@aitne-sh/aitne 0.1.0

package/agent-assets/docs/features/lifestyle/receipts.md

@@ -0,0 +1,71 @@
+---
+schema_version: 1
+slug: features/lifestyle/receipts
+title: Receipts
+id: receipts
+category: features
+summary: |
+  A SQLite-backed log of receipt and invoice attachments the Gmail
+  observer detects, plus an export path that saves them into the
+  operator's external Obsidian vault for tax / reimbursement tracking.
+section: lifestyle
+tags:
+  - lifestyle
+  - receipts
+status: stable
+ask_examples:
+  - Where are my receipts stored?
+  - How do I save a receipt to my Obsidian vault?
+  - What does the receipts table track?
+locale: en-US
+created: 2026-04-25
+updated: 2026-04-26
+related:
+  - features/lifestyle/reading
+  - features/lifestyle/travel-bookings
+  - features/integrations/mail
+---
+
+# Receipts
+
+## In One Sentence
+
+Receipts are PDF / image attachments the Gmail observer flags as
+receipts or invoices; their metadata lives in the `receipts` SQLite
+table, and the agent can export the original file into your external
+Obsidian vault on request.
+
+## What It Does
+
+- The Gmail observer auto-detects receipt / invoice attachments while
+  scanning travel-booking and document mail.
+- Each detection inserts a row into the `receipts` table
+  (`provider_msg_id`, `attachment_id`, `filename`, `mime_type`,
+  `size_bytes`, `category`, `obsidian_path`, `saved_at`, `account_id`).
+- The agent surfaces summaries via the `/api/receipts` and
+  `/api/receipts/summary` HTTP routes.
+- On request, the agent downloads the attachment via
+  `POST /api/receipts/:id/download`, writes it into the external
+  Obsidian vault under `receipts/YYYY/MM/<merchant>-<date>.<ext>`, and
+  patches the row's `obsidian_path` / `saved_at` columns.
+
+There is no Markdown context file for receipts; the durable record is
+the SQLite row plus the optional Obsidian copy.
+
+## Where in the Dashboard
+
+There is no dedicated tab today. Receipts surface inline when you ask
+for them in chat (e.g. "what receipts haven't I saved yet?"). The
+underlying API is documented in `agent-assets/skills/receipts/SKILL.md`.
+
+## Configuration
+
+The detection runs as part of the Gmail observer; see
+[Mail](../integrations/mail.md). The Obsidian save path follows the
+external vault convention `receipts/YYYY/MM/<merchant>-<date>.<ext>`.
+
+## Related
+
+- [Reading](reading.md)
+- [Travel Bookings](travel-bookings.md)
+- [Mail](../integrations/mail.md) — the source observer.

package/agent-assets/docs/features/lifestyle/travel-bookings.md

@@ -0,0 +1,44 @@
+---
+schema_version: 1
+slug: features/lifestyle/travel-bookings
+title: Travel Bookings
+id: travel-bookings
+category: features
+summary: |
+  A lightweight log of trips, flights, hotels, and confirmation
+  numbers. The agent appends to it from confirmation emails or DMs.
+section: lifestyle
+tags:
+  - lifestyle
+  - travel
+status: stable
+ask_examples:
+  - How do I log a flight?
+  - Will the agent remind me about my upcoming trip?
+locale: en-US
+created: 2026-04-25
+updated: 2026-04-25
+related:
+  - features/lifestyle/travel-time
+---
+
+# Travel Bookings
+
+## In One Sentence
+
+A trip log the agent appends to from confirmation emails and DMs,
+referenced by the morning routine on travel days.
+
+## What It Does
+
+- Captures trip dates, modes, and confirmation numbers.
+- Surfaces in the morning routine on the day of departure.
+- Cross-references the travel-time skill for door-to-airport math.
+
+## Where in the Dashboard
+
+Surfaces inline in chat and via the morning briefing on travel days.
+
+## Related
+
+- [Travel Time](travel-time.md)

