@aitne-sh/aitne 0.1.9 → 0.1.11

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

@@ -27,7 +27,7 @@ ask_examples:
   - Where do weekly retros get stored?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-10
 keywords:
   - weekly review
   - Friday review
@@ -39,14 +39,16 @@ related:
   - concepts/routines
   - features/routines/evening-review
   - features/memory-files/agent-journal
+  - features/memory-files/agent-lessons
 process_keys:
   - routine.weekly_review
 config_keys:
   - timezone
   - dayBoundaryHour
+  - selfTuningEnabled
 ui_anchors:
   - /settings/models
-  - /settings/routines
+  - /agents/weekly-review
 context_files:
   - journal/weekly/YYYY-Www.md
   - journal/agent.md
@@ -69,6 +71,22 @@ into every morning routine of the following ISO week.
   Lessons — and writes the user-facing snapshot.
 - Appends an agent-internal block to `journal/agent.md` for
   self-critique, filter quality, and improvement ideas.
+- Feeds the learning loop: for each concrete, actionable system
+  improvement idea it identifies, it also posts a `source=self_critique`
+  feedback signal (in addition to the `journal/agent.md` prose), so the
+  idea is consolidated into the [agent lessons](../memory-files/agent-lessons.md)
+  rather than only living in the journal.
+- Judges the daemon's self-tuning recommendations: when the weekly
+  pre-step finds a cost knob worth changing (e.g. raising the mail
+  pre-pass freshness window because most fetches came back empty), it
+  injects up to three bounded proposals and the review records an
+  apply / reject / defer verdict for each. While `selfTuningEnabled` is
+  `false` (the default) nothing is ever changed automatically — verdicts
+  are recorded for the owner to review (shadow mode). With the flag on,
+  an apply verdict is actuated immediately by the daemon within hard
+  per-key bounds; the owner gets a one-line DM per applied change
+  (`!revert tuning` undoes the latest one) and a daily monitor
+  auto-reverts any change whose 7-day follow-up metrics regressed.
 - Sends a brief Friday-evening notification by default (the silence
   gate triggers only on an essentially blank week).
 - Refreshes `identity/reading-taste.md` and Book Candidates when
@@ -97,7 +115,10 @@ The fire time (Friday 19:00 local) and day-of-week are fixed in code
 and are not operator-tunable. The backend and model that handle this
 routine, however, are configurable: `routine.weekly_review` is a
 configurable process key (default **medium** tier — Sonnet on Claude)
-that you can repoint from **Settings → Models**.
+that you can repoint from **Settings → Models**. The weekly rulebook
+(`policies/routines/weekly.md`) is edited on the weekly-review agent's
+Rulebook tab (`/agents/weekly-review?tab=rulebook`), where the agent
+can also be enabled or disabled.
 
 ## When Something Goes Wrong
 

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

@@ -34,7 +34,7 @@ ask_examples:
   - How do I bridge two domains with `!connect`?
 locale: en-US
 created: 2026-05-12
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - !ingest
   - !compile
@@ -145,9 +145,9 @@ The acknowledgement DM names the mode that ran (`in parallel` /
 Full rebuilds touch every wiki note and are the most expensive
 command in the wiki surface. The flow:
 
-1. The bang handler estimates the cost (raw note count × assumed
-   input tokens × Sonnet 4.6 input price, bracketed optimistic 0.5× /
-   expected 1× / pessimistic 2×).
+1. The bang handler estimates the cost (per raw note, an on-disk
+   char→token approximation × Sonnet 4.6 input price, bracketed
+   optimistic 0.5× / expected 1× / pessimistic 2×).
 2. On an external git-tracked vault with **Auto-commit before
    `!compile full`** enabled and a clean working tree, Aitne runs
    `git add -A && git commit -m "aitne wiki: pre-compile snapshot <ts>"`

package/agent-assets/docs/features/wiki/cost-and-approval.md

@@ -39,7 +39,7 @@ ask_examples:
   - Can I see the cost before running !compile full?
 locale: en-US
 created: 2026-05-21
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - cost estimate
   - cost bracket
@@ -178,8 +178,9 @@ its budget envelope is bounded by the per-process `maxBudgetUsd`
 
