expert_eval_cli 1.5.0 → 2.0.0
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 +40 -21
- package/dist/client.d.ts +13 -23
- package/dist/client.d.ts.map +1 -1
- package/dist/client.js +36 -75
- package/dist/client.js.map +1 -1
- package/dist/commands/eval-records.d.ts.map +1 -1
- package/dist/commands/eval-records.js +76 -111
- package/dist/commands/eval-records.js.map +1 -1
- package/dist/commands/eval-tasks.d.ts.map +1 -1
- package/dist/commands/eval-tasks.js +73 -78
- package/dist/commands/eval-tasks.js.map +1 -1
- package/dist/commands/experts.d.ts.map +1 -1
- package/dist/commands/experts.js +110 -102
- package/dist/commands/experts.js.map +1 -1
- package/dist/commands/versions.d.ts.map +1 -1
- package/dist/commands/versions.js +83 -70
- package/dist/commands/versions.js.map +1 -1
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +1 -5
- package/dist/index.js.map +1 -1
- package/dist/types.d.ts +93 -182
- package/dist/types.d.ts.map +1 -1
- package/dist/types.js +1 -1
- package/dist/types.js.map +1 -1
- package/package.json +4 -3
- package/skill/SKILL.md +15 -11
- package/skill/references/api-reference.md +61 -55
- package/dist/commands/eval-cases.d.ts +0 -3
- package/dist/commands/eval-cases.d.ts.map +0 -1
- package/dist/commands/eval-cases.js +0 -136
- package/dist/commands/eval-cases.js.map +0 -1
- package/dist/commands/eval-items.d.ts +0 -3
- package/dist/commands/eval-items.d.ts.map +0 -1
- package/dist/commands/eval-items.js +0 -204
- package/dist/commands/eval-items.js.map +0 -1
package/dist/index.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";;
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";;AAQA,sCAkBC;AA1BD,yCAAoC;AACpC,gDAAqD;AACrD,sDAA2D;AAC3D,wDAA6D;AAC7D,gEAAoE;AACpE,4DAAgE;AAChE,oEAAwE;AAExE,SAAgB,aAAa;IAC3B,MAAM,OAAO,GAAG,IAAI,mBAAO,EAAE,CAAC;IAE9B,OAAO;SACJ,IAAI,CAAC,aAAa,CAAC;SACnB,WAAW,CAAC,oCAAoC,CAAC;SACjD,OAAO,CAAC,OAAO,CAAC;SAChB,MAAM,CAAC,iBAAiB,EAAE,0DAA0D,EAAE,MAAM,CAAC;SAC7F,MAAM,CAAC,aAAa,EAAE,mCAAmC,EAAE,KAAK,CAAC,CAAC;IAErE,OAAO,CAAC,UAAU,CAAC,IAAA,yBAAe,GAAE,CAAC,CAAC;IACtC,OAAO,CAAC,UAAU,CAAC,IAAA,+BAAkB,GAAE,CAAC,CAAC;IACzC,OAAO,CAAC,UAAU,CAAC,IAAA,iCAAmB,GAAE,CAAC,CAAC;IAC1C,OAAO,CAAC,UAAU,CAAC,IAAA,wCAAsB,GAAE,CAAC,CAAC;IAC7C,OAAO,CAAC,UAAU,CAAC,IAAA,oCAAoB,GAAE,CAAC,CAAC;IAC3C,OAAO,CAAC,UAAU,CAAC,IAAA,4CAAwB,GAAE,CAAC,CAAC;IAE/C,OAAO,OAAO,CAAC;AACjB,CAAC"}
|
package/dist/types.d.ts
CHANGED
|
@@ -1,61 +1,69 @@
|
|
|
1
|
+
export type JsonObject = Record<string, unknown>;
|
|
2
|
+
export type ExpertStatus = 'developing' | 'adjusting' | 'published' | 'paused';
|
|
3
|
+
export type EvalTaskStatus = 'pending' | 'in_progress' | 'failed' | 'changes_requested' | 'passed';
|
|
4
|
+
export type EvalRecordStatus = 'untested' | 'passed' | 'warning' | 'failed';
|
|
5
|
+
export type EvalRecordLevel = 'PASS' | 'WARNING' | 'FAIL' | string;
|
|
6
|
+
export type AgentAccountStatus = 'ready' | 'running';
