opencode-windows-scheduler 1.5.2 → 1.5.5
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 +107 -2
- package/CROSS_PLATFORM.md +107 -71
- package/LICENSE +21 -21
- package/README.md +74 -26
- package/ROADMAP-STRATEGY.md +11 -4
- package/ROADMAP.md +322 -112
- package/dist/core/analytics.d.ts +3 -0
- package/dist/core/analytics.d.ts.map +1 -1
- package/dist/core/analytics.js +4 -0
- package/dist/core/audit.d.ts +2 -1
- package/dist/core/audit.d.ts.map +1 -1
- package/dist/core/audit.js +32 -1
- package/dist/core/cron-to-schtasks.d.ts.map +1 -1
- package/dist/core/cron-to-schtasks.js +21 -4
- package/dist/core/file-watcher.d.ts.map +1 -1
- package/dist/core/file-watcher.js +16 -1
- package/dist/core/git-trigger.d.ts +4 -2
- package/dist/core/git-trigger.d.ts.map +1 -1
- package/dist/core/git-trigger.js +34 -16
- package/dist/core/local-ai.d.ts +52 -0
- package/dist/core/local-ai.d.ts.map +1 -0
- package/dist/core/local-ai.js +119 -0
- package/dist/core/lock.d.ts +14 -0
- package/dist/core/lock.d.ts.map +1 -1
- package/dist/core/lock.js +81 -4
- package/dist/core/matrix.d.ts.map +1 -1
- package/dist/core/matrix.js +3 -2
- package/dist/core/native-notify.d.ts.map +1 -1
- package/dist/core/native-notify.js +3 -0
- package/dist/core/one-shot.d.ts +7 -1
- package/dist/core/one-shot.d.ts.map +1 -1
- package/dist/core/one-shot.js +15 -2
- package/dist/core/permissions.d.ts +69 -0
- package/dist/core/permissions.d.ts.map +1 -0
- package/dist/core/permissions.js +143 -0
- package/dist/core/ps-wrapper.d.ts +9 -30
- package/dist/core/ps-wrapper.d.ts.map +1 -1
- package/dist/core/ps-wrapper.js +477 -108
- package/dist/core/record-history.d.ts +11 -0
- package/dist/core/record-history.d.ts.map +1 -1
- package/dist/core/record-history.js +106 -4
- package/dist/core/savings.d.ts +70 -0
- package/dist/core/savings.d.ts.map +1 -0
- package/dist/core/savings.js +87 -0
- package/dist/core/schedule-gate.js +7 -3
- package/dist/core/schedule-v2.js +1 -1
- package/dist/core/scheduler/index.d.ts +13 -1
- package/dist/core/scheduler/index.d.ts.map +1 -1
- package/dist/core/scheduler/index.js +35 -4
- package/dist/core/scheduler/linux.d.ts +4 -1
- package/dist/core/scheduler/linux.d.ts.map +1 -1
- package/dist/core/scheduler/linux.js +53 -20
- package/dist/core/scheduler/mac.d.ts +2 -1
- package/dist/core/scheduler/mac.d.ts.map +1 -1
- package/dist/core/scheduler/mac.js +24 -6
- package/dist/core/scheduler/posix.d.ts +1 -1
- package/dist/core/scheduler/posix.d.ts.map +1 -1
- package/dist/core/scheduler/posix.js +2 -2
- package/dist/core/scheduler/registry.d.ts +3 -2
- package/dist/core/scheduler/registry.d.ts.map +1 -1
- package/dist/core/scheduler/registry.js +6 -5
- package/dist/core/scheduler/windows.d.ts +49 -1
- package/dist/core/scheduler/windows.d.ts.map +1 -1
- package/dist/core/scheduler/windows.js +219 -34
- package/dist/core/secrets.d.ts +5 -3
- package/dist/core/secrets.d.ts.map +1 -1
- package/dist/core/secrets.js +86 -8
- package/dist/core/self-analysis.d.ts +117 -0
- package/dist/core/self-analysis.d.ts.map +1 -0
- package/dist/core/self-analysis.js +539 -0
- package/dist/core/session.d.ts +11 -3
- package/dist/core/session.d.ts.map +1 -1
- package/dist/core/session.js +34 -5
- package/dist/core/shutdown.d.ts +26 -0
- package/dist/core/shutdown.d.ts.map +1 -0
- package/dist/core/shutdown.js +49 -0
- package/dist/core/summary.d.ts +69 -0
- package/dist/core/summary.d.ts.map +1 -0
- package/dist/core/summary.js +250 -0
- package/dist/core/telegram.d.ts +10 -0
- package/dist/core/telegram.d.ts.map +1 -1
- package/dist/core/telegram.js +228 -47
- package/dist/core/triage-chain.d.ts +40 -0
- package/dist/core/triage-chain.d.ts.map +1 -0
- package/dist/core/triage-chain.js +80 -0
- package/dist/core/triage-compare.d.ts +68 -0
- package/dist/core/triage-compare.d.ts.map +1 -0
- package/dist/core/triage-compare.js +184 -0
- package/dist/core/triage-rules.d.ts +23 -0
- package/dist/core/triage-rules.d.ts.map +1 -0
- package/dist/core/triage-rules.js +196 -0
- package/dist/core/triage-shadow.d.ts +91 -0
- package/dist/core/triage-shadow.d.ts.map +1 -0
- package/dist/core/triage-shadow.js +160 -0
- package/dist/core/triage-worker.d.ts +55 -0
- package/dist/core/triage-worker.d.ts.map +1 -0
- package/dist/core/triage-worker.js +314 -0
- package/dist/core/triage.d.ts +76 -0
- package/dist/core/triage.d.ts.map +1 -0
