@aitne-sh/aitne 0.1.12 → 0.1.13
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/agent-assets/agent-profiles/background-task.md +8 -1
- package/agent-assets/agent-profiles/routine-fetch-window.md +11 -0
- package/agent-assets/agents/evening-review/agent.md +6 -2
- package/agent-assets/agents/lesson-maintenance/agent.md +56 -0
- package/agent-assets/agents/morning-routine/agent.md +7 -2
- package/agent-assets/agents/source-librarian/agent.md +51 -0
- package/agent-assets/docs/concepts/agent-day.md +15 -15
- package/agent-assets/docs/concepts/auth-health.md +10 -7
- package/agent-assets/docs/concepts/backends-and-tiers.md +21 -13
- package/agent-assets/docs/concepts/costs-and-quotas.md +10 -10
- package/agent-assets/docs/concepts/delegated-mode.md +18 -18
- package/agent-assets/docs/concepts/memory-model.md +25 -24
- package/agent-assets/docs/concepts/observations.md +27 -19
- package/agent-assets/docs/concepts/process-keys.md +25 -26
- package/agent-assets/docs/concepts/routines.md +18 -17
- package/agent-assets/docs/concepts/safety-and-execution.md +20 -17
- package/agent-assets/docs/concepts/safety-model.md +16 -15
- package/agent-assets/docs/concepts/skills.md +7 -4
- package/agent-assets/docs/features/integrations/browser-history.md +52 -47
- package/agent-assets/docs/features/integrations/calendar.md +7 -7
- package/agent-assets/docs/features/integrations/git.md +15 -13
- package/agent-assets/docs/features/integrations/github.md +12 -10
- package/agent-assets/docs/features/integrations/mail.md +47 -45
- package/agent-assets/docs/features/integrations/notion.md +15 -11
- package/agent-assets/docs/features/integrations/obsidian.md +27 -23
- package/agent-assets/docs/features/lifestyle/git.md +7 -8
- package/agent-assets/docs/features/lifestyle/reading.md +11 -8
- package/agent-assets/docs/features/lifestyle/receipts.md +21 -22
- package/agent-assets/docs/features/lifestyle/travel-bookings.md +9 -9
- package/agent-assets/docs/features/memory-files/agent-journal.md +12 -10
- package/agent-assets/docs/features/memory-files/agent-lessons.md +46 -21
- package/agent-assets/docs/features/memory-files/projects.md +13 -14
- package/agent-assets/docs/features/memory-files/roadmap.md +16 -15
- package/agent-assets/docs/features/memory-files/schedule.md +10 -10
- package/agent-assets/docs/features/memory-files/today.md +18 -18
- package/agent-assets/docs/features/memory-files/user-profile.md +17 -17
- package/agent-assets/docs/features/messaging/bang-commands.md +15 -15
- package/agent-assets/docs/features/messaging/dashboard-chat.md +7 -6
- package/agent-assets/docs/features/messaging/discord.md +7 -5
- package/agent-assets/docs/features/messaging/overview.md +14 -14
- package/agent-assets/docs/features/messaging/pairing-and-magic-phrase.md +12 -12
- package/agent-assets/docs/features/messaging/slack.md +9 -8
- package/agent-assets/docs/features/messaging/telegram.md +7 -7
- package/agent-assets/docs/features/messaging/whatsapp.md +6 -6
- package/agent-assets/docs/features/operations/activity-and-conversations.md +9 -9
- package/agent-assets/docs/features/operations/approvals.md +13 -12
- package/agent-assets/docs/features/operations/backend-routing.md +38 -37
- package/agent-assets/docs/features/operations/browser-tasks.md +63 -57
- package/agent-assets/docs/features/operations/cost-tracking.md +5 -5
- package/agent-assets/docs/features/operations/managed-chromium.md +23 -22
- package/agent-assets/docs/features/operations/notifications.md +15 -15
- package/agent-assets/docs/features/operations/quiet-hours.md +14 -15
- package/agent-assets/docs/features/operations/schedule-approaching.md +16 -14
- package/agent-assets/docs/features/routines/activity-scan.md +14 -11
- package/agent-assets/docs/features/routines/custom-routines.md +9 -7
- package/agent-assets/docs/features/routines/evening-review.md +6 -7
- package/agent-assets/docs/features/routines/morning-routine.md +22 -21
- package/agent-assets/docs/features/routines/weekly-review.md +57 -51
- package/agent-assets/docs/features/wiki/commands.md +27 -21
- package/agent-assets/docs/features/wiki/cost-and-approval.md +28 -23
- package/agent-assets/docs/features/wiki/dashboard.md +21 -23
- package/agent-assets/docs/features/wiki/overview.md +17 -25
- package/agent-assets/docs/features/wiki/search.md +15 -17
- package/agent-assets/docs/features/wiki/workspaces.md +55 -56
- package/agent-assets/docs/getting-started/01-what-is-this.md +3 -4
- package/agent-assets/docs/getting-started/02-first-steps.md +12 -13
- package/agent-assets/docs/getting-started/03-what-can-this-do.md +7 -7
- package/agent-assets/docs/getting-started/04-first-day.md +4 -5
