dsh-doublecheck 0.9.6 → 0.9.8
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/CHANGELOG.md +27 -0
- package/README.es.md +41 -36
- package/README.hi.md +41 -36
- package/README.md +41 -36
- package/README.pt.md +41 -36
- package/README.zh.md +41 -36
- package/lib/domain/evidence.d.ts +36 -3
- package/lib/domain/evidence.js +38 -3
- package/lib/domain/gate.js +14 -10
- package/lib/domain/projection.js +17 -13
- package/lib/domain/report.js +18 -16
- package/lib/domain/stages.js +19 -17
- package/lib/index.js +2 -0
- package/package.json +23 -24
package/CHANGELOG.md
CHANGED
|
@@ -2,6 +2,33 @@
|
|
|
2
2
|
|
|
3
3
|
All notable changes to dsh-doublecheck are recorded here, newest first.
|
|
4
4
|
|
|
5
|
+
## [0.9.8] - 2026-09-09
|
|
6
|
+
|
|
7
|
+
### Fixed
|
|
8
|
+
|
|
9
|
+
- Adapt the PTC sub-dispatch event vocabulary to the session-format V3 line: the host renamed the durable `tool/code-dispatch` event to `tool/ptc-dispatch` (payload unchanged), so on `0.1.5-alpha.1` the four evidence folds (discipline stage, test evidence, report facts, session projection) silently missed PTC test runs and dispatched `edit`/`write` calls. A shared `ptcSettle()` normalizer now folds the current label and matches the predecessor label structurally, so both the published `0.1.2-rc.1` line and the V3 line stay supported by the unchanged peer band.
|
|
10
|
+
- Point `scripts/scan-sessions.mjs` at the generation-suffixed log filename (`session.v3.jsonl.zstd`, highest `vN` per directory) instead of the hardcoded flat `session.jsonl.zstd`, and require the session project directory as an explicit argument so the tool can never default to the real `~/.dsh` store.
|
|
11
|
+
|
|
12
|
+
### Changed
|
|
13
|
+
|
|
14
|
+
- Add the `typecheck:ci` gate (`tsconfig.ci.json`, published-type resolution) and run it in `prepublishOnly`; no behavior change.
|
|
15
|
+
- Extend the CI/compat install probes to a `0.1.2-rc.1` + `0.1.5-alpha.1` matrix instead of replacing the old pin, so both release lines keep an install smoke.
|
|
16
|
+
|
|
17
|
+
### Docs
|
|
18
|
+
|
|
19
|
+
- Refresh the five-language README compatibility sections: harness baseline `dsh-v0.1.5-alpha.1`, the `tool/ptc-dispatch` event name, and the `Session.append` / settings-seam facts re-verified on `0.1.5-alpha.1`; no behavior change.
|
|
20
|
+
|
|
21
|
+
## [0.9.7] - 2026-09-07
|
|
22
|
+
|
|
23
|
+
### Fixed
|
|
24
|
+
|
|
25
|
+
- Regenerate the committed `lib/` after the seam-marker docs commit so the CI build-drift gate stays green; no behavior change.
|
|
26
|
+
|
|
27
|
+
### Docs
|
|
28
|
+
|
|
29
|
+
- Fix the DSH plugin badge URL: shields.io rejects the four-segment static badge form with "404 badge not found"; the label now uses the documented double-dash form (`dsh--plugin`), rendering identically; no behavior change.
|
|
30
|
+
|
|
31
|
+
|
|
5
32
|
## [0.9.6] - 2026-09-07
|
|
6
33
|
|
|
7
34
|
### Fixed
|
package/README.es.md
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
*Los requisitos se interrogan antes de la primera edición; la entrega se demuestra, nunca se afirma.*
|
|
9
9
|
|
|
10
10
|
[](LICENSE)
|
|
11
|
-
[](https://github.com/topics/dsh-plugin)
|
|
12
12
|
[](#)
|
|
13
13
|
[](https://github.com/PerryLink/dsh-doublecheck/actions)
|
|
14
14
|
[](https://github.com/PerryLink/dsh-doublecheck/releases)
|
|
@@ -25,7 +25,7 @@
|
|
|
25
25
|
|
|
26
26
|
| Superficie | Estado |
|
|
27
27
|
|---|---|
|
|
28
|
-
| Harness | DeepSeek Harness `dsh-v0.1.
|
|
28
|
+
| Harness | DeepSeek Harness `dsh-v0.1.5-alpha.1`. Verificado el 2026-09-09 contra el checkout master `dsh-v0.1.5-alpha.1` (cadena completa de puertas + humo de instalación del perfil); la línea publicada `0.1.2-rc.1` sigue soportada. |
|
|
29
29
|
| Node | `^22.19.0 \|\| >=24.0.0` |
|
|
30
30
|
| Plataformas | Todas (host puro; sin código nativo, sin solicitudes de red directas propias) |
|
|
31
31
|
| Modelo | Cualquiera (el guard nunca llama a un modelo; las fases de crítico y revisor se ejecutan como subagentes del harness) |
|
|
@@ -208,7 +208,7 @@ El CLI solo serializa el `GateState` ya asentado — nunca vuelve a ejecutar la
|
|
|
208
208
|
|
|
209
209
|
## Permisos y datos
|
|
210
210
|
|
|
211
|
-
- **Lee**: el registro de sesión (`tool/call` / `tool/result` / `tool/
|
|
211
|
+
- **Lee**: el registro de sesión (`tool/call` / `tool/result` / `tool/ptc-dispatch`, fuentes `user/message` inyectadas y los registros de veredicto ajenos `autoReview/*`) solo en proceso; el estado opcional del servicio de modo plan. Antes del renombrado de V3 el host registra los subenvíos PTC con la etiqueta predecesora `tool/code-dispatch`; ambas etiquetas se pliegan de forma idéntica.
|
|
212
212
|
- **Escribe**: `doublecheck-spec.md`, `doublecheck-report.md` y `gate-report.md` en el workspace de sesión (rutas configurables) a través de la interfaz `ctx.fs`; los eventos de sesión durables `doublecheck/state` y `doublecheck/gate`.
|
|
213
213
|
- **Llamadas a modelo**: las fases de consistencia y revisión local de la puerta (un subagente cada una por `/gate run`), la revisión adversarial opcional y el flujo de verificación de `doublecheck_report` inician ejecuciones de subagente; nada más llama a un modelo o a la red.
|
|
214
214
|
- **Nunca toca**: credenciales, variables de entorno o cualquier archivo fuera del workspace de sesión. El manifiesto del workshop declara solo `filesystem:read` y `filesystem:write`. Los informes de la puerta llevan solo conteos, ids y veredictos; los secretos reconocidos en los textos del revisor se redactan antes de almacenarlos o mostrarlos.
|
|
@@ -225,6 +225,7 @@ El CLI solo serializa el `GateState` ya asentado — nunca vuelve a ejecutar la
|
|
|
225
225
|
|
|
226
226
|
- **Escrituras durables.** `/doublecheck on\|off` → `doublecheck/state` y `/gate run` → `doublecheck/gate` necesitan la superficie de append `ignorable` del host (post-rc.6 hasta `0.1.1-rc.2`). En hosts sin esa superficie (rc.6/rc.8 y `0.1.2-alpha.1`, que eliminó el sobre — `0.1.2-rc.1` restaura el campo solo para compatibilidad de lectura de logs almacenados y aún no puede estamparlo), las escrituras se omiten y el interruptor queda en proceso.
|
|
227
227
|
0.1.2-rc.1 (adaptado el 2026-09-02): el sobre de sesión conserva su campo ignorable solo para compatibilidad de lectura de logs almacenados - Session.append aún no puede estamparlo, por lo que el comportamiento de la puerta no cambia.
|
|
228
|
+
0.1.5-alpha.1 (adaptado el 2026-09-09): el formato de sesión V3 renombra el evento durable de subenvío `tool/code-dispatch` a `tool/ptc-dispatch` (carga útil sin cambios; ambas etiquetas se pliegan de forma idéntica). Session.append sigue sin canal `ignorable`, así que las escrituras durables se omiten y el interruptor permanece en proceso - comportamiento sin cambios. El espacio de ajustes `doublecheck.gate` sigue siendo una interfaz débil (véase Limitaciones conocidas).
|
|
228
229
|
- **Interfaces opcionales.** El espacio de ajustes `doublecheck.gate` se registra solo cuando el servicio de ajustes está montado; la línea de modo plan de `/gate status` lee el `ctx.planMode` opcional (muestra `unknown` sin él); la revisión adversarial necesita `ctx.subagents`; la verificación necesita `workflowEngine`.
|
|
229
230
|
- **Degradación local.** `gate.review.engine: auto` degrada al revisor local cuando dsh-auto-review está ausente o no tiene registros de veredicto en esta sesión — el informe nombra la razón en lugar de inventar un veredicto.
|
|
230
231
|
- **La evidencia dsh-eval se basa en archivos.** El motor de evaluación de dsh-auto-review (`dsh-eval`) escribe sus resultados de regresión de prompt / estrés / equidad en un archivo de informe del espacio de trabajo, no en el registro de sesión. `gate.tests.evalReports.enabled` pliega ese archivo (desactivado por defecto; salta cuando está ausente) y los recuentos pliegados viajan en el registro duradero `doublecheck/gate` para que una ejecución asentada siga siendo reproducible.
|
|
@@ -253,42 +254,46 @@ pnpm run pack:check # build + pack the tarball
|
|
|
253
254
|
|
|
254
255
|
## PerryLink DSH Plugin Family
|
|
255
256
|
|
|
256
|
-
Este proyecto es uno de los [
|
|
257
|
+
Este proyecto es uno de los [37 complementos de DeepSeek Harness](https://github.com/PerryLink) mantenidos por [PerryLink](https://github.com/PerryLink). Si este te ayuda, probablemente los demás también:
|
|
257
258
|
|
|
258
259
|
| Plugin | One-liner |
|
|
259
260
|
|---|---|
|
|
260
|
-
| **[dsh-
|
|
261
|
-
| **[dsh-
|
|
262
|
-
| **[dsh-
|
|
263
|
-
| **[dsh-
|
|
264
|
-
| **[dsh-
|
|
265
|
-
| **[dsh-
|
|
266
|
-
| **[dsh-
|
|
267
|
-
| **[dsh-
|
|
268
|
-
| **[dsh-
|
|
269
|
-
| **[dsh-
|
|
270
|
-
| **[dsh-
|
|
271
|
-
| **[dsh-
|
|
272
|
-
| **[dsh-
|
|
273
|
-
| **[dsh-
|
|
274
|
-
| **[dsh-
|
|
275
|
-
| **[dsh-
|
|
276
|
-
| **[dsh-
|
|
277
|
-
| **[dsh-
|
|
278
|
-
| **[dsh-
|
|
279
|
-
| **[dsh-
|
|
280
|
-
| **[dsh-
|
|
281
|
-
| **[dsh-
|
|
282
|
-
| **[dsh-
|
|
283
|
-
| **[dsh-
|
|
284
|
-
| **[dsh-
|
|
285
|
-
| **[dsh-
|
|
286
|
-
| **[dsh-
|
|
287
|
-
| **[dsh-
|
|
288
|
-
| **[dsh-
|
|
289
|
-
| **[dsh-
|
|
290
|
-
| **[dsh-
|
|
291
|
-
| **[dsh-
|
|
261
|
+
| **[dsh-auto-review](https://github.com/PerryLink/dsh-auto-review)** | Auto-revisión de segundo modelo en la cadena de aprobación, con cierre en fallo por defecto | |
|
|
262
|
+
| **[dsh-background-agents](https://github.com/PerryLink/dsh-background-agents)** | Agentes hijos en segundo plano durables con barra lateral de UI web, mensajería e interrupción | |
|
|
263
|
+
| **[dsh-budget](https://github.com/PerryLink/dsh-budget)** | Gobernanza de costes para DeepSeek Harness: presupuestos, carbono y latencia en un panel. | |
|
|
264
|
+
| **[dsh-checkpoint-rewind](https://github.com/PerryLink/dsh-checkpoint-rewind)** | Equivalente a /rewind de Claude Code: instantáneas, bifurcaciones de sesión, restauración de un solo uso | |
|
|
265
|
+
| **[dsh-claude-move](https://github.com/PerryLink/dsh-claude-move)** | Migra sesiones, memoria, habilidades y CLAUDE.md de Claude Code a DSH | |
|
|
266
|
+
| **[dsh-click](https://github.com/PerryLink/dsh-click)** | Control de escritorio nativo multiplataforma para DeepSeek Harness — Windows primero. | |
