agent-steward 0.0.3 → 0.0.4
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 +20 -0
- package/README.md +3 -3
- package/ROADMAP-STRATEGY.md +9 -9
- package/ROADMAP.md +50 -34
- package/dist/core/dlq-api.d.ts +44 -0
- package/dist/core/dlq-api.d.ts.map +1 -0
- package/dist/core/dlq-api.js +68 -0
- package/dist/core/dry-run.d.ts.map +1 -1
- package/dist/core/dry-run.js +18 -1
- package/dist/core/lock.d.ts +20 -4
- package/dist/core/lock.d.ts.map +1 -1
- package/dist/core/lock.js +97 -22
- package/dist/core/one-shot.d.ts +5 -1
- package/dist/core/one-shot.d.ts.map +1 -1
- package/dist/core/one-shot.js +33 -8
- package/dist/core/opencode-cli.d.ts +28 -0
- package/dist/core/opencode-cli.d.ts.map +1 -0
- package/dist/core/opencode-cli.js +74 -0
- package/dist/core/opencode-models.d.ts +62 -0
- package/dist/core/opencode-models.d.ts.map +1 -0
- package/dist/core/opencode-models.js +277 -0
- package/dist/core/ps-wrapper.d.ts +1 -1
- package/dist/core/ps-wrapper.d.ts.map +1 -1
- package/dist/core/ps-wrapper.js +11 -1
- package/dist/core/record-history.d.ts +15 -0
- package/dist/core/record-history.d.ts.map +1 -1
- package/dist/core/record-history.js +56 -32
- package/dist/core/router/dispatch.d.ts +36 -0
- package/dist/core/router/dispatch.d.ts.map +1 -0
- package/dist/core/router/dispatch.js +59 -0
- package/dist/core/router/escalation.d.ts +47 -0
- package/dist/core/router/escalation.d.ts.map +1 -0
- package/dist/core/router/escalation.js +87 -0
- package/dist/core/router/planner.d.ts +53 -0
- package/dist/core/router/planner.d.ts.map +1 -0
- package/dist/core/router/planner.js +113 -0
- package/dist/core/router/rules.d.ts +46 -0
- package/dist/core/router/rules.d.ts.map +1 -0
- package/dist/core/router/rules.js +85 -0
- package/dist/core/run-panel-api.d.ts +94 -0
- package/dist/core/run-panel-api.d.ts.map +1 -0
- package/dist/core/run-panel-api.js +169 -0
- package/dist/core/schedule-gate.js +5 -1
- package/dist/core/schedule-v2.d.ts +34 -0
- package/dist/core/schedule-v2.d.ts.map +1 -1
- package/dist/core/schedule-v2.js +91 -5
- package/dist/core/scheduler/at-fallback.d.ts +55 -2
- package/dist/core/scheduler/at-fallback.d.ts.map +1 -1
- package/dist/core/scheduler/at-fallback.js +135 -5
- package/dist/core/scheduler/linux.d.ts +10 -1
- package/dist/core/scheduler/linux.d.ts.map +1 -1
- package/dist/core/scheduler/linux.js +29 -11
- package/dist/core/scheduler/posix.d.ts.map +1 -1
- package/dist/core/scheduler/posix.js +25 -1
- package/dist/core/scheduler/registry.d.ts +11 -0
- package/dist/core/scheduler/registry.d.ts.map +1 -1
- package/dist/core/scheduler/registry.js +83 -21
- package/dist/core/scheduler/run-now.d.ts +16 -0
- package/dist/core/scheduler/run-now.d.ts.map +1 -0
- package/dist/core/scheduler/run-now.js +28 -0
- package/dist/core/secrets.d.ts.map +1 -1
- package/dist/core/secrets.js +125 -28
- package/dist/core/session.d.ts.map +1 -1
- package/dist/core/session.js +18 -11
- package/dist/core/task-name.d.ts +24 -0
- package/dist/core/task-name.d.ts.map +1 -0
- package/dist/core/task-name.js +40 -0
- package/dist/core/wrappers/bash.d.ts.map +1 -1
- package/dist/core/wrappers/bash.js +49 -4
- package/dist/db/capability-repo.d.ts +83 -0
- package/dist/db/capability-repo.d.ts.map +1 -0
- package/dist/db/capability-repo.js +182 -0
- package/dist/db/history-repo.d.ts +8 -0
- package/dist/db/history-repo.d.ts.map +1 -1
- package/dist/db/history-repo.js +19 -0
- package/dist/db/index.d.ts +4 -0
- package/dist/db/index.d.ts.map +1 -1
- package/dist/db/index.js +39 -1
- package/dist/db/migrate.d.ts.map +1 -1
- package/dist/db/migrate.js +3 -1
- package/dist/db/run-context.d.ts +103 -0
- package/dist/db/run-context.d.ts.map +1 -0
- package/dist/db/run-context.js +224 -0
- package/dist/db/run-dlq.d.ts +100 -0
- package/dist/db/run-dlq.d.ts.map +1 -0
- package/dist/db/run-dlq.js +191 -0
- package/dist/db/run-resume.d.ts +5 -2
- package/dist/db/run-resume.d.ts.map +1 -1
- package/dist/db/run-resume.js +30 -11
- package/dist/db/runs-repo.d.ts +13 -5
- package/dist/db/runs-repo.d.ts.map +1 -1
- package/dist/db/runs-repo.js +28 -5
- package/dist/db/schema.d.ts +2 -2
- package/dist/db/schema.d.ts.map +1 -1
- package/dist/db/schema.js +154 -2
- package/dist/db/settings-repo.d.ts +11 -0
- package/dist/db/settings-repo.d.ts.map +1 -1
- package/dist/db/settings-repo.js +25 -0
- package/dist/db/step-idempotency.d.ts +51 -0
- package/dist/db/step-idempotency.d.ts.map +1 -0
- package/dist/db/step-idempotency.js +136 -0
- package/dist/index.d.ts +4 -4
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +102 -4
- package/dist/rpc.d.ts +678 -0
- package/dist/rpc.d.ts.map +1 -1
- package/dist/rpc.js +235 -0