- package/agent-assets/docs/glossary.md +17 -16
- package/agent-assets/docs/guides/add-a-custom-routine.md +17 -12
- package/agent-assets/docs/guides/backup-and-restore.md +19 -16
- package/agent-assets/docs/guides/budget-and-cost-for-wiki.md +55 -62
- package/agent-assets/docs/guides/build-your-wiki.md +11 -12
- package/agent-assets/docs/guides/change-which-model-handles-x.md +30 -28
- package/agent-assets/docs/guides/connect-a-new-mail-account.md +30 -29
- package/agent-assets/docs/guides/explore-with-trace-and-connect.md +30 -32
- package/agent-assets/docs/guides/import-knowledge-file.md +9 -10
- package/agent-assets/docs/guides/install-and-run.md +9 -10
- package/agent-assets/docs/guides/maintain-wiki-health.md +10 -10
- package/agent-assets/docs/guides/migrate-machines.md +16 -14
- package/agent-assets/docs/guides/multiple-wikis-for-multiple-domains.md +11 -12
- package/agent-assets/docs/guides/pause-the-agent.md +25 -25
- package/agent-assets/docs/guides/reinstall-cleanly.md +13 -12
- package/agent-assets/docs/guides/setup-wizard.md +9 -11
- package/agent-assets/docs/guides/switch-default-backend.md +9 -9
- package/agent-assets/docs/guides/use-an-existing-obsidian-vault.md +9 -11
- package/agent-assets/docs/pages/activity.md +76 -0
- package/agent-assets/docs/pages/agents.md +78 -0
- package/agent-assets/docs/pages/analytics.md +70 -0
- package/agent-assets/docs/pages/browser.md +73 -0
- package/agent-assets/docs/pages/chat.md +67 -0
- package/agent-assets/docs/pages/connections.md +78 -0
- package/agent-assets/docs/pages/git.md +73 -0
- package/agent-assets/docs/pages/knowledge.md +75 -0
- package/agent-assets/docs/pages/overview.md +90 -0
- package/agent-assets/docs/pages/reading.md +65 -0
- package/agent-assets/docs/pages/settings.md +77 -0
- package/agent-assets/docs/pages/tasks.md +74 -0
- package/agent-assets/docs/pages/wiki.md +73 -0
- package/agent-assets/docs/reference/api.md +18 -17
- package/agent-assets/docs/reference/cli-commands.md +13 -10
- package/agent-assets/docs/reference/config.md +40 -35
- package/agent-assets/docs/reference/disallowed-tools.md +18 -17
- package/agent-assets/docs/reference/keyboard-shortcuts.md +6 -8
- package/agent-assets/docs/reference/knowledge-layout.md +10 -10
- package/agent-assets/docs/reference/process-keys.md +20 -22
- package/agent-assets/docs/reference/skills.md +18 -16
- package/agent-assets/docs/troubleshooting/auth-failed.md +13 -11
- package/agent-assets/docs/troubleshooting/dashboard-shows-degraded.md +10 -10
- package/agent-assets/docs/troubleshooting/fallback-keeps-firing.md +26 -24
- package/agent-assets/docs/troubleshooting/messaging-not-pairing.md +8 -9
- package/agent-assets/docs/troubleshooting/morning-routine-didnt-run.md +19 -18
- package/agent-assets/docs/troubleshooting/observation-not-detected.md +14 -15
- package/agent-assets/docs/troubleshooting/quota-exhausted.md +28 -26
- package/agent-assets/docs/troubleshooting/wiki-ingest-full-blocked.md +35 -34
- package/agent-assets/docs/troubleshooting/wiki-write-failed.md +21 -24
- package/agent-assets/skills/agent-create/SKILL.md +39 -5
- package/agent-assets/skills/background-task/SKILL.md +9 -4
- package/agent-assets/skills/board/SKILL.md +8 -9
- package/agent-assets/skills/browser-task/SKILL.md +2 -0
- package/agent-assets/skills/context/seeds/file-responsibilities.seed.json +2 -1
- package/agent-assets/skills/schedule/SKILL.md +6 -5
- package/agent-assets/skills/sources/SKILL.md +68 -0
- package/agent-assets/skills/sources/curation.json +21 -0
- package/agent-assets/skills/sources/seeds/filing-rules.seed.json +25 -0
- package/agent-assets/skills/sources/seeds/source-collections.seed.json +20 -0
- package/agent-assets/skills/task/SKILL.md +5 -2
- package/agent-assets/task-flows/background_task.md +29 -3
- package/agent-assets/task-flows/message.received.dm.md +1 -1
- package/agent-assets/task-flows/routine.activity_scan.md +17 -2
- package/agent-assets/task-flows/routine.evening_review.md +72 -11
- package/agent-assets/task-flows/routine.fetch_window.md +21 -0
- package/agent-assets/task-flows/routine.monthly_review.md +3 -1
- package/agent-assets/task-flows/routine.morning_routine_today.md +26 -7
- package/agent-assets/task-flows/routine.source_maintenance.md +50 -0
- package/agent-assets/task-flows/scheduled.dm.md +8 -3
- package/agent-assets/templates/_manifest.json +1 -0
- package/agent-assets/templates/knowledge/sources/_index.md +19 -0
- package/package.json +4 -4
|
@@ -19,7 +19,6 @@ tags:
|
|
|
19
19
|
- routines
|
|
20
20
|
- autonomous
|
|
21
21
|
- journal
|
|
22
|
-
- reflection
|
|
23
22
|
status: stable
|
|
24
23
|
ask_examples:
|
|
25
24
|
- When does the weekly review run?
