndefined();
+ });
+});
diff --git a/extensions/qwen/stream.ts b/extensions/qwen/stream.ts
new file mode 100644
index 00000000000..c37c3287f70
--- /dev/null
+++ b/extensions/qwen/stream.ts
@@ -0,0 +1,56 @@
+import type { StreamFn } from "@mariozechner/pi-agent-core";
+import { streamSimple } from "@mariozechner/pi-ai";
+import type { ProviderWrapStreamFnContext } from "openclaw/plugin-sdk/plugin-entry";
+import { normalizeProviderId } from "openclaw/plugin-sdk/provider-model-shared";
+import { streamWithPayloadPatch } from "openclaw/plugin-sdk/provider-stream-shared";
+
+type QwenThinkingLevel = ProviderWrapStreamFnContext["thinkingLevel"];
+
+function isQwenProviderId(providerId: string): boolean {
+ const normalized = normalizeProviderId(providerId);
+ return (
+ normalized === "qwen" ||
+ normalized === "modelstudio" ||
+ normalized === "qwencloud" ||
+ normalized === "dashscope"
+ );
+}
+
+function resolveOpenAICompatibleThinkingEnabled(params: {
+ thinkingLevel: QwenThinkingLevel;
+ options: Parameters[2];
+}): boolean {
+ const options = (params.options ?? {}) as { reasoningEffort?: unknown; reasoning?: unknown };
+ const raw = options.reasoningEffort ?? options.reasoning ?? params.thinkingLevel ?? "high";
+ if (typeof raw !== "string") {
+ return true;
+ }
+ const normalized = raw.trim().toLowerCase();
+ return normalized !== "off" && normalized !== "none";
+}
+
+export function createQwenThinkingWrapper(
+ baseStreamFn: StreamFn | undefined,
+ thinkingLevel: QwenThinkingLevel,
+): StreamFn {
+ const underlying = baseStreamFn ?? streamSimple;
+ return (model, context, options) => {
+ if (model.api !== "openai-completions" || !model.reasoning) {
+ return underlying(model, context, options);
+ }
+ const enableThinking = resolveOpenAICompatibleThinkingEnabled({ thinkingLevel, options });
+ return streamWithPayloadPatch(underlying, model, context, options, (payloadObj) => {
+ payloadObj.enable_thinking = enableThinking;
+ delete payloadObj.reasoning_effort;
+ delete payloadObj.reasoningEffort;
+ delete payloadObj.reasoning;
+ });
+ };
+}
+
+export function wrapQwenProviderStream(ctx: ProviderWrapStreamFnContext): StreamFn | undefined {
+ if (!isQwenProviderId(ctx.provider) || (ctx.model && ctx.model.api !== "openai-completions")) {
+ return undefined;
+ }
+ return createQwenThinkingWrapper(ctx.streamFn, ctx.thinkingLevel);
+}
diff --git a/extensions/vllm/api.ts b/extensions/vllm/api.ts
index b01c8e166bc..c8053f4e637 100644
--- a/extensions/vllm/api.ts
+++ b/extensions/vllm/api.ts
@@ -5,3 +5,4 @@ export {
VLLM_PROVIDER_LABEL,
} from "./defaults.js";
export { buildVllmProvider } from "./models.js";
+export { createVllmQwenThinkingWrapper, wrapVllmProviderStream } from "./stream.js";
diff --git a/extensions/vllm/index.ts b/extensions/vllm/index.ts
index dcc0f4e2dbf..5ccaee19684 100644
--- a/extensions/vllm/index.ts
+++ b/extensions/vllm/index.ts
@@ -10,6 +10,7 @@ import {
VLLM_MODEL_PLACEHOLDER,
VLLM_PROVIDER_LABEL,
} from "./api.js";
+import { wrapVllmProviderStream } from "./stream.js";
const PROVIDER_ID = "vllm";
@@ -89,6 +90,7 @@ export default definePluginEntry({
"vLLM requires authentication to be registered as a provider. " +
'Set VLLM_API_KEY (any value works) or run "openclaw configure". ' +
