expert_eval_cli 1.4.0 → 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 -19
- package/dist/client.d.ts.map +1 -1
- package/dist/client.js +36 -67
- 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 +96 -174
- 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 -75
- 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
|
}
|
|
@@ -64,26 +72,44 @@ export interface EvalCase {
|
|
|
64
72
|
evalTaskId: string;
|
|
65
73
|
instruction: string;
|
|
66
74
|
expectedResult: string;
|
|
75
|
+
actualResult?: string | null;
|
|
67
76
|
evaluationCriteria: string;
|
|
68
77
|
artifactLink?: string | null;
|
|
78
|
+
taskLink?: string | null;
|
|
79
|
+
extras?: JsonObject | null;
|
|
80
|
+
status?: EvalRecordStatus;
|
|
69
81
|
executionStartTime?: string | null;
|
|
70
82
|
executionEndTime?: string | null;
|
|
71
83
|
createdAt: string;
|
|
72
84
|
updatedAt: string;
|
|
73
85
|
}
|
|
74
|
-
export interface EvalTaskPackage {
|
|
75
|
-
bucketId: string;
|
|
76
|
-
filePath: string;
|
|
77
|
-
}
|
|
78
86
|
export interface EvalTask {
|
|
79
87
|
id: string;
|
|
80
88
|
expertId: string;
|
|
81
89
|
versionId: string;
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
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;
|
|
87
113
|
createdAt: string;
|
|
88
114
|
updatedAt: string;
|
|
89
115
|
}
|
|
@@ -110,165 +136,61 @@ export interface ApiErrorResponse {
|
|
|
110
136
|
export interface CreateExpertPayload {
|
|
111
137
|
expertId: string;
|
|
112
138
|
name: string;
|
|
113
|
-
|
|
114
|
-
type?: string;
|
|
115
|
-
field?: string;
|
|
116
|
-
title?: string;
|
|
117
|
-
organization?: string;
|
|
118
|
-
membersCount?: number | null;
|
|
119
|
-
members?: string[];
|
|
120
|
-
tags?: string[];
|
|
139
|
+
owner?: string | null;
|
|
121
140
|
description?: string | null;
|
|
122
|
-
|
|
123
|
-
aiTags?: string[];
|
|
124
|
-
owner?: string[];
|
|
125
|
-
latestVersionTask?: string | null;
|
|
141
|
+
status?: ExpertStatus;
|
|
126
142
|
}
|
|
127
143
|
export interface UpdateExpertPayload {
|
|
128
|
-
|
|
129
|
-
|
|
130
|
-
avatar?: string | null;
|
|
131
|
-
type?: string;
|
|
132
|
-
field?: string;
|
|
133
|
-
title?: string;
|
|
134
|
-
organization?: string;
|
|
135
|
-
membersCount?: number | null;
|
|
136
|
-
members?: string[];
|
|
137
|
-
tags?: string[];
|
|
144
|
+
name?: string;
|
|
145
|
+
owner?: string | null;
|
|
138
146
|
description?: string | null;
|
|
139
|
-
|
|
140
|
-
aiTags?: string[];
|
|
141
|
-
owner?: string[];
|
|
142
|
-
latestVersionTask?: string | null;
|
|
147
|
+
status?: ExpertStatus;
|
|
143
148
|
}
|
|
144
149
|
export interface CreateVersionPayload {
|
|
145
|
-
hash: string;
|
|
146
|
-
diff?: string | null;
|
|
147
|
-
commitMessage?: string | null;
|
|
148
|
-
author?: string | null;
|
|
149
|
-
evaluationDate?: string | null;
|
|
150
|
-
summary?: string | null;
|
|
151
|
-
}
|
|
152
|
-
export interface UpdateVersionPayload {
|
|
153
|
-
hash: string;
|
|
154
|
-
diff?: string | null;
|
|
155
|
-
commitMessage?: string | null;
|
|
156
|
-
author?: string | null;
|
|
157
|
-
evaluationDate?: string | null;
|
|
158
|
-
summary?: string | null;
|
|
159
|
-
}
|
|
160
|
-
export interface CreateEvalTaskPayload {
|
|
161
150
|
expertId: string;
|
|
162
|
-
|
|
163
|
-
|
|
164
|
-
|
|
165
|
-
|
|
166
|
-
|
|
167
|
-
dcg?: number | null;
|
|
151
|
+
packageZip?: string;
|
|
152
|
+
packageName?: string | null;
|
|
153
|
+
agentJson?: JsonObject | null;
|
|
154
|
+
agentYaml?: string | null;
|
|
155
|
+
skillJson?: JsonObject[] | null;
|
|
168
156
|
}
|
|
169
|
-
export interface
|
|
170
|
-
expertId: string;
|
|
157
|
+
export interface CreateEvalTaskPayload {
|
|
171
158
|
versionId: string;
|
|
172
|
-
|
|
173
|
-
package?: EvalTaskPackage | null;
|
|
174
|
-
isPassed?: boolean;
|
|
175
|
-
bac?: number | null;
