@aitne-sh/aitne 0.1.6 → 0.1.8

package/agent-assets/docs/features/messaging/slack.md

@@ -3,6 +3,11 @@ schema_version: 1
 slug: features/messaging/slack
 title: Slack
 id: slack
+aliases:
+  - slack bot
+  - slack adapter
+  - slack pairing
+  - slack DM
 category: features
 summary: |
   Pair a Slack workspace by installing a bot user, pasting tokens
@@ -10,7 +15,8 @@ summary: |
 section: messaging
 tags:
   - messaging
-  - integration
+  - integrations
+  - slack
 status: stable
 ask_examples:
   - How do I pair Slack?
@@ -18,6 +24,12 @@ ask_examples:
 locale: en-US
 created: 2026-04-25
 updated: 2026-04-25
+keywords:
+  - slack
+  - OAuth
+  - bot token
+  - owner channel
+  - messaging adapter
 related:
   - features/messaging/overview
   - features/messaging/pairing-and-magic-phrase

package/agent-assets/docs/features/messaging/telegram.md

@@ -12,7 +12,7 @@ summary: |
 section: messaging
 tags:
   - messaging
-  - integration
+  - integrations
   - core
 status: stable
 ask_examples:
@@ -21,6 +21,12 @@ ask_examples:
 locale: en-US
 created: 2026-04-25
 updated: 2026-04-25
+keywords:
+  - telegram
+  - telegram bot
+  - bot token
+  - telegram pairing
+  - messaging adapter
 related:
   - features/messaging/pairing-and-magic-phrase
   - features/messaging/overview

package/agent-assets/docs/features/messaging/whatsapp.md

@@ -3,6 +3,10 @@ schema_version: 1
 slug: features/messaging/whatsapp
 title: WhatsApp
 id: whatsapp
+aliases:
+  - whatsapp bot
+  - whatsapp adapter
+  - whatsapp pairing
 category: features
 summary: |
   Pair WhatsApp via the Cloud API or a bridge service. Once paired, DMs
@@ -10,7 +14,8 @@ summary: |
 section: messaging
 tags:
   - messaging
-  - integration
+  - integrations
+  - whatsapp
 status: stable
 ask_examples:
   - Can I use WhatsApp with Aitne?
@@ -18,6 +23,12 @@ ask_examples:
 locale: en-US
 created: 2026-04-25
 updated: 2026-04-25
+keywords:
+  - whatsapp
+  - twilio
+  - bot token
+  - owner channel
+  - messaging adapter
 related:
   - features/messaging/overview
 ---

package/agent-assets/docs/features/operations/activity-and-conversations.md

@@ -54,7 +54,7 @@ detail lives one click deeper under Conversations.
 
 Activity is the unified view of:
 
-- **Routines**: morning, evening, weekly, monthly, hourly fires.
+- **Routines**: morning, evening, weekly, hourly fires.
 - **Reactive sessions**: DMs, dashboard chat, mentions.
 - **Background actions**: notifications sent, mail labeled, schedule
   files written.
@@ -86,7 +86,7 @@ written to as a side-effect of every other event in the system
 There is nothing to configure on the Activity view itself; what shows
 up is a function of which routines are enabled and which integrations
 are connected. Retention is unlimited locally — the SQLite database
-keeps everything until you `pa stop && rm ~/.personal-agent/data/personal_agent.db`.
+keeps everything until you `aitne stop && rm ~/.personal-agent/data/personal_agent.db*` (the `*` also clears the `-shm`/`-wal` companions).
 
 ## When Something Goes Wrong
 

package/agent-assets/docs/features/operations/approvals.md

@@ -23,6 +23,12 @@ ask_examples:
 locale: en-US
 created: 2026-04-25
 updated: 2026-04-25
+keywords:
+  - approval
+  - approve tier
+  - /dashboard/approvals
+  - agent approval queue
+  - approve before action
 related:
   - concepts/safety-and-execution
   - features/operations/notifications

