dsh-eval-pack 0.0.0-stage → 0.1.0-alpha.3
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/LICENSE +202 -0
- package/NOTICE +5 -0
- package/README-es.md +111 -0
- package/README-hi.md +111 -0
- package/README-pt.md +111 -0
- package/README-zh.md +111 -0
- package/README.md +110 -2
- package/cordis.patch.yml +3 -0
- package/docs/assets/dsh-eval-pack-flow.svg +11 -0
- package/lib/core/harness.d.ts +11 -0
- package/lib/core/harness.js +28 -0
- package/lib/plugin/index.d.ts +4 -0
- package/lib/plugin/index.js +7 -0
- package/lib/plugin/tools.d.ts +1 -0
- package/lib/plugin/tools.js +20 -0
- package/package.json +73 -4
package/LICENSE
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
1
|
+
|
|
2
|
+
Apache License
|
|
3
|
+
Version 2.0, January 2004
|
|
4
|
+
http://www.apache.org/licenses/
|
|
5
|
+
|
|
6
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
7
|
+
|
|
8
|
+
1. Definitions.
|
|
9
|
+
|
|
10
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
11
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
12
|
+
|
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
14
|
+
the copyright owner that is granting the License.
|
|
15
|
+
|
|
16
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
17
|
+
other entities that control, are controlled by, or are under common
|
|
18
|
+
control with that entity. For the purposes of this definition,
|
|
19
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
20
|
+
direction or management of such entity, whether by contract or
|
|
21
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
22
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
23
|
+
|
|
24
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
25
|
+
exercising permissions granted by this License.
|
|
26
|
+
|
|
27
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
28
|
+
including but not limited to software source code, documentation
|
|
29
|
+
source, and configuration files.
|
|
30
|
+
|
|
31
|
+
"Object" form shall mean any form resulting from mechanical
|
|
32
|
+
transformation or translation of a Source form, including but
|
|
33
|
+
not limited to compiled object code, generated documentation,
|
|
34
|
+
and conversions to other media types.
|
|
35
|
+
|
|
36
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
37
|
+
Object form, made available under the License, as indicated by a
|
|
38
|
+
copyright notice that is included in or attached to the work
|
|
39
|
+
(an example is provided in the Appendix below).
|
|
40
|
+
|
|
41
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
42
|
+
form, that is based on (or derived from) the Work and for which the
|
|
43
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
44
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
45
|
+
of this License, Derivative Works shall not include works that remain
|
|
46
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
47
|
+
the Work and Derivative Works thereof.
|
|
48
|
+
|
|
49
|
+
"Contribution" shall mean any work of authorship, including
|
|
50
|
+
the original version of the Work and any modifications or additions
|
|
51
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
52
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
53
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
54
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
55
|
+
means any form of electronic, verbal, or written communication sent
|
|
56
|
+
to the Licensor or its representatives, including but not limited to
|
|
57
|
+
communication on electronic mailing lists, source code control systems,
|
|
58
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
59
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
60
|
+
excluding communication that is conspicuously marked or otherwise
|
|
61
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
62
|
+
|
|
63
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
64
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
65
|
+
subsequently incorporated within the Work.
|
|
66
|
+
|
|
67
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
68
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
69
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
70
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
71
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
72
|
+
Work and such Derivative Works in Source or Object form.
|
|
73
|
+
|
|
74
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
75
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
76
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
77
|
+
(except as stated in this section) patent license to make, have made,
|
|
78
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
79
|
+
where such license applies only to those patent claims licensable
|
|
80
|
+
by such Contributor that are necessarily infringed by their
|
|
81
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
82
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
83
|
+
institute patent litigation against any entity (including a
|
|
84
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
85
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
86
|
+
or contributory patent infringement, then any patent licenses
|
|
87
|
+
granted to You under this License for that Work shall terminate
|
|
88
|
+
as of the date such litigation is filed.
|
|
89
|
+
|
|
90
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
91
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
92
|
+
modifications, and in Source or Object form, provided that You
|
|
93
|
+
meet the following conditions:
|
|
94
|
+
|
|
95
|
+
(a) You must give any other recipients of the Work or
|
|
96
|
+
Derivative Works a copy of this License; and
|
|
97
|
+
|
|
98
|
+
(b) You must cause any modified files to carry prominent notices
|
|
99
|
+
stating that You changed the files; and
|
|
100
|
+
|
|
101
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
102
|
+
that You distribute, all copyright, patent, trademark, and
|
|
103
|
+
attribution notices from the Source form of the Work,
|
|
104
|
+
excluding those notices that do not pertain to any part of
|
|
105
|
+
the Derivative Works; and
|
|
106
|
+
|
|
107
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
108
|
+
distribution, then any Derivative Works that You distribute must
|
|
109
|
+
include a readable copy of the attribution notices contained
|
|
110
|
+
within such NOTICE file, excluding those notices that do not
|
|
111
|
+
pertain to any part of the Derivative Works, in at least one
|
|
112
|
+
of the following places: within a NOTICE text file distributed
|
|
113
|
+
as part of the Derivative Works; within the Source form or
|
|
114
|
+
documentation, if provided along with the Derivative Works; or,
|
|
115
|
+
within a display generated by the Derivative Works, if and
|
|
116
|
+
wherever such third-party notices normally appear. The contents
|
|
117
|
+
of the NOTICE file are for informational purposes only and
|
|
118
|
+
do not modify the License. You may add Your own attribution
|
|
119
|
+
notices within Derivative Works that You distribute, alongside
|
|
120
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
121
|
+
that such additional attribution notices cannot be construed
|
|
122
|
+
as modifying the License.
|
|
123
|
+
|
|
124
|
+
You may add Your own copyright statement to Your modifications and
|
|
125
|
+
may provide additional or different license terms and conditions
|
|
126
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
127
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
128
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
129
|
+
the conditions stated in this License.
|
|
130
|
+
|
|
131
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
132
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
133
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
134
|
+
this License, without any additional terms or conditions.
|
|
135
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
136
|
+
the terms of any separate license agreement you may have executed
|
|
137
|
+
with Licensor regarding such Contributions.
|
|
138
|
+
|
|
139
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
140
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
141
|
+
except as required for reasonable and customary use in describing the
|
|
142
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
143
|
+
|
|
144
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
145
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
146
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
147
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
148
|
+
implied, including, without limitation, any warranties or conditions
|
|
149
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
150
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
151
|
+
appropriateness of using or redistributing the Work and assume any
|
|
152
|
+
risks associated with Your exercise of permissions under this License.
|
|
153
|
+
|
|
154
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
155
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
156
|
+
unless required by applicable law (such as deliberate and grossly
|
|
157
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
158
|
+
liable to You for damages, including any direct, indirect, special,
|
|
159
|
+
incidental, or consequential damages of any character arising as a
|
|
160
|
+
result of this License or out of the use or inability to use the
|
|
161
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
162
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
163
|
+
other commercial damages or losses), even if such Contributor
|
|
164
|
+
has been advised of the possibility of such damages.
|
|
165
|
+
|
|
166
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
167
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
168
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
169
|
+
or other liability obligations and/or rights consistent with this
|
|
170
|
+
License. However, in accepting such obligations, You may act only
|
|
171
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
172
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
173
|
+
defend, and hold each Contributor harmless for any liability
|
|
174
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
175
|
+
of your accepting any such warranty or additional liability.