package/agent-assets/docs/features/lifestyle/travel-time.md

@@ -0,0 +1,52 @@
+---
+schema_version: 1
+slug: features/lifestyle/travel-time
+title: Travel Time
+id: travel-time
+aliases:
+  - door to door
+  - eta
+category: features
+summary: |
+  A skill that estimates door-to-door travel time given an origin
+  and destination — used by schedule-approaching reminders for
+  events with location.
+section: lifestyle
+tags:
+  - lifestyle
+  - travel
+  - skill
+status: stable
+ask_examples:
+  - How long will it take me to get to the airport?
+  - Does the agent know about traffic?
+locale: en-US
+created: 2026-04-25
+updated: 2026-04-25
+related:
+  - features/lifestyle/travel-bookings
+  - features/operations/schedule-approaching
+---
+
+# Travel Time
+
+## In One Sentence
+
+A skill the agent calls to estimate door-to-door travel time before
+a calendar event with a location.
+
+## What It Does
+
+- Reads origin (current location, configured home/work) and
+  destination (event location).
+- Returns a typical-time estimate with mode (drive, transit, walk).
+- Used by `schedule-approaching` reminders to lead-time the alert.
+
+## Where in the Dashboard
+
+There is no operator surface for the travel-time data itself; the
+estimates appear inline in event reminders and morning routines.
+
+## Related
+
+- [Schedule Approaching](../operations/schedule-approaching.md)

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

@@ -0,0 +1,105 @@
+---
+schema_version: 1
+slug: features/memory-files/agent-journal
+title: agent/journal.md
+id: agent-journal
+aliases:
+  - journal
+  - agent journal
+  - agent log
+category: features
+summary: |
+  The agent's append-only log of decisions, retros, and judgement
+  calls. Distinct from Activity (which is action-shaped) — the journal
+  is reflection-shaped.
+section: memory-files
+tags:
+  - memory
+  - journal
+  - reflection
+status: stable
+ask_examples:
+  - What is the agent journal?
+  - Where does the agent log its own decisions?
+  - How is the journal different from Activity?
+locale: en-US
+created: 2026-04-25
+updated: 2026-04-25
+keywords:
+  - journal
+  - retros
+  - decisions
+  - reflection
+related:
+  - features/routines/evening-review
+  - features/routines/weekly-review
+  - features/operations/activity-and-conversations
+ui_anchors:
+  - /connections/journal
+  - /settings/journal
+context_files:
+  - agent/journal.md
+---
+
+# agent/journal.md
+
+## In One Sentence
+
+`agent/journal.md` is the agent's own running diary — what it noticed,
+what it tried, what it would do differently — appended (never
+rewritten) so a long timeline accumulates.
+
+## What It Does
+
+The journal is the place the agent writes about its own work in the
+first person. Each entry has:
+
+- A timestamp.
+- A short context line (which routine / conversation prompted it).
+- The reflection itself.
+
+Unlike Activity, the journal is opinion-shaped. The evening review
+adds the day's reflections; the weekly retro reads them back to
+look for patterns; the monthly retro distills them into trend notes.
+
+## When It Runs / How It Is Triggered
+
+- **Evening review** adds the largest chunk — what worked, what was
+  surprising, what felt off.
+- **Weekly review** appends a retro that quotes prior journal entries
+  to find a thread.
+- **In-the-moment** entries fire when the agent notices something
+  worth flagging during reactive work.
+
+## What It Outputs
+
+- An ever-growing append-only file at
+  `~/.personal-agent/context/agent/journal.md`.
+- A linked-from-roadmap section when an entry tied a project to a new
+  decision.
+
+## Where in the Dashboard
+
+- **Connections → Journal** is the read view of the file.
+- **Settings → Journal** controls retention and which routines
+  contribute (currently always-on for evening / weekly / monthly).
+
+## Configuration
+
+There is no per-entry configuration. The file is plain Markdown — you
+can hand-edit, prune, or git-version it like any other context file.
+
+## When Something Goes Wrong
+
+- A journal that **stops growing** points at the evening review not
+  running. See [Evening Review](../routines/evening-review.md).
+- A journal that **looks duplicated** usually means a routine retried
+  after a fallback. The agent's own anti-duplicate check is best-effort,
+  not bulletproof — manual prune is fine.
+
+## Related
+
+- [Evening Review](../routines/evening-review.md) — the daily writer.
+- [Weekly Review](../routines/weekly-review.md) — the consumer.
+- [Activity](../operations/activity-and-conversations.md) — the
+  action-shaped audit log, distinct from the journal.

