@aitne-sh/aitne 0.1.9 → 0.1.11

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
@@ -75,10 +75,10 @@ api_endpoints:
   - PATCH /api/config
   - POST /api/voice/install
 ui_anchors:
-  - /settings/advanced
+  - /settings/infrastructure
   - /settings/models
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-08
 related:
   - reference/api
   - reference/cli-commands
@@ -93,7 +93,7 @@ The full `AgentConfig` schema lives in
 `packages/shared/src/editable-config-keys.ts` govern what is editable
 and when:
 
-- **`EDITABLE_RUNTIME_KEY_TUPLE`** — the ~80 keys mutable at runtime
+- **`EDITABLE_RUNTIME_KEY_TUPLE`** — the ~130 keys mutable at runtime
   via `PATCH /api/config`. Both the daemon and the dashboard import
   from this tuple so the accepted-key set is enforced at compile time
   in both packages.
@@ -117,7 +117,7 @@ Anything not in those tuples must be set via env or restart.
 ## Selected Keys
 
 A representative slice of `EDITABLE_RUNTIME_KEY_TUPLE` — the full list
-of ~80 keys is in `editable-config-keys.ts`. Names below are exact and
+of ~130 keys is in `editable-config-keys.ts`. Names below are exact and
 case-sensitive.
 
 ### Identity and timezone
@@ -125,25 +125,32 @@ case-sensitive.
 | Key | Type | Notes |
 |---|---|---|
 | `agentDisplayName` | string | What the agent calls itself in DMs. |
-| `character` | string | Persona key (one of the entries in `agent-assets/agent-profiles/`). |
+| `character` | string | Free-text user-defined communication style / persona (max 1000 chars). When non-empty, rendered as a `## Character (user-defined)` block into each backend's instruction file. The agent profile itself is selected by ProcessKey, not by this key. |
 | `timezone` | IANA tz | Empty falls back to the system tz. |
 | `dayBoundaryHour` | 0–9 | Default `4`. Controls the agent-day rollover (must be an early-morning hour). |
 | `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
 
@@ -237,6 +244,24 @@ case-sensitive.
 | `advisorEnabled` | boolean | SDK advisor toggle. |
 | `advisorModel` | string / null | Model id; default `null`. Validated against `ADVISOR_ALLOWED_MODELS`, which the SDK pins to `claude-sonnet-4-6` and `claude-opus-4-6` only. Newer Opus generations (`claude-opus-4-7`, `claude-opus-4-8`) are silently skipped by the SDK advisor path — see `docs/advisor.md`. |
 
+### Feedback learning
+
+The feedback learning loop (capture → nightly consolidation → injection of
+durable lessons). All six knobs are runtime-editable via `PATCH /api/config`,
+surfaced by `GET /config`, and tunable from the dashboard `/settings/lessons`
+page. Defaults and ranges below are enforced in
+`packages/daemon/src/settings/runtime-settings.ts`.
+
+| 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`. |
+| `feedbackLessonStaleDays` | 7–365 | Default `60` (env `FEEDBACK_LESSON_STALE_DAYS`). Lessons whose `last=` date is older are pruned, except `kind=constraint` (durable). |
+| `feedbackSignalRetentionDays` | 30–365 | Default `180` (env `FEEDBACK_SIGNAL_RETENTION_DAYS`). Consumed `feedback_signals` rows older than this are swept. |
+
 ## Routine Schedule Times Are Not Configurable
 
 The morning, evening, weekly, and monthly routines fire at fixed times
@@ -249,11 +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/disallowed-tools.md

@@ -25,7 +25,7 @@ ask_examples:
   - Why can't the agent read my .env or SSH keys?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - disallowedTools
   - deniedTools
@@ -42,8 +42,9 @@ related:
 # Disallowed Tools
 
 There are two distinct deny layers — the **absolute-block layer**
-(non-overridable) and the **default strict-mode list** (in `config.ts`,
-relaxable in Allow mode or via `allowedToolsOverride`).
+(non-overridable) and the **default strict-mode list** (`DEFAULT_DISALLOWED_TOOLS`
+in `src/settings/runtime-settings.ts`, relaxable in Allow mode or via
+`allowedToolsOverride`).
 
 ## Absolute-block layer (cannot be widened past)
 
@@ -78,7 +79,8 @@ managed-Chromium chokepoints above).
 
