@aitne-sh/aitne 0.1.9 → 0.1.10

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/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

@@ -52,7 +52,7 @@ context_files:
 api_endpoints:
   - POST /api/knowledge/import
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 related:
   - getting-started/02-first-steps
   - getting-started/03-what-can-this-do
@@ -273,7 +273,7 @@ Shortest path from zero to that:
    - 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
+3. **Watch the next firing in Agent Log** 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

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
@@ -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).

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

@@ -27,7 +27,7 @@ ask_examples:
   - What does the pre-compile snapshot do?
 locale: en-US
 created: 2026-05-12
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - wiki budget
   - wiki cost
@@ -126,7 +126,7 @@ before `!compile full`** enabled, Aitne runs:
 git -C <vault> status --porcelain
 # must be empty — dirty trees refuse the operation entirely
 git -C <vault> add -A
-git -C <vault> commit -m "aitne wiki: pre-compile snapshot <ISO-8601-ts>"
+git -C <vault> commit --allow-empty -m "aitne wiki: pre-compile snapshot <ISO-8601-ts>"
 ```
 
 before the compile session starts. The commit message is

package/agent-assets/docs/guides/connect-a-new-mail-account.md

@@ -27,7 +27,7 @@ ask_examples:
   - How do I connect an Outlook mailbox?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - mail
   - imap
@@ -48,6 +48,7 @@ api_endpoints:
   - /api/config/mail/app-password
 config_keys:
   - enabledMailProviders
+  - mailPollIntervalSeconds
 context_files:
   - state/today.md
 ---
@@ -96,7 +97,8 @@ kind authenticates differently:
 4. Save. Registration succeeds regardless of the enabled-providers
    setting (`enabledMailProviders`); the account goes live only when
    you flip its **Enable** toggle on the mail card.
-5. The first poll runs within a minute of being enabled.
+5. The account is picked up on the next mail poll tick (default every
+   180 seconds, configurable via `mailPollIntervalSeconds`).
 
 ## Verification
 

package/agent-assets/docs/guides/explore-with-trace-and-connect.md

@@ -30,7 +30,7 @@ ask_examples:
   - How do I run !trace against a non-default wiki workspace?
 locale: en-US
 created: 2026-05-12
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - "!trace"
   - "!connect"
@@ -187,6 +187,7 @@ Every report is a regular wiki file under `30_outputs/`. You can:
 ## Cost Envelope
 
 Both commands run at Sonnet medium tier with a default $1.00
-spend cap per run, identical to `!ask`. The 7-day cost rollup on
-**Settings → Wiki** breaks the spend out per command so you can
-see where the budget went.
+spend cap per run, identical to `!ask`. The **Settings → Wiki**
+overview shows a single 7-day cost stat across all wiki commands;
+to see per-command spend, filter the timeline on `/wiki/timeline`
+by `wiki.trace` or `wiki.connect`.

package/agent-assets/docs/guides/install-and-run.md

@@ -29,7 +29,7 @@ ask_examples:
   - How do I install the aitne npm package?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - install
   - first run
@@ -60,7 +60,7 @@ through the setup wizard.
   Google (`GEMINI_API_KEY` / `GOOGLE_API_KEY`). API keys are the
   recommended and provider-supported way to run Aitne. If you skip
   the key, Aitne falls back to the corresponding CLI's local
-  subscription login (`claude`, `codex login`, `gemini auth`); see
+  subscription login (`claude auth login`, `codex login`, `gemini`); see
   [Costs and Quotas](../concepts/costs-and-quotas.md) for the trade-
   offs and the provider policies that apply.
 - The CLI binary for whichever backend you pick (Claude Code, Codex

package/agent-assets/docs/guides/maintain-wiki-health.md

@@ -28,7 +28,7 @@ ask_examples:
   - What is a taxonomy candidate?
 locale: en-US
 created: 2026-05-12
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - wiki health
   - wiki lint
@@ -68,7 +68,7 @@ notes itself.
 ## When to Run
 
 `!lint` runs on the `wiki.lint` process key (medium tier — Sonnet
-by default, $1.00 budget envelope) and never changes your notes.
+by default, $0.50 budget envelope) and never changes your notes.
 Run it whenever you want a snapshot of wiki health. A practical
 cadence:
 

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: 2026-05-28
+updated: 2026-06-07
 keywords:
   - pause agent
   - stop agent
@@ -38,6 +38,7 @@ related:
 ui_anchors:
   - /settings/schedule
   - /settings/routines
+  - /agents
 config_keys:
   - hourlyCheckEnabled
   - monthlyReviewEnabled
@@ -88,10 +89,13 @@ If you want to mute specific behaviour rather than pause everything, use
    Routines still run; they just don't notify you.
 
 Morning (fires at the day boundary, default 04:00), evening (18:00),
-and weekly (Fri 18:00) reviews have no per-routine enable toggle in the
-dashboard — to stop them, use `!stop` above. You can still edit each
