failproofai 0.0.6-beta.1 → 0.0.6-beta.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/.next/standalone/.failproofai/policies/review-policies.mjs +4 -3
- package/.next/standalone/.next/BUILD_ID +1 -1
- package/.next/standalone/.next/build-manifest.json +3 -3
- package/.next/standalone/.next/prerender-manifest.json +3 -3
- package/.next/standalone/.next/required-server-files.json +1 -1
- package/.next/standalone/.next/server/app/_global-error/page/server-reference-manifest.json +1 -1
- package/.next/standalone/.next/server/app/_global-error/page.js.nft.json +1 -1
- package/.next/standalone/.next/server/app/_global-error/page_client-reference-manifest.js +1 -1
- package/.next/standalone/.next/server/app/_global-error.html +1 -1
- package/.next/standalone/.next/server/app/_global-error.rsc +7 -7
- package/.next/standalone/.next/server/app/_global-error.segments/__PAGE__.segment.rsc +2 -2
- package/.next/standalone/.next/server/app/_global-error.segments/_full.segment.rsc +7 -7
- package/.next/standalone/.next/server/app/_global-error.segments/_head.segment.rsc +3 -3
- package/.next/standalone/.next/server/app/_global-error.segments/_index.segment.rsc +3 -3
- package/.next/standalone/.next/server/app/_global-error.segments/_tree.segment.rsc +1 -1
- package/.next/standalone/.next/server/app/_not-found/page/server-reference-manifest.json +1 -1
- package/.next/standalone/.next/server/app/_not-found/page.js.nft.json +1 -1
- package/.next/standalone/.next/server/app/_not-found/page_client-reference-manifest.js +1 -1
- package/.next/standalone/.next/server/app/_not-found.html +2 -2
- package/.next/standalone/.next/server/app/_not-found.rsc +15 -15
- package/.next/standalone/.next/server/app/_not-found.segments/_full.segment.rsc +15 -15
- package/.next/standalone/.next/server/app/_not-found.segments/_head.segment.rsc +4 -4
- package/.next/standalone/.next/server/app/_not-found.segments/_index.segment.rsc +10 -10
- package/.next/standalone/.next/server/app/_not-found.segments/_not-found/__PAGE__.segment.rsc +2 -2
- package/.next/standalone/.next/server/app/_not-found.segments/_not-found.segment.rsc +3 -3
- package/.next/standalone/.next/server/app/_not-found.segments/_tree.segment.rsc +1 -1
- package/.next/standalone/.next/server/app/index.html +1 -1
- package/.next/standalone/.next/server/app/index.rsc +15 -15
- package/.next/standalone/.next/server/app/index.segments/__PAGE__.segment.rsc +2 -2
- package/.next/standalone/.next/server/app/index.segments/_full.segment.rsc +15 -15
- package/.next/standalone/.next/server/app/index.segments/_head.segment.rsc +4 -4
- package/.next/standalone/.next/server/app/index.segments/_index.segment.rsc +10 -10
- package/.next/standalone/.next/server/app/index.segments/_tree.segment.rsc +1 -1
- package/.next/standalone/.next/server/app/page/server-reference-manifest.json +1 -1
- package/.next/standalone/.next/server/app/page.js.nft.json +1 -1
- package/.next/standalone/.next/server/app/page_client-reference-manifest.js +1 -1
- package/.next/standalone/.next/server/app/policies/page/server-reference-manifest.json +8 -8
- package/.next/standalone/.next/server/app/policies/page.js.nft.json +1 -1
- package/.next/standalone/.next/server/app/policies/page_client-reference-manifest.js +1 -1
- package/.next/standalone/.next/server/app/project/[name]/page/server-reference-manifest.json +1 -1
- package/.next/standalone/.next/server/app/project/[name]/page.js.nft.json +1 -1
- package/.next/standalone/.next/server/app/project/[name]/page_client-reference-manifest.js +1 -1
- package/.next/standalone/.next/server/app/project/[name]/session/[sessionId]/page/react-loadable-manifest.json +2 -2
- package/.next/standalone/.next/server/app/project/[name]/session/[sessionId]/page/server-reference-manifest.json +2 -2
- package/.next/standalone/.next/server/app/project/[name]/session/[sessionId]/page.js.nft.json +1 -1
- package/.next/standalone/.next/server/app/project/[name]/session/[sessionId]/page_client-reference-manifest.js +1 -1
- package/.next/standalone/.next/server/app/projects/page/server-reference-manifest.json +1 -1
- package/.next/standalone/.next/server/app/projects/page.js.nft.json +1 -1
- package/.next/standalone/.next/server/app/projects/page_client-reference-manifest.js +1 -1
- package/.next/standalone/.next/server/chunks/[root-of-the-server]__0g72weg._.js +1 -1
- package/.next/standalone/.next/server/chunks/package_json_[json]_cjs_0z7w.hh._.js +1 -1
- package/.next/standalone/.next/server/chunks/ssr/[root-of-the-server]__092s1ta._.js +2 -2
- package/.next/standalone/.next/server/chunks/ssr/{[root-of-the-server]__0~kmh8w._.js → [root-of-the-server]__096k.db._.js} +2 -2
- package/.next/standalone/.next/server/chunks/ssr/[root-of-the-server]__09icjsf._.js +2 -2
- package/.next/standalone/.next/server/chunks/ssr/[root-of-the-server]__0g.lg8b._.js +2 -2
- package/.next/standalone/.next/server/chunks/ssr/[root-of-the-server]__0h..k-e._.js +2 -2
- package/.next/standalone/.next/server/chunks/ssr/{[root-of-the-server]__0rh.18_._.js → [root-of-the-server]__0kyh86x._.js} +2 -2
- package/.next/standalone/.next/server/chunks/ssr/[root-of-the-server]__0okos0k._.js +2 -2
- package/.next/standalone/.next/server/chunks/ssr/[root-of-the-server]__0w6l33k._.js +2 -2
- package/.next/standalone/.next/server/chunks/ssr/[root-of-the-server]__11pa2ra._.js +2 -2
- package/.next/standalone/.next/server/chunks/ssr/[root-of-the-server]__12t-wym._.js +2 -2
- package/.next/standalone/.next/server/chunks/ssr/_10lm7or._.js +2 -2
- package/.next/standalone/.next/server/chunks/ssr/app_global-error_tsx_0xerkr6._.js +1 -1
- package/.next/standalone/.next/server/chunks/ssr/app_policies_hooks-client_tsx_0q-m0y-._.js +1 -1
- package/.next/standalone/.next/server/middleware-build-manifest.js +3 -3
- package/.next/standalone/.next/server/pages/404.html +2 -2