|
|
@@ -27,7 +26,7 @@ ask_examples:
|
|
|
27
26
|
- Where do weekly retros get stored?
|
|
28
27
|
locale: en-US
|
|
29
28
|
created: 2026-04-25
|
|
30
|
-
updated: 2026-
|
|
29
|
+
updated: 2026-07-01
|
|
31
30
|
keywords:
|
|
32
31
|
- weekly review
|
|
33
32
|
- Friday review
|
|
@@ -58,49 +57,54 @@ context_files:
|
|
|
58
57
|
|
|
59
58
|
## In One Sentence
|
|
60
59
|
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
60
|
+
Every Friday evening, a medium-tier weekly retrospective (a look back
|
|
61
|
+
over the week) runs and writes a summary into
|
|
62
|
+
`journal/weekly/YYYY-Www.md` — one file per ISO week (the standard
|
|
63
|
+
Mon–Sun week numbering). Its **Carry Over / Next Week Focus /
|
|
64
|
+
Lessons** sections are then copied into every morning routine of the
|
|
65
|
+
following ISO week.
|
|
65
66
|
|
|
66
67
|
## What It Does
|
|
67
68
|
|
|
68
69
|
- Reads each `journal/daily/YYYY-MM-DD.md` for the current ISO week,
|
|
69
70
|
the week's calendar retrospective, the roadmap, and active projects.
|
|
70
|
-
-
|
|
71
|
-
Lessons — and writes the
|
|
72
|
-
-
|
|
71
|
+
- Pulls this together along three lines — Outcomes, Forward items,
|
|
72
|
+
and Behavioral Lessons — and writes the summary you read.
|
|
73
|
+
- Adds a private, agent-only block to `journal/agent.md` covering
|
|
73
74
|
self-critique, filter quality, and improvement ideas.
|
|
74
|
-
- Feeds the learning loop: for each concrete, actionable
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
|
|
78
|
-
|
|
79
|
-
-
|
|
80
|
-
pre-step
|
|
81
|
-
pre-pass freshness window because most fetches came back
|
|
82
|
-
|
|
83
|
-
apply / reject / defer verdict for each. While
|
|
84
|
-
`false` (the default) nothing
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
-
|
|
93
|
-
|
|
75
|
+
- Feeds the learning loop: for each concrete, actionable improvement
|
|
76
|
+
idea it finds, it also posts a `source=self_critique` feedback
|
|
77
|
+
signal (on top of the `journal/agent.md` note), so the idea gets
|
|
78
|
+
folded into the [agent lessons](../memory-files/agent-lessons.md)
|
|
79
|
+
instead of only living in the journal.
|
|
80
|
+
- Reviews the daemon's self-tuning suggestions: when the weekly
|
|
81
|
+
pre-step spots a cost setting worth changing (for example, widening
|
|
82
|
+
the mail pre-pass freshness window because most fetches came back
|
|
83
|
+
empty), it puts forward up to three bounded proposals, and the
|
|
84
|
+
review records an apply / reject / defer verdict for each. While
|
|
85
|
+
`selfTuningEnabled` is `false` (the default), nothing changes
|
|
86
|
+
automatically — the verdicts are only recorded for the owner to
|
|
87
|
+
review (this is called shadow mode). With the flag on, an apply
|
|
88
|
+
verdict takes effect immediately, kept inside hard per-key limits;
|
|
89
|
+
the owner gets a one-line DM for each applied change
|
|
90
|
+
(`!revert tuning` undoes the most recent one), and a daily monitor
|
|
91
|
+
automatically rolls back any change whose 7-day follow-up metrics
|
|
92
|
+
got worse.
|
|
93
|
+
- Sends a short Friday-evening notification by default. It stays quiet
|
|
94
|
+
(the silence gate) only when the week was essentially blank.
|
|
95
|
+
- Refreshes `identity/reading-taste.md` and your Book Candidates once
|
|
96
|
+
enough new highlights have piled up.
|
|
94
97
|
|
|
95
98
|
## When It Runs / How It Is Triggered
|
|
96
99
|
|
|
97
|
-
|
|
98
|
-
The schedule is fixed in
|
|
99
|
-
|
|
100
|
-
the **Fri / Sat / Sun
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
100
|
+
It runs every **Friday at 19:00 local time**, one hour after
|
|
101
|
+
`evening_review`. The schedule is fixed in
|
|
102
|
+
`packages/daemon/src/core/scheduler.ts` and can't be changed. If the
|
|
103
|
+
Friday run is missed (say, the daemon was down), the **Fri / Sat / Sun
|
|
104
|
+
catch-up window** in `schedule-helpers.ts` runs the retro as soon as
|
|
105
|
+
the daemon recovers, before the new ISO week begins. A Mon–Thu
|
|
106
|
+
catch-up is left out on purpose, so the next week's `<previous_week>`
|
|
107
|
+
injection stays a stable Mon–Sun.
