@aitne-sh/aitne 0.1.10 → 0.1.12

package/agent-assets/docs/guides/add-a-custom-routine.md

@@ -1,46 +1,54 @@
 ---
 schema_version: 1
 slug: guides/add-a-custom-routine
-title: Add a Custom Routine
+title: Create a Recurring Agent
 id: add-a-custom-routine
 aliases:
+  - recurring agent
+  - new agent
+  - user agent
   - custom routine
-  - user-defined routine
   - add a routine
   - scheduled task
 category: guides
 summary: |
-  Define a new autonomous routine — slug, cron expression, model tier, and
-  budget cap — via /settings/routines. The form writes a vault file at
-  policies/routines/custom/<slug>.md; saving it registers the cron job.
+  Make the agent run a prompt you write on a schedule you pick by
+  creating a user Agent — via the "New Agent" form on /agents or
+  POST /api/agents. The Markdown body (the prompt) becomes the task
+  prompt for every run; runs appear on the Agent's detail page.
 section: add-a-custom-routine
 tags:
   - guides
+  - agents
   - routines
   - scheduler
   - autonomous
   - core
 status: stable
 ask_examples:
-  - How do I add a custom routine?
-  - What can a custom routine do?
+  - How do I create a recurring agent?
   - How do I schedule the agent to run on a cron?
+  - How do I add a custom routine?
+  - Where do I see my agent's runs?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-10
 keywords:
-  - custom routine
-  - schedule
+  - recurring agent
+  - new agent
   - cron
+  - schedule
   - recurrence
-  - backend_tier
-  - process_key
+  - task prompt
+  - agent.task
 ui_anchors:
-  - /settings/routines
+  - /agents
 api_endpoints:
-  - PUT /api/context/*
+  - POST /api/agents
+  - GET /api/agents/{slug}/executions
+  - POST /api/agents/{slug}/run-now
 context_files:
-  - policies/routines/custom/<slug>.md
+  - policies/agents/<slug>/agent.md
 related:
   - features/routines/custom-routines
   - concepts/routines
@@ -48,76 +56,122 @@ related:
   - concepts/backends-and-tiers
 ---
 
-# Add a Custom Routine
+# Create a Recurring Agent
 
 ## Goal
 
-Make the agent fire a particular kind of work on a schedule you pick.
+Make the agent fire a particular kind of work on a schedule you pick —
+as a user **Agent** you can watch, tune, and toggle from `/agents`.
 
 ## Prerequisites
 
 - Daemon running.
 
-## Steps
-
-1. Open `/settings/routines` (the older `/connections/routines` URL
-   redirects here).
-2. Click **Add**. The "New custom routine" dialog opens.
-3. Fill the form:
-   - **Slug** — lowercase kebab-case, 1–64 chars, no leading/trailing
-     hyphen (e.g. `tuesday-notion-sweep`). It becomes the ProcessKey
-     `routine.custom.<slug>` and the file name
-     `policies/routines/custom/<slug>.md`.
-   - **Cron expression** — standard 5-field cron in the daemon's
-     timezone (e.g. `0 11 * * 2` for 11:00 every Tuesday). The dialog
-     previews the next three fire times.
-   - **Backend tier** — `lite` (Haiku), `medium` (Sonnet), or `high`
-     (Opus). Default is `medium`. Custom routines have no concrete
-     model picker; the tier is written to the file's `backend_tier`
-     frontmatter, and the BackendRouter resolves the actual model at
-     fire time. (See [Backends and tiers](../concepts/backends-and-tiers.md).)
-   - **Max budget (USD)** — per-execute cap (default `0.05`; must be a
-     positive number).
-   - **Description** — optional free text. It becomes the body of the
-     generated vault file, above an empty `## Checks` section seeded
-     with a `### First check` placeholder. Edit the file later on the
-     same page to flesh out the check list.
-4. Click **Create**. The dashboard writes the vault file via the
-   context API (`PUT /api/context/policies/routines/custom/<slug>`).
-   Because the file ships with `enabled: true` and a `cron:` field,
-   saving it registers (or refreshes) the cron job, and the next-fire
-   timestamp appears in the routine list.