- package/.next/standalone/.next/server/pages/500.html +1 -1
- package/.next/standalone/.next/server/server-reference-manifest.js +1 -1
- package/.next/standalone/.next/server/server-reference-manifest.json +9 -9
- package/.next/standalone/.next/static/chunks/{0gbf4cphy8ksq.js → 0-dm_9a6nsc2l.js} +1 -1
- package/.next/standalone/.next/static/chunks/{12~yi9oj8av8p.js → 01pmw1-asbek~.js} +2 -2
- package/.next/standalone/.next/static/chunks/{0v.yd0kg_ld3r.js → 051m32nx~n5yr.js} +1 -1
- package/.next/standalone/.next/static/chunks/{09_k80d~cq2wg.js → 0a-yctdwn368y.js} +1 -1
- package/.next/standalone/.next/static/chunks/{0bvhsa6zva2o..js → 0ksdlt_1hucdm.js} +1 -1
- package/.next/standalone/.next/static/chunks/{01b~z8f1ws0rk.js → 0l-mu4okl-cj1.js} +1 -1
- package/.next/standalone/.next/static/chunks/{08t08igdql9yt.js → 0mazj-p-~2kc6.js} +1 -1
- package/.next/standalone/.next/static/chunks/0qakntsrpc~1j.js +6 -0
- package/.next/standalone/.next/static/chunks/{03rz6ykw-a2xi.js → 156zca6aewyr-.js} +1 -1
- package/.next/standalone/CHANGELOG.md +18 -0
- package/.next/standalone/bin/failproofai.mjs +91 -4
- package/.next/standalone/dist/cli.mjs +1156 -55
- package/.next/standalone/docs/ar/built-in-policies.mdx +140 -103
- package/.next/standalone/docs/ar/custom-policies.mdx +72 -72
- package/.next/standalone/docs/ar/examples.mdx +86 -33
- package/.next/standalone/docs/ar/getting-started.mdx +82 -29
- package/.next/standalone/docs/built-in-policies.mdx +3 -3
- package/.next/standalone/docs/de/built-in-policies.mdx +97 -60
- package/.next/standalone/docs/de/custom-policies.mdx +56 -56
- package/.next/standalone/docs/de/examples.mdx +72 -18
- package/.next/standalone/docs/de/getting-started.mdx +72 -20
- package/.next/standalone/docs/es/built-in-policies.mdx +91 -54
- package/.next/standalone/docs/es/custom-policies.mdx +55 -55
- package/.next/standalone/docs/es/examples.mdx +73 -19
- package/.next/standalone/docs/es/getting-started.mdx +72 -20
- package/.next/standalone/docs/fr/built-in-policies.mdx +99 -62
- package/.next/standalone/docs/fr/custom-policies.mdx +51 -51
- package/.next/standalone/docs/fr/examples.mdx +78 -24
- package/.next/standalone/docs/fr/getting-started.mdx +65 -13
- package/.next/standalone/docs/he/built-in-policies.mdx +139 -99
- package/.next/standalone/docs/he/custom-policies.mdx +75 -75
- package/.next/standalone/docs/he/examples.mdx +87 -33
- package/.next/standalone/docs/he/getting-started.mdx +84 -33
- package/.next/standalone/docs/hi/built-in-policies.mdx +203 -166
- package/.next/standalone/docs/hi/custom-policies.mdx +71 -70
- package/.next/standalone/docs/hi/examples.mdx +90 -36
- package/.next/standalone/docs/hi/getting-started.mdx +80 -27
- package/.next/standalone/docs/i18n/README.ar.md +69 -69
- package/.next/standalone/docs/i18n/README.de.md +46 -46
- package/.next/standalone/docs/i18n/README.es.md +42 -42
- package/.next/standalone/docs/i18n/README.fr.md +39 -39
- package/.next/standalone/docs/i18n/README.he.md +83 -83
- package/.next/standalone/docs/i18n/README.hi.md +69 -69
- package/.next/standalone/docs/i18n/README.it.md +72 -72
- package/.next/standalone/docs/i18n/README.ja.md +71 -71
- package/.next/standalone/docs/i18n/README.ko.md +52 -52
- package/.next/standalone/docs/i18n/README.pt-br.md +44 -44
- package/.next/standalone/docs/i18n/README.ru.md +66 -66
- package/.next/standalone/docs/i18n/README.tr.md +82 -83
- package/.next/standalone/docs/i18n/README.vi.md +70 -71
- package/.next/standalone/docs/i18n/README.zh.md +51 -51
- package/.next/standalone/docs/it/built-in-policies.mdx +115 -78
- package/.next/standalone/docs/it/custom-policies.mdx +69 -69
- package/.next/standalone/docs/it/examples.mdx +93 -39
- package/.next/standalone/docs/it/getting-started.mdx +73 -21
- package/.next/standalone/docs/ja/built-in-policies.mdx +155 -118
- package/.next/standalone/docs/ja/custom-policies.mdx +71 -71
- package/.next/standalone/docs/ja/examples.mdx +76 -22
- package/.next/standalone/docs/ja/getting-started.mdx +65 -13
- package/.next/standalone/docs/ko/built-in-policies.mdx +103 -66
- package/.next/standalone/docs/ko/custom-policies.mdx +67 -67
- package/.next/standalone/docs/ko/examples.mdx +87 -33
- package/.next/standalone/docs/ko/getting-started.mdx +61 -9
- package/.next/standalone/docs/pt-br/built-in-policies.mdx +72 -35
- package/.next/standalone/docs/pt-br/custom-policies.mdx +56 -56
- package/.next/standalone/docs/pt-br/examples.mdx +78 -24
- package/.next/standalone/docs/pt-br/getting-started.mdx +64 -12
- package/.next/standalone/docs/ru/built-in-policies.mdx +135 -98
- package/.next/standalone/docs/ru/custom-policies.mdx +82 -81
- package/.next/standalone/docs/ru/examples.mdx +77 -22
- package/.next/standalone/docs/ru/getting-started.mdx +74 -22
- package/.next/standalone/docs/tr/built-in-policies.mdx +126 -89
- package/.next/standalone/docs/tr/custom-policies.mdx +59 -60
- package/.next/standalone/docs/tr/examples.mdx +97 -42
- package/.next/standalone/docs/tr/getting-started.mdx +75 -23
- package/.next/standalone/docs/vi/built-in-policies.mdx +116 -81
- package/.next/standalone/docs/vi/custom-policies.mdx +68 -68
- package/.next/standalone/docs/vi/examples.mdx +93 -38
- package/.next/standalone/docs/vi/getting-started.mdx +74 -22
- package/.next/standalone/docs/zh/built-in-policies.mdx +117 -82
- package/.next/standalone/docs/zh/custom-policies.mdx +49 -49
- package/.next/standalone/docs/zh/examples.mdx +90 -36
- package/.next/standalone/docs/zh/getting-started.mdx +73 -21
- package/.next/standalone/package.json +1 -1
- package/.next/standalone/server.js +1 -1
- package/.next/standalone/src/auth/login.ts +104 -0
- package/.next/standalone/src/auth/logout.ts +50 -0
- package/.next/standalone/src/auth/token-store.ts +64 -0
- package/.next/standalone/src/hooks/builtin-policies.ts +27 -21