|
|
267
|
+
| **[dsh-composer-history](https://github.com/PerryLink/dsh-composer-history)** | Historial de entrada estilo terminal para el compositor web: flechas, búsqueda Ctrl+R | |
|
|
268
|
+
| **[dsh-data-quality](https://github.com/PerryLink/dsh-data-quality)** | Comprobaciones de calidad de datasets y verificación de citas (el puente numérico opcional consumido aquí) | |
|
|
269
|
+
| **[dsh-defend](https://github.com/PerryLink/dsh-defend)** | Defensa contra inyección de prompts, jailbreak y fuga de secretos para DeepSeek Harness. | |
|
|
270
|
+
| **[dsh-draw](https://github.com/PerryLink/dsh-draw)** | Enrutamiento unificado de generación de imágenes estáticas para DeepSeek Harness. | |
|
|
271
|
+
| **[dsh-fast](https://github.com/PerryLink/dsh-fast)** | Diagnóstico de rendimiento de solo lectura para DeepSeek Harness. | |
|
|
272
|
+
| **[dsh-fund-research](https://github.com/PerryLink/dsh-fund-research)** | Informes de investigación deterministas para fondos mutuos públicos chinos | |
|
|
273
|
+
| **[dsh-github](https://github.com/PerryLink/dsh-github)** | Integración de PR/issues de GitHub para DSH, cada escritura controlada por aprobación | |
|
|
274
|
+
| **[dsh-industry-research](https://github.com/PerryLink/dsh-industry-research)** | Orquestación de investigación sectorial que sella sus entregables mediante el `ctx.researchReport.assemble` de este plugin | |
|
|
275
|
+
| **[dsh-library](https://github.com/PerryLink/dsh-library)** | Base de conocimiento documental local para DeepSeek Harness. | |
|
|
276
|
+
| **[dsh-local-ai](https://github.com/PerryLink/dsh-local-ai)** | Integración de modelos locales (Ollama) para DeepSeek Harness. | |
|
|
277
|
+
| **[dsh-lsp-actions](https://github.com/PerryLink/dsh-lsp-actions)** | Diagnósticos, formato, autocompletado, acciones de código y renombrado LSP sobre servidores de lenguaje | |
|
|
278
|
+
| **[dsh-mask](https://github.com/PerryLink/dsh-mask)** | Middleware de enmascaramiento de PII: anonimiza en el límite del modelo, restaura en la capa de visualización | |
|
|
279
|
+
| **[dsh-mcp-panel](https://github.com/PerryLink/dsh-mcp-panel)** | Panel de tiempo de ejecución MCP de solo lectura: comando /mcp + pestaña Settings con estado, herramientas y errores | |
|
|
280
|
+
| **[dsh-memento](https://github.com/PerryLink/dsh-memento)** | Memoria entre sesiones controlada por aprobación: costura ctx.memory + SQLite + herramienta de memoria | |
|
|
281
|
+
| **[dsh-observe](https://github.com/PerryLink/dsh-observe)** | Exportador de observabilidad OpenTelemetry y Langfuse para DeepSeek Harness. | |
|
|
282
|
+
| **[dsh-output-styles](https://github.com/PerryLink/dsh-output-styles)** | Cambio de estilo en tiempo de ejecución equivalente a outputStyles de Claude Code | |
|
|
283
|
+
| **[dsh-reach](https://github.com/PerryLink/dsh-reach)** | Puente multicanal de aprobación/preguntas: WeChat/Telegram/Feishu, consola de sesión |
|
|
284
|
+
| **[dsh-permission-rules](https://github.com/PerryLink/dsh-permission-rules)** | Reglas de permisos declarativas allow/deny/ask estilo Claude Code con auditoría | |
|
|
285
|
+
| **[dsh-personal-directive](https://github.com/PerryLink/dsh-personal-directive)** | Inyector de directivas personales con interruptor en la barra superior (edición framework) |
|
|
286
|
+
| **[dsh-plugin-guide](https://github.com/PerryLink/dsh-plugin-guide)** | Base de conocimiento de desarrollo de plugins como habilidad de agente bajo demanda | |
|
|
287
|
+
| **[dsh-research-report](https://github.com/PerryLink/dsh-research-report)** | Motor de informes de investigación verificables con evidencia direccionada por contenido | |
|
|
288
|
+
| **[dsh-score](https://github.com/PerryLink/dsh-score)** | Puntuación de calidad multidimensional para plugins de DeepSeek Harness. | |
|
|
289
|
+
| **[dsh-session-pin](https://github.com/PerryLink/dsh-session-pin)** | Fija sesiones en la barra lateral web con orden durable | |
|
|
290
|
+
| **[dsh-session-sync](https://github.com/PerryLink/dsh-session-sync)** | Sincronización de sesiones entre dispositivos para DeepSeek Harness — un espejo git dedicado de tu almacén de sesiones. | |
|
|
291
|
+
| **[dsh-skill-pack-security](https://github.com/PerryLink/dsh-skill-pack-security)** | Paquete de habilidades de auditoría de seguridad: escaneo de secretos, revisión de dependencias y cadena de suministro | |
|
|
292
|
+
| **[dsh-talk](https://github.com/PerryLink/dsh-talk)** | Bucle de sesión con voz para DeepSeek Harness: háblale y escucha su respuesta. | |
|
|
293
|
+
| **[dsh-test-drive](https://github.com/PerryLink/dsh-test-drive)** | Pruebas de instalación y humo aisladas para plugins de DeepSeek Harness. | |
|
|
294
|
+
| **[dsh-ticktick](https://github.com/PerryLink/dsh-ticktick)** | Puente de tareas TickTick/Dida365: panel de cabecera de sesión + 11 herramientas |
|
|
295
|
+
| **[dsh-translate](https://github.com/PerryLink/dsh-translate)** | Traducción de parámetros entre proveedores y reparación determinista de JSON para DeepSeek Harness. | |
|
|
296
|
+
| **[dsh-wechat](https://github.com/PerryLink/dsh-wechat)** | Puente WeChat ↔ DSH (bot Tencent iLink): texto/imagen/archivo/voz, aprobaciones en el chat |
|
|
292
297
|
|
|
293
298
|
### Instalar desde el mercado de DSH Desktop
|
|
294
299
|
|
package/README.hi.md
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
*पहली एडिट से पहले आवश्यकताओं की पड़ताल होती है; डिलीवरी साबित की जाती है, दावा नहीं किया जाता।*
|
|
9
9
|
|
|
10
10
|
[](LICENSE)
|
|
11
|
-
[](https://github.com/topics/dsh-plugin)
|
|
12
12
|
[](#)
|
|
13
13
|
[](https://github.com/PerryLink/dsh-doublecheck/actions)
|
|
14
14
|
[](https://github.com/PerryLink/dsh-doublecheck/releases)
|
|
@@ -25,7 +25,7 @@
|
|
|
25
25
|
|
|
26
26
|
| सतह | स्थिति |
|
|
27
27
|
|---|---|
|
|
28
|
-
| Harness | DeepSeek Harness `dsh-v0.1.
|
|
28
|
+
| Harness | DeepSeek Harness `dsh-v0.1.5-alpha.1`। 2026-09-09 को `dsh-v0.1.5-alpha.1` master checkout के विरुद्ध सत्यापित (पूर्ण द्वार श्रृंखला + प्रोफ़ाइल इंस्टॉल स्मोक); प्रकाशित `0.1.2-rc.1` पिन लाइन अभी भी समर्थित है। |
|
|
29
29
|
| Node | `^22.19.0 \|\| >=24.0.0` |
|
|
30
30
|
| प्लेटफ़ॉर्म | सभी (शुद्ध host; कोई नेटिव कोड नहीं, स्वयं का कोई सीधा नेटवर्क अनुरोध नहीं) |
|
|
31
31
|
| मॉडल | कोई भी (guard स्वयं कभी मॉडल नहीं बुलाता; critic और reviewer चरण harness subagent के रूप में चलते हैं) |
|
|
@@ -208,7 +208,7 @@ CLI केवल पहले से स्थापित `GateState` को
|
|
|
208
208
|
|
|
209
209
|
## अनुमतियाँ और डेटा
|
|
210
210
|
|
|
211
|
-
- **पढ़ता है**: सत्र लॉग (`tool/call` / `tool/result` / `tool/
|
|
211
|
+
- **पढ़ता है**: सत्र लॉग (`tool/call` / `tool/result` / `tool/ptc-dispatch`, इंजेक्ट किए गए `user/message` स्रोत, और बाहरी `autoReview/*` निर्णय रिकॉर्ड) केवल प्रक्रिया के भीतर; वैकल्पिक प्लान-मोड सेवा स्थिति। V3 नाम-परिवर्तन से पहले का host PTC उप-प्रेषण पूर्ववर्ती लेबल `tool/code-dispatch` से दर्ज करता है; दोनों लेबल समान रूप से फ़ोल्ड होते हैं।
|
|
212
212
|
- **लिखता है**: सत्र कार्यक्षेत्र में `doublecheck-spec.md`, `doublecheck-report.md` और `gate-report.md` (पथ कॉन्फ़िगर करने योग्य) `ctx.fs` इंटरफ़ेस के माध्यम से; टिकाऊ `doublecheck/state` और `doublecheck/gate` सत्र इवेंट।
|
|
213
213
|
- **मॉडल कॉलें**: द्वार के संगति और स्थानीय-समीक्षा चरण (प्रत्येक `/gate run` पर एक-एक subagent), वैकल्पिक प्रतिकूल समीक्षा, और `doublecheck_report` सत्यापन वर्कफ़्लो subagent रन शुरू करते हैं; इसके अलावा कुछ भी मॉडल या नेटवर्क नहीं बुलाता।
|
|
214
214
|
- **कभी नहीं छूता**: क्रेडेंशियल, पर्यावरण चर, या सत्र कार्यक्षेत्र के बाहर कोई फ़ाइल। workshop मेनिफ़ेस्ट केवल `filesystem:read` और `filesystem:write` घोषित करता है। द्वार रिपोर्टें केवल गणना, id और निर्णय रखती हैं; समीक्षक पाठों में पहचाने गए रहस्य भंडारण या प्रदर्शन से पहले संपादित (redacted) कर दिए जाते हैं।
|
|
@@ -225,6 +225,7 @@ CLI केवल पहले से स्थापित `GateState` को
|
|
|
225
225
|
|
|
226
226
|
- **टिकाऊ लेखन।** `/doublecheck on\|off` → `doublecheck/state` और `/gate run` → `doublecheck/gate` को host की `ignorable` append सतह (rc.6 के बाद से `0.1.1-rc.2` तक) चाहिए। उस सतह के बिना hosts (rc.6/rc.8 और `0.1.2-alpha.1`, जिसने envelope हटा दिया — `0.1.2-rc.1` केवल संग्रहीत-लॉग पठन संगतता के लिए फ़ील्ड बहाल करता है और अभी भी स्टैम्प नहीं कर सकता) पर लेखन छोड़ दिया जाता है और स्विच प्रक्रिया-स्थानीय रहता है।
|
|
227
227
|
0.1.2-rc.1 (2026-09-02 को अनुकूलित): सत्र लिफ़ाफ़ा अपना ignorable फ़ील्ड केवल संग्रहीत-लॉग पठन संगतता के लिए रखता है - Session.append अभी भी इसे स्टैम्प नहीं कर सकता, इसलिए गेट व्यवहार अपरिवर्तित है।
|
|
228
|
+
0.1.5-alpha.1 (2026-09-09 को अनुकूलित): सत्र प्रारूप V3 टिकाऊ उप-प्रेषण इवेंट `tool/code-dispatch` का नाम `tool/ptc-dispatch` करता है (पेलोड अपरिवर्तित; दोनों लेबल समान रूप से फ़ोल्ड होते हैं)। Session.append में अभी भी `ignorable` चैनल नहीं है, इसलिए टिकाऊ लेखन छोड़े जाते हैं और स्विच प्रक्रिया-स्थानीय रहता है - व्यवहार अपरिवर्तित। `doublecheck.gate` सेटिंग्स नेमस्पेस अभी भी एक कमज़ोर इंटरफ़ेस है (ज्ञात सीमाएँ देखें)।
|
|
228
229
|
- **वैकल्पिक इंटरफ़ेस।** `doublecheck.gate` सेटिंग्स नेमस्पेस केवल तब पंजीकृत होता है जब सेटिंग्स सेवा माउंट हो; `/gate status` की प्लान-मोड पंक्ति वैकल्पिक `ctx.planMode` पढ़ती है (इसके बिना `unknown` दिखाती है); प्रतिकूल समीक्षा को `ctx.subagents` चाहिए; सत्यापन को `workflowEngine` चाहिए।
|
|
229
230
|
- **स्थानीय अवनति।** जब dsh-auto-review अनुपस्थित हो या इस सत्र में उसके कोई निर्णय रिकॉर्ड न हों, तो `gate.review.engine: auto` स्थानीय समीक्षक पर घट जाता है — रिपोर्ट निर्णय गढ़ने के बजाय कारण बताती है।
|
|
230
231
|
- **dsh-eval साक्ष्य फ़ाइल-आधारित है।** dsh-auto-review का मूल्यांकन इंजन (`dsh-eval`) अपने prompt-regression / stress / fairness परिणाम कार्यक्षेत्र रिपोर्ट फ़ाइल में लिखता है, सत्र लॉग में नहीं। `gate.tests.evalReports.enabled` उस फ़ाइल को मोड़ता है (डिफ़ॉल्ट रूप से बंद; अनुपस्थित होने पर छोड़ देता है) और मोड़ी गई गणनाएँ टिकाऊ `doublecheck/gate` रिकॉर्ड पर चलती हैं, ताकि तयशुदा रन फिर भी रीप्ले हो सके।
|
|
@@ -253,42 +254,46 @@ pnpm run pack:check # build + pack the tarball
|
|
|
253
254
|
|
|
254
255
|
## PerryLink DSH Plugin Family
|
|
255
256
|
|
|
256
|
-
यह प्रोजेक्ट [PerryLink](https://github.com/PerryLink) द्वारा अनुरक्षित [
|
|
257
|
+
यह प्रोजेक्ट [PerryLink](https://github.com/PerryLink) द्वारा अनुरक्षित [37 DeepSeek Harness प्लगइनों](https://github.com/PerryLink) में से एक है। अगर यह आपकी मदद करता है, तो बाकी भी करेंगे:
|
|
257
258
|
|
|
258
259
|
| Plugin | One-liner |
|
|
259
260
|
|---|---|
|
|
260
|
-
| **[dsh-
|
|
261
|
-
| **[dsh-
|
|
262
|
-
| **[dsh-
|
|
263
|
-
| **[dsh-
|
|
264
|
-
| **[dsh-
|
|
265
|
-
| **[dsh-
|
|
266
|
-
| **[dsh-
|
|
267
|
-
| **[dsh-
|
|
268
|
-
| **[dsh-
|
|
269
|
-
| **[dsh-
|
|
270
|
-
| **[dsh-
|
|
271
|
-
| **[dsh-
|
|
272
|
-
| **[dsh-
|
|
273
|
-
| **[dsh-
|
|
274
|
-
| **[dsh-
|
|
275
|
-
| **[dsh-
|
|
276
|
-
| **[dsh-
|
|
277
|
-
| **[dsh-
|
|
278
|
-
| **[dsh-
|
|
279
|
-
| **[dsh-
|
|
280
|
-
| **[dsh-
|
|
281
|
-
| **[dsh-
|
|
282
|
-
| **[dsh-
|
|
283
|
-
| **[dsh-
|
|
284
|
-
| **[dsh-
|
|
285
|
-
| **[dsh-
|
|
286
|
-
| **[dsh-
|
|
287
|
-
| **[dsh-
|
|
288
|
-
| **[dsh-
|
|
289
|
-
| **[dsh-
|
|
290
|
-
| **[dsh-
|
|
291
|
-
| **[dsh-
|
|
261
|
+
| **[dsh-auto-review](https://github.com/PerryLink/dsh-auto-review)** | अनुमोदन श्रृंखला पर द्वितीय-मॉडल स्वतः-समीक्षा, डिफ़ॉल्ट रूप से विफल-बंद | |
|
|
262
|
+
| **[dsh-background-agents](https://github.com/PerryLink/dsh-background-agents)** | वेब UI साइडबार, संदेश और अवरोधन के साथ टिकाऊ पृष्ठभूमि चाइल्ड एजेंट | |
|
|
263
|
+
| **[dsh-budget](https://github.com/PerryLink/dsh-budget)** | DeepSeek Harness के लिए लागत प्रशासन: बजट, कार्बन और विलंबता एक पैनल में। | |
|
|
264
|
+
| **[dsh-checkpoint-rewind](https://github.com/PerryLink/dsh-checkpoint-rewind)** | Claude Code /rewind-समतुल्य: स्नैपशॉट, सत्र फ़ॉर्क, एक-बार पुनर्स्थापना | |
|
|
265
|
+
| **[dsh-claude-move](https://github.com/PerryLink/dsh-claude-move)** | Claude Code सत्र, मेमोरी, कौशल और CLAUDE.md को DSH में स्थानांतरित करें | |
|
|
266
|
+
| **[dsh-click](https://github.com/PerryLink/dsh-click)** | DeepSeek Harness के लिए क्रॉस-प्लेटफ़ॉर्म नेटिव डेस्कटॉप नियंत्रण — Windows पहले। | |
|
|
267
|
+
| **[dsh-composer-history](https://github.com/PerryLink/dsh-composer-history)** | वेब कंपोज़र के लिए टर्मिनल-शैली इनपुट इतिहास: तीर, Ctrl+R खोज | |
|
|
268
|
+
| **[dsh-data-quality](https://github.com/PerryLink/dsh-data-quality)** | डेटासेट गुणवत्ता जाँच व उद्धरण सत्यापन (यहाँ उपभोग किया गया वैकल्पिक संख्या-सेतु) | |
|
|
269
|
+
| **[dsh-defend](https://github.com/PerryLink/dsh-defend)** | DeepSeek Harness के लिए प्रॉम्प्ट-इंजेक्शन, जेलब्रेक और सीक्रेट-लीक रक्षा। | |
|
|
270
|
+
| **[dsh-draw](https://github.com/PerryLink/dsh-draw)** | DeepSeek Harness के लिए एकीकृत स्थैतिक-छवि निर्माण रूटिंग। | |
|
|
271
|
+
| **[dsh-fast](https://github.com/PerryLink/dsh-fast)** | DeepSeek Harness के लिए रीड-ओनली प्रदर्शन डायग्नोस्टिक्स। | |
|
|
272
|
+
| **[dsh-fund-research](https://github.com/PerryLink/dsh-fund-research)** | चीनी सार्वजनिक म्यूचुअल फंड के लिए नियतात्मक अनुसंधान रिपोर्ट | |
|
|
273
|
+
| **[dsh-github](https://github.com/PerryLink/dsh-github)** | DSH के लिए GitHub PR/issues एकीकरण, हर लेखन अनुमोदन-द्वारित | |
|
|
274
|
+
| **[dsh-industry-research](https://github.com/PerryLink/dsh-industry-research)** | उद्योग-अनुसंधान ऑर्केस्ट्रेशन जो इस प्लगिन के `ctx.researchReport.assemble` से डिलीवरेबल सील करता है | |
|
|
275
|
+
| **[dsh-library](https://github.com/PerryLink/dsh-library)** | DeepSeek Harness के लिए स्थानीय दस्तावेज़ ज्ञानकोश। | |
|
|
276
|
+
| **[dsh-local-ai](https://github.com/PerryLink/dsh-local-ai)** | DeepSeek Harness के लिए स्थानीय-मॉडल (Ollama) एकीकरण। | |
|
|
277
|
+
| **[dsh-lsp-actions](https://github.com/PerryLink/dsh-lsp-actions)** | भाषा सर्वरों पर LSP निदान, फ़ॉर्मेटिंग, पूर्णता, कोड क्रियाएँ और नाम बदलना | |
|
|
278
|
+
| **[dsh-mask](https://github.com/PerryLink/dsh-mask)** | PII मास्किंग मिडलवेयर: मॉडल सीमा पर अनाम करें, डिस्प्ले लेयर पर पुनर्स्थापित करें | |
|
|
279
|
+
| **[dsh-mcp-panel](https://github.com/PerryLink/dsh-mcp-panel)** | केवल-पढ़ने वाला MCP रनटाइम पैनल: /mcp कमांड + स्थिति, टूल और त्रुटियों वाला Settings टैब | |
|
|
280
|
+
| **[dsh-memento](https://github.com/PerryLink/dsh-memento)** | अनुमोदन-द्वारित क्रॉस-सत्र मेमोरी: ctx.memory सीम + SQLite + मेमोरी टूल | |
|
|
281
|
+
| **[dsh-observe](https://github.com/PerryLink/dsh-observe)** | DeepSeek Harness के लिए OpenTelemetry और Langfuse अवलोकनीयता निर्यातक। | |
|
|
282
|
+
| **[dsh-output-styles](https://github.com/PerryLink/dsh-output-styles)** | Claude Code outputStyles-समतुल्य रनटाइम शैली बदलाव | |
|
|
283
|
+
| **[dsh-reach](https://github.com/PerryLink/dsh-reach)** | मल्टी-चैनल अनुमोदन/प्रश्न ब्रिज: WeChat/Telegram/Feishu, सत्र कंसोल |
|
|
284
|
+
| **[dsh-permission-rules](https://github.com/PerryLink/dsh-permission-rules)** | ऑडिट के साथ Claude Code-शैली घोषणात्मक allow/deny/ask अनुमति नियम | |
|
|
285
|
+
| **[dsh-personal-directive](https://github.com/PerryLink/dsh-personal-directive)** | शीर्ष-बार टॉगल के साथ व्यक्तिगत निर्देश इंजेक्टर (फ्रेमवर्क संस्करण) |
|
|
286
|
+
| **[dsh-plugin-guide](https://github.com/PerryLink/dsh-plugin-guide)** | माँग पर एजेंट कौशल के रूप में प्लगइन-विकास ज्ञान आधार | |
|
|
287
|
+
| **[dsh-research-report](https://github.com/PerryLink/dsh-research-report)** | सामग्री-पता साक्ष्य और सीलबंद संस्करणों वाला सत्यापन-योग्य अनुसंधान-रिपोर्ट इंजन | |
|
|
288
|
+
| **[dsh-score](https://github.com/PerryLink/dsh-score)** | DeepSeek Harness प्लगिनों की बहु-आयामी गुणवत्ता स्कोरिंग। | |
|
|
289
|
+
| **[dsh-session-pin](https://github.com/PerryLink/dsh-session-pin)** | टिकाऊ क्रम के साथ वेब साइडबार में सत्र पिन करें | |
|
|
290
|
+
| **[dsh-session-sync](https://github.com/PerryLink/dsh-session-sync)** | DeepSeek Harness के लिए क्रॉस-डिवाइस सत्र सिंक — आपके सत्र स्टोर का एक समर्पित git मिरर। | |
|
|
291
|
+
| **[dsh-skill-pack-security](https://github.com/PerryLink/dsh-skill-pack-security)** | सुरक्षा-ऑडिट कौशल पैक: गुप्त स्कैन, निर्भरता और आपूर्ति-श्रृंखला समीक्षा | |
|
|
292
|
+
| **[dsh-talk](https://github.com/PerryLink/dsh-talk)** | DeepSeek Harness के लिए आवाज़-प्रथम सत्र लूप: बोलें और उत्तर सुनें। | |
|
|
293
|
+
| **[dsh-test-drive](https://github.com/PerryLink/dsh-test-drive)** | DeepSeek Harness प्लगिनों के लिए पृथक इंस्टॉल-एंड-स्मोक टेस्ट ड्राइव। | |
|
|
294
|
+
| **[dsh-ticktick](https://github.com/PerryLink/dsh-ticktick)** | TickTick/Dida365 कार्य ब्रिज: सत्र-हेडर पैनल + 11 टूल |
|
|
295
|
+
| **[dsh-translate](https://github.com/PerryLink/dsh-translate)** | DeepSeek Harness के लिए वेंडर पैरामीटर अनुवाद और नियतात्मक JSON मरम्मत। | |
|
|
296
|
+
| **[dsh-wechat](https://github.com/PerryLink/dsh-wechat)** | WeChat ↔ DSH ब्रिज (Tencent iLink bot): टेक्स्ट/इमेज/फ़ाइल/आवाज़, चैट में अनुमोदन |
|
|
292
297
|
|
|
293
298
|
### DSH Desktop मार्केट से इंस्टॉल करें
|
|
294
299
|
|
package/README.md
CHANGED
|
@@ -9,7 +9,7 @@
|
|
|
9
9
|
*Requirements get interrogated before the first edit; delivery is proven, never claimed.*
|
|
10
10
|
|
|
11
11
|
[](LICENSE)
|
|
12
|
-
[](https://github.com/topics/dsh-plugin)
|
|
13
13
|
[](#)
|
|
14
14
|
[](https://github.com/PerryLink/dsh-doublecheck/actions)
|
|
15
15
|
[](https://github.com/PerryLink/dsh-doublecheck/releases)
|
|
@@ -26,7 +26,7 @@
|
|
|
26
26
|
|
|
27
27
|
| Surface | Status |
|
|
28
28
|
|---|---|
|
|
29
|
-
| Harness | DeepSeek Harness `dsh-v0.1.
|
|
29
|
+
| Harness | DeepSeek Harness `dsh-v0.1.5-alpha.1`. Verified 2026-09-09 against the `dsh-v0.1.5-alpha.1` master checkout (full gate chain + profile install smoke); the published `0.1.2-rc.1` pin line stays supported. |
|
|
30
30
|
| Node | `^22.19.0 \|\| >=24.0.0` |
|
|
31
31
|
| Platforms | All (pure host; no native code, no direct network requests of its own) |
|
|
32
32
|
| Model | Any (the guard itself never calls a model; the critic and reviewer phases run as harness subagents) |
|
|
@@ -209,7 +209,7 @@ The CLI only serializes the already-settled `GateState` — it never re-runs the
|
|
|
209
209
|
|
|
210
210
|
## Permissions & data
|
|
211
211
|
|
|
212
|
-
- **Reads**: the session log (`tool/call` / `tool/result` / `tool/
|
|
212
|
+
- **Reads**: the session log (`tool/call` / `tool/result` / `tool/ptc-dispatch`, injected `user/message` sources, and the foreign `autoReview/*` verdict records) in-process only; the optional plan-mode service state. PTC sub-dispatches carry the predecessor `tool/code-dispatch` label on hosts before the V3 rename; both labels fold identically.
|
|
213
213
|
- **Writes**: `doublecheck-spec.md`, `doublecheck-report.md`, `gate-report.md`, and `gate-report.json` in the session workspace (paths configurable) through the `ctx.fs` seam; the durable `doublecheck/state` and `doublecheck/gate` session events.
|
|
214
214
|
- **Model calls**: the gate's consistency and local-review phases (one subagent each per `/gate run`), the optional adversary review, and the `doublecheck_report` verification workflow start subagent runs; nothing else calls a model or the network.
|
|
215
215
|
- **Never touched**: credentials, environment variables, or any file outside the session workspace. The workshop manifest declares `filesystem:read` and `filesystem:write` only. Gate reports carry counts, ids, and verdicts only; recognized secrets in reviewer texts are redacted before storage or display.
|
|
@@ -226,6 +226,7 @@ The CLI only serializes the already-settled `GateState` — it never re-runs the
|
|
|
226
226
|
|
|
227
227
|
- **Durable writes.** `/doublecheck on\|off` → `doublecheck/state` and `/gate run` → `doublecheck/gate` ride the host's `ignorable` append surface (post-rc.6 through `0.1.1-rc.2`). On hosts without that surface (rc.6/rc.8, and `0.1.2-alpha.1`, which removed the envelope — `0.1.2-rc.1` restores the field for stored-log read compatibility only and still cannot stamp it), the writes are skipped and the switch stays process-local.
|
|
228
228
|
0.1.2-rc.1 (adapted 2026-09-02): the session envelope keeps its ignorable field for stored-log read compatibility only - Session.append still cannot stamp it, so audit-gate behavior is unchanged.
|
|
229
|
+
0.1.5-alpha.1 (adapted 2026-09-09): session format V3 renames the durable sub-dispatch event `tool/code-dispatch` to `tool/ptc-dispatch` (payload unchanged; both labels fold identically). Session.append still exposes no `ignorable` channel, so durable writes stay skipped and the switch stays process-local - behavior unchanged. The `doublecheck.gate` settings namespace remains a weak seam (see Known limitations).