|
|
1
7
|
export interface Expert {
|
|
2
8
|
id: string;
|
|
3
9
|
expertId: string;
|
|
4
10
|
name: string;
|
|
11
|
+
status: ExpertStatus;
|
|
5
12
|
avatar?: string | null;
|
|
6
|
-
type?: string;
|
|
7
|
-
field?: string;
|
|
8
|
-
title?: string;
|
|
9
|
-
organization?: string;
|
|
10
|
-
membersCount?: number | null;
|
|
11
|
-
members?: string[];
|
|
12
13
|
tags?: string[];
|
|
13
14
|
description?: string | null;
|
|
14
|
-
recommendedQuestion?: Record<string, string> | null;
|
|
15
15
|
aiTags?: string[];
|
|
16
|
-
owner?: string
|
|
17
|
-
|
|
16
|
+
owner?: string | null;
|
|
17
|
+
latestVersionId?: string | null;
|
|
18
|
+
latestVersionNo?: number | null;
|
|
19
|
+
latestUploadedAt?: string | null;
|
|
20
|
+
agentJson?: JsonObject | null;
|
|
21
|
+
agentYaml?: string | null;
|
|
22
|
+
skillJson?: JsonObject[] | null;
|
|
18
23
|
createdAt: string;
|
|
19
24
|
updatedAt: string;
|
|
20
25
|
}
|
|
21
26
|
export interface Version {
|
|
22
27
|
id: string;
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
28
|
+
expertId: string;
|
|
29
|
+
versionNo: number;
|
|
30
|
+
packageUrl: string;
|
|
31
|
+
packageName?: string | null;
|
|
32
|
+
agentJson?: JsonObject | null;
|
|
33
|
+
agentYaml?: string | null;
|
|
34
|
+
uploadedAt: string;
|
|
29
35
|
createdAt: string;
|
|
30
36
|
updatedAt: string;
|
|
31
37
|
}
|
|
32
|
-
export
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
38
|
+
export interface EvalResultSummary {
|
|
39
|
+
total: number;
|
|
40
|
+
passed: number;
|
|
41
|
+
warning: number;
|
|
42
|
+
failed: number;
|
|
43
|
+
untested: number;
|
|
44
|
+
failItemCodes?: string[];
|
|
45
|
+
warnItemCodes?: string[];
|
|
46
|
+
}
|
|
47
|
+
export interface EvalCaseSummary {
|
|
48
|
+
total: number;
|
|
49
|
+
passed: number;
|
|
50
|
+
failed: number;
|
|
51
|
+
untested: number;
|
|
46
52
|
}
|
|
47
53
|
export interface EvalRecord {
|
|
48
54
|
id: string;
|
|
49
55
|
evalTaskId: string;
|
|
50
56
|
evalItemId: string;
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
|
|
57
|
+
itemCode: string;
|
|
58
|
+
itemTitle: string;
|
|
59
|
+
category?: string | null;
|
|
60
|
+
dimensionName?: string | null;
|
|
61
|
+
level?: EvalRecordLevel | null;
|
|
62
|
+
automatable?: boolean;
|
|
63
|
+
standard?: string | null;
|
|
64
|
+
status: EvalRecordStatus;
|
|
65
|
+
comment?: string | null;
|
|
66
|
+
evidence?: string | null;
|
|
59
67
|
createdAt: string;
|
|
60
68
|
updatedAt: string;
|
|
61
69
|
}
|
|
@@ -68,25 +76,40 @@ export interface EvalCase {
|
|
|
68
76
|
evaluationCriteria: string;
|
|
69
77
|
artifactLink?: string | null;
|
|
70
78
|
taskLink?: string | null;
|
|
71
|
-
extras?:
|
|
79
|
+
extras?: JsonObject | null;
|
|
80
|
+
status?: EvalRecordStatus;
|
|
72
81
|
executionStartTime?: string | null;
|
|
73
82
|
executionEndTime?: string | null;
|
|
74
83