|
|
176
|
-
dcg?: number | null;
|
|
177
|
-
}
|
|
178
|
-
export interface CreateEvalItemPayload {
|
|
179
|
-
itemCode: string;
|
|
180
|
-
title: string;
|
|
181
|
-
category?: string;
|
|
182
|
-
description?: string | null;
|
|
183
|
-
maxScore?: number;
|
|
184
|
-
itemTypes?: EvalItemType[];
|
|
185
|
-
query?: string | null;
|
|
186
|
-
acceptanceCriteria?: string | null;
|
|
187
|
-
isVeto?: boolean;
|
|
188
|
-
}
|
|
189
|
-
export interface UpdateEvalItemPayload {
|
|
190
|
-
itemCode?: string;
|
|
191
|
-
title?: string;
|
|
192
|
-
category?: string;
|
|
193
|
-
description?: string | null;
|
|
194
|
-
maxScore?: number;
|
|
195
|
-
itemTypes?: EvalItemType[];
|
|
196
|
-
query?: string | null;
|
|
197
|
-
acceptanceCriteria?: string | null;
|
|
198
|
-
isVeto?: boolean;
|
|
199
|
-
}
|
|
200
|
-
export interface CreateEvalRecordPayload {
|
|
201
|
-
evalTaskId: string;
|
|
202
|
-
evalItemId: string;
|
|
203
|
-
query?: string | null;
|
|
204
|
-
result?: string | null;
|
|
205
|
-
isPassed: boolean;
|
|
206
|
-
dcg?: number | null;
|
|
207
|
-
thinkingProcess?: string | null;
|
|
208
|
-
expertItemTitle?: string | null;
|
|
209
|
-
executionStartTime?: string | null;
|
|
210
|
-
executionEndTime?: string | null;
|
|
159
|
+
name?: string | null;
|
|
211
160
|
}
|
|
212
161
|
export interface UpdateEvalRecordPayload {
|
|
213
|
-
|
|
214
|
-
|
|
215
|
-
|
|
216
|
-
result?: string | null;
|
|
217
|
-
isPassed?: boolean;
|
|
218
|
-
dcg?: number | null;
|
|
219
|
-
thinkingProcess?: string | null;
|
|
220
|
-
expertItemTitle?: string | null;
|
|
221
|
-
executionStartTime?: string | null;
|
|
222
|
-
executionEndTime?: string | null;
|
|
162
|
+
status?: EvalRecordStatus;
|
|
163
|
+
comment?: string | null;
|
|
164
|
+
evidence?: string | null;
|
|
223
165
|
}
|
|
224
|
-
export interface
|
|
225
|
-
|
|
226
|
-
|
|
227
|
-
|
|
228
|
-
evaluationCriteria: string;
|
|
229
|
-
artifactLink?: string | null;
|
|
230
|
-
executionStartTime?: string | null;
|
|
231
|
-
executionEndTime?: string | null;
|
|
166
|
+
export interface BatchUpdateEvalRecordsPayload {
|
|
167
|
+
records: Array<UpdateEvalRecordPayload & {
|
|
168
|
+
id: string;
|
|
169
|
+
}>;
|
|
232
170
|
}
|
|
233
171
|
export interface ListExpertsParams {
|
|
234
172
|
page?: number;
|
|
235
173
|
pageSize?: number;
|
|
236
174
|
keyword?: string;
|
|
175
|
+
status?: ExpertStatus;
|
|
237
176
|
}
|
|
238
177
|
export interface ListVersionsParams {
|
|
239
178
|
page?: number;
|
|
240
179
|
pageSize?: number;
|
|
180
|
+
expertId?: string;
|
|
241
181
|
}
|
|
242
182
|
export interface ListEvalTasksParams {
|
|
243
183
|
page?: number;
|
|
244
184
|
pageSize?: number;
|
|
245
185
|
expertId?: string;
|
|
246
186
|
versionId?: string;
|
|
247
|
-
|
|
248
|
-
export interface ListEvalItemsParams {
|
|
249
|
-
page?: number;
|
|
250
|
-
pageSize?: number;
|
|
251
|
-
category?: string;
|
|
252
|
-
itemTypes?: EvalItemType[];
|
|
187
|
+
status?: EvalTaskStatus;
|
|
253
188
|
}
|
|
254
189
|
export interface ListEvalRecordsParams {
|
|
255
|
-
|
|
256
|
-
pageSize?: number;
|
|
257
|
-
evalTaskId?: string;
|
|
258
|
-
evalItemId?: string;
|
|
259
|
-
}
|
|
260
|
-
export interface AgentAccount {
|
|
261
|
-
id: string;
|
|
262
|
-
agentId: string;
|
|
263
|
-
owner?: string | null;
|
|
264
|
-
status: 'ready' | 'running';
|
|
265
|
-
startTime?: string | null;
|
|
266
|
-
endTime?: string | null;
|
|
267
|
-
createdAt: string;
|
|
268
|
-
updatedAt: string;
|
|
190
|
+
evalTaskId: string;
|
|
269
191
|
}
|
|
270
192
|
export interface ListAgentAccountsParams {
|
|
271
|
-
status?:
|
|
193
|
+
status?: AgentAccountStatus;
|
|
272
194
|
owner?: string;
|
|
273
195
|
}
|
|
274
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
|
|
@@ -14,27 +14,32 @@ List experts (paginated).