|
|
176
|
+
|
|
177
|
+
END OF TERMS AND CONDITIONS
|
|
178
|
+
|
|
179
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
180
|
+
|
|
181
|
+
To apply the Apache License to your work, attach the following
|
|
182
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
183
|
+
replaced with your own identifying information. (Don't include
|
|
184
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
185
|
+
comment syntax for the file format. We also recommend that a
|
|
186
|
+
file or class name and description of purpose be included on the
|
|
187
|
+
same "printed page" as the copyright notice for easier
|
|
188
|
+
identification within third-party archives.
|
|
189
|
+
|
|
190
|
+
Copyright [yyyy] [name of copyright owner]
|
|
191
|
+
|
|
192
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
193
|
+
you may not use this file except in compliance with the License.
|
|
194
|
+
You may obtain a copy of the License at
|
|
195
|
+
|
|
196
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
197
|
+
|
|
198
|
+
Unless required by applicable law or agreed to in writing, software
|
|
199
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
200
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
201
|
+
See the License for the specific language governing permissions and
|
|
202
|
+
limitations under the License.
|
package/NOTICE
ADDED
package/README-es.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
1
|
+
<div align="center">
|
|
2
|
+
|
|
3
|
+
# dsh-eval-pack
|
|
4
|
+
|
|
5
|
+
[](https://www.npmjs.com/package/dsh-eval-pack)
|
|
6
|
+
[](https://github.com/PerryLink/dsh-eval-pack/actions)
|
|
7
|
+
[](LICENSE)
|
|
8
|
+
[](https://github.com/topics/dsh-plugin)
|
|
9
|
+
[](https://perrylink.github.io/dsh-plugins/)
|
|
10
|
+
|
|
11
|
+
**Lint de eval-pack público/sintético y calificador JSON determinista; no es un benchmark validado.**
|
|
12
|
+
|
|
13
|
+
> **Estado: alpha / synthetic público / parcial / no contabilizado / no GA.** Sin evidencia de clientes, datos de clientes ni promesa de producción.
|
|
14
|
+
|
|
15
|
+
[English](README.md) · [简体中文](README-zh.md) · [Español](README-es.md) · [Português](README-pt.md) · [हिन्दी](README-hi.md)
|
|
16
|
+
|
|
17
|
+
```sh
|
|
18
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
</div>
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
|
|
25
|
+
*Flujo: entrada local → plugin → salida local. No requiere llamada a un modelo.*
|
|
26
|
+
|
|
27
|
+
## Instalación
|
|
28
|
+
|
|
29
|
+
Instalar y verificar:
|
|
30
|
+
|
|
31
|
+
```sh
|
|
32
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
33
|
+
dsh --profile <profile> --dump-config | grep dsh-eval-pack
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
Desinstalar:
|
|
37
|
+
|
|
38
|
+
```sh
|
|
39
|
+
dsh plugin --profile <profile> remove dsh-eval-pack
|
|
40
|
+
```
|
|
41
|
+
|
|
42
|
+
## Qué hace
|
|
43
|
+
|
|
44
|
+
Lint de eval-pack público/sintético y calificador JSON determinista; no es un benchmark validado. Se ejecuta localmente en DeepSeek Harness. La tabla siguiente es la superficie exacta de herramientas; los ejemplos usan la interfaz real.
|
|
45
|
+
|
|
46
|
+
La entrada y la salida permanecen locales; no se sube nada.
|
|
47
|
+
|
|
48
|
+
## Herramientas
|
|
49
|
+
|
|
50
|
+
Los nombres y descripciones de herramientas se mantienen en inglés para coincidir con la salida runtime.
|
|
51
|
+
|
|
52
|
+
| Herramienta | Propósito (en inglés) | Riesgo |
|
|
53
|
+
|---|---|---|
|
|
54
|
+
| `eval.pack_lint` | Validate eval-pack name/version and unique task ids | R0 |
|
|
55
|
+
| `eval.grade` | Deterministic JSON equality grade | R0 |
|
|
56
|
+
|
|
57
|
+
## Inicio rápido
|
|
58
|
+
|
|
59
|
+
```sh
|
|
60
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
61
|
+
dsh --profile <profile> --dump-config | grep dsh-eval-pack
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
## Límites
|
|
65
|
+
|
|
66
|
+
- Solo público/sintético; sin datos ni evidencia de clientes.
|
|
67
|
+
- Alpha/parcial, no contabilizado, sin GA ni promesa de producción.
|
|
68
|
+
- Sin modelo ni red salvo que una herramienta lo indique.
|
|
69
|
+
- Los límites exactos están en la tabla y en `ACCEPTANCE.csv`.
|
|
70
|
+
|
|
71
|
+
## Muestra pública
|
|
72
|
+
|
|
73
|
+
Las fixtures públicas/sintéticas están en `test/fixtures/`; `ACCEPTANCE.csv` registra las comprobaciones con `counted=false`.
|
|
74
|
+
|
|
75
|
+
## Desarrollo
|
|
76
|
+
|
|
77
|
+
```sh
|
|
78
|
+
pnpm install --frozen-lockfile
|
|
79
|
+
pnpm build && pnpm lint && pnpm typecheck && pnpm test
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
## Familia
|
|
83
|
+
|
|
84
|
+
<details>
|
|
85
|
+
<summary>Familia de plugins DSH (15 paquetes + 2 suites)</summary>
|
|
86
|
+
|
|
87
|
+
| Package | npm |
|
|
88
|
+
|---|---|
|
|
89
|
+
| **[dsh-einvoice](https://github.com/PerryLink/dsh-einvoice)** | [npm](https://www.npmjs.com/package/dsh-einvoice) |
|
|
90
|
+
| **[dsh-docx-redline](https://github.com/PerryLink/dsh-docx-redline)** | [npm](https://www.npmjs.com/package/dsh-docx-redline) |
|
|
91
|
+
| **[dsh-policy-ledger](https://github.com/PerryLink/dsh-policy-ledger)** | [npm](https://www.npmjs.com/package/dsh-policy-ledger) |
|
|
92
|
+
| **[dsh-ghg](https://github.com/PerryLink/dsh-ghg)** | [npm](https://www.npmjs.com/package/dsh-ghg) |
|
|
93
|
+
| **[dsh-bankrec](https://github.com/PerryLink/dsh-bankrec)** | [npm](https://www.npmjs.com/package/dsh-bankrec) |
|
|
94
|
+
| **[dsh-ap-three-way](https://github.com/PerryLink/dsh-ap-three-way)** | [npm](https://www.npmjs.com/package/dsh-ap-three-way) |
|
|
95
|
+
| **[dsh-ifc-qto](https://github.com/PerryLink/dsh-ifc-qto)** | [npm](https://www.npmjs.com/package/dsh-ifc-qto) |
|
|
96
|
+
| **[dsh-qms-capa](https://github.com/PerryLink/dsh-qms-capa)** | [npm](https://www.npmjs.com/package/dsh-qms-capa) |
|
|
97
|
+
| **[dsh-legal-intake](https://github.com/PerryLink/dsh-legal-intake)** | [npm](https://www.npmjs.com/package/dsh-legal-intake) |
|
|
98
|
+
| **[dsh-legal-clause](https://github.com/PerryLink/dsh-legal-clause)** | [npm](https://www.npmjs.com/package/dsh-legal-clause) |
|
|
99
|
+
| **[dsh-freight-audit](https://github.com/PerryLink/dsh-freight-audit)** | [npm](https://www.npmjs.com/package/dsh-freight-audit) |
|
|
100
|
+
| **[dsh-hs-candidate](https://github.com/PerryLink/dsh-hs-candidate)** | [npm](https://www.npmjs.com/package/dsh-hs-candidate) |
|
|
101
|
+
| **[dsh-travel-recon](https://github.com/PerryLink/dsh-travel-recon)** | [npm](https://www.npmjs.com/package/dsh-travel-recon) |
|
|
102
|
+
| **[dsh-pim-lint](https://github.com/PerryLink/dsh-pim-lint)** | [npm](https://www.npmjs.com/package/dsh-pim-lint) |
|
|
103
|
+
| **[dsh-eval-pack](https://github.com/PerryLink/dsh-eval-pack)** | [npm](https://www.npmjs.com/package/dsh-eval-pack) |
|
|
104
|
+
| **[dsh-finops-suite](https://github.com/PerryLink/dsh-finops-suite)** | [npm](https://www.npmjs.com/package/dsh-finops-suite) |
|
|
105
|
+
| **[dsh-contract-suite](https://github.com/PerryLink/dsh-contract-suite)** | [npm](https://www.npmjs.com/package/dsh-contract-suite) |
|
|
106
|
+
|
|
107
|
+
</details>
|
|
108
|
+
|
|
109
|
+
## Licencia
|
|
110
|
+
|
|
111
|
+
Apache-2.0. See `LICENSE`, `NOTICE`, `THIRD-PARTY-NOTICES`.