- package/dist/core/triage.js +271 -0
- package/dist/core/watch-paths.d.ts +6 -0
- package/dist/core/watch-paths.d.ts.map +1 -0
- package/dist/core/watch-paths.js +62 -0
- package/dist/core/wrappers/bash.d.ts +15 -3
- package/dist/core/wrappers/bash.d.ts.map +1 -1
- package/dist/core/wrappers/bash.js +153 -120
- package/dist/db/history-repo.d.ts +1 -1
- package/dist/db/history-repo.d.ts.map +1 -1
- package/dist/db/history-repo.js +29 -14
- package/dist/db/schema.d.ts +1 -1
- package/dist/db/schema.d.ts.map +1 -1
- package/dist/db/schema.js +31 -0
- package/dist/history.d.ts +2 -2
- package/dist/history.d.ts.map +1 -1
- package/dist/history.js +3 -3
- package/dist/i18n.d.ts +25 -2
- package/dist/i18n.d.ts.map +1 -1
- package/dist/i18n.js +75 -10
- package/dist/index.d.ts +66 -3
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +527 -68
- package/dist/integrations.d.ts +9 -1
- package/dist/integrations.d.ts.map +1 -1
- package/dist/integrations.js +34 -6
- package/dist/notifications.d.ts +30 -2
- package/dist/notifications.d.ts.map +1 -1
- package/dist/notifications.js +289 -10
- package/dist/profiles.d.ts +1 -1
- package/dist/profiles.d.ts.map +1 -1
- package/dist/profiles.js +21 -3
- package/dist/rpc.d.ts +401 -5
- package/dist/rpc.d.ts.map +1 -1
- package/dist/rpc.js +138 -5
- package/dist/server.d.ts +20 -0
- package/dist/server.d.ts.map +1 -1
- package/dist/server.js +136 -14
- package/dist/settings.d.ts +167 -3
- package/dist/settings.d.ts.map +1 -1
- package/dist/settings.js +322 -3
- package/dist/task-transfer.d.ts +8 -1
- package/dist/task-transfer.d.ts.map +1 -1
- package/dist/task-transfer.js +2 -2
- package/dist/types.d.ts +8 -1
- package/dist/types.d.ts.map +1 -1
- package/dist/types.js +23 -5
- package/dist/workspaces.d.ts +9 -0
- package/dist/workspaces.d.ts.map +1 -1
- package/dist/workspaces.js +25 -0
- package/docs/ARCHITECTURE.md +48 -28
- package/docs/CONCEPT.md +230 -0
- package/docs/CROSS_PLATFORM.ru.md +150 -0
- package/docs/CROSS_PLATFORM.zh.md +146 -0
- package/docs/FAQ.md +52 -0
- package/docs/FAQ.ru.md +53 -0
- package/docs/FAQ.zh.md +43 -0
- package/docs/FEATURES.md +141 -44
- package/docs/FEATURES.zh.md +655 -0
- package/docs/LOCAL-AI.md +300 -0
- package/docs/MIGRATION.md +17 -0
- package/docs/README.ru.md +22 -16
- package/docs/README.zh.md +286 -0
- package/docs/SAVINGS.md +61 -0
- package/docs/SAVINGS.ru.md +60 -0
- package/docs/SAVINGS.zh.md +52 -0
- package/docs/ZH-LOCALE-PLAN.md +324 -0
- package/docs/spikes/local-model-structured-output.md +81 -0
- package/docs/spikes/ollama-qwen3-4b-smoke.json +28 -0
- package/docs/spikes/ollama-qwen3-4b.json +163 -0
- package/gui-experimental.cjs +8 -8
- package/locales/en.json +85 -0
- package/locales/ru.json +85 -0
- package/locales/zh.json +780 -0
- package/package.json +31 -7
- package/scripts/bench-local.mjs +321 -0
- package/scripts/check-zh-locale.mjs +218 -0
- package/scripts/run-tests.mjs +236 -0
- package/scripts/spike-local-structured.mjs +182 -0
- package/scripts/test-locale.mjs +4 -3
- package/skills/scheduled-job-best-practices/SKILL.md +6 -3
- package/skills/scheduled-job-best-practices/references/recipes.md +40 -0
- package/src/core/analytics.ts +10 -0
- package/src/core/audit.ts +39 -1
- package/src/core/cron-to-schtasks.ts +23 -4
- package/src/core/file-watcher.ts +20 -1
- package/src/core/git-trigger.ts +34 -16
- package/src/core/local-ai.ts +173 -0
- package/src/core/lock.ts +88 -3
- package/src/core/matrix.ts +5 -1
- package/src/core/native-notify.ts +3 -0
- package/src/core/one-shot.ts +18 -2
- package/src/core/permissions.ts +200 -0
- package/src/core/ps-wrapper.ts +492 -108
- package/src/core/record-history.ts +111 -4
- package/src/core/savings.ts +150 -0
- package/src/core/schedule-gate.ts +9 -3
- package/src/core/schedule-v2.ts +1 -1
- package/src/core/scheduler/index.ts +41 -3
- package/src/core/scheduler/linux.ts +67 -22
- package/src/core/scheduler/mac.ts +24 -7
- package/src/core/scheduler/posix.ts +2 -2
- package/src/core/scheduler/registry.ts +7 -5
- package/src/core/scheduler/windows.ts +237 -32
- package/src/core/secrets.ts +101 -7
- package/src/core/self-analysis.ts +744 -0
- package/src/core/session.ts +40 -5
- package/src/core/shutdown.ts +69 -0
- package/src/core/summary.ts +318 -0
- package/src/core/telegram.ts +266 -55
- package/src/core/triage-chain.ts +125 -0
- package/src/core/triage-compare.ts +277 -0