 Per workspace, in `/settings/wiki` — the **Approval threshold (USD)**
 input. The value lives on `wiki_workspaces.full_compile_approval_threshold_usd`
-with a CHECK constraint `> 0`. Setting it lower escalates more runs
-to manual approval; setting it higher trusts the estimator more.
+and the PATCH endpoint validates it to the `$0`–`$100` range. Setting it
+lower escalates more runs to manual approval; setting it higher trusts
+the estimator more.
 
 A common pattern: start at $2.00, watch the spend on the next
 `!compile full`, then dial up or down based on how close the

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

@@ -37,7 +37,7 @@ ask_examples:
   - What does the Enable Wiki button do?
 locale: en-US
 created: 2026-05-21
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - /wiki
   - /wiki/timeline
@@ -128,7 +128,7 @@ States:
 The last 8 entries from `log.md`, the wiki's append-only operational
 log. Each entry shows the wiki process key (`wiki.ingest_url`,
 `wiki.compile`, `wiki.ask`, `wiki.lint`, `wiki.trace`, `wiki.connect`),
-the operation (`write`, `delete`, …), the affected path, and the
+the operation (`post`, `patch`), the affected path, and the
 timestamp. A **View full timeline** button at the top of the card
 opens `/wiki/timeline`.
 
@@ -184,10 +184,11 @@ The configuration surface. Two-state:
 
 A two-card chooser:
 
-- **Internal** (recommended) — managed by Aitne in its data directory
-  (default `~/.personal-agent/wiki`), schema seeded automatically.
-  The **Enable internal wiki** button turns it on with nothing else
-  to configure.
+- **Internal** (recommended) — managed by Aitne inside the context
+  vault (default `<contextDir>/knowledge/wiki`, i.e.
+  `~/.personal-agent/context/knowledge/wiki`), schema seeded
+  automatically. The **Enable internal wiki** button turns it on with
+  nothing else to configure.
 - **Existing Obsidian vault** (external) — point Aitne at a folder you
   already own via the path picker, then confirm with **Use this
   folder**.

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

@@ -26,7 +26,7 @@ ask_examples:
   - Can I point the wiki at my Obsidian vault?
 locale: en-US
 created: 2026-05-12
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - wiki
   - wiki workspace
@@ -110,8 +110,8 @@ competes for budget with daily reactive memory.
 Aitne offers two modes:
 
 - **Internal** (recommended starting point) — the daemon owns the
-  vault at `$PA_DATA_DIR/wiki`. No sandbox issues, daemon-managed
-  snapshots, isolated from iCloud sync conflicts.
+  vault at `$PA_DATA_DIR/context/knowledge/wiki`. No sandbox issues,
+  daemon-managed snapshots, isolated from iCloud sync conflicts.
 - **External** — you point the wiki at an existing Obsidian vault on
   disk. The daemon writes directly when the filesystem allows, and
   falls back to the official Obsidian CLI when the vault sits in a

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

@@ -36,7 +36,7 @@ ask_examples:
   - What is fts_wiki?
 locale: en-US
 created: 2026-05-21
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - wiki search
   - fts_wiki
@@ -119,10 +119,10 @@ is the file on disk, not a row in another SQL table. This matters:
   because the source rows live in SQLite.
 - Wiki content lives on the filesystem. There's no source table to
   trigger off, so the wiki API write endpoints
-  (`POST /api/wiki/:ws/files/:path`, `PATCH /api/wiki/:ws/files/:path`,
-  `DELETE /api/wiki/:ws/files/:path`) call
-  `upsertWikiFulltextRow` / `deleteWikiFulltextRow` directly after a
-  successful disk write.
+  (`POST /api/wiki/:ws/files/:path`, `PATCH /api/wiki/:ws/files/:path`)
+  call `upsertWikiFulltextRow` directly after a successful disk write.
+  (`deleteWikiFulltextRow` is reached internally — it's how
+  `upsertWikiFulltextRow` drops a `log`/`inbox` row from the index.)
 