|
createdAt: string;
|
|
75
84
|
updatedAt: string;
|
|
76
85
|
}
|
|
77
|
-
export interface EvalTaskPackage {
|
|
78
|
-
bucketId: string;
|
|
79
|
-
filePath: string;
|
|
80
|
-
}
|
|
81
86
|
export interface EvalTask {
|
|
82
87
|
id: string;
|
|
83
88
|
expertId: string;
|
|
84
89
|
versionId: string;
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
+
versionNo: number;
|
|
91
|
+
name: string;
|
|
92
|
+
status: EvalTaskStatus;
|
|
93
|
+
resultSummary: EvalResultSummary;
|
|
94
|
+
caseSummary: EvalCaseSummary;
|
|
95
|
+
evaluator?: string | null;
|
|
96
|
+
startedAt?: string | null;
|
|
97
|
+
completedAt?: string | null;
|
|
98
|
+
createdAt: string;
|
|
99
|
+
updatedAt: string;
|
|
100
|
+
expertName?: string;
|
|
101
|
+
expertUuidId?: string;
|
|
102
|
+
version?: Version;
|
|
103
|
+
records?: EvalRecord[];
|
|
104
|
+
cases?: EvalCase[];
|
|
105
|
+
}
|
|
106
|
+
export interface AgentAccount {
|
|
107
|
+
id: string;
|
|
108
|
+
agentId: string;
|
|
109
|
+
owner?: string | null;
|
|
110
|
+
status: AgentAccountStatus;
|
|
111
|
+
startTime?: string | null;
|
|
112
|
+
endTime?: string | null;
|
|
90
113
|
createdAt: string;
|
|
91
114
|
updatedAt: string;
|
|
92
115
|
}
|
|
@@ -113,173 +136,61 @@ export interface ApiErrorResponse {
|
|
|
113
136
|
export interface CreateExpertPayload {
|
|
114
137
|
expertId: string;
|
|
115
138
|
name: string;
|
|
116
|
-
|
|
117
|
-
type?: string;
|
|
118
|
-
field?: string;
|
|
119
|
-
title?: string;
|
|
120
|
-
organization?: string;
|
|
121
|
-
membersCount?: number | null;
|
|
122
|
-
members?: string[];
|
|
123
|
-
tags?: string[];
|
|
139
|
+
owner?: string | null;
|
|
124
140
|
description?: string | null;
|
|
125
|
-
|
|
126
|
-
aiTags?: string[];
|
|
127
|
-
owner?: string[];
|
|
128
|
-
latestVersionTask?: string | null;
|
|
141
|
+
status?: ExpertStatus;
|
|
129
142
|
}
|
|
130
143
|
export interface UpdateExpertPayload {
|
|
131
|
-
|
|
132
|
-
|
|
133
|
-
avatar?: string | null;
|
|
134
|
-
type?: string;
|
|
135
|
-
field?: string;
|
|
136
|
-
title?: string;
|
|
137
|
-
organization?: string;
|
|
138
|
-
membersCount?: number | null;
|
|
139
|
-
members?: string[];
|
|
140
|
-
tags?: string[];
|
|
144
|
+
name?: string;
|
|
145
|
+
owner?: string | null;
|
|
141
146
|
description?: string | null;
|
|
142
|
-
|
|
143
|
-
aiTags?: string[];
|
|
144
|
-
owner?: string[];
|
|
145
|
-
latestVersionTask?: string | null;
|
|
147
|
+
status?: ExpertStatus;
|
|
146
148
|
}
|
|
147
149
|
export interface CreateVersionPayload {
|
|
148
|
-
hash: string;
|
|
149
|
-
diff?: string | null;
|
|
150
|
-
commitMessage?: string | null;
|
|
151
|
-
author?: string | null;
|
|
152
|
-
evaluationDate?: string | null;
|
|
153
|
-
summary?: string | null;
|
|
154
|
-
}
|
|
155
|
-
export interface UpdateVersionPayload {
|
|
156
|
-
hash: string;
|
|
157
|
-
diff?: string | null;
|