- package/src/core/triage-rules.ts +238 -0
- package/src/core/triage-shadow.ts +240 -0
- package/src/core/triage-worker.ts +344 -0
- package/src/core/triage.ts +366 -0
- package/src/core/watch-paths.ts +70 -0
- package/src/core/wrappers/bash.ts +181 -138
- package/src/db/history-repo.ts +31 -18
- package/src/db/schema.ts +31 -0
- package/src/gui.tsx +551 -14
- package/src/history.ts +7 -3
- package/src/i18n.ts +87 -13
- package/src/index.ts +649 -71
- package/src/integrations.ts +50 -6
- package/src/notifications.ts +468 -5
- package/src/profiles.ts +21 -3
- package/src/rpc.ts +143 -5
- package/src/server.ts +135 -16
- package/src/settings.ts +582 -5
- package/src/task-transfer.ts +10 -3
- package/src/types.ts +24 -5
- package/src/workspaces.ts +22 -0
package/docs/LOCAL-AI.md
ADDED
|
@@ -0,0 +1,300 @@
|
|
|
1
|
+
# Local assistant (triage)
|
|
2
|
+
|
|
3
|
+
The local assistant is an optional, fully offline classifier for run outcomes.
|
|
4
|
+
After a run finishes, the scheduler can ask a local model to classify the
|
|
5
|
+
outcome (quality, timeout, permission, network, unknown) and write the verdict
|
|
6
|
+
to the triage audit. It is **opt-in**: when no model is available the scheduler
|
|
7
|
+
keeps working exactly as before and notifications are never blocked.
|
|
8
|
+
|
|
9
|
+
Triage is not a scheduler feature by itself — it only affects notifications. It
|
|
10
|
+
never changes run status, retries, Quality Gates, DAG dependencies or history.
|
|
11
|
+
|
|
12
|
+
## How it works
|
|
13
|
+
|
|
14
|
+
```
|
|
15
|
+
run finished ──► triage chain ──► notify / skip / log-only (shadow)
|
|
16
|
+
│
|
|
17
|
+
├─ llm — local model classifies the failure
|
|
18
|
+
└─ rules - built-in patterns (timeout, permission, network, quality, cost, task)
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
- `off` — no triage; every notification is sent (default).
|
|
22
|
+
- `rules` — built-in rules only. No model, no network calls.
|
|
23
|
+
- `llm` — the configured local model only.
|
|
24
|
+
- `auto` — the model first, then the rules engine (recommended).
|
|
25
|
+
|
|
26
|
+
Rules semantics: if `rules` is omitted (`undefined`), the built-in rule set is
|
|
27
|
+
active. An explicit empty array (`rules: []`) disables the rules engine entirely.
|
|
28
|
+
A non-empty custom array replaces the built-in set; it does not extend it.
|
|
29
|
+
|
|
30
|
+
### Built-in rules
|
|
31
|
+
|
|
32
|
+
The built-in set classifies errors by text, status, cost and task name. All
|
|
33
|
+
built-in rules are notify-only: they never suppress a notification.
|
|
34
|
+
|
|
35
|
+
| Rule | Match | Severity |
|
|
36
|
+
| --- | --- | --- |
|
|
37
|
+
| `error-timeout` | timeout / deadline in the error text | high |
|
|
38
|
+
| `error-permission` | permission denied, access denied, forbidden | high |
|
|
39
|
+
| `error-network` | connection refused/reset, DNS, network error | high |
|
|
40
|
+
| `error-quality` | Quality Gate, failed tests, failed build, lint | high |
|
|
41
|
+
| `cost-high` | `costUsd >= 1` | high |
|
|
42
|
+
| `task-important` | task name contains deploy, release, publish, production, backup, restore or migration | high |
|
|
43
|
+
| `status-error` | status is `error` | high |
|
|
44
|
+
| `status-partial` | status is `partial` | medium |
|
|
45
|
+
| `status-success` | status is `success` | low |
|
|
46
|
+
|
|
47
|
+
A custom array replaces the built-in set. For example, this configuration
|
|
48
|
+
suppresses noisy nightly runs and marks runs costing $5 or more as high:
|
|
49
|
+
|
|
50
|
+
```json
|
|
51
|
+
"notifications": {
|
|
52
|
+
"triage": {
|
|
53
|
+
"mode": "rules",
|
|
54
|
+
"rules": [
|
|
55
|
+
{ "id": "skip-nightly", "field": "task", "operator": "contains", "value": "nightly", "action": "skip", "priority": 50 },
|
|
56
|
+
{ "id": "expensive", "field": "cost", "operator": "gte", "value": 5, "severity": "high", "priority": 90 }
|
|
57
|
+
]
|
|
58
|
+
}
|
|
59
|
+
}
|
|
60
|
+
```
|
|
61
|
+
|
|
62
|
+
The result is validated against a fixed JSON schema. Invalid JSON, an
|
|
63
|
+
unreachable endpoint, a timeout or low confidence all fall back to the rules
|
|
64
|
+
engine (fail-open). With `fallback: "notify"` the scheduler skips the rules step
|
|
65
|
+
and delivers the notification instead. The legacy name `"skip"` is still
|
|
66
|
+
accepted and normalized to `"notify"`.