 The schema (`packages/daemon/src/db/schema.ts`):
 

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

@@ -37,7 +37,7 @@ ask_examples:
   - Can two wikis live in nested folders?
 locale: en-US
 created: 2026-05-21
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - wiki workspace
   - workspace
@@ -98,7 +98,7 @@ side-by-side wikis as you have distinct knowledge domains.
 |---|---|---|
 | Root path | `$PA_DATA_DIR/context/knowledge/wiki/<name>` (daemon-owned, inside the context vault) | Any path you pick (typically an existing Obsidian vault) |
 | Writes | Atomic local-fs writes | Atomic local-fs writes when permitted; Obsidian-CLI fallback for sandboxed paths |
-| Backup surface | `md_file_snapshots` table | git auto-commit (when the vault is git-tracked) + sibling backup mirror under `90_meta/health/pre-migrate-<date>/` |
+| Backup surface | On-disk `.snapshots/<timestamp>/` tree under the workspace root | git auto-commit (when the vault is git-tracked) + sibling backup mirror under `90_meta/health/pre-migrate-<date>/` |
 | iCloud-friendly | Yes (lives in `~/.personal-agent`) | Yes via the Obsidian CLI fallback (requires the Obsidian app running) |
 | Best for | First-time users, isolated wiki, no Obsidian dependency | Power users with an existing Obsidian vault they want the agent to extend |
 

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

@@ -90,8 +90,8 @@ You can change the times, disable any of them, or add your own.
 
 → [Morning Routine](../features/routines/morning-routine.md) ·
 [Evening Review](../features/routines/evening-review.md) ·
-[Hourly Check](../features/routines/hourly-check.md) ·
-[Custom Routines](../features/routines/custom-routines.md)
+[Activity Scan](../features/routines/activity-scan.md) ·
+[Create a Recurring Agent](../guides/add-a-custom-routine.md)
 
 ### Reach you through a messenger
 
@@ -117,7 +117,7 @@ Pairing is one-time per channel.
 
 When you connect an integration, the agent polls it on a schedule and
 records anything that looks relevant as an
-[observation](../concepts/observations.md). The hourly routine then
+[observation](../concepts/observations.md). The activity scan then
 decides what (if anything) is worth telling you about.
 
 - [Mail](../features/integrations/mail.md) — Gmail, Outlook, Yahoo,

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

@@ -31,7 +31,7 @@ keywords:
   - dashboard onboarding
   - health pill
 created: 2026-04-27
-updated: 2026-05-28
+updated: 2026-06-07
 related:
   - getting-started/01-what-is-this
   - getting-started/03-what-can-this-do
@@ -55,8 +55,10 @@ health pill, a paired messaging app, and a backend the agent can call.
 ## What you should see right now
 
 If the dashboard just opened, you are on `/setup` — the setup wizard.
-The dashboard refuses to leave this page until the minimum is filled
-in (a backend, a messaging pair). Run through it once, top to bottom.
+The dashboard sends you back to this page until the required steps are
+done (Basics, Vault, a main backend, and the Customize Rules step that
+saves your management rules). Messaging and the other integrations are
+skippable in the wizard. Run through it once, top to bottom.
 