|
|
229
230
|
- **Optional seams.** The `doublecheck.gate` settings namespace registers only when the settings service is mounted; the `/gate status` plan-mode line reads the optional `ctx.planMode` (shows `unknown` without it); the adversary review needs `ctx.subagents`; verification needs `workflowEngine`.
|
|
230
231
|
- **Local degrade.** `gate.review.engine: auto` degrades to the local reviewer when dsh-auto-review is absent or has no verdict records this session — the report names the reason instead of inventing a verdict.
|
|
231
232
|
- **dsh-eval evidence is file-based.** The dsh-auto-review eval engine (`dsh-eval`) writes its prompt-regression / stress / fairness results to a workspace report file, not the session log. `gate.tests.evalReports.enabled` folds that file (off by default; skips when absent) and the folded counts ride the durable `doublecheck/gate` record so a settled run still replays.
|
|
@@ -254,42 +255,46 @@ pnpm run pack:check # build + pack the tarball
|
|
|
254
255
|
|
|
255
256
|
## PerryLink DSH Plugin Family
|
|
256
257
|
|
|
257
|
-
This project is one of the [
|
|
258
|
+
This project is one of the [37 DeepSeek Harness plugins](https://github.com/PerryLink) maintained by [PerryLink](https://github.com/PerryLink). If this one helps you, the others likely will too:
|
|
258
259
|
|
|
259
260
|
| Plugin | One-liner |
|
|
260
261
|
|---|---|
|
|
261
|
-
| **[dsh-
|
|
262
|
-
| **[dsh-
|
|
263
|
-
| **[dsh-
|
|
264
|
-
| **[dsh-
|
|
265
|
-
| **[dsh-
|
|
266
|
-
| **[dsh-
|
|
267
|
-
| **[dsh-
|
|
268
|
-
| **[dsh-
|
|
269
|
-
| **[dsh-
|
|
270
|
-
| **[dsh-
|
|
271
|
-
| **[dsh-
|
|
272
|
-
| **[dsh-
|
|
273
|
-
| **[dsh-
|
|
274
|
-
| **[dsh-
|
|
275
|
-
| **[dsh-
|
|
276
|
-
| **[dsh-
|
|
277
|
-
| **[dsh-
|
|
278
|
-
| **[dsh-
|
|
279
|
-
| **[dsh-
|
|
280
|
-
| **[dsh-
|
|
281
|
-
| **[dsh-
|
|
282
|
-
| **[dsh-
|
|
283
|
-
| **[dsh-
|
|
284
|
-
| **[dsh-
|
|
285
|
-
| **[dsh-
|
|
286
|
-
| **[dsh-
|
|
287
|
-
| **[dsh-
|
|
288
|
-
| **[dsh-
|
|
289
|
-
| **[dsh-
|
|
290
|
-
| **[dsh-
|
|
291
|
-
| **[dsh-
|
|
292
|
-
| **[dsh-
|
|
262
|
+
| **[dsh-auto-review](https://github.com/PerryLink/dsh-auto-review)** | Second-model auto-review on the approval chain, fail-closed by default | |
|
|
263
|
+
| **[dsh-background-agents](https://github.com/PerryLink/dsh-background-agents)** | Durable background child agents with a Web UI sidebar, messaging and interrupt | |
|
|
264
|
+
| **[dsh-budget](https://github.com/PerryLink/dsh-budget)** | Cost governance for DeepSeek Harness: budgets, carbon, and latency in one panel. | |
|
|
265
|
+
| **[dsh-checkpoint-rewind](https://github.com/PerryLink/dsh-checkpoint-rewind)** | Claude Code /rewind-equivalent: snapshots, session forks, one-shot restore | |
|
|
266
|
+
| **[dsh-claude-move](https://github.com/PerryLink/dsh-claude-move)** | Migrate Claude Code sessions, memory, skills and CLAUDE.md into DSH | |
|
|
267
|
+
| **[dsh-click](https://github.com/PerryLink/dsh-click)** | Cross-platform native desktop control for DeepSeek Harness — Windows first. | |
|
|
268
|
+
| **[dsh-composer-history](https://github.com/PerryLink/dsh-composer-history)** | Terminal-style input history for the web composer: arrows, Ctrl+R search | |
|
|
269
|
+
| **[dsh-data-quality](https://github.com/PerryLink/dsh-data-quality)** | Dataset quality checks and citation cross-checks (the optional numeric bridge consumed here) | |
|
|
270
|
+
| **[dsh-defend](https://github.com/PerryLink/dsh-defend)** | Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness. | |
|
|
271
|
+
| **[dsh-draw](https://github.com/PerryLink/dsh-draw)** | Unified static-image generation routing for DeepSeek Harness. | |
|
|
272
|
+
| **[dsh-fast](https://github.com/PerryLink/dsh-fast)** | Read-only performance diagnostics for DeepSeek Harness. | |
|
|
273
|
+
| **[dsh-fund-research](https://github.com/PerryLink/dsh-fund-research)** | Deterministic research reports for Chinese public mutual funds | |
|
|
274
|
+
| **[dsh-github](https://github.com/PerryLink/dsh-github)** | GitHub PR/issues integration for DSH, every write gated by approval | |
|
|
275
|
+
| **[dsh-industry-research](https://github.com/PerryLink/dsh-industry-research)** | Industry research orchestration that seals its deliverables through this plugin's `ctx.researchReport.assemble` | |
|
|
276
|
+
| **[dsh-library](https://github.com/PerryLink/dsh-library)** | Local document knowledge base for DeepSeek Harness. | |
|
|
277
|
+
| **[dsh-local-ai](https://github.com/PerryLink/dsh-local-ai)** | Local-model (Ollama) integration for DeepSeek Harness. | |
|
|
278
|
+
| **[dsh-lsp-actions](https://github.com/PerryLink/dsh-lsp-actions)** | LSP diagnostics, formatting, completion, code actions and rename over language servers | |
|
|
279
|
+
| **[dsh-mask](https://github.com/PerryLink/dsh-mask)** | PII masking middleware: anonymize at the model boundary, restore at the display layer | |
|
|
280
|
+
| **[dsh-mcp-panel](https://github.com/PerryLink/dsh-mcp-panel)** | Read-only MCP runtime panel: /mcp command + Settings tab with status, tools and errors | |
|
|
281
|
+
| **[dsh-memento](https://github.com/PerryLink/dsh-memento)** | Approval-gated cross-session memory: ctx.memory seam + SQLite + memory tool | |
|
|
282
|
+
| **[dsh-observe](https://github.com/PerryLink/dsh-observe)** | OpenTelemetry and Langfuse observability exporter for DeepSeek Harness. | |
|
|
283
|
+
| **[dsh-output-styles](https://github.com/PerryLink/dsh-output-styles)** | Claude Code outputStyles-equivalent runtime style switching | |
|
|
284
|
+
| **[dsh-reach](https://github.com/PerryLink/dsh-reach)** | Multi-channel approval/question bridge: WeChat/Telegram/Feishu, session console |
|
|
285
|
+
| **[dsh-permission-rules](https://github.com/PerryLink/dsh-permission-rules)** | Claude Code-style declarative allow/deny/ask permission rules with audit | |
|
|
286
|
+
| **[dsh-personal-directive](https://github.com/PerryLink/dsh-personal-directive)** | Personal directive injector with top-bar toggle (framework edition) |
|
|
287
|
+
| **[dsh-plugin-guide](https://github.com/PerryLink/dsh-plugin-guide)** | Plugin-development knowledge base as an on-demand agent skill | |
|
|
288
|
+
| **[dsh-research-report](https://github.com/PerryLink/dsh-research-report)** | Verifiable research-report engine: content-addressed evidence ledger and sealed versions | |
|
|
289
|
+
| **[dsh-score](https://github.com/PerryLink/dsh-score)** | Multi-dimensional quality scoring for DeepSeek Harness plugins. | |
|
|
290
|
+
| **[dsh-session-pin](https://github.com/PerryLink/dsh-session-pin)** | Pin sessions in the Web sidebar with durable ordering | |
|
|
291
|
+
| **[dsh-session-sync](https://github.com/PerryLink/dsh-session-sync)** | Cross-device session sync for DeepSeek Harness — a dedicated git mirror of your session store. | |
|
|
292
|
+
| **[dsh-skill-pack-security](https://github.com/PerryLink/dsh-skill-pack-security)** | Security-audit skill pack: secret scan, dependency and supply-chain review | |
|
|
293
|
+
| **[dsh-talk](https://github.com/PerryLink/dsh-talk)** | Voice-first session loop for DeepSeek Harness: talk to it, hear it answer. | |
|
|
294
|
+
| **[dsh-test-drive](https://github.com/PerryLink/dsh-test-drive)** | Isolated install-and-smoke test drives for DeepSeek Harness plugins. | |
|
|
295
|
+
| **[dsh-ticktick](https://github.com/PerryLink/dsh-ticktick)** | TickTick/Dida365 task bridge: session-header panel + 11 tools |
|
|
296
|
+
| **[dsh-translate](https://github.com/PerryLink/dsh-translate)** | Vendor parameter translation and deterministic JSON repair for DeepSeek Harness. | |
|
|
297
|
+
| **[dsh-wechat](https://github.com/PerryLink/dsh-wechat)** | WeChat ↔ DSH bridge (Tencent iLink bot): text/image/file/voice, approvals in chat |
|
|
293
298
|
|
|
294
299
|
### Install from the DSH Desktop Market
|
|
295
300
|
|
package/README.pt.md
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
*Os requisitos são interrogados antes da primeira edição; a entrega é comprovada, nunca afirmada.*
|
|
9
9
|
|
|
10
10
|
[](LICENSE)
|
|
11
|
-
[](https://github.com/topics/dsh-plugin)
|
|
12
12
|
[](#)
|
|
13
13
|
[](https://github.com/PerryLink/dsh-doublecheck/actions)
|
|
14
14
|
[](https://github.com/PerryLink/dsh-doublecheck/releases)
|
|
@@ -25,7 +25,7 @@
|
|
|
25
25
|
|
|
26
26
|
| Superfície | Status |
|
|
27
27
|
|---|---|
|
|
28
|
-
| Harness | DeepSeek Harness `dsh-v0.1.
|
|
28
|
+
| Harness | DeepSeek Harness `dsh-v0.1.5-alpha.1`. Verificado em 2026-09-09 contra o checkout master `dsh-v0.1.5-alpha.1` (cadeia completa de portões + smoke de instalação do perfil); a linha publicada `0.1.2-rc.1` continua suportada. |
|
|
29
29
|
| Node | `^22.19.0 \|\| >=24.0.0` |
|
|
30
30
|
| Plataformas | Todas (host puro; sem código nativo, sem requisições de rede diretas próprias) |
|
|
31
31
|
| Modelo | Qualquer (o guard nunca chama um modelo; as fases de crítico e revisor rodam como subagentes do harness) |
|
|
@@ -208,7 +208,7 @@ O CLI apenas serializa o `GateState` já assentado — nunca reexecuta a porta d
|
|
|
208
208
|
|
|
209
209
|
## Permissões e dados
|
|
210
210
|
|
|
211
|
-
- **Lê**: o registro de sessão (`tool/call` / `tool/result` / `tool/
|
|
211
|
+
- **Lê**: o registro de sessão (`tool/call` / `tool/result` / `tool/ptc-dispatch`, fontes `user/message` injetadas e os registros de veredicto alheios `autoReview/*`) somente em processo; o estado opcional do serviço de modo plano. Antes da renomeação da V3, o host registra os subenvios PTC com o rótulo predecessor `tool/code-dispatch`; os dois rótulos são dobrados de forma idêntica.
|
|
212
212
|
- **Escreve**: `doublecheck-spec.md`, `doublecheck-report.md` e `gate-report.md` no workspace da sessão (caminhos configuráveis) por meio da interface `ctx.fs`; os eventos de sessão duráveis `doublecheck/state` e `doublecheck/gate`.
|
|
213
213
|
- **Chamadas a modelo**: as fases de consistência e revisão local do portão (um subagente cada por `/gate run`), a revisão adversarial opcional e o fluxo de verificação de `doublecheck_report` iniciam execuções de subagente; nada mais chama um modelo ou a rede.
|
|
214
214
|
- **Nunca toca**: credenciais, variáveis de ambiente ou qualquer arquivo fora do workspace da sessão. O manifesto do workshop declara apenas `filesystem:read` e `filesystem:write`. Os relatórios do portão carregam apenas contagens, ids e veredictos; segredos reconhecidos nos textos do revisor são redigidos antes de armazenar ou exibir.
|
|
@@ -225,6 +225,7 @@ O CLI apenas serializa o `GateState` já assentado — nunca reexecuta a porta d
|
|
|
225
225
|
|
|
226
226
|
- **Escritas duráveis.** `/doublecheck on\|off` → `doublecheck/state` e `/gate run` → `doublecheck/gate` precisam da superfície de append `ignorable` do host (pós-rc.6 até `0.1.1-rc.2`). Em hosts sem essa superfície (rc.6/rc.8 e `0.1.2-alpha.1`, que removeu o envelope — `0.1.2-rc.1` restaura o campo apenas para compatibilidade de leitura de logs armazenados e ainda não consegue estampá-lo), as escritas são omitidas e o interruptor permanece em processo.
|
|
227
227
|
0.1.2-rc.1 (adaptado em 2026-09-02): o envelope de sessão mantém seu campo ignorable apenas para compatibilidade de leitura de logs armazenados - o Session.append ainda não consegue estampá-lo, então o comportamento da porta não muda.