|
|
67
|
+
|
|
68
|
+
The model only **classifies** a run: a valid verdict never suppresses a
|
|
69
|
+
notification on its own. Only a matching rule with `action: "skip"` can
|
|
70
|
+
suppress delivery. This is intentional: an uncertain small model must not be
|
|
71
|
+
able to hide a real failure.
|
|
72
|
+
|
|
73
|
+
## Delivery latency (async triage)
|
|
74
|
+
|
|
75
|
+
In `llm` and `auto` modes triage runs asynchronously. `record-history` delivers
|
|
76
|
+
the notification immediately and starts a detached worker for the model call;
|
|
77
|
+
the worker writes the verdict to `audit_log` with `async: true`. The configured
|
|
78
|
+
`timeoutMs` applies to that background request, not to delivery: a cold model
|
|
79
|
+
that takes 40 seconds cannot delay the webhook, chain triggers or the task lock.
|
|
80
|
+
|
|
81
|
+
Only `rules` mode triages synchronously, because rules are the only thing that
|
|
82
|
+
can suppress a notification. In `llm`/`auto` the model and its rules fallback
|
|
83
|
+
are advisory: the notification is already sent, so `action: "skip"` in the
|
|
84
|
+
audit means “would have been skipped”, not “was suppressed”. Use `rules` mode
|
|
85
|
+
if rules must actually suppress delivery. The GUI shows this warning when a
|
|
86
|
+
model mode is selected.
|
|
87
|
+
|
|
88
|
+
In shadow mode the worker records `shadow: true` and `suppressed: false`, so a
|
|
89
|
+
shadow report remains a safe preview of triage decisions.
|
|
90
|
+
|
|
91
|
+
## Requirements
|
|
92
|
+
|
|
93
|
+
- [Ollama](https://ollama.com/) running locally, or any OpenAI-compatible
|
|
94
|
+
server (a `baseUrl` ending with `/v1` switches to the OpenAI protocol).
|
|
95
|
+
- One pulled model, for example `qwen3:4b`.
|
|
96
|
+
- No internet access is required after the model is downloaded.
|
|
97
|
+
|
|
98
|
+
```bash
|
|
99
|
+
ollama serve
|
|
100
|
+
ollama pull qwen3:4b
|
|
101
|
+
```
|
|
102
|
+
|
|
103
|
+
## Configuration
|
|
104
|
+
|
|
105
|
+
Triage settings live under `notifications.triage` and are edited from the GUI
|
|
106
|
+
side panel ("Local assistant") or through the `manage_local_ai` agent tool.
|
|
107
|
+
|
|
108
|
+
The panel shows a persistent connection status next to **Test connection**:
|
|
109
|
+
grey means "not checked", amber "checking", green "connected", red "no
|
|
110
|
+
connection" with the provider error. The test sends one synthetic
|
|
111
|
+
classification request (it is not saved) and reports the model, protocol and
|
|
112
|
+
latency. Status resets when `mode`, `baseUrl` or `model` changes, so a stale
|
|
113
|
+
green cannot hide a new endpoint. A red status never blocks notifications:
|
|
114
|
+
`llm`/`auto` triage is asynchronous and fail-open.
|
|
115
|
+
|
|
116
|
+
| Setting | Values | Default | Meaning |
|
|
117
|
+
| --- | --- | --- | --- |
|
|
118
|
+
| `mode` | `off` / `rules` / `llm` / `auto` | `off` | Triage strategy. |
|
|
119
|
+
| `baseUrl` | URL | `http://127.0.0.1:11434` | Ollama or OpenAI-compatible endpoint. |
|
|
120
|
+
| `model` | string | `""` | Model id, for example `qwen3:4b`. |
|
|
121
|
+
| `timeoutMs` | 1000..120000 | `60000` | Background request timeout in `llm`/`auto`; does not delay delivery. |
|
|
122
|
+
| `fallback` | `rules` / `notify` | `rules` | Behaviour when the model fails or is unsure. |
|
|
123
|
+
| `confidenceThreshold` | 0..1 | `0.6` | Minimum model confidence; below it the fallback applies. |
|
|
124
|
+
| `shadow.enabled` | boolean | `true` | Log decisions without suppressing notifications. |
|
|
125
|
+
| `shadow.days` | 1..365 | `14` | Shadow period length. |
|
|
126
|
+
| `shadow.startedAt` | ISO string / null | `null` | Start of the shadow period; `null` restarts it. |
|
|
127
|
+
|
|
128
|
+
`fallback: "skip"` is accepted as a legacy alias for `notify` and is normalized
|
|
129
|
+
on load, so old settings keep working without edits.
|
|
130
|
+
|
|
131
|
+
## Message summaries
|
|
132
|
+
|
|
133
|
+
`notifications.summary` turns a notification into at most three short lines for
|
|
134
|
+
Telegram and OS toasts. The same Ollama/OpenAI-compatible provider is used, but
|
|
135
|
+
the request is independent of triage and has its own timeout.
