copilot-custom-endpoint 3.7.0 → 4.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +41 -32
- package/docs/example-config.md +55 -53
- package/docs/models/glm.md +41 -41
- package/docs/models/kimi.md +13 -4
- package/docs/models/mimo.md +31 -37
- package/docs/models/minimax.md +34 -37
- package/docs/models/qwen.md +29 -24
- package/docs/pricing.md +15 -3
- package/lib/kimi-rewrite.mjs +78 -0
- package/lib/mimo-rewrite.mjs +1 -20
- package/lib/qwen-rewrite.mjs +45 -0
- package/lib/rewrite-summary.mjs +40 -0
- package/package.json +2 -2
- package/proxy/kimi-proxy.mjs +8 -102
- package/proxy/qwen-proxy.mjs +6 -63
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
import { hasActiveToolCall, summarizePayload } from './rewrite-summary.mjs'
|
|
2
|
+
|
|
3
|
+
export const QWEN_REWRITE_DEFAULTS = {
|
|
4
|
+
disableThinkingWithTools: true
|
|
5
|
+
}
|
|
6
|
+
|
|
7
|
+
/**
|
|
8
|
+
* Rewrite a DashScope/Qwen chat-completions payload in place.
|
|
9
|
+
*
|
|
10
|
+
* Thinking stays on for plain chat (the field is removed so DashScope uses its
|
|
11
|
+
* default) and is suppressed only for detected tool activity.
|
|
12
|
+
*
|
|
13
|
+
* @returns {{ summary: object, consoleMsg: string }}
|
|
14
|
+
*/
|
|
15
|
+
export function rewriteQwen(payload, options = {}) {
|
|
16
|
+
const { disableThinkingWithTools } = {
|
|
17
|
+
...QWEN_REWRITE_DEFAULTS,
|
|
18
|
+
...options
|
|
19
|
+
}
|
|
20
|
+
|
|
21
|
+
const hasTools = hasActiveToolCall(payload)
|
|
22
|
+
const incomingEnableThinking = payload.enable_thinking
|
|
23
|
+
const suppressThinking = disableThinkingWithTools && hasTools
|
|
24
|
+
|
|
25
|
+
if (suppressThinking) {
|
|
26
|
+
payload.enable_thinking = false
|
|
27
|
+
} else {
|
|
28
|
+
delete payload.enable_thinking
|
|
29
|
+
}
|
|
30
|
+
|
|
31
|
+
const rewriteInfo = {
|
|
32
|
+
incomingEnableThinking,
|
|
33
|
+
rewrittenEnableThinking: suppressThinking ? false : undefined
|
|
34
|
+
}
|
|
35
|
+
|
|
36
|
+
const modeTag = hasTools ? '[tools]' : '[chat]'
|
|
37
|
+
const consoleMsg = `${modeTag} enable_thinking=${String(incomingEnableThinking)} -> ${
|
|
38
|
+
suppressThinking ? 'false' : '<deleted>'
|
|
39
|
+
}, model=${payload.model ?? '?'}`
|
|
40
|
+
|
|
41
|
+
return {
|
|
42
|
+
summary: summarizePayload(payload, hasTools, rewriteInfo),
|
|
43
|
+
consoleMsg
|
|
44
|
+
}
|
|
45
|
+
}
|
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Build the NDJSON log summary shared by the provider rewrites.
|
|
3
|
+
* Keep this shape stable — it is the documented debug_log contract.
|
|
4
|
+
*/
|
|
5
|
+
export function summarizePayload(payload, hasTools, rewriteInfo) {
|
|
6
|
+
const messages = Array.isArray(payload.messages) ? payload.messages : []
|
|
7
|
+
const tools = Array.isArray(payload.tools) ? payload.tools : []
|
|
8
|
+
|
|
9
|
+
return {
|
|
10
|
+
model: payload.model,
|
|
11
|
+
stream: payload.stream,
|
|
12
|
+
...rewriteInfo,
|
|
13
|
+
maxTokens:
|
|
14
|
+
payload.max_tokens ??
|
|
15
|
+
payload.max_completion_tokens ??