 ## Default strict-mode list (relaxable)
 
-`config.ts > disallowedTools` ships with additional defaults that the
+`DEFAULT_DISALLOWED_TOOLS` (in `src/settings/runtime-settings.ts`, the
+seed for `config.disallowedTools`) ships with additional defaults that the
 operator can widen out of via `allowedToolsOverride` or by switching
 to Allow mode. These include `Bash(chmod *)`, `Bash(chown *)`,
 `Bash(git push --force *)`, `Bash(git reset --hard *)` and a handful

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

package/agent-assets/docs/reference/knowledge-layout.md

@@ -34,7 +34,7 @@ ask_examples:
   - Which files can the agent write to?
 locale: en-US
 created: 2026-05-18
-updated: 2026-05-28
+updated: 2026-06-08
 keywords:
   - context
   - knowledge
@@ -63,7 +63,7 @@ process_keys:
   - routine.evening_review
   - routine.weekly_review
   - routine.monthly_review
-  - routine.hourly_check
+  - routine.activity_scan
   - routine.roadmap_refresh
 config_keys:
   - dayBoundaryHour
@@ -171,7 +171,7 @@ the write-permission whitelist in `packages/daemon/src/api/routes/context/permis
 │   │           └── <slug>.md
 │   └── dossiers/                   Per-flow carry-forward state (agent-owned)
 │       ├── _index.md
-│       └── <flow>.md               One per routine (hourly/morning/evening/…)
+│       └── <flow>.md               One per routine (activity-scan/morning/evening/…)
 │
 └── policies/                       USER-authored config + rules
     ├── _index.md
@@ -182,18 +182,23 @@ the write-permission whitelist in `packages/daemon/src/api/routes/context/permis
     ├── journal-export.md           Inclusion / exclusion rules for exporting journal/daily/
     ├── integrations.md             Integration-mode snapshot (daemon-rendered,
     │                               chokidar-watched at this new path)
+    ├── agent-lessons.md            Feedback Learning Loop global lessons (lazy)
+    ├── agents/                     User-authored Agent definitions (lazy)
+    │   └── <slug>/
+    │       ├── agent.md
+    │       └── lessons.md          Per-agent Feedback Learning Loop lessons (lazy)
     ├── management-captures/        One captured policy per file
     │   ├── _index.md
     │   └── <slug>.md
     ├── routines/                   Per-cadence checklist rulebooks
     │   ├── _index.md
-    │   ├── hourly.md               Extension checks for routine.hourly_check
+    │   ├── activity-scan.md         Extension checks for routine.activity_scan
     │   ├── morning.md               …for routine.morning_routine
     │   ├── evening.md               …for routine.evening_review
     │   ├── weekly.md                …for routine.weekly_review
     │   ├── monthly.md               …for routine.monthly_review
     │   └── custom/
-    │       └── <slug>.md           User-defined cron routines
+    │       └── <slug>.md           Retired custom routines (inert; migrated to user Agents)
     └── skills/                     User-registered skills (lazy directory)
         └── <slug>/
             └── SKILL.md            Built-in skills stay in agent-assets/skills/ (read-only)
@@ -237,7 +242,8 @@ runner merges that file into the reconciler block.)
 The current agent-day's working view. Daemon-managed structure:
 
 ```
-# Today
+# YYYY-MM-DD (day-of-week)   — line 1 is the canonical agent-day date
+> Day type: …               — parsed by every event handler
 ## User Schedule    — events for the day (from calendar observers)
 ## User Tasks       — what you need to do today
 ## Agent Plan       — what the agent intends to do today
@@ -380,15 +386,19 @@ the built-in steps.
 | File | Cadence | Process key |
 |---|---|---|
 | `_index.md` | — | (navigation) |
-| `hourly.md` | every hour (during active window) | `routine.hourly_check` |
+| `activity-scan.md` | every 2 h default (during active window) | `routine.activity_scan` |
 | `morning.md` | 04:00 daily | `routine.morning_routine` |
 | `evening.md` | evening | `routine.evening_review` |
 | `weekly.md` | Friday | `routine.weekly_review` |
 | `monthly.md` | month-end | `routine.monthly_review` |
-| `custom/<slug>.md` | user cron | `routine.custom.<slug>` |
+| `custom/<slug>.md` | — (retired) | `routine.custom.<slug>` (historical) |
 
-`custom/<slug>.md` is the only routine path that supports `DELETE` —
-when removed, the scheduler unregisters the cron job on the next reload.