package/agent-assets/docs/features/operations/backend-routing.md

@@ -25,6 +25,13 @@ ask_examples:
 locale: en-US
 created: 2026-04-25
 updated: 2026-04-25
+keywords:
+  - backend routing
+  - BackendRouter
+  - fallback
+  - main fallback
+  - BackendQuotaError
+  - BackendDecisiveFailure
 related:
   - concepts/backends-and-tiers
   - features/operations/cost-tracking

package/agent-assets/docs/features/operations/cost-tracking.md

@@ -23,6 +23,12 @@ ask_examples:
 locale: en-US
 created: 2026-04-25
 updated: 2026-04-25
+keywords:
+  - cost tracking
+  - analytics
+  - spend
+  - per-process cost
+  - rollup
 related:
   - concepts/costs-and-quotas
 config_keys:

package/agent-assets/docs/features/operations/notifications.md

@@ -24,6 +24,12 @@ ask_examples:
 locale: en-US
 created: 2026-04-25
 updated: 2026-04-25
+keywords:
+  - notification
+  - notify
+  - quiet hours
+  - rate limit
+  - notification batch
 related:
   - features/operations/quiet-hours
   - features/operations/approvals

package/agent-assets/docs/features/operations/schedule-approaching.md

@@ -9,7 +9,8 @@ aliases:
 category: features
 summary: |
   Lightweight pre-event nudges fire when a calendar event is close
-  enough to remind the operator about. The lead time is configurable.
+  enough to remind the operator about. The 15-minute lead time is
+  fixed in code today.
 section: operations
 tags:
   - operations
@@ -18,10 +19,15 @@ tags:
 status: stable
 ask_examples:
   - How does the agent remind me about meetings?
-  - Can I change the lead time?
+  - What is the pre-event reminder lead time?
 locale: en-US
 created: 2026-04-25
 updated: 2026-04-25
+keywords:
+  - schedule approaching
+  - pre-event reminder
+  - departure time
+  - ETA reminder
 related:
   - features/integrations/calendar
   - features/operations/notifications
@@ -31,29 +37,36 @@ related:
 
 ## In One Sentence
 
-Pre-event reminders fire on a configurable lead time before each
-calendar event.
+Pre-event reminders fire 15 minutes before each calendar event.
 
 ## What It Does
 
 - Watches the calendar event queue.
-- Fires a notification N minutes before each event.
+- Fires a notification ~15 minutes before each event (fixed in
+  `imminent-event-scheduler.ts`; not currently a config key).
 - Optionally includes the travel-time estimate when the event has
   a location and the travel-time skill is enabled.
+- Deduplicates via the `imminent_event_notifications` table so the
+  same event never fires twice across reschedules / poll cycles.
 
 ## When It Runs / How It Is Triggered
 
-The scheduler keeps a sorted view of upcoming events; a tick at the
-event's lead-time mark fires the notification.
+The scheduler keeps a sorted view of upcoming events from the
+`integration_snapshots` table and emits one `schedule.approaching`
+event per item via the EventBus when the event is ≤ 15 minutes away.
 
 ## Where in the Dashboard
 
-- **Settings → Schedule** holds the lead-time options.
+- Reminders surface on the connected messaging app and in the
+  Activity feed. There is no dashboard setting for lead time today.
 
 ## When Something Goes Wrong
 
 - A reminder you expected: confirm the calendar integration is
-  reading the right calendar (some operators have multiple).
+  reading the right calendar (some operators have multiple), and
+  that the calendar is running in `direct` mode — in `delegated` /
+  `native` / `disabled` modes the daemon does not emit approaching
+  reminders.
 
 ## Related
 

package/agent-assets/docs/features/routines/custom-routines.md

@@ -9,12 +9,12 @@ aliases:
   - user routine
 category: features
 summary: |
-  Beyond the built-in morning / evening / weekly / monthly / hourly
-  routines, the operator can define custom routines that fire on any
-  cron schedule.
+  Beyond the built-in morning / evening / weekly / hourly routines,
+  the operator can define custom routines that fire on any cron
+  schedule.
 section: routines
 tags:
-  - routine
+  - routines
   - autonomous
   - advanced
 status: stable
@@ -25,6 +25,12 @@ ask_examples:
 locale: en-US
 created: 2026-04-25
 updated: 2026-04-25
+keywords:
+  - custom routine
+  - routine.custom.<slug>
+  - user-defined routine
+  - scheduled task
+  - recurring schedule
 related:
   - guides/add-a-custom-routine
   - concepts/routines