- package/.next/standalone/src/hooks/handler.ts +35 -15
- package/.next/standalone/src/relay/daemon.ts +362 -0
- package/.next/standalone/src/relay/pid.ts +76 -0
- package/.next/standalone/src/relay/queue.ts +225 -0
- package/bin/failproofai.mjs +91 -4
- package/dist/cli.mjs +1156 -55
- package/package.json +1 -1
- package/src/auth/login.ts +104 -0
- package/src/auth/logout.ts +50 -0
- package/src/auth/token-store.ts +64 -0
- package/src/hooks/builtin-policies.ts +27 -21
- package/src/hooks/handler.ts +35 -15
- package/src/relay/daemon.ts +362 -0
- package/src/relay/pid.ts +76 -0
- package/src/relay/queue.ts +225 -0
- package/.next/standalone/.next/static/chunks/0wlyoif4_kj_t.js +0 -6
- /package/.next/standalone/.next/static/{CkmOT-ZvDN-sVULinGVKT → r-wX0MuAfCjbhJm3phQc8}/_buildManifest.js +0 -0
- /package/.next/standalone/.next/static/{CkmOT-ZvDN-sVULinGVKT → r-wX0MuAfCjbhJm3phQc8}/_clientMiddlewareManifest.js +0 -0
- /package/.next/standalone/.next/static/{CkmOT-ZvDN-sVULinGVKT → r-wX0MuAfCjbhJm3phQc8}/_ssgManifest.js +0 -0
|
@@ -23,51 +23,51 @@
|
|
|
23
23
|
|
|
24
24
|
**Traduzioni**: [简体中文](docs/i18n/README.zh.md) | [日本語](docs/i18n/README.ja.md) | [한국어](docs/i18n/README.ko.md) | [Español](docs/i18n/README.es.md) | [Português](docs/i18n/README.pt-br.md) | [Deutsch](docs/i18n/README.de.md) | [Français](docs/i18n/README.fr.md) | [Русский](docs/i18n/README.ru.md) | [हिन्दी](docs/i18n/README.hi.md) | [Türkçe](docs/i18n/README.tr.md) | [Tiếng Việt](docs/i18n/README.vi.md) | [Italiano](docs/i18n/README.it.md) | [العربية](docs/i18n/README.ar.md) | [עברית](docs/i18n/README.he.md)
|
|
25
25
|
|
|
26
|
-
Il modo più semplice per gestire le
|
|
26
|
+
Il modo più semplice per gestire le politiche che mantengono i tuoi agenti AI affidabili, focalizzati e in esecuzione autonoma - per **Claude Code** e **Agents SDK**.
|
|
27
27
|
|
|
28
|
-
- **30
|
|
29
|
-
- **
|
|
30
|
-
- **Configurazione Facile** -
|
|
31
|
-
- **Monitoraggio Agenti** - Vedi cosa hanno fatto i tuoi agenti mentre eri
|
|
28
|
+
- **30 Politiche Integrate** - Individua i fallimenti comuni degli agenti direttamente. Blocca i comandi distruttivi, previeni le fughe di segreti, mantieni gli agenti entro i confini del progetto, rileva i loop e molto altro.
|
|
29
|
+
- **Politiche Personalizzate** - Scrivi le tue regole di affidabilità in JavaScript. Usa l'API `allow`/`deny`/`instruct` per applicare convenzioni, prevenire derive, limitare operazioni o integrarti con sistemi esterni.
|
|
30
|
+
- **Configurazione Facile** - Regola qualsiasi politica senza scrivere codice. Imposta allowlist, rami protetti, soglie per progetto o globalmente. La configurazione a tre livelli si unisce automaticamente.
|
|
31
|
+
- **Monitoraggio degli Agenti** - Vedi cosa hanno fatto i tuoi agenti mentre eri via. Sfoglia le sessioni, ispeziona ogni chiamata di tool e rivedi esattamente dove le politiche sono state attivate.
|
|
32
32
|
|
|
33
|
-
Tutto
|
|
33
|
+
Tutto viene eseguito localmente - nessun dato lascia il tuo computer.
|
|
34
34
|
|
|
35
35
|
---
|
|
36
36
|
|
|
37
37
|
## Requisiti
|
|
38
38
|
|
|
39
39
|
- Node.js >= 20.9.0
|
|
40
|
-
- Bun >= 1.3.0 (
|
|
40
|
+
- Bun >= 1.3.0 (facoltativo - necessario solo per lo sviluppo / compilazione da source)
|
|
41
41
|
|
|
42
42
|
---
|
|
43
43
|
|
|
44
|
-
##
|
|
44
|
+
## Installazione
|
|
45
45
|
|
|
46
46
|
```bash
|
|
47
47
|
npm install -g failproofai
|
|
48
|
-
#
|
|
48
|
+
# oppure
|
|
49
49
|
bun add -g failproofai
|
|
50
50
|
```
|
|
51
51
|
|
|
52
52
|
---
|
|
53
53
|
|
|
54
|
-
##
|
|
54
|
+
## Guida Rapida
|
|
55
55
|
|
|
56
|
-
### 1. Abilita le
|
|
56
|
+
### 1. Abilita le politiche globalmente
|
|
57
57
|
|
|
58
58
|
```bash
|
|
59
59
|
failproofai policies --install
|
|
60
60
|
```
|
|
61
61
|
|
|
62
|
-
Scrive
|
|
62
|
+
Scrive voci di hook in `~/.claude/settings.json`. Claude Code richiamerà failproofai prima e dopo ogni chiamata di tool.
|
|
63
63
|
|
|
64
|
-
### 2. Avvia
|
|
64
|
+
### 2. Avvia la dashboard
|
|
65
65
|
|
|
66
66
|
```bash
|
|
67
67
|
failproofai
|
|
68
68
|
```
|
|
69
69
|
|
|
70
|
-
Apre `http://localhost:8020` - sfoglia le sessioni, ispeziona i log, gestisci le
|
|
70
|
+
Apre `http://localhost:8020` - sfoglia le sessioni, ispeziona i log, gestisci le politiche.
|
|
71
71
|
|
|
72
72
|
### 3. Controlla cosa è attivo
|
|
73
73
|
|
|
@@ -77,27 +77,27 @@ failproofai policies
|
|
|
77
77
|
|
|
78
78
|
---
|
|
79
79
|
|
|
80
|
-
## Installazione delle
|
|
80
|
+
## Installazione delle Politiche
|
|
81
81
|
|
|
82
82
|
### Ambiti
|
|
83
83
|
|
|
84
84
|
| Ambito | Comando | Dove scrive |
|
|
85
|
-
|
|
85
|
+
|--------|---------|-----------|
|
|
86
86
|
| Globale (predefinito) | `failproofai policies --install` | `~/.claude/settings.json` |
|
|
87
87
|
| Progetto | `failproofai policies --install --scope project` | `.claude/settings.json` |
|
|
88
88
|
| Locale | `failproofai policies --install --scope local` | `.claude/settings.local.json` |
|
|
89
89
|
|
|
90
|
-
### Installa
|
|
90
|
+
### Installa politiche specifiche
|
|
91
91
|
|
|
92
92
|
```bash
|
|
93
93
|
failproofai policies --install block-sudo block-rm-rf sanitize-api-keys
|
|
94
94
|
```
|
|
95
95
|
|
|
96
|
-
### Rimuovi
|
|
96
|
+
### Rimuovi politiche
|
|
97
97
|
|
|
98
98
|
```bash
|
|
99
99
|
failproofai policies --uninstall
|
|
100
|
-
#
|
|
100
|
+
# oppure per uno specifico ambito:
|
|
101
101
|
failproofai policies --uninstall --scope project
|
|
102
102
|
```
|
|
103
103
|
|
|
@@ -105,7 +105,7 @@ failproofai policies --uninstall --scope project
|
|
|
105
105
|
|
|
106
106
|
## Configurazione
|
|
107
107
|
|
|
108
|
-
La configurazione delle
|
|
108
|
+
La configurazione delle politiche si trova in `~/.failproofai/policies-config.json` (globale) o `.failproofai/policies-config.json` nel tuo progetto (per progetto).