-
-The generated file looks roughly like this:
-
-```yaml
----
-type: rule
-slug: tuesday-notion-sweep
-cron: "0 11 * * 2"
-process_key: routine.custom.tuesday-notion-sweep
-enabled: true
-backend_tier: medium
-max_budget_usd: 0.05
----
+## Steps (dashboard)
+
+1. Open **Agents** (`/agents`) and click **New Agent**.
+2. Fill the form:
+   - **Name** — the human label in the agents list (e.g. "Daily
+     Digest").
+   - **ID** — lowercase kebab-case slug. It becomes the URL
+     (`/agents/<id>`) and the definition file
+     `policies/agents/<id>/agent.md`. Must not collide with an
+     existing Agent (built-in slugs are reserved too).
+   - **Schedule** — pick a frequency (hourly / daily / weekly /
+     monthly) and its fields, e.g. weekly on Tuesday at 11:00. An
+     optional toggle defers runs that land inside your quiet hours.
+   - **Backend engine / Model tier** — `lite` (Haiku-class), `medium`
+     (Sonnet-class), or `high` (Opus-class). See
+     [Backends and tiers](../concepts/backends-and-tiers.md).
+   - **Limits** — max turns, max budget (USD) per run, and timeout
+     (minutes).
+   - **Task prompt** — what the agent should do on each run. This text
+     becomes the Markdown body of `agent.md` and is the prompt the
+     agent receives every time it fires.
+   - An **Advanced (YAML)** toggle reveals the raw `agent.md` editor
+     for long-tail fields the form doesn't expose (tags, tools,
+     success criteria, error handling).
+3. Save. The dashboard writes `policies/agents/<slug>/agent.md`
+   through the context vault and opens the new Agent's detail page;
+   the daemon imports the file without a restart.
+
+## Steps (API)
+
+`POST /api/agents` is the programmatic counterpart:
+
+```bash
+curl -X POST http://localhost:8321/api/agents \
+  -H "Content-Type: application/json" \
+  -d '{
+    "slug": "tuesday-notion-sweep",
+    "name": "Tuesday Notion Sweep",
+    "description": "Weekly Notion inbox cleanup",
+    "schedule": { "kind": "cron", "expression": "0 11 * * 2" },
+    "backend": { "tier": "medium" },
+    "limits": { "max_budget_usd": 0.10 },
+    "prompt": "- Review my Notion inbox for items older than a week.\n- File or archive each one.\n- DM me a one-paragraph summary."
+  }'
 ```
 
-To stop a routine without deleting it, set `enabled: false` in the
-file and save — that unregisters the cron job.
+- **`prompt` becomes the Agent's task prompt** — it is stored as the
+  Markdown body of `agent.md` and sent to the agent on every run.
+- **`schedule`** takes one of two forms: a raw 5-field cron
+  (`{ "kind": "cron", "expression": "0 11 * * 2" }`, interpreted in
+  the daemon's timezone unless `schedule.timezone` is set) or a
+  structured rule (`{ "kind": "recurring", "recurrence": { "frequency":
+  "weekly", "daysOfWeek": ["tuesday"], "time": "11:00" } }`).
+  `/agents` is recurring-only — a one-time task belongs on
+  `POST /api/schedule` instead.
+- **`backend.tier`** is optional; omitted, the Agent inherits the
+  `agent.task` process default (medium). `backend.process_key`
+  defaults to `agent.task` — you don't need to set it.
+- **`limits`** defaults: 20 turns, $0.25 per run, 10-minute timeout.
+- Success returns `201 { "status": "created", "slug": ... }`. A taken
+  slug returns `409 slug_collision`; validation failures return `400`
+  with a field-level `issues` list.
+
+## Where to See Runs
+
+- **`/agents`** lists every Agent with its schedule, enable toggle,
+  7-day metrics, and last run.
+- **`/agents/<slug>`** is the detail page: the full definition, recent
+  execution history with results and cost, and a **Run now** button
+  (`POST /api/agents/<slug>/run-now`).
+- **Activity** logs each run alongside everything else the agent does.
+- Programmatically: `GET /api/agents/<slug>/executions`.
 
 ## Verification
 
-- Wait for the cron to fire; check Activity for the row tagged
-  `routine.custom.<slug>`.
+- Click **Run now** on the detail page (or wait for the schedule); an
+  execution row should appear with its result and cost.
 
 ## If It Fails
 
-- A cron that resolves to "never" (or is otherwise invalid): the
-  dialog shows the preview error and refuses to save it.