|
|
16
|
+
payload.max_output_tokens,
|
|
17
|
+
toolChoice: payload.tool_choice,
|
|
18
|
+
toolCount: tools.length,
|
|
19
|
+
hasTools,
|
|
20
|
+
messageCount: messages.length,
|
|
21
|
+
messageRoles: messages.map((message) => message?.role).slice(0, 16),
|
|
22
|
+
topLevelKeys: Object.keys(payload).sort()
|
|
23
|
+
}
|
|
24
|
+
}
|
|
25
|
+
|
|
26
|
+
/**
|
|
27
|
+
* A request counts as tool activity when a "tool" role message is present or
|
|
28
|
+
* `tool_choice` is set to anything other than "none"/null. A nonempty `tools`
|
|
29
|
+
* array alone is not enough — see docs/models/qwen.md.
|
|
30
|
+
*/
|
|
31
|
+
export function hasActiveToolCall(payload) {
|
|
32
|
+
const messages = Array.isArray(payload.messages) ? payload.messages : []
|
|
33
|
+
const hasToolRole = messages.some((message) => message?.role === 'tool')
|
|
34
|
+
const toolChoice = payload.tool_choice
|
|
35
|
+
|
|
36
|
+
return (
|
|
37
|
+
hasToolRole ||
|
|
38
|
+
(toolChoice !== undefined && toolChoice !== 'none' && toolChoice !== null)
|
|
39
|
+
)
|
|
40
|
+
}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "copilot-custom-endpoint",
|
|
3
|
-
"version": "
|
|
3
|
+
"version": "4.0.0",
|
|
4
4
|
"description": "Local proxies for VS Code Copilot custom endpoints — Kimi K2, Qwen 3.x & MiMo V2.6",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"type": "module",
|
|
@@ -57,4 +57,4 @@
|
|
|
57
57
|
"dependencies": {
|
|
58
58
|
"dotenv": "^17.4.2"
|
|
59
59
|
}
|
|
60
|
-
}
|
|
60
|
+
}
|
package/proxy/kimi-proxy.mjs
CHANGED
|
@@ -2,6 +2,7 @@
|
|
|
2
2
|
import 'dotenv/config'
|
|
3
3
|
import { fileURLToPath } from 'node:url'
|
|
4
4
|
import { createProxy } from '../lib/create-proxy.mjs'
|
|
5
|
+
import { rewriteKimi } from '../lib/kimi-rewrite.mjs'
|
|
5
6
|
|
|
6
7
|
/**
|
|
7
8
|
* Supported model scope for this proxy:
|
|
@@ -86,107 +87,6 @@ if (!Number.isFinite(forcedTopP)) {
|
|
|
86
87
|
)
|
|
87
88
|
}
|
|
88
89
|
|
|
89
|
-
// ---- Provider-specific rewrite logic ----
|
|
90
|
-
|
|
91
|
-
function summarizePayload(payload, hasTools, rewriteInfo) {
|
|
92
|
-
const messages = Array.isArray(payload.messages) ? payload.messages : []
|
|
93
|
-
const tools = Array.isArray(payload.tools) ? payload.tools : []
|
|
94
|
-
|
|
95
|
-
return {
|
|
96
|
-
model: payload.model,
|
|
97
|
-
stream: payload.stream,
|
|
98
|
-
...rewriteInfo,
|
|
99
|
-
maxTokens:
|
|
100
|
-
payload.max_tokens ??
|
|
101
|
-
payload.max_completion_tokens ??
|
|
102
|
-
payload.max_output_tokens,
|
|
103
|
-
toolChoice: payload.tool_choice,
|
|
104
|
-
toolCount: tools.length,
|
|
105
|
-
hasTools,
|
|
106
|
-
messageCount: messages.length,
|
|
107
|
-
messageRoles: messages.map((message) => message?.role).slice(0, 16),
|
|
108
|
-
topLevelKeys: Object.keys(payload).sort()
|
|
109
|
-
}
|
|
110
|
-
}
|
|
111
|
-
|
|
112
|
-
function rewriteKimi(payload) {
|
|
113
|
-
const incomingTemperature = payload.temperature
|
|
114
|
-
const incomingTopP = payload.top_p
|
|
115
|
-
const incomingThinkingType = payload?.thinking?.type
|
|
116
|
-
const incomingReasoningEffort = payload?.reasoning_effort
|
|
117
|
-
const model = payload.model ?? ''
|
|
118
|
-
|
|
119
|
-
// K2.7 and K3 are always-thinking and reject thinking: disabled.