|
|
104
108
|
|
|
105
109
|
## What It Outputs
|
|
106
110
|
|
|
@@ -111,25 +115,27 @@ a Mon–Thu catch-up is intentionally out of scope so the next week's
|
|
|
111
115
|
|
|
112
116
|
## Configuration
|
|
113
117
|
|
|
114
|
-
The
|
|
115
|
-
and
|
|
116
|
-
|
|
117
|
-
|
|
118
|
-
|
|
118
|
+
The run time (Friday 19:00 local) and the day of the week are fixed in
|
|
119
|
+
code and can't be changed. What you *can* change is the backend and
|
|
120
|
+
model behind this routine: `routine.weekly_review` is a configurable
|
|
121
|
+
process key (default **medium** tier — Sonnet on Claude) that you can
|
|
122
|
+
repoint from **Settings → Models**. The weekly rulebook
|
|
119
123
|
(`policies/routines/weekly.md`) is edited on the weekly-review agent's
|
|
120
|
-
Rulebook tab (`/agents/weekly-review?tab=rulebook`), where
|
|
121
|
-
|
|
124
|
+
Rulebook tab (`/agents/weekly-review?tab=rulebook`), where you can also
|
|
125
|
+
enable or disable the agent.
|
|
122
126
|
|
|
123
127
|
## When Something Goes Wrong
|
|
124
128
|
|
|
125
|
-
- The retro **doesn't
|
|
126
|
-
retries on Saturday and Sunday agent-days
|
|
127
|
-
|
|
128
|
-
|
|
129
|
-
|
|
130
|
-
|
|
131
|
-
|
|
132
|
-
|
|
129
|
+
- The retro **doesn't run on Friday**: the Fri–Sun catch-up window
|
|
130
|
+
retries on the Saturday and Sunday agent-days (the agent's own day,
|
|
131
|
+
which rolls over at `dayBoundaryHour` rather than at midnight). If
|
|
132
|
+
the daemon is down for the whole Fri–Sun window, the weekly file is
|
|
133
|
+
never written, and the next week's morning routines simply carry on
|
|
134
|
+
without the `<previous_week>` block.
|
|
135
|
+
- The retro **runs but the file is empty** (the silence gate): this is
|
|
136
|
+
fine for a genuinely blank week — the file is still written, just
|
|
137
|
+
with empty sections, and the next week's morning routine sees
|
|
138
|
+
`(none recorded)` sub-blocks. That is the intended signal, not a bug.
|
|
133
139
|
|
|
134
140
|
## Related
|
|
135
141
|
|
|
@@ -21,8 +21,6 @@ summary: |
|
|
|
21
21
|
section: wiki
|
|
22
22
|
tags:
|
|
23
23
|
- wiki
|
|
24
|
-
- bang-commands
|
|
25
|
-
- core
|
|
26
24
|
status: stable
|
|
27
25
|
ask_examples:
|
|
28
26
|
- How do I send a URL to the wiki?
|
|
@@ -34,7 +32,7 @@ ask_examples:
|
|
|
34
32
|
- How do I bridge two domains with `!connect`?
|
|
35
33
|
locale: en-US
|
|
36
34
|
created: 2026-05-12
|
|
37
|
-
updated: 2026-
|
|
35
|
+
updated: 2026-07-01
|
|
38
36
|
keywords:
|
|
39
37
|
- !ingest
|
|
40
38
|
- !compile
|
|
@@ -48,6 +46,7 @@ keywords:
|
|
|
48
46
|
related:
|
|
49
47
|
- features/wiki/overview
|
|
50
48
|
- features/messaging/bang-commands
|
|
49
|
+
- features/wiki/cost-and-approval
|
|
51
50
|
- guides/budget-and-cost-for-wiki
|
|
52
51
|
- guides/maintain-wiki-health
|
|
53
52
|
- guides/explore-with-trace-and-connect
|
|
@@ -67,9 +66,10 @@ ui_anchors:
|
|
|
67
66
|
|
|
68
67
|
# Wiki Commands
|
|
69
68
|
|
|
70
|
-
|
|
69
|
+
These are bang commands — chat messages that start with `!`. Send
|
|
70
|
+
them from a paired DM channel once the wiki is turned on. Open
|
|
71
71
|
**Settings → Wiki** (`/settings/wiki`) to enable a workspace, then
|
|
72
|
-
|
|
72
|
+
read the results under **My Life → Wiki** (`/wiki`).
|
|
73
73
|
|
|
74
74
|
| Command | Effect |
|
|
75
75
|
|---|---|
|
|
@@ -91,17 +91,17 @@ batch at 10 URLs.
|
|
|
91
91
|
## `@<workspace>` — addressing a non-default workspace
|
|
92
92
|
|
|
93
93
|
If you run more than one wiki workspace (Phase 5), every bang command
|
|
94
|
-
accepts an optional `@<name>` token
|
|
95
|
-
token
|
|
96
|
-
|
|
97
|
-
|
|
94
|
+
accepts an optional `@<name>` token right after the bang. Aitne reads
|
|
95
|
+
this token first and removes it before the command parses the rest of
|
|
96
|
+
your message, so multi-word topics and comma-separated arguments still
|
|
97
|
+
work as usual:
|
|
98
98
|
|
|
99
99
|
!compile @research full
|
|
100
100
|
!ask @parenting what did the pediatrician recommend?
|
|
101
101
|
!connect @research diffusion models, score matching
|
|
102
102
|
|
|
103
103
|
Omit the token and the command targets the **default** workspace.
