forked from ericc-ch/copilot-api
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathcreate-chat-completions.ts
More file actions
235 lines (201 loc) · 5.13 KB
/
create-chat-completions.ts
File metadata and controls
235 lines (201 loc) · 5.13 KB
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
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
import consola from "consola"
import { events } from "fetch-event-stream"
import type { UpstreamTrace } from "~/lib/upstream-trace"
import { copilotHeaders, copilotBaseUrl } from "~/lib/api-config"
import { HTTPError } from "~/lib/error"
import {
isClaudeThinkingModel,
isCodexResponsesModel,
parseModelNameWithLevel,
} from "~/lib/model-level"
import { state } from "~/lib/state"
export const createChatCompletions = async (
payload: ChatCompletionsPayload,
trace?: UpstreamTrace,
) => {
if (!state.copilotToken) throw new Error("Copilot token not found")
const enableVision = payload.messages.some(
(x) =>
typeof x.content !== "string"
&& x.content?.some((x) => x.type === "image_url"),
)
// Agent/user check for X-Initiator header
// Determine if any message is from an agent ("assistant" or "tool")
const isAgentCall = payload.messages.some((msg) =>
["assistant", "tool"].includes(msg.role),
)
// Build headers and add X-Initiator
const headers: Record<string, string> = {
...copilotHeaders(state, enableVision, trace?.requestId),
"X-Initiator": isAgentCall ? "agent" : "user",
}
const response = await fetch(`${copilotBaseUrl(state)}/chat/completions`, {
method: "POST",
headers,
body: JSON.stringify(payload),
})
if (trace) {
trace.upstreamStatus = response.status
}
if (!response.ok) {
consola.error("Failed to create chat completions", response)
throw new HTTPError("Failed to create chat completions", response)
}
if (payload.stream) {
return events(response)
}
return (await response.json()) as ChatCompletionResponse
}
// Streaming types
export interface ChatCompletionChunk {
id: string
object: "chat.completion.chunk"
created: number
model: string
choices: Array<Choice>
system_fingerprint?: string
usage?: {
prompt_tokens: number
completion_tokens: number
total_tokens: number
prompt_tokens_details?: {
cached_tokens: number
}
completion_tokens_details?: {
accepted_prediction_tokens: number
rejected_prediction_tokens: number
}
}
}
interface Delta {
content?: string | null
role?: "user" | "assistant" | "system" | "tool"
tool_calls?: Array<{
index: number
id?: string
type?: "function"
function?: {
name?: string
arguments?: string
}
}>
}
interface Choice {
index: number
delta: Delta
finish_reason: "stop" | "length" | "tool_calls" | "content_filter" | null
logprobs: object | null
}
// Non-streaming types
export interface ChatCompletionResponse {
id: string
object: "chat.completion"
created: number
model: string
choices: Array<ChoiceNonStreaming>
system_fingerprint?: string
usage?: {
prompt_tokens: number
completion_tokens: number
total_tokens: number
prompt_tokens_details?: {
cached_tokens: number
}
}
}
interface ResponseMessage {
role: "assistant"
content: string | null
tool_calls?: Array<ToolCall>
}
interface ChoiceNonStreaming {
index: number
message: ResponseMessage
logprobs: object | null
finish_reason: "stop" | "length" | "tool_calls" | "content_filter"
}
// Payload types
export interface ChatCompletionsPayload {
messages: Array<Message>
model: string
temperature?: number | null
top_p?: number | null
max_tokens?: number | null
stop?: string | Array<string> | null
n?: number | null
stream?: boolean | null
frequency_penalty?: number | null
presence_penalty?: number | null
logit_bias?: Record<string, number> | null
logprobs?: boolean | null
response_format?: { type: "json_object" } | null
seed?: number | null
tools?: Array<Tool> | null
tool_choice?:
| "none"
| "auto"
| "required"
| { type: "function"; function: { name: string } }
| null
user?: string | null
reasoning_effort?: "low" | "medium" | "high" | "xhigh" | null
reasoning?: {
effort?: "low" | "medium" | "high" | "xhigh" | null
} | null
}
export interface Tool {
type: "function"
function: {
name: string
description?: string
parameters: Record<string, unknown>
}
}
export interface Message {
role: "user" | "assistant" | "system" | "tool" | "developer"
content: string | Array<ContentPart> | null
name?: string
tool_calls?: Array<ToolCall>
tool_call_id?: string
}
export interface ToolCall {
id: string
type: "function"
function: {
name: string
arguments: string
}
}
export type ContentPart = TextPart | ImagePart
export interface TextPart {
type: "text"
text: string
}
export interface ImagePart {
type: "image_url"
image_url: {
url: string
detail?: "low" | "high" | "auto"
}
}
export function normalizeChatCompletionsPayloadModel(
payload: ChatCompletionsPayload,
): ChatCompletionsPayload {
const { baseModel, level } = parseModelNameWithLevel(payload.model)
if (!level) return payload
if (isCodexResponsesModel(baseModel)) {
return {
...payload,
model: baseModel,
reasoning_effort: level,
}
}
if (isClaudeThinkingModel(baseModel)) {
return {
...payload,
model: baseModel,
reasoning: { effort: level },
}
}
return { ...payload, model: baseModel }
}