- package/dist/server.d.ts +31 -0
- package/dist/server.d.ts.map +1 -1
- package/dist/server.js +95 -35
- package/dist/types.d.ts.map +1 -1
- package/dist/types.js +7 -0
- package/dist/workspaces.d.ts +25 -3
- package/dist/workspaces.d.ts.map +1 -1
- package/dist/workspaces.js +43 -8
- package/docs/ARCHITECTURE.md +229 -5
- package/docs/CONCEPT.md +171 -91
- package/docs/EXECUTION-LOOP.md +196 -0
- package/docs/README.ru.md +2 -2
- package/docs/README.zh.md +3 -3
- package/docs/SAFETY.md +122 -0
- package/docs/SAVINGS.md +29 -0
- package/docs/SAVINGS.ru.md +29 -0
- package/docs/SAVINGS.zh.md +18 -0
- package/gui-experimental.cjs +8 -8
- package/locales/en.json +67 -0
- package/locales/ru.json +67 -0
- package/locales/zh.json +67 -0
- package/package.json +28 -3
- package/scripts/audit-bundle.mjs +215 -0
- package/src/core/dlq-api.ts +98 -0
- package/src/core/dry-run.ts +25 -1
- package/src/core/lock.ts +95 -22
- package/src/core/one-shot.ts +36 -8
- package/src/core/opencode-cli.ts +103 -0
- package/src/core/opencode-models.ts +315 -0
- package/src/core/ps-wrapper.ts +11 -1
- package/src/core/record-history.ts +75 -37
- package/src/core/router/dispatch.ts +94 -0
- package/src/core/router/escalation.ts +129 -0
- package/src/core/router/planner.ts +166 -0
- package/src/core/router/rules.ts +109 -0
- package/src/core/run-panel-api.ts +262 -0
- package/src/core/schedule-gate.ts +6 -2
- package/src/core/schedule-v2.ts +114 -5
- package/src/core/scheduler/at-fallback.ts +190 -5
- package/src/core/scheduler/linux.ts +32 -10
- package/src/core/scheduler/posix.ts +20 -1
- package/src/core/scheduler/registry.ts +107 -26
- package/src/core/scheduler/run-now.ts +32 -0
- package/src/core/secrets.ts +127 -27
- package/src/core/session.ts +23 -10
- package/src/core/task-name.ts +67 -0
- package/src/core/wrappers/bash.ts +49 -4
- package/src/db/capability-repo.ts +285 -0
- package/src/db/history-repo.ts +22 -0
- package/src/db/index.ts +37 -1
- package/src/db/migrate.ts +3 -1
- package/src/db/run-context.ts +370 -0
- package/src/db/run-dlq.ts +310 -0
- package/src/db/run-resume.ts +48 -12
- package/src/db/runs-repo.ts +30 -7
- package/src/db/schema.ts +154 -2
- package/src/db/settings-repo.ts +31 -0
- package/src/db/step-idempotency.ts +185 -0
- package/src/gui.tsx +515 -0
- package/src/index.ts +124 -4
- package/src/rpc.ts +251 -0
- package/src/server.ts +112 -36
- package/src/types.ts +9 -0
- package/src/workspaces.ts +58 -9
package/dist/workspaces.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"workspaces.d.ts","sourceRoot":"","sources":["../src/workspaces.ts"],"names":[],"mappings":"AAQA;;;;;;GAMG;AACH,MAAM,WAAW,SAAS;IACxB,EAAE,EAAE,MAAM,CAAC;IACX,IAAI,EAAE,MAAM,CAAC;IACb,IAAI,EAAE,MAAM,CAAC;IACb,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,wEAAwE;IACxE,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IAC7B,8EAA8E;IAC9E,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,SAAS,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,WAAW,iBAAiB;IAChC,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,CAAC;IACb,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,IAAI,CAAC;IACpC,OAAO,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CACzB;AAED,MAAM,WAAW,oBAAoB;IACnC,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,SAAS,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC1B,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,IAAI,CAAC;IACpC,OAAO,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CACzB;AAED,wEAAwE;AACxE,eAAO,MAAM,uBAAuB,MAAM,CAAC;AAE3C,iDAAiD;AACjD,eAAO,MAAM,gBAAgB,UAO5B,CAAC;AAIF;;;GAGG;AACH,wBAAgB,qBAAqB,CACnC,KAAK,EAAE,OAAO,GACb,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,SAAS,CA6BpC;AAED;;;GAGG;AACH,wBAAgB,mBAAmB,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAsB3E;AAED,+DAA+D;AAC/D,wBAAgB,oBAAoB,CAAC,OAAO,CAAC,EAAE,MAAM,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAO7E;AAED;;;;;GAKG;AACH,wBAAgB,mBAAmB,CACjC,SAAS,EAAE,SAAS,GAAG,SAAS,EAChC,kBAAkB,CAAC,EAAE,MAAM,EAAE,GAC5B,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,
|
|
1
|
+