|
|
228
|
+
0.1.5-alpha.1 (adaptado em 2026-09-09): o formato de sessão V3 renomeia o evento durável de subenvio `tool/code-dispatch` para `tool/ptc-dispatch` (carga útil inalterada; os dois rótulos são dobrados de forma idêntica). O Session.append continua sem canal `ignorable`, então as escritas duráveis são omitidas e o interruptor permanece em processo - comportamento inalterado. O namespace de configurações `doublecheck.gate` continua sendo uma interface fraca (ver Limitações conhecidas).
|
|
228
229
|
- **Interfaces opcionais.** O namespace de configurações `doublecheck.gate` é registrado apenas quando o serviço de configurações está montado; a linha de modo plano de `/gate status` lê o `ctx.planMode` opcional (mostra `unknown` sem ele); a revisão adversarial precisa de `ctx.subagents`; a verificação precisa de `workflowEngine`.
|
|
229
230
|
- **Degradação local.** `gate.review.engine: auto` degrada para o revisor local quando o dsh-auto-review está ausente ou não tem registros de veredicto nesta sessão — o relatório nomeia a razão em vez de inventar um veredicto.
|
|
230
231
|
- **A evidência dsh-eval é baseada em arquivos.** O motor de avaliação do dsh-auto-review (`dsh-eval`) grava seus resultados de regressão de prompt / estresse / equidade em um arquivo de relatório do espaço de trabalho, não no registro de sessão. `gate.tests.evalReports.enabled` dobra esse arquivo (desativado por padrão; pula quando ausente) e as contagens dobradas viajam no registro durável `doublecheck/gate` para que uma execução assentada ainda seja reproduzível.
|
|
@@ -253,42 +254,46 @@ pnpm run pack:check # build + pack the tarball
|
|
|
253
254
|
|
|
254
255
|
## PerryLink DSH Plugin Family
|
|
255
256
|
|
|
256
|
-
Este projeto é um dos [
|
|
257
|
+
Este projeto é um dos [37 plugins de DeepSeek Harness](https://github.com/PerryLink) mantidos por [PerryLink](https://github.com/PerryLink). Se este ajuda você, os outros provavelmente também:
|
|
257
258
|
|
|
258
259
|
| Plugin | One-liner |
|
|
259
260
|
|---|---|
|
|
260
|
-
| **[dsh-
|
|
261
|
-
| **[dsh-
|
|
262
|
-
| **[dsh-
|
|
263
|
-
| **[dsh-
|
|
264
|
-
| **[dsh-
|
|
265
|
-
| **[dsh-
|
|
266
|
-
| **[dsh-
|
|
267
|
-
| **[dsh-
|
|
268
|
-
| **[dsh-
|
|
269
|
-
| **[dsh-
|
|
270
|
-
| **[dsh-
|
|
271
|
-
| **[dsh-
|
|
272
|
-
| **[dsh-
|
|
273
|
-
| **[dsh-
|
|
274
|
-
| **[dsh-
|
|
275
|
-
| **[dsh-
|
|
276
|
-
| **[dsh-
|
|
277
|
-
| **[dsh-
|
|
278
|
-
| **[dsh-
|
|
279
|
-
| **[dsh-
|
|
280
|
-
| **[dsh-
|
|
281
|
-
| **[dsh-
|
|
282
|
-
| **[dsh-
|
|
283
|
-
| **[dsh-
|
|
284
|
-
| **[dsh-
|
|
285
|
-
| **[dsh-
|
|
286
|
-
| **[dsh-
|
|
287
|
-
| **[dsh-
|
|
288
|
-
| **[dsh-
|
|
289
|
-
| **[dsh-
|
|
290
|
-
| **[dsh-
|
|
291
|
-
| **[dsh-
|
|
261
|
+
| **[dsh-auto-review](https://github.com/PerryLink/dsh-auto-review)** | Auto-revisão de segundo modelo na cadeia de aprovação, com falha fechada por padrão | |
|
|
262
|
+
| **[dsh-background-agents](https://github.com/PerryLink/dsh-background-agents)** | Agentes filhos em segundo plano duráveis com barra lateral de UI web, mensagens e interrupção | |
|
|
263
|
+
| **[dsh-budget](https://github.com/PerryLink/dsh-budget)** | Governança de custos para DeepSeek Harness: orçamentos, carbono e latência em um painel. | |
|
|
264
|
+
| **[dsh-checkpoint-rewind](https://github.com/PerryLink/dsh-checkpoint-rewind)** | Equivalente ao /rewind do Claude Code: instantâneos, bifurcações de sessão, restauração de uso único | |
|
|
265
|
+
| **[dsh-claude-move](https://github.com/PerryLink/dsh-claude-move)** | Migre sessões, memória, habilidades e CLAUDE.md do Claude Code para o DSH | |
|
|
266
|
+
| **[dsh-click](https://github.com/PerryLink/dsh-click)** | Controle de desktop nativo multiplataforma para DeepSeek Harness — Windows primeiro. | |
|
|
267
|
+
| **[dsh-composer-history](https://github.com/PerryLink/dsh-composer-history)** | Histórico de entrada estilo terminal para o compositor web: setas, busca Ctrl+R | |
|
|
268
|
+
| **[dsh-data-quality](https://github.com/PerryLink/dsh-data-quality)** | Verificações de qualidade de datasets e verificação de citações (a ponte numérica opcional consumida aqui) | |
|
|
269
|
+
| **[dsh-defend](https://github.com/PerryLink/dsh-defend)** | Defesa contra injeção de prompt, jailbreak e vazamento de segredos para DeepSeek Harness. | |
|
|
270
|
+
| **[dsh-draw](https://github.com/PerryLink/dsh-draw)** | Roteamento unificado de geração de imagens estáticas para DeepSeek Harness. | |
|
|
271
|
+
| **[dsh-fast](https://github.com/PerryLink/dsh-fast)** | Diagnóstico de desempenho só de leitura para DeepSeek Harness. | |
|
|
272
|
+
| **[dsh-fund-research](https://github.com/PerryLink/dsh-fund-research)** | Relatórios de pesquisa deterministas para fundos mútuos públicos chineses | |
|
|
273
|
+
| **[dsh-github](https://github.com/PerryLink/dsh-github)** | Integração de PR/issues do GitHub para o DSH, cada escrita controlada por aprovação | |
|
|
274
|
+
| **[dsh-industry-research](https://github.com/PerryLink/dsh-industry-research)** | Orquestração de pesquisa setorial que sela as suas entregas através do `ctx.researchReport.assemble` deste plugin | |
|
|
275
|
+
| **[dsh-library](https://github.com/PerryLink/dsh-library)** | Base de conhecimento documental local para DeepSeek Harness. | |
|
|
276
|
+
| **[dsh-local-ai](https://github.com/PerryLink/dsh-local-ai)** | Integração de modelos locais (Ollama) para DeepSeek Harness. | |
|
|
277
|
+
| **[dsh-lsp-actions](https://github.com/PerryLink/dsh-lsp-actions)** | Diagnósticos, formatação, autocompletar, ações de código e renomeação LSP sobre servidores de linguagem | |
|
|
278
|
+
| **[dsh-mask](https://github.com/PerryLink/dsh-mask)** | Middleware de mascaramento de PII: anonimiza no limite do modelo, restaura na camada de exibição | |
|
|
279
|
+
| **[dsh-mcp-panel](https://github.com/PerryLink/dsh-mcp-panel)** | Painel de tempo de execução MCP somente leitura: comando /mcp + aba Settings com status, ferramentas e erros | |
|
|
280
|
+
| **[dsh-memento](https://github.com/PerryLink/dsh-memento)** | Memória entre sessões controlada por aprovação: costura ctx.memory + SQLite + ferramenta de memória | |
|
|
281
|
+
| **[dsh-observe](https://github.com/PerryLink/dsh-observe)** | Exportador de observabilidade OpenTelemetry e Langfuse para DeepSeek Harness. | |
|
|
282
|
+
| **[dsh-output-styles](https://github.com/PerryLink/dsh-output-styles)** | Troca de estilo em tempo de execução equivalente ao outputStyles do Claude Code | |
|
|
283
|
+
| **[dsh-reach](https://github.com/PerryLink/dsh-reach)** | Ponte multicanal de aprovação/perguntas: WeChat/Telegram/Feishu, console de sessão |
|
|
284
|
+
| **[dsh-permission-rules](https://github.com/PerryLink/dsh-permission-rules)** | Regras de permissão declarativas allow/deny/ask estilo Claude Code com auditoria | |
|
|
285
|
+
| **[dsh-personal-directive](https://github.com/PerryLink/dsh-personal-directive)** | Injetor de diretivas pessoais com alternância na barra superior (edição framework) |
|
|
286
|
+
| **[dsh-plugin-guide](https://github.com/PerryLink/dsh-plugin-guide)** | Base de conhecimento de desenvolvimento de plugins como habilidade de agente sob demanda | |
|
|
287
|
+
| **[dsh-research-report](https://github.com/PerryLink/dsh-research-report)** | Motor de relatórios de pesquisa verificáveis com evidência endereçada por conteúdo | |
|
|
288
|
+
| **[dsh-score](https://github.com/PerryLink/dsh-score)** | Pontuação de qualidade multidimensional para plugins de DeepSeek Harness. | |
|
|
289
|
+
| **[dsh-session-pin](https://github.com/PerryLink/dsh-session-pin)** | Fixe sessões na barra lateral web com ordenação durável | |
|
|
290
|
+
| **[dsh-session-sync](https://github.com/PerryLink/dsh-session-sync)** | Sincronização de sessões entre dispositivos para DeepSeek Harness — um espelho git dedicado do seu armazenamento de sessões. | |
|
|
291
|
+
| **[dsh-skill-pack-security](https://github.com/PerryLink/dsh-skill-pack-security)** | Pacote de habilidades de auditoria de segurança: varredura de segredos, revisão de dependências e cadeia de suprimentos | |
|
|
292
|
+
| **[dsh-talk](https://github.com/PerryLink/dsh-talk)** | Loop de sessão com voz para DeepSeek Harness: fale e ouça a resposta. | |
|
|
293
|
+
| **[dsh-test-drive](https://github.com/PerryLink/dsh-test-drive)** | Test drives isolados de instalação e smoke para plugins de DeepSeek Harness. | |
|
|
294
|
+
| **[dsh-ticktick](https://github.com/PerryLink/dsh-ticktick)** | Ponte de tarefas TickTick/Dida365: painel no cabeçalho da sessão + 11 ferramentas |
|
|
295
|
+
| **[dsh-translate](https://github.com/PerryLink/dsh-translate)** | Tradução de parâmetros entre fornecedores e reparo determinístico de JSON para DeepSeek Harness. | |
|
|
296
|
+
| **[dsh-wechat](https://github.com/PerryLink/dsh-wechat)** | Ponte WeChat ↔ DSH (bot Tencent iLink): texto/imagem/arquivo/voz, aprovações no chat |
|
|
292
297
|
|
|
293
298
|
### Instalar a partir do mercado do DSH Desktop
|
|
294
299
|
|
package/README.zh.md
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
*需求在第一次改动之前就被拷问清楚；交付是被证明的，而不是被口头宣称的。*
|
|
9
9
|
|
|
10
10
|
[](LICENSE)
|
|
11
|
-
[](https://github.com/topics/dsh-plugin)
|
|
12
12
|
[](#)
|
|
13
13
|
[](https://github.com/PerryLink/dsh-doublecheck/actions)
|
|
14
14
|
[](https://github.com/PerryLink/dsh-doublecheck/releases)
|
|
@@ -25,7 +25,7 @@
|
|
|
25
25
|
|
|
26
26
|
| 方面 | 状态 |
|
|
27
27
|
|---|---|
|
|
28
|
-
| Harness | DeepSeek Harness `dsh-v0.1.
