@aitne-sh/aitne 0.1.9 → 0.1.10

package/agent-assets/docs/features/memory-files/agent-lessons.md

@@ -0,0 +1,177 @@
+---
+schema_version: 1
+slug: features/memory-files/agent-lessons
+title: agent lessons
+id: agent-lessons
+aliases:
+  - lessons
+  - agent lessons
+  - feedback learning loop
+  - policies/agent-lessons.md
+category: features
+summary: |
+  The agent's learned-behavior stores — a global policies/agent-lessons.md
+  plus a per-agent policies/agents/<slug>/lessons.md. Your corrections and
+  preferences, the agent's own self-critiques, and your reactions are
+  captured as feedback signals, consolidated nightly into dated lessons,
+  re-generalized monthly, and injected back into the right executions.
+section: memory-files
+tags:
+  - memory
+  - feedback
+  - learning
+  - routines
+status: beta
+ask_examples:
+  - What are the agent lessons?
+  - Where does the agent remember my corrections?
+  - How does the feedback learning loop work?
+  - What is a provisional lesson?
+  - How do I tune the lesson caps?
+locale: en-US
+created: 2026-06-08
+updated: 2026-06-08
+keywords:
+  - lessons
+  - feedback
+  - learning loop
+  - corrections
+  - preferences
+  - self-critique
+  - provisional
+related:
+  - features/routines/evening-review
+  - features/routines/weekly-review
+  - features/memory-files/agent-journal
+  - reference/knowledge-layout
+process_keys:
+  - routine.evening_review
+  - routine.weekly_review
+  - routine.monthly_review
+context_files:
+  - policies/agent-lessons.md
+  - policies/agents/<slug>/lessons.md
+ui_anchors:
+  - /settings/lessons
+---
+
+# agent lessons
+
+## In one sentence
+
+The lesson stores are where the agent remembers how you want it to
+behave: a short, dated list of learned directives that grows from your
+corrections and the agent's own retros, and is fed back into the agent's
+work so it stops repeating the same mistakes.
+
+## What they are
+
+There are two kinds of store:
+
+- **Global agent behavior** — `policies/agent-lessons.md`. Lessons that
+  apply to the agent as a whole. These are injected into your DM
+  conversations and into the routines that decide whether to notify you.
+- **Per-agent** — `policies/agents/<slug>/lessons.md`, one per Agent
+  Definition. These are injected **only** into that agent's own
+  executions, so a lesson learned for your "weekly-report" agent never
+  leaks into an unrelated one.
+
+Both live under `~/.personal-agent/context/policies/`, alongside your
+other rule files, and are plain Markdown you can read or hand-edit.
+
+Each store is a `## Lessons` section of dated bullets. A lesson looks
+like:
+
+```
+- [2026-06-07] Keep the budget section in the weekly report. <!-- ev=2 kind=correction src=explicit conf=high last=2026-06-07 -->
+```
+
+The trailing HTML comment is bookkeeping the daemon manages: how much
+evidence backs the lesson (`ev`), what kind it is (a `correction`, a
+`do-more`/`do-less`, a hard `constraint`, …), how it was sourced, and
+when it was last reinforced. You can ignore the comment when reading —
+the prose before it is the directive.
+
+## How a lesson is born
+
+You never write these files to teach the agent a lesson; the loop does
+it for you. There are three ways signals enter:
+
+- **You correct it or state a preference.** When, in a DM, you correct
+  the agent, tell it how you want something done, or say
+  stop / do-more / do-less, it records that once as a feedback signal.
+  This does **not** change the current reply — your correction already
+  lives in that conversation — but it is remembered for later.
+- **The agent critiques itself.** The [weekly](../routines/weekly-review.md)
+  and monthly reviews post each concrete, actionable improvement idea as
+  a `self_critique` signal.
+- **Your reactions.** Whether you replied to or ignored a proactive
+  message is recorded as a weaker signal.
+
+Those raw signals don't become lessons immediately. Each night the
+[evening review](../routines/evening-review.md) folds the day's
+unconsumed signals into the right store as dated lessons, then marks them
+consumed (it skips the step entirely when nothing pends). Once a month
+the monthly review runs a re-generalize pass that collapses several
+same-theme lessons into one higher-level principle, keeping each store
+small.