|
package/README-hi.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
1
|
+
<div align="center">
|
|
2
|
+
|
|
3
|
+
# dsh-eval-pack
|
|
4
|
+
|
|
5
|
+
[](https://www.npmjs.com/package/dsh-eval-pack)
|
|
6
|
+
[](https://github.com/PerryLink/dsh-eval-pack/actions)
|
|
7
|
+
[](LICENSE)
|
|
8
|
+
[](https://github.com/topics/dsh-plugin)
|
|
9
|
+
[](https://perrylink.github.io/dsh-plugins/)
|
|
10
|
+
|
|
11
|
+
**सार्वजनिक/सिंथेटिक eval-pack lint और नियतात्मक JSON ग्रेडर; मान्य बेंचमार्क नहीं।**
|
|
12
|
+
|
|
13
|
+
> **स्थिति: alpha / सार्वजनिक-सिंथेटिक / आंशिक / गिना नहीं गया / GA नहीं।** ग्राहक साक्ष्य, ग्राहक डेटा या उत्पादन-तैयारी का दावा नहीं।
|
|
14
|
+
|
|
15
|
+
[English](README.md) · [简体中文](README-zh.md) · [Español](README-es.md) · [Português](README-pt.md) · [हिन्दी](README-hi.md)
|
|
16
|
+
|
|
17
|
+
```sh
|
|
18
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
</div>
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
|
|
25
|
+
*वर्कफ़्लो: स्थानीय इनपुट → प्लगइन → स्थानीय आउटपुट। मॉडल कॉल आवश्यक नहीं।*
|
|
26
|
+
|
|
27
|
+
## इंस्टॉल
|
|
28
|
+
|
|
29
|
+
इंस्टॉल और सत्यापन:
|
|
30
|
+
|
|
31
|
+
```sh
|
|
32
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
33
|
+
dsh --profile <profile> --dump-config | grep dsh-eval-pack
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
अनइंस्टॉल:
|
|
37
|
+
|
|
38
|
+
```sh
|
|
39
|
+
dsh plugin --profile <profile> remove dsh-eval-pack
|
|
40
|
+
```
|
|
41
|
+
|
|
42
|
+
## यह क्या करता है
|
|
43
|
+
|
|
44
|
+
सार्वजनिक/सिंथेटिक eval-pack lint और नियतात्मक JSON ग्रेडर; मान्य बेंचमार्क नहीं। DeepSeek Harness पर स्थानीय रूप से चलता है। नीचे दी गई तालिका ही सटीक टूल सतह है; उदाहरण वास्तविक कमांड का उपयोग करते हैं।
|
|
45
|
+
|
|
46
|
+
इनपुट और आउटपुट स्थानीय रहते हैं; कुछ अपलोड नहीं होता।
|
|
47
|
+
|
|
48
|
+
## टूल्स
|
|
49
|
+
|
|
50
|
+
टूल नाम और विवरण runtime आउटपुट से मेल खाने के लिए अंग्रेज़ी में रखे गए हैं।
|
|
51
|
+
|
|
52
|
+
| टूल | उद्देश्य (अंग्रेज़ी) | जोखिम |
|
|
53
|
+
|---|---|---|
|
|
54
|
+
| `eval.pack_lint` | Validate eval-pack name/version and unique task ids | R0 |
|
|
55
|
+
| `eval.grade` | Deterministic JSON equality grade | R0 |
|
|
56
|
+
|
|
57
|
+
## त्वरित शुरुआत
|
|
58
|
+
|
|
59
|
+
```sh
|
|
60
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
61
|
+
dsh --profile <profile> --dump-config | grep dsh-eval-pack
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
## सीमाएँ
|
|
65
|
+
|
|
66
|
+
- केवल सार्वजनिक/सिंथेटिक; ग्राहक डेटा या साक्ष्य नहीं।
|
|
67
|
+
- alpha/आंशिक, गिना नहीं गया, GA या उत्पादन-तैयारी का दावा नहीं।
|
|
68
|
+
- जब तक टूल स्पष्ट न कहे, मॉडल या नेटवर्क कॉल नहीं।
|
|
69
|
+
- सटीक सीमाएँ तालिका और `ACCEPTANCE.csv` में हैं।
|
|
70
|
+
|
|
71
|
+
## सार्वजनिक नमूना
|
|
72
|
+
|
|
73
|
+
सार्वजनिक/सिंथेटिक fixtures `test/fixtures/` में हैं; `ACCEPTANCE.csv` सार्वजनिक जाँचों को `counted=false` के साथ दर्ज करता है।
|
|
74
|
+
|
|
75
|
+
## विकास
|
|
76
|
+
|
|
77
|
+
```sh
|
|
78
|
+
pnpm install --frozen-lockfile
|
|
79
|
+
pnpm build && pnpm lint && pnpm typecheck && pnpm test
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
## परिवार
|
|
83
|
+
|
|
84
|
+
<details>
|
|
85
|
+
<summary>DSH डोमेन प्लगइन परिवार (15 पैकेज + 2 suites)</summary>
|
|
86
|
+
|
|
87
|
+
| Package | npm |
|
|
88
|
+
|---|---|
|
|
89
|
+
| **[dsh-einvoice](https://github.com/PerryLink/dsh-einvoice)** | [npm](https://www.npmjs.com/package/dsh-einvoice) |
|
|
90
|
+
| **[dsh-docx-redline](https://github.com/PerryLink/dsh-docx-redline)** | [npm](https://www.npmjs.com/package/dsh-docx-redline) |
|
|
91
|
+
| **[dsh-policy-ledger](https://github.com/PerryLink/dsh-policy-ledger)** | [npm](https://www.npmjs.com/package/dsh-policy-ledger) |
|
|
92
|
+
| **[dsh-ghg](https://github.com/PerryLink/dsh-ghg)** | [npm](https://www.npmjs.com/package/dsh-ghg) |
|
|
93
|
+
| **[dsh-bankrec](https://github.com/PerryLink/dsh-bankrec)** | [npm](https://www.npmjs.com/package/dsh-bankrec) |
|
|
94
|
+
| **[dsh-ap-three-way](https://github.com/PerryLink/dsh-ap-three-way)** | [npm](https://www.npmjs.com/package/dsh-ap-three-way) |
|
|
95
|
+
| **[dsh-ifc-qto](https://github.com/PerryLink/dsh-ifc-qto)** | [npm](https://www.npmjs.com/package/dsh-ifc-qto) |
|
|
96
|
+
| **[dsh-qms-capa](https://github.com/PerryLink/dsh-qms-capa)** | [npm](https://www.npmjs.com/package/dsh-qms-capa) |
|
|
97
|
+
