Merge remote-tracking branch 'origin/main' into screens

# Conflicts:
#	.claude/settings.local.json
#	CLAUDE.md
#	bolt_pet/controller.py

.claude/settings.local.json

@@ -29,7 +29,30 @@
       "Bash(QT_QPA_PLATFORM=offscreen .venv/bin/python -c ' *)",
       "Bash(git push *)",
       "Bash(git remote *)",
-      "Bash(grep -v '^$')"
+      "Bash(grep -v '^$')",
+      "Bash(.venv/bin/pip install *)",
+      "Bash(QT_QPA_PLATFORM=offscreen .venv/bin/python *)",
+      "Bash(python3 *)",
+      "Bash(.venv/bin/pytest tests/test_monitors.py -q)",
+      "Bash(QT_QPA_PLATFORM=offscreen .venv/bin/pytest tests/test_pet_window_features.py -q)",
+      "Bash(git fetch *)",
+      "Bash(git switch *)",
+      "Bash(git add *)",
+      "Bash(git merge *)",
+      "Bash(echo \"=== EXIT: $? ===\")",
+      "Bash(git commit *)",
+      "Bash(QT_QPA_PLATFORM=offscreen /root/Documents/bolt-pet/.venv/bin/pytest tests/ -q)",
+      "Bash(.venv/bin/pytest tests/test_desk_api.py tests/test_desk_files.py tests/test_desk_voice.py tests/test_desk_status.py tests/test_desk_keys.py tests/test_desk_guild_action.py tests/test_desk_admin.py tests/test_desk_billing_auth.py -q)",
+      "Bash(docker inspect *)",
+      "Bash(python3 -m json.tool)",
+      "Bash(docker restart bolt *)",
+      "Bash(curl -s -m 5 \"http://localhost:5002/desk/health\")",
+      "Bash(python3 -c ' *)",
+      "Bash(QT_QPA_PLATFORM=offscreen /root/Documents/bolt-pet/.venv/bin/pytest /home/themajesticmagician/Documents/Bolt-Pet/tests/ -q)",
+      "Bash(docker exec bolt *)",
+      "Bash(QT_QPA_PLATFORM=offscreen /root/Documents/bolt-pet/.venv/bin/pytest /home/themajesticmagician/Documents/Bolt-Pet/tests/test_file_ops.py -q)",
+      "Bash(grep -rn *)",
+      "Bash(git ls-tree *)"
     ]
   }
 }

.env.example

@@ -40,6 +40,17 @@ ELEVENLABS_VOICE_ID=
 #VAD_SILENCE_END_SEC=1.2
 #VAD_MAX_UTTERANCE_SECONDS=15
 #VAD_MIN_UTTERANCE_SECONDS=0.4
+#VAD_GRACE_SECONDS=4            # how long to wait for you to start talking
+
+# ── Follow-up listening (optional) ──────────────────────────────────────────
+# When a reply ends on a question, the pet keeps listening for your answer
+# instead of dropping back to idle and making you say the wake word again.
+# FOLLOW_UP_MAX_TURNS caps how many question-and-answer rounds can chain
+# without you re-triggering it (0 = no cap) — a stop on runaway loops if the
+# server ends every reply with "?" and the mic keeps feeding it noise.
+#FOLLOW_UP_LISTEN=true
+#FOLLOW_UP_MAX_TURNS=3
+#FOLLOW_UP_GRACE_SECONDS=7      # longer than VAD_GRACE_SECONDS: you were asked something
 
 # ── Pet window (optional) ───────────────────────────────────────────────────
 #PET_SIZE=160
@@ -102,6 +113,30 @@ ELEVENLABS_VOICE_ID=
 # error?" has a referent. Text only — no screenshots leave the machine.
 #SCREEN_CONTEXT=true
 
+# ── Monitors (optional) ─────────────────────────────────────────────────────
+# Tacks a one-line summary of your screen layout onto each utterance (how
+# many, their sizes, which one the pet is standing on) so Bolt can decide to
+# `petctl jump 2` without asking what you've got plugged in. Costs nothing —
+# the list comes from the UI, nothing is probed per turn.
+#MONITOR_CONTEXT=true
+
+# ── Screen text / OCR (optional) ────────────────────────────────────────────
+# Lets Bolt read what's actually on a monitor with `petctl read [n|here|all]`
+# and use it in his reply. Pull-only — nothing is captured unless he asks,
+# and every read is logged.
+#
+# Needs the extras from requirements.txt plus an OCR engine:
+#     pip install mss pytesseract && sudo apt install tesseract-ocr
+#   or, without sudo:
+#     pip install mss rapidocr-onnxruntime
+# mss captures on X11/Windows/macOS but NOT Wayland.
+#
+# This sends the text of a whole screen to the server when used. That's not a
+# new capability — the shell relay could already screenshot and OCR — but it's
+# a far easier one to reach for. SCREEN_TEXT=false removes it entirely.
+#SCREEN_TEXT=true
+#SCREEN_TEXT_MAX_CHARS=4000
+
 # ── Quiet hours / do-not-disturb (optional) ────────────────────────────────
 # Comma-separated HH:MM-HH:MM ranges; wrapping past midnight is fine. While
 # napping the pet dims, stops wandering and makes no proactive noise — the
@@ -128,6 +163,25 @@ ELEVENLABS_VOICE_ID=
 #WAKE_NEAR_MISS_MARGIN=0.2
 #WAKE_NEAR_MISS_LIMIT=40
 
+# ── sudo password prompts (optional) ────────────────────────────────────────
+# The pet has no terminal, so a server-relayed `sudo` would block forever on
+# a tty nobody is watching. With this on, bare `sudo` becomes `sudo -A` and
+# the password is collected in a desktop dialog you have to answer — a real
+# askpass binary if one is installed, otherwise a generated zenity/kdialog
+# wrapper in ~/.cache/bolt-pet/askpass.sh.
+# Set it to false if you'd rather Bolt never be able to ask for root: sudo
+# commands then just fail. Read the dialogs — that box is the only thing
+# between "Bolt decided to run sudo" and it running.
+#SUDO_ASKPASS_PROMPT=true
+#SUDO_ASKPASS_HELPER=            # blank = auto-detect
+#SUDO_COMMAND_TIMEOUT_SECONDS=180  # long enough for a human to answer
+
+# ── File delivery (optional) ────────────────────────────────────────────────
+# The server's deliver_files tool ("send me that report") queues workspace
+# files on this session; the pet fetches and saves them automatically.
+#RECEIVE_FILES=true
+#DELIVERED_FILES_DIR=~/Downloads/Bolt
+
 # ── Misc (optional) ──────────────────────────────────────────────────────────
 #COMMAND_TIMEOUT_SECONDS=30
 #HEARTBEAT_INTERVAL_SECONDS=60

CLAUDE.md

@@ -11,13 +11,18 @@ dependency** on the server repo; it's a standalone HTTP client configured via
 its own `.env`.
 
 Pipeline: `mic → openWakeWord ("thunderbolt", on-device) / push-to-talk /
-click → record utterance → Deepgram STT → + active-window context → POST
+click → record utterance → Deepgram STT → + active-window + screen-layout
-/desk/converse → [server may relay a shell command to run on this machine, or
+context → POST /desk/converse → [server may relay a shell command to run on
-a `petctl` pseudo-command that moves/emotes the pet instead] → reply →
+this machine, or a `petctl` pseudo-command that moves/emotes the pet, jumps it
+to another monitor, or reads a screen's text back instead] → reply →
 ElevenLabs streaming TTS (or offline pyttsx3 fallback) → speakers`, with the
 pet sprite/speech bubble reflecting state throughout, and playback
 interruptible by talking over it (barge-in).
 
+Because a relayed command's output goes back up the tool-result relay before
+the final reply, a `petctl read` mid-turn means Bolt can look at a monitor and
+then talk about what's on it in the same answer.
+
 Side channels that let the pet act between turns: the heartbeat (proactive
 announcements), the desktop notification bridge, and autonomous wandering —
 all suppressed while it's napping (quiet hours / fullscreen DND).
@@ -34,6 +39,9 @@ run.bat           # Windows
 QT_QPA_PLATFORM=offscreen .venv/bin/pytest tests/
 .venv/bin/pytest tests/test_state.py::test_happy_path_transitions  # single test
 
+# Redraw the pet's sprite frames (the committed PNGs are this script's output)
+python scripts/generate_bolt_sprites.py             # --out /tmp/x to preview first
+
 # Convert a grid sprite sheet into the per-frame-PNG convention sprite.py expects
 python scripts/slice_spritesheet.py path/to/sheet.png assets/sprites/idle --cols 6 --rows 1
 ```
@@ -60,10 +68,10 @@ logs a missing-config message and exits its thread instead of starting.
   a `QWidget` directly. Also drives the periodic heartbeat
   (`_maybe_heartbeat`, gated by `HEARTBEAT_INTERVAL_SECONDS`) which lets the
   server push proactive spoken announcements between user turns, and on the
-  same tick re-evaluates nap state and drains queued desktop notifications.
+  same tick re-evaluates nap state, checks for delivered files, and drains
-  It owns the live wake-word threshold (`wake_threshold()` is passed to
+  queued desktop notifications. It owns the live wake-word threshold
-  `listen_for_wake_word` as a *callable* so the tray slider takes effect
+  (`wake_threshold()` is passed to `listen_for_wake_word` as a *callable* so
-  mid-listen) and the conversation `history`.
+  the tray slider takes effect mid-listen) and the conversation `history`.
 - **`server_client.py`** — HTTP client for the desk API, dependency-free
   beyond `requests` so it's easy to mock in tests. `converse()` loops relaying
   server-issued shell commands (`run_local_command`, executed via
@@ -71,7 +79,24 @@ logs a missing-config message and exits its thread instead of starting.
   `/desk/tool_result` until the server sends a final `reply` (capped at
   `_MAX_RELAY_HOPS`). This is the same "full desktop control" trust model as
   the server repo's other desk clients — commands only ever originate from
-  the user's own voice/click requests in their own session.
+  the user's own voice/click requests in their own session. `list_outbox_files`
+  / `download_outbox_file` hit the same `/desk/files` and `/desk/files/<id>`
+  endpoints the server's `deliver_files` tool queues onto — see `file_delivery.py`.
+- **`file_delivery.py`** — the filesystem half of receiving files the server
+  queues via its `deliver_files` tool (`ai/desk_api.py` in the main tmn-api
+  repo — "send me that report" during a conversation spools the matched
+  workspace files, zipping multiple into one, onto the session's outbox).
+  `controller._check_deliveries` lists `/desk/files` and downloads anything
+  queued — right after a conversation/notification turn (the common case)
+  and once per heartbeat tick for anything queued out-of-band — saving each
+  under `DELIVERED_FILES_DIR` (default `~/Downloads/Bolt`). Downloading a
+  file dequeues it server-side, so it's only ever handed out once; `save()`
+  never overwrites an existing download, suffixing `" (1)"`, `" (2)"`, ... on
+  a name collision. `sanitize_filename()` reduces a server-supplied name to
+  its bare filename (`Path(...).name`), which is defense-in-depth against a
+  delivered name that's secretly a path, since a per-user desk API key means
+  the name isn't always coming from someone as trusted as the owner. Toggle
+  off entirely with `RECEIVE_FILES=false`.
 - **`audio/`** — `mic.py` (energy-based VAD utterance capture, ported from the
   server repo's `bolt_desk.py`), `wake_word.py` (openWakeWord `thunderbolt.onnx`
   detection + `NearMissLog` for threshold tuning — see below), `stt.py`
@@ -90,17 +115,75 @@ logs a missing-config message and exits its thread instead of starting.
   accepts an injectable stream/model/protocol so tests don't need real audio
   hardware or a display.
 - **`pet_actions.py`** — `petctl` pseudo-commands (`petctl move top-left`,
-  `petctl emote wave`, `say`/`wander`/`nap`). The desk API has no "move the
+  `petctl emote wave`, `say`/`wander`/`nap`, plus the screen verbs
-  pet" payload type and this repo can't change the server, so these ride the
+  `jump`/`monitors`/`read`). The desk API has no "move the pet" payload type
-  existing shell-command relay: `controller._handle_command` parses them and
+  and this repo can't change the server, so these ride the existing
-  they never reach `subprocess`; anything else is a real shell command exactly
+  shell-command relay: `controller._handle_command` parses them and they never
-  as before. Pure parsing; the UI half is `PetWindow.apply_action`.
+  reach `subprocess`; anything else is a real shell command exactly as before.
+  Pure parsing; the UI half is `PetWindow.apply_action`. Note `jump`'s target
+  is *not* validated here — which monitors exist is a runtime fact this pure
+  module doesn't have, so the spec passes through to `monitors.resolve()`.
+  Query verbs (`monitors`, `read`) are answered in `_handle_command` rather
+  than by `pet_actions.describe()`, because their output *is* the point: it
+  goes back up the tool-result relay for Bolt to use in his reply.
+- **`file_ops.py`** — `filectl` pseudo-commands, checked in `_handle_command`
+  right after petctl and before falling through to a real shell command.
+  Executing arbitrary commands already worked via the shell relay
+  (`run_local_command` — see `server_client.py` below); what filectl adds is
+  a *reliable* way to do the read/write/edit/list slice of that, since
+  getting the model to hand-roll a shell heredoc for multi-line content full
+  of quotes/`$`/backticks is failure-prone — and `list` exists as its own op
+  (rather than relying on the model shelling out to `ls`/`dir`) because this
+  project is cross-platform and the model shouldn't have to guess which
+  listing command applies on Windows vs. Linux vs. macOS; one glob-based op
+  (`pattern`, default `*`; `recursive` for `rglob` instead of `glob`) covers
+  all three. Wire format is `filectl <json>` where `<json>` is a
+  **single-line** compact JSON object —
+  `{"op": "list"|"read"|"write"|"edit", "path": ..., ...}` — not a multi-line
+  marker block (an earlier design): the server relays this as the argument
+  to the ordinary `command` tool marker, and that marker's extractor
+  (`ai/agents/default.py` in the main repo) only captures up to the next
+  newline, so anything genuinely multi-line silently got truncated no matter
+  how the prompt worded it. JSON sidesteps that for free — `json.dumps`
+  already encodes embedded newlines as the two characters `\n`, not a real
+  line break, so multi-line file content still fits on the one physical line
+  the extractor sees. `edit` requires the old text to match exactly once —
+  same discipline as this project's own code-editing tool — and raises
+  rather than guessing if it's missing or ambiguous. This doesn't expand
+  what the server can do to this machine (a relayed shell command could
+  already overwrite anything the desktop user can write — see the security
+  notes below); it's a safer path to the same capability. Pure parsing
+  (`parse`) is separated from the filesystem I/O (`execute`), matching
+  pet_actions.py's parse/describe split.
 - **`screen_context.py`** — active-window title (xprop/xdotool, Win32,
   osascript) appended to each utterance via `context_for()`, plus
   `is_fullscreen_active()` for do-not-disturb. Text only — the desk API takes
   no images. Every probe is best-effort and returns None/False rather than
   raising; the parsing is split into pure functions that are tested without a
   display server.
+- **`monitors.py`** — the screen layout, and resolving `petctl jump` targets
+  (a 1-based number, a name, `next`/`prev`/`primary`/`other`, or a direction
+  like `left`/`up` worked out from the actual geometry). Pure — no Qt, no
+  subprocess. The monitor list is *published by the UI*
+  (`PetWindow.publish_monitors` builds it from `QGuiApplication.screens()` and
+  emits it over a queued signal to `controller.set_monitors`), because the
+  controller and the window must agree on what "monitor 2" means: enumerating
+  with `xrandr` on one side and Qt's screen list on the other gives different
+  orderings on the same machine, and Bolt would announce one screen and land
+  on another. Qt is the single source of truth; `Monitor.index` is 0-based and
+  `.number` is the 1-based value used in every string a human or the model
+  sees. The controller resolves a jump to a concrete index *before* emitting
+  it, so the window can't re-resolve against a different list.
+- **`screen_text.py`** — OCR, so Bolt can read what's on a monitor
+  (`petctl read [n|here|all]`). **Pull, not push**: nothing captures on its own
+  — the server has to ask, and the text goes back as that command's output.
+  That's deliberate; OCR of a 4K screen costs a second or two that would
+  otherwise be added to *every* utterance, and screen contents leaving the
+  machine should be a visible decision rather than a constant. Capture needs
+  `mss` (X11/Win32/macOS, **not** Wayland), recognition needs Tesseract or
+  RapidOCR; both are optional and soft-fail with a reason the way `hotkey.py`
+  does, and `read_monitor()` never raises because its return value is command
+  output. Engine selection takes injected probes so it's testable wherever.
 - **`quiet.py`** — quiet-hours spec parsing (`23:00-08:00`, wraps midnight,
   comma-separated). Napping suppresses *proactive* noise and wandering only;
   wake word / click / push-to-talk still work.
@@ -108,6 +191,14 @@ logs a missing-config message and exits its thread instead of starting.
   `dbus-monitor`, parses Notify calls (pure `iter_notifications()`), filters
   and rate-limits them (`NotificationGate`), and the controller forwards
   survivors through `converse()`. Off by default — each one is a round trip.
+- **`sudo_askpass.py`** — makes server-relayed `sudo` usable from a process
+  with no terminal, by pointing sudo's `SUDO_ASKPASS` at a GUI helper and
+  rewriting bare `sudo` to `sudo -A` (`add_askpass_flag`, a conservative regex
+  that skips anything already carrying a flag and anything inside quotes).
+  Prefers a real askpass binary and falls back to generating a
+  zenity/kdialog wrapper in `~/.cache/bolt-pet/askpass.sh`. Resolution order
+  is injectable (`is_executable`/`which`) so it's testable on a machine with a
+  different set installed. See the security notes — the dialog is the boundary.
 - **`updater.py`** — self-update from the Gitea releases API. Polls
   `<UPDATE_REPO_API>/releases/latest` for a tag newer than
   `bolt_pet.__version__` and moves the checkout to it with
@@ -137,7 +228,13 @@ logs a missing-config message and exits its thread instead of starting.
   covered) strips markdown, emoji, URLs and stray symbols the voice would read
   literally ("asterisk asterisk"), turns bullet lists into full sentences, and
   words a few symbols (`&` → "and"). `for_display()` is the looser version for
-  the speech bubble — markdown syntax gone, emoji kept. Pure string logic, no
+  the speech bubble — markdown syntax gone, emoji kept. `is_question()` decides
+  whether a reply leaves the pet waiting on an answer: it tests the *spoken*
+  form (so a '?' inside a stripped code block or URL doesn't count) and only a
+  trailing one counts, since a question asked in passing isn't awaiting a
+  reply. `controller._should_follow_up` uses it to keep listening without the
+  wake word, capped by `FOLLOW_UP_MAX_TURNS` so a server that ends every reply
+  with a question can't loop forever off mic noise. Pure string logic, no
   Qt/audio imports.
 - **`ui/`** — `app.py` wires `QApplication` + `PetWindow` + `PetTray` + the
   history/tuner windows + the push-to-talk hotkey + the controller thread
@@ -148,6 +245,15 @@ logs a missing-config message and exits its thread instead of starting.
     target every `PET_WANDER_INTERVAL_SECONDS` (randomized), suppressed
     whenever the pet is non-IDLE, napping, dragged, or has a bubble up. A
     commanded `petctl move` overrides all of that except the drag.
+  - **the walk cycle** — while actually travelling, `_animation_key()` swaps
+    the state animation for the side-view `walk/` frames (not a `PetState` —
+    see the sprites README). It is stepped by *distance travelled*
+    (`_WALK_PIXELS_PER_FRAME`), never by the animation timer, so the planted
+    paw tracks backwards at exactly the speed the window moves forwards;
+    `_advance_frame` deliberately no-ops while walking so the two can't
+    double-step it. The art is drawn facing right and `_oriented()` mirrors it
+    (cached per frame) when heading left. No `walk/` art → falls back to the
+    old coded bob rather than a placeholder blob.
   - **emotes** — `emote_transform()` is pure maths (dx, dy, rotation, scale
     from a 0..1 progress) kept out of `paintEvent` so the curves are unit
     tested; every emote must return to the identity transform at progress 1.0
@@ -160,9 +266,14 @@ logs a missing-config message and exits its thread instead of starting.
   - **edge snapping** (`PET_EDGE_SNAP`) after a drag or a stroll, and **nap
     dimming** (`set_napping`).
   `sprite.py` loads `assets/sprites/<state>/*.png` (filename-sorted, looping —
-  currently Kenney's CC0 robot pack, see `assets/sprites/README.md`) and falls
+  the art is *generated* by `scripts/generate_bolt_sprites.py`, a Pillow
+  drawing of Bolt as a shepherd pup; edit the script and re-run it rather than
+  the committed PNGs, see `assets/sprites/README.md`) and falls
   back to a procedurally-drawn placeholder blob per state if a folder has no
-  frames; `tray.py` is the system tray menu (talk now / mute / nap / wander /
+  frames. It also loads `EXTRA_ANIMATIONS` — currently just `walk/` — keyed by
+  name rather than by `PetState`, with `has()` reporting whether a key is
+  backed by real art so callers can decline a placeholder instead of trotting
+  a blob across the desktop; `tray.py` is the system tray menu (talk now / mute / nap / wander /
   click-through / history / wake-word tuning / quit) — the pet window has no
   title bar or taskbar entry; `history_window.py` and `wake_tuner.py` are the
   two dialogs it opens.
@@ -231,9 +342,47 @@ matches the trust model of the server repo's other desk clients. Keep
 `DESK_API_KEY` private and don't expose the desk API port to the open
 internet.
 
-Two newer features widen what leaves this machine, both switchable in `.env`:
+`file_ops.py`'s `filectl` read/write/edit pseudo-commands ride that same
+relay and are bound by the same trust model — no path is off-limits beyond
+normal filesystem permissions for the desktop user, exactly like a relayed
+`cat`/`sed`/`rm` already isn't. They don't grant the server anything a shell
+command couldn't already do; they just make the read/write/edit path
+reliable instead of relying on the model getting shell quoting right.
+
+`sudo_askpass.py` widens that further, by design: with `SUDO_ASKPASS_PROMPT`
+on (the default), a relayed bare `sudo` is rewritten to `sudo -A` and the
+password is collected in a desktop dialog, so commands can escalate to root
+instead of hanging on a tty the pet doesn't have. The dialog is the security
+boundary — it's the only thing between the server deciding to run `sudo` and
+it running, so the prompt is deliberately not suppressible per-command and
+those commands get their own longer timeout (`SUDO_COMMAND_TIMEOUT_SECONDS`)
+rather than being made non-interactive. Set `SUDO_ASKPASS_PROMPT=false` to
+take the capability away entirely; sudo commands then fail. Note that
+`sudo -n` / `sudo -A` / `sudo -u …` in a relayed command are never rewritten,
+so an explicit non-interactive sudo stays non-interactive.
+
+**Don't run the pet as root.** It needs no privileges of its own, PortAudio
+can't reach the user's PipeWire socket from a root session (raw ALSA devices
+reject the 16 kHz capture rate — `paInvalidSampleRate`), and every relayed
+command would run unconstrained.
+
+Several features widen what leaves this machine, all switchable in `.env`:
 `SCREEN_CONTEXT` appends the focused window's *title* to each utterance
-(titles often contain file paths, document names, or subject lines), and
+(titles often contain file paths, document names, or subject lines),
-`NOTIFICATION_BRIDGE` (off by default) forwards matching desktop
+`MONITOR_CONTEXT` appends the screen layout (sizes and names only — no
-notifications to the server. Neither sends screenshots or notification
+contents), and `NOTIFICATION_BRIDGE` (off by default) forwards matching
-contents you haven't matched with `NOTIFICATION_FILTER`.
+desktop notifications to the server. None of those send screenshots or
+notification contents you haven't matched with `NOTIFICATION_FILTER`.
+
+`SCREEN_TEXT` is the biggest of them: `petctl read` OCRs a whole monitor and
+sends the recognised text to the server — everything visible, not just the
+focused window. Two things keep it honest. It's **pull-only**: no capture
+happens unless the server explicitly asks, so it can't leak in the background
+the way a per-turn annotation would, and each read is logged. And it is
+strictly *not* a new capability — the shell relay could already run a
+screenshot tool and pipe it through OCR — it just makes a thing the trust
+model already allowed reliable, bounded (`SCREEN_TEXT_MAX_CHARS`) and
+visible. It is nonetheless far easier to reach for than the shell route, so
+if that trade isn't one you want, `SCREEN_TEXT=false` removes it and
+`petctl read` starts reporting that it's disabled. Capture is `mss`-based and
+therefore silently unavailable on Wayland.

bolt_pet/__init__.py

@@ -4,4 +4,4 @@ __version__ is what the auto-updater compares against the newest tag on the
 Gitea releases page (see updater.py), so bump it in the same commit you tag.
 """
 
-__version__ = "0.1.0"
+__version__ = "0.2.2"

bolt_pet/assets/sprites/README.md

@@ -1,37 +1,84 @@
 # Sprite assets
 
-Art: [Kenney's Robot Pack](https://kenney.nl/assets/robot-pack) (CC0 — no
+Art: Bolt himself — a cream shepherd pup with a slate cap, a lightning blaze
-attribution required, credited here anyway), the green side-view robot.
+on his forehead and a bolt tag on his collar. The frames are **generated, not
-Source pack lives at `~/Documents/kenney_robot-pack`; only the frames listed
+hand-drawn**: `scripts/generate_bolt_sprites.py` draws every one of them with
-below were copied in.
+Pillow and writes this folder.
+
+```bash
+python scripts/generate_bolt_sprites.py                  # rewrite this folder
+python scripts/generate_bolt_sprites.py --out /tmp/prev  # preview elsewhere first
+python scripts/generate_bolt_sprites.py --states idle    # just one state
+```
+
+That means tweaking the art is editing code, not 24 PNGs: the palette is a
+block of constants at the top of the script, the body/head/ear/tail shapes are
+one function each in normalised 0..1 coordinates, and each state's animation is
+a list of pose dicts in `frames_for()`. Everything is super-sampled 4x and
+downscaled on save, because PIL's draw primitives have no antialiasing.
+
+**Regenerate after editing** — the PNGs here are committed, so a change to the
+script alone doesn't move the pet.
 
 Convention the loader (`bolt_pet/ui/sprite.py`) expects:
 