|
158
|
-
commitMessage?: string | null;
|
|
159
|
-
author?: string | null;
|
|
160
|
-
evaluationDate?: string | null;
|
|
161
|
-
summary?: string | null;
|
|
162
|
-
}
|
|
163
|
-
export interface CreateEvalTaskPayload {
|
|
164
150
|
expertId: string;
|
|
165
|
-
|
|
166
|
-
|
|
167
|
-
|
|
168
|
-
|
|
169
|
-
|
|
170
|
-
dcg?: number | null;
|
|
151
|
+
packageZip?: string;
|
|
152
|
+
packageName?: string | null;
|
|
153
|
+
agentJson?: JsonObject | null;
|
|
154
|
+
agentYaml?: string | null;
|
|
155
|
+
skillJson?: JsonObject[] | null;
|
|
171
156
|
}
|
|
172
|
-
export interface
|
|
173
|
-
expertId: string;
|
|
157
|
+
export interface CreateEvalTaskPayload {
|
|
174
158
|
versionId: string;
|
|
175
|
-
|
|
176
|
-
package?: EvalTaskPackage | null;
|
|
177
|
-
isPassed?: boolean;
|
|
178
|
-
bac?: number | null;
|
|
179
|
-
dcg?: number | null;
|
|
180
|
-
}
|
|
181
|
-
export interface CreateEvalItemPayload {
|
|
182
|
-
itemCode: string;
|
|
183
|
-
title: string;
|
|
184
|
-
category?: string;
|
|
185
|
-
description?: string | null;
|
|
186
|
-
maxScore?: number;
|
|
187
|
-
itemTypes?: EvalItemType[];
|
|
188
|
-
query?: string | null;
|
|
189
|
-
acceptanceCriteria?: string | null;
|
|
190
|
-
isVeto?: boolean;
|
|
191
|
-
}
|
|
192
|
-
export interface UpdateEvalItemPayload {
|
|
193
|
-
itemCode?: string;
|
|
194
|
-
title?: string;
|
|
195
|
-
category?: string;
|
|
196
|
-
description?: string | null;
|
|
197
|
-
maxScore?: number;
|
|
198
|
-
itemTypes?: EvalItemType[];
|
|
199
|
-
query?: string | null;
|
|
200
|
-
acceptanceCriteria?: string | null;
|
|
201
|
-
isVeto?: boolean;
|
|
202
|
-
}
|
|
203
|
-
export interface CreateEvalRecordPayload {
|
|
204
|
-
evalTaskId: string;
|
|
205
|
-
evalItemId: string;
|
|
206
|
-
query?: string | null;
|
|
207
|
-
result?: string | null;
|
|
208
|
-
isPassed: boolean;
|
|
209
|
-
dcg?: number | null;
|
|
210
|
-
thinkingProcess?: string | null;
|
|
211
|
-
expertItemTitle?: string | null;
|
|
212
|
-
executionStartTime?: string | null;
|
|
213
|
-
executionEndTime?: string | null;
|
|
159
|
+
name?: string | null;
|
|
214
160
|
}
|
|
215
161
|
export interface UpdateEvalRecordPayload {
|
|
216
|
-
|
|
217
|
-
|
|
218
|
-
|
|
219
|
-
result?: string | null;
|
|
220
|
-
isPassed?: boolean;
|
|
221
|
-
dcg?: number | null;
|
|
222
|
-
thinkingProcess?: string | null;
|
|
223
|
-
expertItemTitle?: string | null;
|
|
224
|
-
executionStartTime?: string | null;
|
|
225
|
-
executionEndTime?: string | null;
|
|
162
|
+
status?: EvalRecordStatus;
|
|
163
|
+
comment?: string | null;
|
|
164
|
+
evidence?: string | null;
|
|
226
165
|
}
|
|
227
|
-
export interface
|
|
228
|
-
|
|
229
|
-
|
|
230
|
-
|
|
231
|
-
actualResult?: string | null;
|
|
232
|
-
evaluationCriteria: string;
|
|
233
|
-
artifactLink?: string | null;
|
|
234
|
-
taskLink?: string | null;
|
|
235
|
-