+
+## Provisional vs. active
+
+A new lesson is stored but is not necessarily *injected* right away. A
+lesson carries a `<!-- provisional -->` marker until it has enough
+corroborating evidence; provisional lessons sit in the file but are not
+fed into the agent's prompts. This avoids over-fitting to a single
+offhand comment.
+
+How a lesson crosses from provisional to active:
+
+- A behavioral or self-critique lesson must reach weighted evidence at or
+  above the **promotion threshold** (`feedbackPromotionThreshold`,
+  default 2). Evidence is weighted by source — an explicit or corrected
+  signal counts 1.0, a reply or self-critique 0.5, an ignore 0.25.
+- An **explicit owner directive** ("always do X", "stop doing Y")
+  promotes on the first occurrence — it is taken at your word.
+- An **ignore on its own never promotes** a lesson, and is never read as
+  disapproval.
+
+## Bounded by design
+
+The stores can't grow without limit. Each is capped in bytes and entry
+count — the global store at `feedbackLessonMaxBytesGlobal` bytes
+(default 8192) / 40 entries, the per-agent stores at
+`feedbackLessonMaxBytesPerAgent` (default 4096) / 20 entries. When a
+store is full, the lowest-signal lessons are dropped first. Lessons that
+go untouched for `feedbackLessonStaleDays` (default 60) are pruned — with
+one exception: a `kind=constraint` lesson is durable and is never
+stale-pruned or collapsed away. The underlying feedback signals
+themselves are retained for `feedbackSignalRetentionDays` (default 180).
+
+## Where in the dashboard
+
+**Settings → Lessons** (`/settings/lessons`, labelled "Lessons" with a
+**Preview** badge) is the read/tune surface. From there you can view and
+edit the lessons themselves and adjust every knob above:
+`feedbackLearningEnabled` (the master kill-switch, on by default),
+`feedbackPromotionThreshold`, the byte caps, the stale-days horizon, and
+the signal retention window. Turning `feedbackLearningEnabled` off stops
+both capture and consolidation.
+
+## Configuration
+
+All of the loop's knobs are listed above and live on the Lessons page;
+there is nothing to configure in the files themselves. Because the stores
+are plain Markdown, **you** can hand-edit, prune, or remove a lesson at
+any time — the loop will pick up from whatever it finds the next night.
+
+## Related
+
+- [Evening Review](../routines/evening-review.md) — folds the day's
+  feedback signals into these stores each night.
+- [Weekly Review](../routines/weekly-review.md) — posts self-critique
+  signals that feed the loop. The monthly review re-generalizes the
+  stores once a month.
+- [agent journal](agent-journal.md) — the reflection-shaped diary, a
+  separate file from these directive stores.
+- [Knowledge layout](../../reference/knowledge-layout.md) — where the
+  `policies/` stores sit in the wider context vault.

package/agent-assets/docs/features/memory-files/projects.md

@@ -25,7 +25,7 @@ ask_examples:
   - How does the agent write to a project file?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - projects
   - project file
@@ -67,9 +67,11 @@ only the minimum — `type: project`, `owner: shared`, an `updated`
 date, and an H1 title. By convention the agent also writes `slug`,
 `state`, `start`, `due`, `stakeholders`, `next_milestone`, and `tags`.
 
-`state` is what marks a project **active**: the dashboard's project
-view filters on it, and the morning routine only surfaces projects
-whose `state` is active.
+`state` is what marks a project **active**: the Obsidian `_active.base`
+Bases view filters on it (`state != "archived"`), and the morning
+routine surfaces every project whose `state` is not `archived` — a
+file with no `state` (or any state other than `archived`) is treated
+as active and surfaced.
 
 ```markdown
 ---

package/agent-assets/docs/features/memory-files/roadmap.md

@@ -24,7 +24,7 @@ ask_examples:
   - How do I add a roadmap entry?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - roadmap.md
   - roadmap
@@ -56,9 +56,10 @@ rows that the morning routine fires on the day they come due.
 - Captures long-running goals that span more than a single day, so
   they don't fall out of `state/today.md` (which is replaced fresh
   each morning).
-- Preparation Timeline rows like "T-7 days: book hotel" surface in
-  the morning routine on the day each offset lands — turning a far-off
-  milestone into concrete actions at the right moment.