"See: https://docs.openclaw.ai/providers/vllm",
+ wrapStreamFn: wrapVllmProviderStream,
});
},
});
diff --git a/extensions/vllm/stream.test.ts b/extensions/vllm/stream.test.ts
new file mode 100644
index 00000000000..73352acbf81
--- /dev/null
+++ b/extensions/vllm/stream.test.ts
@@ -0,0 +1,170 @@
+import type { StreamFn } from "@mariozechner/pi-agent-core";
+import type { Context, Model } from "@mariozechner/pi-ai";
+import { describe, expect, it } from "vitest";
+import { createVllmQwenThinkingWrapper, wrapVllmProviderStream } from "./stream.js";
+
+function capturePayload(params: {
+ format: "chat-template" | "top-level";
+ thinkingLevel?: "off" | "low" | "medium" | "high" | "xhigh" | "max";
+ reasoning?: unknown;
+ initialPayload?: Record;
+ model?: Partial>;
+}): Record {
+ let captured: Record = {};
+ const baseStreamFn: StreamFn = (_model, _context, options) => {
+ const payload = { ...params.initialPayload };
+ options?.onPayload?.(payload, _model);
+ captured = payload;
+ return {} as ReturnType;
+ };
+
+ const wrapped = createVllmQwenThinkingWrapper({
+ baseStreamFn,
+ format: params.format,
+ thinkingLevel: params.thinkingLevel ?? "high",
+ });
+ void wrapped(
+ {
+ api: "openai-completions",
+ provider: "vllm",
+ id: "Qwen/Qwen3-8B",
+ reasoning: true,
+ ...params.model,
+ } as Model<"openai-completions">,
+ { messages: [] } as Context,
+ params.reasoning === undefined ? {} : ({ reasoning: params.reasoning } as never),
+ );
+
+ return captured;
+}
+
+describe("createVllmQwenThinkingWrapper", () => {
+ it("maps Qwen chat-template thinking off to chat_template_kwargs", () => {
+ const payload = capturePayload({
+ format: "chat-template",
+ reasoning: "none",
+ initialPayload: {
+ reasoning_effort: "high",
+ reasoning: { effort: "high" },
+ reasoningEffort: "high",
+ },
+ });
+
+ expect(payload).toEqual({
+ chat_template_kwargs: {
+ enable_thinking: false,
+ preserve_thinking: true,
+ },
+ });
+ });
+
+ it("maps Qwen chat-template thinking on to chat_template_kwargs", () => {
+ expect(capturePayload({ format: "chat-template", reasoning: "medium" })).toEqual({
+ chat_template_kwargs: {
+ enable_thinking: true,
+ preserve_thinking: true,
+ },
+ });
+ });
+
+ it("preserves explicit chat-template kwargs while setting enable_thinking", () => {
+ expect(
+ capturePayload({
+ format: "chat-template",
+ thinkingLevel: "off",
+ initialPayload: {
+ chat_template_kwargs: {
+ preserve_thinking: false,
+ force_nonempty_content: true,
+ },
+ },
+ }),
+ ).toEqual({
+ chat_template_kwargs: {
+ enable_thinking: false,
+ preserve_thinking: false,
+ force_nonempty_content: true,
+ },
+ });
+ });
+
+ it("maps Qwen top-level thinking format to enable_thinking", () => {
+ expect(capturePayload({ format: "top-level", thinkingLevel: "off" })).toEqual({
+ enable_thinking: false,
+ });
+ expect(capturePayload({ format: "top-level", thinkingLevel: "high" })).toEqual({
+ enable_thinking: true,
+ });
+ });
+
+ it("skips non-reasoning and non-completions models", () => {
+ expect(capturePayload({ format: "chat-template", model: { reasoning: false } })).toEqual({});
+ expect(
+ capturePayload({ format: "chat-template", model: { api: "openai-responses" as never } }),
+ ).toEqual({});
+ });
+});
+
+describe("wrapVllmProviderStream", () => {