extras?: Record<string, unknown> | null;
|
|
236
|
-
executionStartTime?: string | null;
|
|
237
|
-
executionEndTime?: string | null;
|
|
166
|
+
export interface BatchUpdateEvalRecordsPayload {
|
|
167
|
+
records: Array<UpdateEvalRecordPayload & {
|
|
168
|
+
id: string;
|
|
169
|
+
}>;
|
|
238
170
|
}
|
|
239
171
|
export interface ListExpertsParams {
|
|
240
172
|
page?: number;
|
|
241
173
|
pageSize?: number;
|
|
242
174
|
keyword?: string;
|
|
175
|
+
status?: ExpertStatus;
|
|
243
176
|
}
|
|
244
177
|
export interface ListVersionsParams {
|
|
245
178
|
page?: number;
|
|
246
179
|
pageSize?: number;
|
|
180
|
+
expertId?: string;
|
|
247
181
|
}
|
|
248
182
|
export interface ListEvalTasksParams {
|
|
249
183
|
page?: number;
|
|
250
184
|
pageSize?: number;
|
|
251
185
|
expertId?: string;
|
|
252
186
|
versionId?: string;
|
|
253
|
-
|
|
254
|
-
export interface ListEvalItemsParams {
|
|
255
|
-
page?: number;
|
|
256
|
-
pageSize?: number;
|
|
257
|
-
category?: string;
|
|
258
|
-
itemTypes?: EvalItemType[];
|
|
187
|
+
status?: EvalTaskStatus;
|
|
259
188
|
}
|
|
260
189
|
export interface ListEvalRecordsParams {
|
|
261
|
-
page?: number;
|
|
262
|
-
pageSize?: number;
|
|
263
|
-
evalTaskId?: string;
|
|
264
|
-
evalItemId?: string;
|
|
265
|
-
}
|
|
266
|
-
export interface ListEvalCasesParams {
|
|
267
|
-
page?: number;
|
|
268
|
-
pageSize?: number;
|
|
269
190
|
evalTaskId: string;
|
|
270
191
|
}
|
|
271
|
-
export interface AgentAccount {
|
|
272
|
-
id: string;
|
|
273
|
-
agentId: string;
|
|
274
|
-
owner?: string | null;
|
|
275
|
-
status: 'ready' | 'running';
|
|
276
|
-
startTime?: string | null;
|
|
277
|
-
endTime?: string | null;
|
|
278
|
-
createdAt: string;
|
|
279
|
-
updatedAt: string;
|
|
280
|
-
}
|
|
281
192
|
export interface ListAgentAccountsParams {
|
|
282
|
-
status?:
|
|
193
|
+
status?: AgentAccountStatus;
|
|
283
194
|
owner?: string;
|
|
284
195
|
}
|
|
285
196
|
//# sourceMappingURL=types.d.ts.map
|
package/dist/types.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"AAIA,MAAM,
|
|
1
|
+
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"AAIA,MAAM,MAAM,UAAU,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;AAEjD,MAAM,MAAM,YAAY,GAAG,YAAY,GAAG,WAAW,GAAG,WAAW,GAAG,QAAQ,CAAC;AAC/E,MAAM,MAAM,cAAc,GAAG,SAAS,GAAG,aAAa,GAAG,QAAQ,GAAG,mBAAmB,GAAG,QAAQ,CAAC;AACnG,MAAM,MAAM,gBAAgB,GAAG,UAAU,GAAG,QAAQ,GAAG,SAAS,GAAG,QAAQ,CAAC;AAC5E,MAAM,MAAM,eAAe,GAAG,MAAM,GAAG,SAAS,GAAG,MAAM,GAAG,MAAM,CAAC;AACnE,MAAM,MAAM,kBAAkB,GAAG,OAAO,GAAG,SAAS,CAAC;AAErD,MAAM,WAAW,MAAM;IACrB,EAAE,EAAE,MAAM,CAAC;IACX,QAAQ,EAAE,MAAM,CAAC;IACjB,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,YAAY,CAAC;IACrB,MAAM,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACvB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,WAAW,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC5B,MAAM,CAAC,EAAE,MAAM,EAAE,CAAC;IAClB,KAAK,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACtB,eAAe,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAChC,eAAe,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAChC,gBAAgB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACjC,SAAS,CAAC,EAAE,UAAU,GAAG,IAAI,CAAC;IAC9B,SAAS,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC1B,SAAS,CAAC,EAAE,UAAU,EAAE,GAAG,IAAI,CAAC;IAChC,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,WAAW,OAAO;IACtB,EAAE,EAAE,MAAM,CAAC;IACX,QAAQ,EAAE,MAAM,CAAC;IACjB,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,EAAE,MAAM,CAAC;IACnB,WAAW,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC5B,SAAS,CAAC,EAAE,UAAU,GAAG,IAAI,CAAC;IAC9B,SAAS,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC1B,UAAU,EAAE,MAAM,CAAC;IACnB,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,WAAW,iBAAiB;IAChC,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,MAAM,CAAC;IACf,OAAO,EAAE,MAAM,CAAC;IAChB,MAAM,EAAE,MAAM,CAAC;IACf,QAAQ,EAAE,MAAM,CAAC;IACjB,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;CAC1B;AAED,MAAM,WAAW,eAAe;IAC9B,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;IACf,QAAQ,EAAE,MAAM,CAAC;CAClB;AAED,MAAM,WAAW,UAAU;IACzB,EAAE,EAAE,MAAM,CAAC;IACX,UAAU,EAAE,MAAM,CAAC;IACnB,UAAU,EAAE,MAAM,CAAC;IACnB,QAAQ,EAAE,MAAM,CAAC;IACjB,SAAS,EAAE,MAAM,CAAC;IAClB,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,aAAa,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC9B,KAAK,CAAC,EAAE,eAAe,GAAG,IAAI,CAAC;IAC/B,WAAW,CAAC,EAAE,OAAO,CAAC;IACtB,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,MAAM,EAAE,gBAAgB,CAAC;IACzB,OAAO,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACxB,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,WAAW,QAAQ;IACvB,EAAE,EAAE,MAAM,CAAC;IACX,UAAU,EAAE,MAAM,CAAC;IACnB,WAAW,EAAE,MAAM,CAAC;IACpB,cAAc,EAAE,MAAM,CAAC;IACvB,YAAY,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC7B,kBAAkB,EAAE,MAAM,CAAC;IAC3B,YAAY,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC7B,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACzB,MAAM,CAAC,EAAE,UAAU,GAAG,IAAI,CAAC;IAC3B,MAAM,CAAC,EAAE,gBAAgB,CAAC;IAC1B,kBAAkB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACnC,gBAAgB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACjC,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,WAAW,QAAQ;IACvB,EAAE,EAAE,MAAM,CAAC;IACX,QAAQ,EAAE,MAAM,CAAC;IACjB,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,cAAc,CAAC;IACvB,aAAa,EAAE,iBAAiB,CAAC;IACjC,WAAW,EAAE,eAAe,CAAC;IAC7B,SAAS,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC1B,SAAS,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC1B,WAAW,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC5B,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB,OAAO,CAAC,EAAE,UAAU,EAAE,CAAC;IACvB,KAAK,CAAC,EAAE,QAAQ,EAAE,CAAC;CACpB;AAED,MAAM,WAAW,YAAY;IAC3B,EAAE,EAAE,MAAM,CAAC;IACX,