package/agent-assets/docs/features/routines/evening-review.md

@@ -14,7 +14,7 @@ summary: |
   items for tomorrow's plan.
 section: routines
 tags:
-  - routine
+  - routines
   - autonomous
   - daily
   - light-tier

package/agent-assets/docs/features/routines/hourly-check.md

@@ -12,7 +12,7 @@ summary: |
   consumes accumulated observations from the polling integrations.
 section: routines
 tags:
-  - routine
+  - routines
   - autonomous
   - light-tier
 status: stable

package/agent-assets/docs/features/routines/morning-routine.md

@@ -14,10 +14,9 @@ summary: |
   morning hour to produce today.md and the day's plan.
 section: routines
 tags:
-  - routine
+  - routines
   - autonomous
   - daily
-  - heavy-tier
   - core
 status: stable
 ask_examples:
@@ -27,7 +26,7 @@ ask_examples:
   - What model does morning routine use?
 locale: en-US
 created: 2026-04-25
-updated: 2026-04-25
+updated: 2026-05-17
 keywords:
   - morning
   - day plan
@@ -43,7 +42,8 @@ ui_anchors:
   - /
 process_keys:
   - routine.morning_routine
-  - routine.morning_routine_initial
+  - routine.morning_routine_today
+  - routine.morning_routine_journal
 config_keys:
   - dayBoundaryHour
 context_files:
@@ -62,10 +62,14 @@ roadmap, and recent observations.
 ## What It Does
 
 The morning routine is the single highest-value process in Aitne.
-It runs at the **heavy tier** (default Opus 4.7 on Claude, GPT-5.5 on
-Codex, Gemini 3 Pro on Gemini) because every downstream routine for
-the next 24 hours reads its output. A bad morning briefing degrades
-the entire day.
+It runs as a **two-stage pipeline** — Stage A (`routine.morning_routine_today`)
+on the medium tier rebuilds `today.md`, walks the roadmap, fans out
+the day's schedule, and self-reports structured metadata; Stage B
+(`routine.morning_routine_journal`) on the lite tier authors
+`daily/<yesterday>.md` in parallel from a daemon-prepared skeleton.
+Every downstream routine for the next 24 hours reads Stage A's
+output, so a bad morning briefing still degrades the entire day —
+hence the medium-tier ceiling on Stage A even after the split.
 
 In sequence, the routine:
 
@@ -85,9 +89,13 @@ so a post-midnight install does not run two morning routines back-to-back.
 There is no separate `morningRoutineHour` — the morning routine and the
 agent-day rollover are the same instant.
 
-`routine.morning_routine_initial` is a one-shot heavy-tier variant fired
-during the setup wizard's first day. After the first run, only
-`routine.morning_routine` triggers.
+There is no separate "initial" process key. The first morning after
+setup is detected inline by Stage A from the absence of `yesterday.md`;
+the daemon injects a `<roadmap_skeleton>` block carrying the pre-aggregated
+Annual Goals / Quarterly Focus / Preparation Timeline facts so Stage A
+can populate the wizard's placeholder roadmap on medium tier instead of
+paying for a one-shot heavy session. (Pre-Phase 7, this branch dispatched
+under `routine.morning_routine_initial` on the heavy tier.)
 
 ## What It Outputs
 
@@ -107,15 +115,16 @@ during the setup wizard's first day. After the first run, only
 | Setting | Default | Notes |
 |---|---|---|
 | `dayBoundaryHour` | `4` | Both the agent-day boundary and the morning-routine fire time. See [Agent Day](../../concepts/agent-day.md). |
-| Tier (heavy/light) | heavy | Forced heavy by default — Sonnet/Flash routines tend to skip critical context. |
-| Max turns | 50 (router cap, P95+) | Adjustable per-process in Settings → Models. |
-| Max budget USD | 5.00 | Per-execute cap. The router enforces this before token costs accumulate. |
+| Stage A tier (`routine.morning_routine_today`) | medium (Sonnet 4.6) | Synthesises `today.md` + the day's roadmap fan-out. Adjustable per-row in Settings → Models. |
+| Stage B tier (`routine.morning_routine_journal`) | lite (Haiku 4.5) | Appends yesterday's entry to `agent-journal.md`. |
+| Max turns | 50 | Stage A default. Adjustable per-process in Settings → Models. |
+| Max budget USD | 2.00 (Stage A: 0.50, Stage B: 0.10) | Per-execute envelope cap. The router enforces this before token costs accumulate. |
 