|
|
104
|
-
See
|
|
104
|
+
See [guides/multiple-wikis-for-multiple-domains](../../guides/multiple-wikis-for-multiple-domains.md)
|
|
105
105
|
for a walkthrough.
|
|
106
106
|
|
|
107
107
|
## `!compile --preview` — the dry run
|
|
@@ -119,14 +119,15 @@ Use `!compile --preview` (or `--dry-run`) when you want to see what
|
|
|
119
119
|
- **est. duration** — Rough wall-clock estimate (intentionally
|
|
120
120
|
pessimistic).
|
|
121
121
|
|
|
122
|
-
|
|
123
|
-
merge or skip pages
|
|
124
|
-
predict
|
|
125
|
-
Reply `!compile` (or `!compile full`) to
|
|
122
|
+
Treat the preview as an upper bound. The real compile runs an LLM,
|
|
123
|
+
which may merge or skip pages as it works, so the preview cannot
|
|
124
|
+
predict the outcome exactly — but it will never undercount the pages
|
|
125
|
+
it touches. Reply `!compile` (or `!compile full`) to run the compile
|
|
126
|
+
for real.
|
|
126
127
|
|
|
127
128
|
## Dispatch Mode for `!ingest`
|
|
128
129
|
|
|
129
|
-
`!ingest`
|
|
130
|
+
`!ingest` follows the per-workspace **dispatch mode** set in
|
|
130
131
|
Settings → Wiki:
|
|
131
132
|
|
|
132
133
|
- **Parallel** (default): all URLs fan out simultaneously up to the
|
|
@@ -142,8 +143,8 @@ The acknowledgement DM names the mode that ran (`in parallel` /
|
|
|
142
143
|
|
|
143
144
|
## `!compile full` — the Cost Gate
|
|
144
145
|
|
|
145
|
-
Full rebuilds touch every wiki note
|
|
146
|
-
command in the wiki surface.
|
|
146
|
+
Full rebuilds touch every wiki note, so they are the most expensive
|
|
147
|
+
command in the wiki surface. Here is what happens when you run one:
|
|
147
148
|
|
|
148
149
|
1. The bang handler estimates the cost (per raw note, an on-disk
|
|
149
150
|
char→token approximation × Sonnet 5 input price, bracketed
|
|
@@ -160,15 +161,20 @@ command in the wiki surface. The flow:
|
|
|
160
161
|
4. Otherwise, the run starts autonomously and you receive a
|
|
161
162
|
completion DM with actual spend.
|
|
162
163
|
|
|
163
|
-
The same estimate is shown live in **Settings → Wiki
|
|
164
|
-
see what the next `!compile full` will cost before you run it.
|
|
164
|
+
The same estimate is shown live in **Settings → Wiki**, so you can
|
|
165
|
+
see what the next `!compile full` will cost before you run it. See
|
|
166
|
+
[features/wiki/cost-and-approval](cost-and-approval.md) for the full
|
|
167
|
+
cost-estimation and approval reference.
|
|
165
168
|
|
|
166
169
|
## Operational Triad — `!lint`, `!trace`, `!connect`
|
|
167
170
|
|
|
168
171
|
These three commands round out the wiki surface for ongoing
|
|
169
172
|
maintenance and exploration. None of them write to the content
|
|
170
173
|
layers (`10_raw/`, `20_wiki/`); they only produce health reports
|
|
171
|
-
(`90_meta/health/`) or output documents (`30_outputs/`).
|
|
174
|
+
(`90_meta/health/`) or output documents (`30_outputs/`). This
|
|
175
|
+
section is the command reference; for the step-by-step workflows,
|
|
176
|
+
see [guides/maintain-wiki-health](../../guides/maintain-wiki-health.md)
|
|
177
|
+
and [guides/explore-with-trace-and-connect](../../guides/explore-with-trace-and-connect.md).
|
|
172
178
|
|
|
173
179
|
### `!lint`
|
|
174
180
|
|
|
@@ -197,7 +203,7 @@ Timeline & health** (`/wiki/timeline`).
|
|
|
197
203
|
### `!trace <topic>`
|
|
198
204
|
|
|
199
205
|
Reconstructs the chronological evolution of an idea across every
|
|
200
|
-
wiki layer. Use a free-form topic — the skill
|
|
206
|
+
wiki layer. Use a free-form topic — the skill matches it against
|
|
201
207
|
`90_meta/taxonomy.md` before deriving the output slug:
|
|
202
208
|
|
|
203
209
|
```
|
|
@@ -25,7 +25,6 @@ tags:
|
|
|
25
25
|
- cost
|
|
26
26
|
- approval
|
|
27
27
|
- safety
|
|
28
|
-
- core
|
|
29
28
|
status: stable
|
|
30
29
|
ask_examples:
|
|
31
30
|
- How does !compile full estimate cost?
|
|
@@ -39,7 +38,7 @@ ask_examples:
|
|
|
39
38
|
- Can I see the cost before running !compile full?