| **[dsh-legal-intake](https://github.com/PerryLink/dsh-legal-intake)** | [npm](https://www.npmjs.com/package/dsh-legal-intake) |
|
|
98
|
+
| **[dsh-legal-clause](https://github.com/PerryLink/dsh-legal-clause)** | [npm](https://www.npmjs.com/package/dsh-legal-clause) |
|
|
99
|
+
| **[dsh-freight-audit](https://github.com/PerryLink/dsh-freight-audit)** | [npm](https://www.npmjs.com/package/dsh-freight-audit) |
|
|
100
|
+
| **[dsh-hs-candidate](https://github.com/PerryLink/dsh-hs-candidate)** | [npm](https://www.npmjs.com/package/dsh-hs-candidate) |
|
|
101
|
+
| **[dsh-travel-recon](https://github.com/PerryLink/dsh-travel-recon)** | [npm](https://www.npmjs.com/package/dsh-travel-recon) |
|
|
102
|
+
| **[dsh-pim-lint](https://github.com/PerryLink/dsh-pim-lint)** | [npm](https://www.npmjs.com/package/dsh-pim-lint) |
|
|
103
|
+
| **[dsh-eval-pack](https://github.com/PerryLink/dsh-eval-pack)** | [npm](https://www.npmjs.com/package/dsh-eval-pack) |
|
|
104
|
+
| **[dsh-finops-suite](https://github.com/PerryLink/dsh-finops-suite)** | [npm](https://www.npmjs.com/package/dsh-finops-suite) |
|
|
105
|
+
| **[dsh-contract-suite](https://github.com/PerryLink/dsh-contract-suite)** | [npm](https://www.npmjs.com/package/dsh-contract-suite) |
|
|
106
|
+
|
|
107
|
+
</details>
|
|
108
|
+
|
|
109
|
+
## लाइसेंस
|
|
110
|
+
|
|
111
|
+
Apache-2.0. See `LICENSE`, `NOTICE`, `THIRD-PARTY-NOTICES`.
|
package/README-pt.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
1
|
+
<div align="center">
|
|
2
|
+
|
|
3
|
+
# dsh-eval-pack
|
|
4
|
+
|
|
5
|
+
[](https://www.npmjs.com/package/dsh-eval-pack)
|
|
6
|
+
[](https://github.com/PerryLink/dsh-eval-pack/actions)
|
|
7
|
+
[](LICENSE)
|
|
8
|
+
[](https://github.com/topics/dsh-plugin)
|
|
9
|
+
[](https://perrylink.github.io/dsh-plugins/)
|
|
10
|
+
|
|
11
|
+
**Lint de eval-pack público/sintético e corretor JSON determinístico; não é um benchmark validado.**
|
|
12
|
+
|
|
13
|
+
> **Status: alpha / sintético público / parcial / não contabilizado / não GA.** Sem evidência de clientes, dados de clientes ou promessa de produção.
|
|
14
|
+
|
|
15
|
+
[English](README.md) · [简体中文](README-zh.md) · [Español](README-es.md) · [Português](README-pt.md) · [हिन्दी](README-hi.md)
|
|
16
|
+
|
|
17
|
+
```sh
|
|
18
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
</div>
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
|
|
25
|
+
*Fluxo: entrada local → plugin → saída local. Não exige chamada a modelo.*
|
|
26
|
+
|
|
27
|
+
## Instalação
|
|
28
|
+
|
|
29
|
+
Instalar e verificar:
|
|
30
|
+
|
|
31
|
+
```sh
|
|
32
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
33
|
+
dsh --profile <profile> --dump-config | grep dsh-eval-pack
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
Desinstalar:
|
|
37
|
+
|
|
38
|
+
```sh
|
|
39
|
+
dsh plugin --profile <profile> remove dsh-eval-pack
|
|
40
|
+
```
|
|
41
|
+
|
|
42
|
+
## O que faz
|
|
43
|
+
|
|
44
|
+
Lint de eval-pack público/sintético e corretor JSON determinístico; não é um benchmark validado. Executa localmente no DeepSeek Harness. A tabela abaixo é a superfície exata de ferramentas; os exemplos usam a interface real.
|
|
45
|
+
|
|
46
|
+
Entrada e saída permanecem locais; nada é enviado.
|
|
47
|
+
|
|
48
|
+
## Ferramentas
|
|
49
|
+
|
|
50
|
+
Nomes e descrições de ferramentas ficam em inglês para corresponder à saída runtime.
|
|
51
|
+
|
|
52
|
+
| Ferramenta | Finalidade (em inglês) | Risco |
|
|
53
|
+
|---|---|---|
|
|
54
|
+
| `eval.pack_lint` | Validate eval-pack name/version and unique task ids | R0 |
|
|
55
|
+
| `eval.grade` | Deterministic JSON equality grade | R0 |
|
|
56
|
+
|
|
57
|
+
## Início rápido
|
|
58
|
+
|
|
59
|
+
```sh
|
|
60
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
61
|
+
dsh --profile <profile> --dump-config | grep dsh-eval-pack
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
## Limites
|
|
65
|
+
|
|
66
|
+
- Apenas público/sintético; sem dados ou evidência de clientes.
|
|
67
|
+
- Alpha/parcial, não contabilizado, sem GA ou promessa de produção.
|
|
68
|
+
- Sem modelo ou rede, a menos que uma ferramenta indique.
|
|
69
|
+
- Os limites exatos estão na tabela e em `ACCEPTANCE.csv`.
|
|
70
|
+
|
|
71
|
+
## Amostra pública
|
|
72
|
+
|
|
73
|
+
As fixtures públicas/sintéticas ficam em `test/fixtures/`; `ACCEPTANCE.csv` registra as verificações com `counted=false`.