 ## When Something Goes Wrong
 
 - The most common failure is **morning routine did not run** because the daemon was offline at the trigger window. The next launch picks the run up via the catch-up scheduler if it is still the same agent day.
 - A failed morning routine emits a fallback-success notification when the secondary backend caught the run, or a fallback-failed notification (high priority) when both failed.
-- Heavy-tier quota exhaustion is the second most common cause: a provider rate limit on your `ANTHROPIC_API_KEY`, or — when running on the subscription fallback — the rolling Opus window of the underlying Claude plan. Switch the routine's model to a different heavy-tier option in Settings → Models or wait for the provider window to refresh.
+- Backend quota exhaustion is the second most common cause: a provider rate limit on your `ANTHROPIC_API_KEY`, or — when running on the subscription fallback — the rolling window of the underlying Claude plan. Switch the routine's model in Settings → Models (or wait for the provider window to refresh); if a fallback backend is configured, the router will automatically retry there first.
 
 ## Related
 

package/agent-assets/docs/features/routines/weekly-review.md

@@ -13,7 +13,7 @@ summary: |
   weekly retro into the weekly/ directory.
 section: routines
 tags:
-  - routine
+  - routines
   - autonomous
   - light-tier
 status: stable
@@ -24,6 +24,11 @@ ask_examples:
 locale: en-US
 created: 2026-04-25
 updated: 2026-04-25
+keywords:
+  - weekly review
+  - Friday review
+  - week roll-up
+  - agent week
 related:
   - concepts/routines
   - features/memory-files/agent-journal
@@ -36,22 +41,39 @@ process_keys:
 ## In One Sentence
 
 A light-tier weekly retro fires once per week and writes a synthesis
-into `weekly/<YYYY-MM-DD>.md`.
+into `weekly/YYYY-Www.md` (ISO week), whose **Carry Over / Next Week
+Focus / Lessons** sections are then lifted into every morning routine
+of the following ISO week.
 
 ## What It Does
 
-- Reads journal entries since the last weekly retro.
-- Reads completed tasks and roadmap movement.
-- Writes a synthesis: what shipped, what slipped, what surprised.
+- Reads daily files for the current ISO week, the past-7-day calendar
+  retrospective, roadmap, and active projects.
+- Synthesizes three axes — Outcomes, Forward items, Behavioral
+  Lessons — and writes the user-facing snapshot.
+- Appends an agent-internal block to `agent/journal.md` for self-
+  critique, filter quality, and improvement ideas.
+- Sends a brief Friday-evening notification by default (silence gate
+  triggers only on an essentially blank week).
+- Refreshes `user/reading-taste.md` and Book Candidates when enough
+  new highlights have accumulated.
 
 ## When It Runs / How It Is Triggered
 
-Every **Friday at 18:00 local time**. The schedule is fixed in
-`packages/daemon/src/core/scheduler.ts` and is not operator-configurable.
+Every **Friday at 19:00 local time** (one hour after `evening_review`).
+The schedule is fixed in `packages/daemon/src/core/scheduler.ts` and is
+not operator-configurable. If the Friday fire misses (daemon outage),
+the **Fri / Sat / Sun catch-up window** in `schedule-helpers.ts` fires
+the retro when the daemon recovers, before the new ISO week begins —
+a Mon–Thu catch-up is intentionally out of scope so the next week's
+`<previous_week>` injection stays stable Mon–Sun.
 
 ## What It Outputs
 
-- One file per week under `~/.personal-agent/context/weekly/`.
+- One file per week under `~/.personal-agent/context/weekly/YYYY-Www.md`
+  (zero-padded ISO week, e.g. `2026-W19.md`).
+- A `## Weekly YYYY-Www` block appended to
+  `~/.personal-agent/context/agent/journal.md`.
 