|
|
|
14
14
|
Query params:
|
|
15
15
|
- `page` (int, default 1)
|
|
16
16
|
- `pageSize` (int, default 50)
|
|
17
|
-
- `keyword` (string, optional)
|
|
17
|
+
- `keyword` (string, optional; matches name/business ID/description)
|
|
18
|
+
- `status` (`developing` | `adjusting` | `published` | `paused`, optional)
|
|
18
19
|
|
|
19
20
|
Response: `{ items: Expert[], total, page, pageSize }`
|
|
20
21
|
|
|
21
22
|
### `POST /openapi/experts`
|
|
22
|
-
Create expert
|
|
23
|
+
Create an expert.
|
|
23
24
|
|
|
24
|
-
Body: `{ expertId, name,
|
|
25
|
+
Body: `{ expertId, name, owner?, description?, status? }`
|
|
25
26
|
|
|
26
|
-
### `
|
|
27
|
-
|
|
27
|
+
### `GET /openapi/experts/{expertId}`
|
|
28
|
+
Get expert by business ID.
|
|
28
29
|
|
|
29
|
-
|
|
30
|
+
### `PATCH /openapi/experts/{expertId}`
|
|
31
|
+
Partially update an expert.
|
|
30
32
|
|
|
31
|
-
|
|
32
|
-
Get expert by primary ID.
|
|
33
|
+
Body: `{ name?, owner?, description?, status? }`
|
|
33
34
|
|
|
34
|
-
### `DELETE /openapi/experts/{
|
|
35
|
-
Delete expert by
|
|
35
|
+
### `DELETE /openapi/experts/{expertId}`
|
|
36
|
+
Delete expert by business ID. Response: `{ id }`
|
|
36
37
|
|
|
37
|
-
|
|
38
|
+
### `GET /openapi/experts/{expertId}/agent-card`
|
|
39
|
+
Get raw `agent.json` object for the expert.
|
|
40
|
+
|
|
41
|
+
### `GET /openapi/experts/{expertId}/agent.yml`
|
|
42
|
+
Get raw YAML text for the expert. Response content type: `text/yaml`.
|
|
38
43
|
|
|
39
44
|
## Versions
|
|
40
45
|
|
|
@@ -44,80 +49,81 @@ List versions (paginated).
|
|
|
44
49
|
Query params:
|
|
45
50
|
- `page` (int, default 1)
|
|
46
51
|
- `pageSize` (int, default 50)
|
|
47
|
-
- `expertId` (string, optional
|
|
52
|
+
- `expertId` (string, optional)
|
|
48
53
|
|
|
49
54
|
### `POST /openapi/versions`
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
Body: `{ expertId, hash, commitMessage?, author?, versionDate?, isPassed, bac?, dcg? }`
|
|
55
|
+
Upload Base64 encoded ZIP content and create a version. The server unzips and parses `agent.json`/`agent.yaml` plus `skills/*/SKILL.md` frontmatter, and creates evaluation tasks/records automatically. If already parsed, callers may provide parsed fields and skip server-side parsing.
|
|
53
56
|
|
|
54
|
-
|
|
55
|
-
Update version (idempotent by `expertId` + `hash`).
|
|
56
|
-
|
|
57
|
-
Body: same shape as POST.
|
|
57
|
+
Body: `{ expertId, packageZip?, packageName?, agentJson?, agentYaml?, skillJson? }`
|
|
58
58
|
|
|
59
59
|
### `GET /openapi/versions/{id}`
|
|
60
60
|
Get version by primary ID.
|
|
61
61
|
|
|
62
62
|
### `DELETE /openapi/versions/{id}`
|
|
63
|
-
Delete version by primary ID.