|
|
40
39
|
locale: en-US
|
|
41
40
|
created: 2026-05-21
|
|
42
|
-
updated: 2026-
|
|
41
|
+
updated: 2026-07-01
|
|
43
42
|
keywords:
|
|
44
43
|
- cost estimate
|
|
45
44
|
- cost bracket
|
|
@@ -106,26 +105,30 @@ The same estimator backs four surfaces so the numbers cannot drift:
|
|
|
106
105
|
|
|
107
106
|
## How the estimator works
|
|
108
107
|
|
|
109
|
-
|
|
110
|
-
|
|
111
|
-
|
|
112
|
-
|
|
113
|
-
|
|
108
|
+
The estimate is plain JavaScript math — it never starts an agent or
|
|
109
|
+
calls the model, so it costs nothing and returns instantly. The
|
|
110
|
+
estimator (`packages/daemon/src/core/wiki/cost-estimate.ts`) opens
|
|
111
|
+
each raw note under `10_raw/`, approximates its token count from the
|
|
112
|
+
text on disk, then multiplies the total by the tier unit cost and
|
|
113
|
+
wraps it in a 0.5×/2× bracket (a low/high range).
|
|
114
114
|
|
|
115
115
|
### Character → token approximation
|
|
116
116
|
|
|
117
|
-
- **Latin / English content** —
|
|
118
|
-
OpenAI rule-of-thumb; matches Anthropic's
|
|
119
|
-
for prose
|
|
120
|
-
-
|
|
121
|
-
|
|
122
|
-
|
|
123
|
-
|
|
124
|
-
|
|
125
|
-
|
|
126
|
-
|
|
127
|
-
|
|
128
|
-
|
|
117
|
+
- **Latin / English content** — about 4 characters per token. This
|
|
118
|
+
is the well-known OpenAI rule-of-thumb; it matches Anthropic's
|
|
119
|
+
tokenizer within ±15% for prose, confirmed against the
|
|
120
|
+
gpt-tokenizer package.
|
|
121
|
+
- **CJK content** (Chinese, Japanese, Korean) — about 1.5 characters
|
|
122
|
+
per token. The tokenizer merges short CJK runs, but not as
|
|
123
|
+
aggressively as it merges Latin word fragments, so each character
|
|
124
|
+
carries more weight.
|
|
125
|
+
|
|
126
|
+
To pick a ratio, the classifier counts the Unicode code points whose
|
|
127
|
+
script is one of Han, Hiragana, Katakana, Hangul, or Bopomofo. If a
|
|
128
|
+
file is majority-CJK, the CJK ratio applies to the whole file;
|
|
129
|
+
otherwise the Latin ratio does. Splitting each file script-by-script
|
|
130
|
+
would be slightly more accurate, but it adds 30% more code for a
|
|
131
|
+
sub-percent gain on typical mixed-script files, so we don't.
|
|
129
132
|
|
|
130
133
|
### The 0.5×/2× bracket
|
|
131
134
|
|
|
@@ -188,7 +191,8 @@ estimate landed to the actual cost.
|
|
|
188
191
|
|
|
189
192
|
## The pre-compile git snapshot
|
|
190
193
|
|
|
191
|
-
|
|
194
|
+
This only matters for an **external + git-tracked** vault — a vault
|
|
195
|
+
stored outside Aitne whose folder is a git repository. The gate
|
|
192
196
|
decides:
|
|
193
197
|
|
|
194
198
|
| Workspace state | Outcome |
|
|
@@ -202,9 +206,10 @@ decides:
|
|
|
202
206
|
The snapshot is your rollback target if `!compile full` produces a
|
|
203
207
|
surprise — `git reset --hard <snapshot-commit>` puts the vault back.
|
|
204
208
|
|
|
205
|
-
The pre-compile commit uses no special author identity
|
|
206
|
-
under whatever git is configured to use.
|
|
207
|
-
|
|
209
|
+
The pre-compile commit uses no special author identity — it lands
|
|
210
|
+
under whatever name and email your git is already configured to use.
|
|
211
|
+
If you want to credit Aitne as a co-author, set that up in your git
|
|
212
|
+
config.
|
|
208
213
|
|
|
209
214
|
## The `--preview` dry-run
|
|
210
215
|
|
|
@@ -23,8 +23,6 @@ section: wiki
|
|
|
23
23
|
tags:
|
|
24
24
|
- wiki
|
|
25
25
|
- dashboard
|
|
26
|
-
- reference
|
|
27
|
-
- core
|
|
28
26
|
status: stable
|
|
29
27
|
ask_examples:
|
|
30
28
|
- What does the /wiki page show?
|
|
@@ -37,7 +35,7 @@ ask_examples:
|
|
|
37
35
|
- What does the Enable Wiki button do?
|
|
38
36
|
locale: en-US
|
|
39
37
|
created: 2026-05-21
|
|
40
|
-
updated: 2026-
|
|
38
|
+
updated: 2026-07-01
|
|
41
39
|
keywords:
|
|
42
40
|
- /wiki
|
|
43
41
|
- /wiki/timeline
|
|
@@ -82,12 +80,12 @@ process_keys:
|
|
|
82
80
|
|
|
83
81
|
# Wiki Dashboard Surfaces
|
|
84
82
|
|
|
85
|
-
The wiki has three
|
|
86
|
-
Aitne
|
|
87
|
-
configuration lives under **Setup → Settings**.
|
|
88
|
-
|
|
83
|
+
The wiki has three separate pages in the dashboard. The split mirrors
|
|
84
|
+
how the rest of Aitne is organized: content you browse lives under
|
|
85
|
+
**My Life**, and configuration lives under **Setup → Settings**. All
|
|
86
|
+
three pages read through the same daemon routes (`/api/wiki/*`). Every
|
|
89
87
|
request carries an `x-process-key: wiki.ask` header so the safety
|
|
90
|
-
layer can
|
|
88
|
+
layer can record who is reading what.