 ## Configuration
 
@@ -60,11 +82,15 @@ and tier are fixed in code.
 
 ## When Something Goes Wrong
 
-- The retro **doesn't fire**: catch-up does not span more than one
-  week — if the daemon was offline for several days the retro is
-  skipped.
+- The retro **doesn't fire on Friday**: the Fri–Sun catch-up window
+  retries on Saturday and Sunday agent-days. A full Fri–Sun outage
+  results in a missing weekly file; the next week's morning routines
+  proceed without the `<previous_week>` block.
+- The retro **runs but the file is empty** (silence gate): legitimate
+  for a blank week — the file is still written with empty sections,
+  and the next week's morning routine sees `(none recorded)` sub-
+  blocks, which is the deliberate downstream signal.
 
 ## Related
 
 - [Evening Review](evening-review.md)
-- [Monthly Review](monthly-review.md)

package/agent-assets/docs/features/wiki/commands.md

@@ -22,6 +22,7 @@ section: wiki
 tags:
   - wiki
   - bang-commands
+  - core
 status: stable
 ask_examples:
   - How do I send a URL to the wiki?
@@ -34,6 +35,16 @@ ask_examples:
 locale: en-US
 created: 2026-05-12
 updated: 2026-05-12
+keywords:
+  - !ingest
+  - !compile
+  - !ask
+  - !lint
+  - !trace
+  - !connect
+  - !wiki
+  - bang commands
+  - wiki commands
 related:
   - features/wiki/overview
   - features/messaging/bang-commands

package/agent-assets/docs/features/wiki/overview.md

@@ -17,6 +17,7 @@ section: wiki
 tags:
   - wiki
   - knowledge
+  - core
 status: stable
 ask_examples:
   - What is the wiki?
@@ -25,10 +26,19 @@ ask_examples:
   - Can I point the wiki at my Obsidian vault?
 locale: en-US
 created: 2026-05-12
-updated: 2026-05-12
+updated: 2026-05-17
+keywords:
+  - wiki
+  - wiki workspace
+  - 00_inbox
+  - 10_raw
+  - 20_wiki
+  - 30_outputs
+  - wiki layers
+  - external vault
 related:
   - features/wiki/commands
-  - features/memory-files
+  - concepts/memory-model
   - guides/build-your-wiki
   - guides/use-an-existing-obsidian-vault
   - guides/budget-and-cost-for-wiki
@@ -113,7 +123,7 @@ commit or stash first.
 The wiki has two distinct surfaces in the dashboard. The split mirrors
 how Aitne organises the rest of the app — configuration lives under
 **Setup → Settings**, day-to-day content browsing lives under **My
-Life** next to Knowledge / Reading / Git / Trip / Finance / Health.
+Life** next to Knowledge / Reading / Git.
 
 | Page | Section | Use it for |
 |---|---|---|

package/agent-assets/docs/getting-started/01-what-is-this.md

@@ -3,6 +3,12 @@ schema_version: 1
 slug: getting-started/01-what-is-this
 title: What is Aitne?
 id: what-is-this
+aliases:
+  - aitne
+  - what is aitne
+  - what is this
+  - introduction
+  - personal AI agent
 category: getting-started
 summary: |
   Aitne is a local-first proactive personal AI agent. It runs
@@ -13,15 +19,26 @@ section: getting-started
 tags:
   - core
   - getting-started
+  - overview
 status: stable
 ask_examples:
   - What is Aitne?
   - How is this different from ChatGPT?
   - Where does my data live?
   - What can Aitne actually do for me?
+  - Which backends can Aitne drive?
 locale: en-US
+keywords:
+  - introduction
+  - overview
+  - what is aitne
+  - personal agent
+  - local-first
+  - proactive
+  - markdown memory
+  - backends
 created: 2026-04-25
-updated: 2026-04-27
+updated: 2026-05-15
 related:
   - getting-started/02-first-steps
   - getting-started/03-what-can-this-do
@@ -33,10 +50,11 @@ related:
 # What is Aitne?
 