|
|
28
|
+
| Harness | DeepSeek Harness `dsh-v0.1.5-alpha.1`。已于 2026-09-09 对照 `dsh-v0.1.5-alpha.1` master checkout 核验（完整门禁链 + profile 安装冒烟）；已发布的 `0.1.2-rc.1` 钉号线仍受支持。 |
|
|
29
29
|
| Node | `^22.19.0 \|\| >=24.0.0` |
|
|
30
30
|
| 平台 | 全部（纯宿主；无原生代码，自身无直接网络请求） |
|
|
31
31
|
| 模型 | 任意（守卫本身从不调用模型；评审与批评阶段作为宿主 subagent 运行） |
|
|
@@ -208,7 +208,7 @@ CLI 只序列化已定的 `GateState` —— 它从不重新运行四阶段门
|
|
|
208
208
|
|
|
209
209
|
## 权限与数据
|
|
210
210
|
|
|
211
|
-
- **读取**：仅进程内读取会话日志（`tool/call` / `tool/result` / `tool/
|
|
211
|
+
- **读取**：仅进程内读取会话日志（`tool/call` / `tool/result` / `tool/ptc-dispatch`、注入的 `user/message` 来源，以及外部的 `autoReview/*` 裁决记录）；可选的计划模式服务状态。V3 改名前的宿主用旧标签 `tool/code-dispatch` 记录 PTC 子调用；两个标签折叠结果完全一致。
|
|
212
212
|
- **写入**：会话工作区中的 `doublecheck-spec.md`、`doublecheck-report.md` 和 `gate-report.md`（路径可配置），通过 `ctx.fs` 接口；持久的 `doublecheck/state` 和 `doublecheck/gate` 会话事件。
|
|
213
213
|
- **模型调用**：门禁的一致性阶段和本地评审阶段（每次 `/gate run` 各一个 subagent）、可选的对抗式评审，以及 `doublecheck_report` 验证工作流会启动 subagent 运行；除此之外不调用模型或网络。
|
|
214
214
|
- **绝不触碰**：凭据、环境变量，或会话工作区之外的任何文件。workshop 清单只声明 `filesystem:read` 和 `filesystem:write`。门禁报告只携带计数、id 和裁决；评审文本中被识别的机密在存储或显示之前会被脱敏。
|
|
@@ -225,6 +225,7 @@ CLI 只序列化已定的 `GateState` —— 它从不重新运行四阶段门
|
|
|
225
225
|
|
|
226
226
|
- **持久写入。** `/doublecheck on\|off` → `doublecheck/state` 与 `/gate run` → `doublecheck/gate` 需要宿主的 `ignorable` 追加接口（rc.6 之后至 `0.1.1-rc.2`）。在无此接口的宿主上（rc.6/rc.8，以及移除该信封的 `0.1.2-alpha.1`——`0.1.2-rc.1` 仅恢复存量日志读取兼容字段、仍无法盖章），写入被跳过、开关保持进程内状态。
|
|
227
227
|
0.1.2-rc.1（2026-09-02 已适配）：会话信封保留 ignorable 字段但仅用于存量日志读取兼容——Session.append 仍无法盖章，门控行为不变。
|
|
228
|
+
0.1.5-alpha.1（2026-09-09 已适配）：会话格式 V3 把持久子调用事件 `tool/code-dispatch` 改名为 `tool/ptc-dispatch`（载荷不变；两个标签折叠结果一致）。Session.append 仍无 `ignorable` 写入通道，写入继续跳过、开关保持进程内——行为不变。`doublecheck.gate` 设置命名空间仍是弱接口（见「已知限制」）。
|
|
228
229
|
- **可选接口。** `doublecheck.gate` 设置命名空间仅在挂载设置服务时注册；`/gate status` 的计划模式行读取可选的 `ctx.planMode`（没有则显示 `unknown`）；对抗式评审需要 `ctx.subagents`；验证需要 `workflowEngine`。
|
|
229
230
|
- **本地降级。** 当 dsh-auto-review 缺失或本会话没有裁决记录时，`gate.review.engine: auto` 会降级到本地评审者——报告会写明原因，而不是捏造裁决。
|
|
230
231
|
- **dsh-eval 证据基于文件。** dsh-auto-review 评测引擎（`dsh-eval`）把其 prompt 回归 / 压测 / 公平性结果写入工作区报告文件，而非会话日志。`gate.tests.evalReports.enabled` 折叠该文件（默认关闭；缺失时跳过），折叠出的计数随持久 `doublecheck/gate` 记录保存，使已定的运行仍可重放。
|
|
@@ -253,42 +254,46 @@ pnpm run pack:check # build + pack the tarball
|
|
|
253
254
|
|
|
254
255
|
## PerryLink DSH Plugin Family
|
|
255
256
|
|
|
256
|
-
这是 [PerryLink](https://github.com/PerryLink) 维护的 [
|
|
257
|
+
这是 [PerryLink](https://github.com/PerryLink) 维护的 [37 个 DeepSeek Harness 插件](https://github.com/PerryLink) 之一。如果它能帮到你，其他的也会：
|
|
257
258
|
|
|
258
259
|
| Plugin | One-liner |
|
|
259
260
|
|---|---|
|
|
260
|
-
| **[dsh-
|
|
261
|
-
| **[dsh-
|
|
262
|
-
| **[dsh-
|
|
263
|
-
| **[dsh-
|
|
264
|
-
| **[dsh-
|
|
265
|
-
| **[dsh-
|
|
266
|
-
| **[dsh-
|
|
267
|
-
| **[dsh-
|
|
268
|
-
| **[dsh-
|
|
269
|
-
| **[dsh-
|
|
270
|
-
| **[dsh-
|
|
271
|
-
| **[dsh-
|
|
272
|
-
| **[dsh-
|
|
273
|
-
| **[dsh-
|
|
274
|
-
| **[dsh-
|
|
275
|
-
| **[dsh-
|
|
276
|
-
| **[dsh-
|
|
277
|
-
| **[dsh-
|
|
278
|
-
| **[dsh-
|
|
279
|
-
| **[dsh-
|
|
280
|
-
| **[dsh-
|
|
281
|
-
| **[dsh-
|
|
282
|
-
| **[dsh-
|
|
283
|
-
| **[dsh-
|
|
284
|
-
| **[dsh-
|
|
285
|
-
| **[dsh-
|
|
286
|
-
| **[dsh-
|
|
287
|
-
| **[dsh-
|
|
288
|
-
| **[dsh-
|
|
289
|
-
| **[dsh-
|
|
290
|
-
| **[dsh-
|
|
291
|
-
| **[dsh-
|
|
261
|
+
| **[dsh-auto-review](https://github.com/PerryLink/dsh-auto-review)** | 审批链上的第二模型自动审查，默认失败关闭 | |
|
|
262
|
+
| **[dsh-background-agents](https://github.com/PerryLink/dsh-background-agents)** | 带 Web UI 侧栏、消息与中断的持久后台子代理 | |
|
|
263
|
+
| **[dsh-budget](https://github.com/PerryLink/dsh-budget)** | DeepSeek Harness 的成本治理：预算、碳排与延迟一屏呈现。 | |
|
|
264
|
+
| **[dsh-checkpoint-rewind](https://github.com/PerryLink/dsh-checkpoint-rewind)** | Claude Code /rewind 等价：快照、会话 fork、一次性恢复 | |
|
|
265
|
+
| **[dsh-claude-move](https://github.com/PerryLink/dsh-claude-move)** | 把 Claude Code 会话、记忆、技能与 CLAUDE.md 迁入 DSH | |
|
|
266
|
+
| **[dsh-click](https://github.com/PerryLink/dsh-click)** | 跨平台原生桌面控制（DeepSeek Harness），Windows 优先。 | |
|
|
267
|
+
| **[dsh-composer-history](https://github.com/PerryLink/dsh-composer-history)** | Web 输入框的终端式历史：方向键、Ctrl+R 搜索 | |
|
|
268
|
+
| **[dsh-data-quality](https://github.com/PerryLink/dsh-data-quality)** | 数据集质量检查与引文核查（本插件可选消费的数字核查桥） | |
|
|
269
|
+
| **[dsh-defend](https://github.com/PerryLink/dsh-defend)** | DeepSeek Harness 的提示注入、越狱与密钥泄露防护。 | |
|
|
270
|
+
| **[dsh-draw](https://github.com/PerryLink/dsh-draw)** | DeepSeek Harness 的统一静态图像生成路由。 | |
|
|
271
|
+
| **[dsh-fast](https://github.com/PerryLink/dsh-fast)** | DeepSeek Harness 只读性能诊断。 | |
|
|
272
|
+
| **[dsh-fund-research](https://github.com/PerryLink/dsh-fund-research)** | 面向中国公募基金的确定性研究报告 | |
|
|
273
|
+
| **[dsh-github](https://github.com/PerryLink/dsh-github)** | 面向 DSH 的 GitHub PR/issues 集成，每次写入经审批门控 | |
|
|
274
|
+
| **[dsh-industry-research](https://github.com/PerryLink/dsh-industry-research)** | 行业研究编排，经本插件的 `ctx.researchReport.assemble` 封存交付物 | |
|
|
275
|
+
| **[dsh-library](https://github.com/PerryLink/dsh-library)** | DeepSeek Harness 的本地文档知识库。 | |
|
|
276
|
+
| **[dsh-local-ai](https://github.com/PerryLink/dsh-local-ai)** | DeepSeek Harness 的本地模型（Ollama）接入。 | |
|
|
277
|
+
| **[dsh-lsp-actions](https://github.com/PerryLink/dsh-lsp-actions)** | 通过语言服务器的 LSP 诊断、格式化、补全、代码操作与重命名 | |
|
|
278
|
+
| **[dsh-mask](https://github.com/PerryLink/dsh-mask)** | PII 脱敏中间件：模型边界匿名化、展示层还原 | |
|
|
279
|
+
| **[dsh-mcp-panel](https://github.com/PerryLink/dsh-mcp-panel)** | 只读 MCP 运行时面板：/mcp 命令 + 带状态、工具与错误的 Settings 标签页 | |
|
|
280
|
+
| **[dsh-memento](https://github.com/PerryLink/dsh-memento)** | 审批门控的跨会话记忆：ctx.memory 接缝 + SQLite + 记忆工具 | |
|
|
281
|
+
| **[dsh-observe](https://github.com/PerryLink/dsh-observe)** | DeepSeek Harness 的 OpenTelemetry 与 Langfuse 可观测导出器。 | |
|
|
282
|
+
| **[dsh-output-styles](https://github.com/PerryLink/dsh-output-styles)** | Claude Code outputStyles 等价的运行时风格切换 | |
|
|
283
|
+
| **[dsh-reach](https://github.com/PerryLink/dsh-reach)** | 多渠道审批/提问桥接:微信/Telegram/飞书,会话控制台 |
|
|
284
|
+
| **[dsh-permission-rules](https://github.com/PerryLink/dsh-permission-rules)** | Claude Code 风格声明式 allow/deny/ask 权限规则，带审计 | |
|
|
285
|
+
| **[dsh-personal-directive](https://github.com/PerryLink/dsh-personal-directive)** | 个人指令注入器:顶栏开关(框架版) |
|
|
286
|
+
| **[dsh-plugin-guide](https://github.com/PerryLink/dsh-plugin-guide)** | 作为按需代理技能的插件开发知识库 | |
|
|
287
|
+
| **[dsh-research-report](https://github.com/PerryLink/dsh-research-report)** | 可验证研究报告引擎：内容寻址证据账本与封存版本 | |
|
|
288
|
+
| **[dsh-score](https://github.com/PerryLink/dsh-score)** | DeepSeek Harness 插件的多维质量评分。 | |
|
|
289
|
+
| **[dsh-session-pin](https://github.com/PerryLink/dsh-session-pin)** | 在 Web 侧栏置顶会话，带持久排序 | |
|
|
290
|
+
| **[dsh-session-sync](https://github.com/PerryLink/dsh-session-sync)** | DeepSeek Harness 的跨设备会话同步——会话存储的专用 git 镜像。 | |
|
|
291
|
+
| **[dsh-skill-pack-security](https://github.com/PerryLink/dsh-skill-pack-security)** | 安全审计技能包：密钥扫描、依赖与供应链审查 | |
|
|
292
|
+
| **[dsh-talk](https://github.com/PerryLink/dsh-talk)** | DeepSeek Harness 的语音优先会话闭环：对它说，听它答。 | |
|
|
293
|
+
| **[dsh-test-drive](https://github.com/PerryLink/dsh-test-drive)** | DeepSeek Harness 插件的隔离试装冒烟。 | |
|
|
294
|
+
| **[dsh-ticktick](https://github.com/PerryLink/dsh-ticktick)** | TickTick/滴答清单任务桥接:会话头面板 + 11 个工具 |
|
|
295
|
+
| **[dsh-translate](https://github.com/PerryLink/dsh-translate)** | DeepSeek Harness 的厂商参数翻译与确定性 JSON 修复。 | |
|
|
296
|
+
| **[dsh-wechat](https://github.com/PerryLink/dsh-wechat)** | 微信 ↔ DSH 桥接(Tencent iLink 机器人):文本/图片/文件/语音,聊天内审批卡片 |
|
|
292
297
|
|
|
293
298
|
### 从 DSH Desktop 市场安装
|
|
294
299
|
|
package/lib/domain/evidence.d.ts
CHANGED
|
@@ -2,13 +2,14 @@
|
|
|
2
2
|
* Test-run evidence classification for the red/green gates.
|
|
3
3
|
*
|
|
4
4
|
* The durable session log is the only source of truth: a shell tool call
|
|
5
|
-
* (`bash` / `pwsh`, including
|
|
6
|
-
*
|
|
5
|
+
* (`bash` / `pwsh`, including PTC sub-dispatches) whose command matches the
|
|
6
|
+
* configured test patterns is a test run, and its rendered result text
|
|
7
7
|
* carries the exit facts (`[exit code: N]`, timeout, signal, sandbox-denial
|
|
8
8
|
* markers). A failing run is red evidence; a passing run is green evidence.
|
|
9
9
|
*
|
|
10
10
|
* @module dsh-doublecheck/domain/evidence
|
|
11
11
|
*/
|
|
12
|
+
import type { SessionEvent } from '@deepseek-ai/dsh-session';
|
|
12
13
|
/** Compiled red/green evidence detection knobs. */
|
|
13
14
|
export interface TestRunDetection {
|
|
14
15
|
/** Tool names that can execute shell commands. */
|
|
@@ -45,9 +46,41 @@ export interface DetectionConfig {
|
|
|
45
46
|
export declare function compileDetection(config: DetectionConfig): TestRunDetection;
|
|
46
47
|
/** The detection record with every list empty: test-run evidence is ignored. */
|
|
47
48
|
export declare function emptyDetection(): TestRunDetection;
|
|
49
|
+
/** The rendered result blocks of a settled sub-dispatch (structural: only the fields the evidence folds read). */
|
|
50
|
+
export type PtcContent = ReadonlyArray<{
|
|
51
|
+
type?: unknown;
|
|
52
|
+
text?: unknown;
|
|
53
|
+
content?: unknown;
|
|
54
|
+
}>;
|
|
55
|
+
/** One settled PTC sub-dispatch payload, whatever generation names the event. */
|
|
56
|
+
export interface PtcSettle {
|
|
57
|
+
/** The dispatched tool name (`bash` / `pwsh` / `edit` / `write` …). */
|
|
58
|
+
name: string;
|
|
59
|
+
/** The dispatch arguments: a normalized record on the current line, a JSON string on the predecessor. */
|
|
60
|
+
arguments: unknown;
|
|
61
|
+
/** Whether the sub-dispatch failed at the infrastructure level. */
|
|
62
|
+
isError: boolean;
|
|
63
|
+
/** The rendered model-facing result blocks. */
|
|
64
|
+
content: PtcContent;
|
|
65
|
+
}
|
|
66
|
+
/**
|
|
67
|
+
* Normalize one settled PTC sub-dispatch event, across the event-vocabulary
|
|
68
|
+
* rename at the session-format V2→V3 edge.