|
|
74
|
+
|
|
75
|
+
## Desenvolvimento
|
|
76
|
+
|
|
77
|
+
```sh
|
|
78
|
+
pnpm install --frozen-lockfile
|
|
79
|
+
pnpm build && pnpm lint && pnpm typecheck && pnpm test
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
## Família
|
|
83
|
+
|
|
84
|
+
<details>
|
|
85
|
+
<summary>Família de plugins DSH (15 pacotes + 2 suites)</summary>
|
|
86
|
+
|
|
87
|
+
| Package | npm |
|
|
88
|
+
|---|---|
|
|
89
|
+
| **[dsh-einvoice](https://github.com/PerryLink/dsh-einvoice)** | [npm](https://www.npmjs.com/package/dsh-einvoice) |
|
|
90
|
+
| **[dsh-docx-redline](https://github.com/PerryLink/dsh-docx-redline)** | [npm](https://www.npmjs.com/package/dsh-docx-redline) |
|
|
91
|
+
| **[dsh-policy-ledger](https://github.com/PerryLink/dsh-policy-ledger)** | [npm](https://www.npmjs.com/package/dsh-policy-ledger) |
|
|
92
|
+
| **[dsh-ghg](https://github.com/PerryLink/dsh-ghg)** | [npm](https://www.npmjs.com/package/dsh-ghg) |
|
|
93
|
+
| **[dsh-bankrec](https://github.com/PerryLink/dsh-bankrec)** | [npm](https://www.npmjs.com/package/dsh-bankrec) |
|
|
94
|
+
| **[dsh-ap-three-way](https://github.com/PerryLink/dsh-ap-three-way)** | [npm](https://www.npmjs.com/package/dsh-ap-three-way) |
|
|
95
|
+
| **[dsh-ifc-qto](https://github.com/PerryLink/dsh-ifc-qto)** | [npm](https://www.npmjs.com/package/dsh-ifc-qto) |
|
|
96
|
+
| **[dsh-qms-capa](https://github.com/PerryLink/dsh-qms-capa)** | [npm](https://www.npmjs.com/package/dsh-qms-capa) |
|
|
97
|
+
| **[dsh-legal-intake](https://github.com/PerryLink/dsh-legal-intake)** | [npm](https://www.npmjs.com/package/dsh-legal-intake) |
|
|
98
|
+
| **[dsh-legal-clause](https://github.com/PerryLink/dsh-legal-clause)** | [npm](https://www.npmjs.com/package/dsh-legal-clause) |
|
|
99
|
+
| **[dsh-freight-audit](https://github.com/PerryLink/dsh-freight-audit)** | [npm](https://www.npmjs.com/package/dsh-freight-audit) |
|
|
100
|
+
| **[dsh-hs-candidate](https://github.com/PerryLink/dsh-hs-candidate)** | [npm](https://www.npmjs.com/package/dsh-hs-candidate) |
|
|
101
|
+
| **[dsh-travel-recon](https://github.com/PerryLink/dsh-travel-recon)** | [npm](https://www.npmjs.com/package/dsh-travel-recon) |
|
|
102
|
+
| **[dsh-pim-lint](https://github.com/PerryLink/dsh-pim-lint)** | [npm](https://www.npmjs.com/package/dsh-pim-lint) |
|
|
103
|
+
| **[dsh-eval-pack](https://github.com/PerryLink/dsh-eval-pack)** | [npm](https://www.npmjs.com/package/dsh-eval-pack) |
|
|
104
|
+
| **[dsh-finops-suite](https://github.com/PerryLink/dsh-finops-suite)** | [npm](https://www.npmjs.com/package/dsh-finops-suite) |
|
|
105
|
+
| **[dsh-contract-suite](https://github.com/PerryLink/dsh-contract-suite)** | [npm](https://www.npmjs.com/package/dsh-contract-suite) |
|
|
106
|
+
|
|
107
|
+
</details>
|
|
108
|
+
|
|
109
|
+
## Licença
|
|
110
|
+
|
|
111
|
+
Apache-2.0. See `LICENSE`, `NOTICE`, `THIRD-PARTY-NOTICES`.
|
package/README-zh.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
1
|
+
<div align="center">
|
|
2
|
+
|
|
3
|
+
# dsh-eval-pack
|
|
4
|
+
|
|
5
|
+
[](https://www.npmjs.com/package/dsh-eval-pack)
|
|
6
|
+
[](https://github.com/PerryLink/dsh-eval-pack/actions)
|
|
7
|
+
[](LICENSE)
|
|
8
|
+
[](https://github.com/topics/dsh-plugin)
|
|
9
|
+
[](https://perrylink.github.io/dsh-plugins/)
|
|
10
|
+
|
|
11
|
+
**公开/合成 eval-pack lint 与确定性 JSON 评分。**
|
|
12
|
+
|
|
13
|
+
> **状态：alpha / 公开合成 / partial / not counted / 非 GA。** 不含客户证据、客户数据，也不作生产可用声明。
|
|
14
|
+
|
|
15
|
+
[English](README.md) · [简体中文](README-zh.md) · [Español](README-es.md) · [Português](README-pt.md) · [हिन्दी](README-hi.md)
|
|
16
|
+
|
|
17
|
+
```sh
|
|
18
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
</div>
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
|
|
25
|
+
*工作流：本地输入 → 插件 → 本地输出；不需要调用模型。*
|
|
26
|
+
|
|
27
|
+
## 安装
|
|
28
|
+
|
|
29
|
+
安装并验证：
|
|
30
|
+
|
|
31
|
+
```sh
|
|
32
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
33
|
+
dsh --profile <profile> --dump-config | grep dsh-eval-pack
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
卸载：
|
|
37
|
+
|
|
38
|
+
```sh
|
|
39
|
+
dsh plugin --profile <profile> remove dsh-eval-pack
|
|
40
|
+
```
|
|
41
|
+
|
|
42
|
+
## 它做什么
|
|
43
|
+
|
|
44
|
+
公开/合成 eval-pack lint 与确定性 JSON 评分。 在 DeepSeek Harness 本地运行；下表就是实际工具面，示例使用真实命令面。
|
|
45
|
+
|
|
46
|
+
输入和输出都留在本地，不上传。
|
|
47
|
+
|
|
48
|
+
## 工具
|
|
49
|
+
|
|
50
|
+
工具名和说明保留英文，以对应运行输出。
|
|
51
|
+
|
|
52
|
+
| 工具 | 用途（英文对应运行输出） | 风险 |
|
|
53
|
+
|---|---|---|
|
|
54
|
+
| `eval.pack_lint` | Validate eval-pack name/version and unique task ids | R0 |
|
|
55
|
+
| `eval.grade` | Deterministic JSON equality grade | R0 |
|
|
56
|
+
|
|
57
|
+
## 快速开始
|
|
58
|
+
|
|
59
|
+
```sh
|
|
60
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
61
|
+
dsh --profile <profile> --dump-config | grep dsh-eval-pack
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
## 边界
|
|
65
|
+
|
|
66
|
+
- 仅公开/合成样例；不含客户数据或客户证据。
|
|
67
|
+
- alpha/partial、not counted，不作 GA 或生产可用声明。
|
|
68
|
+
- 除非工具明确说明，否则不调用模型、不联网。
|
|
69
|
+
- 每个工具的精确边界见工具表与 `ACCEPTANCE.csv`。
|
|
70
|
+
|
|
71
|
+
## 公开样例
|
|
72
|
+
|
|
73
|
+
公开/合成 fixture 在 `test/fixtures/`；`ACCEPTANCE.csv` 记录公开检查，全部 `counted=false`。
|
|
74
|
+
|
|
75
|
+
## 开发
|
|
76
|
+
|
|
77
|
+
```sh
|
|
78
|
+
pnpm install --frozen-lockfile
|
|
79
|
+
pnpm build && pnpm lint && pnpm typecheck && pnpm test