+- Preparation Timeline rows like "2026-06-13 [notify]: book hotel"
+  surface in the morning routine on the day each row is dated (or once
+  it is overdue) — turning a far-off milestone into concrete actions at
+  the right moment.
 - Cross-links to project files for deeper context.
 
 ## What It Looks Like
@@ -67,25 +68,27 @@ A goal with a Preparation Timeline is just Markdown the agent reads
 each morning. For example:
 
 ```markdown
-## Conference talk — 2026-06-20
+### 2026-06-20: Conference talk
 
 Goal: deliver the keynote in Tokyo.
 
-Preparation Timeline:
-- T-14 days: finalize slide deck
-- T-7 days: book hotel
-- T-2 days: dry run with the team
-- T-0: travel day
+**Preparation Timeline:**
+- 2026-06-06 [today]: finalize slide deck
+- 2026-06-13 [notify]: book hotel
+- 2026-06-18 [today]: dry run with the team
+- 2026-06-20 [today]: travel day
 ```
 
-On 2026-06-06 the morning routine sees the `T-14` offset come due and
-pulls "finalize slide deck" into that day's plan; on 2026-06-13 it
-surfaces "book hotel", and so on.
+Each Preparation Timeline row carries an absolute date and a tag
+(`[notify]`, `[today]`, `[check]`, or `[schedule]`). On 2026-06-06 the
+morning routine sees the `2026-06-06` row come due and pulls "finalize
+slide deck" into that day's plan; on 2026-06-13 it surfaces "book
+hotel", and so on.
 
 ## When It Runs / How It Is Triggered
 
 Read by the morning routine each day, which walks the roadmap and
-surfaces any Preparation Timeline rows whose offset fires that day.
+surfaces any Preparation Timeline rows dated for that day (or overdue).
 The file is updated by the operator, or by the agent on request (for
 example via the roadmap skill or `aitne run-now roadmap_maintenance`).
 

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

@@ -29,7 +29,7 @@ ask_examples:
   - Can I send the agent a voice note?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - messaging
   - dm
@@ -75,10 +75,10 @@ so you can talk to the agent the same way you'd type.
 ## What It Does
 
 - **Reactive DMs**: the agent answers every direct message you send.
-- **@-mentions (Slack only)**: @-mentioning the agent inside a shared
-  channel routes to the `message.mention` ProcessKey and is answered
-  the same way as a DM. Telegram, Discord, and WhatsApp drop all
-  non-DM traffic (no group support).
+- **@-mentions (Slack and Discord)**: @-mentioning the agent inside a
+  shared channel routes to the `message.mention` ProcessKey and is
+  answered the same way as a DM. Telegram and WhatsApp drop all non-DM
+  traffic (no group support).
 - **Outbound notifications**: routines and observations fire alerts
   back through the same channel.
 - **Voice attachments**: when the platform attaches audio (Telegram

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

@@ -8,7 +8,7 @@ aliases:
 category: features
 summary: |
   Pair Telegram by creating a bot via @BotFather, pasting the token
-  into Aitne, and DMing the magic phrase.
+  into Aitne, and scanning the pairing QR code.
 section: messaging
 tags:
   - messaging
@@ -24,7 +24,7 @@ ask_examples:
   - Where do I get a Telegram bot token?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - telegram
   - telegram bot
@@ -41,7 +41,7 @@ related:
 ## In One Sentence
 
 The fastest messaging app to pair: create a Telegram bot, paste the
-token, type the magic phrase.
+token, scan the pairing QR code.
 
 ## What It Does
 
@@ -51,7 +51,7 @@ token, type the magic phrase.
 ## When It Runs / How It Is Triggered
 
 Before pairing, nothing listens. Once you paste the bot token and complete
-magic-phrase pairing, Aitne long-polls Telegram's Bot API continuously for new
+QR / deep-link pairing, Aitne long-polls Telegram's Bot API continuously for new
 direct messages.
 
 ## Where in the Dashboard
@@ -63,17 +63,18 @@ direct messages.
 | Field | Notes |
 |---|---|
 | Bot Token | From @BotFather. |
-| Owner Channel | Auto-set on successful magic-phrase pairing. |
+| Owner Channel | Auto-set on successful QR / deep-link pairing. |
 
 ## When Something Goes Wrong
 
 - Bot replied to in a group instead of a DM: group chats are filtered
   out by design; the agent only listens to direct messages.