 ```
 assets/sprites/
-  idle/        frame_00.png                    robot_greenBody   (standing)
+  idle/        frame_00..07.png   breathing, tail wag, blink on frame 06
-  listening/   frame_00.png, frame_01.png       robot_greenDrive1/2 (tracks rolling — "leaning in")
+  listening/   frame_00..03.png   ears perked, head tilted in, collar tag lit, sound arcs
-  thinking/    frame_00.png, frame_01.png       robot_greenDamage1/2 (flicker — "processing")
+  thinking/    frame_00..05.png   eyes up, head cocked, cycling dots
-  talking/     frame_00.png, frame_01.png       robot_greenBody, robot_greenJump (bounce)
+  talking/     frame_00..03.png   mouth open/close with tongue, ears bouncing
-  error/       frame_00.png                     robot_greenHurt
+  error/       frame_00..01.png   X eyes, ears drooped, red spark
+  walk/        frame_00..07.png   side-view walk cycle (see below)
 ```
 
-- One subfolder per pet state (matches `bolt_pet.state.PetState`).
+- One subfolder per pet state (matches `bolt_pet.state.PetState`), **plus
+  `walk/`**, which is not a state — see below.
 - Any `*.png` filenames work — they're played back in alphabetical-sort
-  order, looping, at `IDLE_ANIMATION_FPS` (see `.env`).
+  order, looping, at `IDLE_ANIMATION_FPS` (see `.env`). At the default 6fps
-- Frames are scaled to fit within `PET_SIZE` (default 160px), keeping aspect
+  the 8-frame idle loop runs about 1.3s.
-  ratio, and centered in the (square) pet window — the source art here isn't
+- Frames are square (320px, 2x the default `PET_SIZE` of 160) so they
-  square, so don't assume it fills the frame edge-to-edge.
+  downscale cleanly; the loader scales to fit `PET_SIZE` keeping aspect ratio
+  and centres them in the square pet window.
 - A state directory with no frames in it falls back to a small
   procedurally-drawn placeholder blob (see `_placeholder_frames` in
   `sprite.py`).
 
+## The walk cycle
+
+`walk/` is the one animation that isn't a `PetState`. Walking is a property of
+*movement* — orthogonal to whether he's idle, listening or talking — so it
+stays out of the state machine and is keyed by name instead
+(`sprite.EXTRA_ANIMATIONS`). `PetWindow` uses it whenever the pet is actually
+travelling and falls back to the state animation the moment it stops.
+
+Three things about it are load-bearing if you redraw it:
+
+- **It's a side view, drawn facing right.** The other poses are a
+  front-facing sit, which is fine standing still but slides like a chess
+  piece when moving. `PetWindow._oriented()` mirrors the frames (cached) when
+  he walks left, so only the right-facing version exists on disk.
+- **The cycle is advanced by distance travelled, not by the animation
+  timer** (`_WALK_PIXELS_PER_FRAME`, one frame per ~13px). That's what keeps
+  a planted paw tracking backwards at exactly the speed the window moves
+  forwards. Drive it off the clock and the feet skate whenever
+  `PET_WANDER_SPEED` doesn't happen to match `IDLE_ANIMATION_FPS`. If you
+  change the number of frames or the stride length in
+  `paw_position()`, retune that constant to match or he'll moonwalk.
+- **The frames carry their own vertical bob**, so the window's own bob is
+  switched off while they're in use. Only the no-walk-art fallback still
+  bobs in code.
+
+Delete `walk/` and everything still runs — he reverts to sliding with a small
+coded bob, which is what the pet did before the cycle existed.
+
 ## Swapping in different art
 
 Replace any state's PNGs (same alphabetical-order-loops convention) to
-change its look — no code changes needed. If your source is a single grid
+change its look — no code changes needed, and nothing forces you to keep
-spritesheet (rows/cols of frames in one PNG) rather than one-file-per-frame,
+using the generator. If your source is a single grid spritesheet (rows/cols
-use `scripts/slice_spritesheet.py` to cut it into this folder-of-frames
+of frames in one PNG) rather than one-file-per-frame, use
+`scripts/slice_spritesheet.py` to cut it into this folder-of-frames
 convention:
 
 ```bash

bolt_pet/audio/mic.py

@@ -44,6 +44,7 @@ def record_utterance(
     silence_end_sec: float = None,
     max_utterance_s: float = None,
     min_utterance_s: float = None,
+    grace_s: float = None,
     frame_len: int = config.FRAME_LEN,
     sample_rate: int = config.SAMPLE_RATE,
 ) -> Optional[np.ndarray]:
@@ -53,18 +54,24 @@ def record_utterance(
     *should_continue* is polled each frame so a caller can cancel recording
     (e.g. the pet window was closed) without needing threading primitives
     baked into this function.
+
+    *grace_s* is how long to wait for speech to *begin* before giving up.
+    The controller stretches it for follow-up questions, where you're being
+    asked something and need a moment to think rather than having just said
+    the wake word on purpose.
     """
     rms_threshold = config.RMS_THRESHOLD if rms_threshold is None else rms_threshold
     silence_end_sec = config.SILENCE_END_SEC if silence_end_sec is None else silence_end_sec
     max_utterance_s = config.MAX_UTTERANCE_S if max_utterance_s is None else max_utterance_s
     min_utterance_s = config.MIN_UTTERANCE_S if min_utterance_s is None else min_utterance_s
+    grace_s = config.GRACE_SECONDS if grace_s is None else grace_s
 
     frames: list[np.ndarray] = []
     started = False
     silence_frames = 0
     silence_limit = int(silence_end_sec * sample_rate / frame_len)
     max_frames = int(max_utterance_s * sample_rate / frame_len)
-    grace_frames = int(4.0 * sample_rate / frame_len)  # wait up to 4s for speech to begin
+    grace_frames = int(grace_s * sample_rate / frame_len)  # how long to wait for speech to begin
     waited = 0
 
     while should_continue():

bolt_pet/config.py

@@ -78,8 +78,36 @@ RMS_THRESHOLD = int(os.environ.get("VAD_RMS_THRESHOLD", "300"))
 SILENCE_END_SEC = float(os.environ.get("VAD_SILENCE_END_SEC", "1.2"))
 MAX_UTTERANCE_S = float(os.environ.get("VAD_MAX_UTTERANCE_SECONDS", "15"))
 MIN_UTTERANCE_S = float(os.environ.get("VAD_MIN_UTTERANCE_SECONDS", "0.4"))
+# How long to wait for you to *start* talking before giving up on a turn.
+GRACE_SECONDS = float(os.environ.get("VAD_GRACE_SECONDS", "4"))
+
+# ── follow-up listening ─────────────────────────────────────────────────────
+# When a reply ends on a question, the pet keeps listening for the answer
+# instead of dropping back to idle and making you say the wake word again.
+# The grace period is longer than a normal turn's because you were asked
+# something and may need a beat to think. FOLLOW_UP_MAX_TURNS caps how many
+# question-and-answer rounds can chain without you re-triggering it — a stop
+# on runaway loops if the server ends every reply with a question and the mic
+# keeps feeding it noise. 0 means no cap.
+
+FOLLOW_UP_LISTEN = os.environ.get("FOLLOW_UP_LISTEN", "true").lower() in ("1", "true", "yes", "on")
+FOLLOW_UP_MAX_TURNS = int(os.environ.get("FOLLOW_UP_MAX_TURNS", "3"))
+FOLLOW_UP_GRACE_SECONDS = float(os.environ.get("FOLLOW_UP_GRACE_SECONDS", "7"))
 
 COMMAND_TIMEOUT_SECONDS = int(os.environ.get("COMMAND_TIMEOUT_SECONDS", "30"))
+
+# ── sudo password prompts ───────────────────────────────────────────────────
+# The pet has no terminal, so a relayed `sudo` would block on a tty nobody is
+# watching. With this on, bare `sudo` is rewritten to `sudo -A` and the
+# password is collected in a desktop dialog (a real askpass binary if one is
+# installed, otherwise a generated zenity/kdialog wrapper). Turn it off and
+# sudo commands simply fail, which is the safer default if you'd rather Bolt
+# never be able to ask for root at all.
+SUDO_ASKPASS_PROMPT = os.environ.get("SUDO_ASKPASS_PROMPT", "true").lower() in ("1", "true", "yes", "on")
+SUDO_ASKPASS_HELPER = os.environ.get("SUDO_ASKPASS_HELPER", "")  # blank = auto-detect
+# Longer than COMMAND_TIMEOUT_SECONDS because a person has to notice the
+# dialog, read it, and type — 30s is nowhere near enough for that.
+SUDO_COMMAND_TIMEOUT_SECONDS = int(os.environ.get("SUDO_COMMAND_TIMEOUT_SECONDS", "180"))
 HEARTBEAT_INTERVAL_SECONDS = float(os.environ.get("HEARTBEAT_INTERVAL_SECONDS", "60"))
 
 # ── barge-in (interrupt playback while the pet is talking) ──────────────────
@@ -116,6 +144,30 @@ TTS_STREAMING = os.environ.get("TTS_STREAMING", "true").lower() in ("1", "true",
 
 SCREEN_CONTEXT = os.environ.get("SCREEN_CONTEXT", "true").lower() in ("1", "true", "yes", "on")
 
+# ── monitors ────────────────────────────────────────────────────────────────
+# A one-line note about the screen layout (how many, their sizes, which one
+# the pet is standing on) rides along with each utterance, so Bolt can decide
+# to `petctl jump` somewhere without asking you what you've got plugged in.
+# Cheap — the list comes from the UI, nothing is probed per turn.
+
+MONITOR_CONTEXT = os.environ.get("MONITOR_CONTEXT", "true").lower() in (
+    "1", "true", "yes", "on"
+)
+
+# ── screen text (OCR) ───────────────────────────────────────────────────────
+# Lets Bolt actually read a monitor, via `petctl read`. Pull-only: nothing is
+# captured unless the server asks for it, and every read is logged. Needs the
+# optional capture/OCR extras — see the comments in requirements.txt.
+#
+# This widens what can leave the machine more than any other switch here: the
+# recognised text of a whole screen goes to the server. It is *not* a new
+# capability (the shell relay could already run a screenshot tool and OCR it),
+# but it is a much easier one to use by accident. Set SCREEN_TEXT=false to
+# take it away entirely.
+
+SCREEN_TEXT = os.environ.get("SCREEN_TEXT", "true").lower() in ("1", "true", "yes", "on")
+SCREEN_TEXT_MAX_CHARS = int(os.environ.get("SCREEN_TEXT_MAX_CHARS", "4000"))
+
 # ── quiet hours / do-not-disturb ────────────────────────────────────────────
 # Comma-separated HH:MM-HH:MM ranges (wrapping midnight is fine). While
 # napping the pet dims, stops wandering, and makes no proactive noise —
@@ -133,6 +185,17 @@ NOTIFICATION_BRIDGE = os.environ.get("NOTIFICATION_BRIDGE", "false").lower() in
 NOTIFICATION_FILTER = os.environ.get("NOTIFICATION_FILTER", "")
 NOTIFICATION_MIN_INTERVAL_SECONDS = float(os.environ.get("NOTIFICATION_MIN_INTERVAL_SECONDS", "60"))
 
+# ── file delivery ────────────────────────────────────────────────────────
+# The server's deliver_files tool (ai/desk_api.py in the main tmn-api repo)
+# queues workspace files on this session — e.g. "send me that report" — for
+# the client to fetch via GET /desk/files. Downloading a file dequeues it
+# server-side, so each one lands here exactly once.
+
+RECEIVE_FILES = os.environ.get("RECEIVE_FILES", "true").lower() in ("1", "true", "yes", "on")
+DELIVERED_FILES_DIR = Path(
+    os.environ.get("DELIVERED_FILES_DIR") or str(Path.home() / "Downloads" / "Bolt")
+).expanduser()
+
 # ── conversation history ────────────────────────────────────────────────────
 
 HISTORY_LIMIT = int(os.environ.get("HISTORY_LIMIT", "100"))

bolt_pet/controller.py

@@ -20,8 +20,9 @@ from typing import Optional
 from PySide6.QtCore import QObject, Signal
 
 from . import (
-    config, history as history_mod, notifications, pet_actions, quiet,
+    config, file_delivery, file_ops, history as history_mod,
-    screen_context, server_client, speech_text, updater,
+    monitors as monitors_mod, notifications, pet_actions, quiet,
+    screen_context, screen_text, server_client, speech_text, updater,
 )
 from .audio import barge_in, mic, stt, tts, wake_word
 from .state import PetState, PetStateMachine
@@ -53,6 +54,13 @@ class PetController(QObject):
         # window. Append-only from this thread; the UI only ever snapshots it.
         self.history = history_mod.ConversationHistory(limit=config.HISTORY_LIMIT)
 
+        # The screen layout, as published by the UI (see set_monitors). Held
+        # here rather than probed, so "monitor 2" means the same thing to the
+        # controller and to the window that has to jump there — see
+        # monitors.py for why that matters.
+        self._monitors: list[monitors_mod.Monitor] = []
+        self._pet_monitor: Optional[int] = None
+
         # Wake-word sensitivity is live-tunable (tray tuner), so it's read
         # through a callable on every frame rather than captured per listen.
         self._wake_threshold = config.WAKE_WORD_THRESHOLD
@@ -63,6 +71,13 @@ class PetController(QObject):
         self._nap_forced: Optional[bool] = None  # petctl nap on/off overrides the schedule
         self._last_nap_check = 0.0
 
+        # When a reply ends on a question the pet keeps listening for the
+        # answer. _follow_ups counts how many have chained without you
+        # re-triggering, so a server that ends every reply with "?" can't
+        # loop forever off mic noise.
+        self._pending_follow_up = False
+        self._follow_ups = 0
+
         self._last_update_check = 0.0
         self._update_pending = False  # applied on disk, waiting for the restart
 
@@ -200,9 +215,21 @@ class PetController(QObject):
         self._near_misses.observe(score, threshold, time.time())
 
     def _handle_conversation_turn(self) -> None:
+        # A turn you started yourself ends any follow-up chain in progress.
+        following_up, self._pending_follow_up = self._pending_follow_up, False
+        if not following_up:
+            self._follow_ups = 0
+
         self._state.transition(PetState.LISTENING)
-        pcm = mic.record_utterance(self._stream, should_continue=self._should_continue)
+        pcm = mic.record_utterance(
+            self._stream,
+            should_continue=self._should_continue,
+            # Answering a question deserves longer than saying the wake word
+            # on purpose does — you were just asked something.
+            grace_s=config.FOLLOW_UP_GRACE_SECONDS if following_up else None,
+        )
         if pcm is None:
+            self._follow_ups = 0  # silence ends the chain
             self._state.transition(PetState.IDLE)
             return
 
@@ -224,7 +251,7 @@ class PetController(QObject):
             # What's focused right now rides along, so "what's this error?"
             # has a referent without you having to describe the window.
             reply = server_client.converse(
-                screen_context.context_for(text), on_command=self._handle_command
+                self._with_context(text), on_command=self._handle_command
             )
         except server_client.ServerError as exc:
             self.log.emit(f"Server error: {exc}")
@@ -232,26 +259,112 @@ class PetController(QObject):
             self._state.transition(PetState.IDLE)
             return
 