+ it("registers when vLLM Qwen thinking format params are configured", () => {
+ expect(
+ wrapVllmProviderStream({
+ provider: "vllm",
+ modelId: "Qwen/Qwen3-8B",
+ extraParams: { qwenThinkingFormat: "chat-template" },
+ model: {
+ api: "openai-completions",
+ provider: "vllm",
+ id: "Qwen/Qwen3-8B",
+ reasoning: true,
+ } as Model<"openai-completions">,
+ streamFn: undefined,
+ } as never),
+ ).toBeTypeOf("function");
+
+ expect(
+ wrapVllmProviderStream({
+ provider: "vllm",
+ modelId: "Qwen/Qwen3-8B",
+ extraParams: { qwen_thinking_format: "enable_thinking" },
+ model: {
+ api: "openai-completions",
+ provider: "vllm",
+ id: "Qwen/Qwen3-8B",
+ reasoning: true,
+ } as Model<"openai-completions">,
+ streamFn: undefined,
+ } as never),
+ ).toBeTypeOf("function");
+ });
+
+ it("skips unconfigured vLLM and non-vLLM providers", () => {
+ expect(
+ wrapVllmProviderStream({
+ provider: "vllm",
+ modelId: "Qwen/Qwen3-8B",
+ extraParams: {},
+ model: {
+ api: "openai-completions",
+ provider: "vllm",
+ id: "Qwen/Qwen3-8B",
+ } as Model<"openai-completions">,
+ streamFn: undefined,
+ } as never),
+ ).toBeUndefined();
+
+ expect(
+ wrapVllmProviderStream({
+ provider: "openai",
+ modelId: "gpt-5.4",
+ extraParams: { qwenThinkingFormat: "chat-template" },
+ model: {
+ api: "openai-completions",
+ provider: "openai",
+ id: "gpt-5.4",
+ } as Model<"openai-completions">,
+ streamFn: undefined,
+ } as never),
+ ).toBeUndefined();
+ });
+});
diff --git a/extensions/vllm/stream.ts b/extensions/vllm/stream.ts
new file mode 100644
index 00000000000..c7b24de2547
--- /dev/null
+++ b/extensions/vllm/stream.ts
@@ -0,0 +1,117 @@
+import type { StreamFn } from "@mariozechner/pi-agent-core";
+import { streamSimple } from "@mariozechner/pi-ai";
+import type { ProviderWrapStreamFnContext } from "openclaw/plugin-sdk/plugin-entry";
+import { normalizeProviderId } from "openclaw/plugin-sdk/provider-model-shared";
+import { streamWithPayloadPatch } from "openclaw/plugin-sdk/provider-stream-shared";
+
+type VllmThinkingLevel = ProviderWrapStreamFnContext["thinkingLevel"];
+type VllmQwenThinkingFormat = "chat-template" | "top-level";
+
+function isVllmProviderId(providerId: string): boolean {
+ return normalizeProviderId(providerId) === "vllm";
+}
+
+function normalizeQwenThinkingFormat(value: unknown): VllmQwenThinkingFormat | undefined {
+ if (typeof value !== "string") {
+ return undefined;
+ }
+ const normalized = value.trim().toLowerCase().replace(/_/g, "-");
+ if (
+ normalized === "chat-template" ||
+ normalized === "chat-template-kwargs" ||
+ normalized === "chat-template-kwarg" ||
+ normalized === "chat-template-arguments"
+ ) {
+ return "chat-template";
+ }
+ if (
+ normalized === "top-level" ||
+ normalized === "enable-thinking" ||
+ normalized === "request-body"
+ ) {
+ return "top-level";
+ }
+ return undefined;
+}
+
+function resolveVllmQwenThinkingFormat(
+ extraParams: ProviderWrapStreamFnContext["extraParams"],
+): VllmQwenThinkingFormat | undefined {
+ return normalizeQwenThinkingFormat(
+ extraParams?.qwenThinkingFormat ?? extraParams?.qwen_thinking_format,
+ );
+}
+
+function resolveOpenAICompatibleThinkingEnabled(params: {
+ thinkingLevel: VllmThinkingLevel;
+ options: Parameters[2];
+}): boolean {
+ const options = (params.options ?? {}) as { reasoningEffort?: unknown; reasoning?: unknown };