 Aitne is a local-first personal AI agent. It runs as a long-running
-daemon on your own machine, drives Claude Code, Codex CLI, or Gemini
-CLI via provider API keys you register (with the CLI's local
-subscription login as a fallback), and keeps all of its memory as
-plain Markdown files under `~/.personal-agent/`.
+daemon on your own machine, drives Claude Code, Codex CLI, Gemini
+CLI, or OpenCode (`@opencode-ai/sdk` server) via provider API keys
+you register (with the CLI's local subscription login as a
+fallback), and keeps all of its memory as plain Markdown files under
+`~/.personal-agent/`.
 
 Unlike a chat assistant that only responds when you type, Aitne also
 runs on its own — on a schedule, in reaction to changes it sees in
@@ -130,17 +148,20 @@ an opaque vector store.
 
 → [Memory Model](../concepts/memory-model.md)
 
-### Drive Claude Code / Codex / Gemini via API keys
+### Drive Claude Code / Codex / Gemini / OpenCode via API keys
 
-Aitne drives Claude Code, Codex CLI, and Gemini CLI on your behalf.
-The recommended setup is to register a provider API key for each
-backend you want to use — this matches what Anthropic, OpenAI, and
-Google document for headless / programmatic agent use, and gives you
-predictable per-call billing that is unambiguously permitted.
+Aitne drives Claude Code, Codex CLI, Gemini CLI, and OpenCode on
+your behalf. The recommended setup is to register a provider API key
+for each backend you want to use — this matches what Anthropic,
+OpenAI, and Google document for headless / programmatic agent use,
+and gives you predictable per-call billing that is unambiguously
+permitted.
 
 - Claude — `ANTHROPIC_API_KEY` (via Claude Code)
 - Codex — `OPENAI_API_KEY` (via Codex CLI)
 - Gemini — `GEMINI_API_KEY` / `GOOGLE_API_KEY` (via Gemini CLI)
+- OpenCode — provider key (Anthropic / OpenAI / OpenRouter / …)
+  forwarded into the OpenCode server in Managed or Remote mode
 
 If you skip the API key, Aitne falls back to whatever local
 subscription login the CLI already has on your machine (`claude`,

package/agent-assets/docs/getting-started/02-first-steps.md

@@ -3,6 +3,11 @@ schema_version: 1
 slug: getting-started/02-first-steps
 title: First Steps in the Dashboard
 id: first-steps
+aliases:
+  - first steps
+  - first time
+  - dashboard onboarding
+  - after install
 category: getting-started
 summary: |
   What to do the moment the dashboard opens — finish the setup wizard,
@@ -11,20 +16,27 @@ section: getting-started
 tags:
   - core
   - getting-started
+  - setup
 status: stable
 ask_examples:
   - I just opened the dashboard. What now?
   - How do I get the agent to talk to me?
   - Do I have to connect every integration?
+  - Where is the setup wizard?
 locale: en-US
+keywords:
+  - first steps
+  - setup wizard
+  - pair messaging
+  - dashboard onboarding
+  - health pill
 created: 2026-04-27
-updated: 2026-05-04
+updated: 2026-05-15
 related:
   - getting-started/01-what-is-this
   - getting-started/03-what-can-this-do
   - getting-started/04-first-day
   - guides/setup-wizard
-  - guides/use-cloud-providers
 ---
 
 # First Steps in the Dashboard
@@ -59,8 +71,9 @@ in (a backend, a messaging pair). Run through it once, top to bottom.
    because most providers do not support running agents on a
    personal subscription. The same picker also lets you point the
    backend at a cloud provider (Bedrock / Vertex / Foundry / Azure
-   OpenAI / Gemini-Vertex) instead of the direct API key — see
-   [Use a Cloud Provider for Models](../guides/use-cloud-providers.md).
+   OpenAI / Gemini-Vertex) instead of the direct API key — the
+   provider dropdown on `/settings/models` is the single surface for
+   both direct keys and cloud-provider credentials.
    Defaults are sensible and can be changed later from
    `/settings/models`. Background:
    [Backends and Tiers](../concepts/backends-and-tiers.md).