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
## 家族
|
|
83
|
+
|
|
84
|
+
<details>
|
|
85
|
+
<summary>DSH 领域插件家族（15 个包 + 2 个 suite）</summary>
|
|
86
|
+
|
|
87
|
+
| Package | npm |
|
|
88
|
+
|---|---|
|
|
89
|
+
| **[dsh-einvoice](https://github.com/PerryLink/dsh-einvoice)** | [npm](https://www.npmjs.com/package/dsh-einvoice) |
|
|
90
|
+
| **[dsh-docx-redline](https://github.com/PerryLink/dsh-docx-redline)** | [npm](https://www.npmjs.com/package/dsh-docx-redline) |
|
|
91
|
+
| **[dsh-policy-ledger](https://github.com/PerryLink/dsh-policy-ledger)** | [npm](https://www.npmjs.com/package/dsh-policy-ledger) |
|
|
92
|
+
| **[dsh-ghg](https://github.com/PerryLink/dsh-ghg)** | [npm](https://www.npmjs.com/package/dsh-ghg) |
|
|
93
|
+
| **[dsh-bankrec](https://github.com/PerryLink/dsh-bankrec)** | [npm](https://www.npmjs.com/package/dsh-bankrec) |
|
|
94
|
+
| **[dsh-ap-three-way](https://github.com/PerryLink/dsh-ap-three-way)** | [npm](https://www.npmjs.com/package/dsh-ap-three-way) |
|
|
95
|
+
| **[dsh-ifc-qto](https://github.com/PerryLink/dsh-ifc-qto)** | [npm](https://www.npmjs.com/package/dsh-ifc-qto) |
|
|
96
|
+
| **[dsh-qms-capa](https://github.com/PerryLink/dsh-qms-capa)** | [npm](https://www.npmjs.com/package/dsh-qms-capa) |
|
|
97
|
+
| **[dsh-legal-intake](https://github.com/PerryLink/dsh-legal-intake)** | [npm](https://www.npmjs.com/package/dsh-legal-intake) |
|
|
98
|
+
| **[dsh-legal-clause](https://github.com/PerryLink/dsh-legal-clause)** | [npm](https://www.npmjs.com/package/dsh-legal-clause) |
|
|
99
|
+
| **[dsh-freight-audit](https://github.com/PerryLink/dsh-freight-audit)** | [npm](https://www.npmjs.com/package/dsh-freight-audit) |
|
|
100
|
+
| **[dsh-hs-candidate](https://github.com/PerryLink/dsh-hs-candidate)** | [npm](https://www.npmjs.com/package/dsh-hs-candidate) |
|
|
101
|
+
| **[dsh-travel-recon](https://github.com/PerryLink/dsh-travel-recon)** | [npm](https://www.npmjs.com/package/dsh-travel-recon) |
|
|
102
|
+
| **[dsh-pim-lint](https://github.com/PerryLink/dsh-pim-lint)** | [npm](https://www.npmjs.com/package/dsh-pim-lint) |
|
|
103
|
+
| **[dsh-eval-pack](https://github.com/PerryLink/dsh-eval-pack)** | [npm](https://www.npmjs.com/package/dsh-eval-pack) |
|
|
104
|
+
| **[dsh-finops-suite](https://github.com/PerryLink/dsh-finops-suite)** | [npm](https://www.npmjs.com/package/dsh-finops-suite) |
|
|
105
|
+
| **[dsh-contract-suite](https://github.com/PerryLink/dsh-contract-suite)** | [npm](https://www.npmjs.com/package/dsh-contract-suite) |
|
|
106
|
+
|
|
107
|
+
</details>
|
|
108
|
+
|
|
109
|
+
## 许可证
|
|
110
|
+
|
|
111
|
+
Apache-2.0. See `LICENSE`, `NOTICE`, `THIRD-PARTY-NOTICES`.
|
package/README.md
CHANGED
|
@@ -1,3 +1,111 @@
|
|
|
1
|
-
|
|
1
|
+
<div align="center">
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
# dsh-eval-pack
|
|
4
|
+
|
|
5
|
+
[](https://www.npmjs.com/package/dsh-eval-pack)
|
|
6
|
+
[](https://github.com/PerryLink/dsh-eval-pack/actions)
|
|
7
|
+
[](LICENSE)
|
|
8
|
+
[](https://github.com/topics/dsh-plugin)
|
|
9
|
+
[](https://perrylink.github.io/dsh-plugins/)
|
|
10
|
+
|
|
11
|
+
**Public/synthetic eval-pack lint and deterministic JSON grader; not a validated benchmark.**
|
|
12
|
+
|
|
13
|
+
> **Status: alpha / public-synthetic / partial / not counted / not GA.** No customer evidence, customer data, or production-readiness claim.
|
|
14
|
+
|
|
15
|
+
[English](README.md) · [简体中文](README-zh.md) · [Español](README-es.md) · [Português](README-pt.md) · [हिन्दी](README-hi.md)
|
|
16
|
+
|
|
17
|
+
```sh
|
|
18
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
</div>
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
|
|
25
|
+
*Workflow: local input → plugin → local output. No model call is required.*
|
|
26
|
+
|
|
27
|
+
## Install
|
|
28
|
+
|
|
29
|
+
Install and verify:
|
|
30
|
+
|
|
31
|
+
```sh
|
|
32
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
33
|
+
dsh --profile <profile> --dump-config | grep dsh-eval-pack
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
Uninstall:
|
|
37
|
+
|
|
38
|
+
```sh
|
|
39
|
+
dsh plugin --profile <profile> remove dsh-eval-pack
|
|
40
|
+
```
|
|
41
|
+
|
|
42
|
+
## What it does
|
|
43
|
+
|
|
44
|
+
Public/synthetic eval-pack lint and deterministic JSON grader; not a validated benchmark. Runs locally on DeepSeek Harness. The table below is the exact tool surface; the examples use the real command surface.
|
|
45
|
+
|
|
46
|
+
Input and output stay local; nothing is uploaded.
|
|
47
|
+
|
|
48
|
+
## Tools
|
|
49
|
+
|
|
50
|
+
Tool names and descriptions are kept in English to match the runtime output.
|
|
51
|
+
|
|
52
|
+
| Tool | Purpose | Risk |
|
|
53
|
+
|---|---|---|
|
|
54
|
+
| `eval.pack_lint` | Validate eval-pack name/version and unique task ids | R0 |
|
|
55
|
+
| `eval.grade` | Deterministic JSON equality grade | R0 |
|
|
56
|
+
|
|
57
|
+
## Quick start
|
|
58
|
+
|
|
59
|
+
```sh
|
|
60
|
+
dsh plugin --profile <profile> add dsh-eval-pack
|
|
61
|
+
dsh --profile <profile> --dump-config | grep dsh-eval-pack
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
## Limits
|
|
65
|
+
|
|
66
|
+
- Public/synthetic only; no customer data or customer evidence.
|
|
67
|
+
- Alpha/partial, not counted, no GA or production-readiness claim.
|
|
68
|
+
- No model or network call unless a tool explicitly says so.