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

@@ -0,0 +1,56 @@
+---
+schema_version: 1
+slug: features/memory-files/projects
+title: projects/ files
+id: projects
+aliases:
+  - project files
+  - projects directory
+category: features
+summary: |
+  One Markdown file per active project under projects/. Each captures
+  the project's why, status, key links, and the per-project log of
+  agent activity. Cross-linked from the roadmap.
+section: memory-files
+tags:
+  - memory
+  - projects
+status: stable
+ask_examples:
+  - Where do I find the per-project files?
+  - How does the agent decide a project is active?
+locale: en-US
+created: 2026-04-25
+updated: 2026-04-25
+related:
+  - features/memory-files/roadmap
+context_files:
+  - projects/<slug>.md
+---
+
+# projects/ Files
+
+## In One Sentence
+
+One Markdown file per active project; the agent appends notes,
+decisions, and external references over the project's lifetime.
+
+## What It Does
+
+- Captures the project's purpose, status, links, recent decisions.
+- Surfaces in the morning routine when the project is active and
+  has Preparation Timeline rows.
+- Becomes the canonical reference the agent quotes from in DMs.
+
+## When It Runs / How It Is Triggered
+
+Read on demand. Written when the operator asks the agent to
+remember something project-specific.
+
+## Where in the Dashboard
+
+- **Knowledge → Context Files → projects/**.
+
+## Related
+
+- [roadmap.md](roadmap.md)

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

@@ -0,0 +1,61 @@
+---
+schema_version: 1
+slug: features/memory-files/roadmap
+title: roadmap.md
+id: roadmap
+aliases:
+  - roadmap
+  - long term goals
+  - preparation timeline
+category: features
+summary: |
+  roadmap.md captures long-running goals plus Preparation Timeline
+  rows that fire on specific days. The morning routine walks the
+  roadmap each day to surface items whose offsets fire.
+section: memory-files
+tags:
+  - memory
+  - planning
+  - core
+status: stable
+ask_examples:
+  - What is the roadmap file?
+  - What is a Preparation Timeline?
+  - How does the morning routine use the roadmap?
+locale: en-US
+created: 2026-04-25
+updated: 2026-04-25
+related:
+  - features/routines/morning-routine
+  - features/memory-files/projects
+context_files:
+  - roadmap.md
+---
+
+# roadmap.md
+
+## In One Sentence
+
+A multi-week plan: each goal carries dates and Preparation Timeline
+rows the morning routine fires on the day of.
+
+## What It Does
+
+- Captures long-running goals beyond a single day.
+- Preparation Timeline rows like "T-7 days: book hotel" surface in
+  the morning routine on the right day.
+- Cross-links to project files for deeper context.
+
+## When It Runs / How It Is Triggered
+
+Read by the morning routine; updated by the operator (or the agent
+on request).
+
+## Where in the Dashboard
+
+- **Knowledge → Context Files → roadmap.md**.
+
+## Related
+
+- [Morning Routine](../routines/morning-routine.md)
+- [Projects](projects.md)

