@aitne-sh/aitne 0.1.11 → 0.1.12
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/README.md +4 -0
- package/agent-assets/agents/morning-routine/agent.md +3 -4
- package/agent-assets/docs/concepts/backends-and-tiers.md +13 -10
- package/agent-assets/docs/features/messaging/dashboard-chat.md +1 -1
- package/agent-assets/docs/features/routines/morning-routine.md +1 -1
- package/agent-assets/docs/features/wiki/commands.md +1 -1
- package/agent-assets/docs/features/wiki/dashboard.md +1 -1
- package/agent-assets/docs/getting-started/01-what-is-this.md +1 -1
- package/agent-assets/docs/glossary.md +4 -3
- package/agent-assets/docs/guides/budget-and-cost-for-wiki.md +5 -3
- package/agent-assets/docs/guides/change-which-model-handles-x.md +1 -1
- package/agent-assets/docs/guides/multiple-wikis-for-multiple-domains.md +1 -1
- package/agent-assets/docs/guides/setup-wizard.md +1 -1
- package/agent-assets/docs/troubleshooting/wiki-ingest-full-blocked.md +1 -1
- package/agent-assets/playbooks/markdown-note.md +43 -0
- package/agent-assets/playbooks/monitoring.md +29 -0
- package/agent-assets/playbooks/research.md +47 -0
- package/agent-assets/skills/agent-create/SKILL.md +35 -30
- package/agent-assets/skills/agent-create/references/prompt-frame-extended.md +132 -0
- package/agent-assets/skills/agent-create/references/prompt-frame.md +125 -0
- package/agent-assets/skills/background-task/SKILL.md +4 -4
- package/agent-assets/skills/background-task-reply/SKILL.md +2 -2
- package/agent-assets/skills/board/SKILL.md +93 -0
- package/agent-assets/skills/browser-history/SKILL.md +3 -3
- package/agent-assets/skills/browser-history-respond/SKILL.md +3 -3
- package/agent-assets/skills/browser-task/SKILL.md +2 -2
- package/agent-assets/skills/schedule/SKILL.md +15 -13
- package/agent-assets/skills/schedule/references/batch.md +1 -1
- package/agent-assets/skills/schedule/references/model-selection.md +1 -1
- package/agent-assets/skills/schedule/references/prompt-frame.md +125 -0
- package/agent-assets/skills/task/SKILL.md +79 -0
- package/agent-assets/task-flows/scheduled.dm.md +21 -13
- package/package.json +4 -4
|
@@ -93,14 +93,18 @@ person at 9am than during the day."
|
|
|
93
93
|
|
|
94
94
|
## Sub-flow routing
|
|
95
95
|
|
|
96
|
-
The specific dm_session
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
96
|
+
The specific dm_session sub-flow is selected by the **structural**
|
|
97
|
+
`sub_flow` field inside `<task_context>` — a value the daemon sets and
|
|
98
|
+
the user never edits, so routing stays correct even after the task's
|
|
99
|
+
prompt/content is freely edited (e.g. through the `task` board facade).
|
|
100
|
+
Read `sub_flow` out of the JSON in the `<task_context>` block and match
|
|
101
|
+
it below. If `sub_flow` is absent (legacy rows predating the field),
|
|
102
|
+
fall back to `{event_data[task]}` prefix matching.
|
|
103
|
+
|
|
104
|
+
- `sub_flow` is `morning_briefing` (legacy fallback: task starts with `morning briefing`) → see `## Morning briefing` below
|
|
105
|
+
- `sub_flow` is `task_delivery` (legacy fallback: task starts with `task delivery:`) → see `## Task delivery` below
|
|
106
|
+
- `sub_flow` is `profile_interview` (legacy fallback: task starts with `profile_interview:`) → see `## Profile interview` below
|
|
107
|
+
- `sub_flow` is `confirm` (legacy fallback: task starts with `confirm:`) → see `## Confirmation follow-up` below
|
|
104
108
|
- (future sub-flows added here)
|
|
105
109
|
|
|
106
110
|
If no sub-flow matches:
|
|
@@ -122,7 +126,8 @@ user verbatim — defeating the skip.