+        self._check_deliveries()
         self._speak(reply)
         self._state.transition(PetState.IDLE)
 
+    def _with_context(self, text: str) -> str:
+        """Everything the server gets alongside what you actually said: the
+        focused window title, and a one-line note about the screen layout so
+        Bolt knows how many monitors there are and where he's standing
+        without having to ask. Only the *layout* rides along for free — the
+        text on those screens costs an OCR pass, so it stays behind
+        `petctl read`."""
+        text = screen_context.context_for(text)
+        if config.MONITOR_CONTEXT:
+            text = monitors_mod.annotate(text, self._monitors, self._pet_monitor)
+        return text
+
+    # ── screen layout, published by the UI ───────────────────────────────
+
+    def set_monitors(self, monitors: list) -> None:
+        """Slot: the window telling us what screens exist (queued signal)."""
+        self._monitors = list(monitors)
+        self.log.emit(
+            "Screens: " + (monitors_mod.summary(self._monitors) or "none reported")
+        )
+
+    def set_pet_monitor(self, index: int) -> None:
+        """Slot: the window telling us which screen the pet is standing on."""
+        self._pet_monitor = int(index)
+
     def _handle_command(self, command: str) -> str:
         """Server-relayed command. `petctl ...` drives the pet's body and
-        never reaches a shell; everything else is a real command, exactly as
+        `filectl ...` does local file read/write/edit — neither ever reaches
-        before (see the security notes in the README)."""
+        a shell; everything else is a real command, exactly as before (see
+        the security notes in the README)."""
         try:
             action = pet_actions.parse(command)
         except pet_actions.ActionError as exc:
             self.log.emit(f"petctl: {exc}")
             return f"[pet] {exc}"
-        if action is None:
+        if action is not None:
-            return server_client.run_local_command(command)
             self.log.emit(f"Pet action: {action}")
-        if action["action"] == "nap":
+
+            # Queries answer from here rather than from pet_actions.describe():
+            # their output *is* the useful part, and it's what the server reads
+            # back off the tool-result relay.
+            kind = action["action"]
+            if kind == "monitors":
+                return monitors_mod.describe(self._monitors, self._pet_monitor)
+            if kind == "read":
+                return self._read_screen(action["target"])
+            if kind == "jump":
+                try:
+                    target = monitors_mod.resolve(
+                        self._monitors, action["target"], self._pet_monitor
+                    )
+                except ValueError as exc:
+                    self.log.emit(f"petctl jump: {exc}")
+                    return f"[pet] {exc}"
+                # Hand the window a resolved index, so it can't re-resolve the
+                # spec against a different screen ordering.
+                self.action.emit({"action": "jump", "monitor": target.index})
+                return f"[pet] jumped to monitor {target.label}"
+
+            if kind == "nap":
                 self.set_napping(bool(action["enabled"]))
             self.action.emit(action)
             return pet_actions.describe(action)
 
+        try:
+            file_action = file_ops.parse(command)
+        except file_ops.FileOpError as exc:
+            self.log.emit(f"filectl: {exc}")
+            return f"[filectl] {exc}"
+        if file_action is not None:
+            self.log.emit(file_ops.describe(file_action))
+            try:
+                return file_ops.execute(file_action)
+            except file_ops.FileOpError as exc:
+                self.log.emit(f"filectl: {exc}")
+                return f"[filectl] {exc}"
+
+        return server_client.run_local_command(command)
+
+    def _read_screen(self, target: str) -> str:
+        """`petctl read` — OCR a screen and hand the text back to the server."""
+        if not config.SCREEN_TEXT:
+            return "[pet] screen reading is disabled (set SCREEN_TEXT=true in .env)"
+        if not self._monitors:
+            return "[pet] no monitor information available"
+        limit = config.SCREEN_TEXT_MAX_CHARS
+        if target in ("all", "everything", "*"):
+            self.log.emit(f"Reading all {len(self._monitors)} screens…")
+            return screen_text.read_monitors(self._monitors, limit)
+        if target in ("here", "", "this", "current"):
+            index = self._pet_monitor if self._pet_monitor is not None else 0
+            monitor = self._monitors[min(index, len(self._monitors) - 1)]
+        else:
+            try:
+                monitor = monitors_mod.resolve(
+                    self._monitors, target, self._pet_monitor
+                )
+            except ValueError as exc:
+                return f"[pet] {exc}"
+        self.log.emit(f"Reading monitor {monitor.number} ({monitor.name})…")
+        return screen_text.read_monitor(monitor, limit)
+
     def _speak(self, text: str) -> None:
         self._state.transition(PetState.TALKING)
         # Bubble gets the markdown stripped but emoji kept (it can't render
@@ -270,6 +383,9 @@ class PetController(QObject):
             on_error=lambda exc: self.log.emit(f"TTS failed: {exc}"),
             should_stop=should_stop,
         )
+        # Read the scoring history *before* resetting, or the log reports the
+        # blank counters instead of what actually fired.
+        detail = self._barge_in_detail()
         if self._barge_in is not None:
             # Playback fed the pet's own voice into the wake model's rolling
             # window. Clear it before the idle listener starts scoring again,
@@ -278,8 +394,36 @@ class PetController(QObject):
         if not completed:
             # You talked over it — take that as the start of the next turn
             # rather than making you say the wake word again.
-            self.log.emit(f"Interrupted — listening. {self._barge_in_detail()}")
+            self.log.emit(f"Interrupted — listening. {detail}")
+            self._follow_ups = 0  # you're clearly engaged; start the count over
             self._talk_now.set()
+        elif self._should_follow_up(text):
+            self._follow_ups += 1
+            cap = config.FOLLOW_UP_MAX_TURNS
+            self.log.emit(
+                f"Asked a question — listening for your answer "
+                f"({self._follow_ups}{'/' + str(cap) if cap > 0 else ''})."
+            )
+            self._pending_follow_up = True
+            self._talk_now.set()
+
+    def _should_follow_up(self, text: str) -> bool:
+        """Whether *text* leaves the pet waiting on an answer.
+
+        Muted is excluded because mute means "don't listen to me" — an
+        automatic turn would walk straight past it. Napping isn't: quiet
+        hours suppress the pet *starting* something, and a question is only
+        ever asked in reply to you."""
+        if not config.FOLLOW_UP_LISTEN or self._muted:
+            return False
+        if not speech_text.is_question(text):
+            return False
+        # Only worth mentioning the cap on a reply that would otherwise have
+        # kept listening, or it fires on every statement the pet makes.
+        if config.FOLLOW_UP_MAX_TURNS > 0 and self._follow_ups >= config.FOLLOW_UP_MAX_TURNS:
+            self.log.emit("Follow-up limit reached — say the wake word to keep going.")
+            return False
+        return True
 
     def _barge_in_detail(self) -> str:
         """Why the interruption fired, for the log. How far into playback it
@@ -359,10 +503,39 @@ class PetController(QObject):
             except server_client.ServerError as exc:
                 self.log.emit(f"Couldn't forward notification: {exc}")
                 return
+            self._check_deliveries()
             if reply.strip():
                 self._speak(reply)
                 self._state.transition(PetState.IDLE)
 
+    # ── file delivery ────────────────────────────────────────────────────
+
+    def _check_deliveries(self) -> None:
+        """Download anything the server has queued via deliver_files —
+        called right after a conversation/notification turn (the common
+        case: "send me that file") and once per heartbeat for anything
+        queued out-of-band. Best-effort: a failure here is logged, not
+        raised, so it can't sour a turn that already got its spoken reply."""
+        if not config.RECEIVE_FILES:
+            return
+        try:
+            queued = server_client.list_outbox_files()
+        except server_client.ServerError as exc:
+            self.log.emit(f"Couldn't check for delivered files: {exc}")
+            return
+        for entry in queued:
+            file_id = entry.get("id")
+            name = entry.get("name") or file_id
+            if not file_id:
+                continue
+            try:
+                data = server_client.download_outbox_file(file_id)
+            except server_client.ServerError as exc:
+                self.log.emit(f"Couldn't download {name}: {exc}")
+                continue
+            path = file_delivery.save(config.DELIVERED_FILES_DIR, name, data)
+            self.log.emit(f"Received file: {path}")
+
     # ── auto-update ──────────────────────────────────────────────────────
 
     def _maybe_update(self) -> None:
@@ -418,6 +591,7 @@ class PetController(QObject):
             return
         if self._napping:
             return  # quiet hours: still answers when spoken to, just doesn't start
+        self._check_deliveries()
         self._drain_notifications()
         if self._state.state != PetState.IDLE:
             return

bolt_pet/file_delivery.py

@@ -0,0 +1,54 @@
+"""Saves files the server queues via its deliver_files tool (ai/desk_api.py
+in the main tmn-api repo) to a local downloads folder.
+
+The server side of this is already generic — any desk client can list
+GET /desk/files and fetch GET /desk/files/<id> (see server_client.
+list_outbox_files / download_outbox_file) — so this module is just the
+filesystem half: turn a server-supplied display name into a safe path and
+write the bytes.
+
+Pure filename/path logic lives here so it's testable without touching a real
+mic/network; the only I/O is the final write in save().
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+_FALLBACK_NAME = "delivered_file"
+
+
+def sanitize_filename(name: str) -> str:
+    """Reduce a server-supplied name to a bare filename. Defends against a
+    delivered name that's actually a path (../../etc, an absolute path, ...)
+    — Path(...).name strips every directory component, and anything that
+    collapses to nothing (or "." / "..") falls back to a generic name."""
+    candidate = Path(str(name or "").strip()).name
+    if candidate in ("", ".", ".."):
+        return _FALLBACK_NAME
+    return candidate
+
+
+def unique_path(directory: Path, name: str) -> Path:
+    """*name* under *directory*, suffixed " (1)", " (2)", ... if that name is
+    already taken — a delivered file never overwrites an earlier download."""
+    directory = Path(directory)
+    directory.mkdir(parents=True, exist_ok=True)
+    candidate = directory / name
+    if not candidate.exists():
+        return candidate
+    stem, suffix = candidate.stem, candidate.suffix
+    n = 1
+    while True:
+        candidate = directory / f"{stem} ({n}){suffix}"
+        if not candidate.exists():
+            return candidate
+        n += 1
+
+
+def save(directory: Path, name: str, data: bytes) -> Path:
+    """Write *data* under *directory* as *name* (sanitized + uniquified),
+    returning the path written."""
+    path = unique_path(directory, sanitize_filename(name))
+    path.write_bytes(data)
+    return path

bolt_pet/file_ops.py

@@ -0,0 +1,280 @@
+"""Local file read/edit/write, intercepted from the server-relayed command
+channel the same way pet_actions.py intercepts petctl (see server_client.
+run_local_command / controller._handle_command). Whatever text the server's
+"command" tool sends is just a string this repo is free to interpret before
+it ever reaches subprocess — a `filectl` pseudo-command is one such
+interpretation, giving the model a way to read/write/edit files on this
+machine without constructing a raw shell heredoc, where quoting, `$`,
+backticks, and embedded quotes make anything beyond a one-liner failure-prone.
+
+Executing arbitrary commands already works today (that's exactly what
+run_local_command/subprocess.run does) — filectl doesn't add that ability,
+it only makes the read/write/edit slice of it reliable. It also doesn't
+expand what the server can already do to this machine: a relayed shell
+command could already overwrite any file the desktop user can write (see the
+security notes in CLAUDE.md) — filectl is a safer *path* to the same
+capability, not a new capability.
+
+Wire format: `filectl <json>`, where <json> is a single-line, compact JSON
+object — critically, ONE LINE. The server's "command" tool marker only
+captures the argument up to the next newline (see TOOL_SPECS/
+_extract_all_tool_calls in the main repo's ai/agents/default.py — "command"
+is not declared multiline), so a marker-delimited multi-line payload (this
+module's first design) silently got truncated at the first line no matter
+how the prompt worded it. JSON sidesteps that for free: json.dumps() already
+encodes embedded newlines as the two characters "\n", not an actual line
+break, so arbitrarily multi-line file content still fits on the one physical
+line the extractor captures.
+
+    filectl {"op": "list", "path": "<dir>", "pattern": "<glob>", "recursive": <bool>}
+    filectl {"op": "read", "path": "<path>", "start": <line>, "end": <line>}
+    filectl {"op": "write", "path": "<path>", "content": "<text>"}
+    filectl {"op": "edit", "path": "<path>", "old": "<text>", "new": "<text>"}
+
+"pattern"/"recursive" (list) and "start"/"end" (read) are optional. `list`
+exists even though a real `ls`/`dir` shell command already works, because
+this repo is cross-platform (Windows/macOS/Linux) and the model shouldn't
+have to guess which listing command applies on this machine — one glob-based
+op covers all three. Must be invoked as the argument to the
+ordinary `command` tool marker (e.g. `command: filectl {"op": "write", ...}`)
+— see the pet-only paragraph in the main repo's ai/desk_api.py
+_system_context for the exact instruction the model is given, including the
+"keep it one line" requirement.
+
+Pure parsing (parse) is separated from the filesystem I/O (execute) so the
+syntax is unit-testable without touching disk, matching pet_actions.py's
+parse/describe split.
+"""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Optional
+
+_PREFIXES = ("filectl", "file")
+
+# Keeps a runaway read/write/list from blowing up the tool_result relay (and,
+# for read/list, from flooding the model's context with a giant response).
+_MAX_READ_BYTES = 200_000
+_MAX_WRITE_BYTES = 2_000_000
+_MAX_LIST_ENTRIES = 500
+
+HELP = (
+    'filectl {"op": "list", "path": "<dir>", "pattern": "<glob>", "recursive": <bool>}\n'
+    'filectl {"op": "read", "path": "<path>", "start": <line>, "end": <line>}\n'
+    'filectl {"op": "write", "path": "<path>", "content": "<text>"}\n'
+    'filectl {"op": "edit", "path": "<path>", "old": "<text>", "new": "<text>"}\n'
+    "Must be all on one line — this rides the single-line \"command\" marker."
+)
+
+
+class FileOpError(Exception):
+    """Bad filectl syntax or a filesystem error — reported back to the
+    server as command output, exactly like ActionError in pet_actions.py."""
+
+
+def is_file_command(command: str) -> bool:
+    stripped = (command or "").strip()
+    if not stripped:
+        return False
+    first_word = stripped.split(None, 1)[0]
+    return first_word.lower() in _PREFIXES
+
+
+def parse(command: str) -> Optional[dict]:
+    """Parse a `filectl <json>` string into an action dict, or None if this
+    isn't a filectl command at all (caller should try the next handler, or
+    fall back to a real shell command). Raises FileOpError on a filectl
+    command that doesn't make sense."""
+    if not is_file_command(command):
+        return None
+    stripped = command.strip()
+    _, _, rest = stripped.partition(" ")
+    rest = rest.strip()
+    if not rest or rest.lower() in ("help", "-h", "--help"):
+        return {"action": "help"}
+
+    try:
+        payload = json.loads(rest)
+    except json.JSONDecodeError as exc:
+        raise FileOpError(f"couldn't parse filectl JSON ({exc}); usage:\n{HELP}") from exc
+    if not isinstance(payload, dict):
+        raise FileOpError(f"filectl payload must be a JSON object; usage:\n{HELP}")
+
+    op = str(payload.get("op") or "help").lower()
+
+    if op == "help":
+        return {"action": "help"}
+
+    if op == "list":
+        path = _required_str(payload, "path")
+        pattern = payload.get("pattern", "*")
+        if not isinstance(pattern, str) or not pattern:
+            raise FileOpError('"pattern" must be a non-empty string')
+        return {
+            "action": "list", "path": path,
+            "pattern": pattern, "recursive": bool(payload.get("recursive")),
+        }
+
+    if op == "read":
+        path = _required_str(payload, "path")
+        return {
+            "action": "read", "path": path,
+            "start": _line_number(payload.get("start"), "start"),
+            "end": _line_number(payload.get("end"), "end"),
+        }
+
+    if op == "write":
+        path = _required_str(payload, "path")
+        if payload.get("content") is None:
+            raise FileOpError('write needs "content"')
+        return {"action": "write", "path": path, "content": str(payload["content"])}
+
+    if op == "edit":
+        path = _required_str(payload, "path")
+        if payload.get("old") is None or payload.get("new") is None:
+            raise FileOpError('edit needs "old" and "new"')
+        old, new = str(payload["old"]), str(payload["new"])
+        if old == new:
+            raise FileOpError("old and new text are identical — nothing to edit")
+        return {"action": "edit", "path": path, "old": old, "new": new}
+
+    raise FileOpError(f"unknown filectl op {op!r}; usage:\n{HELP}")
+
+
+def _required_str(payload: dict, key: str) -> str:
+    value = payload.get(key)
+    if not isinstance(value, str) or not value.strip():
+        raise FileOpError(f'filectl needs a non-empty "{key}"')
+    return value
+
+
+def _line_number(value, label: str) -> Optional[int]:
+    if value is None:
+        return None
+    if isinstance(value, bool) or not isinstance(value, int):
+        raise FileOpError(f"{label} must be an integer line number, got {value!r}")
+    return value
+
+
+def describe(action: dict) -> str:
+    """Text handed back to the server before execute() runs — mirrors
+    pet_actions.describe, used only for the log line."""
+    kind = action.get("action")
+    if kind == "help":
+        return "[filectl] help"
+    return f"[filectl] {kind} {action.get('path', '')}"
+
+
+def execute(action: dict) -> str:
+    """Actually perform a parsed filectl action, returning the text to send
+    back to the server as the command's output. Raises FileOpError on any
+    filesystem problem, same as a bad-syntax parse error."""
+    kind = action.get("action")
+    if kind == "help":
+        return HELP
+    if kind == "list":
+        return _do_list(action)
+    if kind == "read":
+        return _do_read(action)
+    if kind == "write":
+        return _do_write(action)
+    if kind == "edit":
+        return _do_edit(action)
+    return "[filectl] ok"
+
+
+def _resolve(path_str: str) -> Path:
+    return Path(path_str).expanduser()
+
+
+def _do_list(action: dict) -> str:
+    path = _resolve(action["path"])
+    if not path.is_dir():
+        raise FileOpError(f"no such directory: {path}")
+    pattern = action["pattern"]
+    glob = path.rglob if action["recursive"] else path.glob
+    try:
+        entries = sorted(glob(pattern), key=lambda p: str(p).lower())
+    except OSError as exc:
+        raise FileOpError(f"couldn't list {path}: {exc}") from exc
+    if not entries:
+        return f"[no entries matching {pattern!r} in {path}]"
+    truncated = len(entries) > _MAX_LIST_ENTRIES
+    lines = []
+    for entry in entries[:_MAX_LIST_ENTRIES]:
+        rel = entry.relative_to(path)
+        if entry.is_dir():
+            lines.append(f"{rel}/")
+            continue
+        try:
+            size = entry.stat().st_size
+        except OSError:
+            size = -1
+        lines.append(f"{rel}\t{size}B")
+    if truncated:
+        lines.append(f"... truncated at {_MAX_LIST_ENTRIES} entries (of {len(entries)}) — narrow \"pattern\"")
+    return "\n".join(lines)
+
+
+def _do_read(action: dict) -> str:
+    path = _resolve(action["path"])
+    if not path.is_file():
+        raise FileOpError(f"no such file: {path}")
+    try:
+        data = path.read_bytes()
+    except OSError as exc:
+        raise FileOpError(f"couldn't read {path}: {exc}") from exc
+    if len(data) > _MAX_READ_BYTES:
+        raise FileOpError(
+            f"{path} is {len(data)} bytes, over the {_MAX_READ_BYTES}-byte filectl read limit — "
+            'pass "start"/"end" to read a slice instead'
+        )
+    try:
+        text = data.decode("utf-8")
+    except UnicodeDecodeError as exc:
+        raise FileOpError(f"{path} isn't valid UTF-8 text: {exc}") from exc
+    lines = text.splitlines()
+    start = max(1, action.get("start") or 1)
+    end = min(len(lines), action.get("end") or len(lines))
+    if not lines:
+        return "[empty file]"
+    return "\n".join(f"{i:>6}\t{lines[i - 1]}" for i in range(start, end + 1))
+
+
+def _do_write(action: dict) -> str:
+    path = _resolve(action["path"])
+    content = action["content"]
+    if len(content.encode("utf-8")) > _MAX_WRITE_BYTES:
+        raise FileOpError(f"content is over the {_MAX_WRITE_BYTES}-byte filectl write limit")
+    try:
+        path.parent.mkdir(parents=True, exist_ok=True)
+        path.write_text(content, encoding="utf-8")
+    except OSError as exc:
+        raise FileOpError(f"couldn't write {path}: {exc}") from exc
+    return f"[filectl] wrote {len(content)} chars to {path}"
+
+
+def _do_edit(action: dict) -> str:
+    path = _resolve(action["path"])
+    old, new = action["old"], action["new"]
+    if not path.is_file():
+        raise FileOpError(f"no such file: {path}")
+    try:
+        text = path.read_text(encoding="utf-8")
+    except OSError as exc:
+        raise FileOpError(f"couldn't read {path}: {exc}") from exc
+    count = text.count(old)
+    if count == 0:
+        raise FileOpError(f"didn't find that text in {path} — nothing changed")
+    if count > 1:
+        raise FileOpError(
+            f"that text appears {count} times in {path} — filectl edit needs a unique match; "
+            "include more surrounding context"
+        )
+    try:
+        path.write_text(text.replace(old, new, 1), encoding="utf-8")
+    except OSError as exc:
+        raise FileOpError(f"couldn't write {path}: {exc}") from exc
+    return f"[filectl] edited {path}"