|
|
120
|
-
// K2.7 uses `thinking` parameter; K3 uses `reasoning_effort` instead.
|
|
121
|
-
// Detect K2.7 variants (e.g. kimi-k2.7-code) and K3-family variants
|
|
122
|
-
// (e.g. kimi-k3, kimi-k3.1-pro, kimi-k3.1-pro-highspeed) and skip the
|
|
123
|
-
// thinking-disable rewrite while keeping temperature/top_p enforcement.
|
|
124
|
-
const isK27 = model.startsWith('kimi-k2.7')
|
|
125
|
-
const isK3 = model.startsWith('kimi-k3')
|
|
126
|
-
const isAlwaysThinking = isK27 || isK3
|
|
127
|
-
|
|
128
|
-
// Determine if a tool is actually being invoked:
|
|
129
|
-
// - tool_choice is set and not "none"
|
|
130
|
-
// - OR there is a "tool" role message in the conversation
|
|
131
|
-
const messages = Array.isArray(payload.messages) ? payload.messages : []
|
|
132
|
-
const hasToolRole = messages.some((message) => message?.role === 'tool')
|
|
133
|
-
const toolChoice = payload.tool_choice
|
|
134
|
-
const hasActiveToolCall =
|
|
135
|
-
hasToolRole ||
|
|
136
|
-
(toolChoice !== undefined && toolChoice !== 'none' && toolChoice !== null)
|
|
137
|
-
const hasTools = hasActiveToolCall
|
|
138
|
-
|
|
139
|
-
const useNonThinkingMode =
|
|
140
|
-
!isAlwaysThinking && disableThinkingWithTools && hasTools
|
|
141
|
-
const rewrittenTemperature = useNonThinkingMode
|
|
142
|
-
? forcedNonThinkingTemperature
|
|
143
|
-
: forcedTemperature
|
|
144
|
-
|
|
145
|
-
// Capture incoming state before mutation
|
|
146
|
-
payload.__incomingThinkingType = incomingThinkingType
|
|
147
|
-
payload.__incomingReasoningEffort = incomingReasoningEffort
|
|
148
|
-
|
|
149
|
-
// Apply rewrites
|
|
150
|
-
payload.temperature = rewrittenTemperature
|
|
151
|
-
payload.top_p = forcedTopP
|
|
152
|
-
|
|
153
|
-
if (useNonThinkingMode) {
|
|
154
|
-
payload.thinking = { type: 'disabled' }
|
|
155
|
-
}
|
|
156
|
-
|
|
157
|
-
// K3 does not accept `thinking` — delete it if present so it doesn't cause a 400
|
|
158
|
-
if (isK3 && payload.thinking) {
|
|
159
|
-
delete payload.thinking
|
|
160
|
-
}
|
|
161
|
-
|
|
162
|
-
const rewrittenThinkingType = payload.thinking?.type
|
|
163
|
-
const rewriteInfo = {
|
|
164
|
-
model,
|
|
165
|
-
isK27,
|
|
166
|
-
isK3,
|
|
167
|
-
incomingTemperature,
|
|
168
|
-
rewrittenTemperature,
|
|
169
|
-
incomingTopP,
|
|
170
|
-
rewrittenTopP: forcedTopP,
|
|
171
|
-
incomingThinkingType,
|
|
172
|
-
rewrittenThinkingType,
|
|
173
|
-
incomingReasoningEffort
|
|
174
|
-
}
|
|
175
|
-
|
|
176
|
-
const summary = summarizePayload(payload, hasTools, rewriteInfo)
|
|
177
|
-
|
|
178
|
-
const modeTag = hasTools ? '[tools]' : '[chat]'
|
|
179
|
-
const k27Tag = isK27 ? '[k2.7]' : ''
|
|
180
|
-
const k3Tag = isK3 ? '[k3]' : ''
|
|
181
|
-