+ const raw = options.reasoningEffort ?? options.reasoning ?? params.thinkingLevel ?? "high";
+ if (typeof raw !== "string") {
+ return true;
+ }
+ const normalized = raw.trim().toLowerCase();
+ return normalized !== "off" && normalized !== "none";
+}
+
+function setQwenChatTemplateThinking(payload: Record, enabled: boolean): void {
+ const existing = payload.chat_template_kwargs;
+ if (existing && typeof existing === "object" && !Array.isArray(existing)) {
+ const next: Record = {
+ ...(existing as Record),
+ enable_thinking: enabled,
+ };
+ if (!Object.hasOwn(next, "preserve_thinking")) {
+ next.preserve_thinking = true;
+ }
+ payload.chat_template_kwargs = next;
+ return;
+ }
+ payload.chat_template_kwargs = {
+ enable_thinking: enabled,
+ preserve_thinking: true,
+ };
+}
+
+export function createVllmQwenThinkingWrapper(params: {
+ baseStreamFn: StreamFn | undefined;
+ format: VllmQwenThinkingFormat;
+ thinkingLevel: VllmThinkingLevel;
+}): StreamFn {
+ const underlying = params.baseStreamFn ?? streamSimple;
+ return (model, context, options) => {
+ if (model.api !== "openai-completions" || !model.reasoning) {
+ return underlying(model, context, options);
+ }
+ const enableThinking = resolveOpenAICompatibleThinkingEnabled({
+ thinkingLevel: params.thinkingLevel,
+ options,
+ });
+ return streamWithPayloadPatch(underlying, model, context, options, (payloadObj) => {
+ if (params.format === "chat-template") {
+ setQwenChatTemplateThinking(payloadObj, enableThinking);
+ } else {
+ payloadObj.enable_thinking = enableThinking;
+ }
+ delete payloadObj.reasoning_effort;
+ delete payloadObj.reasoningEffort;
+ delete payloadObj.reasoning;
+ });
+ };
+}
+
+export function wrapVllmProviderStream(ctx: ProviderWrapStreamFnContext): StreamFn | undefined {
+ if (!isVllmProviderId(ctx.provider) || (ctx.model && ctx.model.api !== "openai-completions")) {
+ return undefined;
+ }
+ const format = resolveVllmQwenThinkingFormat(ctx.extraParams);
+ if (!format) {
+ return undefined;
+ }
+ return createVllmQwenThinkingWrapper({
+ baseStreamFn: ctx.streamFn,
+ format,
+ thinkingLevel: ctx.thinkingLevel,
+ });
+}
diff --git a/src/agents/openai-completions-compat.ts b/src/agents/openai-completions-compat.ts
index b0619f5f25c..e81fcfa9c87 100644
--- a/src/agents/openai-completions-compat.ts
+++ b/src/agents/openai-completions-compat.ts
@@ -17,7 +17,7 @@ export type OpenAICompletionsCompatDefaults = {
supportsReasoningEffort: boolean;
supportsUsageInStreaming: boolean;
maxTokensField: "max_completion_tokens" | "max_tokens";
- thinkingFormat: "openai" | "openrouter" | "deepseek" | "zai" | "qwen" | "qwen-chat-template";
+ thinkingFormat: "openai" | "openrouter" | "deepseek" | "zai";
visibleReasoningDetailTypes: string[];
supportsStrictMode: boolean;
};
diff --git a/src/agents/openai-transport-stream.test.ts b/src/agents/openai-transport-stream.test.ts
index bb44991b6fa..e961c131352 100644
--- a/src/agents/openai-transport-stream.test.ts
+++ b/src/agents/openai-transport-stream.test.ts
@@ -1816,78 +1816,6 @@ describe("openai transport stream", () => {
expect(params.stream_options).toMatchObject({ include_usage: true });
});
- it("maps qwen-chat-template thinking compat to vLLM chat template kwargs", () => {