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

@@ -0,0 +1,112 @@
+---
+schema_version: 1
+slug: features/memory-files/schedule
+title: daily/ files
+id: schedule-files
+aliases:
+  - schedule directory
+  - daily directory
+  - per-date schedule
+  - daily/YYYY-MM-DD.md
+category: features
+summary: |
+  Per-date synthesis files (daily/YYYY-MM-DD.md) the morning routine
+  writes from yesterday.md plus the SQLite event log. They are the
+  read-only archive each day rolls into; the dashboard's Schedule view
+  also reads them.
+section: memory-files
+tags:
+  - memory
+  - schedule
+  - core
+status: stable
+ask_examples:
+  - Where does the agent store the day's archived plan?
+  - Why is yesterday still showing up in /schedule?
+  - How do I hand-edit a day's plan?
+locale: en-US
+created: 2026-04-25
+updated: 2026-04-26
+keywords:
+  - schedule
+  - daily
+  - per-date
+  - calendar snapshot
+related:
+  - features/routines/morning-routine
+  - features/memory-files/today
+  - concepts/agent-day
+ui_anchors:
+  - /schedule
+context_files:
+  - daily/<date>.md
+---
+
+# daily/ Files
+
+## In One Sentence
+
+`daily/YYYY-MM-DD.md` is the morning routine's synthesized archive of
+the agent-day; the dashboard's Schedule view and downstream routines
+read from this directory.
+
+> **Heads up — directory renamed.** The mechanical
+> `schedule/YYYY-MM-DD.md` copy was retired in B-007. The morning
+> routine now synthesizes `daily/YYYY-MM-DD.md` from `yesterday.md`
+> plus the SQLite event log instead. Hand-pruning the old `schedule/`
+> directory is safe.
+
+## What It Does
+
+Each file under `~/.personal-agent/context/daily/` corresponds to one
+**agent day** (the file name uses the agent-day date, not the calendar
+date — see [Agent Day](../../concepts/agent-day.md)). The morning
+routine writes the file shortly after rolling `today.md` →
+`yesterday.md`. It contains:
+
+- Calendar events from connected calendars.
+- Mail-driven items the agent flagged for that day.
+- Preparation Timeline rows from `roadmap.md` whose offset fired that day.
+- Carryover items the agent did not finish.
+
+The synthesis is template-driven and reads from the in-process DB
+snapshot of the closing `today.md` plus the day's event records, so
+late edits made directly to `today.md` after rotation cannot retroactively
+rewrite a previous `daily/` file.
+
+## When It Runs / How It Is Triggered
+
+The morning routine writes today's file once at start-of-day. Other
+routines read it but do not rewrite.
+
+## What It Outputs
+
+- A Markdown file with sections for events, preparations, and
+  carryover items.
+- A `last_updated` line so the dashboard knows freshness.
+
+## Where in the Dashboard
+
+- **Schedule (`/schedule`)** reads adjacent `daily/<date>.md` files
+  to render the past/today/upcoming columns. Hand-edits are picked up
+  on the next view refresh.
+
+## Configuration
+
+There is nothing to configure on these files directly; they are a
+side effect of the morning routine. Retention is unlimited — old
+files accumulate. A manual prune (`rm daily/2025-*.md`) is safe.
+
+## When Something Goes Wrong
+
+- An **empty** daily file usually means the morning routine did not
+  run. See [Morning Routine Didn't Run](../../troubleshooting/morning-routine-didnt-run.md).
+- A view that **shows yesterday** is the day-boundary subtlety:
+  before `dayBoundaryHour`, the agent day is still yesterday. See
+  [Agent Day](../../concepts/agent-day.md).
+
+## Related
+
+- [Morning Routine](../routines/morning-routine.md) — the writer.
+- [today.md](today.md) — the live, hand-editable surface for the
+  current agent day.