bolt_pet/monitors.py

@@ -0,0 +1,213 @@
+"""Which screens exist, and which one the pet is standing on.
+
+Deliberately free of Qt *and* of any subprocess probing: the monitor list is
+published by the UI (`ui/pet_window.py` builds it from
+`QGuiApplication.screens()`) and handed to the controller over a queued
+signal, the same way every other UI↔controller message travels.
+
+That indirection is the whole point. The pet has to agree with itself about
+what "monitor 2" means — if the controller enumerated screens with `xrandr`
+while the window jumped using Qt's screen list, the two orderings could
+disagree and Bolt would announce one screen and land on another. Making Qt the
+single source of truth removes that class of bug, and leaves everything here
+pure enough to unit test without a display.
+
+Indices are **1-based in every string a human or the model ever sees**, and
+0-based in the list itself. `Monitor.index` is the 0-based one; `.number` is
+what gets printed.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Iterable, Optional
+
+# Directional specs understood by resolve(), mapped to a (dx, dy) heading.
+_DIRECTIONS = {
+    "left": (-1, 0),
+    "right": (1, 0),
+    "up": (0, -1),
+    "above": (0, -1),
+    "down": (0, 1),
+    "below": (0, 1),
+}
+
+
+@dataclass(frozen=True)
+class Monitor:
+    """One screen, in the global desktop coordinate space."""
+
+    index: int  # 0-based position in the published list
+    name: str
+    x: int
+    y: int
+    width: int
+    height: int
+    primary: bool = False
+
+    @property
+    def number(self) -> int:
+        """1-based, for anything a person or the model reads."""
+        return self.index + 1
+
+    @property
+    def right(self) -> int:
+        return self.x + self.width
+
+    @property
+    def bottom(self) -> int:
+        return self.y + self.height
+
+    @property
+    def center(self) -> tuple[int, int]:
+        return self.x + self.width // 2, self.y + self.height // 2
+
+    def contains(self, x: int, y: int) -> bool:
+        return self.x <= x < self.right and self.y <= y < self.bottom
+
+    @property
+    def label(self) -> str:
+        bits = f"{self.number}: {self.name} {self.width}x{self.height}"
+        return bits + " (primary)" if self.primary else bits
+
+
+def monitor_containing(
+    monitors: Iterable[Monitor], x: int, y: int
+) -> Optional[Monitor]:
+    """The screen holding point (x, y), or None if it's off every screen."""
+    for monitor in monitors:
+        if monitor.contains(x, y):
+            return monitor
+    return None
+
+
+def nearest_monitor(monitors: Iterable[Monitor], x: int, y: int) -> Optional[Monitor]:
+    """Screen whose centre is closest to (x, y) — the fallback when a point
+    lands in the dead space between mismatched screens."""
+    monitors = list(monitors)
+    if not monitors:
+        return None
+    return min(
+        monitors,
+        key=lambda m: (m.center[0] - x) ** 2 + (m.center[1] - y) ** 2,
+    )
+
+
+def resolve(
+    monitors: list[Monitor], spec: str, current: Optional[int] = None
+) -> Monitor:
+    """Turn a `petctl jump` target into a screen.
+
+    Accepts a 1-based number, a name (case-insensitive substring, so "hdmi"
+    finds "HDMI-0"), `next`/`prev`, `primary`, `other`, or a direction
+    (`left`/`right`/`up`/`down`) relative to *current*. Raises ValueError with
+    a message meant to be read by the model, since it goes back as tool
+    output.
+    """
+    if not monitors:
+        raise ValueError("no monitors have been reported yet")
+    spec = (spec or "").strip().lower()
+    if not spec:
+        raise ValueError("jump needs a target monitor")
+    count = len(monitors)
+    if current is None or not (0 <= current < count):
+        current = next((m.index for m in monitors if m.primary), 0)
+
+    if spec.isdigit():
+        number = int(spec)
+        if not (1 <= number <= count):
+            raise ValueError(
+                f"there is no monitor {number}; you have {count} "
+                f"(1-{count})"
+            )
+        return monitors[number - 1]
+
+    if spec in ("next", "forward"):
+        return monitors[(current + 1) % count]
+    if spec in ("prev", "previous", "back"):
+        return monitors[(current - 1) % count]
+    if spec == "primary":
+        return next((m for m in monitors if m.primary), monitors[0])
+    if spec == "other":
+        # With two screens "the other one" is unambiguous; with more it's just
+        # the next one round, which is at least always a *different* screen.
+        return monitors[(current + 1) % count]
+    if spec == "random":
+        # Deterministic-free choice is the caller's business; pick the screen
+        # furthest from the current one so "random" always visibly moves.
+        here = monitors[current].center
+        return max(
+            monitors,
+            key=lambda m: (m.center[0] - here[0]) ** 2 + (m.center[1] - here[1]) ** 2,
+        )
+
+    if spec in _DIRECTIONS:
+        dx, dy = _DIRECTIONS[spec]
+        here = monitors[current].center
+        candidates = []
+        for monitor in monitors:
+            if monitor.index == current:
+                continue
+            ox, oy = monitor.center
+            along = (ox - here[0]) * dx + (oy - here[1]) * dy
+            if along <= 0:
+                continue  # not in that direction at all
+            drift = abs((ox - here[0]) * dy + (oy - here[1]) * dx)
+            candidates.append((drift, along, monitor))
+        if not candidates:
+            raise ValueError(
+                f"there's no monitor to the {spec} of monitor "
+                f"{monitors[current].number}"
+            )
+        # Prefer the best-aligned screen, then the closest of those.
+        candidates.sort(key=lambda item: (item[0], item[1]))
+        return candidates[0][2]
+
+    matches = [m for m in monitors if spec in m.name.lower()]
+    if len(matches) == 1:
+        return matches[0]
+    if len(matches) > 1:
+        raise ValueError(
+            f"{spec!r} matches several monitors: "
+            + ", ".join(m.label for m in matches)
+        )
+    raise ValueError(
+        f"unknown monitor {spec!r}; you have: "
+        + "; ".join(m.label for m in monitors)
+        + " — or use next/prev/primary/left/right/up/down"
+    )
+
+
+def describe(monitors: list[Monitor], current: Optional[int] = None) -> str:
+    """Full listing, used as `petctl monitors` output."""
+    if not monitors:
+        return "[pet] no monitor information available"
+    lines = [f"[pet] {len(monitors)} monitor(s):"]
+    for monitor in monitors:
+        here = " <- Bolt is here" if monitor.index == current else ""
+        lines.append(
+            f"  {monitor.label} at +{monitor.x}+{monitor.y}{here}"
+        )
+    return "\n".join(lines)
+
+
+def summary(monitors: list[Monitor], current: Optional[int] = None) -> Optional[str]:
+    """One-line version tacked onto each utterance — short on purpose, since
+    it rides along with every single thing you say."""
+    if not monitors:
+        return None
+    parts = ", ".join(f"{m.number}) {m.name} {m.width}x{m.height}" for m in monitors)
+    line = f"{len(monitors)} monitors: {parts}"
+    if current is not None and 0 <= current < len(monitors):
+        line += f"; Bolt is on {monitors[current].number}"
+    return line
+
+
+def annotate(text: str, monitors: list[Monitor], current: Optional[int] = None) -> str:
+    """Attach the screen summary as a separate aside, matching the style of
+    screen_context.annotate() so the model can ignore it when irrelevant."""
+    text = (text or "").strip()
+    line = summary(monitors, current)
+    if not text or not line:
+        return text
+    return f"{text}\n\n[{line}]"

bolt_pet/pet_actions.py

@@ -29,8 +29,18 @@ ANCHORS = (
 
 EMOTES = ("wave", "hop", "spin", "nod", "shake", "bounce", "wiggle")
 
+# Where `petctl jump` can be aimed. A bare number (1-based) works too, as does
+# any unique part of a monitor's name — resolution lives in monitors.resolve().
+MONITOR_SPECS = (
+    "next", "prev", "primary", "other", "random",
+    "left", "right", "up", "down",
+)
+
 HELP = (
     "petctl move <x> <y> | <" + "|".join(ANCHORS) + ">\n"
+    "petctl jump <monitor number|" + "|".join(MONITOR_SPECS) + "|name>\n"
+    "petctl monitors\n"
+    "petctl read [monitor number|here|all]\n"
     "petctl emote <" + "|".join(EMOTES) + ">\n"
     "petctl say <text>\n"
     "petctl wander on|off\n"
@@ -82,6 +92,24 @@ def parse(command: str) -> Optional[dict]:
             raise ActionError(f"unknown position {args[0]!r}; try one of: " + ", ".join(ANCHORS))
         return {"action": "move", "anchor": anchor}
 
+    if verb in ("jump", "monitor", "screen"):
+        if not args:
+            raise ActionError(
+                "jump needs a monitor: a number, a name, or one of "
+                + ", ".join(MONITOR_SPECS)
+            )
+        # The spec isn't validated here on purpose: which monitors exist is a
+        # runtime fact this pure module doesn't have. monitors.resolve() does
+        # it once the published screen list is in hand.
+        return {"action": "jump", "target": " ".join(args).strip()}
+
+    if verb in ("monitors", "screens", "displays"):
+        return {"action": "monitors"}
+
+    if verb in ("read", "look", "ocr", "see"):
+        target = (" ".join(args).strip() or "here").lower()
+        return {"action": "read", "target": target}
+
     if verb in ("emote", "do"):
         if not args:
             raise ActionError("emote needs a name: " + ", ".join(EMOTES))
@@ -124,6 +152,8 @@ def describe(action: dict) -> str:
     if kind == "move":
         where = action.get("anchor") or f"({action.get('x')}, {action.get('y')})"
         return f"[pet] walking to {where}"
+    if kind == "jump":
+        return f"[pet] jumping to monitor {action['target']}"
     if kind == "emote":
         return f"[pet] {action['emote']}"
     if kind == "say":

bolt_pet/screen_text.py

@@ -0,0 +1,187 @@
+"""Reading the text that's actually on a monitor, via screenshot + OCR.
+
+This is the "Bolt can see what's on screen" half of the screen features. It is
+**pull, not push**: nothing here runs on its own. The server has to ask, by
+relaying `petctl read`, and the recognised text goes back as that command's
+output through the existing tool-result relay (see server_client.converse).
+That's deliberate on two counts — OCR of a 4K screen costs a second or two,
+which would be tacked onto every single utterance if it ran automatically, and
+"screen contents leave this machine" should be a thing Bolt decides to do and
+you can see in the log, not a silent constant.
+
+Both halves are optional and soft-fail with a reason, the way hotkey.py does:
+capture needs `mss`, recognition needs a Tesseract or RapidOCR install. With
+neither, `petctl read` reports what's missing instead of raising, and the rest
+of the pet carries on.
+
+The pure parts (cleaning OCR output, formatting the reply, deciding which
+engine to use given what's installed) are split out and unit tested; only
+capture and the OCR call itself need a real screen.
+"""
+
+from __future__ import annotations
+
+import re
+import shutil
+from typing import Callable, Optional
+
+from .monitors import Monitor
+
+DEFAULT_MAX_CHARS = 4000
+
+INSTALL_HINT = (
+    "install one of: `pip install mss pytesseract` + `sudo apt install "
+    "tesseract-ocr` (fastest), or `pip install mss rapidocr-onnxruntime` "
+    "(no system package needed)"
+)
+
+# Lines that are almost certainly OCR noise rather than text: window chrome
+# fragments, isolated punctuation, single stray characters.
+_MIN_MEANINGFUL = 2
+
+
+def _module_available(name: str) -> bool:
+    import importlib.util
+
+    try:
+        return importlib.util.find_spec(name) is not None
+    except (ImportError, ValueError):
+        return False
+
+
+# ── pure helpers (unit tested; no screen, no OCR engine needed) ──────────────
+
+def resolve_engine(
+    has_module: Callable[[str], bool] = _module_available,
+    which: Callable[[str], Optional[str]] = shutil.which,
+) -> tuple[Optional[str], str]:
+    """Pick an OCR engine from what's installed.
+
+    Returns `(engine, reason)`. *engine* is None when nothing usable is
+    present, and *reason* then explains what to install. Probes are injected
+    so this is testable on a machine with a different set of things installed.
+    """
+    if has_module("pytesseract") and which("tesseract"):
+        return "pytesseract", ""
+    if has_module("rapidocr_onnxruntime"):
+        return "rapidocr", ""
+    if has_module("pytesseract") and not which("tesseract"):
+        return None, (
+            "pytesseract is installed but the tesseract binary isn't on PATH "
+            "(try: sudo apt install tesseract-ocr)"
+        )
+    return None, f"no OCR engine available — {INSTALL_HINT}"
+
+
+def capture_available(has_module: Callable[[str], bool] = _module_available) -> bool:
+    return has_module("mss")
+
+
+def clean_ocr_text(raw: str, max_chars: int = DEFAULT_MAX_CHARS) -> str:
+    """Squeeze raw OCR output into something worth sending.
+
+    Screen OCR produces a lot of junk — single stray glyphs off window
+    borders, runs of blank lines, the same toolbar label recognised twice. All
+    of that costs tokens and tells the model nothing, so it goes.
+    """
+    if not raw:
+        return ""
+    lines: list[str] = []
+    for line in raw.splitlines():
+        line = re.sub(r"[^\S\n]+", " ", line).strip()
+        if not line:
+            continue
+        if len(re.sub(r"[^0-9A-Za-z]", "", line)) < _MIN_MEANINGFUL:
+            continue
+        if lines and line == lines[-1]:
+            continue  # consecutive duplicate
+        lines.append(line)
+    text = "\n".join(lines)
+    if max_chars and len(text) > max_chars:
+        text = text[: max_chars - 1].rstrip() + "…"
+        text += "\n[truncated]"
+    return text
+
+
+def format_reading(monitor: Optional[Monitor], text: str) -> str:
+    """The tool output handed back for `petctl read`."""
+    where = f"monitor {monitor.number} ({monitor.name})" if monitor else "screen"
+    if not text.strip():
+        return f"[pet] read {where}: no text recognised"
+    return f"[pet] text on {where}:\n{text}"
+
+
+# ── capture + recognition (needs a real screen) ──────────────────────────────
+
+def capture(monitor: Monitor):
+    """Grab *monitor* as a PIL image, or None if capture isn't available."""
+    try:
+        import mss
+        from PIL import Image
+    except ImportError:
+        return None
+    try:
+        box = {
+            "left": monitor.x,
+            "top": monitor.y,
+            "width": monitor.width,
+            "height": monitor.height,
+        }
+        with mss.mss() as sct:
+            shot = sct.grab(box)
+        return Image.frombytes("RGB", shot.size, shot.bgra, "raw", "BGRX")
+    except Exception:
+        return None
+
+
+def _ocr(image, engine: str) -> str:
+    if engine == "pytesseract":
+        import pytesseract
+
+        # Grayscale first: tesseract is measurably better on it than on the
+        # colour desktop, and it's a cheap conversion.
+        return pytesseract.image_to_string(image.convert("L"))
+    if engine == "rapidocr":
+        import numpy as np
+        from rapidocr_onnxruntime import RapidOCR
+
+        result, _ = RapidOCR()(np.array(image))
+        if not result:
+            return ""
+        return "\n".join(line[1] for line in result)
+    return ""
+
+
+def read_monitor(monitor: Monitor, max_chars: int = DEFAULT_MAX_CHARS) -> str:
+    """OCR one screen and return the formatted tool output.
+
+    Never raises: every failure path returns a sentence explaining itself,
+    because the return value goes straight back to the server as the result of
+    a command Bolt chose to run.
+    """
+    if not capture_available():
+        return f"[pet] can't capture the screen — {INSTALL_HINT}"
+    engine, reason = resolve_engine()
+    if engine is None:
+        return f"[pet] can't read the screen — {reason}"
+    image = capture(monitor)
+    if image is None:
+        return (
+            f"[pet] couldn't capture monitor {monitor.number} "
+            "(is this a Wayland session? mss needs X11)"
+        )
+    try:
+        raw = _ocr(image, engine)
+    except Exception as exc:
+        return f"[pet] OCR failed on monitor {monitor.number}: {exc}"
+    return format_reading(monitor, clean_ocr_text(raw, max_chars))
+
+
+def read_monitors(monitors: list[Monitor], max_chars: int = DEFAULT_MAX_CHARS) -> str:
+    """OCR several screens, splitting the character budget between them."""
+    if not monitors:
+        return "[pet] no monitor information available"
+    if len(monitors) == 1:
+        return read_monitor(monitors[0], max_chars)
+    share = max(400, max_chars // len(monitors))
+    return "\n\n".join(read_monitor(m, share) for m in monitors)

bolt_pet/server_client.py

@@ -20,7 +20,7 @@ from typing import Callable, Optional
 
 import requests
 
-from . import config
+from . import config, sudo_askpass
 
 _MAX_RELAY_HOPS = 16
 
@@ -42,12 +42,25 @@ def check_health(timeout: float = 10.0) -> dict:
 def run_local_command(command: str, timeout: int = None) -> str:
     """Execute a command relayed by the server, exactly as bolt_desk.py does —
     "full desktop control" for things like "open firefox" or "how full is my
-    disk". Runs as the current desktop user. See README security notes."""
+    disk". Runs as the current desktop user. See README security notes.
+
+    `sudo` gets special handling: the pet has no terminal, so sudo would sit
+    waiting on a tty that nobody is looking at. With SUDO_ASKPASS_PROMPT on,
+    bare `sudo` becomes `sudo -A` and the password is collected in a desktop
+    dialog you have to answer — which also gives those commands a longer
+    timeout, since a human has to notice the window and type."""
+    env = None
+    if config.SUDO_ASKPASS_PROMPT and sudo_askpass.needs_password_prompt(command):
+        helper = sudo_askpass.find_helper()
+        if helper:
+            env = sudo_askpass.environment(helper)
+            command = sudo_askpass.add_askpass_flag(command)
+            timeout = timeout or config.SUDO_COMMAND_TIMEOUT_SECONDS
     timeout = timeout or config.COMMAND_TIMEOUT_SECONDS
     try:
         completed = subprocess.run(
             command, shell=True, capture_output=True, text=True,
-            timeout=timeout, cwd=str(Path.home()),
+            timeout=timeout, cwd=str(Path.home()), env=env,
         )
         output = (completed.stdout or "") + (completed.stderr or "")
         return f"[exit {completed.returncode}]\n{output}"[:6000]
@@ -102,6 +115,37 @@ def converse(
     raise ServerError(str(payload.get("error") or "unknown server response"))
 
 
+def list_outbox_files(timeout: float = 15.0) -> list:
+    """Files the server has queued for this session via its deliver_files
+    tool (e.g. "send me that report" during a conversation) — each entry has
+    id/name/size. Downloading one (download_outbox_file) dequeues it
+    server-side, so a file is only ever handed out once."""
+    try:
+        response = requests.get(
+            f"{config.SERVER_URL}/desk/files",
+            params={"session_id": config.SESSION_ID},
+            headers=_headers(), timeout=timeout,
+        )
+        response.raise_for_status()
+        return list(response.json().get("files") or [])
+    except Exception as exc:
+        raise ServerError(f"couldn't list delivered files: {exc}") from exc
+
+
+def download_outbox_file(file_id: str, timeout: float = 60.0) -> bytes:
+    """Fetches and dequeues one file listed by list_outbox_files()."""
+    try:
+        response = requests.get(
+            f"{config.SERVER_URL}/desk/files/{file_id}",
+            params={"session_id": config.SESSION_ID},
+            headers=_headers(), timeout=timeout,
+        )
+        response.raise_for_status()
+        return response.content
+    except Exception as exc:
+        raise ServerError(f"couldn't download delivered file {file_id!r}: {exc}") from exc
+
+
 def report_status(timeout: float = 15.0) -> Optional[str]:
     """Heartbeat — lets the desk API attach a pending spoken announcement
     (proactive nudges, reminders fired since the last heartbeat) that the pet

bolt_pet/speech_text.py

@@ -118,6 +118,22 @@ def for_speech(text: str) -> str:
     return text.strip()
 