 ## Steps
 

package/agent-assets/docs/getting-started/04-first-day.md

@@ -43,7 +43,7 @@ ui_anchors:
   - /knowledge?tab=context-files
   - /connections
   - /connections/mcp
-  - /settings/routines
+  - /agents
   - /activity
 context_files:
   - identity/profile.md
@@ -52,14 +52,14 @@ context_files:
 api_endpoints:
   - POST /api/knowledge/import
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-10
 related:
   - getting-started/02-first-steps
   - getting-started/03-what-can-this-do
   - guides/setup-wizard
   - guides/import-knowledge-file
   - features/routines/morning-routine
-  - features/routines/custom-routines
+  - guides/add-a-custom-routine
   - features/memory-files/user-profile
   - concepts/delegated-mode
   - concepts/skills
@@ -236,12 +236,11 @@ recurring:
   and message me on WhatsApp."* The agent stores a recurring
   schedule and runs the same prompt at the same cron. Best for
   per-channel reminders and small recurring asks.
-- **Custom routines** — heavier, multi-step jobs that should write
-  to Markdown memory and DM you with a summary. Add one under
-  **Settings → Routines → Add custom routine**, or DM the agent the
-  cron + steps and ask it to save the routine. See
-  [Custom Routines](../features/routines/custom-routines.md) and
-  [Add a Custom Routine](../guides/add-a-custom-routine.md).
+- **User Agents** — heavier, multi-step jobs that should write
+  to Markdown memory and DM you with a summary. Create one under
+  **Agents → New Agent** (`/agents`), or DM the agent the
+  cron + steps and ask it to save it as an Agent. See
+  [Create a Recurring Agent](../guides/add-a-custom-routine.md).
 
 ### A worked example: a richer morning routine
 
@@ -265,23 +264,22 @@ Shortest path from zero to that:
    notes." This makes the gaps obvious — Notion not connected?
    Calendar not connected? WhatsApp not paired? Drive not reachable
    through a connector or MCP server? Fix them as they show up.
-2. **Once each piece works standalone**, open **Settings → Routines
-   → Add custom routine**:
-   - Slug: `morning-deep-prep`
-   - Cron: `0 7 * * 1-5`
-   - Backend tier: `high (opus)` — this is a heavy, multi-tool job
-   - Max budget (USD): `0.20` (a generous per-execute override; the
-     form default is `0.05`)
-   - Description: paste the four numbered steps above verbatim.
-3. **Watch the next firing in Activity** and iterate. The vault file
-   at `~/.personal-agent/context/policies/routines/custom/morning-deep-prep.md`
-   is a plain Markdown file: edit the `## Checks` body to refine the
-   step wording, or the `cron:` field in the YAML frontmatter to
-   change the schedule. The watcher picks up changes without a
-   restart.
-
-→ [Custom Routines](../features/routines/custom-routines.md) ·
-[Add a Custom Routine](../guides/add-a-custom-routine.md)
+2. **Once each piece works standalone**, open **Agents → New Agent**
+   (`/agents`):
+   - Name / ID: `morning-deep-prep`
+   - Schedule: weekdays (Mon–Fri) at 07:00
+   - Model tier: `high (opus)` — this is a heavy, multi-tool job
+   - Max budget (USD): `0.20` (a generous per-execute override)
+   - Task prompt: paste the four numbered steps above verbatim.
+3. **Watch the next firing in Agent Log** and iterate. The agent
+   definition lives in the vault at
+   `~/.personal-agent/context/policies/agents/morning-deep-prep/agent.md`
+   — a plain Markdown file whose body is the task prompt and whose
+   YAML frontmatter carries the schedule — but the easiest place to
+   refine the step wording or the schedule is the agent's own page
+   at `/agents/morning-deep-prep`.
+
+→ [Create a Recurring Agent](../guides/add-a-custom-routine.md)
 
 ---
 
@@ -294,8 +292,8 @@ By end of day one you should have:
   **Activity**.
 - One DM whose answer references something only your connected
   apps could have told the agent.
-- (Stretch) one custom routine or recurring schedule in **Settings
-  → Routines** that you'd be sad to lose.
+- (Stretch) one user agent or recurring schedule under **Agents**
+  (`/agents`) that you'd be sad to lose.
 