-routine's instructions on `/settings/routines`, but that page does not
-turn them on or off.
+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.
 
 ## Last resort: stop the daemon
 

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: 2026-05-28
+updated: 2026-06-07
 keywords:
   - setup
   - wizard
@@ -58,6 +58,7 @@ ui_anchors:
   - /settings/models
   - /connections
   - /settings/routines
+  - /settings/schedule
 ---
 
 # Setup Wizard Walkthrough
@@ -187,10 +188,12 @@ character prompt referenced in Step 1 actually gets written.
 
 ## After the wizard
 
-Routines are **not** configured in the wizard. Enable and schedule the
-morning / evening / weekly reviews and the hourly check post-setup on
-`/settings/routines`. Repositories are also added after setup, from
-Settings → Connections → Repositories.
+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.
 
 ## Verification
 

package/agent-assets/docs/guides/use-an-existing-obsidian-vault.md

@@ -26,7 +26,7 @@ ask_examples:
   - Why is Split greyed out?
 locale: en-US
 created: 2026-05-12
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - external vault
   - existing obsidian vault
@@ -68,11 +68,11 @@ vs Split**.
 
 Open **`/settings/wiki`** in the dashboard (or open `/wiki` and follow
 the **Enable Wiki** button — both land on the same page). If you have
-no workspace yet, the page shows two CTAs:
+no workspace yet, the page shows two options:
 
-- **Enable Internal Workspace** — uses the daemon-owned root.
-- **Probe & Create External** — points at the path you choose with
-  the folder picker.
+- **Internal** → **Enable internal wiki** — uses the daemon-owned root.
+- **Existing Obsidian vault** → **Use this folder** — points at the
+  path you choose with the folder picker.
 
 ### Picking the path
 
@@ -110,7 +110,7 @@ levels:
   an existing wiki layout is detected, the wizard will surface the
   Adopt / Migrate decision in Step 3.
 
-The **Probe & Create External** button is greyed out while the banner
+The **Use this folder** button is greyed out while the banner
 is an error so you cannot fire a workspace-create that the daemon
 already knows will fail.
 

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

@@ -28,7 +28,7 @@ ask_examples:
   - How do I list registered backends?
 locale: en-US
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-08
 keywords:
   - API
   - REST
@@ -54,7 +54,7 @@ The daemon serves a single Hono app on `127.0.0.1:PA_API_PORT` (default
 `8321`). Almost all endpoints are mounted under `/api/*`; the lone
 exception is the GitHub webhook receiver, mounted at root `/webhook/github`.
 **Source of truth:** `packages/daemon/src/api/server.ts` (`createApp`)
-registers most route groups, with two post-compose mounts in
+registers most route groups, with one post-compose mount in
 `packages/daemon/src/bootstrap/api.ts` (the docs corpus + docs-QA, wired
 only after the indexer handle exists). Each group lives in its own file
 or directory under `packages/daemon/src/api/routes/`.
@@ -93,13 +93,13 @@ callers pass it as `Authorization: Bearer <token>`.
 | Activity sources | `/api/activity-sources/*` | `activity-sources.ts` | Activity feed sources. |
 | Entities | `/api/entities/*` | `entities.ts` | Entity registry CRUD. |
 | SoT bindings | `/api/sot-bindings/*` | `sot-bindings.ts` | Source-of-truth bindings (vault ↔ daemon). |
-| Voice | `/api/voice/*` | `voice.ts` | Voice transcript cache + transcribe-on-demand. |
+| Voice | `/api/voice/*` | `voice.ts` | Whisper model install / status / weight-removal opt-in surface for the dashboard. |
 
 ### Integrations
 
 | Group | Path | Source | Purpose |
 |---|---|---|---|
-| Mail | `/api/mail/*` | `mail.ts`, `mail-search.ts` | Multi-provider mail proxy (Gmail / Outlook / Yahoo / iCloud / IMAP) + FTS5 local search. |
+| Mail | `/api/mail/*` | `mail/` | Multi-provider mail proxy (Gmail / Outlook / Yahoo / iCloud / IMAP) + FTS5 local search. |
 | Calendar | `/api/calendar/*` | `calendar.ts` | Google Calendar proxy. |
 | Apple Calendar | `/api/apple-calendar/*` | `apple-calendar.ts` | macOS Calendar.app bridge. |
 | Notion | `/api/notion/*` | `notion.ts` | Notion proxy. |
@@ -107,7 +107,7 @@ callers pass it as `Authorization: Bearer <token>`.
 | Git | `/api/git/*`, `/api/git-accounts/*` | `git.ts`, `git-accounts.ts`, `git-templates.ts` | Read-only git proxy (`/api/git/{log,diff,show}`), repo templates (`/api/git/templates/*`), and git-account CRUD (`/api/git-accounts/*`). |
 | Repositories | `/api/repositories/*` | `repositories.ts` | Unified repository CRUD (replaces split Git/GitHub settings). |
 | GitHub | `/api/github/*`, `POST /webhook/github` | `github.ts` | GitHub proxy and webhook receiver (mounted under `/`, not `/api`). |
-| Integrations | `/api/integrations/*` | `integrations.ts`, `integrations-reconcile.ts` | Integration mode CRUD (`direct \| delegated \| native \| disabled`), live probe endpoint, mode reconciliation. |