{"version":3,"file":"workspaces.d.ts","sourceRoot":"","sources":["../src/workspaces.ts"],"names":[],"mappings":"AAQA;;;;;;GAMG;AACH,MAAM,WAAW,SAAS;IACxB,EAAE,EAAE,MAAM,CAAC;IACX,IAAI,EAAE,MAAM,CAAC;IACb,IAAI,EAAE,MAAM,CAAC;IACb,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,wEAAwE;IACxE,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IAC7B,8EAA8E;IAC9E,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,SAAS,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,WAAW,iBAAiB;IAChC,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,CAAC;IACb,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,IAAI,CAAC;IACpC,OAAO,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CACzB;AAED,MAAM,WAAW,oBAAoB;IACnC,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,SAAS,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC1B,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,IAAI,CAAC;IACpC,OAAO,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CACzB;AAED,wEAAwE;AACxE,eAAO,MAAM,uBAAuB,MAAM,CAAC;AAE3C,iDAAiD;AACjD,eAAO,MAAM,gBAAgB,UAO5B,CAAC;AAIF;;;GAGG;AACH,wBAAgB,qBAAqB,CACnC,KAAK,EAAE,OAAO,GACb,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,SAAS,CA6BpC;AAED;;;GAGG;AACH,wBAAgB,mBAAmB,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAsB3E;AAED,+DAA+D;AAC/D,wBAAgB,oBAAoB,CAAC,OAAO,CAAC,EAAE,MAAM,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAO7E;AAED,oFAAoF;AACpF,qBAAa,4BAA6B,SAAQ,KAAK;IACrD,QAAQ,CAAC,aAAa,EAAE,MAAM,CAAC;IAC/B,QAAQ,CAAC,OAAO,EAAE,MAAM,EAAE,CAAC;gBAEf,aAAa,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE;CASrD;AAED,UAAU,oBAAoB;IAC5B,GAAG,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IAC5B,OAAO,EAAE,MAAM,EAAE,CAAC;CACnB;AAED;;;;;GAKG;AACH,wBAAgB,2BAA2B,CACzC,SAAS,EAAE,SAAS,GAAG,SAAS,EAChC,kBAAkB,CAAC,EAAE,MAAM,EAAE,GAC5B,oBAAoB,CAQtB;AAED;;;;;GAKG;AACH,wBAAgB,mBAAmB,CACjC,SAAS,EAAE,SAAS,GAAG,SAAS,EAChC,kBAAkB,CAAC,EAAE,MAAM,EAAE,GAC5B,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAQxB;AAED,4CAA4C;AAC5C,wBAAgB,eAAe,IAAI,MAAM,CAExC;AAID;;;;GAIG;AACH,wBAAgB,aAAa,CAAC,GAAG,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,SAAS,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAW7F;AAED;;;GAGG;AACH,wBAAgB,eAAe,CAAC,SAAS,EAAE,MAAM,GAAG,MAAM,CAEzD;AAED;;;;;;;;;GASG;AACH,wBAAgB,qBAAqB,CACnC,SAAS,EAAE,SAAS,GAAG,SAAS,EAChC,SAAS,EAAE,MAAM,EACjB,aAAa,EAAE,MAAM,EACrB,kBAAkB,CAAC,EAAE,MAAM,EAAE,GAC5B,MAAM,GAAG,SAAS,CAqCpB;AA2BD,6DAA6D;AAC7D,wBAAgB,qBAAqB,CAAC,aAAa,EAAE,MAAM,GAAG,IAAI,CAOjE;AAED;;;;;;;GAOG;AACH,wBAAgB,qBAAqB,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,GAAG,IAAI,CAQlE;AAED;;;GAGG;AACH,wBAAgB,aAAa,CAAC,aAAa,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAavE;AAED,8EAA8E;AAC9E,wBAAgB,aAAa,CAAC,aAAa,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAavE;AAED,gCAAgC;AAChC,wBAAgB,cAAc,IAAI,SAAS,EAAE,CAK5C;AAED,uBAAuB;AACvB,wBAAgB,YAAY,CAAC,EAAE,EAAE,MAAM,GAAG,SAAS,GAAG,SAAS,CAI9D;AAED,6DAA6D;AAC7D,wBAAgB,kBAAkB,CAAC,aAAa,EAAE,MAAM,GAAG,SAAS,GAAG,SAAS,CAM/E;AAED,8DAA8D;AAC9D,wBAAgB,YAAY,CAAC,KAAK,EAAE,iBAAiB,GAAG,SAAS,CA6ChE;AAED,yCAAyC;AACzC,wBAAgB,eAAe,CAAC,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,oBAAoB,GAAG,SAAS,CAkElF;AAED;;;GAGG;AACH,wBAAgB,eAAe,CAAC,EAAE,EAAE,MAAM,GAAG,OAAO,CAenD;AAED,kDAAkD;AAClD,wBAAgB,eAAe,IAAI,MAAM,CAGxC"}
|
package/dist/workspaces.js
CHANGED
|
@@ -87,22 +87,42 @@ export function readWorkspaceEnvFile(envFile) {
|
|
|
87
87
|
return {};
|
|
88
88
|
}
|
|
89
89
|
}
|
|
90
|
+
/** Ошибка конфигурации: в env workspace остались неразрешённые `${secret:NAME}`. */
|
|
91
|
+
export class MissingWorkspaceSecretsError extends Error {
|
|
92
|
+
constructor(workspaceName, secrets) {
|
|
93
|
+
super(`Workspace "${workspaceName}": не найдены секреты: ${secrets.join(", ")}. ` +
|
|
94
|
+
"Запуск отменён, чтобы не подставлять литералы ${secret:...} в окружение задачи.");
|
|
95
|
+
this.name = "MissingWorkspaceSecretsError";
|
|
96
|
+
this.workspaceName = workspaceName;
|
|
97
|
+
this.secrets = secrets;
|
|
98
|
+
}
|
|
99
|
+
}
|
|
90
100
|
/**
|
|
91
|
-
* Итоговые env-переменные workspace
|
|
92
|
-
*
|
|
93
|
-
*
|
|
94
|
-
*
|
|
101
|
+
* Итоговые env-переменные workspace вместе со списком отсутствующих секретов.
|
|
102
|
+
* Ссылки `${secret:NAME}` не подменяются пустой строкой: имя попадает в
|
|
103
|
+
* `missing`, а сама ссылка остаётся в env — вызывающая сторона решает,
|
|
104
|
+
* прервать запуск или только предупредить.
|
|
95
105
|
*/
|
|
96
|
-
export function
|
|
106
|
+
export function resolveWorkspaceEnvDetailed(workspace, allowedSecretNames) {
|
|
97
107
|
if (!workspace)
|
|
98
|
-
return {};
|
|
108
|
+
return { env: {}, missing: [] };
|
|
99
109
|
const merged = {
|
|
100
110
|
...readWorkspaceEnvFile(workspace.envFile),
|
|
101
111
|
...(workspace.env ?? {}),
|
|
102
112
|
};
|
|
103
113
|
const resolved = resolveSecretRefs(merged, allowedSecretNames);
|
|
114
|
+
return { env: resolved.env, missing: resolved.missing };
|
|
115
|
+
}
|
|
116
|
+
/**
|
|
117
|
+
* Итоговые env-переменные workspace: сначала .env-файл, затем явные пары
|
|
118
|
+
* (пары важнее файла). Отсутствующий секрет даёт предупреждение с именем,
|
|
119
|
+
* но не значение. Никогда не бросает — для запуска задачи используйте
|
|
120
|
+
* writeWorkspaceEnvFile(), который в этом случае отказывает.