|
|
136
|
+
|
|
137
|
+
| Setting | Values | Default | Meaning |
|
|
138
|
+
| --- | --- | --- | --- |
|
|
139
|
+
| `summary.enabled` | boolean | `false` | Use the model summary instead of the template message. |
|
|
140
|
+
| `summary.maxLines` | 1..3 | `3` | Maximum number of lines. |
|
|
141
|
+
| `summary.maxCharsPerLine` | 20..500 | `120` | Hard cut per line. |
|
|
142
|
+
| `summary.timeoutMs` | 1000..120000 | `8000` | Summary request timeout. |
|
|
143
|
+
|
|
144
|
+
The model must answer with strict JSON `{"lines": ["...", "..."]}`. Any
|
|
145
|
+
failure — no provider, HTTP error, timeout, invalid JSON or schema — falls back
|
|
146
|
+
to a deterministic truncation: status and task name, the error text, then
|
|
147
|
+
runtime, tokens and cost. A summary never blocks or drops the notification:
|
|
148
|
+
delivery waits at most `timeoutMs`.
|
|
149
|
+
|
|
150
|
+
## Managing triage from the agent
|
|
151
|
+
|
|
152
|
+
The `manage_local_ai` tool has three actions.
|
|
153
|
+
|
|
154
|
+
Read the current state:
|
|
155
|
+
|
|
156
|
+
```json
|
|
157
|
+
{ "action": "get" }
|
|
158
|
+
```
|
|
159
|
+
|
|
160
|
+
Update one or more fields (merged with the current settings):
|
|
161
|
+
|
|
162
|
+
```json
|
|
163
|
+
{
|
|
164
|
+
"action": "update",
|
|
165
|
+
"mode": "auto",
|
|
166
|
+
"baseUrl": "http://127.0.0.1:11434",
|
|
167
|
+
"model": "qwen3:4b",
|
|
168
|
+
"timeoutMs": 60000,
|
|
169
|
+
"fallback": "rules",
|
|
170
|
+
"confidenceThreshold": 0.6,
|
|
171
|
+
"shadow": { "enabled": true, "days": 14 }
|
|
172
|
+
}
|
|
173
|
+
```
|
|
174
|
+
|
|
175
|
+
Send one classification request against the configured model (or a candidate
|
|
176
|
+
patch without saving it):
|
|
177
|
+
|
|
178
|
+
```json
|
|
179
|
+
{ "action": "test", "model": "qwen3:4b", "timeoutMs": 60000 }
|
|
180
|
+
```
|
|
181
|
+
|
|
182
|
+
`get` and `update` return a summary: `mode`, `baseUrl`, `model`, `timeoutMs`,
|
|
183
|
+
`fallback`, `confidenceThreshold`, `rules` (number of active rules or `null`),
|
|
184
|
+
`shadow`, `llmReady`, `shadowActive` and `protocol` (`ollama` or `openai`).
|
|
185
|
+
|
|
186
|
+
## Picking a model by RAM
|
|
187
|
+
|
|
188
|
+
The classifier is a small, structured task: a 4B model is usually enough. The
|
|
189
|
+
benchmark below prints a tier for the current machine.
|
|
190
|
+
|
|
191
|
+
| RAM | Tier | Recommended model | Notes |
|
|
192
|
+
| --- | --- | --- | --- |
|
|
193
|
+
| < 8 GB | rules-only | `qwen3:0.6b` | Prefer `mode: "rules"`; a tiny model may be too slow. |
|
|
194
|
+
| 8–15 GB | light | `qwen3:1.7b` | Fast, lower accuracy. |
|
|
195
|
+
| 15–30 GB | balanced | `qwen3:4b` | Recommended default. |
|
|
196
|
+
| > 30 GB | max | `qwen3:8b` | Better accuracy, more latency. |
|
|
197
|
+
|
|
198
|
+
## Benchmarking a machine
|
|
199
|
+
|
|
200
|
+
`scripts/bench-local.mjs` measures latency, schema validity and throughput
|
|
201
|
+
(tokens/s) for the configured model. It reuses the same triage prompt and JSON
|
|
202
|
+
schema as the scheduler.
|
|
203
|
+
|
|
204
|
+
```bash
|
|
205
|
+
npm run bench:local -- --model qwen3:4b --runs 3
|
|
206
|
+
npm run bench:local -- --model qwen3:4b --runs 5 --out bench.json
|
|
207
|
+
```
|
|
208
|
+
|
|
209
|
+
Options: `--base-url`, `--model`, `--runs` (1..50), `--timeout` (1000..600000),
|
|
210
|
+
`--out`, `--help`.
|
|
211
|
+
|
|
212
|
+
The report is a versioned JSON envelope (`schemaVersion: "1"`) suitable for
|
|
213
|
+
crowdsourcing results:
|
|
214
|
+
|
|
215
|
+
```json
|
|
216
|
+
{
|
|
217
|
+
"schemaVersion": "1",
|
|
218
|
+
"generatedAt": "2026-11-15T12:00:00.000Z",
|
|
219
|
+
"available": true,
|
|
220
|
+
"machine": { "platform": "win32", "arch": "x64", "cpu": "…", "cpuCount": 16, "ramGb": 15.9, "nodeVersion": "v24.21.0" },
|
|
221
|
+
"tier": { "id": "balanced", "recommendedModel": "qwen3:4b", "reason": "…" },
|
|
222
|
+
"model": "qwen3:4b",
|
|
223
|
+
"runs": 3,
|
|
224
|
+
"metrics": {
|
|
225
|
+
"schemaValid": 3,
|
|
226
|
+
"schemaValidRate": 1,
|
|
227
|
+
"jsonValid": 3,
|
|
228
|
+
"jsonValidRate": 1,
|
|
229
|
+
"avgLatencyMs": 23785,
|
|
230
|
+
"p95LatencyMs": 26904,
|
|
231
|
+
"avgTokPerSec": 28.7,
|
|
232
|
+
"p95TokPerSec": 28.98
|
|
233
|
+
},
|
|
234
|
+
"results": []
|
|
235
|
+
}
|
|
236
|
+
```
|
|
237
|
+
|
|
238
|
+
Exit codes: `0` when at least 70% of responses are schema-valid, `1` otherwise,
|
|
239
|
+
`2` when the endpoint or model is unavailable (the JSON report is still written
|
|
240
|
+
with `available: false`).