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

@@ -0,0 +1,73 @@
+---
+schema_version: 1
+slug: features/memory-files/today
+title: today.md
+id: today-md
+aliases:
+  - today
+  - day plan
+category: features
+summary: |
+  today.md is the live, hand-editable plan for the current agent day.
+  The morning routine writes it; the operator and the agent both
+  append to it during the day.
+section: memory-files
+tags:
+  - core
+  - memory
+status: stable
+ask_examples:
+  - What is in today.md?
+  - Can I edit today.md by hand?
+  - Why does today.md keep getting rewritten?
+locale: en-US
+created: 2026-04-25
+updated: 2026-04-25
+keywords:
+  - today
+  - day plan
+related:
+  - features/routines/morning-routine
+  - features/memory-files/schedule
+  - concepts/agent-day
+context_files:
+  - today.md
+---
+
+# today.md
+
+## In One Sentence
+
+The single live file that captures the day's plan, log, tasks, and
+hand-off — rebuilt by the morning routine, appended-to by everything
+else during the day.
+
+## What It Does
+
+Sections:
+
+- **User Schedule** — calendar events.
+- **Tasks** — today's external + agent-tracked tasks.
+- **Agent Plan** — what the agent intends to work on today.
+- **Agent Log** — what actually happened.
+- **Handoff** — what carries to tomorrow.
+
+## When It Runs / How It Is Triggered
+
+- The morning routine fully rewrites it.
+- The hourly check appends short observations under Agent Log.
+- The evening review reads it before writing the journal.
+
+## Where in the Dashboard
+
+- **Knowledge → Context Files → today.md** to view and edit.
+
+## When Something Goes Wrong
+
+- An empty today.md after the morning hour: see [Morning Routine
+  Didn't Run](../../troubleshooting/morning-routine-didnt-run.md).
+
+## Related
+
+- [Morning Routine](../routines/morning-routine.md)
+- [schedule/ files](schedule.md)

package/agent-assets/docs/features/memory-files/user-profile.md

@@ -0,0 +1,81 @@
+---
+schema_version: 1
+slug: features/memory-files/user-profile
+title: user/profile.md
+id: user-profile
+aliases:
+  - user.md
+  - user/profile.md
+  - user profile
+  - about-me
+category: features
+summary: |
+  user/profile.md is the agent's stable profile of the operator — role,
+  focus areas, preferences, names of important people. The agent reads
+  it on every session and appends with the operator's permission.
+section: memory-files
+tags:
+  - memory
+  - profile
+  - core
+status: stable
+ask_examples:
+  - What is user/profile.md?
+  - How do I tell the agent something about me?
+  - Will the agent change my profile without asking?
+locale: en-US
+created: 2026-04-25
+updated: 2026-04-25
+related:
+  - getting-started/04-first-day
+  - concepts/memory-model
+context_files:
+  - user/profile.md
+  - user/people.md
+  - user/work.md
+  - user/expertise.md
+  - user/personal.md
+  - user/goals.md
+---
+
+# user/profile.md
+
+## In One Sentence
+
+A stable, mostly hand-edited profile of you — the agent reads it
+every session and appends only with explicit permission.
+
+## What It Does
+
+- Captures who you are, what you do, who matters in your life.
+- Pinned at the top of every session prompt so the agent has the
+  same baseline understanding turn-to-turn.
+- The companion files in the `user/` directory split the dossier into
+  topic-shaped slices: `user/people.md`, `user/work.md`,
+  `user/expertise.md`, `user/personal.md`, `user/goals.md`. The agent
+  loads them on demand instead of inlining everything.
+
+## When It Runs / How It Is Triggered
+
+Read continuously. Written only when the operator says "remember
+that…" or during a profile sweep routine
+(`routine.user_profile_sweep`).
+
+## Where in the Dashboard
+
+- **Knowledge → Context Files → user/profile.md** to view and edit.
+  The other `user/*.md` slices are listed alongside.
+- **Knowledge → Upload** to seed `user/*.md` from a Markdown / text
+  file — useful for migrating an existing profile out of ChatGPT,
+  Gemini, Obsidian, or Notion. See
+  [Import a Knowledge File](../../guides/import-knowledge-file.md).
+
+## When Something Goes Wrong
+
+- The agent forgets something it should remember: append it to
+  the appropriate `user/*.md` slice by hand.
+
+## Related
+
+- [Memory Model](../../concepts/memory-model.md)
+- [Import a Knowledge File](../../guides/import-knowledge-file.md)