|
|
121
|
+
*/
|
|
122
|
+
export function resolveWorkspaceEnv(workspace, allowedSecretNames) {
|
|
123
|
+
const resolved = resolveWorkspaceEnvDetailed(workspace, allowedSecretNames);
|
|
104
124
|
if (resolved.missing.length > 0) {
|
|
105
|
-
console.warn(`[workspace] "${workspace
|
|
125
|
+
console.warn(`[workspace] "${workspace?.name ?? ""}": не найдены секреты: ${resolved.missing.join(", ")}`);
|
|
106
126
|
}
|
|
107
127
|
return resolved.env;
|
|
108
128
|
}
|
|
@@ -142,12 +162,27 @@ export function workspaceEnvDir(pluginDir) {
|
|
|
142
162
|
*
|
|
143
163
|
* Возвращает путь к файлу или undefined, если у workspace нет переменных.
|
|
144
164
|
* Пустой env удаляет ранее созданный файл. На POSIX права 0600.
|
|
165
|
+
*
|
|
166
|
+
* Если хотя бы один `${secret:NAME}` не разрешён, старый env-файл удаляется
|
|
167
|
+
* и бросается MissingWorkspaceSecretsError: задача не должна запускаться с
|
|
168
|
+
* литералом `${secret:...}` вместо значения (P2-21).
|
|
145
169
|
*/
|
|
146
170
|
export function writeWorkspaceEnvFile(workspace, pluginDir, sanitizedName, allowedSecretNames) {
|
|
147
171
|
if (!workspace)
|
|
148
172
|
return undefined;
|
|
149
173
|
const file = join(workspaceEnvDir(pluginDir), `${sanitizedName}.env`);
|
|
150
|
-
const env =
|
|
174
|
+
const { env, missing } = resolveWorkspaceEnvDetailed(workspace, allowedSecretNames);
|
|
175
|
+
if (missing.length > 0) {
|
|
176
|
+
// Fail closed: не оставляем старый файл, иначе обёртка продолжит
|
|
177
|
+
// подхватывать устаревшие значения секретов.
|
|
178
|
+
try {
|
|
179
|
+
rmSync(file, { force: true });
|
|
180
|
+
}
|
|
181
|
+
catch {
|
|
182
|
+
// файла нет — не ошибка
|
|
183
|
+
}
|
|
184
|
+
throw new MissingWorkspaceSecretsError(workspace.name, missing);
|
|
185
|
+
}
|
|
151
186
|
const keys = Object.keys(env);
|
|
152
187
|
if (!keys.length) {
|
|
153
188
|
try {
|
package/docs/ARCHITECTURE.md
CHANGED
|
@@ -141,6 +141,14 @@ cloud model — without involving a model for known step types.
|
|
|
141
141
|
Агент хочет прочитать файл → роутер смотрит в таблицу → видит `direct + local` →
|
|
142
142
|
выполняет напрямую, без MCP, без модели.
|
|
143
143
|
|
|
144
|
+
Реализация (Спринт 36.5.a): `src/core/router/rules.ts` — замороженная таблица
|
|
145
|
+
`STATIC_ROUTE_RULES`, `routeStaticStep(taskType)` (нормализует `Run Tests` /
|
|
146
|
+
`run-tests` → `run_tests`), `isStaticTaskType`, `listStaticRouteRules`.
|
|
147
|
+
Модуль не импортирует ни БД, ни модель, ни транспорт, поэтому горячий путь
|
|
148
|
+
физически не может стоить токенов; неизвестный тип возвращает `undefined` и
|
|
149
|
+
передаётся слою 2. Покрытие — `test-router-rules.mjs` (22 проверки, включая
|
|
150
|
+
1000 маршрутизаций быстрее 50 мс).
|
|
151
|
+
|
|
144
152
|
### Слой 2 — Capability Map (0 токенов, быстро)
|
|
145
153
|
|
|
146
154
|
SQLite-таблица `task_type → model / success_rate / avg_cost / avg_time /
|
|
@@ -152,6 +160,15 @@ last_10_runs`. Обучается на исходах гейта (CONCEPT §9 le
|
|
|
152
160
|
Это и есть learning loop: роутер учится на гейтах и становится точнее без затрат
|
|
153
161
|
токенов на само решение.
|
|
154
162
|
|
|
163
|
+
Реализация (Спринт 36.5.b): `src/db/capability-repo.ts`, таблица `capability_map`
|
|
164
|
+
(`SCHEMA_VERSION = 6`). `recordCapabilityOutcome` обновляет счётчики, считает
|
|
165
|
+
`success_rate` и скользящие средние стоимости/времени, хранит `last_10_runs`
|
|
166
|
+
(JSON, новые справа). `decideCapabilityRoute` решает по правилам:
|
|
167
|
+
меньше `MIN_RUNS_FOR_DECISION = 3` исходов → `explore` (решает слой 3),
|
|
168
|
+
`≥ 0.85` → `local`, `≤ 0.30` → `cloud`, между порогами → `review`. Пороги
|
|
169
|
+
передаются параметром, поэтому политика меняется без миграции данных.
|
|
170
|
+
Покрытие — `test-capability-map.mjs`.
|
|
171
|
+
|
|
155
172
|
### Слой 3 — локальная модель (только декомпозиция и неоднозначность)
|
|
156
173
|
|
|
157
174
|
Модель не маршрутизирует каждый шаг. Она только:
|
|
@@ -160,6 +177,12 @@ last_10_runs`. Обучается на исходах гейта (CONCEPT §9 le
|
|
|
160
177
|
|
|
161
178
|
После этого каждый шаг проходит через Слой 1 и Слой 2.