|
|
241
|
+
|
|
242
|
+
## Shadow mode
|
|
243
|
+
|
|
244
|
+
Shadow mode is the safe way to evaluate triage. Decisions are written to the
|
|
245
|
+
persistent audit journal (`audit_log`, action `triage.decision`), but no
|
|
246
|
+
notification is suppressed. In `llm`/`auto` the verdict arrives asynchronously
|
|
247
|
+
after delivery; in `rules` mode it is computed before delivery. Check the shadow
|
|
248
|
+
report before switching to `mode: "auto"`: it shows how many notifications
|
|
249
|
+
would have been skipped and whether any of those were false positives.
|
|
250
|
+
|
|
251
|
+
The journal survives restarts and runs in the short-lived `record-history`
|
|
252
|
+
process, unlike the old in-memory counters. Read individual decisions with
|
|
253
|
+
`get_audit_log` (`action: "triage.decision"`); the report is also available as
|
|
254
|
+
`rpc.get_shadow_report` (including the last 50 decisions). The report covers
|
|
255
|
+
the configured shadow window `[startedAt, startedAt + days]`; resetting it
|
|
256
|
+
deletes only shadow rows and keeps ordinary decision history.
|
|
257
|
+
|
|
258
|
+
Start with `mode: "auto"`, `shadow.enabled: true` and `shadow.days: 14`. After
|
|
259
|
+
the period, review the shadow report and only then disable shadow mode.
|
|
260
|
+
|
|
261
|
+
## Troubleshooting
|
|
262
|
+
|
|
263
|
+
| Symptom | Cause | Fix |
|
|
264
|
+
| --- | --- | --- |
|
|
265
|
+
| `connection refused` / `fetch failed` | Ollama is not running | `ollama serve` |
|
|
266
|
+
| `model not found` | Model not pulled | `ollama pull <model>`, then check `ollama list` |
|
|
267
|
+
| Requests time out | Model too large for the machine or context too long | Lower the model tier, raise `timeoutMs`, cap context (below) |
|
|
268
|
+
| `llmReady: false` in `manage_local_ai` `get` | Endpoint or model unavailable | Check `baseUrl` and `model` |
|
|
269
|
+
| Very slow first response | Cold model load | Run once to warm the model; the benchmark shows steady-state numbers |
|
|
270
|
+
| Invalid JSON from the model | Model too small or prompt drift | Use a larger model or `mode: "rules"` |
|
|
271
|
+
|
|
272
|
+
### OLLAMA_CONTEXT_LENGTH
|
|
273
|
+
|
|
274
|
+
Ollama allocates a large context window by default, which costs RAM and slows
|
|
275
|
+
CPU inference. For triage, a short context is enough. Set it in the environment
|
|
276
|
+
before starting the server:
|
|
277
|
+
|
|
278
|
+
```bash
|
|
279
|
+
# Windows (PowerShell)
|
|
280
|
+
$env:OLLAMA_CONTEXT_LENGTH = "2048"
|
|
281
|
+
ollama serve
|
|
282
|
+
```
|
|
283
|
+
|
|
284
|
+
```bash
|
|
285
|
+
# Linux / macOS
|
|
286
|
+
OLLAMA_CONTEXT_LENGTH=2048 ollama serve
|
|
287
|
+
```
|
|
288
|
+
|
|
289
|
+
Restart Ollama after changing the variable. If the model still does not fit,
|
|
290
|
+
choose a smaller tier or use `mode: "rules"`.
|
|
291
|
+
|
|
292
|
+
## Limits
|
|
293
|
+
|
|
294
|
+
- Triage only affects notifications. It never rewrites run results.
|
|
295
|
+
- The model runs locally; prompts and logs are not sent to a third party.
|
|
296
|
+
- A missing model never blocks scheduling: rules or direct delivery take over.
|
|
297
|
+
- The classifier is intentionally conservative. When in doubt it delivers the
|
|
298
|
+
notification (fail-open).
|
|
299
|
+
- The benchmark measures a single machine; results are not a guarantee for other
|
|
300
|
+
hardware.
|
package/docs/MIGRATION.md
CHANGED
|
@@ -240,6 +240,20 @@ For every migrated job:
|
|
|
240
240
|
right workspace path.
|
|
241
241
|
6. Wait for at least one natural scheduled run before deleting the old definition.
|
|
242
242
|
|
|
243
|
+
## Local AI / triage migration
|
|
244
|
+
|
|
245
|
+
If you are migrating from a setup that used cloud AI for lightweight task triage or
|
|
246
|
+
classification, you can move that load to a local model to save tokens:
|
|
247
|
+
|
|
248
|
+
1. Install Ollama: `ollama serve` and `ollama pull qwen3:4b` (or a smaller model for
|
|
249
|
+
RAM-constrained machines — see `docs/LOCAL-AI.md` for tier recommendations).