|
|
91
89
|
|
|
92
90
|
## `/wiki` — workspace home
|
|
93
91
|
|
|
@@ -112,13 +110,13 @@ Two action buttons at the bottom of the card: **Timeline & health**
|
|
|
112
110
|
|
|
113
111
|
### 2. Index
|
|
114
112
|
|
|
115
|
-
Renders the latest `20_wiki/_index.md`, the
|
|
116
|
-
|
|
117
|
-
`!compile` run.
|
|
113
|
+
Renders the latest `20_wiki/_index.md`, the running catalogue of wiki
|
|
114
|
+
pages that the agent keeps up to date. The agent rewrites this file at
|
|
115
|
+
the end of every `!compile` run.
|
|
118
116
|
|
|
119
117
|
States:
|
|
120
|
-
- **Empty** — no `_index.md` yet; the
|
|
121
|
-
from a DM.
|
|
118
|
+
- **Empty** — no `_index.md` yet; the card's call-to-action button
|
|
119
|
+
tells you to run `!compile` from a DM.
|
|
122
120
|
- **Loaded** — the file is rendered verbatim as a monospaced code
|
|
123
121
|
block (the index uses wikilink syntax, so rendering as markdown
|
|
124
122
|
would lose information).
|
|
@@ -139,10 +137,10 @@ error toast.
|
|
|
139
137
|
### Disabled state
|
|
140
138
|
|
|
141
139
|
When no `active=1` workspace exists in `wiki_workspaces`, the page
|
|
142
|
-
shows an **Enable Wiki**
|
|
143
|
-
sidebar entry is always visible (
|
|
144
|
-
|
|
145
|
-
the sidebar, a
|
|
140
|
+
shows an **Enable Wiki** button that jumps to `/settings/wiki`. The
|
|
141
|
+
sidebar entry is always visible (it shows as long as the workspace
|
|
142
|
+
list can be loaded), so you can still land on this disabled page from
|
|
143
|
+
the sidebar, a shared link, or browser history.
|
|
146
144
|
|
|
147
145
|
## `/wiki/timeline` — full chronological history + health
|
|
148
146
|
|
|
@@ -172,9 +170,9 @@ log plus an **All commands** default. Entries render the same way
|
|
|
172
170
|
they do in the `/wiki` recent-activity card — process-key badge,
|
|
173
171
|
operation, path, timestamp.
|
|
174
172
|
|
|
175
|
-
Both surfaces read live from the wiki API
|
|
176
|
-
|
|
177
|
-
|
|
173
|
+
Both surfaces read live from the wiki API. The timeline page simply
|
|
174
|
+
displays files the wiki skills already write to disk — there is no
|
|
175
|
+
separate database table behind it.
|
|
178
176
|
|
|
179
177
|
## `/settings/wiki` — configuration
|
|
180
178
|
|
|
@@ -186,9 +184,9 @@ A two-card chooser:
|
|
|
186
184
|
|
|
187
185
|
- **Internal** (recommended) — managed by Aitne inside the context
|
|
188
186
|
vault (default `<contextDir>/knowledge/wiki`, i.e.
|
|
189
|
-
`~/.personal-agent/context/knowledge/wiki`),
|
|
190
|
-
|
|
191
|
-
nothing else to configure.
|
|
187
|
+
`~/.personal-agent/context/knowledge/wiki`), with the folder
|
|
188
|
+
structure set up for you. The **Enable internal wiki** button turns
|
|
189
|
+
it on with nothing else to configure.
|
|
192
190
|
- **Existing Obsidian vault** (external) — point Aitne at a folder you
|
|
193
191
|
already own via the path picker, then confirm with **Use this
|
|
194
192
|
folder**.
|
|
@@ -17,7 +17,6 @@ section: wiki
|
|
|
17
17
|
tags:
|
|
18
18
|
- wiki
|
|
19
19
|
- knowledge
|
|
20
|
-
- core
|
|
21
20
|
status: stable
|
|
22
21
|
ask_examples:
|
|
23
22
|
- What is the wiki?
|
|
@@ -26,7 +25,7 @@ ask_examples:
|
|
|
26
25
|
- Can I point the wiki at my Obsidian vault?
|
|
27
26
|
locale: en-US
|
|
28
27
|
created: 2026-05-12
|
|
29
|
-
updated: 2026-
|
|
28
|
+
updated: 2026-07-01
|
|
30
29
|
keywords:
|
|
31
30
|
- wiki
|
|
32
31
|
- wiki workspace
|
|
@@ -88,10 +87,10 @@ and questions you ask it.
|
|
|
88
87
|
The three commands you reach for daily:
|
|
89
88
|
|
|
90
89
|
- **URL ingest**: send `!ingest <url>` from a paired DM channel; the wiki
|
|
91
|
-
agent fetches the source,
|
|
90
|
+
agent fetches the source, summarizes it, and stores a raw note.
|
|
92
91
|
- **Compile**: `!compile` (incremental) and `!compile full` (full
|
|
93
|
-
rebuild) turn raw notes into
|
|
94
|
-
cross-links and an `_index.md`
|
|
92
|
+
rebuild) turn raw notes into synthesized wiki articles with
|
|
93
|
+
cross-links and an `_index.md` catalog.