|
|
69
|
+
*
|
|
70
|
+
* The current line names the settled sub-dispatch `tool/ptc-dispatch` (the
|
|
71
|
+
* host's V2→V3 migration renames the predecessor `tool/code-dispatch`, keeping
|
|
72
|
+
* the payload values), so a stored V2 log arrives under the new label. A host
|
|
73
|
+
* on the older release line still emits the predecessor label, which is outside
|
|
74
|
+
* this line's `SessionEventMap`; it is matched structurally instead of as a
|
|
75
|
+
* switch case, so the fold never depends on which generation wrote the log.
|
|
76
|
+
*
|
|
77
|
+
* @param event - one committed session event.
|
|
78
|
+
* @returns the settled payload, or `undefined` when the event is not a settled sub-dispatch.
|
|
79
|
+
*/
|
|
80
|
+
export declare function ptcSettle(event: SessionEvent): PtcSettle | undefined;
|
|
48
81
|
/**
|
|
49
82
|
* Parse a raw tool-call `arguments` value (a JSON string from the model, or an
|
|
50
|
-
* already-normalized object from a
|
|
83
|
+
* already-normalized object from a PTC sub-dispatch) into a plain record.
|
|
51
84
|
* @param raw - the raw arguments value from the durable event.
|
|
52
85
|
* @returns the parsed record, or `undefined` when the string is not valid JSON.
|
|
53
86
|
*/
|
package/lib/domain/evidence.js
CHANGED
|
@@ -2,8 +2,8 @@
|
|
|
2
2
|
* Test-run evidence classification for the red/green gates.
|
|
3
3
|
*
|
|
4
4
|
* The durable session log is the only source of truth: a shell tool call
|
|
5
|
-
* (`bash` / `pwsh`, including
|
|
6
|
-
*
|
|
5
|
+
* (`bash` / `pwsh`, including PTC sub-dispatches) whose command matches the
|
|
6
|
+
* configured test patterns is a test run, and its rendered result text
|
|
7
7
|
* carries the exit facts (`[exit code: N]`, timeout, signal, sandbox-denial
|
|
8
8
|
* markers). A failing run is red evidence; a passing run is green evidence.
|
|
9
9
|
*
|
|
@@ -56,9 +56,44 @@ export function emptyDetection() {
|
|
|
56
56
|
testFilePatterns: [],
|
|
57
57
|
};
|
|
58
58
|
}
|
|
59
|
+
/**
|
|
60
|
+
* Normalize one settled PTC sub-dispatch event, across the event-vocabulary
|
|
61
|
+
* rename at the session-format V2→V3 edge.
|
|
62
|
+
*
|
|
63
|
+
* The current line names the settled sub-dispatch `tool/ptc-dispatch` (the
|
|
64
|
+
* host's V2→V3 migration renames the predecessor `tool/code-dispatch`, keeping
|
|
65
|
+
* the payload values), so a stored V2 log arrives under the new label. A host
|
|
66
|
+
* on the older release line still emits the predecessor label, which is outside
|
|
67
|
+
* this line's `SessionEventMap`; it is matched structurally instead of as a
|
|
68
|
+
* switch case, so the fold never depends on which generation wrote the log.
|
|
69
|
+
*
|
|
70
|
+
* @param event - one committed session event.
|
|
71
|
+
* @returns the settled payload, or `undefined` when the event is not a settled sub-dispatch.
|
|
72
|
+
*/
|
|
73
|
+
export function ptcSettle(event) {
|
|
74
|
+
if (event.type === 'tool/ptc-dispatch') {
|
|
75
|
+
return {
|
|
76
|
+
name: event.data.name,
|
|
77
|
+
arguments: event.data.arguments,
|
|
78
|
+
isError: event.data.isError,
|
|
79
|
+
content: event.data.content,
|
|
80
|
+
};
|
|
81
|
+
}
|
|
82
|
+
if (event.type !== 'tool/code-dispatch')
|
|
83
|
+
return undefined;
|
|
84
|
+
const legacy = event.data;
|
|
85
|
+
if (legacy === null || legacy === undefined || typeof legacy.name !== 'string')
|
|
86
|
+
return undefined;
|
|
87
|
+
return {
|
|
88
|
+
name: legacy.name,
|
|
89
|
+
arguments: legacy.arguments,
|
|
90
|
+
isError: legacy.isError === true,
|
|
91
|
+
content: Array.isArray(legacy.content) ? legacy.content : [],
|
|
92
|
+
};
|
|
93
|
+
}
|
|
59
94
|
/**
|
|
60
95
|
* Parse a raw tool-call `arguments` value (a JSON string from the model, or an
|
|
61
|
-
* already-normalized object from a
|
|
96
|
+
* already-normalized object from a PTC sub-dispatch) into a plain record.
|
|
62
97
|
* @param raw - the raw arguments value from the durable event.
|
|
63
98
|
* @returns the parsed record, or `undefined` when the string is not valid JSON.
|
|
64
99
|
*/
|
package/lib/domain/gate.js
CHANGED
|
@@ -25,7 +25,7 @@
|
|
|
25
25
|
*
|
|
26
26
|
* @module dsh-doublecheck/domain/gate
|
|
27
27
|
*/
|
|
28
|
-
import { isTestCommand, joinTextBlocks, parseRawArguments, shellCommand, testOutcome, } from "./evidence.js";
|
|
28
|
+
import { isTestCommand, joinTextBlocks, parseRawArguments, ptcSettle, shellCommand, testOutcome, } from "./evidence.js";
|
|
29
29
|
import { SPEC_TOOL_NAME } from "./stages.js";
|
|
30
30
|
import { SPEC_FIELD_NAMES } from "./vocabulary.js";
|
|
31
31
|
/** All gate phases in checklist order. */
|
|
@@ -110,6 +110,19 @@ export function foldTestEvidence(events, detection, coverageRegex) {
|
|
|
110
110
|
const evidence = { failed: 0, passed: 0, lastOutcome: 'none', failingAfterGreen: 0, coveragePct: null };
|
|
111
111
|
const pendingTests = new Map();
|
|
112
112
|
for (const event of events) {
|
|
113
|
+
// A settled PTC sub-dispatch is a test run exactly like a native shell
|
|
114
|
+
// call; the normalizer accepts both event generations, so the evidence
|
|
115
|
+
// does not depend on which one wrote the log.
|
|
116
|
+
const settle = ptcSettle(event);
|
|
117
|
+
if (settle !== undefined) {
|
|
118
|
+
const args = parseRawArguments(settle.arguments);
|
|
119
|
+
const command = shellCommand(settle.name, args, detection);
|
|
120
|
+
if (command !== undefined && isTestCommand(command, detection)) {
|
|
121
|
+
const text = joinTextBlocks(settle.content);
|
|
122
|
+
foldTestEvidenceOutcome(evidence, testOutcome(text, settle.isError), text, coverageRegex);
|
|
123
|
+
}
|
|
124
|
+
continue;
|
|
125
|
+
}
|
|
113
126
|
switch (event.type) {
|
|
114
127
|
case 'tool/call': {
|
|
115
128
|
const args = parseRawArguments(event.data.arguments);
|
|
@@ -127,15 +140,6 @@ export function foldTestEvidence(events, detection, coverageRegex) {
|
|
|
127
140
|
foldTestEvidenceOutcome(evidence, testOutcome(text, event.data.error !== undefined), text, coverageRegex);
|
|
128
141
|
break;
|
|
129
142
|
}
|
|
130
|
-
case 'tool/code-dispatch': {
|
|
131
|
-
const args = parseRawArguments(event.data.arguments);
|
|
132
|
-
const command = shellCommand(event.data.name, args, detection);
|
|
133
|
-
if (command !== undefined && isTestCommand(command, detection)) {
|
|
134
|
-
const text = joinTextBlocks(event.data.content);
|
|
135
|
-
foldTestEvidenceOutcome(evidence, testOutcome(text, event.data.isError), text, coverageRegex);
|
|
136
|
-
}
|
|
137
|
-
break;
|
|
138
|
-
}
|
|
139
143
|
}
|
|
140
144
|
}
|
|
141
145
|
return evidence;
|
package/lib/domain/projection.js
CHANGED
|
@@ -10,7 +10,7 @@
|
|
|
10
10
|
*
|
|
11
11
|
* @module dsh-doublecheck/domain/projection
|
|
12
12
|
*/
|
|
13
|
-
import { isTestCommand, isTestFilePath, joinTextBlocks, mutationTargetPath, parseRawArguments, shellCommand, testOutcome, } from "./evidence.js";
|
|
13
|
+
import { isTestCommand, isTestFilePath, joinTextBlocks, mutationTargetPath, parseRawArguments, ptcSettle, shellCommand, testOutcome, } from "./evidence.js";
|
|
14
14
|
import { SPEC_TOOL_NAME } from "./stages.js";
|
|
15
15
|
import { countRedChecks } from "./gate.js";
|
|
16
16
|
/** State for the empty log. */
|
|
@@ -38,6 +38,22 @@ export function emptyDoublecheckState() {
|
|
|
38
38
|
* discipline fact.
|
|
39
39
|
*/
|
|
40
40
|
export function applyDoublecheckEvent(state, event, detection) {
|
|
41
|
+
// A settled PTC sub-dispatch is a discipline fact exactly like a native
|
|
42
|
+
// call. The normalizer accepts both event generations, so the projection
|
|
43
|
+
// does not depend on which one wrote the log.
|
|
44
|
+
const settle = ptcSettle(event);
|
|
45
|
+
if (settle !== undefined) {
|
|
46
|
+
const args = parseRawArguments(settle.arguments);
|
|
47
|
+
const command = shellCommand(settle.name, args, detection);
|
|
48
|
+
if (command !== undefined && isTestCommand(command, detection)) {
|
|
49
|
+
const outcome = testOutcome(joinTextBlocks(settle.content), settle.isError);
|
|
50
|
+
if (outcome === 'fail')
|
|
51
|
+
return { ...state, color: 'red', stage: 'red' };
|
|
52
|
+
if (outcome === 'pass')
|
|
53
|
+
return { ...state, color: 'green', stage: 'green' };
|
|
54
|
+
}
|
|
55
|
+
return state;
|
|
56
|
+
}
|
|
41
57
|
switch (event.type) {
|
|
42
58
|
case 'tool/call': {
|
|
43
59
|
const args = parseRawArguments(event.data.arguments);
|
|
@@ -82,18 +98,6 @@ export function applyDoublecheckEvent(state, event, detection) {
|
|
|
82
98
|
}
|
|
83
99
|
return state;
|
|
84
100
|
}
|
|
85
|
-
case 'tool/code-dispatch': {
|
|
86
|
-
const args = parseRawArguments(event.data.arguments);
|
|
87
|
-
const command = shellCommand(event.data.name, args, detection);
|
|
88
|
-
if (command !== undefined && isTestCommand(command, detection)) {
|
|
89
|
-
const outcome = testOutcome(joinTextBlocks(event.data.content), event.data.isError);
|
|
90
|
-
if (outcome === 'fail')
|
|
91
|
-
return { ...state, color: 'red', stage: 'red' };
|
|
92
|
-
if (outcome === 'pass')
|
|
93
|
-
return { ...state, color: 'green', stage: 'green' };
|
|
94
|
-
}
|
|
95
|
-
return state;
|
|
96
|
-
}
|
|
97
101
|
case 'user/message': {
|
|
98
102
|
const source = event.data.source;
|
|
99
103
|
if (source.kind === 'doublecheck-review' && !state.reviewed) {
|
package/lib/domain/report.js
CHANGED
|
@@ -11,7 +11,7 @@
|
|
|
11
11
|
*
|
|
12
12
|
* @module dsh-doublecheck/domain/report
|
|
13
13
|
*/
|
|
14
|
-
import { isTestCommand, isTestFilePath, joinTextBlocks, mutationTargetPath, parseRawArguments, shellCommand, testOutcome, } from "./evidence.js";
|
|
14
|
+
import { isTestCommand, isTestFilePath, joinTextBlocks, mutationTargetPath, parseRawArguments, ptcSettle, shellCommand, testOutcome, } from "./evidence.js";
|
|
15
15
|
import { SPEC_TOOL_NAME } from "./stages.js";
|
|
16
16
|
import { VERIFY_DIMENSIONS, } from "./vocabulary.js";
|
|
17
17
|
/** Maximum timeline rows rendered into the report document. */
|
|
@@ -32,6 +32,23 @@ export function foldReportFacts(events, detection) {
|
|
|
32
32
|
/** Spec calls awaiting a result: only a successful pair commits the spec. */
|
|
33
33
|
const pendingSpecs = new Map();
|
|
34
34
|
for (const event of events) {
|
|
35
|
+
// A settled PTC sub-dispatch runs through the same pre-execute policy
|
|
36
|
+
// gates, so a dispatched test run or edit is a real delivery fact and must
|
|
37
|
+
// count exactly like a native call. The normalizer accepts both event
|
|
38
|
+
// generations, so the fold does not depend on which one wrote the log.