|
|
109
109
|
|
|
110
110
|
```json
|
|
111
111
|
{
|
|
@@ -142,44 +142,44 @@ La configurazione delle policy si trova in `~/.failproofai/policies-config.json`
|
|
|
142
142
|
|
|
143
143
|
---
|
|
144
144
|
|
|
145
|
-
##
|
|
146
|
-
|
|
147
|
-
|
|
|
148
|
-
|
|
149
|
-
| `block-sudo` | Previeni
|
|
150
|
-
| `block-rm-rf` | Previeni l'eliminazione accidentale
|
|
151
|
-
| `block-curl-pipe-sh` | Previeni
|
|
152
|
-
| `block-failproofai-commands` | Previeni l'
|
|
153
|
-
| `sanitize-jwt` |
|
|
154
|
-
| `sanitize-api-keys` |
|
|
155
|
-
| `sanitize-connection-strings` |
|
|
145
|
+
## Politiche integrate
|
|
146
|
+
|
|
147
|
+
| Politica | Descrizione | Configurabile |
|
|
148
|
+
|----------|-------------|:---:|
|
|
149
|
+
| `block-sudo` | Previeni agli agenti di eseguire comandi di sistema privilegiati | `allowPatterns` |
|
|
150
|
+
| `block-rm-rf` | Previeni l'eliminazione accidentale di file ricorsiva | `allowPaths` |
|
|
151
|
+
| `block-curl-pipe-sh` | Previeni agli agenti di eseguire script non attendibili tramite shell | |
|
|
152
|
+
| `block-failproofai-commands` | Previeni l'auto-disinstallazione | |
|
|
153
|
+
| `sanitize-jwt` | Interrompi la perdita di token JWT nel contesto dell'agente | |
|
|
154
|
+
| `sanitize-api-keys` | Interrompi la perdita di chiavi API nel contesto dell'agente | `additionalPatterns` |
|
|
155
|
+
| `sanitize-connection-strings` | Interrompi la perdita di credenziali del database nel contesto dell'agente | |
|
|
156
156
|
| `sanitize-private-key-content` | Redigi i blocchi di chiave privata PEM dall'output | |
|
|
157
|
-
| `sanitize-bearer-tokens` | Redigi i token
|
|
158
|
-
| `block-env-files` |
|
|
159
|
-
| `protect-env-vars` | Previeni
|
|
157
|
+
| `sanitize-bearer-tokens` | Redigi i token Bearer di autorizzazione dall'output | |
|
|
158
|
+
| `block-env-files` | Impedisci agli agenti di leggere file .env | |
|
|
159
|
+
| `protect-env-vars` | Previeni agli agenti di stampare variabili d'ambiente | |
|
|
160
160
|
| `block-read-outside-cwd` | Mantieni gli agenti entro i confini del progetto | `allowPaths` |
|
|
161
|
-
| `block-secrets-write` | Previeni le scritture
|
|
161
|
+
| `block-secrets-write` | Previeni le scritture su file di chiave privata e certificati | `additionalPatterns` |
|
|
162
162
|
| `block-push-master` | Previeni i push accidentali a main/master | `protectedBranches` |
|
|
163
|
-
| `block-work-on-main` | Mantieni gli agenti
|
|
163
|
+
| `block-work-on-main` | Mantieni gli agenti fuori dai rami protetti | `protectedBranches` |
|
|
164
164
|
| `block-force-push` | Previeni `git push --force` | |
|
|
165
|
-
| `warn-git-amend` | Ricorda agli agenti prima di
|
|
165
|
+
| `warn-git-amend` | Ricorda agli agenti prima di correggere i commit | |
|
|
166
166
|
| `warn-git-stash-drop` | Ricorda agli agenti prima di eliminare gli stash | |
|
|
167
|
-
| `warn-all-files-staged` |
|
|
168
|
-
| `warn-destructive-sql` |
|
|
169
|
-
| `warn-schema-alteration` |
|
|
170
|
-
| `warn-large-file-write` |
|
|
171
|
-
| `warn-package-publish` |
|
|
172
|
-
| `warn-background-process` |
|
|
173
|
-
| `warn-global-package-install` |
|
|
174
|
-
| …e
|
|
167
|
+
| `warn-all-files-staged` | Individua l'accidentale `git add -A` | |
|
|
168
|
+
| `warn-destructive-sql` | Individua DROP/DELETE SQL prima dell'esecuzione | |
|
|
169
|
+
| `warn-schema-alteration` | Individua ALTER TABLE prima dell'esecuzione | |
|
|
170
|
+
| `warn-large-file-write` | Individua le scritture di file inaspettatamente grandi | `thresholdKb` |
|
|
171
|
+
| `warn-package-publish` | Individua l'accidentale `npm publish` | |
|
|
172
|
+
| `warn-background-process` | Individua i lanci di processi di background non intenzionali | |
|
|
173
|
+
| `warn-global-package-install` | Individua le installazioni di pacchetti globali non intenzionali | |
|
|
174
|
+
| …e altri | | |
|
|
175
175
|
|
|
176
|
-
Dettagli completi delle
|
|
176
|
+
Dettagli completi delle politiche e riferimento dei parametri: [docs/built-in-policies.mdx](docs/built-in-policies.mdx)
|
|
177
177
|
|
|
178
178
|
---
|
|
179
179
|
|
|
180
|
-
##
|
|
180
|
+
## Politiche Personalizzate
|
|
181
181
|
|
|
182
|
-
Scrivi le tue
|
|
182
|
+
Scrivi le tue politiche per mantenere gli agenti affidabili e focalizzati:
|
|
183
183
|
|
|
184
184
|
```js
|
|
185
185
|
import { customPolicies, allow, deny, instruct } from "failproofai";
|
|
@@ -203,35 +203,35 @@ Installa con:
|
|
|
203
203
|
failproofai policies --install --custom ./my-policies.js
|
|
204
204
|
```
|
|
205
205
|
|
|
206
|
-
###
|
|
206
|
+
### Helper di Decisione
|
|
207
207
|
|
|
208
208
|
| Funzione | Effetto |
|
|
209
209
|
|----------|--------|
|
|
210
|
-
| `allow()` |
|
|
211
|
-
| `allow(message)` |
|
|
210
|
+
| `allow()` | Autorizza l'operazione |
|
|
211
|
+
| `allow(message)` | Autorizza e invia il contesto informativo a Claude |
|
|
212
212
|
| `deny(message)` | Blocca l'operazione; il messaggio viene mostrato a Claude |
|
|
213
213
|
| `instruct(message)` | Aggiungi contesto al prompt di Claude; non blocca |
|
|
214
214
|
|
|
215
|
-
### Oggetto
|
|
215
|
+
### Oggetto Contesto (`ctx`)
|
|
216
216
|
|
|
217
217
|
| Campo | Tipo | Descrizione |
|
|
218
218
|
|-------|------|-------------|
|
|
219
219
|
| `eventType` | `string` | `"PreToolUse"`, `"PostToolUse"`, `"Notification"`, `"Stop"` |
|
|
220
|
-
| `toolName` | `string` |
|
|
221
|
-
| `toolInput` | `object` | Parametri di input
|
|
222
|
-
| `payload` | `object` | Payload grezzo completo
|
|
220
|
+
| `toolName` | `string` | Tool being called (`"Bash"`, `"Write"`, `"Read"`, …) |
|
|
221
|
+
| `toolInput` | `object` | Parametri di input del tool |
|
|
222
|
+
| `payload` | `object` | Payload di evento grezzo completo |
|
|
223
223
|
| `session.cwd` | `string` | Directory di lavoro della sessione Claude Code |
|
|
224
224
|
| `session.sessionId` | `string` | Identificatore della sessione |
|
|
225
|
-
| `session.transcriptPath` | `string` | Percorso del file
|
|
225
|
+
| `session.transcriptPath` | `string` | Percorso del file transcript della sessione |
|
|
226
226
|
|
|
227
|
-
I hook
|
|
227
|
+
I custom hook supportano importazioni locali transitive, async/await e accesso a `process.env`. Gli errori sono fail-open (registrati in `~/.failproofai/hook.log`, le politiche integrate continuano). Vedi [docs/custom-hooks.mdx](docs/custom-hooks.mdx) per la guida completa.
