AskaEth
3dc1232bc2
- 只翻注释/文档字符串：`go/scanner` 剥注释后按 token 序列+literal 逐 token 比对，**54/54 文件 SAME**；
改动文件总行数与 HEAD 漂移 = 0（严格 1:1，无合并/拆行）
- 裁决编号与 design 节号逐字保留（03.4.1/03.4.2/03.4.3/14.4.1/14.4.5/07.4.2-4、design/04 §3.1/§3.2 等）；
`chat_template_kwargs` / `enable_thinking` / `reasoning_effort` / `thinking:{type}` 字段名与形状说明未动
- 存疑译法（已登记）：`persona` 在叙事语境用「角色」、标识符语境保留 `persona`（仓库既有模块本身混用）；
`rung`→「级」；`provider` 存在「提供商/提供者」两种落笔（可按需一键统一）
- 复核：build/vet 绿 + 两包测试绿；gofmt 干净；残留英文注释 0 条
- 既有存量（未修，只报告）：`model/anthropic_test.go` 612 行 >500；`applyAnthropicEvent` 115 行 >80
70 lines
2.8 KiB
Go
70 lines
2.8 KiB
Go
package model
|
||
|
||
import (
|
||
"context"
|
||
"fmt"
|
||
"net/http"
|
||
"strings"
|
||
"testing"
|
||
|
||
"git.yeij.top/AskaEth/Cyrene_v2/internal/config"
|
||
)
|
||
|
||
// TestAnthropicChat_Chat_DefaultMaxTokensLargeEnoughForThinking 守护思考
|
||
// 模型的修复：其推理与可见答案共享 max_tokens 预算时，
|
||
// 零值默认必须给两者都留出空间。它还断言显式的
|
||
// Request.MaxTokens 绝不会被该默认覆盖
|
||
// （anthropic_test.go 里既有的 64-token 用例就是兼容性证明）。
|
||
func TestAnthropicChat_Chat_DefaultMaxTokensLargeEnoughForThinking(t *testing.T) {
|
||
t.Parallel()
|
||
ch := make(chan anthropicCaptured, 1)
|
||
srv := newAnthropicServer(t, http.StatusOK, "application/json", anthropicTextResponse, ch)
|
||
ad := NewAnthropicChat(config.LLMConfig{AnthropicBaseURL: srv.URL, AnthropicModel: "claude-test"})
|
||
|
||
if _, err := ad.Chat(context.Background(),
|
||
Request{Messages: []Message{TextMessage(RoleUser, "hi")}}, Options{}); err != nil {
|
||
t.Fatalf("Chat error: %v", err)
|
||
}
|
||
if got := (<-ch).body["max_tokens"]; got != float64(anthropicDefaultMaxTokens) {
|
||
t.Errorf("default body.max_tokens = %v, want %d", got, anthropicDefaultMaxTokens)
|
||
}
|
||
if anthropicDefaultMaxTokens < 4096 {
|
||
t.Errorf("anthropicDefaultMaxTokens = %d, too small for a long thinking turn plus its answer", anthropicDefaultMaxTokens)
|
||
}
|
||
}
|
||
|
||
// TestAnthropicChat_Chat_LongThinkingThenShortText 断言思考块
|
||
// 远长于文本块的响应仍会浮出文本，且
|
||
// 绝不把思考泄漏进 Content（思考不是答案的
|
||
// 红线）。这就是预算足够大时思考模型产出的形状，
|
||
// 与旧 1024 上限造成的截断形成对照。
|
||
func TestAnthropicChat_Chat_LongThinkingThenShortText(t *testing.T) {
|
||
t.Parallel()
|
||
thinking := strings.Repeat("推理", 1500) // 3000 runes, far longer than the answer
|
||
body := fmt.Sprintf(`{
|
||
"id":"msg_think","model":"claude-test",
|
||
"content":[
|
||
{"type":"thinking","thinking":%q},
|
||
{"type":"text","text":"现在是下午三点。"}
|
||
],
|
||
"usage":{"input_tokens":20,"output_tokens":900}
|
||
}`, thinking)
|
||
srv := newAnthropicServer(t, http.StatusOK, "application/json", body, nil)
|
||
ad := NewAnthropicChat(config.LLMConfig{AnthropicBaseURL: srv.URL, AnthropicModel: "claude-test"})
|
||
|
||
out, err := ad.Chat(context.Background(),
|
||
Request{Messages: []Message{TextMessage(RoleUser, "几点了？")}}, Options{})
|
||
if err != nil {
|
||
t.Fatalf("Chat error: %v", err)
|
||
}
|
||
if out.Content != "现在是下午三点。" {
|
||
t.Errorf("Content = %q, want the text block", out.Content)
|
||
}
|
||
if strings.Contains(out.Content, "推理") {
|
||
t.Errorf("Content leaked thinking: %q", out.Content)
|
||
}
|
||
if out.Message.Role != RoleAssistant || len(out.Message.Content) != 1 || out.Message.Content[0].Text != "现在是下午三点。" {
|
||
t.Errorf("Message = %+v, want a single assistant text part", out.Message)
|
||
}
|
||
}
|