 
+def is_question(text: str) -> bool:
+    """True if the reply *ends* by asking the user something — the cue for
+    the pet to keep listening instead of making you say the wake word again.
+
+    Deliberately only looks at the end. A reply that asks something in
+    passing ("What time is it? It's 7:15.") isn't waiting on an answer,
+    whereas one that finishes on a question mark is. The test runs on the
+    spoken form, so a '?' that only exists inside a stripped code block or a
+    URL doesn't count, and trailing decoration (emoji, quotes, brackets) is
+    peeled off first so "Ready to go? 🚀" still reads as a question."""
+    spoken = for_speech(text)
+    while spoken and not (spoken[-1].isalnum() or spoken[-1] == "?"):
+        spoken = spoken[:-1]
+    return spoken.endswith("?")
+
+
 def for_display(text: str) -> str:
     """What the speech bubble shows: markdown syntax removed (the bubble
     can't render it) but emoji and layout-ish punctuation left alone."""

bolt_pet/sudo_askpass.py

@@ -0,0 +1,145 @@
+"""Graphical password prompts for server-relayed `sudo` commands.
+
+The pet has no terminal. When the server relays something like
+`sudo apt update`, sudo tries to read a password from a tty, finds none (or
+finds the terminal the pet was launched from, which you're not looking at),
+and the command fails with no way to answer it.
+
+sudo's own answer to this is SUDO_ASKPASS: with `-A`, it runs a helper
+program and reads the password from the helper's stdout instead of a tty.
+Any GUI prompt that prints what was typed works, so this module finds a real
+askpass binary if one is installed and otherwise generates a one-line wrapper
+around zenity/kdialog, which every desktop has one of.
+
+Worth being clear about what this changes: the prompt is a *feature*, not
+just plumbing. Server-relayed commands already run as your desktop user (see
+server_client.run_local_command); this lets them ask to run as root, and the
+dialog is the only thing standing between "Bolt decided to run sudo" and it
+happening. Leave SUDO_ASKPASS_PROMPT on, and read the dialogs.
+
+The parts that decide *what* to run are pure functions so they're tested
+without a display, a password, or a working sudo.
+"""
+
+from __future__ import annotations
+
+import os
+import re
+import shutil
+import stat
+from pathlib import Path
+from typing import Callable, Optional
+
+from . import config
+
+# Real askpass binaries, in preference order. These are purpose-built for
+# this (they grab the keyboard, hide the input, and don't leave the password
+# in a process argument), so they win over a generated wrapper.
+_KNOWN_HELPERS = (
+    "/usr/bin/ssh-askpass",
+    "/usr/lib/ssh/ssh-askpass",
+    "/usr/lib/openssh/gnome-ssh-askpass3",
+    "/usr/lib/openssh/gnome-ssh-askpass",
+    "/usr/libexec/openssh/ssh-askpass",
+    "/usr/bin/ksshaskpass",
+    "/usr/bin/lxqt-openssh-askpass",
+)
+
+# Dialog tools we can wrap when no askpass binary exists. Each must print the
+# typed password to stdout and nothing else.
+_WRAPPABLE = {
+    "zenity": '{tool} --password --title="Bolt" --text="$1" 2>/dev/null',
+    "kdialog": '{tool} --password "$1" --title "Bolt" 2>/dev/null',
+}
+
+# `sudo` at the start of the command or right after a shell separator, not
+# already carrying a flag. Deliberately conservative: a `sudo` inside a
+# quoted string or a heredoc is left alone, because rewriting it could change
+# what the command means.
+_SUDO = re.compile(r"(^|[;&|]\s*|\n\s*)(sudo)(\s+)(?!-)")
+
+
+def add_askpass_flag(command: str) -> str:
+    """Insert `-A` after each bare `sudo`, so it prompts through the helper
+    instead of a tty. Commands that already pass a flag (`sudo -n`, `sudo -A`,
+    `sudo -u bob`) are left exactly as they are — the caller was explicit."""
+    return _SUDO.sub(r"\1\2 -A\3", command or "")
+
+
+def needs_password_prompt(command: str) -> bool:
+    """True if *command* has a `sudo` that might sit waiting on a dialog.
+    Used to give those commands a longer timeout — 30 seconds is fine for a
+    shell command and nowhere near enough for a human to notice a window,
+    read it, and type a password."""
+    return bool(_SUDO.search(command or ""))
+
+
+def helper_script(tool_path: str) -> str:
+    """The wrapper script for a dialog *tool_path*. sudo passes its prompt
+    ("[sudo] password for maji:") as $1, which is worth showing — it names
+    the user the password is for."""
+    name = Path(tool_path).name
+    body = _WRAPPABLE[name].format(tool=tool_path)
+    return f"#!/bin/sh\n# Generated by bolt-pet. Prints the typed password on stdout for sudo -A.\n{body}\n"
+
+
+def _default_cache_dir() -> Path:
+    base = os.environ.get("XDG_CACHE_HOME") or (Path.home() / ".cache")
+    return Path(base) / "bolt-pet"
+
+
+def find_helper(
+    configured: str = None,
+    is_executable: Callable[[str], bool] = None,
+    which: Callable[[str], Optional[str]] = None,
+    cache_dir: Path = None,
+    write: bool = True,
+) -> Optional[str]:
+    """Path to an askpass helper, or None if the desktop has nothing we can
+    use. Order: whatever SUDO_ASKPASS_HELPER names, then a real askpass
+    binary, then a generated wrapper around zenity/kdialog.
+
+    The lookups are injectable so the resolution order is testable on a box
+    with a different set of these installed than yours."""
+    configured = config.SUDO_ASKPASS_HELPER if configured is None else configured
+    is_executable = is_executable or (lambda path: os.path.isfile(path) and os.access(path, os.X_OK))
+    which = which or shutil.which
+
+    if configured:
+        return configured if is_executable(configured) else None
+
+    for candidate in _KNOWN_HELPERS:
+        if is_executable(candidate):
+            return candidate
+
+    for tool in _WRAPPABLE:
+        tool_path = which(tool)
+        if not tool_path:
+            continue
+        if not write:
+            return tool_path
+        return _write_wrapper(tool_path, cache_dir or _default_cache_dir())
+    return None
+
+
+def _write_wrapper(tool_path: str, cache_dir: Path) -> Optional[str]:
+    """Drop the wrapper script somewhere sudo can execute it. Mode 0700: it
+    isn't secret, but it's a thing that pops up a password box, so nobody
+    else on the machine gets to edit it."""
+    try:
+        cache_dir.mkdir(parents=True, exist_ok=True)
+        script = cache_dir / "askpass.sh"
+        source = helper_script(tool_path)
+        if not script.exists() or script.read_text(encoding="utf-8") != source:
+            script.write_text(source, encoding="utf-8")
+        script.chmod(stat.S_IRWXU)
+        return str(script)
+    except Exception:
+        return None  # no prompt is better than a crashed command relay
+
+
+def environment(helper: str, base: dict = None) -> dict:
+    """The subprocess environment with SUDO_ASKPASS pointed at *helper*."""
+    env = dict(os.environ if base is None else base)
+    env["SUDO_ASKPASS"] = helper
+    return env

bolt_pet/ui/app.py

@@ -46,6 +46,13 @@ def run() -> int:
     controller.finished.connect(thread.quit)
 
     window.talk_requested.connect(controller.request_talk_now)
+    # The window owns the screen list and tells the controller about it, so
+    # both ends agree on what "monitor 2" means (see monitors.py).
+    window.monitors_changed.connect(controller.set_monitors)
+    window.pet_monitor_changed.connect(controller.set_pet_monitor)
+    # PetWindow publishes once in its constructor, which ran before those
+    # connections existed — so say it again now that anyone is listening.
+    window.publish_monitors()
     window.copied.connect(lambda text: _log(f"Copied to clipboard: {text[:60]}"))
 
     history_window = HistoryWindow(controller.history)

bolt_pet/ui/pet_window.py

@@ -20,8 +20,9 @@ from PySide6.QtGui import (
 from PySide6.QtWidgets import QApplication, QWidget
 
 from .. import config
+from ..monitors import Monitor
 from ..state import PetState
-from .sprite import SpriteSet
+from .sprite import WALK, SpriteSet
 
 _DRAG_THRESHOLD_PX = 4
 # Movement runs on its own ~30fps timer, independent of the (slower) sprite
@@ -29,6 +30,12 @@ _DRAG_THRESHOLD_PX = 4
 _WANDER_TICK_MS = 33
 _EMOTE_TICKS = 36  # ~1.2s per emote at the tick rate above
 _NAP_OPACITY = 0.35
+# How far the pet travels per walk-cycle frame. The cycle is advanced by
+# distance rather than by the animation clock so a planted paw tracks backwards
+# at exactly the speed the window moves forwards — drive it off a timer instead
+# and the feet skate whenever PET_WANDER_SPEED doesn't happen to match the fps.
+# Eight frames at 13px is a ~104px stride cycle, a bit under the pet's width.
+_WALK_PIXELS_PER_FRAME = 13.0
 
 
 def emote_transform(emote: str, progress: float) -> tuple[float, float, float, float]:
@@ -164,6 +171,12 @@ class SpeechBubble(QWidget):
 class PetWindow(QWidget):
     talk_requested = Signal()
     copied = Signal(str)  # bubble text the user just put on the clipboard
+    # The screen layout, published *to* the controller (queued, cross-thread).
+    # The window is the only thing allowed to ask Qt about screens, so the
+    # controller and the window can never disagree about what "monitor 2"
+    # means — see monitors.py.
+    monitors_changed = Signal(list)  # list[monitors.Monitor]
+    pet_monitor_changed = Signal(int)  # 0-based index the pet is standing on
 
     def __init__(self, sprite_dir: Optional[Path] = None, size: Optional[int] = None):
         super().__init__()
@@ -201,6 +214,10 @@ class PetWindow(QWidget):
         self._next_wander_at = 0.0
         self._bob_offset = 0
         self._bob_phase = 0.0
+        self._walking = False
+        self._facing = 1  # +1 right, -1 left; the walk art is drawn facing right
+        self._walk_distance = 0.0
+        self._mirror_cache: dict[int, QPixmap] = {}
         self._schedule_next_wander()
         self._wander_timer = QTimer(self)
         self._wander_timer.timeout.connect(self._movement_tick)
@@ -210,6 +227,18 @@ class PetWindow(QWidget):
         self.set_click_through(config.PET_CLICK_THROUGH)
         self._place_start_position()
 
+        self._monitors: list[Monitor] = []
+        self._pet_monitor: Optional[int] = None
+        self._last_published_pos: Optional[QPoint] = None
+        app = QApplication.instance()
+        if app is not None:
+            # Screens come and go — a laptop docking, a TV waking up. Republish
+            # rather than letting Bolt jump to a monitor that's been unplugged.
+            app.screenAdded.connect(lambda _s: self.publish_monitors())
+            app.screenRemoved.connect(lambda _s: self.publish_monitors())
+            app.primaryScreenChanged.connect(lambda _s: self.publish_monitors())
+        self.publish_monitors()
+
     # ── placement ────────────────────────────────────────────────────────
 
     def _place_start_position(self) -> None:
@@ -244,6 +273,8 @@ class PetWindow(QWidget):
             if target is not None:
                 self._wander_target = target
                 self._commanded_move = True  # overrides the idle-only rule
+        elif kind == "jump":
+            self.jump_to_monitor(int(action["monitor"]))
         elif kind == "emote":
             self.start_emote(action["emote"])
         elif kind == "say":
@@ -378,6 +409,98 @@ class PetWindow(QWidget):
         """Stroll immediately (tray menu / anything that wants a nudge)."""
         self._next_wander_at = 0.0
 
+    # ── monitors ─────────────────────────────────────────────────────────
+
+    def _build_monitors(self) -> list[Monitor]:
+        """Snapshot Qt's screen list as plain dataclasses.
+
+        Full `geometry()`, not `availableGeometry()`: these coordinates are
+        what a screen grab gets cropped to, and a grab doesn't stop at the
+        taskbar. Placement uses availableGeometry separately.
+        """
+        primary = QApplication.primaryScreen()
+        out = []
+        for index, screen in enumerate(QApplication.screens()):
+            geo = screen.geometry()
+            out.append(
+                Monitor(
+                    index=index,
+                    name=screen.name() or f"screen-{index + 1}",
+                    x=geo.x(),
+                    y=geo.y(),
+                    width=geo.width(),
+                    height=geo.height(),
+                    primary=screen is primary,
+                )
+            )
+        return out
+
+    def publish_monitors(self, force: bool = True) -> None:
+        """Push the current layout to whoever's listening (the controller).
+
+        *force* re-emits even when nothing changed, which is what the initial
+        wiring in ui/app.py needs: this window is built before the controller
+        exists, so the constructor's first publish goes to nobody.
+        """
+        monitors = self._build_monitors()
+        changed = monitors != self._monitors
+        self._monitors = monitors
+        if changed or force:
+            self.monitors_changed.emit(monitors)
+        self._publish_pet_monitor(force=True)
+
+    def monitors(self) -> list[Monitor]:
+        return list(self._monitors)
+
+    def current_monitor_index(self) -> Optional[int]:
+        center = self.frameGeometry().center()
+        screens = QApplication.screens()
+        if not screens:
+            return None
+        screen = QApplication.screenAt(center)
+        if screen is not None:
+            try:
+                return screens.index(screen)
+            except ValueError:
+                pass
+        # Straddling a gap or dragged off the desktop entirely — fall back to
+        # whichever screen centre is nearest rather than reporting nothing.
+        best = min(
+            range(len(screens)),
+            key=lambda i: (screens[i].geometry().center() - center).manhattanLength(),
+        )
+        return best
+
+    def _publish_pet_monitor(self, force: bool = False) -> None:
+        index = self.current_monitor_index()
+        if index is None:
+            return
+        if force or index != self._pet_monitor:
+            self._pet_monitor = index
+            self.pet_monitor_changed.emit(index)
+
+    def jump_to_monitor(self, index: int) -> None:
+        """Teleport to *index* (0-based, resolved by the controller) and land
+        with a hop. Instant rather than a stroll — Bolt asked to *jump*, and
+        walking between screens would take the long way across the desktop."""
+        screens = QApplication.screens()
+        if not (0 <= index < len(screens)):
+            return
+        geo = screens[index].availableGeometry()
+        point = self._clamp_to_screen(
+            QPoint(
+                geo.left() + (geo.width() - self.width()) // 2,
+                geo.top() + (geo.height() - self.height()) // 2,
+            ),
+            geo,
+        )
+        self._stop_walking()  # drop any stroll in flight, or it walks straight back
+        self.move(point)
+        self._schedule_next_wander()
+        self._publish_pet_monitor(force=True)
+        self.start_emote("hop")
+        self.update()
+
     def _screen_geometry(self):
         # screenAt() so a multi-monitor setup keeps the pet on the screen
         # it's currently standing on rather than yanking it to the primary.
@@ -389,12 +512,17 @@ class PetWindow(QWidget):
         self._next_wander_at = time.monotonic() + random.uniform(0.5 * base, 1.5 * base)
 
     def _stop_walking(self) -> None:
-        if self._wander_target is None and not self._bob_offset:
+        if self._wander_target is None and not self._bob_offset and not self._walking:
             return
         self._wander_target = None
         self._commanded_move = False
         self._bob_phase = 0.0
         self._bob_offset = 0
+        self._walking = False
+        self._walk_distance = 0.0
+        # Back to a standing frame, so the next stroll starts from a contact
+        # pose instead of mid-stride.
+        self.sprites.get(WALK).reset()
         self.update()
 
     def snap_to_edge(self) -> bool:
@@ -447,6 +575,13 @@ class PetWindow(QWidget):
         wandering only happens when it's otherwise unoccupied."""
         self._advance_emote()
         self._wander_tick()
+        # Report crossing a screen boundary — by strolling, by being dragged,
+        # by anything. Guarded on the position actually changing so the common
+        # case (a stationary pet, 30x a second) costs one comparison.
+        position = self.pos()
+        if position != self._last_published_pos:
+            self._last_published_pos = position
+            self._publish_pet_monitor()
 
     def _wander_tick(self) -> None:
         # Only stroll while genuinely idle: not mid-drag, not napping, not
@@ -484,11 +619,51 @@ class PetWindow(QWidget):
             self.snap_to_edge()
         else:
             self.move(round(here.x() + dx / distance * step), round(here.y() + dy / distance * step))
-            self._bob_phase += 0.45  # little walk-cycle hop
+            self._advance_walk(dx, dy, step)
-            self._bob_offset = int(round(-2.5 * abs(math.sin(self._bob_phase))))
             self.update()
         self._reposition_bubble()
 
+    def _advance_walk(self, dx: float, dy: float, step: float) -> None:
+        """Drive the walk cycle from distance travelled (see the constant).
+
+        Falls back to the old bob-in-code if there's no walk art, so a sprite
+        folder without a walk/ directory still looks like it's moving rather
+        than sliding perfectly flat.
+        """
+        self._walking = True
+        # Only turn on meaningful horizontal travel: a near-vertical stroll
+        # would otherwise flip him back and forth on rounding noise.
+        if abs(dx) > 1.0:
+            self._facing = 1 if dx > 0 else -1
+        if not self.sprites.has(WALK):
+            self._bob_phase += 0.45
+            self._bob_offset = int(round(-2.5 * abs(math.sin(self._bob_phase))))
+            return
+        self._bob_offset = 0  # the walk frames carry their own weight shift
+        self._walk_distance += step
+        while self._walk_distance >= _WALK_PIXELS_PER_FRAME:
+            self._walk_distance -= _WALK_PIXELS_PER_FRAME
+            self.sprites.get(WALK).advance()
+
+    def _animation_key(self):
+        """Walking overrides the state animation — but only while genuinely
+        idle-and-moving, so he doesn't trot on the spot mid-sentence."""
+        if self._walking and self.sprites.has(WALK):
+            return WALK
+        return self._current_state
+
+    def _oriented(self, pixmap: Optional[QPixmap]) -> Optional[QPixmap]:
+        """Mirror the (right-facing) walk art when he's heading left. Cached
+        per source frame — flipping on every paint would be wasteful at 30fps."""
+        if pixmap is None or self._facing >= 0:
+            return pixmap
+        key = pixmap.cacheKey()
+        mirrored = self._mirror_cache.get(key)
+        if mirrored is None:
+            mirrored = pixmap.transformed(QTransform().scale(-1, 1), Qt.SmoothTransformation)
+            self._mirror_cache[key] = mirrored
+        return mirrored
+
     # ── state / speech ──────────────────────────────────────────────────
 
     def set_state(self, state: PetState) -> None:
@@ -514,6 +689,11 @@ class PetWindow(QWidget):
     # ── animation ────────────────────────────────────────────────────────
 
     def _advance_frame(self) -> None:
+        # While walking the cycle is stepped by _advance_walk from distance
+        # travelled; letting this timer also advance it would double-step it
+        # and put the feet out of sync with the movement.
+        if self._walking and self.sprites.has(WALK):
+            return
         self.sprites.get(self._current_state).advance()
         self.update()
 
@@ -521,7 +701,10 @@ class PetWindow(QWidget):
         painter = QPainter(self)
         painter.setRenderHint(QPainter.Antialiasing)
         painter.setRenderHint(QPainter.SmoothPixmapTransform)
-        pixmap: Optional[QPixmap] = self.sprites.get(self._current_state).current()
+        key = self._animation_key()
+        pixmap: Optional[QPixmap] = self.sprites.get(key).current()
+        if key == WALK:
+            pixmap = self._oriented(pixmap)
         if pixmap is None:
             self._apply_input_mask(None, 0, 0)
             return

bolt_pet/ui/sprite.py

@@ -95,17 +95,46 @@ def _load_frames_from_dir(directory: Path, size: int) -> list[QPixmap]:
     return frames
 
 
+WALK = "walk"
+
+# Animations that aren't pipeline states. Walking is a property of *movement*,
+# orthogonal to whether the pet is idle/listening/talking, so it deliberately
+# isn't a PetState — state.py stays a description of the conversation, not of
+# the body. Loaded the same way, keyed by name.
+EXTRA_ANIMATIONS = (WALK,)
+
+
 class SpriteSet:
-    """All animations for every PetState, loaded from *sprite_dir*."""
+    """All animations for every PetState, plus the extras, from *sprite_dir*."""
 