+`custom/<slug>.md` files no longer fire — at the first start after the
+upgrade each valid one was converted once into a user Agent at
+`policies/agents/<slug>/agent.md`, and the source was marked inert
+(`enabled: false` + `migrated_to_agent:`; see
+[Custom Routines (Retired)](../features/routines/custom-routines.md)).
+The path still supports `DELETE` so the inert files can be cleaned up.
 
 ---
 
@@ -424,7 +434,7 @@ routine to run without re-scanning the full vault.
 | File | Process key |
 |---|---|
 | `_index.md` | (navigation) |
-| `hourly.md` | `routine.hourly_check` |
+| `activity-scan.md` | `routine.activity_scan` |
 | `morning.md` | `routine.morning_routine`, `routine.morning_routine_today` |
 | `evening.md` | `routine.evening_review` |
 | `weekly.md` | `routine.weekly_review` |
@@ -558,8 +568,10 @@ listed is read-only via the API.
 | `state/profile-questions` · `state/activity/*` | `PUT`, `PATCH` |
 | `identity/_index` · `identity/*` | `PUT`, `PATCH` |
 | `policies/_index` · `policies/*` (top-level files) | `PUT`, `PATCH` |
+| `policies/agent-lessons` | `PUT`, `PATCH` (Feedback Learning Loop global lessons store) |
+| `policies/agents/{slug}/{file}` | `PUT`, `PATCH`, `DELETE` (user-authored Agent definitions) |
 | `policies/routines/_index` · `policies/routines/*` | `PUT`, `PATCH` |
-| `policies/routines/custom/*` | `PUT`, `PATCH`, `DELETE` |
+| `policies/routines/custom/*` | `PUT`, `PATCH`, `DELETE` (legacy — files are inert and no longer fire) |
 | `plans/projects/_index` · `plans/projects/*` | `PUT`, `PATCH` |
 | `plans/projects/_active` | `PUT` (the Obsidian Bases view) |
 | `knowledge/repos/{slug}/overview` · `journal/repos/{slug}/{date}` | `PUT`, `PATCH` |
@@ -570,6 +582,7 @@ listed is read-only via the API.
 | `state/inbox/*` · `state/scratch/*` | `PUT`, `PATCH`, `DELETE` |
 | `journal/agent` | `PUT` once (create-only), then `PATCH` (append) |
 | `policies/management-captures/_index` · `policies/management-captures/*` | `PUT`, `PATCH` |
+| `research/*` | `PUT`, `PATCH` (browser-history research-cluster journals) |
 
 > Legacy URL forms (`/api/context/today.md`, `/api/context/user/profile`, `/api/context/rules/management`, `/api/context/agent/journal`, etc.) are normalized to the class-prefixed canonical paths in-process by `core/context-vault-aliases.ts` before any of the above checks run. Normalization is not a redirect (no HTTP 3xx) so legacy `curl -X PUT/PATCH` callers keep working. The alias bridge lives for one minor release after PR-6's content sweep lands. <!-- drift-allow -->
 

package/agent-assets/docs/reference/process-keys.md

@@ -22,7 +22,7 @@ tags:
 status: stable
 ask_examples:
   - List all the ProcessKeys
-  - What is the default tier for hourly check?
+  - What is the default tier for activity scan?
   - Which ProcessKeys are configurable from the dashboard?
   - What is routine.fetch_window used for?
 locale: en-US
@@ -41,11 +41,11 @@ keywords:
   - delegated_task
   - gmail_classify
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 config_keys:
   - monthlyReviewEnabled
   - delegatedTaskHeavyEnabled
-  - hourlyCheckIntervalMinutes
+  - activityScanIntervalMinutes
   - dayBoundaryHour
 api_endpoints:
   - POST /api/browser-task
@@ -62,7 +62,7 @@ related:
 # ProcessKeys
 
 A **ProcessKey** identifies the kind of work being dispatched (an owner DM,
-the morning routine, an hourly check, …). The dispatcher passes a ProcessKey
+the morning routine, an activity scan, …). The dispatcher passes a ProcessKey
 to the `BackendRouter`, which resolves it to a `{ main, fallback }` backend
 plus an execution tier — the dispatcher never picks a model directly.
 
@@ -80,15 +80,15 @@ The **default tier** column maps to a model size, not a specific id:
 | `routine.morning_routine_journal` | Stage B of the morning-routine pipeline — authors `journal/daily/<yesterday>.md` from the daemon-prepared journal skeleton. | lite | yes |
 | `routine.today_refresh` | Calendar-drift-triggered (calendar change touching today's items; 5-min dedup, fires ~30s later) — drift-refresh of `state/today.md` | medium | yes |
 | `routine.evening_review` | Daily at 18:00 local (fixed) | medium | yes |
-| `routine.weekly_review` | Friday 18:00 local (fixed) | medium | yes |
-| `routine.monthly_review` | Monthly cadence (gated OFF by default — kill switch `monthlyReviewEnabled` in runtime settings). The routine itself is off by default, but its backend/tier binding is still configurable. | medium | yes |