|
|
228
228
|
|
|
229
|
-
###
|
|
229
|
+
### Politiche Basate su Convenzioni
|
|
230
230
|
|
|
231
|
-
|
|
231
|
+
Inserisci file `*policies.{js,mjs,ts}` in `.failproofai/policies/` e vengono caricati automaticamente - nessun flag o modifica di configurazione necessaria. Esegui il commit della directory su git e ogni membro del team ottiene automaticamente gli stessi standard di qualità.
|
|
232
232
|
|
|
233
233
|
```text
|
|
234
|
-
# Livello di progetto —
|
|
234
|
+
# Livello di progetto — eseguito il commit su git, condiviso con il team
|
|
235
235
|
.failproofai/policies/security-policies.mjs
|
|
236
236
|
.failproofai/policies/workflow-policies.mjs
|
|
237
237
|
|
|
@@ -239,15 +239,15 @@ Metti i file `*policies.{js,mjs,ts}` in `.failproofai/policies/` e vengono caric
|
|
|
239
239
|
~/.failproofai/policies/my-policies.mjs
|
|
240
240
|
```
|
|
241
241
|
|
|
242
|
-
Entrambi i livelli
|
|
242
|
+
Entrambi i livelli vengono caricati (unione). I file vengono caricati alfabeticamente all'interno di ogni directory. Prefissa con `01-`, `02-`, ecc. per controllare l'ordine. Man mano che il tuo team scopre nuovi fallimenti, aggiungi una politica e esegui il push - chiunque ottiene l'aggiornamento al prossimo pull. Vedi [examples/convention-policies/](examples/convention-policies/) per esempi pronti all'uso.
|
|
243
243
|
|
|
244
244
|
---
|
|
245
245
|
|
|
246
246
|
## Telemetria
|
|
247
247
|
|
|
248
|
-
Failproof AI raccoglie telemetria di utilizzo anonima tramite PostHog per comprendere l'utilizzo delle funzioni.
|
|
248
|
+
Failproof AI raccoglie telemetria di utilizzo anonima tramite PostHog per comprendere l'utilizzo delle funzioni. Il contenuto della sessione, i nomi dei file, gli input dei tool o le informazioni personali non vengono mai inviati.
|
|
249
249
|
|
|
250
|
-
|
|
250
|
+
Disabilita:
|
|
251
251
|
|
|
252
252
|
```bash
|
|
253
253
|
FAILPROOFAI_TELEMETRY_DISABLED=1 failproofai
|
|
@@ -260,12 +260,12 @@ FAILPROOFAI_TELEMETRY_DISABLED=1 failproofai
|
|
|
260
260
|
| Guida | Descrizione |
|
|
261
261
|
|-------|-------------|
|
|
262
262
|
| [Getting Started](docs/getting-started.mdx) | Installazione e primi passi |
|
|
263
|
-
| [Built-in Policies](docs/built-in-policies.mdx) | Tutte le 30
|
|
264
|
-
| [Custom Policies](docs/custom-policies.mdx) | Scrivi le tue
|
|
263
|
+
| [Built-in Policies](docs/built-in-policies.mdx) | Tutte le 30 politiche integrate con parametri |
|
|
264
|
+
| [Custom Policies](docs/custom-policies.mdx) | Scrivi le tue politiche |
|
|
265
265
|
| [Configuration](docs/configuration.mdx) | Formato del file di configurazione e unione degli ambiti |
|
|
266
|
-
| [Dashboard](docs/dashboard.mdx) | Monitora le sessioni e
|
|
266
|
+
| [Dashboard](docs/dashboard.mdx) | Monitora le sessioni e rivedi l'attività delle politiche |
|
|
267
267
|
| [Architecture](docs/architecture.mdx) | Come funziona il sistema di hook |
|
|
268
|
-
| [Testing](docs/testing.mdx) |
|
|
268
|
+
| [Testing](docs/testing.mdx) | Esecuzione di test e scrittura di nuovi |
|
|
269
269
|
|
|
270
270
|
### Esegui la documentazione localmente
|
|
271
271
|
|
|
@@ -274,7 +274,7 @@ docker build -f Dockerfile.docs -t failproofai-docs .
|
|
|
274
274
|
docker run --rm -p 3000:3000 failproofai-docs
|
|
275
275
|
```
|
|
276
276
|
|
|
277
|
-
Apre il sito della documentazione Mintlify su `http://localhost:3000`. Il
|
|
277
|
+
Apre il sito della documentazione Mintlify su `http://localhost:3000`. Il container guarda i cambiamenti se monti la directory docs:
|
|
278
278
|
|
|
279
279
|
```bash
|
|
280
280
|
docker run --rm -p 3000:3000 -v $(pwd)/docs:/app/docs failproofai-docs
|
|
@@ -282,11 +282,11 @@ docker run --rm -p 3000:3000 -v $(pwd)/docs:/app/docs failproofai-docs
|
|
|
282
282
|
|
|
283
283
|
---
|
|
284
284
|
|
|
285
|
-
## Nota per i
|
|
285
|
+
## Nota per i contribuenti di failproofai
|
|
286
286
|
|
|
287
|
-
Il
|
|
287
|
+
Il `.claude/settings.json` di questo repo usa `bun ./bin/failproofai.mjs --hook <EventType>` invece del comando standard `npx -y failproofai`. Questo è perché eseguire `npx -y failproofai` all'interno del progetto failproofai stesso crea un conflitto di auto-referenza.