-- A prompt that hits the absolute-block guardrails: the routine fires
-  but the offending tool call is logged as `blocked_absolute` in the
+- `409 slug_collision` — pick a different ID; built-in Agent slugs are
+  reserved.
+- `400 invalid_definition` — fix the fields listed in `issues`.
+- `400 one_shot_not_supported` — `/agents` is recurring-only; use
+  `POST /api/schedule` for one-time work.
+- A prompt that hits the absolute-block guardrails: the run fires but
+  the offending tool call is logged as `blocked_absolute` in the
   action log.
 
+## Migrating From Custom Routines
+
+The legacy custom-routine format —
+`policies/routines/custom/<slug>.md` files with `cron:` frontmatter
+and a `## Checks` body — is retired and those files no longer fire.
+At the first daemon start after the upgrade, each valid file was
+converted **once** into a user Agent with the same cron, tier, budget,
+and enabled state; the `## Checks` body became the Agent's task
+prompt, and the source file was kept but marked inert
+(`enabled: false` plus a `migrated_to_agent: <slug>` marker). See
+[Custom Routines (Retired)](../features/routines/custom-routines.md)
+for collision and invalid-file handling.
+
 ## Related
 
-- [Custom Routines](../features/routines/custom-routines.md)
+- [Custom Routines (Retired)](../features/routines/custom-routines.md)
+- [Routines](../concepts/routines.md)
+- [ProcessKeys](../concepts/process-keys.md)
+- [Backends and tiers](../concepts/backends-and-tiers.md)

package/agent-assets/docs/guides/budget-and-cost-for-wiki.md

@@ -91,9 +91,11 @@ Per-file token approximation is script-aware: ~4 characters per token
 for Latin/prose, ~1.5 for majority-CJK files, with a 200-token floor
 per file so empty or one-line stubs still account for the fixed
 per-call overhead (system prompt, skills bundle, tool docs). The unit
-cost (`$0.003` per 1k tokens) matches Claude Sonnet 4.6's ~$3 /
-Mtoken input price. The bracket lets you see a worst case before
-approving.
+cost (`$0.003` per 1k tokens) matches Claude Sonnet 5's ~$3 /
+Mtoken standard input price. (An introductory $2 / Mtoken rate runs
+through 2026-08-31; the estimate lists the standard rate, while the
+SDK's billed `total_cost_usd` reflects the intro price during the
+window.) The bracket lets you see a worst case before approving.
 
 > The dashboard surfaces the top raw files by estimated token count,
 > so you can see which sources dominate the bill before approving.

package/agent-assets/docs/guides/change-which-model-handles-x.md

@@ -76,7 +76,7 @@ delegated routine onto Gemini to save Claude quota.
 
 To give the evening review deeper reasoning, set
 `routine.evening_review` → main `claude`, tier `high`. The next evening
-run resolves to **Opus 4.8** instead of the default Sonnet 4.6. The
+run resolves to **Opus 4.8** instead of the default Sonnet 5. The
 execution budget for that run also scales with the tier (high tier
 carries a larger turn / cost envelope than medium).
 

package/agent-assets/docs/guides/multiple-wikis-for-multiple-domains.md

@@ -196,7 +196,7 @@ vault on Opus 4.8 and a parenting journal on Haiku 4.5 at the same
 time, you cannot — the `wiki.ask` row resolves to one backend/model for
 every workspace. The pragmatic shape is:
 
-- Bind `wiki.ask` to its medium-tier default (Sonnet 4.6), a sensible
+- Bind `wiki.ask` to its medium-tier default (Sonnet 5), a sensible
   cross-workspace balance of cost and quality.
 - Keep cost differences per workspace through each workspace's own
   full-compile approval threshold (see above).

package/agent-assets/docs/guides/pause-the-agent.md

@@ -23,7 +23,7 @@ ask_examples:
   - Can I disable everything for a week?
 locale: en-US
 created: 2026-04-25
-updated: 2026-06-07
+updated: 2026-06-10
 keywords:
   - pause agent
   - stop agent
@@ -36,11 +36,10 @@ related:
   - features/messaging/bang-commands
   - concepts/routines
 ui_anchors:
-  - /settings/schedule
-  - /settings/routines
+  - /settings/hours
   - /agents
 config_keys:
-  - hourlyCheckEnabled
+  - activityScanEnabled
   - monthlyReviewEnabled
   - quietHoursStart
   - quietHoursEnd
@@ -63,7 +62,7 @@ DM `!stop` to the agent on any paired messaging app. This is the
 recommended way to go silent and the only one you need for most cases:
 
 - It pauses **every** cron-driven routine — morning, evening, weekly,
-  monthly, and the hourly check — not just one of them.