const consoleMsg = `${k27Tag}${k3Tag}${modeTag} temperature ${String(incomingTemperature)} -> ${String(rewrittenTemperature)}, top_p ${String(incomingTopP)} -> ${String(forcedTopP)}, thinking ${String(incomingThinkingType)} -> ${String(rewrittenThinkingType)}, reasoning_effort ${String(incomingReasoningEffort)}`
|
|
182
|
-
|
|
183
|
-
// Clean up internal keys before forwarding
|
|
184
|
-
delete payload.__incomingThinkingType
|
|
185
|
-
delete payload.__incomingReasoningEffort
|
|
186
|
-
|
|
187
|
-
return { summary, consoleMsg }
|
|
188
|
-
}
|
|
189
|
-
|
|
190
90
|
// ---- Create and start ----
|
|
191
91
|
|
|
192
92
|
const { start } = createProxy({
|
|
@@ -195,7 +95,13 @@ const { start } = createProxy({
|
|
|
195
95
|
logPath,
|
|
196
96
|
label: 'kimi-proxy',
|
|
197
97
|
healthCheckExtras: { forcedTemperature, forcedTopP },
|
|
198
|
-
rewriteRequest:
|
|
98
|
+
rewriteRequest: (payload) =>
|
|
99
|
+
rewriteKimi(payload, {
|
|
100
|
+
forcedTemperature,
|
|
101
|
+
forcedNonThinkingTemperature,
|
|
102
|
+
forcedTopP,
|
|
103
|
+
disableThinkingWithTools
|
|
104
|
+
}),
|
|
199
105
|
startupMessages: (_port, _upstreamUrl) => [
|
|
200
106
|
`[kimi-proxy] listening on http://127.0.0.1:${_port}/v1/chat/completions`,
|
|
201
107
|
`[kimi-proxy] forwarding to ${_upstreamUrl}`,
|
package/proxy/qwen-proxy.mjs
CHANGED
|
@@ -2,6 +2,7 @@
|
|
|
2
2
|
import 'dotenv/config'
|
|
3
3
|
import { fileURLToPath } from 'node:url'
|
|
4
4
|
import { createProxy } from '../lib/create-proxy.mjs'
|
|
5
|
+
import { rewriteQwen } from '../lib/qwen-rewrite.mjs'
|
|
5
6
|
|
|
6
7
|
/**
|
|
7
8
|
* Supported model scope for this proxy:
|
|
@@ -33,8 +34,9 @@ if (process.argv.includes('--help')) {
|
|
|
33
34
|
console.log(`Qwen proxy
|
|
34
35
|
|
|
35
36
|
Starts a local HTTP proxy that conditionally injects enable_thinking: false
|
|
36
|
-
when the request
|
|
37
|
-
|
|
37
|
+
when the request shows tool activity (a tool-role message or a non-default
|
|
38
|
+
tool_choice), letting Qwen hybrid-thinking models show reasoning in plain
|
|
39
|
+
chat while keeping tool loops stable.
|
|
38
40
|
|
|
39
41
|
The proxy forwards the requested model ID unchanged, including the DashScope
|
|
40
42
|
ID qwen3.8-max and OpenRouter ID qwen/qwen3.8-max-0902.
|
|
@@ -57,66 +59,6 @@ Suggested VS Code model URL:
|
|
|
57
59
|
process.exit(0)
|
|
58
60
|
}
|
|
59
61
|
|
|
60
|
-
// ---- Provider-specific rewrite logic ----
|
|
61
|
-
|
|
62
|
-
function summarizePayload(payload, hasTools, rewriteInfo) {
|
|
63
|
-
const messages = Array.isArray(payload.messages) ? payload.messages : []
|
|
64
|
-
const tools = Array.isArray(payload.tools) ? payload.tools : []
|
|
65
|
-
|
|
66
|
-
return {
|
|
67
|
-
model: payload.model,
|
|
68
|
-
stream: payload.stream,
|
|
69
|
-
hasTools,
|
|
70
|
-
toolCount: tools.length,
|
|
71
|
-
toolChoice: payload.tool_choice,
|
|
72
|
-
...rewriteInfo,
|
|
73
|
-
maxTokens:
|
|
74
|
-
payload.max_tokens ??