|
|
288
288
|
|
|
289
|
-
Per tutti gli altri
|
|
289
|
+
Per tutti gli altri repo, l'approccio consigliato è `npx -y failproofai`, installato tramite:
|
|
290
290
|
|
|
291
291
|
```bash
|
|
292
292
|
failproofai policies --install --scope project
|
|
@@ -304,4 +304,4 @@ Vedi [LICENSE](LICENSE).
|
|
|
304
304
|
|
|
305
305
|
---
|
|
306
306
|
|
|
307
|
-
Costruito e
|
|
307
|
+
Costruito e Mantenuto da **ExosphereHost: Reliability Research Lab for Your Agents**. Aiutiamo le aziende e le startup a migliorare l'affidabilità dei loro agenti AI attraverso i nostri stessi agenti, software e competenze. Scopri di più su [exosphere.host](https://exosphere.host).
|
|
@@ -23,21 +23,21 @@
|
|
|
23
23
|
|
|
24
24
|
**翻訳**: [简体中文](docs/i18n/README.zh.md) | [日本語](docs/i18n/README.ja.md) | [한국어](docs/i18n/README.ko.md) | [Español](docs/i18n/README.es.md) | [Português](docs/i18n/README.pt-br.md) | [Deutsch](docs/i18n/README.de.md) | [Français](docs/i18n/README.fr.md) | [Русский](docs/i18n/README.ru.md) | [हिन्दी](docs/i18n/README.hi.md) | [Türkçe](docs/i18n/README.tr.md) | [Tiếng Việt](docs/i18n/README.vi.md) | [Italiano](docs/i18n/README.it.md) | [العربية](docs/i18n/README.ar.md) | [עברית](docs/i18n/README.he.md)
|
|
25
25
|
|
|
26
|
-
AI
|
|
26
|
+
AIエージェントを安定稼働させ、タスクに集中させ、自律的に動かし続けるためのポリシー管理ツール — **Claude Code** と **Agents SDK** に対応。
|
|
27
27
|
|
|
28
|
-
- **30種類の組み込みポリシー** -
|
|
29
|
-
- **カスタムポリシー** - JavaScriptで独自の信頼性ルールを記述。`allow`/`deny`/`instruct` API
|
|
30
|
-
-
|
|
31
|
-
- **エージェントモニター** -
|
|
28
|
+
- **30種類の組み込みポリシー** - よくあるエージェントの障害パターンをすぐに検出。破壊的なコマンドのブロック、シークレット漏洩の防止、プロジェクト境界内への制限、ループ検出など。
|
|
29
|
+
- **カスタムポリシー** - JavaScriptで独自の信頼性ルールを記述。`allow`/`deny`/`instruct` APIを使って規約の強制、ドリフトの防止、操作のゲート制御、外部システムとの連携が可能。
|
|
30
|
+
- **シンプルな設定** - コードを書かずにどのポリシーも調整できます。許可リスト、保護ブランチ、しきい値をプロジェクト単位またはグローバルに設定。3スコープの設定が自動マージされます。
|
|
31
|
+
- **エージェントモニター** - 離席中にエージェントが何をしたか把握できます。セッションの閲覧、ツール呼び出しの詳細確認、ポリシーが発火した箇所のレビューが可能。
|
|
32
32
|
|
|
33
|
-
すべてローカルで動作 —
|
|
33
|
+
すべてローカルで動作 — データは外部に送信されません。
|
|
34
34
|
|
|
35
35
|
---
|
|
36
36
|
|
|
37
37
|
## 動作要件
|
|
38
38
|
|
|
39
39
|
- Node.js >= 20.9.0
|
|
40
|
-
- Bun >= 1.3.0(任意 — 開発時またはソースからビルドする場合のみ必要)
|
|
40
|
+
- Bun >= 1.3.0 (任意 — 開発時またはソースからビルドする場合のみ必要)
|
|
41
41
|
|
|
42
42
|
---
|
|
43
43
|
|
|
@@ -53,23 +53,23 @@ bun add -g failproofai
|
|
|
53
53
|
|
|
54
54
|
## クイックスタート
|
|
55
55
|
|
|
56
|
-
### 1.
|
|
56
|
+
### 1. ポリシーをグローバルに有効化する
|
|
57
57
|
|
|
58
58
|
```bash
|
|
59
59
|
failproofai policies --install
|
|
60
60
|
```
|
|
61
61
|
|
|
62
|
-
`~/.claude/settings.json`
|
|
62
|
+
`~/.claude/settings.json` にフックエントリを書き込みます。これにより Claude Code は各ツール呼び出しの前後に failproofai を呼び出すようになります。