     def __init__(self, sprite_dir: Path = DEFAULT_SPRITE_DIR, size: int = 160):
         self.size = size
-        self._animations: dict[PetState, SpriteAnimation] = {}
+        self._animations: dict[str, SpriteAnimation] = {}
+        self._loaded: set[str] = set()  # keys backed by real art, not placeholders
         for state in PetState:
             frames = _load_frames_from_dir(sprite_dir / state.value, size)
-            if not frames:
+            if frames:
+                self._loaded.add(state.value)
+            else:
                 frames = _placeholder_frames(state, size)
-            self._animations[state] = SpriteAnimation(frames)
+            self._animations[state.value] = SpriteAnimation(frames)
+        for name in EXTRA_ANIMATIONS:
+            frames = _load_frames_from_dir(sprite_dir / name, size)
+            if frames:
+                self._loaded.add(name)
+                self._animations[name] = SpriteAnimation(frames)
 
-    def get(self, state: PetState) -> SpriteAnimation:
+    @staticmethod
-        return self._animations[state]
+    def _key(key) -> str:
+        return key.value if isinstance(key, PetState) else str(key)
+
+    def get(self, key) -> SpriteAnimation:
+        """Animation for a PetState or an extra name. Unknown/absent extras
+        fall back to idle, so a sprite folder with no walk/ still runs."""
+        return self._animations.get(self._key(key)) or self._animations[PetState.IDLE.value]
+
+    def has(self, key) -> bool:
+        """True only when real frames were found — the caller uses this to
+        decide whether to use an extra animation at all, rather than being
+        handed a placeholder blob that looks nothing like walking."""
+        return self._key(key) in self._loaded

bolt_pet/updater.py

@@ -183,6 +183,22 @@ def current_ref(run: GitRunner) -> str:
     return output.strip()
 
 
+def already_at_tag(run: GitRunner, tag: str) -> bool:
+    """True if HEAD is already the commit *tag* points at.
+
+    Guards the loop you get when a release is cut without bumping
+    __version__ in the tagged commit: the checkout succeeds (it's a no-op),
+    the pet restarts, reads the same old __version__, sees the same "newer"
+    tag, and does it again — a restart every check, forever."""
+    code, head = run(["rev-parse", "HEAD"])
+    if code != 0 or not head.strip():
+        return False
+    code, target = run(["rev-parse", f"tags/{tag}^{{commit}}"])
+    if code != 0 or not target.strip():
+        return False  # tag isn't known locally yet, so we're certainly not on it
+    return head.strip() == target.strip()
+
+
 def _requirements_changed(run: GitRunner, before: str, after: str) -> bool:
     code, output = run(["diff", "--name-only", before, after, "--", "requirements.txt"])
     return code == 0 and bool(output.strip())
@@ -236,6 +252,14 @@ def apply_update(
     if code != 0:
         raise UpdateError(f"git fetch failed: {output}")
 
+    if already_at_tag(run, tag):
+        from . import __version__
+
+        raise UpdateError(
+            f"already checked out {tag}, but __version__ still reads {__version__} — "
+            f"bump it in the tagged commit, or every check re-applies the same release"
+        )
+
     code, output = run(["checkout", "--force", f"tags/{tag}"])
     if code != 0:
         raise UpdateError(f"git checkout {tag} failed: {output}")

requirements.txt

@@ -32,6 +32,18 @@ pynput>=1.7
 # Not imported by the app itself.
 Pillow>=10.0
 
+# Screen reading (`petctl read`) — Bolt OCRs a monitor and uses the text in
+# his reply. Both optional: without them `petctl read` reports what's missing
+# and the rest of the pet is unaffected.
+#   mss         screen capture. X11/Win32/macOS — NOT Wayland.
+#   pytesseract a thin wrapper; the actual engine is a system package:
+#                   sudo apt install tesseract-ocr
+# No-sudo alternative to those two lines: pip install rapidocr-onnxruntime
+# (pure pip, reuses the onnxruntime openwakeword already pulls in, slower to
+# start). screen_text.resolve_engine() picks whichever is present.
+mss>=9.0
+pytesseract>=0.3.10
+
 # Test runner (tests/ — pure logic, no audio hardware or display needed;
 # run with QT_QPA_PLATFORM=offscreen).
 pytest>=8.0

scripts/generate_bolt_sprites.py

@@ -0,0 +1,779 @@
+"""Draw Bolt — the pet — as per-state PNG frame sequences.
+
+Produces the `assets/sprites/<state>/frame_NN.png` convention that
+`bolt_pet/ui/sprite.py` loads (see `assets/sprites/README.md`). The art is
+generated rather than sourced so it stays editable: tweak a colour or a pose
+parameter here and re-run, instead of hand-editing 24 PNGs.
+
+    python scripts/generate_bolt_sprites.py                 # write into the real asset dir
+    python scripts/generate_bolt_sprites.py --out /tmp/prev # preview somewhere else
+
+Everything is drawn in normalised 0..1 coordinates on a square canvas and
+super-sampled `SS`x before being downscaled, because PIL's draw primitives
+have no antialiasing of their own.
+"""
+
+from __future__ import annotations
+
+import argparse
+import math
+from pathlib import Path
+
+from PIL import Image, ImageDraw
+
+SS = 4  # supersampling factor
+OUT = 320  # final frame size (2x the default PET_SIZE of 160)
+S = OUT * SS
+
+# --- palette ---------------------------------------------------------------
+# A cream shepherd-ish pup with a slate cap, amber eyes and a lightning blaze.
+C_OUTLINE = (34, 42, 58, 255)
+C_FUR = (246, 244, 238, 255)
+C_FUR_SHADE = (214, 210, 200, 255)
+C_DARK = (78, 92, 122, 255)
+C_DARK2 = (58, 70, 96, 255)
+C_INNER_EAR = (226, 154, 158, 255)
+C_BROW = (206, 166, 118, 255)
+# The far side of the walking pose. Distinctly darker than C_FUR_SHADE, which
+# is too close to the cream to read as "behind the dog" at 160px.
+C_FUR_FAR = (168, 176, 192, 255)
+C_NOSE = (40, 48, 66, 255)
+C_IRIS = (196, 128, 50, 255)
+C_PUPIL = (30, 36, 50, 255)
+C_WHITE = (255, 255, 255, 255)
+C_BOLT = (255, 206, 61, 255)
+C_COLLAR = (222, 84, 46, 255)
+C_TAG = (255, 198, 68, 255)
+C_TONGUE = (230, 116, 128, 255)
+C_GLOW = (92, 214, 244, 255)
+
+# --- layout constants (normalised) -----------------------------------------
+HEAD_CX, HEAD_CY = 0.50, 0.375
+HEAD_W, HEAD_H = 0.50, 0.44
+NECK_Y = 0.565  # head layer rotates about here so tilts pivot at the neck
+EAR_PIVOT = 0.335, 0.275
+
+OW = 0.0105  # outline width, normalised
+
+
+def px(v: float) -> float:
+    return v * S
+
+
+def _w(width: float) -> int:
+    return max(1, int(round(px(width))))
+
+
+def ell(d, cx, cy, w, h, fill, outline=C_OUTLINE, ow=OW):
+    d.ellipse(
+        [px(cx - w / 2), px(cy - h / 2), px(cx + w / 2), px(cy + h / 2)],
+        fill=fill,
+        outline=outline,
+        width=_w(ow) if outline else 0,
+    )
+
+
+def rrect(d, cx, cy, w, h, r, fill, outline=C_OUTLINE, ow=OW):
+    d.rounded_rectangle(
+        [px(cx - w / 2), px(cy - h / 2), px(cx + w / 2), px(cy + h / 2)],
+        radius=px(r),
+        fill=fill,
+        outline=outline,
+        width=_w(ow) if outline else 0,
+    )
+
+
+def poly(d, pts, fill, outline=C_OUTLINE, ow=OW):
+    d.polygon(
+        [(px(x), px(y)) for x, y in pts],
+        fill=fill,
+        outline=outline,
+        width=_w(ow) if outline else 0,
+    )
+
+
+def rotate_pts(pts, pivot, deg):
+    a = math.radians(deg)
+    ca, sa = math.cos(a), math.sin(a)
+    ox, oy = pivot
+    out = []
+    for x, y in pts:
+        dx, dy = x - ox, y - oy
+        out.append((ox + dx * ca - dy * sa, oy + dx * sa + dy * ca))
+    return out
+
+
+def lerp(a, b, t):
+    return a + (b - a) * t
+
+
+def bolt_shape(cx, cy, w, h):
+    """A lightning bolt polygon in a (w x h) box centred on (cx, cy)."""
+    unit = [
+        (0.62, 0.00),
+        (0.10, 0.56),
+        (0.44, 0.56),
+        (0.28, 1.00),
+        (0.90, 0.40),
+        (0.55, 0.40),
+        (0.80, 0.00),
+    ]
+    return [(cx + (u - 0.5) * w, cy + (v - 0.5) * h) for u, v in unit]
+
+
+# --- body ------------------------------------------------------------------
+def _tail_points(p, steps=26):
+    """Quadratic-bezier spine of the tail as (x, y, radius) samples.
+
+    Shared by the fill and outline passes so a wag can't move one and not the
+    other. The base sits deep inside the haunch, which is drawn over it, so
+    the tail reads as growing out of the body rather than floating beside it.
+    """
+    wag = p["tail"]
+    base = (0.620, 0.845)
+    ctrl = (0.955, 0.870 - 0.025 * wag)
+    end = (0.905, 0.605 - 0.065 * wag)
+    pts = []
+    for i in range(steps + 1):
+        t = i / steps
+        x = (1 - t) ** 2 * base[0] + 2 * (1 - t) * t * ctrl[0] + t**2 * end[0]
+        y = (1 - t) ** 2 * base[1] + 2 * (1 - t) * t * ctrl[1] + t**2 * end[1]
+        pts.append((x, y, lerp(0.080, 0.042, t)))
+    return pts
+
+
+def draw_tapered(d, pts, color_at):
+    """Draw a tapered limb from (x, y, radius) samples.
+
+    Two passes: circles along the spine for the fill, then the two silhouette
+    edges, so it reads as one solid shape instead of a string of beads.
+    *color_at* takes 0..1 along the length, which is how the tail gets its
+    cream tip.
+    """
+    last = len(pts) - 1
+    for i, (x, y, r) in enumerate(pts):
+        ell(d, x, y, r * 2, r * 2, color_at(i / last), outline=None)
+    for side in (1, -1):
+        edge = []
+        for i, (x, y, r) in enumerate(pts):
+            j = min(i + 1, last)
+            k = max(i - 1, 0)
+            tx, ty = pts[j][0] - pts[k][0], pts[j][1] - pts[k][1]
+            n = math.hypot(tx, ty) or 1e-6
+            nx, ny = -ty / n, tx / n
+            edge.append((x + nx * r * side, y + ny * r * side))
+        d.line([(px(x), px(y)) for x, y in edge], fill=C_OUTLINE, width=_w(OW), joint="curve")
+    x, y, r = pts[last]
+    ell(d, x, y, r * 2, r * 2, color_at(1.0))
+
+
+def draw_tail(d, p):
+    # Only the last stretch is the cream tip. The haunch hides the first ~half
+    # of the tail, so a generous tip leaves the visible part looking like a
+    # pale blob floating next to the dog rather than its tail.
+    draw_tapered(d, _tail_points(p), lambda t: C_DARK if t < 0.84 else C_FUR)
+
+
+def draw_body(d, p):
+    br = p["breathe"]
+    # haunches (sitting)
+    ell(d, 0.285, 0.795, 0.235, 0.275, C_DARK)
+    ell(d, 0.715, 0.795, 0.235, 0.275, C_DARK)
+    # torso
+    ell(d, 0.50, 0.745 - 0.004 * br, 0.455 + 0.012 * br, 0.395 + 0.014 * br, C_DARK)
+    # front legs
+    for cx in (0.415, 0.585):
+        rrect(d, cx, 0.845, 0.125, 0.215, 0.062, C_FUR)
+        ell(d, cx, 0.925, 0.155, 0.095, C_FUR)
+    # chest / belly blaze
+    ell(d, 0.50, 0.735 - 0.004 * br, 0.275 + 0.008 * br, 0.315 + 0.012 * br, C_FUR)
+    # toes
+    for cx in (0.415, 0.585):
+        for off in (-0.035, 0.0, 0.035):
+            d.arc(
+                [px(cx + off - 0.017), px(0.902), px(cx + off + 0.017), px(0.945)],
+                start=250,
+                end=290,
+                fill=C_FUR_SHADE,
+                width=_w(0.007),
+            )
+
+
+def draw_collar(d, p):
+    rrect(d, 0.50, 0.585, 0.315, 0.062, 0.031, C_COLLAR)
+    tag = C_GLOW if p.get("tag_glow") else C_TAG
+    ell(d, 0.50, 0.638, 0.082, 0.082, tag)
+    poly(d, bolt_shape(0.50, 0.638, 0.030, 0.052), C_OUTLINE, outline=None)
+
+
+# --- head ------------------------------------------------------------------
+# Ear outline in a *local* frame: origin at the base on the skull, +x points
+# outward (away from the muzzle), +y points up. Keeping it side-agnostic here
+# and mirroring at draw time avoids sign confusion — an earlier version mixed
+# the conventions and the ears flattened into a brim whenever they rotated.
+_EAR_LOCAL = [
+    (-0.058, -0.038),
+    (0.078, -0.038),
+    (0.092, 0.140),
+    (0.030, 0.248),
+    (-0.038, 0.122),
+]
+
+
+def _ear_polygon(side, lean_deg):
+    """Mirror + lean the local ear, returning canvas-space points.
+
+    *lean_deg* tips the ear away from vertical: 0 is fully perked, larger
+    values relax and eventually droop it out sideways.
+    """
+    a = math.radians(lean_deg)
+    ca, sa = math.cos(a), math.sin(a)
+    pivot_x = 0.5 + side * (0.5 - EAR_PIVOT[0])
+    pts = []
+    for x, y in _EAR_LOCAL:
+        rx = x * ca + y * sa
+        ry = -x * sa + y * ca
+        pts.append((pivot_x + side * rx, EAR_PIVOT[1] - ry))
+    return pts
+
+
+def draw_ears(d, p):
+    perk = p["ear"]
+    twitch = p.get("ear_twitch", 0.0)
+    for side in (-1, 1):
+        lean = 18.0 * (1.0 - perk) + 44.0 * max(0.0, -perk)
+        if side == 1:
+            lean -= twitch * 12.0
+        pts = _ear_polygon(side, lean)
+        poly(d, pts, C_DARK)
+        base_mid = (
+            (pts[0][0] + pts[1][0]) / 2,
+            (pts[0][1] + pts[1][1]) / 2,
+        )
+        inner = [(lerp(base_mid[0], x, 0.60), lerp(base_mid[1], y, 0.64)) for x, y in pts]
+        poly(d, inner, C_INNER_EAR, outline=None)
+
+
+def draw_cap(layer, p):
+    """Slate cap over the top of the head, clipped to the head silhouette."""
+    mask = Image.new("L", (S, S), 0)
+    ImageDraw.Draw(mask).ellipse(
+        [
+            px(HEAD_CX - HEAD_W / 2),
+            px(HEAD_CY - HEAD_H / 2),
+            px(HEAD_CX + HEAD_W / 2),
+            px(HEAD_CY + HEAD_H / 2),
+        ],
+        fill=255,
+    )
+    cap = Image.new("RGBA", (S, S), (0, 0, 0, 0))
+    dc = ImageDraw.Draw(cap)
+    ell(dc, HEAD_CX, 0.245, 0.54, 0.30, C_DARK, outline=None)
+    # brow dip between the eyes, so the cap reads as a marking not a helmet
+    ell(dc, HEAD_CX, 0.352, 0.155, 0.115, C_FUR, outline=None)
+    cap.putalpha(Image.composite(cap.getchannel("A"), Image.new("L", (S, S), 0), mask))
+    layer.alpha_composite(cap)
+
+
+def draw_eyes(d, p):
+    blink = p["blink"]
+    lx, ly = 0.383, 0.372
+    rx, ry = 0.617, 0.372
+    dx, dy = p.get("look", (0.0, 0.0))
+    for cx, cy in ((lx, ly), (rx, ry)):
+        if p.get("cross"):
+            for ang in (45, -45):
+                a = math.radians(ang)
+                hx, hy = 0.042 * math.cos(a), 0.042 * math.sin(a)
+                d.line(
+                    [px(cx - hx), px(cy - hy), px(cx + hx), px(cy + hy)],
+                    fill=C_OUTLINE,
+                    width=_w(0.014),
+                )
+            continue
+        if blink > 0.55:
+            d.arc(
+                [px(cx - 0.052), px(cy - 0.030), px(cx + 0.052), px(cy + 0.040)],
+                start=200,
+                end=340,
+                fill=C_OUTLINE,
+                width=_w(0.013),
+            )
+            continue
+        h = lerp(0.118, 0.030, blink)
+        ell(d, cx, cy, 0.106, h, C_WHITE)
+        if h > 0.06:
+            ell(d, cx + dx, cy + dy * 0.6, 0.082, min(h - 0.022, 0.092), C_IRIS, outline=None)
+            ell(d, cx + dx, cy + dy * 0.6, 0.046, min(h - 0.045, 0.056), C_PUPIL, outline=None)
+            ell(d, cx + dx - 0.020, cy + dy * 0.6 - 0.024, 0.030, 0.026, C_WHITE, outline=None)
+    # Tan brow dots on the slate cap (the shepherd/doberman marking) rather
+    # than dashes — as lines above the eyes they read as heavy eyelids and
+    # make an idle pet look permanently fed up.
+    raise_ = p.get("brow", 0.0)
+    angry = p.get("brow_angle", 0.0)
+    for side, cx in ((-1, lx), (1, rx)):
+        by = 0.291 - 0.020 * raise_
+        ell(
+            d,
+            cx + side * 0.006,
+            by + side * angry * 0.020,
+            0.062,
+            0.040,
+            C_BROW,
+            outline=None,
+        )
+
+
+def draw_muzzle(d, p):
+    mouth = p["mouth"]
+    ell(d, 0.50, 0.487, 0.285, 0.195, C_FUR)
+    # nose
+    ell(d, 0.50, 0.440, 0.105, 0.078, C_NOSE, outline=None)
+    ell(d, 0.478, 0.428, 0.030, 0.020, (92, 102, 124, 255), outline=None)
+    if mouth > 0.02:
+        h = 0.030 + 0.085 * mouth
+        w = 0.105 + 0.055 * mouth
+        ell(d, 0.50, 0.500 + h / 2 - 0.008, w, h, C_NOSE)
+        ell(d, 0.50, 0.500 + h * 0.72, w * 0.60, h * 0.52, C_TONGUE, outline=None)
+    else:
+        # closed muzzle: a short philtrum down from the nose into two
+        # downward-bulging curves (PIL arcs run clockwise from 3 o'clock with
+        # y down, so 0->180 is the lower half — the smiling side).
+        d.line([px(0.50), px(0.470), px(0.50), px(0.508)], fill=C_OUTLINE, width=_w(0.011))
+        for side in (-1, 1):
+            cx = 0.50 + side * 0.032
+            d.arc(
+                [px(cx - 0.032), px(0.492), px(cx + 0.032), px(0.536)],
+                start=0,
+                end=180,
+                fill=C_OUTLINE,
+                width=_w(0.011),
+            )
+
+
+def draw_head(layer, p):
+    d = ImageDraw.Draw(layer)
+    draw_ears(d, p)
+    ell(d, HEAD_CX, HEAD_CY, HEAD_W, HEAD_H, C_FUR)
+    draw_cap(layer, p)
+    # blaze
+    poly(d, bolt_shape(0.50, 0.243, 0.088, 0.150), C_BOLT, outline=None)
+    draw_muzzle(d, p)
+    draw_eyes(d, p)
+
+
+# --- extras ----------------------------------------------------------------
+def draw_extras(layer, p):
+    d = ImageDraw.Draw(layer)
+    kind = p.get("extras")
+    if kind == "listen":
+        for i in range(3):
+            r = 0.045 + i * 0.036
+            alpha = int(210 - i * 55)
+            phase = p.get("phase", 0)
+            if (phase + i) % 3 == 0:
+                alpha = min(255, alpha + 45)
+            d.arc(
+                [px(0.845 - r), px(0.235 - r), px(0.845 + r), px(0.235 + r)],
+                start=200,
+                end=340,
+                fill=C_GLOW[:3] + (alpha,),
+                width=_w(0.014),
+            )
+    elif kind == "think":
+        phase = p.get("phase", 0)
+        for i in range(3):
+            grow = 1.0 if i == phase % 3 else 0.62
+            ell(
+                layer_d := d,
+                0.735 + i * 0.072,
+                0.145 - i * 0.030,
+                0.040 * grow,
+                0.040 * grow,
+                C_GLOW,
+                outline=C_OUTLINE,
+                ow=0.008,
+            )
+    elif kind == "error":
+        poly(d, bolt_shape(0.815, 0.185, 0.070, 0.120), (235, 92, 74, 255))
+
+
+# --- side view: the walk cycle ---------------------------------------------
+# The pose above is a front-facing sit, which is right for standing around but
+# slides like a chess piece the moment the pet actually moves. Walking gets its
+# own construction: a profile torso, four legs following a paw path, and a head
+# side-on. Drawn facing RIGHT — ui/pet_window.py mirrors it when he walks left.
+
+_GROUND = 0.930  # paw centre while a foot is planted
+_STRIDE = 0.088  # how far ahead of / behind the pivot a paw reaches
+_LIFT = 0.080  # peak height of a paw mid-swing
+_STANCE = 0.62  # fraction of the cycle a foot spends on the ground
+
+FRONT_PIVOT = (0.650, 0.620)
+HIND_PIVOT = (0.315, 0.640)
+WALK_HEAD = (0.780, 0.370, 0.260, 0.250)  # cx, cy, w, h
+
+
+def paw_position(pivot, phase):
+    """Where one paw is at *phase* (0..1) of the cycle.
+
+    Stance is the half that matters: the foot is planted and travels backwards
+    under the dog at a constant rate. The window advances this cycle by
+    distance travelled rather than by clock, so that backwards travel cancels
+    the forward motion and the feet don't skate.
+    """
+    phase %= 1.0
+    if phase < _STANCE:
+        t = phase / _STANCE
+        return pivot[0] + _STRIDE - 2 * _STRIDE * t, _GROUND
+    t = (phase - _STANCE) / (1.0 - _STANCE)
+    return (
+        pivot[0] - _STRIDE + 2 * _STRIDE * t,
+        _GROUND - _LIFT * math.sin(math.pi * t),
+    )
+
+
+def draw_leg(d, pivot, paw, fill, bend=0.032, top=0.052, toe=0.030):
+    """A limb from pivot to paw: a bezier through a displaced knee, tapered
+    from thigh to ankle.
+
+    Tapering matters more than it sounds — a constant-width limb reads as a
+    length of white pipe, and four of them make the dog look like furniture.
+    """
+    vx, vy = paw[0] - pivot[0], paw[1] - pivot[1]
+    length = math.hypot(vx, vy) or 1e-6
+    nx, ny = -vy / length, vx / length  # perpendicular; points backwards
+    knee = (
+        (pivot[0] + paw[0]) / 2 + nx * bend,
+        (pivot[1] + paw[1]) / 2 + ny * bend,
+    )
+    pts = []
+    for i in range(13):
+        t = i / 12
+        x = (1 - t) ** 2 * pivot[0] + 2 * (1 - t) * t * knee[0] + t**2 * paw[0]
+        y = (1 - t) ** 2 * pivot[1] + 2 * (1 - t) * t * knee[1] + t**2 * paw[1]
+        pts.append((x, y, lerp(top, toe, t)))
+    draw_tapered(d, pts, lambda _t: fill)
+    ell(d, paw[0], paw[1] + 0.008, 0.098, 0.056, fill)
+
+
+def draw_walk_tail(d, p, dy):
+    """A curled plume over the back.
+
+    Cubic rather than quadratic: a single control point can only bend one way,
+    which gives a straight tapered tube — a club with a white ball on the end,
+    not a tail. The curl back over the spine is what makes it read.
+    """
+    wag = p["tail"]
+    base = (0.250, 0.575 + dy)
+    c1 = (0.075, 0.545 + dy - 0.030 * wag)
+    c2 = (0.070, 0.300 + dy - 0.040 * wag)
+    end = (0.215, 0.290 + dy - 0.020 * wag)
+    pts = []
+    for i in range(29):
+        t = i / 28
+        u = 1 - t
+        x = u**3 * base[0] + 3 * u**2 * t * c1[0] + 3 * u * t**2 * c2[0] + t**3 * end[0]
+        y = u**3 * base[1] + 3 * u**2 * t * c1[1] + 3 * u * t**2 * c2[1] + t**3 * end[1]
+        pts.append((x, y, lerp(0.076, 0.028, t)))
+    draw_tapered(d, pts, lambda t: C_DARK if t < 0.90 else C_FUR)
+
+
+def draw_torso(d, dy):
+    """Rump + barrel + chest as one silhouette.
+
+    Drawn in two passes — every shape swollen by the stroke width in the
+    outline colour, then every shape again at true size in the fill. Outlining
+    each piece individually instead leaves the construction arcs showing
+    across the body, which looks like the dog has panel lines.
+    """
+    shapes = [
+        ("ell", 0.300, 0.600 + dy, 0.290, 0.300, 0.0),
+        ("rrect", 0.480, 0.585 + dy, 0.520, 0.265, 0.130),
+        ("ell", 0.650, 0.590 + dy, 0.250, 0.280, 0.0),
+    ]
+    grow = 2 * OW
+    for colour, pad in ((C_OUTLINE, grow), (C_DARK, 0.0)):
+        for shape in shapes:
+            kind, cx, cy, w, h, extra = shape
+            if kind == "ell":
+                ell(d, cx, cy, w + pad, h + pad, colour, outline=None)
+            else:
+                rrect(d, cx, cy, w + pad, h + pad, extra + pad / 2, colour, outline=None)
+    # Belly kept small and low: any bigger and it merges with the cream legs
+    # into one white mass with a slate lid.
+    ell(d, 0.490, 0.672 + dy, 0.350, 0.098, C_FUR, outline=None)
+
+
+def draw_walk_head(layer, p, dy):
+    d = ImageDraw.Draw(layer)
+    cx, cy, w, h = WALK_HEAD[0], WALK_HEAD[1] + dy, WALK_HEAD[2], WALK_HEAD[3]
+
+    # ear first, so the head covers its base
+    bounce = p.get("ear_bounce", 0.0)
+    ear = [
+        (0.690, cy - 0.030),
+        (0.700, cy - 0.150 - 0.012 * bounce),
+        (0.752, cy - 0.205 - 0.018 * bounce),
+        (0.788, cy - 0.090),
+    ]
+    poly(d, ear, C_DARK)
+    inner = [(lerp(0.735, x, 0.58), lerp(cy - 0.040, y, 0.62)) for x, y in ear]
+    poly(d, inner, C_INNER_EAR, outline=None)
+
+    # neck into the chest
+    d.line(
+        [px(0.660), px(cy + 0.190), px(0.735), px(cy + 0.080)],
+        fill=C_OUTLINE,
+        width=_w(0.215),
+        joint="curve",
+    )
+    d.line(
+        [px(0.660), px(cy + 0.190), px(0.735), px(cy + 0.080)],
+        fill=C_DARK,
+        width=_w(0.190),
+        joint="curve",
+    )
+
+    ell(d, cx, cy, w, h, C_FUR)
+
+    # slate cap, clipped to the skull
+    mask = Image.new("L", (S, S), 0)
+    ImageDraw.Draw(mask).ellipse(
+        [px(cx - w / 2), px(cy - h / 2), px(cx + w / 2), px(cy + h / 2)], fill=255
+    )
+    cap = Image.new("RGBA", (S, S), (0, 0, 0, 0))
+    dc = ImageDraw.Draw(cap)
+    ell(dc, cx - 0.010, cy - 0.070, w * 1.02, h * 0.72, C_DARK, outline=None)
+    cap.putalpha(Image.composite(cap.getchannel("A"), Image.new("L", (S, S), 0), mask))
+    layer.alpha_composite(cap)
+
+    poly(d, bolt_shape(0.762, cy - 0.088, 0.062, 0.108), C_BOLT, outline=None)
+
+    # muzzle, nose, mouth
+    ell(d, 0.880, cy + 0.048, 0.145, 0.108, C_FUR)
+    ell(d, 0.950, cy + 0.018, 0.058, 0.048, C_NOSE, outline=None)
+    d.arc(
+        [px(0.885), px(cy + 0.058), px(0.945), px(cy + 0.100)],
+        start=0,
+        end=150,
+        fill=C_OUTLINE,
+        width=_w(0.010),
+    )
+
+    # one eye in profile, plus the brow marking
+    ell(d, 0.812, cy - 0.020, 0.092, 0.100, C_WHITE)
+    ell(d, 0.820, cy - 0.020, 0.062, 0.070, C_IRIS, outline=None)
+    ell(d, 0.824, cy - 0.020, 0.036, 0.042, C_PUPIL, outline=None)
+    ell(d, 0.812, cy - 0.040, 0.026, 0.022, C_WHITE, outline=None)
+    ell(d, 0.795, cy - 0.088, 0.055, 0.034, C_BROW, outline=None)
+
+    # Collar: a band *across* the neck, so it has to run perpendicular to it.
+    # Along the neck it just reads as an orange brick stuck to his chest.
+    collar = [
+        (px(0.648), px(cy + 0.098)),
+        (px(0.762), px(cy + 0.196)),
+    ]
+    d.line(collar, fill=C_OUTLINE, width=_w(0.070), joint="curve")
+    d.line(collar, fill=C_COLLAR, width=_w(0.050), joint="curve")
+    ell(d, 0.712, cy + 0.196, 0.070, 0.070, C_TAG)
+    poly(d, bolt_shape(0.712, cy + 0.196, 0.025, 0.044), C_OUTLINE, outline=None)
+
+
+def render_walk_frame(p) -> Image.Image:
+    base = Image.new("RGBA", (S, S), (0, 0, 0, 0))
+    d = ImageDraw.Draw(base)
+    phase = p["phase"]
+    # Two contacts per cycle, so the body dips twice — the give-away that a
+    # walk cycle is weight-bearing rather than a slide.
+    dy = -0.011 * abs(math.sin(2 * math.pi * phase))
+    head_dy = dy * 0.6 - 0.006 * math.sin(2 * math.pi * phase + 0.7)
+
+    # Diagonal pairs (a trot): each front leg moves with the opposite hind.
+    far_front = paw_position(FRONT_PIVOT, phase + 0.5)
+    far_hind = paw_position(HIND_PIVOT, phase)
+    near_front = paw_position(FRONT_PIVOT, phase)
+    near_hind = paw_position(HIND_PIVOT, phase + 0.5)
+
+    draw_walk_tail(d, p, dy)
+    # far side first, in the shade colour, so the near legs read as in front
+    draw_leg(d, (HIND_PIVOT[0], HIND_PIVOT[1] + dy), far_hind, C_FUR_FAR, bend=0.046)
+    draw_leg(d, (FRONT_PIVOT[0], FRONT_PIVOT[1] + dy), far_front, C_FUR_FAR)
+
+    draw_torso(d, dy)
+
+    draw_leg(d, (HIND_PIVOT[0], HIND_PIVOT[1] + dy), near_hind, C_FUR, bend=0.046)
+    draw_leg(d, (FRONT_PIVOT[0], FRONT_PIVOT[1] + dy), near_front, C_FUR)
+
+    draw_walk_head(base, p, head_dy)
+    return base.resize((OUT, OUT), Image.LANCZOS)
+
+
+# --- frame assembly --------------------------------------------------------
+def default_pose(**over):
+    p = dict(
+        breathe=0.0,
+        tail=0.0,
+        ear=0.0,
+        ear_twitch=0.0,
+        blink=0.0,
+        mouth=0.0,
+        tilt=0.0,
+        head_dy=0.0,
+        look=(0.0, 0.0),
+        brow=0.0,
+        brow_angle=0.0,
+        cross=False,
+        tag_glow=False,
+        extras=None,
+        phase=0,
+    )
+    p.update(over)
+    return p
+
+
+def render_frame(p) -> Image.Image:
+    if p.get("pose") == "walk":
+        return render_walk_frame(p)
+    base = Image.new("RGBA", (S, S), (0, 0, 0, 0))
+
+    body = Image.new("RGBA", (S, S), (0, 0, 0, 0))
+    db = ImageDraw.Draw(body)
+    draw_tail(db, p)
+    draw_body(db, p)
+    draw_collar(db, p)
+    base.alpha_composite(body)
+
+    head = Image.new("RGBA", (S, S), (0, 0, 0, 0))
+    draw_head(head, p)
+    if p["tilt"]:
+        head = head.rotate(
+            p["tilt"], resample=Image.BICUBIC, center=(px(HEAD_CX), px(NECK_Y))
+        )
+    dy = int(px(p["head_dy"]))
+    if dy:
+        shifted = Image.new("RGBA", (S, S), (0, 0, 0, 0))
+        shifted.alpha_composite(head, (0, dy))
+        head = shifted
+    base.alpha_composite(head)
+
+    draw_extras(base, p)
+    return base.resize((OUT, OUT), Image.LANCZOS)
+
+
+def frames_for(state: str) -> list[dict]:
+    if state == "idle":
+        out = []
+        for i in range(8):
+            t = i / 8
+            br = math.sin(t * 2 * math.pi)
+            out.append(
+                default_pose(
+                    breathe=br,
+                    head_dy=-0.006 * br,
+                    tail=math.sin(t * 4 * math.pi),
+                    blink=1.0 if i == 6 else 0.0,
+                )
+            )
+        return out
+    if state == "listening":
+        out = []
+        for i in range(4):
+            t = i / 4
+            out.append(
+                default_pose(
+                    ear=1.0,
+                    ear_twitch=0.35 * math.sin(t * 2 * math.pi),
+                    tilt=-7 + 2.0 * math.sin(t * 2 * math.pi),
+                    brow=1.0,
+                    tail=0.5 * math.sin(t * 2 * math.pi),
+                    head_dy=-0.008,
+                    tag_glow=True,
+                    extras="listen",
+                    phase=i,
+                )
+            )
+        return out
+    if state == "thinking":
+        out = []
+        for i in range(6):
+            t = i / 6
+            out.append(
+                default_pose(
+                    ear=0.25,
+                    tilt=6.0,
+                    look=(0.022, -0.026),
+                    brow=0.5,
+                    breathe=0.4 * math.sin(t * 2 * math.pi),
+                    tail=0.2 * math.sin(t * 2 * math.pi),
+                    extras="think",
+                    phase=i // 2,
+                )
+            )
+        return out
+    if state == "talking":
+        out = []
+        for i in range(4):
+            t = i / 4
+            open_ = (math.sin(t * 2 * math.pi) + 1) / 2
+            out.append(
+                default_pose(
+                    mouth=0.25 + 0.75 * open_,
+                    ear=0.6,
+                    head_dy=-0.010 * open_,
+                    breathe=open_,
+                    tail=math.sin(t * 2 * math.pi + 1.0),
+                    brow=0.35,
+                )
+            )
+        return out
+    if state == "walk":
+        # 8 frames: two full strides, so the loop lands back on the pose it
+        # started from and the cycle is seamless however it's entered.
+        out = []
+        for i in range(8):
+            phase = i / 8
+            out.append(
+                default_pose(
+                    pose="walk",
+                    phase=phase,
+                    tail=math.sin(2 * math.pi * phase),
+                    ear_bounce=math.sin(2 * math.pi * phase + 0.9),
+                )
+            )
+        return out
+    if state == "error":
+        return [
+            default_pose(ear=-1.0, cross=True, brow_angle=1.0, mouth=0.35, tail=-0.6,
+                         extras="error"),
+            default_pose(ear=-0.85, cross=True, brow_angle=1.0, mouth=0.15, tail=-0.4,
+                         head_dy=0.008),
+        ]
+    raise ValueError(state)
+
+
+STATES = ["idle", "listening", "thinking", "talking", "error", "walk"]
+
+
+def main():
+    ap = argparse.ArgumentParser(description=__doc__)
+    ap.add_argument(
+        "--out",
+        type=Path,
+        default=Path(__file__).resolve().parent.parent / "bolt_pet" / "assets" / "sprites",
+    )
+    ap.add_argument("--states", nargs="*", default=STATES)
+    args = ap.parse_args()
+
+    for state in args.states:
+        d = args.out / state
+        d.mkdir(parents=True, exist_ok=True)
+        for old in d.glob("*.png"):
+            old.unlink()
+        for i, pose in enumerate(frames_for(state)):
+            render_frame(pose).save(d / f"frame_{i:02d}.png")
+        print(f"{state}: {len(frames_for(state))} frames -> {d}")
+
+
+if __name__ == "__main__":
+    main()

