feat(persona,model,loop): 人格 thinking 配置 + 5 个死字段接线 + 推理旋钮（按 provider 映射）

按 DevDocs/design/01 §2.1/§2.2 与 design/04 §3.2 实现（规格含联网核过的官方依据：思考内容刻意不角色化、不写分步思考指令、思考控制只走参数级）。
- 人格 schema 新增 thinking：budgetTokens / effort / showToUser(*bool，省略=nil=保持现行为，显式 false=只落库) / mode(default|on|off→Enable 三态)；非法 mode/负预算 → ErrInvalidThinking（不静默）
- 5 个死字段接上注入：personality→values→speechStyle→catchphrase→background 拼为独立段落（带【】小标题，空值不拼）；**全空时输出与旧实现逐字节一致**（有专门测试）
- model.Request 新增 Thinking{ BudgetTokens, Enable } 与 ReasoningEffort；新增 model/reasoning.go：厂商识别（模型名→baseURL 兜底）、取值白名单（OpenAI 系 none…max / DeepSeek low|high|max）、非法值降级+WARN、**不支持一律 WARN 而非静默**；Anthropic 映射 thinking{budget_tokens} 并**保证 budget<max_tokens**（不足时抬高 max_tokens+WARN，正是历史上思考吃光预算→空回复那个坑）
- loop：新增 Options.ThinkingShowToUser(*bool) 仅门控 thinking_* 帧（正文/工具帧不受影响）；场景级 mute 语义不变
- 补一处任务清单外但必需的接线：persona→model.Request 的 thinking 映射（否则 budget/effort/mode 会变成新的死字段）；showToUser 刻意不产生 Thinking（纯呈现开关）
- 管理端：personaUpsertRequest 补 thinking DTO + 校验（400）；PUT 省略时**保留已存块**（防旧客户端抹配置）；写侧 yaml round-trip 已验证
- Docs/api-client v0.40→v0.41（可选请求字段）
- 测试：26 个新用例（loader 解析/拼接逐字节/映射、anthropic 非流式+流式预算约束、openai 透传/降级/丢弃、Qwen 诚实 WARN、loop 门控、DTO round-trip）；3 次变异验证（省略与 false 混同 / 去掉预算约束 / 短路门控 各自 FAIL）
- 验收：go build/vet/test 全绿（含 57 包）+ linux/darwin 交叉编译 + 前端 build；唯一 FAIL 是既有 flake TestInterruptCancelsTurnAndClearsPending（3/20 新代码 vs 3/20 纯 HEAD，已归因非本次引入）

internal/runtime/model/anthropic.go

@@ -6,6 +6,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"log/slog"
 	"net/http"
 	"strings"
 	"time"
@@ -24,8 +25,19 @@ const (
 	anthropicDefaultMaxTokens = 8192
 	// anthropicDataPrefix marks a payload embedded as a data: URI.
 	anthropicDataPrefix = "data:"
+	// anthropicThinkingTypeEnabled is the wire value of an enabled extended-
+	// thinking directive.
+	anthropicThinkingTypeEnabled = "enabled"
 )
 
+// anthropicThinking is the wire form of the extended-thinking directive. It is
+// omitted entirely when the caller did not ask for thinking (or asked for it to
+// be off), because Anthropic treats a missing field as "no thinking".
+type anthropicThinking struct {
+	Type         string `json:"type"`
+	BudgetTokens int    `json:"budget_tokens"`
+}
+
 // anthropicRequest is the body sent to /v1/messages. Messages carry Anthropic's
 // content-block model and the system prompt lives at the request root.
 type anthropicRequest struct {
@@ -36,6 +48,7 @@ type anthropicRequest struct {
 	ToolChoice  any                `json:"tool_choice,omitempty"`
 	Temperature *float64           `json:"temperature,omitempty"`
 	MaxTokens   int                `json:"max_tokens"`
+	Thinking    *anthropicThinking `json:"thinking,omitempty"`
 	Stream      bool               `json:"stream,omitempty"`
 }
 
@@ -90,6 +103,10 @@ type AnthropicChatAdapter struct {
 	model    string
 	client   *http.Client
 	recorder Recorder
+	// log reports reasoning adjustments and ignored directives. It is never nil:
+	// a discard logger tagged with this adapter's source is installed when the
+	// caller supplies none, so a provider decision is always traceable.
+	log *slog.Logger
 }
 
 // AnthropicOption configures an AnthropicChatAdapter.
@@ -111,6 +128,17 @@ func WithAnthropicModel(m string) AnthropicOption {
 	return func(a *AnthropicChatAdapter) { a.model = m }
 }
 
+// WithAnthropicLogger attaches the logger used to report reasoning adjustments
+// (budget raised to fit max_tokens, ignored directives). A nil logger is ignored
+// so the discard default stays in place.
+func WithAnthropicLogger(l *slog.Logger) AnthropicOption {
+	return func(a *AnthropicChatAdapter) {
+		if l != nil {
+			a.log = l
+		}
+	}
+}
+
 // NewAnthropicChat builds an Anthropic adapter from a supplier config. baseURL is
 // trimmed of any trailing slash before the /v1/messages path is appended.
 func NewAnthropicChat(cfg config.LLMConfig, opts ...AnthropicOption) *AnthropicChatAdapter {
@@ -123,6 +151,7 @@ func NewAnthropicChat(cfg config.LLMConfig, opts ...AnthropicOption) *AnthropicC
 			Transport: http.DefaultTransport,
 			Timeout:   defaultHTTPTimeout,
 		},
+		log: discardLogger("runtime/model/anthropic"),
 	}
 	for _, o := range opts {
 		o(a)
@@ -264,6 +293,9 @@ func (a *AnthropicChatAdapter) buildRequest(req Request, stream bool) ([]byte, e
 		return nil, err
 	}
 	tokenLimit := effectiveMaxTokens(req.MaxTokens, anthropicDefaultMaxTokens)
+	// Extended thinking shares max_tokens with the visible answer, so the budget
+	// is resolved together with the limit it requires (design/04 §3.2 red line).
+	tokenLimit, thinking := anthropicThinkingFor(req.Thinking, tokenLimit, a.log)
 	wire := anthropicRequest{
 		Model:       req.Model,
 		System:      system,
@@ -272,6 +304,7 @@ func (a *AnthropicChatAdapter) buildRequest(req Request, stream bool) ([]byte, e
 		ToolChoice:  req.ToolChoice,
 		Temperature: req.Temperature,
 		MaxTokens:   tokenLimit,
+		Thinking:    thinking,
 		Stream:      stream,
 	}
 	buf, err := json.Marshal(wire)