|
|
63
63
|
|
|
64
|
-
### 2.
|
|
64
|
+
### 2. ダッシュボードを起動する
|
|
65
65
|
|
|
66
66
|
```bash
|
|
67
67
|
failproofai
|
|
68
68
|
```
|
|
69
69
|
|
|
70
|
-
`http://localhost:8020` が開きます —
|
|
70
|
+
`http://localhost:8020` が開きます — セッションの閲覧、ログの確認、ポリシーの管理ができます。
|
|
71
71
|
|
|
72
|
-
### 3.
|
|
72
|
+
### 3. 有効なポリシーを確認する
|
|
73
73
|
|
|
74
74
|
```bash
|
|
75
75
|
failproofai policies
|
|
@@ -87,13 +87,13 @@ failproofai policies
|
|
|
87
87
|
| プロジェクト | `failproofai policies --install --scope project` | `.claude/settings.json` |
|
|
88
88
|
| ローカル | `failproofai policies --install --scope local` | `.claude/settings.local.json` |
|
|
89
89
|
|
|
90
|
-
###
|
|
90
|
+
### 特定のポリシーをインストールする
|
|
91
91
|
|
|
92
92
|
```bash
|
|
93
93
|
failproofai policies --install block-sudo block-rm-rf sanitize-api-keys
|
|
94
94
|
```
|
|
95
95
|
|
|
96
|
-
###
|
|
96
|
+
### ポリシーを削除する
|
|
97
97
|
|
|
98
98
|
```bash
|
|
99
99
|
failproofai policies --uninstall
|
|
@@ -138,48 +138,48 @@ failproofai policies --uninstall --scope project
|
|
|
138
138
|
}
|
|
139
139
|
```
|
|
140
140
|
|
|
141
|
-
**3つの設定スコープ**は自動的にマージされます(プロジェクト → ローカル →
|
|
141
|
+
**3つの設定スコープ**は自動的にマージされます(プロジェクト → ローカル → グローバル)。完全なマージルールは [docs/configuration.mdx](docs/configuration.mdx) を参照してください。
|
|
142
142
|
|
|
143
143
|
---
|
|
144
144
|
|
|
145
145
|
## 組み込みポリシー
|
|
146
146
|
|
|
147
|
-
| ポリシー | 説明 |
|
|
147
|
+
| ポリシー | 説明 | 設定可能なパラメータ |
|
|
148
148
|
|--------|-------------|:---:|
|
|
149
|
-
| `block-sudo` |
|
|
150
|
-
| `block-rm-rf` |
|
|
151
|
-
| `block-curl-pipe-sh` |
|
|
152
|
-
| `block-failproofai-commands` |
|
|
153
|
-
| `sanitize-jwt` | JWT
|
|
154
|
-
| `sanitize-api-keys` | API
|
|
155
|
-
| `sanitize-connection-strings` |
|
|
156
|
-
| `sanitize-private-key-content` | 出力からPEM
|
|
157
|
-
| `sanitize-bearer-tokens` | 出力からAuthorization Bearer
|
|
158
|
-
| `block-env-files` | エージェントが.env
|
|
159
|
-
| `protect-env-vars` |
|
|
160
|
-
| `block-read-outside-cwd` |
|
|
161
|
-
| `block-secrets-write` |
|
|
162
|
-
| `block-push-master` | main/master
|
|
163
|
-
| `block-work-on-main` |
|
|
164
|
-
| `block-force-push` | `git push --force`
|
|
165
|
-
| `warn-git-amend` |
|
|
166
|
-
| `warn-git-stash-drop` |
|
|
167
|
-
| `warn-all-files-staged` | 誤った `git add -A`
|
|
168
|
-
| `warn-destructive-sql` | 実行前にDROP/DELETE SQL
|
|
169
|
-
| `warn-schema-alteration` | 実行前にALTER TABLE
|
|
170
|
-
| `warn-large-file-write` |
|
|
171
|
-
| `warn-package-publish` | 誤った `npm publish`
|
|
172
|
-
| `warn-background-process` |
|
|
173
|
-
| `warn-global-package-install` |
|
|
149
|
+
| `block-sudo` | エージェントが特権システムコマンドを実行するのを防ぐ | `allowPatterns` |
|
|
150
|
+
| `block-rm-rf` | 誤った再帰的ファイル削除を防ぐ | `allowPaths` |
|
|
151
|
+
| `block-curl-pipe-sh` | 信頼できないスクリプトをシェルにパイプするのを防ぐ | |
|
|
152
|
+
| `block-failproofai-commands` | 自己アンインストールを防ぐ | |
|
|
153
|
+
| `sanitize-jwt` | JWTトークンがエージェントコンテキストに漏洩するのを止める | |
|
|
154
|
+
| `sanitize-api-keys` | APIキーがエージェントコンテキストに漏洩するのを止める | `additionalPatterns` |
|
|
155
|
+
| `sanitize-connection-strings` | データベース認証情報がエージェントコンテキストに漏洩するのを止める | |
|
|
156
|
+
| `sanitize-private-key-content` | 出力からPEM秘密鍵ブロックを削除する | |
|
|
157
|
+
| `sanitize-bearer-tokens` | 出力からAuthorization Bearerトークンを削除する | |
|
|
158
|
+
| `block-env-files` | エージェントが.envファイルを読み取るのを防ぐ | |
|
|
159
|
+
| `protect-env-vars` | エージェントが環境変数を出力するのを防ぐ | |
|
|
160
|
+
| `block-read-outside-cwd` | エージェントをプロジェクト境界内に留める | `allowPaths` |
|
|
161
|
+
| `block-secrets-write` | 秘密鍵・証明書ファイルへの書き込みを防ぐ | `additionalPatterns` |
|
|
162
|
+
| `block-push-master` | main/masterへの誤ったプッシュを防ぐ | `protectedBranches` |
|
|
163
|
+
| `block-work-on-main` | エージェントを保護ブランチから遠ざける | `protectedBranches` |
|
|
164
|
+
| `block-force-push` | `git push --force` を防ぐ | |
|
|
165
|
+
| `warn-git-amend` | コミットをamendする前にエージェントに通知する | |
|
|
166
|
+
| `warn-git-stash-drop` | stashをdropする前にエージェントに通知する | |
|
|
167
|
+
| `warn-all-files-staged` | 誤った `git add -A` を検出する | |
|
|
168
|
+
| `warn-destructive-sql` | 実行前にDROP/DELETE SQLを検出する | |
|
|
169
|
+
| `warn-schema-alteration` | 実行前にALTER TABLEを検出する | |
|
|
170
|
+
| `warn-large-file-write` | 予期しない大きなファイル書き込みを検出する | `thresholdKb` |
|
|
171
|
+
| `warn-package-publish` | 誤った `npm publish` を検出する | |
|
|
172
|
+
| `warn-background-process` | 意図しないバックグラウンドプロセスの起動を検出する | |
|
|
173
|
+
| `warn-global-package-install` | 意図しないグローバルパッケージのインストールを検出する | |
|
|
174
174
|
| …その他 | | |
|
|
175
175
|
|
|
176
|
-
|
|
176
|
+
ポリシーの詳細とパラメータリファレンス: [docs/built-in-policies.mdx](docs/built-in-policies.mdx)
|
|
177
177
|
|
|
178
178
|
---
|
|
179
179
|
|
|
180
180
|
## カスタムポリシー
|
|
181
181
|
|
|
182
|
-
|
|
182
|
+
エージェントを安定稼働させ、タスクに集中させるための独自ポリシーを作成できます:
|
|
183
183
|
|
|
184
184
|
```js
|
|
185
185
|
import { customPolicies, allow, deny, instruct } from "failproofai";
|
|
@@ -197,7 +197,7 @@ customPolicies.add({
|
|
|
197
197
|
});
|
|
198
198
|
```
|
|
199
199
|
|
|
200
|
-
|
|
200
|
+
以下のコマンドでインストールします:
|
|
201
201
|
|
|
202
202
|
```bash
|
|
203
203
|
failproofai policies --install --custom ./my-policies.js
|
|
@@ -205,14 +205,14 @@ failproofai policies --install --custom ./my-policies.js
|
|
|
205
205
|
|
|
206