|
|
69
|
+
- The exact per-tool boundaries are in the table and `ACCEPTANCE.csv`.
|
|
70
|
+
|
|
71
|
+
## Public sample
|
|
72
|
+
|
|
73
|
+
Public/synthetic fixtures live in `test/fixtures/`; `ACCEPTANCE.csv` records the public checks with `counted=false`.
|
|
74
|
+
|
|
75
|
+
## Development
|
|
76
|
+
|
|
77
|
+
```sh
|
|
78
|
+
pnpm install --frozen-lockfile
|
|
79
|
+
pnpm build && pnpm lint && pnpm typecheck && pnpm test
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
## Family
|
|
83
|
+
|
|
84
|
+
<details>
|
|
85
|
+
<summary>DSH domain plugin family (15 packages + 2 suites)</summary>
|
|
86
|
+
|
|
87
|
+
| Package | npm |
|
|
88
|
+
|---|---|
|
|
89
|
+
| **[dsh-einvoice](https://github.com/PerryLink/dsh-einvoice)** | [npm](https://www.npmjs.com/package/dsh-einvoice) |
|
|
90
|
+
| **[dsh-docx-redline](https://github.com/PerryLink/dsh-docx-redline)** | [npm](https://www.npmjs.com/package/dsh-docx-redline) |
|
|
91
|
+
| **[dsh-policy-ledger](https://github.com/PerryLink/dsh-policy-ledger)** | [npm](https://www.npmjs.com/package/dsh-policy-ledger) |
|
|
92
|
+
| **[dsh-ghg](https://github.com/PerryLink/dsh-ghg)** | [npm](https://www.npmjs.com/package/dsh-ghg) |
|
|
93
|
+
| **[dsh-bankrec](https://github.com/PerryLink/dsh-bankrec)** | [npm](https://www.npmjs.com/package/dsh-bankrec) |
|
|
94
|
+
| **[dsh-ap-three-way](https://github.com/PerryLink/dsh-ap-three-way)** | [npm](https://www.npmjs.com/package/dsh-ap-three-way) |
|
|
95
|
+
| **[dsh-ifc-qto](https://github.com/PerryLink/dsh-ifc-qto)** | [npm](https://www.npmjs.com/package/dsh-ifc-qto) |
|
|
96
|
+
| **[dsh-qms-capa](https://github.com/PerryLink/dsh-qms-capa)** | [npm](https://www.npmjs.com/package/dsh-qms-capa) |
|
|
97
|
+
| **[dsh-legal-intake](https://github.com/PerryLink/dsh-legal-intake)** | [npm](https://www.npmjs.com/package/dsh-legal-intake) |
|
|
98
|
+
| **[dsh-legal-clause](https://github.com/PerryLink/dsh-legal-clause)** | [npm](https://www.npmjs.com/package/dsh-legal-clause) |
|
|
99
|
+
| **[dsh-freight-audit](https://github.com/PerryLink/dsh-freight-audit)** | [npm](https://www.npmjs.com/package/dsh-freight-audit) |
|
|
100
|
+
| **[dsh-hs-candidate](https://github.com/PerryLink/dsh-hs-candidate)** | [npm](https://www.npmjs.com/package/dsh-hs-candidate) |
|
|
101
|
+
| **[dsh-travel-recon](https://github.com/PerryLink/dsh-travel-recon)** | [npm](https://www.npmjs.com/package/dsh-travel-recon) |
|
|
102
|
+
| **[dsh-pim-lint](https://github.com/PerryLink/dsh-pim-lint)** | [npm](https://www.npmjs.com/package/dsh-pim-lint) |
|
|
103
|
+
| **[dsh-eval-pack](https://github.com/PerryLink/dsh-eval-pack)** | [npm](https://www.npmjs.com/package/dsh-eval-pack) |
|
|
104
|
+
| **[dsh-finops-suite](https://github.com/PerryLink/dsh-finops-suite)** | [npm](https://www.npmjs.com/package/dsh-finops-suite) |
|
|
105
|
+
| **[dsh-contract-suite](https://github.com/PerryLink/dsh-contract-suite)** | [npm](https://www.npmjs.com/package/dsh-contract-suite) |
|
|
106
|
+
|
|
107
|
+
</details>
|
|
108
|
+
|
|
109
|
+
## License
|
|
110
|
+
|
|
111
|
+
Apache-2.0. See `LICENSE`, `NOTICE`, `THIRD-PARTY-NOTICES`.
|
package/cordis.patch.yml
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
1
|
+
<svg xmlns="http://www.w3.org/2000/svg" width="960" height="240" viewBox="0 0 960 240" role="img" aria-label="dsh-eval-pack workflow">
|
|
2
|
+
<rect width="960" height="240" rx="18" fill="#0b1020"/>
|
|
3
|
+
<rect x="24" y="24" width="912" height="192" rx="14" fill="#111a2e" stroke="#27314a"/>
|
|
4
|
+
<g><rect x="40" y="56" width="44" height="52" rx="5" fill="none" stroke="#6ea8fe" stroke-width="2"/><path d="M50 68h24M50 76h24M50 84h16" stroke="#6ea8fe" stroke-width="2"/></g>
|
|
5
|
+
<path d="M220 120h100" stroke="#6ea8fe" stroke-width="2" marker-end="url(#a)"/>
|
|
6
|
+
<rect x="330" y="76" width="300" height="88" rx="12" fill="#0b1020" stroke="#6ea8fe"/>
|
|
7
|
+
<text x="480" y="124" text-anchor="middle" fill="#e8edf7" font-family="ui-monospace,monospace" font-size="20" font-weight="700">dsh-eval-pack</text>
|
|
8
|
+
<path d="M640 120h100" stroke="#6ea8fe" stroke-width="2" marker-end="url(#a)"/>
|
|
9
|
+
<g transform="translate(810,0)"><rect x="46" y="58" width="40" height="46" rx="4" fill="none" stroke="#6ea8fe" stroke-width="2"/><path d="M54 68h24M54 76h24M54 84h18M54 92h12" stroke="#6ea8fe" stroke-width="2"/></g>
|
|
10
|
+
<defs><marker id="a" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="6" markerHeight="6" orient="auto"><path d="M0 0L10 5L0 10z" fill="#6ea8fe"/></marker></defs>
|
|
11
|
+
</svg>
|
|
@@ -0,0 +1,11 @@
|
|
|
1
|
+
export interface EvalTask {
|
|
2
|
+
id: string;
|
|
3
|
+
expected?: unknown;
|
|
4
|
+
}
|
|
5
|
+
export interface EvalPack {
|
|
6
|
+
name: string;
|
|
7
|
+
version: string;
|
|
8
|
+
tasks: EvalTask[];
|
|
9
|
+
}
|
|
10
|
+
export declare function lintPack(input: unknown): string[];
|
|
11
|
+
export declare function grade(actual: unknown, expected: unknown): boolean;
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
export function lintPack(input) {
|
|
2
|
+
const errors = [];
|
|
3
|
+
if (!input || typeof input !== 'object')
|
|
4
|
+
return ['E_PACK_NOT_OBJECT'];