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACtB,MAAM,EAAE,kBAAkB,CAAC;IAC3B,SAAS,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC1B,OAAO,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACxB,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;CACnB;AAMD,MAAM,WAAW,iBAAiB,CAAC,CAAC;IAClC,KAAK,EAAE,CAAC,EAAE,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,CAAC;IACb,QAAQ,EAAE,MAAM,CAAC;CAClB;AAMD,MAAM,WAAW,SAAS;IACxB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,OAAO,CAAC,EAAE,MAAM,CAAC;CAClB;AAED,MAAM,MAAM,YAAY,GAAG,MAAM,GAAG,KAAK,GAAG,OAAO,GAAG,MAAM,CAAC;AAE7D,MAAM,WAAW,aAAa;IAC5B,MAAM,CAAC,EAAE,YAAY,CAAC;IACtB,KAAK,CAAC,EAAE,OAAO,CAAC;CACjB;AAED,MAAM,WAAW,gBAAgB;IAC/B,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,OAAO,CAAC,EAAE,OAAO,CAAC;CACnB;AAMD,MAAM,WAAW,mBAAmB;IAClC,QAAQ,EAAE,MAAM,CAAC;IACjB,IAAI,EAAE,MAAM,CAAC;IACb,KAAK,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACtB,WAAW,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC5B,MAAM,CAAC,EAAE,YAAY,CAAC;CACvB;AAED,MAAM,WAAW,mBAAmB;IAClC,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,KAAK,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACtB,WAAW,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC5B,MAAM,CAAC,EAAE,YAAY,CAAC;CACvB;AAED,MAAM,WAAW,oBAAoB;IACnC,QAAQ,EAAE,MAAM,CAAC;IACjB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,WAAW,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC5B,SAAS,CAAC,EAAE,UAAU,GAAG,IAAI,CAAC;IAC9B,SAAS,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC1B,SAAS,CAAC,EAAE,UAAU,EAAE,GAAG,IAAI,CAAC;CACjC;AAED,MAAM,WAAW,qBAAqB;IACpC,SAAS,EAAE,MAAM,CAAC;IAClB,IAAI,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CACtB;AAED,MAAM,WAAW,uBAAuB;IACtC,MAAM,CAAC,EAAE,gBAAgB,CAAC;IAC1B,OAAO,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACxB,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CAC1B;AAED,MAAM,WAAW,6BAA6B;IAC5C,OAAO,EAAE,KAAK,CAAC,uBAAuB,GAAG;QAAE,EAAE,EAAE,MAAM,CAAA;KAAE,CAAC,CAAC;CAC1D;AAMD,MAAM,WAAW,iBAAiB;IAChC,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,MAAM,CAAC,EAAE,YAAY,CAAC;CACvB;AAED,MAAM,WAAW,kBAAkB;IACjC,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,QAAQ,CAAC,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,WAAW,mBAAmB;IAClC,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,MAAM,CAAC,EAAE,cAAc,CAAC;CACzB;AAED,MAAM,WAAW,qBAAqB;IACpC,UAAU,EAAE,MAAM,CAAC;CACpB;AAED,MAAM,WAAW,uBAAuB;IACtC,MAAM,CAAC,EAAE,kBAAkB,CAAC;IAC5B,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB"}
|
package/dist/types.js
CHANGED
package/dist/types.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"types.js","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":";AAAA,+BAA+B;AAC/B,
|
|
1
|
+
{"version":3,"file":"types.js","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":";AAAA,+BAA+B;AAC/B,2BAA2B;AAC3B,+BAA+B"}
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "expert_eval_cli",