|
|
39
|
+
const settle = ptcSettle(event);
|
|
40
|
+
if (settle !== undefined) {
|
|
41
|
+
const args = parseRawArguments(settle.arguments);
|
|
42
|
+
const command = shellCommand(settle.name, args, detection);
|
|
43
|
+
if (command !== undefined && isTestCommand(command, detection)) {
|
|
44
|
+
foldTestRun(facts, command, testOutcome(joinTextBlocks(settle.content), settle.isError));
|
|
45
|
+
}
|
|
46
|
+
const path = mutationTargetPath(settle.name, args, detection);
|
|
47
|
+
if (path !== undefined && !isTestFilePath(path, detection)) {
|
|
48
|
+
facts.edits += 1;
|
|
49
|
+
}
|
|
50
|
+
continue;
|
|
51
|
+
}
|
|
35
52
|
switch (event.type) {
|
|
36
53
|
case 'tool/call': {
|
|
37
54
|
const args = parseRawArguments(event.data.arguments);
|
|
@@ -68,21 +85,6 @@ export function foldReportFacts(events, detection) {
|
|
|
68
85
|
foldTestRun(facts, command, testOutcome(joinTextBlocks(event.data.message.content), event.data.error !== undefined));
|
|
69
86
|
break;
|
|
70
87
|
}
|
|
71
|
-
case 'tool/code-dispatch': {
|
|
72
|
-
const args = parseRawArguments(event.data.arguments);
|
|
73
|
-
const command = shellCommand(event.data.name, args, detection);
|
|
74
|
-
if (command !== undefined && isTestCommand(command, detection)) {
|
|
75
|
-
foldTestRun(facts, command, testOutcome(joinTextBlocks(event.data.content), event.data.isError));
|
|
76
|
-
}
|
|
77
|
-
// Code Mode dispatches run through the same pre-execute policy gates,
|
|
78
|
-
// so a dispatched edit is a real implementation edit and must count
|
|
79
|
-
// toward the report exactly like a native call.
|
|
80
|
-
const path = mutationTargetPath(event.data.name, args, detection);
|
|
81
|
-
if (path !== undefined && !isTestFilePath(path, detection)) {
|
|
82
|
-
facts.edits += 1;
|
|
83
|
-
}
|
|
84
|
-
break;
|
|
85
|
-
}
|
|
86
88
|
case 'user/message': {
|
|
87
89
|
const source = event.data.source;
|
|
88
90
|
if (source.kind !== 'doublecheck-review')
|
package/lib/domain/stages.js
CHANGED
|
@@ -14,7 +14,7 @@
|
|
|
14
14
|
*
|
|
15
15
|
* @module dsh-doublecheck/domain/stages
|
|
16
16
|
*/
|
|
17
|
-
import { emptyDetection, isTestCommand, isTestFilePath, joinTextBlocks, mutationTargetPath, parseRawArguments, shellCommand, testOutcome, } from "./evidence.js";
|
|
17
|
+
import { emptyDetection, isTestCommand, isTestFilePath, joinTextBlocks, mutationTargetPath, parseRawArguments, ptcSettle, shellCommand, testOutcome, } from "./evidence.js";
|
|
18
18
|
/** All discipline stages in order. */
|
|
19
19
|
export const DISCIPLINE_STAGES = [
|
|
20
20
|
'grill', 'design', 'red', 'green', 'review', 'verify',
|
|
@@ -82,6 +82,24 @@ export function foldDisciplineRange(state, events, start, detection) {
|
|
|
82
82
|
const event = events[index];
|
|
83
83
|
if (event === undefined)
|
|
84
84
|
continue;
|
|
85
|
+
// A settled PTC sub-dispatch runs through the same pre-execute policy
|
|
86
|
+
// gates, so a dispatched test run or edit is a real discipline fact and
|
|
87
|
+
// must count exactly like a native call. The normalizer accepts both event
|
|
88
|
+
// generations, so the fold does not depend on which one wrote the log.
|
|
89
|
+
const settle = ptcSettle(event);
|
|
90
|
+
if (settle !== undefined) {
|
|
91
|
+
const args = parseRawArguments(settle.arguments);
|
|
92
|
+
const command = shellCommand(settle.name, args, detection);
|
|
93
|
+
if (command !== undefined && isTestCommand(command, detection)) {
|
|
94
|
+
foldTestOutcome(state, testOutcome(joinTextBlocks(settle.content), settle.isError));
|
|
95
|
+
}
|
|
96
|
+
const path = mutationTargetPath(settle.name, args, detection);
|
|
97
|
+
if (path !== undefined && !isTestFilePath(path, detection)) {
|
|
98
|
+
state.pendingGreen = true;
|
|
99
|
+
state.editCount += 1;
|
|
100
|
+
}
|
|
101
|
+
continue;
|
|
102
|
+
}
|
|
85
103
|
switch (event.type) {
|
|
86
104
|
case 'tool/call': {
|
|
87
105
|
const args = parseRawArguments(event.data.arguments);
|
|
@@ -118,22 +136,6 @@ export function foldDisciplineRange(state, events, start, detection) {
|
|
|
118
136
|
}
|
|
119
137
|
break;
|
|
120
138
|
}
|
|
121
|
-
case 'tool/code-dispatch': {
|
|
122
|
-
const args = parseRawArguments(event.data.arguments);
|
|
123
|
-
const command = shellCommand(event.data.name, args, detection);
|
|
124
|
-
if (command !== undefined && isTestCommand(command, detection)) {
|
|
125
|
-
foldTestOutcome(state, testOutcome(joinTextBlocks(event.data.content), event.data.isError));
|
|
126
|
-
}
|
|
127
|
-
// Code Mode dispatches run through the same pre-execute policy gates,
|
|
128
|
-
// so a dispatched edit is a real implementation edit and must count
|
|
129
|
-
// toward the green gate and the report exactly like a native call.
|
|
130
|
-
const path = mutationTargetPath(event.data.name, args, detection);
|
|
131
|
-
if (path !== undefined && !isTestFilePath(path, detection)) {
|
|
132
|
-
state.pendingGreen = true;
|
|
133
|
-
state.editCount += 1;
|
|
134
|
-
}
|
|
135
|
-
break;
|
|
136
|
-
}
|
|
137
139
|
}
|
|
138
140
|
}
|
|
139
141
|
return state;
|
package/lib/index.js
CHANGED
|
@@ -12,5 +12,7 @@ export * from "./domain/vagueness.js";
|
|
|
12
12
|
export * from "./domain/vocabulary.js";
|
|
13
13
|
export * from "./domain/report.js";
|
|
14
14
|
export * from "./domain/gate.js";
|
|
15
|
+
// Consumer: the grill/guard rows consume the domain folds above; renderSpecMarkdown turns specs into model-facing text for the contract tools.
|
|
15
16
|
export { renderSpecMarkdown } from "./grill/index.js";
|
|
17
|
+
// Service Provider: BundledSkillProvider supplies the bundled grill-requirements skill to the doublecheck-grill row.
|
|
16
18
|
export { BundledSkillProvider, parseSkillAsset, PROVIDER_NAME } from "./grill/provider.js";
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-doublecheck",
|
|
3
|
-
"version": "0.9.
|
|
3
|
+
"version": "0.9.8",
|
|
4
4
|
"description": "Delivery quality gate for DeepSeek Harness: grill the requirements, test the implementation, prove the delivery, and gate the handoff with a deliverable/rework decision.",
|
|
5
5
|
"packageManager": "pnpm@11.7.0",
|
|
6
6
|
"repository": {
|
|
@@ -56,8 +56,9 @@
|
|
|
56
56
|
"scripts": {
|
|
57
57
|
"build": "tsc --noEmitOnError && node scripts/fix-dts.mjs",
|
|
58
58
|
"prepare": "tsc --noEmitOnError && node scripts/fix-dts.mjs",
|
|
59
|
-
"prepublishOnly": "tsc --noEmitOnError && node scripts/fix-dts.mjs && pnpm run test",
|
|
59
|
+
"prepublishOnly": "pnpm run typecheck:ci && tsc --noEmitOnError && node scripts/fix-dts.mjs && pnpm run test",
|
|
60
60
|
"typecheck": "tsc --noEmit && tsc -p tsconfig.tests.json",
|
|
61
|
+
"typecheck:ci": "tsc -p tsconfig.ci.json --noEmit",
|
|
61
62
|
"lint": "eslint src tests",
|
|
62
63
|
"test": "vitest run",
|
|
63
64
|
"test:coverage": "vitest run --coverage",
|
|
@@ -110,9 +111,7 @@
|
|
|
110
111
|
"filesystem:write"
|
|
111
112
|
],
|
|
112
113
|
"compatibility": {
|
|
113
|
-
"dshVersions": [
|
|
114
|
-
"0.1.2-rc.1"
|
|
115
|
-
]
|
|
114
|
+
"dshVersions": ["0.1.2-rc.1","0.1.5-alpha.1"]
|
|
116
115
|
},
|
|
117
116
|
"capability": {
|
|
118
117
|
"id": "doublecheck",
|
|
@@ -129,14 +128,14 @@
|
|
|
129
128
|
},
|
|
130
129
|
"peerDependencies": {
|
|
131
130
|
"@deepseek-ai/cordis": "^4.0.2",
|
|
132
|
-
"@deepseek-ai/dsh-agent": ">=0.1.2-rc.1 <0.2.0",
|
|
133
|
-
"@deepseek-ai/dsh-commands": ">=0.1.2-rc.1 <0.2.0",
|
|
134
|
-
"@deepseek-ai/dsh-invariants": ">=0.1.2-rc.1 <0.2.0",
|
|
135
|
-
"@deepseek-ai/dsh-llm": ">=0.1.2-rc.1 <0.2.0",
|
|
136
|
-
"@deepseek-ai/dsh-session": ">=0.1.2-rc.1 <0.2.0",
|
|
137
|
-
"@deepseek-ai/dsh-session-projection": ">=0.1.2-rc.1 <0.2.0",
|
|
138
|
-
"@deepseek-ai/dsh-skill": ">=0.1.2-rc.1 <0.2.0",
|
|
139
|
-
"@deepseek-ai/dsh-tools": ">=0.1.2-rc.1 <0.2.0",
|
|
131
|
+
"@deepseek-ai/dsh-agent": ">=0.1.2-rc.1 <0.2.0 || >=0.1.5-alpha.1 <0.2.0",
|
|
132
|
+
"@deepseek-ai/dsh-commands": ">=0.1.2-rc.1 <0.2.0 || >=0.1.5-alpha.1 <0.2.0",
|
|
133
|
+
"@deepseek-ai/dsh-invariants": ">=0.1.2-rc.1 <0.2.0 || >=0.1.5-alpha.1 <0.2.0",
|
|
134
|
+
"@deepseek-ai/dsh-llm": ">=0.1.2-rc.1 <0.2.0 || >=0.1.5-alpha.1 <0.2.0",
|
|
135
|
+
"@deepseek-ai/dsh-session": ">=0.1.2-rc.1 <0.2.0 || >=0.1.5-alpha.1 <0.2.0",
|
|
136
|
+
"@deepseek-ai/dsh-session-projection": ">=0.1.2-rc.1 <0.2.0 || >=0.1.5-alpha.1 <0.2.0",
|
|
137
|
+
"@deepseek-ai/dsh-skill": ">=0.1.2-rc.1 <0.2.0 || >=0.1.5-alpha.1 <0.2.0",
|
|
138
|
+
"@deepseek-ai/dsh-tools": ">=0.1.2-rc.1 <0.2.0 || >=0.1.5-alpha.1 <0.2.0",
|
|
140
139
|
"@deepseek-ai/schemastery": "^3.18.2"
|
|
141
140
|
},
|
|
142
141
|
"dependencies": {
|
|
@@ -146,17 +145,17 @@
|
|
|
146
145
|
"devDependencies": {
|
|
147
146
|
"@deepseek-ai/cordis": "^4.0.2",
|
|
148
147
|
"@deepseek-ai/cordis-plugin-loader": "^1.0.3",
|
|
149
|
-
"@deepseek-ai/dsh-agent": "0.1.
|
|
150
|
-
"@deepseek-ai/dsh-commands": "0.1.
|
|
151
|
-
"@deepseek-ai/dsh-fs": "0.1.
|
|
152
|
-
"@deepseek-ai/dsh-llm": "0.1.
|
|
153
|
-
"@deepseek-ai/dsh-session": "0.1.
|
|
154
|
-
"@deepseek-ai/dsh-session-projection": "0.1.
|
|
155
|
-
"@deepseek-ai/dsh-skill": "0.1.
|
|
156
|
-
"@deepseek-ai/dsh-subagent": "0.1.
|
|
157
|
-
"@deepseek-ai/dsh-system-prompt": "0.1.
|
|
158
|
-
"@deepseek-ai/dsh-tools": "0.1.
|
|
159
|
-
"@deepseek-ai/dsh-workflow": "0.1.
|
|
148
|
+
"@deepseek-ai/dsh-agent": "0.1.5-alpha.1",
|
|
149
|
+
"@deepseek-ai/dsh-commands": "0.1.5-alpha.1",
|
|
150
|
+
"@deepseek-ai/dsh-fs": "0.1.5-alpha.1",
|
|
151
|
+
"@deepseek-ai/dsh-llm": "0.1.5-alpha.1",
|
|
152
|
+
"@deepseek-ai/dsh-session": "0.1.5-alpha.1",
|
|
153
|
+
"@deepseek-ai/dsh-session-projection": "0.1.5-alpha.1",
|
|
154
|
+
"@deepseek-ai/dsh-skill": "0.1.5-alpha.1",
|
|
155
|
+
"@deepseek-ai/dsh-subagent": "0.1.5-alpha.1",
|
|
156
|
+
"@deepseek-ai/dsh-system-prompt": "0.1.5-alpha.1",
|
|
157
|
+
"@deepseek-ai/dsh-tools": "0.1.5-alpha.1",
|
|
158
|
+
"@deepseek-ai/dsh-workflow": "0.1.5-alpha.1",
|
|
160
159
|
"@deepseek-ai/schemastery": "^3.18.2",
|
|
161
160
|
"@eslint/js": "^9.30.0",
|
|
162
161
|
"@types/node": "^22.15.0",
|