+  monthly, and the activity scan — not just one of them.
 - Non-command DMs are declined with a paused notice (no LLM cost)
   until you resume.
 - The paused state is persisted, so a daemon restart does **not**
@@ -76,26 +75,29 @@ Resume with `!start` whenever you want the agent active again. See
 
 ## Finer-grained control from the dashboard
 
-If you want to mute specific behaviour rather than pause everything, use
-`/settings/schedule`:
-
-1. **Disable the hourly check** — toggle `hourlyCheckEnabled` off. This
-   leaves the morning, evening, weekly, and monthly routines running.
-2. **Disable the monthly review** — toggle `monthlyReviewEnabled` off
-   (it ships off by default).
-3. **Silence notifications without pausing work** — set an extended
-   quiet hours window: e.g. `quietHoursStart: "00:00"`,
-   `quietHoursEnd: "23:59"`. Both fields take an `HH:MM` string.
-   Routines still run; they just don't notify you.
+If you want to mute specific behaviour rather than pause everything:
+
+1. **Disable the activity scan** — open `/agents/activity-scan` and click
+   **Disable**. This leaves the morning, evening, weekly, and monthly
+   routines running. (The agent's enable switch replaced the legacy
+   `activityScanEnabled` config key, now a deprecated fallback.)
+2. **Disable the monthly review** — open `/agents/monthly-review` and
+   click **Disable** (it ships disabled by default; the agent's enable
+   switch replaced the legacy `monthlyReviewEnabled` config key).
+3. **Silence notifications without pausing work** — on `/settings/hours`
+   ("Hours & Notifications"), set an extended quiet hours window: e.g.
+   `quietHoursStart: "00:00"`, `quietHoursEnd: "23:59"`. Both fields
+   take an `HH:MM` string. Routines still run; they just don't notify
+   you.
 
 Morning (fires at the day boundary, default 04:00), evening (18:00),
 and weekly (Fri 19:00) reviews each have a per-routine Enable/Disable
 toggle on the `/agents` page — open `/agents/<slug>` (e.g.
 `/agents/weekly-review`) and click Disable (a stop-warning confirmation
 appears for these system agents). To halt all of them at once, use
-`!stop` above instead. You can still edit each routine's instructions
-on `/settings/routines`, but that page does not turn the built-in
-reviews on or off.
+`!stop` above instead. Each routine's instructions (its rulebook) are
+edited on the same page's **Rulebook** tab
+(`/agents/<slug>?tab=rulebook`).
 
 ## Last resort: stop the daemon
 
@@ -115,7 +117,7 @@ temporary pause that survives across days, prefer `!stop`. Restart with
 
 - A routine still fires after `!stop`: confirm the pause registered by
   checking `!help` or the dashboard banner; re-send `!stop`.
-- A toggle on `/settings/schedule` did not take effect: confirm it
+- A setting on `/settings/hours` did not take effect: confirm it
   saved — the dashboard's "Save" button must be clicked.
 
 ## Related

package/agent-assets/docs/guides/reinstall-cleanly.md

@@ -46,6 +46,8 @@ related:
   - guides/migrate-machines
   - guides/pause-the-agent
   - glossary
+ui_anchors:
+  - /settings/danger-zone
 ---
 
 # Reinstall Cleanly

package/agent-assets/docs/guides/setup-wizard.md

@@ -29,7 +29,7 @@ ask_examples:
   - Where do I paste my API key?
 locale: en-US
 created: 2026-04-25
-updated: 2026-06-07
+updated: 2026-06-10
 keywords:
   - setup
   - wizard
@@ -57,8 +57,8 @@ ui_anchors:
   - /setup
   - /settings/models
   - /connections
-  - /settings/routines
-  - /settings/schedule
+  - /agents
+  - /settings/hours
 ---
 
 # Setup Wizard Walkthrough
@@ -143,7 +143,7 @@ subscription. Anthropic in particular currently prohibits using the
 Claude Agent SDK with a Claude Pro / Max subscription.
