File size: 5,503 Bytes
8d3471e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
package openai

import (
	"encoding/json"
	"strings"
	"testing"

	"ds2api/internal/toolcall"
	"ds2api/internal/util"
)

func TestBuildResponseObjectKeepsFencedToolPayloadAsText(t *testing.T) {
	obj := BuildResponseObject(
		"resp_test",
		"gpt-4o",
		"prompt",
		"",
		"```json\n{\"tool_calls\":[{\"name\":\"search\",\"input\":{\"q\":\"golang\"}}]}\n```",
		[]string{"search"},
		nil,
	)

	outputText, _ := obj["output_text"].(string)
	if !strings.Contains(outputText, "\"tool_calls\"") {
		t.Fatalf("expected output_text to preserve fenced tool payload, got %q", outputText)
	}
	output, _ := obj["output"].([]any)
	if len(output) != 1 {
		t.Fatalf("expected one message output item, got %#v", obj["output"])
	}
	first, _ := output[0].(map[string]any)
	if first["type"] != "message" {
		t.Fatalf("expected message output type, got %#v", first["type"])
	}
}

// Backward-compatible alias for historical test name used in CI logs.
func TestBuildResponseObjectPromotesFencedToolPayloadToFunctionCall(t *testing.T) {
	TestBuildResponseObjectKeepsFencedToolPayloadAsText(t)
}

func TestBuildResponseObjectReasoningOnlyFallsBackToOutputText(t *testing.T) {
	obj := BuildResponseObject(
		"resp_test",
		"gpt-4o",
		"prompt",
		"internal thinking content",
		"",
		nil,
		nil,
	)

	outputText, _ := obj["output_text"].(string)
	if outputText == "" {
		t.Fatalf("expected output_text fallback from reasoning when final text is empty")
	}

	output, _ := obj["output"].([]any)
	if len(output) != 1 {
		t.Fatalf("expected one output item, got %#v", obj["output"])
	}
	first, _ := output[0].(map[string]any)
	if first["type"] != "message" {
		t.Fatalf("expected output type message, got %#v", first["type"])
	}
	content, _ := first["content"].([]any)
	if len(content) == 0 {
		t.Fatalf("expected reasoning content, got %#v", first["content"])
	}
	block0, _ := content[0].(map[string]any)
	if block0["type"] != "reasoning" {
		t.Fatalf("expected first content block reasoning, got %#v", block0["type"])
	}
}

func TestBuildResponseObjectPromotesToolCallFromThinkingWhenTextEmpty(t *testing.T) {
	obj := BuildResponseObject(
		"resp_test",
		"gpt-4o",
		"prompt",
		`<tool_calls><invoke name="search"><parameter name="q">from-thinking</parameter></invoke></tool_calls>`,
		"",
		[]string{"search"},
		nil,
	)

	output, _ := obj["output"].([]any)
	if len(output) != 1 {
		t.Fatalf("expected one output item, got %#v", obj["output"])
	}
	first, _ := output[0].(map[string]any)
	if first["type"] != "function_call" {
		t.Fatalf("expected function_call output, got %#v", first["type"])
	}
}

func TestBuildChatCompletionWithToolCallsCoercesSchemaDeclaredStringArguments(t *testing.T) {
	toolsRaw := []any{
		map[string]any{
			"type": "function",
			"function": map[string]any{
				"name": "Write",
				"parameters": map[string]any{
					"type": "object",
					"properties": map[string]any{
						"content": map[string]any{"type": "string"},
						"taskId":  map[string]any{"type": "string"},
					},
				},
			},
		},
	}
	obj := BuildChatCompletionWithToolCalls(
		"chat_test",
		"gpt-4o",
		"prompt",
		"",
		"",
		[]toolcall.ParsedToolCall{{
			Name: "Write",
			Input: map[string]any{
				"content": map[string]any{"message": "hi"},
				"taskId":  1,
			},
		}},
		toolsRaw,
	)
	choices, _ := obj["choices"].([]map[string]any)
	message, _ := choices[0]["message"].(map[string]any)
	toolCalls, _ := message["tool_calls"].([]map[string]any)
	fn, _ := toolCalls[0]["function"].(map[string]any)
	args := map[string]any{}
	if err := json.Unmarshal([]byte(fn["arguments"].(string)), &args); err != nil {
		t.Fatalf("decode arguments failed: %v", err)
	}
	if args["content"] != `{"message":"hi"}` {
		t.Fatalf("expected content stringified by schema, got %#v", args["content"])
	}
	if args["taskId"] != "1" {
		t.Fatalf("expected taskId stringified by schema, got %#v", args["taskId"])
	}
}

func TestBuildResponseObjectWithToolCallsCoercesSchemaDeclaredStringArguments(t *testing.T) {
	toolsRaw := []any{
		map[string]any{
			"type": "function",
			"function": map[string]any{
				"name": "Write",
				"parameters": map[string]any{
					"type": "object",
					"properties": map[string]any{
						"content": map[string]any{"type": "string"},
					},
				},
			},
		},
	}
	obj := BuildResponseObjectWithToolCalls(
		"resp_test",
		"gpt-4o",
		"prompt",
		"",
		"",
		[]toolcall.ParsedToolCall{{
			Name:  "Write",
			Input: map[string]any{"content": []any{"a", 1}},
		}},
		toolsRaw,
	)
	output, _ := obj["output"].([]any)
	first, _ := output[0].(map[string]any)
	args := map[string]any{}
	if err := json.Unmarshal([]byte(first["arguments"].(string)), &args); err != nil {
		t.Fatalf("decode response arguments failed: %v", err)
	}
	if args["content"] != `["a",1]` {
		t.Fatalf("expected response content stringified by schema, got %#v", args["content"])
	}
}

func TestBuildChatUsageForModelUsesConservativePromptCount(t *testing.T) {
	prompt := strings.Repeat("上下文token ", 40)
	usage := BuildChatUsageForModel("deepseek-v4-flash", prompt, "", "ok", 0)
	promptTokens, _ := usage["prompt_tokens"].(int)
	if promptTokens <= util.EstimateTokens(prompt) {
		t.Fatalf("expected conservative prompt token count > rough estimate, got=%d estimate=%d", promptTokens, util.EstimateTokens(prompt))
	}
	totalTokens, _ := usage["total_tokens"].(int)
	completionTokens, _ := usage["completion_tokens"].(int)
	if totalTokens != promptTokens+completionTokens {
		t.Fatalf("expected total tokens to add up, got usage=%#v", usage)
	}
}