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.go

@@ -40,6 +40,11 @@ type OpenAIChatAdapter struct {
 	model    string
 	client   *http.Client
 	recorder Recorder
+	// reasoningKind is this endpoint's configured reasoning-switch shape
+	// (models.json group reasoning.kind / LLM_REASONING_KIND, 裁决 03.4.2/08.4.1).
+	// Empty means "auto": infer the vendor from the model name/base URL and send
+	// nothing when the shape is ambiguous.
+	reasoningKind string
 	// log reports reasoning_effort validation and ignored thinking directives. It
 	// is never nil: a discard logger tagged with this adapter's source is
 	// installed when the caller supplies none, so a decision is always traceable.
@@ -77,13 +82,18 @@ func WithOpenAILogger(l *slog.Logger) OpenAIOption {
 }
 
 // NewOpenAIChat builds an adapter from a supplier config. baseURL is trimmed of
-// any trailing slash before the /chat/completions path is appended.
+// any trailing slash before the /chat/completions path is appended. The
+// endpoint's configured reasoning shape (cfg.ReasoningKind) travels with the
+// adapter so every chain built from the same config — the group's chain, its
+// per-persona chain and the local rung — resolves its reasoning switches the
+// same way.
 func NewOpenAIChat(cfg config.LLMConfig, opts ...OpenAIOption) *OpenAIChatAdapter {
 	a := &OpenAIChatAdapter{
-		name:    "openai",
-		baseURL: strings.TrimRight(cfg.BaseURL, "/"),
-		apiKey:  cfg.APIKey,
-		model:   cfg.Model,
+		name:          "openai",
+		baseURL:       strings.TrimRight(cfg.BaseURL, "/"),
+		apiKey:        cfg.APIKey,
+		model:         cfg.Model,
+		reasoningKind: strings.TrimSpace(cfg.ReasoningKind),
 		client: &http.Client{
 			Transport: http.DefaultTransport,
 			Timeout:   defaultHTTPTimeout,