|
|
3
|
-
"version": "
|
|
4
|
-
"description": "AI-friendly CLI for ExpertEval
|
|
3
|
+
"version": "2.0.0",
|
|
4
|
+
"description": "AI-friendly CLI for ExpertEval OpenAPI — experts, versions, evaluation tasks, records and agent accounts",
|
|
5
5
|
"main": "dist/index.js",
|
|
6
6
|
"types": "dist/index.d.ts",
|
|
7
7
|
"bin": {
|
|
@@ -35,7 +35,8 @@
|
|
|
35
35
|
"node": ">=18.0.0"
|
|
36
36
|
},
|
|
37
37
|
"dependencies": {
|
|
38
|
-
"commander": "^12.1.0"
|
|
38
|
+
"commander": "^12.1.0",
|
|
39
|
+
"yaml": "^2.9.0"
|
|
39
40
|
},
|
|
40
41
|
"devDependencies": {
|
|
41
42
|
"@types/node": "^22.0.0",
|
package/skill/SKILL.md
CHANGED
|
@@ -3,8 +3,8 @@ name: expert-eval-cli
|
|
|
3
3
|
version: "1.0.1"
|
|
4
4
|
description: >
|
|
5
5
|
ExpertEval CLI 工具技能:帮助用户安装、更新 expert_eval_cli,完成认证,
|
|
6
|
-
并执行 experts、versions、eval-
|
|
7
|
-
当用户提到 ExpertEval
|
|
6
|
+
并执行 experts、versions、eval-tasks、eval-records、agent-accounts 操作。
|
|
7
|
+
当用户提到 ExpertEval、专家评估、评测任务、评审记录、版本管理、评测账号时触发。
|
|
8
8
|
---
|
|
9
9
|
|
|
10
10
|
# ExpertEval CLI 技能
|
|
@@ -110,19 +110,23 @@ expert_eval experts list | cat
|
|
|
110
110
|
| 操作 | 命令 |
|
|
111
111
|
|---|---|
|
|
112
112
|
| 列出专家 | `expert_eval experts list` |
|
|
113
|
-
| 创建专家 | `expert_eval experts create --expert-id exp-001 --name "AI安全专家"` |
|
|
114
|
-
| 更新专家 | `expert_eval experts update
|
|
115
|
-
|
|
|
113
|
+
| 创建专家 | `expert_eval experts create --expert-id exp-001 --name "AI安全专家" --owner 1847292357012580 --status developing` |
|
|
114
|
+
| 更新专家 | `expert_eval experts update exp-001 --name "新名称" --status published` |
|
|
115
|
+
| 查看专家卡/YAML | `expert_eval experts agent-card exp-001` / `expert_eval experts agent-yaml exp-001` |
|
|
116
|
+
| 删除专家 | `expert_eval experts delete <expert-id>` |
|
|
116
117
|
| 列出版本 | `expert_eval versions list --expert-id exp-001` |
|
|
117
|
-
| 创建版本 | `expert_eval versions create --expert-id exp-001 --
|
|
118
|
-
|
|
|
119
|
-
|
|
|
120
|
-
|
|
|
121
|
-
|
|
|
118
|
+
| 创建版本 | `expert_eval versions create --expert-id exp-001 --package-zip-file ./pkg.zip` |
|
|
119
|
+
| 创建评测任务 | `expert_eval eval-tasks create --version-id v-1 --name "v1 评测"` |
|
|
120
|
+
| 获取任务详情 | `expert_eval eval-tasks get <task-id>` |
|
|
121
|
+
| 获取任务记录 | `expert_eval eval-tasks records <task-id>` |
|
|
122
|
+
| 列出评审记录 | `expert_eval eval-records list --eval-task-id task-1` |
|
|
123
|
+
| 修改评审记录 | `expert_eval eval-records update <record-id> --status passed --comment "通过"` |
|
|
124
|
+
| 批量修改记录 | `expert_eval eval-records batch --records-file ./records.json` |
|
|
125
|
+
| 查询评测账号 | `expert_eval agent-accounts list --status ready` |
|
|
122
126
|
|
|
123
127
|
### 分页查询
|
|
124
128
|
|
|
125
|
-
|
|
129
|
+
专家、版本、评测任务 list 命令支持分页;评测记录按 `evalTaskId` 返回全量数组:
|
|
126
130
|
|
|
127
131
|
```bash
|
|
128
132
|
expert_eval experts list --page 2 --page-size 20
|