|
|
162
179
|
|
|
180
|
+
**Реализация (Спринт 36.5.c):** `src/core/router/planner.ts`. `planMission(mission, { decomposer, maxSteps })` вызывает декомпозер — локальную модель — один раз на миссию и нормализует типы через `normalizeTaskType`; без декомпозера работает `decomposeHeuristically` по ключевым словам, без сети и модели. `planMissionSync` — вариант для синхронных мест. Шаг плана содержит только `stepName` и `taskType`, маршрут по-прежнему выбирают слои 1–2; типы вне статических правил собираются в `ambiguousTaskTypes` для `decideCapabilityRoute`. Пустая миссия, пустой или битый план модели — ошибка, а не молчаливый план. Покрытие — `test-planner.mjs`.
|
|
181
|
+
|
|
182
|
+
**Реализация (Спринт 36.5.d):** `escalateAfterGate(current, gate)` в `src/core/router/escalation.ts` решает судьбу шага по одному флагу `passed` и таблице переходов `local → cloud → review → blocked`. Модуль не импортирует ни БД, ни модель, ни сеть: это чистые функции (`nextGateTarget`, `isEscalationExhausted`, `escalationChain`), поэтому 1000 решений стоят доли миллисекунды. Переход в `blocked` означает, что автоматических уровней больше нет и нужен человек.
|
|
183
|
+
|
|
184
|
+
Слои 1–2 собираются в `routeStep(taskType, thresholds)` из `src/core/router/dispatch.ts`: сначала статическое правило (0 токенов), затем Capability Map. Для `review` и `explore` маршрут возвращается без транспорта и исполнителя — исполнять пока нечего. Модуль не импортирует `planner`, поэтому известный тип задачи не может случайно дойти до модели; это закреплено тестом `test-router-dispatch.mjs`, который также проверяет, что статика не оставляет записей в `capability_map` и работает ещё до инициализации БД.
|
|
185
|
+
|
|
163
186
|
### Эскалация
|
|
164
187
|
|
|
165
188
|
При провале гейта роутер эскалирует в облако **по правилу**, без участия модели.
|
|
@@ -202,7 +225,12 @@ last_10_runs`. Обучается на исходах гейта (CONCEPT §9 le
|
|
|
202
225
|
| `src/core/cron-to-schtasks.ts` | Cron → Task Scheduler translation |
|
|
203
226
|
| `src/core/schedule-v2.ts` | Extended cron parser/matcher, timezone math, launch windows, poll-mode decisions |
|
|
204
227
|
| `src/core/schedule-gate.ts` | Wrapper-side gate: cron re-check (poll mode), window postpone, defer-file |
|
|
205
|
-
| `src/db/` | SQLite access: schema, migrations, repositories, recovery; `runs-repo.ts` keeps durable `runs`/`run_steps` state, `run-journal.ts` writes transitions around each step, `run-resume.ts` continues a crashed chain |
|
|
228
|
+
| `src/db/` | SQLite access: schema, migrations, repositories, recovery; `runs-repo.ts` keeps durable `runs`/`run_steps` state, `run-journal.ts` writes transitions around each step, `run-resume.ts` continues a crashed chain, `step-idempotency.ts` replays steps by key, `run-dlq.ts` parks deterministically failed steps |
|
|
229
|
+
| `src/core/router/rules.ts` | Router layer 1: static rules task type → transport + executor, normalization, no imports (0 tokens) |
|
|
230
|
+
| `src/db/capability-repo.ts` | Router layer 2: Capability Map - gate outcomes per task type, success_rate, moving averages, last 10 runs, threshold decision |
|
|
231
|
+
| `src/core/router/planner.ts` | Router layer 3: mission decomposition (model once per mission) and heuristic fallback, steps carry type only, routing stays in layers 1-2 |
|
|
232
|
+
| `src/core/router/dispatch.ts` | Router assembly: `routeStep` runs layer 1 then layer 2 and returns transport/executor, never imports the planner |
|
|
233
|
+
| `src/core/router/escalation.ts` | Gate failure escalation `local → cloud → review → blocked` by pure transition table, no DB, no model |
|
|
206
234
|
| `src/shared/jobs-view.ts` | Task view shared by the GUI and dashboard |
|
|
207
235
|
|
|
208
236
|
## Scheduling backends
|
|
@@ -355,7 +383,7 @@ the whole plugin directory (database, logs, locks, wrappers, prompts) with
|
|
|
355
383
|
|
|
356
384
|
Schema evolution is additive: `applySchema` runs `CREATE TABLE IF NOT EXISTS` on every
|
|
357
385
|
connection and adds missing columns after `PRAGMA table_info`, so upgrading the plugin
|
|
358
|
-
never requires a manual migration. `SCHEMA_VERSION` (currently `
|
|
386
|
+
never requires a manual migration. `SCHEMA_VERSION` (currently `6`) is stored in
|
|
359
387
|
`PRAGMA user_version`; incremental steps live in `MIGRATIONS`.
|
|
360
388
|
|
|
361
389
|
### Durable run state (Sprint 36.1)
|
|
@@ -371,8 +399,8 @@ execution:
|
|
|
371
399
|
`src/db/runs-repo.ts` owns the transitions and rejects invalid ones
|
|
372
400
|
(`InvalidTransitionError`). A failed step can be retried explicitly (`retryStep`),
|
|
373
401
|
which increments `attempt` and returns it to `running`. The tables survive process
|
|
374
|
-
crashes and reconnects, which is the prerequisite for resume (36.2)
|
|
375
|
-
idempotent steps (36.3).
|
|
402
|
+
crashes and reconnects, which is the prerequisite for resume (36.2),
|
|
403
|
+
idempotent steps (36.3) and the dead letter queue (36.4).