- const baseModel = {
- id: "Qwen/Qwen3-8B",
- name: "Qwen3 8B",
- api: "openai-completions",
- provider: "vllm",
- baseUrl: "http://127.0.0.1:8000/v1",
- reasoning: true,
- input: ["text"],
- cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
- contextWindow: 32768,
- maxTokens: 8192,
- compat: { thinkingFormat: "qwen-chat-template" },
- } as unknown as Model<"openai-completions">;
- const context = {
- systemPrompt: "system",
- messages: [],
- tools: [],
- } as never;
-
- const disabled = buildOpenAICompletionsParams(baseModel, context, {
- reasoning: "none",
- } as never) as {
- chat_template_kwargs?: { enable_thinking?: unknown; preserve_thinking?: unknown };
- };
- const enabled = buildOpenAICompletionsParams(baseModel, context, {
- reasoning: "medium",
- } as never) as {
- chat_template_kwargs?: { enable_thinking?: unknown; preserve_thinking?: unknown };
- };
-
- expect(disabled.chat_template_kwargs).toEqual({
- enable_thinking: false,
- preserve_thinking: true,
- });
- expect(disabled).not.toHaveProperty("reasoning_effort");
- expect(enabled.chat_template_kwargs).toEqual({
- enable_thinking: true,
- preserve_thinking: true,
- });
- expect(enabled).not.toHaveProperty("reasoning_effort");
- });
-
- it("maps qwen thinking compat to top-level enable_thinking", () => {
- const params = buildOpenAICompletionsParams(
- {
- id: "qwen3.6-plus",
- name: "Qwen 3.6 Plus",
- api: "openai-completions",
- provider: "qwen-custom",
- baseUrl: "https://example.com/v1",
- reasoning: true,
- input: ["text"],
- cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
- contextWindow: 32768,
- maxTokens: 8192,
- compat: { thinkingFormat: "qwen" },
- } as unknown as Model<"openai-completions">,
- {
- systemPrompt: "system",
- messages: [],
- tools: [],
- } as never,
- {
- reasoning: "none",
- } as never,
- ) as { enable_thinking?: unknown; reasoning_effort?: unknown };
-
- expect(params.enable_thinking).toBe(false);
- expect(params).not.toHaveProperty("reasoning_effort");
- });
-
it("enables streaming usage compat for generic providers on native DashScope endpoints", () => {
const params = buildOpenAICompletionsParams(
{
diff --git a/src/agents/openai-transport-stream.ts b/src/agents/openai-transport-stream.ts
index 6238ff7699b..7ae8ee6f453 100644
--- a/src/agents/openai-transport-stream.ts
+++ b/src/agents/openai-transport-stream.ts
@@ -87,8 +87,12 @@ type OpenAICompletionsOptions = BaseStreamOptions & {
reasoningEffort?: OpenAIReasoningEffort;
};
+type OpenAIModeCompatInput = Omit & {
+ thinkingFormat?: string;
+};
+
type OpenAIModeModel = Omit, "compat"> & {
- compat?: ModelCompatConfig;
+ compat?: OpenAIModeCompatInput | null;
};
type MutableAssistantOutput = {
@@ -1592,7 +1596,7 @@ function getCompat(model: OpenAIModeModel): {
requiresAssistantAfterToolResult:
compat.requiresAssistantAfterToolResult ?? detected.requiresAssistantAfterToolResult,
requiresThinkingAsText: compat.requiresThinkingAsText ?? detected.requiresThinkingAsText,
- thinkingFormat: (compat.thinkingFormat as string | undefined) ?? detected.thinkingFormat,
+ thinkingFormat: compat.thinkingFormat ?? detected.thinkingFormat,
openRouterRouting: (compat.openRouterRouting as Record | undefined) ?? {},
vercelGatewayRouting:
(compat.vercelGatewayRouting as Record | undefined) ??