|
|
250
|
+
2. Configure triage via `manage_local_ai({action: "update", mode: "auto", ...})` or
|
|
251
|
+
through the GUI notifications panel.
|
|
252
|
+
3. Start in `shadow` mode so decisions are logged but not applied, then switch to `auto`
|
|
253
|
+
once confidence is acceptable.
|
|
254
|
+
4. Ollama is optional — if it is unavailable, the plugin falls back to rules-only mode
|
|
255
|
+
(fail-open) and never blocks notifications.
|
|
256
|
+
|
|
243
257
|
## Common pitfalls
|
|
244
258
|
|
|
245
259
|
| Symptom | Cause | Fix |
|
|
@@ -252,6 +266,9 @@ For every migrated job:
|
|
|
252
266
|
| Two runs at once after migration | old scheduler is still enabled | disable the old job |
|
|
253
267
|
| Cron rejected | expression not expressible by `schtasks` | use a supported pattern (`*/N`, fixed minute/hour, weekdays) |
|
|
254
268
|
| Prompts behave differently at night | interactive shell environment vs scheduler environment | use absolute paths, avoid alias-dependent commands |
|
|
269
|
+
| Local AI (Ollama) unreachable | `manage_local_ai` test fails or triage falls back to rules | run `ollama serve`, `ollama pull <model>`, check `OLLAMA_CONTEXT_LENGTH` |
|
|
270
|
+
| Local AI confidence too low | rules fire instead of LLM, more tokens used than expected | raise `confidenceThreshold` in `manage_local_ai`, review rule reasons in audit |
|
|
271
|
+
|
|
255
272
|
|
|
256
273
|
## Rollback
|
|
257
274
|
|
package/docs/README.ru.md
CHANGED
|
@@ -7,13 +7,20 @@
|
|
|
7
7
|
[](../LICENSE)
|
|
8
8
|
[](../package.json)
|
|
9
9
|
|
|
10
|
-
|
|
10
|
+
Translations: [English](../README.md) · [中文](README.zh.md).
|
|
11
11
|
|
|
12
12
|
---
|
|
13
13
|
|
|
14
|
-
|
|
14
|
+
## Быстрый старт
|
|
15
|
+
|
|
16
|
+
1. Установите плагин (см. [Установка](#установка)) и перезапустите OpenCode.
|
|
17
|
+
2. Попросите агента поставить первую задачу — достаточно одного вызова:
|
|
18
|
+
|
|
19
|
+
> Поставь задачу «утренний-отчёт»: каждый день в 09:00 с промптом «Просуммаризируй вчерашние git-коммиты и запиши отчёт в ~/reports/».
|
|
15
20
|
|
|
16
|
-
|
|
21
|
+
3. Откройте дашборд: агент печатает ссылку при создании задачи (по умолчанию `http://localhost:4380`), позже её можно получить инструментом `get_dashboard_info`. Посмотреть демо без установки: `node scripts/demo-dashboard.mjs` — дашборд с демо-данными на `http://localhost:4380`.
|
|
22
|
+
|
|
23
|
+

|
|
17
24
|
|
|
18
25
|
## Зачем
|
|
19
26
|
|
|
@@ -38,18 +45,18 @@ English version: [README.md](../README.md).
|
|
|
38
45
|
| Триггеры | cron, одноразовый запуск (`triggerType: "once"`), git-коммиты (`triggerType: "git"`, фильтры ветки/путей/игнорирования), изменение файла (chokidar, glob-маски `watchGlobs`/`watchIgnore`), MCP-события, входящие webhooks (`POST /api/hooks/:task` с HMAC) |
|
|
39
46
|
| Мультирепо | workspaces с валидацией путей, запуски по workspace, матрица поверх родительской задачи |
|
|
40
47
|
| Наблюдаемость | история SQLite (success / error / timeout / partial / running), метрики (длительность, токены, стоимость), JSONL-логи с `/api/logs`, Prometheus `/metrics`, экспорт OTLP, логи по задачам, веб-дашборд с аналитикой за 14 дней, ретеншн истории и экспорт CSV/JSON |
|
|
41
|
-
| Эксплуатация | dry-run, экспорт/импорт JSON, шаблоны, уведомления по нескольким каналам (webhook, Telegram, нативные toast), тихие часы, дайджест, зашифрованные секреты (`${secret:NAME}`), журнал аудита, настройки |
|
|
42
|
-
| Интерфейсы | панель OpenCode GUI, веб-дашборд,
|
|
48
|
+
| Эксплуатация | dry-run, экспорт/импорт JSON, шаблоны, уведомления по нескольким каналам (webhook, Telegram, нативные toast), тихие часы, дайджест, локальный ассистент для триажа уведомлений (fail-open, shadow-режим), зашифрованные секреты (`${secret:NAME}`), журнал аудита, настройки |
|
|
49
|
+
| Интерфейсы | панель OpenCode GUI, веб-дашборд, 25 инструментов для агента, встроенный скилл |
|
|
43
50
|
|
|
44
51
|
### Язык интерфейса
|
|
45
52
|
|
|
46
|
-
Интерфейс доступен на русском (по умолчанию) и
|
|
53
|
+
Интерфейс доступен на русском (по умолчанию), английском и китайском (упрощённом). Переключатель языка находится в шапке панели планировщика (🌐 Авто / Русский / English / 中文), а также доступен через инструмент `manage_settings` (`action: "update"`, `locale: "zh"`). Значение `locale: "auto"` («Авто») следует за языком интерфейса OpenCode: панель реагирует на смену языка сразу, а разрешённая локаль отправляется на сервер, чтобы уведомления, дайджест и дашборд использовали тот же язык. Переключение применяется без перезапуска. Локализация дашборда ещё не завершена: часть строк на стороне клиента пока остаётся русской. Описания и схемы инструментов агента остаются английскими, диагностика в консоли — русской.