-| `routine.hourly_check` | Every `hourlyCheckIntervalMinutes` (default 60) inside the active window | medium | yes |
-| `routine.hourly_check.triage` | Stage 2 triage gate of every hourly check | lite | yes |
+| `routine.weekly_review` | Friday 19:00 local (fixed) | medium | yes |
+| `routine.monthly_review` | Monthly cadence (gated OFF by default — opt in by enabling the monthly-review agent at `/agents/monthly-review`; the legacy `monthlyReviewEnabled` config key is a deprecated fallback). The routine itself is off by default, but its backend/tier binding is still configurable. | medium | yes |
+| `routine.activity_scan` | Every N interval minutes (default 60) inside the active window — cadence set on `/agents/activity-scan`; legacy key `activityScanIntervalMinutes` is a deprecated fallback | medium | yes |
+| `routine.activity_scan.triage` | Stage 2 triage gate of every activity scan | lite | yes |
 | `routine.fetch_window` | Pre-pass fetcher spawned before each main routine | lite | yes |
 | `routine.user_profile_sweep` | Periodic agent-day profile summarization pass | medium | no |
 | `routine.roadmap_refresh` | Periodic roadmap re-derivation (NOT in `ROUTINE_WINDOWS` — no `routine.fetch_window` pre-pass; the synthesis session itself drives the native-mode MCP fan-out) | medium | yes |
 | `routine.skill_curation` | Background skill-curation / overlay refinement loop (cron cadence picked at `/settings/self-learning`) | medium | yes |
-| `routine.custom.<slug>` | Operator-defined recurrence (see [Custom Routines](../features/routines/custom-routines.md)) | configurable | yes |
+| `routine.custom.<slug>` | Retired — legacy custom routines no longer fire; they were converted to user Agents running under `agent.task` (see [Custom Routines (Retired)](../features/routines/custom-routines.md)). Seen only in historical Activity rows. | — | no |
 | `message.dm` | Owner DM | medium | yes |
 | `message.mention` | @-mention in a paired Slack channel where the agent is invited (DMs are `message.dm`; Telegram/WhatsApp groups are filtered out) | medium | yes |
 | `dashboard.chat` | `/chat` send | medium | yes |

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

@@ -34,7 +34,7 @@ keywords:
   - wiki skill
   - notify skill
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 ui_anchors:
   - /knowledge?tab=skills
 process_keys:
@@ -59,12 +59,16 @@ related:
 Aitne ships a fixed set of built-in skills the agent loads per session. Most
 are always available; a few are **conditional** — loaded only when a gating
 flag is set (`gmail-lifestyle`, `managed-tasks`) or only for a specific event
-type (`browser-task`, on owner DMs). The table below is the canonical roster.
+type (`browser-task` / `background-task` / `background-task-reply`, on owner
+DMs). The table below is the canonical roster.
 
 | Slug | Purpose |
 |---|---|
-| `agent-actions` | Read the agent action log (`agent_actions` table) for retrospective audits. |
+| `agent-actions` | Self-report structured metadata (dayType, anomalies, inbox stats, files-touched) into the session's own `agent_actions` row so daemon-side consumers read structured data instead of parsing prose. Loaded near the end of morning-routine / dispatcher sessions. |
+| `agent-create` | Register a durable, named recurring Agent that fires on a cron cadence via `POST /api/agents`. For ongoing autonomous work (not one-time reminders → `schedule`, not background app-data fetches → `managed-tasks`). Conditional skill loaded on owner DMs / mentions when the message looks like a recurring-work request (gated by `agentCreateActiveForDm`). |
 | `attach` | Attach a generated or downloaded file to the agent's reply when the user expects a file artifact. |
+| `background-task` | Hand a long-running / open-ended task (deep research, a multi-repo CI audit, "monitor X over time", a bulk compile) to the detached background runner via `POST /api/background-task`. Composes a self-contained brief, sets the notification policy (`always` / `if_significant` / `silent`), POSTs, acks, and ends the turn; reads `GET /api/background-task/:id` for follow-up detail. Loaded on `message.received.dm` + `message.received.dm_first`. |
+| `background-task-reply` | Relay the owner's natural-language answer to a background task that parked on a clarifying question (`awaiting_user`) into a structured `POST /api/background-task/:id/clarify` call. No-op unless a task is parked and the conversation shows the question was asked. Loaded on `message.received.dm`. |