|
|
376
404
|
|
|
377
405
|
`src/db/run-journal.ts` (Sprint 36.1.b) writes every transition to disk before
|
|
378
406
|
and after executing the step body: `beginStepAttempt` commits `running` + `started_at`
|
|
@@ -411,13 +439,165 @@ failure, but the run still ends `failed`. This is covered by
|
|
|
411
439
|
`test-run-resume.mjs`, including a real `kill -9` in the middle of a four-step
|
|
412
440
|
chain.
|
|
413
441
|
|
|
442
|
+
The crash path is also exercised nightly by `test-chaos-dag.mjs`: a child process
|
|
443
|
+
runs a four-step chain, the parent sends `SIGKILL` right after the next step has
|
|
444
|
+
committed `running`, and the test then verifies the durable state (`passed` steps
|
|
445
|
+
are untouched, the victim is `running` with `attempt = 1`, later steps are
|
|
446
|
+
`pending`), `PRAGMA integrity_check = ok`, recovery to `failed` with
|
|
447
|
+
`attempt = 1`, and a resume that retries the victim with `attempt = 2` and never
|
|
448
|
+
re-invokes handlers of completed steps. `.github/workflows/nightly.yml` runs it
|
|
449
|
+
on a schedule on Windows and Ubuntu; locally it is `npm run test:chaos`.
|
|
450
|
+
|
|
451
|
+
### Idempotent steps (Sprint 36.3)
|
|
452
|
+
|
|
453
|
+
`run_steps.idempotency_key` is unique per run: schema v4 deduplicates legacy
|
|
454
|
+
duplicates (keeping the first row, nulling the rest) and replaces the old
|
|
455
|
+
non-unique index with the partial unique index `idx_run_steps_key_unique
|
|
456
|
+
(run_id, idempotency_key) WHERE idempotency_key IS NOT NULL`. The index is
|
|
457
|
+
created in the migration, after the dedupe — the same ordering trap as
|
|
458
|
+
`position`.
|
|
459
|
+
|
|
460
|
+
`src/db/step-idempotency.ts` exposes `runStepOnce` / `runStepOnceAsync`:
|
|
461
|
+
|
|
462
|
+
1. a key that belongs to another step in the same run is rejected with
|
|
463
|
+
`IdempotencyConflictError`;
|
|
464
|
+
2. an already `passed`/`skipped` step is **replayed** from `output_json` — the
|
|
465
|
+
body is not called, `attempt` does not grow and no side effect repeats
|
|
466
|
+
(`replayed: true`, `executed: false`);
|
|
467
|
+
3. a `failed` step is retried with `attempt + 1`, so a transient error does not
|
|
468
|
+
turn into a permanent skip;
|
|
469
|
+
4. a `running` step, or a second call for the same key while the first is still
|
|
470
|
+
inside the body, raises `StepInFlightError` — the in-process `inFlight` set
|
|
471
|
+
covers parallel async calls, the unique index covers the database;
|
|
472
|
+
5. a missing step is created with the key, then executed through the journal
|
|
473
|
+
from 36.1.b.
|
|
474
|
+
|
|
475
|
+
The same key is allowed in different runs; `test-step-idempotency.mjs` covers
|
|
476
|
+
first execution, replay from cache (including after reconnect), conflicts,
|
|
477
|
+
retry and parallel deduplication.
|
|
478
|
+
|
|
479
|
+
### Dead letter queue (Sprint 36.4)
|
|
480
|
+
|
|
481
|
+
A step that fails on every attempt is not transient: resuming the run again just
|
|
482
|
+
burns another attempt and hides the real problem. Schema v5 adds `run_dlq`, the
|
|
483
|
+
durable queue of deterministically failed steps:
|
|
484
|
+
|
|
485
|
+
| Column | Purpose |
|
|
486
|
+
| --- | --- |
|
|
487
|
+
| `run_id`, `step_name` | Which step dead-lettered; cascade-deleted with the run |
|
|
488
|
+
| `status` | `open → retried` or `open → discarded` |
|
|
489
|
+
| `reason` | `attempts-exhausted` (automatic scan) or `manual` |
|
|
490
|
+
| `error`, `attempts` | Snapshot of the failure at the moment of enqueue |
|
|
491
|
+
| `resolved_at`, `resolution` | When and how the entry was closed (`manual-retry`, `discarded`) |
|
|
492
|
+
|
|
493
|
+
`src/db/run-dlq.ts` provides:
|
|
494
|
+
|
|
495
|
+
1. `scanDeadLetters({ runId?, minAttempts = 3, limit })` selects steps with
|
|
496
|
+
`status = failed` and `attempt >= threshold` and enqueues only new ones. The
|
|
497
|
+
partial unique index `idx_run_dlq_open_unique (run_id, step_name) WHERE
|
|
498
|
+
status = 'open'` makes enqueue idempotent, so a repeated scan does not create
|
|
499
|
+
duplicates.
|
|
500
|
+
2. `retryDeadLetter(id)` is the manual retry: it reopens the failed run, calls
|
|
501
|
+
`retryStep` (attempt + 1, step back to `running`) and closes the entry as
|
|
502
|
+
`retried` with `resolution = manual-retry`. Closed entries cannot be retried
|
|
503
|
+
or discarded twice.
|
|
504
|
+
3. `discardDeadLetter(id, resolution = "discarded")` closes the entry without
|
|
505
|
+
touching the step — the run stays failed.
|
|
506
|
+
4. `listDeadLetters` / `countDeadLetters` filter `open` or `all` for dashboards
|
|
507
|
+
(36.6) and metrics.
|
|
508
|
+
|
|
509
|
+
`retryDeadLetter` calls `reopenRun` and `retryStep`, which each open their own
|
|
510
|
+
transaction. `withTransaction` therefore nests through `SAVEPOINT` when a
|
|
511
|
+
transaction is already active, keeping the whole retry atomic instead of failing
|
|
512
|
+
with `cannot start a transaction within a transaction`. `test-run-dlq.mjs`
|
|
513
|
+
covers the threshold, idempotent scans, manual retry, discard, cascade delete,
|
|
514
|
+
reconnect and the v4 → v5 migration.