 
 Per-process model bindings are seeded with fixed defaults: **Claude
-Sonnet 4.6** (`claude-sonnet-4-6`) for owner-facing work and **Claude
+Sonnet 5** (`claude-sonnet-5`) for owner-facing work and **Claude
 Haiku 4.5** (`claude-haiku-4-5-20251001`) for delegated/simple
 polling. Opus (`claude-opus-4-8`) is registered but not seeded — opt
 in per row. There are no subscription-plan questions. Change the
@@ -188,12 +188,15 @@ character prompt referenced in Step 1 actually gets written.
 
 ## After the wizard
 
-Routines are **not** configured in the wizard. Edit the per-cadence
-rulebooks (morning / evening / weekly / hourly) and register custom cron
-routines post-setup on `/settings/routines`; the hourly-check master
-switch, active / quiet hours, and the monthly review live on
-`/settings/schedule`. Repositories are also added after setup, from
-Connections → Repositories.
+Routines are **not** configured in the wizard. Post-setup, each routine
+is an agent under `/agents`: edit the per-cadence rulebooks (morning /
+evening / weekly / activity scan) on the agent's Rulebook tab, create custom
+recurring agents from the New Agent dialog, set the activity-scan switch
+and cadence on `/agents/activity-scan`, and opt into the monthly review
+by enabling `/agents/monthly-review`. Quiet hours, timezone, and
+notification caps live on `/settings/hours` ("Hours & Notifications").
+Repositories are also added after setup, from Connections →
+Repositories.
 
 ## Verification
 

package/agent-assets/docs/reference/api.md

@@ -139,6 +139,17 @@ All three routes are `RiskTier.Autonomous`. `POST /api/feedback` server-restrict
 | Feedback consume | `POST /api/feedback/consume` | `feedback.ts` | `{ids: number[], lessonRef?}` → `{consumed, notFound}`. Marks signals consumed after a consolidation pass. |
 | Feedback lessons | `GET /api/feedback/lessons` | `feedback.ts` | Read-only lesson-store overview for the dashboard — global `agent` store plus every per-agent store on disk, with cap-utilisation metrics. |
 
+### Self-tuning
+
+Both routes are `RiskTier.Autonomous`. The weekly review's Recommend pre-step generates at most 3 bounded recommendations per cycle; verdicts may only reference the single-use ids the daemon generated for the **current** cycle (the pending blob is overwritten — and prior ids expired — every weekly run). Verdicts are always recorded and audited as `agent_actions.action_type='self_tuning.verdict'`, and rejections become `self_critique` feedback signals server-side.
+
+While `selfTuningEnabled=false` (the shipped default) the loop runs in **shadow mode**: nothing is ever actuated and responses carry `shadow: true` with an empty `applied` array. With the flag on (**live mode**), newly-recorded `apply` verdicts actuate per key namespace: config knobs go through the `applyConfigUpdates` chokepoint (bounds enforced there), write a `runtime_state.self_tuning:<key>` ledger entry, audit `self_tuning.applied`, and DM the owner one line with the `!revert tuning` undo hint; `notification:<type>` (R2) applies are recorded as lesson guidance only; `recurring_schedules:<id>` (R4) applies become an owner DM suggestion — never an automatic flip. Retried POSTs are `duplicate` per id and never re-actuate. A daily auto-revert monitor re-measures each applied change after its 7-day verify window and reverts on regression (audit `self_tuning.reverted`, 28-day re-proposal cool-down); clean windows are stamped `self_tuning.verified`.