 | `browser-history` | Read normalised browser activity through `/api/browser-history/*`. Used by research-cluster journal updates, accept-path dispatches, owner pulls of shopping / reload traces, and the morning research summary. Never reads browser SQLite or profile dirs directly. |
 | `browser-history-respond` | Bridge the owner's natural-language reply to a research-offer DM ("dig deeper" / "summarise") into a structured `/api/browser-history/offers/<slug>/{accept,decline}` call. |
 | `browser-task` | Drive managed Chromium for open-ended browser tasks the user describes in DM. POSTs to `/api/browser-task` with a natural-language description; relays sub-agent clarifications back through DM. Loaded only on `message.received.dm`. |
@@ -83,10 +87,10 @@ type (`browser-task`, on owner DMs). The table below is the canonical roster.
 | `roadmap` | Read / write `plans/roadmap.md` (cross-request write lock). |
 | `schedule` | Schedule future agent wake-ups and DMs via the daemon (writes `agent_schedule` and `recurring_schedules` rows). |
 | `scheduled-managed-task` | Surface and act on Managed Tasks that are due now. |
-| `today` | Read or write `state/today.md` — morning routines, hourly checks, DMs that need a today snapshot. |
+| `today` | Read or write `state/today.md` — morning routines, activity scans, DMs that need a today snapshot. |
 | `user-interview` | Manage the profile-interview queue at `state/profile-questions.md`; ask one question at a time. |
 | `user-profile` | Record user facts — identity, people, work, expertise, habits, goals — into the `identity/*` slices (`profile.md`, `people.md`, `work.md`, …). |
-| `wiki` | Build and maintain the personal wiki workspace — `!ingest` / `!compile` / `!ask` / `!lint` / `!trace` / `!connect`. |
+| `wiki-*` | Build and maintain the personal wiki workspace — `!ingest` / `!compile` / `!ask` / `!lint` / `!trace` / `!connect`. Split into per-process sub-skills under `agent-assets/skills/wiki/` (`wiki-vault-rules`, `wiki-ingest`, `wiki-compile`, `wiki-ask`, `wiki-lint`, `wiki-trace`, `wiki-connect`, `wiki-graduate`), each loaded for its matching `wiki.*` ProcessKey. |
 
 ## How skills are sourced
 
@@ -100,4 +104,4 @@ A subset of these skills' sections (knowledge layout, routing tables, search
 recipes, etc.) is refined at runtime through JSON **overlays** maintained by
 the skill-curation loop. The seed files in `agent-assets/skills/` are never
 rewritten — overlays are applied at session-init by the `SkillsCompiler` and
-live under `<dataDir>/overlays/<skill>/<section-id>.json`.
+live under `<dataDir>/skill-curation-overlays/<slug>/<section-id>.json`.

package/agent-assets/docs/troubleshooting/auth-failed.md

@@ -23,7 +23,7 @@ ask_examples:
   - The auth-health pill went red, what now?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - auth failed
   - auth error
@@ -60,8 +60,8 @@ api_endpoints:
    on a healthy install. Re-paste the key on `/settings/models`.
 2. **Subscription-fallback login expired** when no API key was
    registered (the daemon was running on the CLI's local login —
-   `claude`, `codex login`, `gemini auth` — and that session timed
-   out). The recommended fix is to register an API key.
+   `claude auth login`, `codex login`, `gemini` — and that session
+   timed out). The recommended fix is to register an API key.
 3. **Account-level scope change** at the provider (key disabled,
    project deleted, billing suspended). For cloud-provider auth
    (Bedrock / Vertex / Foundry for Claude, Vertex AI for Gemini),
@@ -87,13 +87,14 @@ re-probes immediately — no restart needed.
 **If the backend is on the subscription fallback:** the recommended
 fix is to register an API key on `/settings/models`. The same picker
 also exposes cloud-provider auth — Bedrock / Vertex / Foundry for
-Claude, Vertex AI for Gemini. (Codex Azure OpenAI is not offered here;
-it needs a `~/.codex/config.toml` the env-mirroring path cannot write,
-so Codex stays direct-key only.)
+Claude, Vertex AI for Gemini, and Azure OpenAI for Codex. (Codex Azure
+OpenAI needs a `config.toml` in addition to env vars; the daemon writes
+a managed one under `<dataDir>/codex-home/` and points `CODEX_HOME`
+there, leaving your `~/.codex/` untouched.)
 