|
|
515
|
+
|
|
516
|
+
### Dead letter queue in the GUI (Sprint 36.6)
|
|
517
|
+
|
|
518
|
+
The side panel exposes the queue through `src/core/dlq-api.ts`, a thin facade
|
|
519
|
+
that normalises the filter (`open` by default, plus `all`/`retried`/`discarded`)
|
|
520
|
+
and clamps the limit, then calls `listDeadLetters` / `retryDeadLetter` /
|
|
521
|
+
`discardDeadLetter`. RPC methods `list_dlq`, `retry_dlq` and `discard_dlq` are
|
|
522
|
+
declared in `src/rpc.ts` and handled in `src/index.ts`; the two mutations are
|
|
523
|
+
audited as `dlq.retry` and `dlq.discard`. `retry_dlq` only prepares the step
|
|
524
|
+
(reopen + `attempt + 1` + entry closed) — the handler itself is executed by a
|
|
525
|
+
later resume, so the panel never claims a step has already run. The UI section
|
|
526
|
+
shows the open count, status filter, creation time, run/step, reason, attempts,
|
|
527
|
+
error and status-aware actions; retry and discard ask for confirmation and
|
|
528
|
+
refresh the list through the same facade. `test-dlq-gui.mjs` checks the RPC/GUI
|
|
529
|
+
wiring, locale parity and the facade behaviour on a temporary SQLite database.
|
|
530
|
+
|
|
531
|
+
### Pause with context injection (Sprint 36.7)
|
|
532
|
+
|
|
533
|
+
The durable run model gains a new table `run_injections` (`SCHEMA_VERSION = 7`, migration step 7)
|
|
534
|
+
with columns `id`, `run_id` (cascade delete from `runs`), `step_name`, `kind` (`comment` /
|
|
535
|
+
`file` / `artifact`), `content`, `author`, `metadata_json`, `created_at`, `consumed_at`,
|
|
536
|
+
`consumed_by_step`, `consumed_attempt`, plus indexes `idx_run_injections_run(run_id, created_at)`
|
|
537
|
+
and a partial index `idx_run_injections_pending(run_id, step_name) WHERE consumed_at IS NULL`.
|
|
538
|
+
|
|
539
|
+
A run can be paused between steps: `RunStatus` gains `paused` with transitions
|
|
540
|
+
`pending → running/paused/cancelled`, `running → paused/passed/failed/cancelled`,
|
|
541
|
+
`paused → running/passed/cancelled`. `pauseRunRecord(id)` sets `paused` without filling
|
|
542
|
+
`finished_at`. `pauseRun(runId, input)` in `src/db/run-context.ts` requires an existing,
|
|
543
|
+
non-terminal run with no step currently `running`, addresses the first unfinished step (or an
|
|
544
|
+
explicit `stepName`), rejects completed/missing targets, and stores one injection per provided
|
|
545
|
+
payload (`comment`, `file` with path/content/title, `artifact` with name/content). Secrets are
|
|
546
|
+
masked on write: `redactSecretsInText` covers text/comment/file content, and a recursive
|
|
547
|
+
`redactValue` with `SENSITIVE_KEY_RE` masks whole values of sensitive JSON keys
|
|
548
|
+
(`*TOKEN*`, `*SECRET*`, `*PASSWORD*`, `*API_KEY*`, `*CREDENTIAL*`, `*AUTH*`, ...) to `***`.
|
|
549
|
+
A single injection is capped at `MAX_INJECTION_CONTENT` (100 kB).
|
|
550
|
+
|
|
551
|
+
`listRunInjections(runId, { pendingOnly })` returns history ordered by creation time, exposing
|
|
552
|
+
author, masked content and consumption state. `pendingInjectionsForStep(runId, stepName)` returns
|
|
553
|
+
the not-yet-consumed injections addressed to a step.
|
|
554
|
+
|
|
555
|
+
`StepHandler` now receives `(step, context: StepContext)` where `StepContext.injections` holds
|
|
556
|
+
the injections for that step. `resumeRunSync` / `resumeRun` pass them before executing each step,
|
|
557
|
+
and after a successful step call `consumeInjections(ids, stepName, attempt)` to mark the
|
|
558
|
+
injections consumed exactly once (retry keeps them for the next attempt). `finalize` calls
|
|
559
|
+
`consumeOrphanInjections` so injections addressed to already-completed steps do not look pending
|
|
560
|
+
in the history, and supports `paused → passed` when no steps remain. `ResumeResult` gains
|
|
561
|
+
`injected: string[]`. `test-run-context.mjs` covers schema v7, pause-before-start / pause-between
|
|
562
|
+
steps / explicit targeting, comment + file + artifact with secret masking and author visibility,
|
|
563
|
+
single-consumption on resume, repeated resume without re-delivery, pause without context,
|
|
564
|
+
validation errors (missing/completed/running target, terminal run, no unfinished steps, empty
|
|
565
|
+
path, artifact without content, oversized content), async resume and cascade delete on run
|
|
566
|
+
removal.
|
|
567
|
+
|
|
568
|
+
### Pause and resume in the GUI (Sprint 36.8)
|
|
569
|
+
|
|
570
|
+
`src/core/run-panel-api.ts` is the GUI-facing facade over durable runs. `listRunPanel({ filter, limit })`
|
|
571
|
+
accepts `active` (pending/running/paused/failed), `all`, or a concrete run status, normalizes the
|
|
572
|
+
limit to 1..100 and returns compact `RunPanelRun` entries: status, progress (`doneSteps` /
|
|
573
|
+
`totalSteps`), first unfinished `currentStep` with a stable `anchor`, up to 20 context injections
|
|
574
|
+
(content preview capped at 500 characters, author, timestamps, consumer) and the count of pending
|
|
575
|
+
injections. `active` is also reported for the panel badge.
|
|
576
|
+
|
|
577
|
+
`pauseRunPanel(runId, { comment, author, stepName? })` delegates to `pauseRun`, returning
|
|
578
|
+
`{ success: false, error }` instead of throwing, so the GUI can show the database error next to the
|
|
579
|
+
button. `resumeRunPanel(runId)` only prepares the run: it accepts `paused` or `failed`, calls
|
|
580
|
+
`reopenRun` (status becomes `running`), and returns the next unfinished step from `findResumeStep`.