tests/test_controller_features.py

@@ -5,6 +5,7 @@ the live wake threshold.
 Needs a QApplication (signals), so run with QT_QPA_PLATFORM=offscreen.
 """
 
+import json
 import sys
 from pathlib import Path
 
@@ -79,8 +80,102 @@ def test_petctl_nap_also_flips_the_controller_state(ctrl):
     assert ctrl._napping is True
 
 
+# ── filectl routing ──────────────────────────────────────────────────────────
+# filectl's wire format is a single-line JSON envelope (see file_ops.py's
+# module docstring for why) — build commands with json.dumps so the tests
+# don't hardcode escaping by hand.
+
+def _filectl(payload: dict) -> str:
+    return "filectl " + json.dumps(payload)
+
+
+def test_filectl_commands_never_reach_the_shell(monkeypatch, ctrl, tmp_path):
+    ran = []
+    monkeypatch.setattr(controller_mod.server_client, "run_local_command", lambda cmd: ran.append(cmd))
+    target = tmp_path / "a.txt"
+
+    output = ctrl._handle_command(_filectl({"op": "write", "path": str(target), "content": "hello"}))
+
+    assert ran == []
+    assert target.read_text() == "hello"
+    assert str(target) in output
+
+
+def test_filectl_edit_round_trips_through_the_relay(monkeypatch, ctrl, tmp_path):
+    monkeypatch.setattr(controller_mod.server_client, "run_local_command",
+                        lambda cmd: (_ for _ in ()).throw(AssertionError("should not shell out")))
+    target = tmp_path / "a.py"
+    target.write_text("x = 1\n")
+
+    output = ctrl._handle_command(
+        _filectl({"op": "edit", "path": str(target), "old": "x = 1", "new": "x = 2"})
+    )
+
+    assert target.read_text() == "x = 2\n"
+    assert str(target) in output
+
+
+def test_bad_filectl_syntax_is_reported_back_not_executed(monkeypatch, ctrl):
+    ran = []
+    monkeypatch.setattr(controller_mod.server_client, "run_local_command", lambda cmd: ran.append(cmd))
+    output = ctrl._handle_command("filectl {not valid json")
+    assert ran == []
+    assert "[filectl]" in output
+
+
+def test_filectl_execution_failure_is_reported_back_not_raised(monkeypatch, ctrl):
+    output = ctrl._handle_command(_filectl({"op": "read", "path": "/no/such/file.txt"}))
+    assert "[filectl]" in output
+
+
+def test_ordinary_commands_still_run_locally_alongside_filectl(monkeypatch, ctrl):
+    ran = []
+    monkeypatch.setattr(controller_mod.server_client, "run_local_command",
+                        lambda cmd: ran.append(cmd) or "[exit 0]\n")
+    ctrl._handle_command("df -h /")
+    assert ran == ["df -h /"]
+
+
 # ── barge-in ────────────────────────────────────────────────────────────────
 
+def test_the_interrupt_log_reports_what_fired_not_the_reset_counters(monkeypatch, ctrl):
+    """_speak resets the detector after playback so the pet's own voice
+    doesn't linger in the wake model's window. Reading the stats after that
+    reset reports 0.000 at frame 0 for every interruption, which is worse
+    than no instrumentation — it looks like hard evidence and isn't."""
+    from bolt_pet.audio import barge_in as barge_in_mod
+
+    class Detector(barge_in_mod.WakeWordBargeIn):
+        def __init__(self):
+            self._frames, self._peak, self._last, self._last_threshold = 0, 0.0, 0.0, 0.5
+            self._frame_len = 1280
+            self.reset_calls = 0
+
+        def reset(self):
+            self.reset_calls += 1
+            self._frames, self._peak, self._last = 0, 0.0, 0.0
+
+    detector = Detector()
+    ctrl._barge_in = detector
+    logs = _capture(ctrl.log)
+
+    def interrupted_playback(text, on_error=None, should_stop=None):
+        # What really happens: frames get scored during playback, then one
+        # clears the threshold and playback aborts.
+        detector._frames, detector._peak, detector._last = 7, 0.81, 0.81
+        return False
+
+    monkeypatch.setattr(controller_mod.tts, "speak", interrupted_playback)
+
+    ctrl._speak("a very long explanation")
+
+    interrupted = next(m for m in logs if "Interrupted" in m)
+    assert "0.810" in interrupted and "frame 7" in interrupted
+    # Once before playback (clear the window) and once after (drop the pet's
+    # own voice) — the point is that the *read* happens between them.
+    assert detector.reset_calls == 2
+
+
 def test_interrupted_playback_queues_an_immediate_next_turn(monkeypatch, ctrl):
     logs = _capture(ctrl.log)
     monkeypatch.setattr(controller_mod.tts, "speak",
@@ -99,6 +194,110 @@ def test_uninterrupted_playback_does_not_queue_a_turn(monkeypatch, ctrl):
     assert not ctrl._talk_now.is_set()
 