+
+| Group | Path | Source | Purpose |
+|---|---|---|---|
+| Tuning verdicts | `POST /api/tuning/verdicts` | `tuning.ts` | `{cycleId, verdicts: [{id, verdict: apply\|reject\|defer, reason}]}` → per-id `recorded`/`duplicate`/`conflict` results plus `shadow`, `applied[]`, and `actuationFailures[]`. Idempotent per id (first verdict wins); 400 atomically on any unknown id; 409 on a missing or expired cycle. |
+| Tuning pending | `GET /api/tuning/pending` | `tuning.ts` | The current cycle's recommendations + recorded verdicts, for the owner's validation and the dashboard. `shadow` reflects the live flag. |
+
 ### Docs and wiki
 
 | Group | Path | Source | Purpose |

package/agent-assets/docs/reference/config.md

@@ -36,14 +36,14 @@ keywords:
   - EDITABLE_RUNTIME_KEY_TUPLE
   - RESTART_REQUIRED_KEY_TUPLE
   - dayBoundaryHour
-  - hourlyCheckIntervalMinutes
+  - activityScanIntervalMinutes
   - quietHoursStart
   - quietHoursEnd
   - executeTimeoutMinutes
   - autonomousDailyCostCapUsd
   - allowedToolsOverride
   - voiceTranscriptionEnabled
-  - hourlyCheckPrePassFreshnessMinutes
+  - activityScanPrePassFreshnessMinutes
   - vaultMode
   - PA_DATA_DIR
   - PA_API_PORT
@@ -52,9 +52,9 @@ config_keys:
   - timezone
   - primaryLanguage
   - vaultMode
-  - hourlyCheckEnabled
-  - hourlyCheckIntervalMinutes
-  - hourlyCheckPrePassFreshnessMinutes
+  - activityScanEnabled
+  - activityScanIntervalMinutes
+  - activityScanPrePassFreshnessMinutes
   - quietHoursStart
   - quietHoursEnd
   - maxNotificationsPerHour
@@ -75,7 +75,7 @@ api_endpoints:
   - PATCH /api/config
   - POST /api/voice/install
 ui_anchors:
-  - /settings/advanced
+  - /settings/infrastructure
   - /settings/models
 created: 2026-04-25
 updated: 2026-06-08
@@ -131,19 +131,26 @@ case-sensitive.
 | `primaryLanguage` | BCP-47 | Output language for DMs, journal, and Obsidian writes. Templates stay English-headered. |
 | `vaultMode` | enum | Where context lives — `plain` (default; `<dataDir>/context`) or `obsidian` (an external Obsidian vault). |
 
-### Hourly check and gate
+### Activity scan and gate
+
+The first five keys are **deprecated fallbacks**: the activity-scan
+cadence, active window, min-observations threshold, and enable switch
+moved onto the activity-scan agent (`/agents/activity-scan`, Definition
+tab → Cadence card; Enable/Disable). The keys are still accepted by
+`PATCH /api/config` but no longer surfaced in the dashboard; values
+resolve agent override → legacy config key → built-in default.
 
 | Key | Type | Notes |
 |---|---|---|
-| `hourlyCheckEnabled` | boolean | Default `true`. |
-| `hourlyCheckIntervalMinutes` | number | Default `60`. |
-| `hourlyCheckActiveStartHour` | 0–23 | Default `4`. |
-| `hourlyCheckActiveEndHour` | 1–24 | End-exclusive; `24` ≡ midnight. |
-| `hourlyCheckMinObservations` | number | Default `1`. |
-| `hourlyCheckStage2Enabled` | boolean | cost-reduction-structural §B Stage 2 toggle. |
-| `hourlyCheckHeartbeatHours` | number | Quiet-day heartbeat cadence. |
-| `hourlyCheckLowSignalPendingCeiling` | number | Low-signal ceiling before forcing dispatch. |
-| `hourlyCheckPrePassFreshnessMinutes` | number | Layer-1 freshness window — `harvestForGate` skips a per-integration fetch if `runtime_state.pre_pass_last_run:<key>` is fresher. |
+| `activityScanEnabled` | boolean | **Deprecated fallback** — the agent's enable switch on `/agents/activity-scan` is the source of truth. Default `true`. |
+| `activityScanIntervalMinutes` | number | **Deprecated fallback** — edit on `/agents/activity-scan`. Default `60`. |
+| `activityScanActiveStartHour` | 0–23 | **Deprecated fallback** — edit on `/agents/activity-scan`. Default `4`. |
+| `activityScanActiveEndHour` | 1–24 | **Deprecated fallback** — edit on `/agents/activity-scan`. End-exclusive; `24` ≡ midnight. |
+| `activityScanMinObservations` | number | **Deprecated fallback** — edit on `/agents/activity-scan`. Default `1`. |