-- No reply at all after DMing the magic phrase: confirm the bot has a username
-  set via @BotFather (/setname) — the daemon refuses to build the pairing deep
-  link otherwise.
+- No reply at all after scanning the QR: confirm the bot has a username
+  set via @BotFather (/setname or /newbot) — the daemon refuses to build the
+  pairing deep link otherwise.
 - Pairing never completes: re-check the token in Connections → Messaging →
-  Telegram, then DM the magic phrase from your own account. See
+  Telegram, generate a fresh QR, then scan it (or tap the deep link) and press
+  START in Telegram from your own account. See
   [Pairing & Magic Phrase](pairing-and-magic-phrase.md).
 
 ## Related

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

@@ -26,7 +26,7 @@ ask_examples:
   - How do I find why a routine failed?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - activity
   - conversations
@@ -104,9 +104,10 @@ Retention is unlimited locally — the SQLite database keeps every row
 forever. To prune history without losing your configuration, use
 `POST /api/system/purge-history` (it clears `agent_actions`,
 `conversation_sessions`, and `messages` but leaves settings and the
-context vault intact). To wipe everything, `aitne uninstall --wipe-data`
-removes the whole `~/.personal-agent` data directory after a `WIPE`
-confirmation.
+context vault intact). To wipe everything, `aitne uninstall` removes the
+whole `~/.personal-agent` data directory after a literal `WIPE`
+confirmation (pass `--wipe-data` to skip the prompt and wipe
+non-interactively, or `--keep-data` to leave the directory intact).
 
 ## When Something Goes Wrong
 

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

@@ -24,7 +24,7 @@ ask_examples:
   - Where do I approve a pending action?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - approval
   - approve tier
@@ -83,10 +83,11 @@ Deny asks for confirmation before discarding the item.
 
 ## When Something Goes Wrong
 
-- **An approval that never clears:** the agent session that produced
-  it may have timed out. The action expires with the session — redo
-  the request that triggered it (for example, re-send the DM or
-  re-run the routine).
+- **A stale approval you never answered:** a pending approval is
+  discarded once the agent day rolls over (the next 04:00 local
+  boundary) — it's marked skipped rather than replayed after the
+  day turns. If that happens, redo the request that triggered it
+  (for example, re-send the DM or re-run the routine).
 
 ## Related
 

package/agent-assets/docs/features/operations/managed-chromium.md

@@ -31,7 +31,7 @@ ask_examples:
   - How do I block a site from managed Chromium?
 locale: en-US
 created: 2026-05-22
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - managed chromium
   - browser automation
@@ -136,7 +136,8 @@ ships empty.
 1. The agent prepares the checkout in a managed Chromium tab and
    pauses at the final confirm step.
 2. The daemon mints a single-use token with the prefix `!~` followed
-   by 8 random hex characters (e.g. `!~3a1f9c7b`), inserts a
+   by 8 random base32 characters (alphabet `A-Z2-7`, e.g.
+   `!~K7QM3ZAB`), inserts a
    `browser_automation_purchase_tokens` row keyed on a server-side
    `jti`, and DMs the token to a primary channel together with a
    screenshot of the exact cart state.

package/agent-assets/docs/features/operations/quiet-hours.md

@@ -25,7 +25,7 @@ ask_examples:
   - Will routines still run during quiet hours?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - quiet hours
   - dnd
@@ -94,8 +94,9 @@ timezone) before sending. The window may wrap midnight — the default
 ## Where in the Dashboard
 
 **Settings → Schedule** holds `quietHoursStart` and `quietHoursEnd`,
-shown as a red band on the same 24-hour slider as the hourly-check
-active window. There is **no overlap validation** — quiet hours and the
+shown as a red arc on the same 24-hour ring (dial) as the hourly-check
+active window — drag the handles to adjust either band. There is **no
+overlap validation** — quiet hours and the
 active window are allowed to overlap, and the morning routine fires
 regardless of where the bands sit.