 ## If it fails
 
@@ -312,8 +310,7 @@ By end of day one you should have:
 
 - [Import a Knowledge File](../guides/import-knowledge-file.md)
 - [Morning Routine](../features/routines/morning-routine.md)
-- [Custom Routines](../features/routines/custom-routines.md)
-- [Add a Custom Routine](../guides/add-a-custom-routine.md)
+- [Create a Recurring Agent](../guides/add-a-custom-routine.md)
 - [Delegated Mode](../concepts/delegated-mode.md)
 - [Skills and MCP](../concepts/skills.md)
 - [identity/profile.md](../features/memory-files/user-profile.md)

package/agent-assets/docs/glossary.md

@@ -35,7 +35,7 @@ ask_examples:
   - What is an observation?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - terminology
   - vocabulary
@@ -78,7 +78,7 @@ process_keys:
   - dashboard.docs_qa
   - delegated_task_heavy
   - routine.fetch_window
-  - routine.hourly_check
+  - routine.activity_scan
   - routine.research_cluster_update
 config_keys:
   - dayBoundaryHour
@@ -111,8 +111,8 @@ enabled as fallbacks.
 ## Browser History (B-3)
 
 Local-only history poller that reads the browser's own SQLite database
-(Chrome / Safari / Firefox / Arc) and records page visits as
-observations. Drives the **research cluster** derivation, the weekly
+(Chromium-based browsers — Chrome, Chromium, Edge, Brave, Comet, Atlas)
+and records page visits as observations. Drives the **research cluster** derivation, the weekly
 reload-memory block, and the [`!checks`](features/messaging/bang-commands.md)
 on-demand reload tally. No content is uploaded; only URLs, titles, and
 visit timings the browser itself recorded. See
@@ -206,7 +206,7 @@ connected service: `direct | delegated | native | disabled`.
   MCP / skill harness — `outlook_mail`, `outlook_calendar`).
 - **disabled** — silence; no poller, no native handoff.
 
-Mode lookup goes through `getIntegrationState(db, key)`; never
+Mode lookup goes through `readIntegrationState(db, key)`; never
 hardcode an integration reference outside
 `packages/shared/src/integrations.ts`. See
 [Delegated Mode](concepts/delegated-mode.md).
@@ -230,7 +230,7 @@ Operator-facing umbrella for the two non-heavy lanes on each backend:
 
 - **Medium / Main** (Claude Sonnet 4.6, `gpt-5.4` on Codex,
   `gemini-3.1-pro-preview` on Gemini, Sonnet 4.6 via OpenCode) —
-  default for owner DMs, dashboard chat, the hourly check, and the
+  default for owner DMs, dashboard chat, the activity scan, and the
   morning / evening / weekly review routines.
 - **Lite / Delegated** (Claude Haiku 4.5, `gpt-5.4-mini` on Codex,
   `gemini-3.1-flash-lite-preview` on Gemini, Haiku 4.5 via OpenCode) —
@@ -252,7 +252,7 @@ fallback when upstream reports zero.
 ## Routine Pre-pass
 
 A lite-tier `routine.fetch_window` session spawned before each main
-routine (morning / today_refresh / hourly_check / evening / weekly).
+routine (morning / today_refresh / activity_scan / evening / weekly).
 It fetches each routine's mail / calendar / Notion window
 (`ROUTINE_WINDOWS`) and POSTs the results to `/api/observations`. The
 main routine then consumes the resulting `<fetch_report>` block and
@@ -264,7 +264,7 @@ in 2026-05 to trim morning-routine input tokens by ~24%.
 One row in the `observations` table. A change record a polling
 integration (Obsidian, Git, Notion, calendar, mail, browser history)
 or a `routine.fetch_window` pre-pass wrote into SQLite. The
-`routine.hourly_check` is the consumer — there is no per-change
+`routine.activity_scan` is the consumer — there is no per-change
 notification. `actor='agent'` rows are filtered out by the consumer
 to break the agent-observing-its-own-writes loop. See
 [Observations](concepts/observations.md).