+| Integrations | `/api/integrations/*` | `integrations/`, `integrations-reconcile.ts` | Integration mode CRUD (`direct \| delegated \| native \| disabled`), live probe endpoint, mode reconciliation. |
 | Delegated sync | `/api/delegated/*`, `/api/delegated-sync/*` | `delegated.ts`, `delegated-sync.ts` | Delegated worker control + opt-in cadence config. |
 | MCP | `/api/mcp/*` | `mcp.ts` | Per-session MCP materializer. |
 
@@ -129,6 +129,16 @@ callers pass it as `Authorization: Bearer <token>`.
 | Books | `/api/books/*` | `books.ts` | Reading-list CRUD. |
 | Travel bookings | `/api/travel-bookings/*` | `travel-bookings.ts` | Travel-booking CRUD. |
 
+### Feedback learning
+
+All three routes are `RiskTier.Autonomous`. `POST /api/feedback` server-restricts `source` to `explicit` / `self_critique` — `behavioral` signals are daemon-only (written by `SignalDetector`) and a `behavioral` body returns 400.
+
+| Group | Path | Source | Purpose |
+|---|---|---|---|
+| Feedback | `POST /api/feedback` | `feedback.ts` | Record an explicit or self-critique feedback signal. Dedups on `(scope_type, scope_ref, summary)` within 10 min. When `feedbackLearningEnabled=false` returns `200 {disabled:true}` without recording. |
+| 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. |
+
 ### Docs and wiki
 
 | Group | Path | Source | Purpose |

package/agent-assets/docs/reference/cli-commands.md

@@ -28,7 +28,7 @@ ask_examples:
   - How do I check my install with aitne doctor?
 locale: en-US
 created: 2026-04-27
-updated: 2026-05-28
+updated: 2026-06-07
 keywords:
   - aitne start
   - aitne stop
@@ -95,7 +95,7 @@ needed.
 | `aitne open` | Open the dashboard root in the default browser. |
 | `aitne doctor` | Install-health checks (Node, ports, OS keychain, backend CLIs, native bindings, …). |
 | `aitne audit [--since 24h] [--type X] [--result failed]` | Show the agent action log; flags filter by time, action type, result, or backend. `--json` for machine-readable. |
-| `aitne run-now <job>` | Fire a daemon-internal maintenance job on demand. The only supported job today is `roadmap_maintenance`. Reads the API token from the macOS Keychain, so this command is macOS-only. |
+| `aitne run-now <job>` | Fire a daemon-internal maintenance job on demand. The only supported job today is `roadmap_maintenance`. Reads the API token from the OS secret store (macOS Keychain, Windows DPAPI, Linux libsecret, or the encrypted file fallback), so it works on every supported platform. |
 | `aitne verify [target]` | Run post-launch verification for a shipped design surface (e.g. `evening-review-slimdown`). |
 | `aitne version [--json]` | Print version, Node version, install path, last build time. |
 | `aitne update [--check]` | Print the npm command to upgrade. `--check` makes one network call to compare against the latest published version. |
@@ -150,7 +150,7 @@ and the cost-gate / approval semantics.
 |---|---|---|
 | `PA_DATA_DIR` | `~/.personal-agent` | Where logs, the SQLite DB, context Markdown, and prompts live. |
 | `PA_API_PORT` | `8321` | Daemon HTTP port. |
-| `PA_DASHBOARD_PORT` | `3000` | Dashboard port. |
+| `PA_DASHBOARD_PORT` | `8322` | Dashboard port. |
 
 All runtime state — PIDs, logs, SQLite DB, context Markdown, prompts —
 lives under `PA_DATA_DIR`, **not** inside the repo.

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

@@ -78,7 +78,7 @@ ui_anchors:
   - /settings/advanced
   - /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
@@ -125,7 +125,7 @@ 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. |
@@ -237,6 +237,23 @@ 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. |
+| `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

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/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
@@ -182,6 +182,11 @@ 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
@@ -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
@@ -558,6 +564,8 @@ 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` |
 | `plans/projects/_index` · `plans/projects/*` | `PUT`, `PATCH` |
@@ -570,6 +578,7 @@ 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

@@ -41,7 +41,7 @@ keywords:
   - delegated_task
   - gmail_classify
 created: 2026-04-25
-updated: 2026-05-28
+updated: 2026-06-07
 config_keys:
   - monthlyReviewEnabled
   - delegatedTaskHeavyEnabled
@@ -80,7 +80,7 @@ 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.weekly_review` | Friday 19:00 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 |

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:
@@ -63,7 +63,8 @@ type (`browser-task`, 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. |
 | `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. |
@@ -86,7 +87,7 @@ type (`browser-task`, on owner DMs). The table below is the canonical roster.
 | `today` | Read or write `state/today.md` — morning routines, hourly checks, 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 +101,4 @@ 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`.