|
|
581
|
+
Actual step execution remains with `resumeRun` / the DAG executor; the facade never pretends that a
|
|
582
|
+
step ran.
|
|
583
|
+
|
|
584
|
+
RPC methods `list_durable_runs`, `pause_durable_run` and `resume_durable_run` are declared in
|
|
585
|
+
`src/rpc.ts`, implemented in `src/index.ts`, and audited as `run.pause` / `run.resume` (target is the
|
|
586
|
+
run id). The GUI section «⏯️ Запуски DAG» in `src/gui.tsx` renders the run list with status filter,
|
|
587
|
+
progress, current-step anchor link, a comment field, pause/resume buttons with confirmation, a
|
|
588
|
+
blocked pause plus warning while the current step is `running`, and the context history with author
|
|
589
|
+
and consumer. Locales ru/en/zh stay in sync. `test-pause-gui.mjs` verifies the RPC contract, locale
|
|
590
|
+
parity, current-step/progress output, pause with masked comment and author, active/paused filters,
|
|
591
|
+
resume preparation, rejection of a repeated resume, end-to-end comment delivery through
|
|
592
|
+
`resumeRun`, running-step rejection, failed-run resume and list limits.
|
|
593
|
+
|
|
414
594
|
## Interfaces
|
|
415
595
|
|
|
416
596
|
| Interface | Audience | Entry point |
|
|
417
597
|
| --- | --- | --- |
|
|
418
598
|
| Agent tools | AI agent | 26 tools registered via `ctx.tool.transform` |
|
|
419
599
|
| Agent skill | AI agent | `skills/scheduled-job-best-practices` |
|
|
420
|
-
| RPC | Sidebar GUI | `src/rpc.ts` contracts,
|
|
600
|
+
| RPC | Sidebar GUI | `src/rpc.ts` contracts, 47 methods |
|
|
421
601
|
| Sidebar GUI | Human | `gui-experimental.cjs` |
|
|
422
602
|
| Web dashboard | Human | `startDashboardServer` (localhost, random/fixed port) |
|
|
423
603
|
|
|
@@ -557,3 +737,47 @@ after the agent with the user's privileges and are not filtered by tool policy.
|
|
|
557
737
|
| New agent tool | Add a zod schema + execute function, register in `ctx.tool.transform`, add an RPC contract |
|
|
558
738
|
| New dashboard panel | Extend `server.ts` routes and the HTML template |
|
|
559
739
|
| New matrix policy | Extend `MatrixConfig` in `task-transfer.ts` and the logic in `core/matrix.ts` |
|
|
740
|
+
|
|
741
|
+
## Mission runtime и гибридные входы (план 38–40)
|
|
742
|
+
|
|
743
|
+
> Статус: спека. Что уже в коде, а что нет — [ROADMAP.md](../ROADMAP.md) §1.
|
|
744
|
+
|
|
745
|
+
Система гибридная: ядро (**mission runtime**) не знает про планировщик ОС.
|
|
746
|
+
Планировщик — адаптер входа, регистрация опциональна.
|
|
747
|
+
|
|
748
|
+
### Классы входа
|
|
749
|
+
|
|
750
|
+
| Класс | Вход | Регистрация в ОС | Реализация |
|
|
751
|
+
|---|---|---|---|
|
|
752
|
+
| Ad-hoc | `run_mission` / CLI / GUI / RPC | нет | план 38 |
|
|
753
|
+
| Внутренний | chain / DAG / retry / escalation | нет | сейчас через `backend.runTask` + force-маркер; план 40 — напрямую в runtime |
|
|
754
|
+
| Registered | cron / once / file / git / mcp-event / webhook | да (cron/once) | есть: `core/scheduler/*`, `file-watcher`, `git-trigger`, `integrations` |
|
|
755
|
+
|
|
756
|
+
### Объекты
|
|
757
|
+
|
|
758
|
+
| Объект | Содержимое | Таблица |
|
|
759
|
+
|---|---|---|
|
|
760
|
+
| Миссия | цель + scope + gate-спека + safety + бюджет | `missions` (план 38, опциональный шаблон) |
|
|
761
|
+
| Задача | миссия-шаблон + триггер | `tasks` (есть) |
|
|
762
|
+
| Запуск | durable-исполнение: шаги, попытки, вердикты | `runs` / `run_steps` (есть, SCHEMA_VERSION 7) |
|
|
763
|
+
| Исход гейта | вердикт + provenance + экономика | `gate_outcomes` (план 40) |
|
|
764
|
+
|
|
765
|
+
### Путь исполнения (целевой)
|
|
766
|
+
|
|
767
|
+
```
|
|
768
|
+
вход → intake (gate + safety → политика + бюджет) → createRun(trigger_kind)
|
|
769
|
+
→ planner → [route → context compile → execute → GATE]* → artifact → report
|
|
770
|
+
```
|
|
771
|
+
|
|
772
|
+
Существующий путь планировщика (`wrapper → opencode run → record-history → history`)
|
|
773
|
+
сохраняется для обратной совместимости; в 40 он подключается к runtime и создаёт
|
|
774
|
+
durable-run, а исходы гейта пишутся в ledger.
|
|
775
|
+
|
|
776
|
+
### Что переиспользуется
|
|
777
|
+
|
|
778
|
+
- Durable state: `db/runs-repo`, `run-journal`, `run-resume`, `step-idempotency`, `run-context`.
|
|
779
|
+
- Роутинг: `core/router/rules|dispatch|escalation|planner`, `db/capability-repo`.
|
|
780
|
+
- Права и секреты: `core/permissions`, `core/secrets` (scoped-инъекция).
|
|
781
|
+
- Телеметрия: `core/otel`, `core/prometheus`, `core/structured-log`.
|
|
782
|
+
- Пауза с инъекциями: `db/run-context` + `core/run-panel-api` → основа approval-гейта.
|
|
783
|
+
- Retrieval для scaffolding: подход bag-of-words из `notification_embeddings`.
|