@@ -1631,29 +1635,6 @@ function resolveOpenAICompletionsReasoningEffort(options: OpenAICompletionsOptio
return options?.reasoningEffort ?? options?.reasoning ?? "high";
}
-function isCompletionsThinkingEnabled(effort: string): boolean {
- return normalizeOpenAIReasoningEffort(effort) !== "none";
-}
-
-function setChatTemplateThinking(params: Record, enabled: boolean): void {
- const existing = params.chat_template_kwargs;
- if (existing && typeof existing === "object" && !Array.isArray(existing)) {
- const next: Record = {
- ...(existing as Record),
- enable_thinking: enabled,
- };
- if (!Object.hasOwn(next, "preserve_thinking")) {
- next.preserve_thinking = true;
- }
- params.chat_template_kwargs = next;
- return;
- }
- params.chat_template_kwargs = {
- enable_thinking: enabled,
- preserve_thinking: true,
- };
-}
-
function convertTools(
tools: NonNullable,
compat: ReturnType,
@@ -1837,15 +1818,7 @@ export function buildOpenAICompletionsParams(
fallbackMap: compat.reasoningEffortMap,
})
: undefined;
- if (compat.thinkingFormat === "qwen" && model.reasoning && completionsReasoningEffort) {
- params.enable_thinking = isCompletionsThinkingEnabled(completionsReasoningEffort);
- } else if (
- compat.thinkingFormat === "qwen-chat-template" &&
- model.reasoning &&
- completionsReasoningEffort
- ) {
- setChatTemplateThinking(params, isCompletionsThinkingEnabled(completionsReasoningEffort));
- } else if (
+ if (
compat.thinkingFormat === "openrouter" &&
model.reasoning &&
resolvedCompletionsReasoningEffort
diff --git a/src/config/config-misc.test.ts b/src/config/config-misc.test.ts
index f45be41d15d..217d9995435 100644
--- a/src/config/config-misc.test.ts
+++ b/src/config/config-misc.test.ts
@@ -642,7 +642,7 @@ describe("model compat config schema", () => {
supportsUsageInStreaming: true,
supportsStrictMode: false,
requiresStringContent: true,
- thinkingFormat: "qwen",
+ thinkingFormat: "zai",
requiresToolResultName: true,
requiresAssistantAfterToolResult: false,
requiresThinkingAsText: false,
diff --git a/src/config/schema.base.generated.ts b/src/config/schema.base.generated.ts
index e63da5864dc..91b293642cc 100644
--- a/src/config/schema.base.generated.ts
+++ b/src/config/schema.base.generated.ts
@@ -3105,14 +3105,6 @@ export const GENERATED_BASE_CONFIG_SCHEMA: BaseConfigSchemaResponse = {
type: "string",
const: "zai",
},
- {
- type: "string",
- const: "qwen",
- },
- {
- type: "string",
- const: "qwen-chat-template",
- },
],
},
requiresToolResultName: {
diff --git a/src/config/types.models.ts b/src/config/types.models.ts
index 30b3ae2f554..dcb4474dfcf 100644
--- a/src/config/types.models.ts
+++ b/src/config/types.models.ts
@@ -50,10 +50,9 @@ type SupportedAnthropicMessagesCompatFields = Pick<
>;
type SupportedThinkingFormat =
- | NonNullable
+ | Exclude, "qwen" | "qwen-chat-template">
| "deepseek"
- | "openrouter"
- | "qwen-chat-template";
+ | "openrouter";
export type ModelCompatConfig = SupportedOpenAICompatFields &
SupportedOpenAIResponsesCompatFields &
diff --git a/src/config/zod-schema.core.ts b/src/config/zod-schema.core.ts
index a8ccaf80de6..5d6aa3631f4 100644
--- a/src/config/zod-schema.core.ts
+++ b/src/config/zod-schema.core.ts
@@ -204,8 +204,6 @@ export const ModelCompatSchema = z
z.literal("openrouter"),
z.literal("deepseek"),
z.literal("zai"),
- z.literal("qwen"),
- z.literal("qwen-chat-template"),
])
.optional(),
requiresToolResultName: z.boolean().optional(),
diff --git a/src/model-catalog/normalize.ts b/src/model-catalog/normalize.ts
index 325156de436..ff6b72c7489 100644
--- a/src/model-catalog/normalize.ts
+++ b/src/model-catalog/normalize.ts
@@ -212,9 +212,7 @@ function normalizeModelCatalogCompat(value: unknown): ModelCompatConfig | undefi
thinkingFormat === "openai" ||
thinkingFormat === "openrouter" ||
thinkingFormat === "deepseek" ||
- thinkingFormat === "zai" ||
- thinkingFormat === "qwen" ||
- thinkingFormat === "qwen-chat-template"
+ thinkingFormat === "zai"
) {
compat.thinkingFormat = thinkingFormat;
}