|
|
5
|
+
const pack = input;
|
|
6
|
+
if (!pack.name || typeof pack.name !== 'string')
|
|
7
|
+
errors.push('E_PACK_NAME');
|
|
8
|
+
if (!pack.version || typeof pack.version !== 'string')
|
|
9
|
+
errors.push('E_PACK_VERSION');
|
|
10
|
+
if (!Array.isArray(pack.tasks) || pack.tasks.length === 0)
|
|
11
|
+
errors.push('E_PACK_TASKS_EMPTY');
|
|
12
|
+
else {
|
|
13
|
+
const ids = new Set();
|
|
14
|
+
for (const task of pack.tasks) {
|
|
15
|
+
if (!task || typeof task.id !== 'string' || !task.id) {
|
|
16
|
+
errors.push('E_TASK_ID');
|
|
17
|
+
continue;
|
|
18
|
+
}
|
|
19
|
+
if (ids.has(task.id))
|
|
20
|
+
errors.push(`E_TASK_DUPLICATE:${task.id}`);
|
|
21
|
+
ids.add(task.id);
|
|
22
|
+
}
|
|
23
|
+
}
|
|
24
|
+
return errors;
|
|
25
|
+
}
|
|
26
|
+
export function grade(actual, expected) {
|
|
27
|
+
return JSON.stringify(actual) === JSON.stringify(expected);
|
|
28
|
+
}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
export declare function createTools(): import("@deepseek-ai/dsh-tools").ToolDefinition[];
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
import { defineTool } from '@deepseek-ai/dsh-tools';
|
|
2
|
+
import { grade, lintPack } from '../core/harness.js';
|
|
3
|
+
const text = (t) => [{ type: 'text', text: t }];
|
|
4
|
+
export function createTools() {
|
|
5
|
+
const lint = defineTool({
|
|
6
|
+
name: 'eval.pack_lint',
|
|
7
|
+
description: 'Lint a public/synthetic eval-pack object: name, version, non-empty unique task ids. Read-only; no runner.',
|
|
8
|
+
parameters: { pack: { type: 'object', additionalProperties: true, required: true } },
|
|
9
|
+
output: { schema: { type: 'object', additionalProperties: false, properties: { errors: { type: 'array', items: { type: 'string' }, required: true }, ok: { type: 'boolean', required: true } } }, render: (_a, v) => text(`pack ok=${v.ok}`) },
|
|
10
|
+
async execute(args) { const errors = lintPack(args.pack); return { errors, ok: errors.length === 0 }; },
|
|
11
|
+
});
|
|
12
|
+
const gradeTool = defineTool({
|
|
13
|
+
name: 'eval.grade',
|
|
14
|
+
description: 'Deterministic JSON equality grade for one public/synthetic task. Read-only.',
|
|
15
|
+
parameters: { actual: { type: 'json', required: true }, expected: { type: 'json', required: true } },
|
|
16
|
+
output: { schema: { type: 'object', additionalProperties: false, properties: { pass: { type: 'boolean', required: true } } }, render: (_a, v) => text(`grade ${v.pass ? 'pass' : 'fail'}`) },
|
|
17
|
+
async execute(args) { return { pass: grade(args.actual, args.expected) }; },
|
|
18
|
+
});
|
|
19
|
+
return [lint, gradeTool];
|
|
20
|
+
}
|
package/package.json
CHANGED
|
@@ -1,6 +1,75 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-eval-pack",
|
|
3
|
-
"version": "0.
|
|
4
|
-
"
|
|
5
|
-
"
|
|
6
|
-
|
|
3
|
+
"version": "0.1.0-alpha.3",
|
|
4
|
+
"description": "Public/synthetic eval-pack lint and deterministic JSON grader; not a validated benchmark.",
|
|
5
|
+
"type": "module",
|
|
6
|
+
"main": "./lib/plugin/index.js",
|
|
7
|
+
"types": "./lib/plugin/index.d.ts",
|
|
8
|
+
"exports": {
|
|
9
|
+
".": {
|
|
10
|
+
"types": "./lib/plugin/index.d.ts",
|
|
11
|
+
"default": "./lib/plugin/index.js"
|
|
12
|
+
}
|
|
13
|
+
},
|
|
14
|
+
"files": [
|
|
15
|
+
"lib",
|
|
16
|
+
"cordis.patch.yml",
|
|
17
|
+
"README.md",
|
|
18
|
+
"LICENSE",
|
|
19
|
+
"NOTICE",
|
|
20
|
+
"README-zh.md",
|
|
21
|
+
"README-es.md",
|
|
22
|
+
"README-pt.md",
|
|
23
|
+
"README-hi.md",
|
|
24
|
+
"docs/assets"
|
|
25
|
+
],
|
|
26
|
+
"dsh": {
|
|
27
|
+
"bundle": {
|
|
28
|
+
"patch": "./cordis.patch.yml"
|
|
29
|
+
}
|
|
30
|
+
},
|
|
31
|
+
"engines": {
|
|
32
|
+
"dsh": ">=0.2.1-rc.3 <0.3.0",
|
|
33
|
+
"node": ">=24.9.0 <25"
|
|
34
|
+
},
|
|
35
|
+
"packageManager": "pnpm@11.28.5",
|
|
36
|
+
"scripts": {
|
|
37
|
+
"build": "tsc -p tsconfig.json",
|
|
38
|
+
"lint": "node scripts/lint.mjs",
|
|
39
|
+
"typecheck": "tsc -p tsconfig.json --noEmit",
|
|
40
|
+
"test": "pnpm build && node --test test/*.test.mjs",
|
|
41
|
+
"prepublishOnly": "node scripts/check-npm-name.mjs",
|
|
42
|
+
"gate": "node scripts/gate.mjs"
|
|
43
|
+
},
|
|
44
|
+
"keywords": [
|
|
45
|
+
"deepseek-harness",
|
|
46
|
+
"dsh",
|
|
47
|
+
"dsh-plugin",
|
|
48
|
+
"eval",
|
|
49
|
+
"harness",
|
|
50
|
+
"perrylink",
|
|
51
|
+
"testing"
|
|
52
|
+
],
|
|
53
|
+
"repository": {
|
|
54
|
+
"type": "git",
|
|
55
|
+
"url": "git+https://github.com/PerryLink/dsh-eval-pack.git"
|
|
56
|
+
},
|
|
57
|
+
"license": "Apache-2.0",
|
|
58
|
+
"publishConfig": {
|
|
59
|
+
"access": "public"
|
|
60
|
+
},
|
|
61
|
+
"peerDependencies": {
|
|
62
|
+
"@deepseek-ai/cordis": ">=4.0.5 <5",
|
|
63
|
+
"@deepseek-ai/dsh-tools": ">=0.2.1-rc.3 <0.3.0"
|
|
64
|
+
},
|
|
65
|
+
"devDependencies": {
|
|
66
|
+
"@deepseek-ai/cordis": "4.0.5",
|
|
67
|
+
"@deepseek-ai/dsh-tools": "0.2.1-rc.3",
|
|
68
|
+
"@types/node": "^24.0.0",
|
|
69
|
+
"typescript": "7.0.2"
|
|
70
|
+
},
|
|
71
|
+
"homepage": "https://perrylink.github.io/dsh-plugins/packages/dsh-eval-pack.html",
|
|
72
|
+
"bugs": {
|
|
73
|
+
"url": "https://github.com/PerryLink/dsh-eval-pack/issues"
|
|
74
|
+
}
|
|
75
|
+
}
|