|
|
95
94
|
- **Ask**: `!ask <question>` searches the wiki and writes a cited
|
|
96
95
|
answer under `30_outputs/`.
|
|
97
96
|
|
|
@@ -110,8 +109,9 @@ competes for budget with daily reactive memory.
|
|
|
110
109
|
Aitne offers two modes:
|
|
111
110
|
|
|
112
111
|
- **Internal** (recommended starting point) — the daemon owns the
|
|
113
|
-
vault at `$PA_DATA_DIR/context/knowledge/wiki`. No sandbox
|
|
114
|
-
|
|
112
|
+
vault at `$PA_DATA_DIR/context/knowledge/wiki`. No sandbox
|
|
113
|
+
permission issues, snapshots are managed for you, and it stays clear
|
|
114
|
+
of iCloud sync conflicts.
|
|
115
115
|
- **External** — you point the wiki at an existing Obsidian vault on
|
|
116
116
|
disk. The daemon writes directly when the filesystem allows, and
|
|
117
117
|
falls back to the official Obsidian CLI when the vault sits in a
|
|
@@ -126,7 +126,7 @@ workspaces may not nest.
|
|
|
126
126
|
- `00_inbox/` — human-only capture (the agent has read access but
|
|
127
127
|
cannot write here).
|
|
128
128
|
- `10_raw/` — source-faithful raw notes (append-only).
|
|
129
|
-
- `20_wiki/` —
|
|
129
|
+
- `20_wiki/` — synthesized wiki articles + `_index.md` catalog.
|
|
130
130
|
- `30_outputs/` — answer / report artifacts written by `!ask`.
|
|
131
131
|
- `90_meta/` — taxonomy, schemas, lint reports, and the
|
|
132
132
|
`import-<date>.md` migration record.
|
|
@@ -138,31 +138,23 @@ process keys can write wiki layers.
|
|
|
138
138
|
## Cost Safety
|
|
139
139
|
|
|
140
140
|
`!compile full` rebuilds the entire wiki from raw notes and is the
|
|
141
|
-
most expensive command
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
surfaces on the dashboard home page (`/`), where you Approve or Deny
|
|
148
|
-
it.
|
|
149
|
-
|
|
150
|
-
On a git-tracked external vault, Aitne also runs
|
|
151
|
-
`git add -A && git commit -m "aitne wiki: pre-compile snapshot <ts>"`
|
|
152
|
-
on a clean working tree before the compile so you can roll back if
|
|
153
|
-
the run produces a surprise. A dirty tree refuses the operation —
|
|
154
|
-
commit or stash first.
|
|
141
|
+
most expensive command, so Aitne guards it: the dashboard shows a cost
|
|
142
|
+
estimate before you run it, a large run needs your approval (the
|
|
143
|
+
per-workspace threshold defaults to $2.00), and a git-tracked external
|
|
144
|
+
vault gets a snapshot commit first so you can roll back a surprising
|
|
145
|
+
run. See [Cost estimation and approval](cost-and-approval.md) for the
|
|
146
|
+
exact estimate math, the approval flow, and the pre-compile snapshot.
|
|
155
147
|
|
|
156
148
|
## Where it lives in the dashboard
|
|
157
149
|
|
|
158
150
|
The wiki has two distinct surfaces in the dashboard. The split mirrors
|
|
159
|
-
how Aitne
|
|
151
|
+
how Aitne organizes the rest of the app — configuration lives under
|
|
160
152
|
**Setup → Settings**, day-to-day content browsing lives under **My
|
|
161
153
|
Life** next to Knowledge / Reading / Git.
|
|
162
154
|
|
|
163
155
|
| Page | Section | Use it for |
|
|
164
156
|
|---|---|---|
|
|
165
|
-
| `/wiki` | My Life | Workspace summary, the compiled `_index.md`
|
|
157
|
+
| `/wiki` | My Life | Workspace summary, the compiled `_index.md` catalog, and the latest activity log. The page you open most often. |
|
|
166
158
|
| `/wiki/timeline` | My Life | Full chronological activity log plus the latest `!lint` health report. Linked from `/wiki` and from settings. |
|
|
167
159
|
| `/settings/wiki` | Setup → Settings | Enable / archive a workspace, switch between internal and external mode, pick an external vault path, language, dispatch mode, write strategy, git auto-commit, approval threshold, per-command model selectors. |
|
|
168
160
|
|
|
@@ -196,7 +188,7 @@ This page is a high-level tour. For depth on a specific surface:
|
|
|
196
188
|
- **[Commands reference](commands.md)** — every wiki bang command
|
|
197
189
|
(`!ingest`, `!compile`, `!ask`, `!lint`, `!trace`, `!connect`,
|
|
198
190
|
`!wiki`), the `@<workspace>` addressing token, dispatch modes, and
|
|
199
|
-
the disabled-state
|
|
191
|
+
the disabled-state behavior.
|
|
200
192
|
- **[Dashboard surfaces](dashboard.md)** — what `/wiki`,
|
|
201
193
|
`/wiki/timeline`, and `/settings/wiki` actually render, where each
|
|
202
194
|
card reads from on disk, and how the contextual help button maps
|