|
|
75
|
-
payload.max_completion_tokens ??
|
|
76
|
-
payload.max_output_tokens,
|
|
77
|
-
messageCount: messages.length,
|
|
78
|
-
messageRoles: messages.map((message) => message?.role).slice(0, 16),
|
|
79
|
-
topLevelKeys: Object.keys(payload).sort()
|
|
80
|
-
}
|
|
81
|
-
}
|
|
82
|
-
|
|
83
|
-
function rewriteQwen(payload) {
|
|
84
|
-
// Determine if a tool is actually being invoked:
|
|
85
|
-
// - tool_choice is set and not "none"
|
|
86
|
-
// - OR there is a "tool" role message in the conversation
|
|
87
|
-
const messages = Array.isArray(payload.messages) ? payload.messages : []
|
|
88
|
-
const hasToolRole = messages.some((message) => message?.role === 'tool')
|
|
89
|
-
const toolChoice = payload.tool_choice
|
|
90
|
-
const hasActiveToolCall =
|
|
91
|
-
hasToolRole ||
|
|
92
|
-
(toolChoice !== undefined && toolChoice !== 'none' && toolChoice !== null)
|
|
93
|
-
const hasTools = hasActiveToolCall
|
|
94
|
-
const incomingEnableThinking = payload.enable_thinking
|
|
95
|
-
|
|
96
|
-
if (disableThinkingWithTools && hasTools) {
|
|
97
|
-
// Tool-enabled request: suppress thinking to avoid reasoning_content issues
|
|
98
|
-
payload.enable_thinking = false
|
|
99
|
-
} else {
|
|
100
|
-
// Plain chat: remove enable_thinking so the model uses its default (true)
|
|
101
|
-
delete payload.enable_thinking
|
|
102
|
-
}
|
|
103
|
-
|
|
104
|
-
const rewrittenEnableThinking =
|
|
105
|
-
disableThinkingWithTools && hasTools ? false : undefined
|
|
106
|
-
|
|
107
|
-
const summary = summarizePayload(payload, hasTools, {
|
|
108
|
-
incomingEnableThinking,
|
|
109
|
-
rewrittenEnableThinking
|
|
110
|
-
})
|
|
111
|
-
|
|
112
|
-
const modeTag = hasTools ? '[tools]' : '[chat]'
|
|
113
|
-
const consoleMsg = `${modeTag} enable_thinking=${String(incomingEnableThinking)} -> ${
|
|
114
|
-
hasTools && disableThinkingWithTools ? 'false' : '<deleted>'
|
|
115
|
-
}, model=${payload.model ?? '?'}`
|
|
116
|
-
|
|
117
|
-
return { summary, consoleMsg }
|
|
118
|
-
}
|
|
119
|
-
|
|
120
62
|
// ---- Create and start ----
|
|
121
63
|
|
|
122
64
|
const { start } = createProxy({
|
|
@@ -125,7 +67,8 @@ const { start } = createProxy({
|
|
|
125
67
|
logPath,
|
|
126
68
|
label: 'qwen-proxy',
|
|
127
69
|
healthCheckExtras: { disableThinkingWithTools },
|
|
128
|
-
rewriteRequest:
|
|
70
|
+
rewriteRequest: (payload) =>
|
|
71
|
+
rewriteQwen(payload, { disableThinkingWithTools }),
|
|
129
72
|
startupMessages: (_port, _upstreamUrl) => [
|
|
130
73
|
`[qwen-proxy] listening on http://127.0.0.1:${_port}/v1/chat/completions`,
|
|
131
74
|
`[qwen-proxy] forwarding to ${_upstreamUrl}`,
|