206
|
### 判定ヘルパー
|
|
207
207
|
|
|
208
|
-
| 関数 |
|
|
208
|
+
| 関数 | 効果 |
|
|
209
209
|
|----------|--------|
|
|
210
|
-
| `allow()` |
|
|
211
|
-
| `allow(message)` |
|
|
212
|
-
| `deny(message)` |
|
|
213
|
-
| `instruct(message)` | Claude
|
|
210
|
+
| `allow()` | 操作を許可する |
|
|
211
|
+
| `allow(message)` | 操作を許可し、情報コンテキストを Claude に送信する |
|
|
212
|
+
| `deny(message)` | 操作をブロックする。メッセージが Claude に表示される |
|
|
213
|
+
| `instruct(message)` | Claude のプロンプトにコンテキストを追加する。ブロックはしない |
|
|
214
214
|
|
|
215
|
-
###
|
|
215
|
+
### コンテキストオブジェクト(`ctx`)
|
|
216
216
|
|
|
217
217
|
| フィールド | 型 | 説明 |
|
|
218
218
|
|-------|------|-------------|
|
|
@@ -220,34 +220,34 @@ failproofai policies --install --custom ./my-policies.js
|
|
|
220
220
|
| `toolName` | `string` | 呼び出されるツール(`"Bash"`、`"Write"`、`"Read"` など) |
|
|
221
221
|
| `toolInput` | `object` | ツールの入力パラメータ |
|
|
222
222
|
| `payload` | `object` | 生のイベントペイロード全体 |
|
|
223
|
-
| `session.cwd` | `string` | Claude Code
|
|
223
|
+
| `session.cwd` | `string` | Claude Code セッションのワーキングディレクトリ |
|
|
224
224
|
| `session.sessionId` | `string` | セッション識別子 |
|
|
225
225
|
| `session.transcriptPath` | `string` | セッションのトランスクリプトファイルへのパス |
|
|
226
226
|
|
|
227
|
-
|
|
227
|
+
カスタムフックは推移的なローカルインポート、async/await、`process.env` へのアクセスをサポートしています。エラーはフェイルオープン(`~/.failproofai/hook.log` に記録され、組み込みポリシーは継続)。詳細なガイドは [docs/custom-hooks.mdx](docs/custom-hooks.mdx) を参照してください。
|
|
228
228
|
|
|
229
229
|
### 規約ベースのポリシー
|
|
230
230
|
|
|
231
|
-
`*policies.{js,mjs,ts}` ファイルを `.failproofai/policies/`
|
|
231
|
+
`*policies.{js,mjs,ts}` ファイルを `.failproofai/policies/` に置くだけで自動的に読み込まれます — フラグや設定変更は不要です。ディレクトリをgitにコミットすれば、チーム全員が同じ品質基準を自動的に適用できます。
|
|
232
232
|
|
|
233
233
|
```text
|
|
234
234
|
# プロジェクトレベル — gitにコミットし、チームで共有
|
|
235
235
|
.failproofai/policies/security-policies.mjs
|
|
236
236
|
.failproofai/policies/workflow-policies.mjs
|
|
237
237
|
|
|
238
|
-
# ユーザーレベル —
|
|
238
|
+
# ユーザーレベル — 個人用、すべてのプロジェクトに適用
|
|
239
239
|
~/.failproofai/policies/my-policies.mjs
|
|
240
240
|
```
|
|
241
241
|
|
|
242
|
-
|
|
242
|
+
両方のレベルが読み込まれます(ユニオン)。ファイルは各ディレクトリ内でアルファベット順に読み込まれます。読み込み順を制御するには `01-`、`02-` などのプレフィックスを付けてください。チームが新たな障害パターンを発見したら、ポリシーを追加してプッシュするだけ — 次のプル時に全員が更新を受け取ります。すぐに使えるサンプルは [examples/convention-policies/](examples/convention-policies/) を参照してください。
|
|
243
243
|
|
|
244
244
|
---
|
|
245
245
|
|
|
246
|
-
##
|
|
246
|
+
## テレメトリー
|
|
247
247
|
|
|
248
|
-
Failproof AI
|
|
248
|
+
Failproof AI は機能の利用状況を把握するために、PostHog を通じて匿名の使用状況テレメトリーを収集しています。セッションの内容、ファイル名、ツールの入力、個人情報は一切送信されません。
|
|
249
249
|
|
|
250
|
-
|
|
250
|
+
無効にするには:
|
|
251
251
|
|
|
252
252
|
```bash
|
|
253
253
|
FAILPROOFAI_TELEMETRY_DISABLED=1 failproofai
|
|
@@ -259,22 +259,22 @@ FAILPROOFAI_TELEMETRY_DISABLED=1 failproofai
|
|
|
259
259
|
|
|
260
260
|
| ガイド | 説明 |
|
|
261
261
|
|-------|-------------|
|
|
262
|
-
| [
|
|
263
|
-
| [
|
|
264
|
-
| [
|
|
265
|
-
| [
|
|
266
|
-
| [
|
|
267
|
-
| [
|
|
268
|
-
| [
|
|
262
|
+
| [Getting Started](docs/getting-started.mdx) | インストールと最初のステップ |
|
|
263
|
+
| [Built-in Policies](docs/built-in-policies.mdx) | パラメータ付き30種類の組み込みポリシー |
|
|
264
|
+
| [Custom Policies](docs/custom-policies.mdx) | 独自ポリシーの作成 |
|
|
265
|
+
| [Configuration](docs/configuration.mdx) | 設定ファイルの形式とスコープのマージ |
|
|
266
|
+
| [Dashboard](docs/dashboard.mdx) | セッションの監視とポリシーアクティビティのレビュー |
|
|
267
|
+
| [Architecture](docs/architecture.mdx) | フックシステムの仕組み |
|
|
268
|
+
| [Testing](docs/testing.mdx) | テストの実行と新しいテストの作成 |
|
|
269
269
|
|
|
270
|
-
###
|
|
270
|
+
### ドキュメントをローカルで実行する
|
|
271
271
|
|
|
272
272
|
```bash
|
|
273
273
|
docker build -f Dockerfile.docs -t failproofai-docs .
|
|
274
274
|
docker run --rm -p 3000:3000 failproofai-docs
|
|
275
275
|
```
|
|
276
276
|
|
|
277
|
-
`http://localhost:3000`
|
|
277
|
+
`http://localhost:3000` でMintlifyドキュメントサイトが開きます。docsディレクトリをマウントすると、コンテナは変更を監視します:
|
|
278
278
|
|
|
279
279
|
```bash
|
|
280
280
|
docker run --rm -p 3000:3000 -v $(pwd)/docs:/app/docs failproofai-docs
|
|
@@ -282,11 +282,11 @@ docker run --rm -p 3000:3000 -v $(pwd)/docs:/app/docs failproofai-docs
|
|
|
282
282
|
|
|
283
283
|
---
|
|
284
284
|
|
|
285
|
-
## failproofai
|
|
285
|
+
## failproofaiコントリビューターへのご注意
|
|
286
286
|
|
|
287
|
-
このリポジトリの `.claude/settings.json` は、標準の `npx -y failproofai` コマンドの代わりに `bun ./bin/failproofai.mjs --hook <EventType>`
|
|
287
|
+
このリポジトリの `.claude/settings.json` は、標準の `npx -y failproofai` コマンドの代わりに `bun ./bin/failproofai.mjs --hook <EventType>` を使用しています。これは failproofai プロジェクト内で `npx -y failproofai` を実行すると自己参照の競合が発生するためです。
|
|
288
288
|
|
|
289
|
-
|
|
289
|
+
その他のリポジトリでは、推奨される方法は `npx -y failproofai` で、以下のコマンドでインストールします:
|
|
290
290
|
|
|
291
291
|
```bash
|
|
292
292
|
failproofai policies --install --scope project
|
|
@@ -304,4 +304,4 @@ failproofai policies --install --scope project
|
|
|
304
304
|
|
|
305
305
|
---
|
|
306
306
|
|
|
307
|
-
**ExosphereHost: Reliability Research Lab for Your Agents**
|
|
307
|
+
**ExosphereHost: Reliability Research Lab for Your Agents** が開発・メンテナンスしています。私たちは独自のエージェント、ソフトウェア、専門知識を通じて、企業やスタートアップのAIエージェントの信頼性向上を支援しています。詳細は [exosphere.host](https://exosphere.host) をご覧ください。
|