+| `activityScanStage2Enabled` | boolean | cost-reduction-structural §B Stage 2 toggle. |
+| `activityScanHeartbeatHours` | number | Quiet-day heartbeat cadence. |
+| `activityScanLowSignalPendingCeiling` | number | Low-signal ceiling before forcing dispatch. |
+| `activityScanPrePassFreshnessMinutes` | 0–480 | Default `30`. Layer-1 freshness window — `harvestForGate` skips a per-integration fetch if `runtime_state.pre_pass_last_run:<key>` is fresher. Cap widened 240 → 480 for the self-tuning R1 ladder (120/240/360/480). |
 
 ### Notifications and quiet hours
 
@@ -248,6 +255,7 @@ page. Defaults and ranges below are enforced in
 | Key | Type | Notes |
 |---|---|---|
 | `feedbackLearningEnabled` | boolean | Default `true` (env `FEEDBACK_LEARNING_ENABLED`). Master kill-switch for the whole loop — capture, consolidation, and injection. |
+| `selfTuningEnabled` | boolean | Default `false` (env `SELF_TUNING_ENABLED`). Actuation gate for the self-tuning review cycle. While `false`, the loop runs in shadow mode: the weekly review still receives `<tuning_recommendations>` and records verdicts via `POST /api/tuning/verdicts`, but no config change is ever applied. With the flag on, apply verdicts for config knobs actuate through the bounded config chokepoint — one owner DM per applied change, `!revert tuning` undoes the latest, and a daily monitor auto-reverts any change whose 7-day verify metrics regressed. Flip only after ≥2 clean shadow cycles (SELF_TUNING_REVIEW_CYCLE_DESIGN.md §7 shadow→live gate). |
 | `feedbackPromotionThreshold` | 1–10 | Default `2` (env `FEEDBACK_PROMOTION_THRESHOLD`). Weighted-evidence threshold a behavioral / self-critique lesson must clear before it becomes injectable. |
 | `feedbackLessonMaxBytesGlobal` | 1024–32768 | Default `8192` (env `FEEDBACK_LESSON_MAX_BYTES_GLOBAL`). Byte cap for `policies/agent-lessons.md`. |
 | `feedbackLessonMaxBytesPerAgent` | 512–16384 | Default `4096` (env `FEEDBACK_LESSON_MAX_BYTES_PER_AGENT`). Byte cap for each `policies/agents/<slug>/lessons.md`. |
@@ -266,11 +274,13 @@ shift the whole day, change `dayBoundaryHour` instead.
 | `routine.morning_routine` | Daily at `dayBoundaryHour` (default 04:00). |
 | `routine.evening_review` | Daily at `18:00` local. |
 | `routine.weekly_review` | Friday `19:00` local (one hour after the evening review). |
-| `routine.monthly_review` | Last day of the month at `18:00` local, but **disabled by default** (`monthlyReviewEnabled = false`). |
+| `routine.monthly_review` | Last day of the month at `18:00` local, but **disabled by default** — opt in by enabling the monthly-review agent at `/agents/monthly-review` (`agents.enabled` is the single switch; the legacy `monthlyReviewEnabled` config key is a deprecated fallback, carried forward once by a boot-time reconcile). |
 
-The hourly check is the one autonomous routine with a configurable
-cadence (`hourlyCheckIntervalMinutes`) and active window
-(`hourlyCheckActiveStartHour` / `…ActiveEndHour`).
+The activity scan is the one autonomous routine with a configurable
+cadence and active window — edited on the activity-scan agent's page
+(`/agents/activity-scan`, Definition tab → Cadence card); the legacy
+`activityScanIntervalMinutes` / `activityScanActiveStartHour` /
+`…ActiveEndHour` keys remain as deprecated fallbacks.
 
 ## Restart-Required Keys
 

package/agent-assets/docs/reference/keyboard-shortcuts.md

@@ -23,7 +23,7 @@ ask_examples:
   - What does pressing "?" do in the dashboard?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-10
 keywords:
   - shortcut
   - hotkey
@@ -65,7 +65,7 @@ regardless of where focus sits.
 ## Examples
 
 - Press `Cmd+K`, type "timezone", and hit Enter to jump straight to the
-  Timezone field on `/settings/schedule`.
+  Timezone field on `/settings/hours`.
 - On any screen, press `?` to ask a question about what you are looking
   at; the help slide-over opens pre-scoped to that page's doc.
 - While drafting a message in `/chat`, press `Cmd+Enter` to send without