 If you cannot or do not want to register a key, re-run the
-corresponding CLI login (`claude`, `codex login`, `gemini auth`) and
-the daemon picks up the new credentials on the next probe. Some
+corresponding CLI login (`claude auth login`, `codex login`, `gemini`)
+and the daemon picks up the new credentials on the next probe. Some
 backends also expose an in-dashboard device-code recovery flow
 (`recovery/start` → `recovery/code`) reachable from the pill's
 recovery hint. Note that subscription auth is not provider-supported

package/agent-assets/docs/troubleshooting/dashboard-shows-degraded.md

@@ -13,9 +13,8 @@ category: troubleshooting
 summary: |
   A red "Daemon degraded" banner appears above every page when the daemon
   enters degraded mode. This almost always means your Obsidian-style primary
-  vault is unreachable (path moved, drive unplugged, or not yet seeded), or a
-  context migration is in progress. While degraded, every context write is
-  refused with HTTP 503.
+  vault is unreachable (path moved, drive unplugged, or not yet seeded). While
+  degraded, every context read AND write is refused with HTTP 503.
 section: troubleshooting
 status: stable
 tags:
@@ -29,7 +28,7 @@ ask_examples:
   - Why are context writes being refused with 503?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - degraded
   - degraded banner
@@ -62,8 +61,10 @@ related:
   followed by the offending path.
 - An **Open Management Mode** button on the right of the banner (links to
   Settings → Management Mode).
-- Any routine or skill that writes a context file fails: the context API
-  returns **HTTP 503** for every `POST`/`PUT`/`PATCH`/`DELETE` while degraded.
+- Any routine or skill that touches a context file fails: while degraded the
+  context API returns **HTTP 503** for every request — reads (`GET`) as well as
+  writes (`POST`/`PUT`/`PATCH`/`DELETE`) — so the agent never reads or writes a
+  stale fallback location.
 
 ## What "Degraded" Actually Means
 
@@ -83,15 +84,21 @@ The `reason` in the banner is one of:
 | `primary_vault_unreachable`    | The configured vault path doesn't exist, isn't a directory, or isn't writable (e.g. an external drive was unplugged). |
 | `primary_vault_not_configured` | Vault mode is Obsidian but no `primaryVaultPath` is set. |
 | `primary_vault_missing_content`| The path is reachable but doesn't carry the expected vault markers (it was never seeded / restructured). |
-| `migration_in_progress`        | A context-vault migration (`/api/setup/migrate-context`) is running. Writes are gated until it finishes; reads still work. This one clears itself. |
+
+A context-vault migration (`POST /api/setup/migrate-context`) is a **separate**
+state, not a degraded reason — it does **not** raise this banner. During a
+migration the daemon engages a context-write gate (`migration_in_progress`):
+writes return HTTP 503 while reads still work, `/api/health` stays
+`"status":"ok"`, and the gate clears itself when the migration finishes.
 
 ## Diagnostic Steps
 
 1. **Read the banner.** The `reason` and `path` tell you most of the story.
 2. `aitne logs` — look for `Vault health probe entered degraded mode`; the
    logged `reason` matches the banner.
-3. If the reason is `migration_in_progress`, **wait** — the migration releases
-   the write gate when it completes; do not restart mid-migration.
+3. If a context-vault migration is running (write-gate `migration_in_progress`
+   rather than the banner), **wait** — the migration releases the write gate
+   when it completes; do not restart mid-migration.
 4. Otherwise the issue is your vault path. Confirm it exists and is writable:
    - `ls -ld "<path-from-banner>"` — the directory must exist.
    - `df -h "<path-from-banner>"` — confirm the volume is mounted with free

package/agent-assets/docs/troubleshooting/messaging-not-pairing.md

@@ -22,7 +22,7 @@ tags:
 status: stable
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - magic phrase
   - owner channel
@@ -85,7 +85,7 @@ All secrets are single-use and expire after **5 minutes**.
 
 ## Diagnostic steps
 
-1. On `/connections/messaging`, click **Regenerate phrase** (Slack /
+1. On `/connections/messaging`, click **Generate pairing phrase** (Slack /
    Discord) or re-open the QR / deep link (Telegram / WhatsApp) so you
    start a fresh 5-minute window.
 2. For Slack / Discord, send **only** the four words — no surrounding