 

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

@@ -29,7 +29,7 @@ ask_examples:
   - Which tier does a custom routine run under?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - custom routine
   - routine.custom.<slug>
@@ -159,16 +159,20 @@ under the `medium` tier (Sonnet on the Claude backend), and stops
 spending once the run reaches $0.10.
 
 > **Distinct from `recurring_schedules`.** The `recurring_schedules`
-> table powers DM-style scheduled tasks (`agent.task` /
-> `agent.dm_task`) — e.g. "remind me at 9am every weekday". Those
-> use a structured `RecurrenceRule` (frequency + time + dayOf*) and
-> are managed via `POST /api/recurring-schedules`. They are not the
-> same surface as `routine.custom.<slug>`.
+> table now powers recurring scheduled DMs only (`task_type =
+> 'dm_session'`) — e.g. the morning briefing. They use a structured
+> `RecurrenceRule` (frequency + time + dayOf*) and are managed via
+> `POST /api/recurring-schedules`. Recurring agent *work* moved to the
+> `/agents` layer — `POST /api/recurring-schedules` with any
+> non-`dm_session` task type returns 410 Gone with a pointer to
+> `POST /api/agents`. Neither is the same surface as
+> `routine.custom.<slug>`.
 
 ## When Something Goes Wrong
 
 - A cron expression that resolves to "never": the routine appears in
-  the list but never fires. The dashboard shows next-fire as N/A.
+  the list but never fires. The dashboard's "Next runs" preview shows
+  "No upcoming runs found within the next year for this timezone."
 
 ## Related
 

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

@@ -27,7 +27,7 @@ ask_examples:
   - How do I disable the evening review?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - evening review
   - retro
@@ -48,6 +48,7 @@ context_files:
   - journal/agent.md
   - identity/profile.md
   - policies/routines/evening.md
+  - policies/agent-lessons.md
 ui_anchors:
   - /connections/journal
   - /settings/routines
@@ -64,7 +65,7 @@ your identity files.
 
 ## What It Does
 
-The routine runs three internal bookkeeping steps. These are quiet by
+The routine runs several internal bookkeeping steps. These are quiet by
 design — they prepare state that **tomorrow's morning routine depends on**
 rather than producing a chatty end-of-day report.
 
@@ -80,6 +81,11 @@ rather than producing a chatty end-of-day report.
 3. **Process profile signals.** Reads the day's Raw Signals from your
    profile and routes each into `character`, Learned Context, or a
    detailed identity file under `identity/`, then prunes stale entries.
+4. **Consolidate feedback signals into lessons.** When feedback learning is
+   on (default) and signals are pending, folds the day's unconsumed feedback
+   into the scoped lesson stores (`policies/agent-lessons.md` for agent-scope
+   lessons; identity files for owner directives), then marks them consumed.
+   Skipped entirely when no signals pend.
 
 ## When It Runs / How It Is Triggered
 
@@ -94,6 +100,8 @@ run is skipped while the agent is paused (`!stop`) or setup is incomplete.
 - Roadmap edits in `plans/roadmap.md` when a plan was promoted or fired.
 - A `journal/agent.md` line **only** when a roadmap review date fired or a
   validation error needs recording.
+- Lesson edits in `policies/agent-lessons.md` when feedback signals were
+  pending and consolidated.
 
 The built-in steps emit **no user-facing DM by default** — there is no
 "today wraps up here" message. (The one exception: any check you add to

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

@@ -26,7 +26,7 @@ ask_examples:
   - What model does morning routine use?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - morning
   - day plan
@@ -109,8 +109,9 @@ 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 high-tier session. (The dedicated
-`routine.morning_routine_initial` process key was retired in Phase 4, and
-Phase 7 — 2026-05-16 — removed its high-tier seed entirely.)
+`routine.morning_routine_initial` process key — along with its high-tier
+seed — was retired in Phase 7, 2026-05-16; the first-run branch now flows
+through the parent `routine.morning_routine` envelope.)
 
 ## What It Outputs
 

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

@@ -39,6 +39,7 @@ related:
   - concepts/routines
   - features/routines/evening-review
   - features/memory-files/agent-journal
+  - features/memory-files/agent-lessons
 process_keys:
   - routine.weekly_review
 config_keys:
@@ -69,6 +70,11 @@ 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.
 - 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

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