|
|
64
|
-
|
|
65
|
-
Response: `{ id }`
|
|
63
|
+
Delete version by primary ID. Response: `{ id }`
|
|
66
64
|
|
|
67
|
-
## Eval
|
|
65
|
+
## Eval Tasks
|
|
68
66
|
|
|
69
|
-
### `GET /openapi/eval-
|
|
70
|
-
List
|
|
67
|
+
### `GET /openapi/eval-tasks`
|
|
68
|
+
List evaluation tasks (paginated).
|
|
71
69
|
|
|
72
70
|
Query params:
|
|
73
71
|
- `page` (int, default 1)
|
|
74
72
|
- `pageSize` (int, default 50)
|
|
73
|
+
- `expertId` (string, optional)
|
|
74
|
+
- `versionId` (string, optional)
|
|
75
|
+
- `status` (`pending` | `in_progress` | `failed` | `changes_requested` | `passed`, optional)
|
|
75
76
|
|
|
76
|
-
### `POST /openapi/eval-
|
|
77
|
-
Create
|
|
77
|
+
### `POST /openapi/eval-tasks`
|
|
78
|
+
Create an evaluation task for a version, generating all evaluation records and cases automatically.
|
|
78
79
|
|
|
79
|
-
Body: `{
|
|
80
|
+
Body: `{ versionId, name? }`
|
|
80
81
|
|
|
81
|
-
|
|
82
|
+
### `GET /openapi/eval-tasks/{id}`
|
|
83
|
+
Get task detail, including version raw content, all evaluation records and cases.
|
|
82
84
|
|
|
83
|
-
### `
|
|
84
|
-
|
|
85
|
+
### `DELETE /openapi/eval-tasks/{id}`
|
|
86
|
+
Delete an evaluation task. Response: `{ id }`
|
|
85
87
|
|
|
86
|
-
### `
|
|
87
|
-
|
|
88
|
+
### `GET /openapi/eval-tasks/{id}/records`
|
|
89
|
+
Get all records for an evaluation task, including the original standard content for each item.
|
|
88
90
|
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
### `DELETE /openapi/eval-items/{id}`
|
|
92
|
-
Delete eval item by primary ID.
|
|
93
|
-
|
|
94
|
-
Response: `{ id }`
|
|
91
|
+
### `GET /openapi/eval-tasks/{id}/agent-card`
|
|
92
|
+
Get the raw agent card for the version evaluated by this task.
|
|
95
93
|
|
|
96
94
|
## Eval Records
|
|
97
95
|
|
|
98
96
|
### `GET /openapi/eval-records`
|
|
99
|
-
List
|
|
97
|
+
List evaluation records by task.
|
|
100
98
|
|
|
101
99
|
Query params:
|
|
102
|
-
- `
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
100
|
+
- `evalTaskId` (string, required)
|
|
101
|
+
|
|
102
|
+
Response: `EvalRecord[]`
|
|
103
|
+
|
|
104
|
+
### `POST /openapi/eval-records/batch`
|
|
105
|
+
Batch update evaluation record status, comment and evidence.
|
|
106
106
|
|
|
107
|
-
|
|
108
|
-
Create eval record.
|
|
107
|
+
Body: `{ records: [{ id, status?, comment?, evidence? }] }`
|
|
109
108
|
|
|
110
|
-
|
|
109
|
+
`status`: `untested` | `passed` | `warning` | `failed`
|
|
111
110
|
|
|
112
|
-
### `
|
|
113
|
-
|
|
111
|
+
### `PATCH /openapi/eval-records/{id}`
|
|
112
|
+
Update one evaluation record.
|
|
114
113
|
|
|
115
|
-
|
|
116
|
-
Update eval record by primary ID.
|
|
114
|
+
Body: `{ status?, comment?, evidence? }`
|
|
117
115
|
|
|
118
|
-
|
|
116
|
+
## Agent Accounts
|
|
117
|
+
|
|
118
|
+
### `GET /openapi/agent/account`
|
|
119
|
+
List evaluation accounts.
|
|
120
|
+
|
|
121
|
+
Query params:
|
|
122
|
+
- `status` (`ready` | `running`, optional; default `ready`)
|
|
123
|
+
- `owner` (string, optional)
|
|
119
124
|
|
|
120
|
-
### `
|
|
121
|
-
|
|
125
|
+
### `POST /openapi/agent/account/{agentId}/start`
|
|
126
|
+
Mark an account as running.
|
|
122
127
|
|
|
123
|
-
|
|
128
|
+
### `POST /openapi/agent/account/{agentId}/done`
|
|
129
|
+
Mark an account as ready/done.
|