feat(model): 按 provider 形状独立适配推理开关 + per-persona 提供商链真接线（裁决 03.4.2/08.4.1/03.4.1 余项）

- 新增 reasoning_shape.go：**每个 provider 形状一个 resolver，只发自己形状的字段**
  · deepseek：thinking{type} + reasoning_effort（依据 DevDocs/reference/deepseek 官方本地副本）
  · vllm：chat_template_kwargs.enable_thinking　· dashscope：顶层 enable_thinking（**只允许显式声明**）
  · openai：仅 reasoning_effort　· anthropic：自己的 thinking{budget_tokens}（未改）
  · 未知 kind → WARN 且一个字段都不发（不许静默失效）
- 形状载体：models.json 组级 `reasoning.kind`（可热更新，未声明则不写该键）+ env `LLM_REASONING_KIND`
- 红线：`effort:none` 在只有布尔开关的形状上翻成**显式关思考**，绝不降成任何强度档
- 03.4.1 余项：`Request.PersonaID` + `RuntimeLLM.ForPersona(pid)` 视图；
  每 persona 协议一条链并消费 `RouteProviderForPersona`；`agent/request.go` 非流式路径同一钩子
- **生产装配（主会话补）**：默认 agent 与 personaAgentPool 都改用 `ForPersona(pid)` 视图——
  否则角色级模型/提供商路由在生产里永不被选中（形同虚设）
- 复核：build/vet 绿 + model/agent/config/cmd 包测试绿；5 条变异反证先红后还原
  （其中一条「红但没钉住」已改用例：通道读取加 2s 超时，避免整包 panic 掩盖信号）
- 未落：DashScope 的 auto 推断（缺官方依据，只允许显式声明）；Qwen `/think` 前导消息
  （design/01 §2.1 与 design/11 §3 口径冲突，停手报告）

internal/runtime/model/openai_encode.go

@@ -25,6 +25,15 @@ type openAIChatRequest struct {
 	// only after validation against the detected vendor's whitelist (design/04
 	// §3.2); an unrecognized value is dropped, never turned into a different tier.
 	ReasoningEffort string `json:"reasoning_effort,omitempty"`
+	// ChatTemplateKwargs carries the vLLM-style thinking switch
+	// (chat_template_kwargs.enable_thinking, design/04 §3.2 Qwen3 行). It is sent
+	// only to an endpoint whose provider declared reasoning.kind=vllm.
+	ChatTemplateKwargs *openAIChatTemplateKwargs `json:"chat_template_kwargs,omitempty"`
+	// EnableThinking carries the DashScope compatible-mode thinking switch (the
+	// top-level enable_thinking). It is sent only to an endpoint whose provider
+	// declared reasoning.kind=dashscope — the shape is never inferred, because a
+	// wrong shape 400s the request.
+	EnableThinking *bool `json:"enable_thinking,omitempty"`
 }
 
 // openAIThinking is the wire form of DeepSeek's thinking switch: enabled or
@@ -33,6 +42,12 @@ type openAIThinking struct {
 	Type string `json:"type"`
 }
 
+// openAIChatTemplateKwargs is the wire form of the vLLM (Qwen3) thinking switch:
+// the boolean lives nested under chat_template_kwargs.
+type openAIChatTemplateKwargs struct {
+	EnableThinking *bool `json:"enable_thinking,omitempty"`
+}
+
 // openAIStreamOpts asks the provider to include usage in the final stream chunk.
 type openAIStreamOpts struct {
 	IncludeUsage bool `json:"include_usage"`
@@ -85,20 +100,23 @@ func (a *OpenAIChatAdapter) buildRequest(req Request, stream bool) ([]byte, erro
 	// The vendor behind an OpenAI-compatible endpoint decides which
 	// reasoning_effort tiers are legal and whether it has a thinking switch;
 	// classify it from the resolved model (and the base URL as a fallback) before
-	// touching the request (design/04 §3.2).
+	// touching the request. The endpoint's configured shape (models.json
+	// reasoning.kind, 裁决 03.4.2/08.4.1) wins over that classification, because
+	// the same wire protocol carries different switch shapes (vLLM vs DashScope).
 	vendor := reasoningVendorFor(req.Model, a.baseURL)
-	effort := resolveReasoningEffort(a.log, vendor, req.ReasoningEffort, req.Model)
-	thinking, effort := resolveOpenAIReasoning(a.log, vendor, req.Model, req.Thinking, effort)
-	reportForcedToolChoiceWithThinking(a.log, req.Model, req.ToolChoice, openAIThinkingOn(thinking, effort))
+	plan := resolveOpenAIReasoning(a.log, a.reasoningKind, vendor, req.Model, req.Thinking, req.ReasoningEffort)
+	reportForcedToolChoiceWithThinking(a.log, plan.provider, req.Model, req.ToolChoice, plan.thinkingOn())
 	wire := openAIChatRequest{
-		Model:           req.Model,
-		Messages:        msgs,
-		Temperature:     req.Temperature,
-		MaxTokens:       req.MaxTokens,
-		Stream:          stream,
-		Tools:           buildTools(req.Tools),
-		Thinking:        thinking,
-		ReasoningEffort: effort,
+		Model:              req.Model,
+		Messages:           msgs,
+		Temperature:        req.Temperature,
+		MaxTokens:          req.MaxTokens,
+		Stream:             stream,
+		Tools:              buildTools(req.Tools),
+		Thinking:           plan.thinking,
+		ReasoningEffort:    plan.effort,
+		ChatTemplateKwargs: plan.template,
+		EnableThinking:     plan.enable,
 	}
 	if stream {
 		wire.StreamOptions = &openAIStreamOpts{IncludeUsage: true}