|
|
47
54
|
|
|
48
|
-
Каталоги лежат в `locales/ru.json` и `locales/
|
|
55
|
+
Каталоги лежат в `locales/ru.json`, `locales/en.json` и `locales/zh.json`; набор ключей в них должен совпадать, иначе CI падает.
|
|
49
56
|
|
|
50
57
|
## Установка
|
|
51
58
|
|
|
52
|
-
Нужны OpenCode v2 и Node.js
|
|
59
|
+
Нужны OpenCode v2 и Node.js 22.22+.
|
|
53
60
|
|
|
54
61
|
```bash
|
|
55
62
|
opencode plugin add opencode-windows-scheduler
|
|
@@ -69,12 +76,6 @@ opencode plugin add opencode-windows-scheduler
|
|
|
69
76
|
|
|
70
77
|
`experimental.schedules: false` отключает встроенный планировщик OpenCode, чтобы агент не путал встроенные инструменты расписаний с инструментами этого плагина. После изменения конфигурации перезапустите OpenCode.
|
|
71
78
|
|
|
72
|
-
Альтернатива — глобальная установка через npm:
|
|
73
|
-
|
|
74
|
-
```bash
|
|
75
|
-
npm install -g opencode-windows-scheduler
|
|
76
|
-
```
|
|
77
|
-
|
|
78
79
|
Из исходников:
|
|
79
80
|
|
|
80
81
|
```bash
|
|
@@ -86,7 +87,7 @@ npm run build && npm run build:gui
|
|
|
86
87
|
|
|
87
88
|
## Инструменты для агента
|
|
88
89
|
|
|
89
|
-
Агенту доступен весь функционал —
|
|
90
|
+
Агенту доступен весь функционал — 25 инструментов: расписание, пайплайны, эксплуатация, аналитика и администрирование.
|
|
90
91
|
|
|
91
92
|
| Инструмент | Аргументы | Что делает |
|
|
92
93
|
|---|---|---|
|
|
@@ -105,6 +106,7 @@ npm run build && npm run build:gui
|
|
|
105
106
|
| `get_metrics` | — | Всего запусков, успехов и падений |
|
|
106
107
|
| `get_analytics` | `days?`, `topLimit?` | Отчёт за период: запуски, успешность, длительность, токены, стоимость, топ задач |
|
|
107
108
|
| `manage_settings` | `action`, `maxConcurrent?`, `winterMode?`, `notifications?`, `history?` | Чтение и изменение глобальных настроек (параллелизм, уведомления, retention) |
|
|
109
|
+
| `manage_local_ai` | `action` (`get`/`update`/`test`), `mode?`, `baseUrl?`, `model?`, `timeoutMs?`, `fallback?`, `confidenceThreshold?`, `shadow?` | Настройки локального ассистента для триажа уведомлений и проверка модели одним запросом (см. [LOCAL-AI.md](LOCAL-AI.md)) |
|
|
108
110
|
| `manage_templates` | `action`, поля шаблона | Список, сохранение и удаление шаблонов задач |
|
|
109
111
|
| `manage_profiles` | `action`, `name?`, `port?` | Список, создание, переключение и удаление изолированных профилей |
|
|
110
112
|
| `transfer_tasks` | `action`, `data?` | Экспорт всех задач в JSON и импорт обратно |
|
|
@@ -184,7 +186,7 @@ src/
|
|
|
184
186
|
npm install
|
|
185
187
|
npm run build # tsc
|
|
186
188
|
npm run build:gui # vite
|
|
187
|
-
npm test #
|
|
189
|
+
npm test # 58 сюит, 600+ проверок
|
|
188
190
|
npm run test:en # те же сюиты с английской локалью
|
|
189
191
|
```
|
|
190
192
|
|
|
@@ -195,8 +197,12 @@ npm run test:en # те же сюиты с английской локаль
|
|
|
195
197
|
## Документация
|
|
196
198
|
|
|
197
199
|
- [ARCHITECTURE.md](ARCHITECTURE.md) — модель процессов, модули, бэкенды, модель данных.
|
|
200
|
+
- [CONCEPT.md](CONCEPT.md) — north star: верифицируемая локально-первая оркестрация.
|
|
198
201
|
- [FEATURES.md](FEATURES.md) — полный каталог возможностей с примерами.
|
|
202
|
+
- [FAQ.md](FAQ.md) — сценарии восстановления и ответы по эксплуатации (English).
|
|
199
203
|
- [MIGRATION.md](MIGRATION.md) — переезд с cron, systemd, launchd или Планировщика Windows.
|
|
204
|
+
- [SAVINGS.md](SAVINGS.md) — как считается оценка «Сэкономлено $» (English).
|
|
205
|
+
- [../CROSS_PLATFORM.md](../CROSS_PLATFORM.md) — различия и бэкенды Windows / macOS / Linux.
|
|
200
206
|
|
|
201
207
|
## FAQ
|
|
202
208
|
|