|
|
|
122
126
|
|
|
123
127
|
## Task delivery
|
|
124
128
|
|
|
125
|
-
Triggered by `
|
|
129
|
+
Triggered by `sub_flow` = `task_delivery` in `<task_context>` (legacy
|
|
130
|
+
fallback: `{event_data[task]}` starts with `task delivery:`).
|
|
126
131
|
|
|
127
132
|
Your final assistant turn IS the DM that delivers a background task
|
|
128
133
|
artifact. The daemon has already decided that the owner is active in
|
|
@@ -171,7 +176,8 @@ Delivery rules:
|
|
|
171
176
|
|
|
172
177
|
## Morning briefing
|
|
173
178
|
|
|
174
|
-
Triggered by `
|
|
179
|
+
Triggered by `sub_flow` = `morning_briefing` in `<task_context>` (legacy
|
|
180
|
+
fallback: `{event_data[task]}` starts with `morning briefing`).
|
|
175
181
|
|
|
176
182
|
> Universal rules from the notify skill § Universal user-facing
|
|
177
183
|
> message discipline apply on top of the contract below — particularly
|
|
@@ -417,8 +423,9 @@ inside the closer line.
|
|
|
417
423
|
|
|
418
424
|
## Profile interview
|
|
419
425
|
|
|
420
|
-
Triggered by `
|
|
421
|
-
|
|
426
|
+
Triggered by `sub_flow` = `profile_interview` in `<task_context>` (legacy
|
|
427
|
+
routing fallback: `{event_data[task]}` starts with `profile_interview:<id>
|
|
428
|
+
— <ask-hint>`). This is the **fallback** path — the morning routine
|
|
422
429
|
normally just lays the row latent and waits for an opportunity in DM /
|
|
423
430
|
briefing. The evening sweep promotes a row to a scheduled DM only after
|
|
424
431
|
3 days of no opportunity AND the user has been actively DMing.
|
|
@@ -483,7 +490,8 @@ row open.
|
|
|
483
490
|
|
|
484
491
|
## Confirmation follow-up
|
|
485
492
|
|
|
486
|
-
Triggered by `
|
|
493
|
+
Triggered by `sub_flow` = `confirm` in `<task_context>` (legacy fallback:
|
|
494
|
+
`{event_data[task]}` starts with `confirm:`). The DM
|
|
487
495
|
handler scheduled this row because a gate (e.g. project-creation, a
|
|
488
496
|
managed-task duplicate, a long-horizon ambiguity) was triggered during
|
|
489
497
|
an earlier DM but could not be asked then — either the conversation
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@aitne-sh/aitne",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.12",
|
|
4
4
|
"description": "Aitne — a local-first, proactive personal AI agent. A long-running TypeScript daemon is the nervous system; Claude Code (or Codex / Gemini CLI) is the brain. All persistent memory lives in local Markdown files.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"ai",
|
|
@@ -43,9 +43,9 @@
|
|
|
43
43
|
"README.md"
|
|
44
44
|
],
|
|
45
45
|
"dependencies": {
|
|
46
|
-
"@aitne/daemon": "0.1.
|
|
47
|
-
"@aitne/dashboard": "0.1.
|
|
48
|
-
"@aitne/shared": "0.1.
|
|
46
|
+
"@aitne/daemon": "0.1.12",
|
|
47
|
+
"@aitne/dashboard": "0.1.12",
|
|
48
|
+
"@aitne/shared": "0.1.12"
|
|
49
49
|
},
|
|
50
50
|
"devDependencies": {
|
|
51
51
|
"@typescript-eslint/eslint-plugin": "^8.58.1",
|