 
+# ── follow-up listening ─────────────────────────────────────────────────────
+
+@pytest.fixture
+def spoke(monkeypatch):
+    """Playback that always completes, so only the follow-up rule decides
+    whether another turn is queued."""
+    monkeypatch.setattr(controller_mod.tts, "speak",
+                        lambda text, on_error=None, should_stop=None: True)
+
+
+def test_a_reply_ending_in_a_question_keeps_listening(spoke, ctrl):
+    logs = _capture(ctrl.log)
+
+    ctrl._speak("You're still in ~/Documents/bolt-pet. Ready to run a command?")
+
+    assert ctrl._talk_now.is_set()      # no wake word needed for the answer
+    assert ctrl._pending_follow_up      # and the next turn knows it's an answer
+    assert any("listening for your answer" in message for message in logs)
+
+
+def test_a_statement_does_not_keep_listening(spoke, ctrl):
+    ctrl._speak("It's 7:15 AM on July 23, 2026.")
+    assert not ctrl._talk_now.is_set()
+    assert not ctrl._pending_follow_up
+
+
+def test_a_question_in_passing_does_not_count(spoke, ctrl):
+    """Only a reply that *ends* on a question is waiting for an answer."""
+    ctrl._speak("What time is it? It's 7:15 AM.")
+    assert not ctrl._talk_now.is_set()
+
+
+def test_follow_ups_stop_at_the_cap(spoke, monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "FOLLOW_UP_MAX_TURNS", 2)
+    logs = _capture(ctrl.log)
+
+    for _ in range(2):
+        ctrl._speak("Want me to keep going?")
+        ctrl._talk_now.clear()
+    assert ctrl._follow_ups == 2
+
+    ctrl._speak("Want me to keep going?")
+
+    assert not ctrl._talk_now.is_set()  # chain broken until you re-trigger it
+    assert any("Follow-up limit reached" in message for message in logs)
+
+
+def test_the_cap_is_not_announced_on_ordinary_replies(spoke, monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "FOLLOW_UP_MAX_TURNS", 1)
+    ctrl._follow_ups = 1
+    logs = _capture(ctrl.log)
+
+    ctrl._speak("Done — the file is saved.")
+
+    assert not any("Follow-up limit" in message for message in logs)
+
+
+def test_starting_a_turn_yourself_resets_the_chain(spoke, monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.mic, "record_utterance",
+                        lambda *a, **kw: None)  # you said nothing
+    ctrl._follow_ups = 3
+
+    ctrl._handle_conversation_turn()
+
+    assert ctrl._follow_ups == 0
+
+
+def test_an_answered_question_gets_a_longer_grace_period(spoke, monkeypatch, ctrl):
+    """You were just asked something — you get longer to think than when you
+    deliberately said the wake word."""
+    grace = []
+    monkeypatch.setattr(controller_mod.mic, "record_utterance",
+                        lambda *a, **kw: grace.append(kw.get("grace_s")) or None)
+
+    ctrl._handle_conversation_turn()                 # you started this one
+    ctrl._pending_follow_up = True
+    ctrl._handle_conversation_turn()                 # this one answers a question
+
+    assert grace == [None, controller_mod.config.FOLLOW_UP_GRACE_SECONDS]
+
+
+def test_muting_stops_follow_ups(spoke, ctrl):
+    ctrl._muted = True
+    ctrl._speak("Shall I continue?")
+    assert not ctrl._talk_now.is_set()  # mute means don't listen, question or not
+
+
+def test_follow_up_can_be_turned_off(spoke, monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "FOLLOW_UP_LISTEN", False)
+    ctrl._speak("Shall I continue?")
+    assert not ctrl._talk_now.is_set()
+
+
+def test_being_interrupted_restarts_the_chain(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.tts, "speak",
+                        lambda text, on_error=None, should_stop=None: False)
+    ctrl._follow_ups = 3
+
+    ctrl._speak("a very long explanation")
+
+    assert ctrl._follow_ups == 0  # you're clearly engaged
+    assert ctrl._talk_now.is_set()
+
+
 def test_speech_is_recorded_in_the_history(monkeypatch, ctrl):
     monkeypatch.setattr(controller_mod.tts, "speak",
                         lambda text, on_error=None, should_stop=None: True)
@@ -241,3 +440,81 @@ def test_near_misses_are_recorded_for_the_tuner(ctrl):
 
     ctrl.reset_wake_stats()
     assert ctrl.wake_stats()["near_misses"] == []
+
+
+# ── file delivery ────────────────────────────────────────────────────────────
+
+def test_check_deliveries_downloads_and_saves_queued_files(monkeypatch, ctrl, tmp_path):
+    monkeypatch.setattr(controller_mod.config, "DELIVERED_FILES_DIR", tmp_path)
+    monkeypatch.setattr(controller_mod.server_client, "list_outbox_files",
+                        lambda: [{"id": "abc", "name": "report.pdf", "size": 5}])
+    monkeypatch.setattr(controller_mod.server_client, "download_outbox_file",
+                        lambda file_id: b"hello" if file_id == "abc" else b"")
+
+    ctrl._check_deliveries()
+
+    assert (tmp_path / "report.pdf").read_bytes() == b"hello"
+
+
+def test_check_deliveries_is_a_noop_when_nothing_queued(monkeypatch, ctrl, tmp_path):
+    monkeypatch.setattr(controller_mod.config, "DELIVERED_FILES_DIR", tmp_path)
+    monkeypatch.setattr(controller_mod.server_client, "list_outbox_files", lambda: [])
+    downloaded = []
+    monkeypatch.setattr(controller_mod.server_client, "download_outbox_file",
+                        lambda file_id: downloaded.append(file_id))
+
+    ctrl._check_deliveries()
+
+    assert downloaded == []
+
+
+def test_check_deliveries_can_be_disabled(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "RECEIVE_FILES", False)
+    called = {"n": 0}
+    monkeypatch.setattr(controller_mod.server_client, "list_outbox_files",
+                        lambda: called.__setitem__("n", called["n"] + 1))
+
+    ctrl._check_deliveries()
+
+    assert called["n"] == 0
+
+
+def test_check_deliveries_logs_and_continues_on_download_failure(monkeypatch, ctrl, tmp_path):
+    monkeypatch.setattr(controller_mod.config, "DELIVERED_FILES_DIR", tmp_path)
+    monkeypatch.setattr(controller_mod.server_client, "list_outbox_files", lambda: [
+        {"id": "bad", "name": "a.txt", "size": 1},
+        {"id": "good", "name": "b.txt", "size": 1},
+    ])
+
+    def fake_download(file_id):
+        if file_id == "bad":
+            raise controller_mod.server_client.ServerError("gone")
+        return b"ok"
+
+    monkeypatch.setattr(controller_mod.server_client, "download_outbox_file", fake_download)
+    logs = _capture(ctrl.log)
+
+    ctrl._check_deliveries()
+
+    assert (tmp_path / "b.txt").read_bytes() == b"ok"
+    assert not (tmp_path / "a.txt").exists()
+    assert any("bad" in msg or "a.txt" in msg for msg in logs)
+
+
+def test_check_deliveries_runs_after_a_conversation_turn(monkeypatch, ctrl, tmp_path):
+    monkeypatch.setattr(controller_mod.mic, "record_utterance",
+                        lambda *a, **k: np.zeros(10, dtype=np.int16))
+    monkeypatch.setattr(controller_mod.stt, "transcribe", lambda pcm: "send me that file")
+    monkeypatch.setattr(controller_mod.server_client, "converse",
+                        lambda text, on_command=None: "it's on the way")
+    monkeypatch.setattr(controller_mod.tts, "speak",
+                        lambda text, on_error=None, should_stop=None: True)
+    monkeypatch.setattr(controller_mod.config, "DELIVERED_FILES_DIR", tmp_path)
+    monkeypatch.setattr(controller_mod.server_client, "list_outbox_files",
+                        lambda: [{"id": "abc", "name": "notes.txt", "size": 2}])
+    monkeypatch.setattr(controller_mod.server_client, "download_outbox_file",
+                        lambda file_id: b"hi")
+
+    ctrl._handle_conversation_turn()
+
+    assert (tmp_path / "notes.txt").read_bytes() == b"hi"

tests/test_file_delivery.py

@@ -0,0 +1,54 @@
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from bolt_pet import file_delivery
+
+
+def test_sanitize_filename_strips_directory_components():
+    assert file_delivery.sanitize_filename("../../etc/passwd") == "passwd"
+    assert file_delivery.sanitize_filename("/absolute/path/report.pdf") == "report.pdf"
+    assert file_delivery.sanitize_filename("plain.txt") == "plain.txt"
+
+
+def test_sanitize_filename_falls_back_on_empty_or_dots():
+    assert file_delivery.sanitize_filename("") == "delivered_file"
+    assert file_delivery.sanitize_filename("..") == "delivered_file"
+    assert file_delivery.sanitize_filename(".") == "delivered_file"
+    assert file_delivery.sanitize_filename(None) == "delivered_file"
+
+
+def test_unique_path_returns_the_plain_name_when_free(tmp_path):
+    path = file_delivery.unique_path(tmp_path, "report.pdf")
+    assert path == tmp_path / "report.pdf"
+
+
+def test_unique_path_suffixes_on_collision(tmp_path):
+    (tmp_path / "report.pdf").write_bytes(b"existing")
+    path = file_delivery.unique_path(tmp_path, "report.pdf")
+    assert path == tmp_path / "report (1).pdf"
+
+    (tmp_path / "report (1).pdf").write_bytes(b"also existing")
+    path = file_delivery.unique_path(tmp_path, "report.pdf")
+    assert path == tmp_path / "report (2).pdf"
+
+
+def test_unique_path_creates_the_directory(tmp_path):
+    target = tmp_path / "nested" / "dir"
+    file_delivery.unique_path(target, "a.txt")
+    assert target.is_dir()
+
+
+def test_save_writes_bytes_and_sanitizes_the_name(tmp_path):
+    path = file_delivery.save(tmp_path, "../sneaky/report.pdf", b"hello")
+    assert path == tmp_path / "report.pdf"
+    assert path.read_bytes() == b"hello"
+
+
+def test_save_never_overwrites_an_existing_download(tmp_path):
+    first = file_delivery.save(tmp_path, "notes.txt", b"first")
+    second = file_delivery.save(tmp_path, "notes.txt", b"second")
+    assert first != second
+    assert first.read_bytes() == b"first"
+    assert second.read_bytes() == b"second"

tests/test_file_ops.py

@@ -0,0 +1,266 @@
+"""filectl parsing + execution — the pseudo-commands the server can relay to
+read/write/edit local files instead of a raw shell heredoc.
+
+filectl {"op": ...} is a single-line JSON envelope (not a multi-line
+marker block) because it rides the "command" tool marker, which the main
+repo's tool-call extractor only captures up to the next newline — see the
+module docstring in bolt_pet/file_ops.py."""
+
+import json
+import sys
+from pathlib import Path
+
+import pytest
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from bolt_pet import file_ops
+
+
+def _cmd(payload: dict) -> str:
+    return "filectl " + json.dumps(payload)
+
+
+# ── parsing ──────────────────────────────────────────────────────────────────
+
+def test_non_file_commands_are_left_alone():
+    assert file_ops.parse("ls -la") is None
+    assert file_ops.parse("systemctl restart nginx") is None
+    assert file_ops.parse("") is None
+    # "filed" must not be mistaken for the "file" prefix
+    assert file_ops.parse("filed --list") is None
+
+
+def test_list_parses_defaults():
+    assert file_ops.parse(_cmd({"op": "list", "path": "/tmp"})) == {
+        "action": "list", "path": "/tmp", "pattern": "*", "recursive": False,
+    }
+
+
+def test_list_parses_pattern_and_recursive():
+    assert file_ops.parse(_cmd({"op": "list", "path": "/tmp", "pattern": "*.py", "recursive": True})) == {
+        "action": "list", "path": "/tmp", "pattern": "*.py", "recursive": True,
+    }
+
+
+def test_list_requires_a_path():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.parse(_cmd({"op": "list"}))
+
+
+def test_list_rejects_empty_pattern():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.parse(_cmd({"op": "list", "path": "/tmp", "pattern": ""}))
+
+
+def test_read_parses_path_and_optional_line_range():
+    assert file_ops.parse(_cmd({"op": "read", "path": "/tmp/a.txt"})) == {
+        "action": "read", "path": "/tmp/a.txt", "start": None, "end": None,
+    }
+    assert file_ops.parse(_cmd({"op": "read", "path": "/tmp/a.txt", "start": 10, "end": 40})) == {
+        "action": "read", "path": "/tmp/a.txt", "start": 10, "end": 40,
+    }
+
+
+def test_read_requires_a_path():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.parse(_cmd({"op": "read"}))
+
+
+def test_read_rejects_non_numeric_line_args():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.parse('filectl {"op": "read", "path": "/tmp/a.txt", "start": "start"}')
+
+
+def test_write_parses_path_and_content():
+    assert file_ops.parse(_cmd({"op": "write", "path": "/tmp/a.txt", "content": "hello\nworld"})) == {
+        "action": "write", "path": "/tmp/a.txt", "content": "hello\nworld",
+    }
+
+
+def test_write_allows_empty_content():
+    assert file_ops.parse(_cmd({"op": "write", "path": "/tmp/a.txt", "content": ""})) == {
+        "action": "write", "path": "/tmp/a.txt", "content": "",
+    }
+
+
+def test_write_without_content_raises():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.parse(_cmd({"op": "write", "path": "/tmp/a.txt"}))
+
+
+def test_edit_parses_old_and_new():
+    assert file_ops.parse(_cmd({"op": "edit", "path": "/tmp/a.txt", "old": "foo\nbar", "new": "baz"})) == {
+        "action": "edit", "path": "/tmp/a.txt", "old": "foo\nbar", "new": "baz",
+    }
+
+
+def test_edit_rejects_identical_old_and_new():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.parse(_cmd({"op": "edit", "path": "/tmp/a.txt", "old": "same", "new": "same"}))
+
+
+def test_edit_missing_fields_raises():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.parse(_cmd({"op": "edit", "path": "/tmp/a.txt"}))
+
+
+def test_content_with_embedded_quotes_and_shell_metacharacters_survives():
+    payload = 'echo "hi $USER" `whoami` && rm -rf /'
+    command = _cmd({"op": "write", "path": "/tmp/a.txt", "content": payload})
+    assert "\n" not in command  # stays on one line, as the command marker requires
+    assert file_ops.parse(command) == {"action": "write", "path": "/tmp/a.txt", "content": payload}
+
+
+def test_multiline_content_stays_on_one_physical_line():
+    content = "line one\nline two\nline three with \"quotes\" and \\backslashes\\"
+    command = _cmd({"op": "write", "path": "/tmp/a.txt", "content": content})
+    assert "\n" not in command
+    assert file_ops.parse(command)["content"] == content
+
+
+def test_help():
+    assert file_ops.parse("filectl help") == {"action": "help"}
+    assert file_ops.parse("filectl") == {"action": "help"}
+    assert file_ops.parse(_cmd({"op": "help"})) == {"action": "help"}
+
+
+def test_invalid_json_raises():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.parse("filectl {not valid json")
+
+
+def test_non_object_json_raises():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.parse("filectl [1, 2, 3]")
+
+
+def test_unknown_op_raises():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.parse(_cmd({"op": "frobnicate", "path": "/tmp/a.txt"}))
+
+
+# ── execution ────────────────────────────────────────────────────────────────
+
+def test_list_shows_files_and_subdirectories(tmp_path):
+    (tmp_path / "a.txt").write_text("hi")
+    (tmp_path / "sub").mkdir()
+    (tmp_path / "sub" / "b.txt").write_text("nested")
+
+    action = file_ops.parse(_cmd({"op": "list", "path": str(tmp_path)}))
+    output = file_ops.execute(action)
+
+    assert "a.txt\t2B" in output
+    assert "sub/" in output
+    assert "b.txt" not in output  # non-recursive: nested file not shown
+
+
+def test_list_recursive_finds_nested_files(tmp_path):
+    (tmp_path / "sub").mkdir()
+    (tmp_path / "sub" / "b.txt").write_text("nested")
+
+    action = file_ops.parse(_cmd({"op": "list", "path": str(tmp_path), "recursive": True}))
+    output = file_ops.execute(action)
+
+    assert "sub/b.txt" in output or "sub\\b.txt" in output  # os-dependent separator
+
+
+def test_list_pattern_filters_entries(tmp_path):
+    (tmp_path / "a.py").write_text("x")
+    (tmp_path / "b.txt").write_text("y")
+
+    action = file_ops.parse(_cmd({"op": "list", "path": str(tmp_path), "pattern": "*.py"}))
+    output = file_ops.execute(action)
+
+    assert "a.py" in output
+    assert "b.txt" not in output
+
+
+def test_list_empty_directory_says_so(tmp_path):
+    action = file_ops.parse(_cmd({"op": "list", "path": str(tmp_path)}))
+    output = file_ops.execute(action)
+    assert "no entries" in output
+
+
+def test_list_missing_directory_raises():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.execute({"action": "list", "path": "/no/such/dir", "pattern": "*", "recursive": False})
+
+
+def test_list_rejects_a_file_path(tmp_path):
+    target = tmp_path / "a.txt"
+    target.write_text("hi")
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.execute({"action": "list", "path": str(target), "pattern": "*", "recursive": False})
+
+
+def test_list_truncates_past_the_entry_cap(tmp_path, monkeypatch):
+    monkeypatch.setattr(file_ops, "_MAX_LIST_ENTRIES", 3)
+    for i in range(5):
+        (tmp_path / f"f{i}.txt").write_text("x")
+
+    action = file_ops.parse(_cmd({"op": "list", "path": str(tmp_path)}))
+    output = file_ops.execute(action)
+
+    assert "truncated" in output
+    assert output.count(".txt") == 3
+
+
+def test_write_then_read_round_trips(tmp_path):
+    target = tmp_path / "notes.txt"
+    write_action = file_ops.parse(_cmd({"op": "write", "path": str(target), "content": "line one\nline two"}))
+    result = file_ops.execute(write_action)
+    assert target.read_text() == "line one\nline two"
+    assert str(target) in result
+
+    read_action = file_ops.parse(_cmd({"op": "read", "path": str(target)}))
+    output = file_ops.execute(read_action)
+    assert "line one" in output
+    assert "line two" in output
+
+
+def test_read_missing_file_raises():
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.execute({"action": "read", "path": "/no/such/file.txt", "start": None, "end": None})
+
+
+def test_read_respects_line_range(tmp_path):
+    target = tmp_path / "a.txt"
+    target.write_text("\n".join(f"line{i}" for i in range(1, 11)))
+    action = file_ops.parse(_cmd({"op": "read", "path": str(target), "start": 3, "end": 5}))
+    output = file_ops.execute(action)
+    assert "line3" in output and "line5" in output
+    assert "line1" not in output and "line6" not in output
+
+
+def test_edit_replaces_a_unique_match(tmp_path):
+    target = tmp_path / "a.py"
+    target.write_text("def foo():\n    return 1\n")
+    action = file_ops.parse(_cmd({"op": "edit", "path": str(target), "old": "return 1", "new": "return 2"}))
+    file_ops.execute(action)
+    assert target.read_text() == "def foo():\n    return 2\n"
+
+
+def test_edit_fails_when_text_not_found(tmp_path):
+    target = tmp_path / "a.py"
+    target.write_text("def foo():\n    return 1\n")
+    action = file_ops.parse(_cmd({"op": "edit", "path": str(target), "old": "nope", "new": "x"}))
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.execute(action)
+    assert target.read_text() == "def foo():\n    return 1\n"  # untouched
+
+
+def test_edit_fails_when_text_is_ambiguous(tmp_path):
+    target = tmp_path / "a.py"
+    target.write_text("x = 1\nx = 1\n")
+    action = file_ops.parse(_cmd({"op": "edit", "path": str(target), "old": "x = 1", "new": "x = 2"}))
+    with pytest.raises(file_ops.FileOpError):
+        file_ops.execute(action)
+    assert target.read_text() == "x = 1\nx = 1\n"  # untouched
+
+
+def test_write_creates_parent_directories(tmp_path):
+    target = tmp_path / "nested" / "dir" / "a.txt"
+    action = file_ops.parse(_cmd({"op": "write", "path": str(target), "content": "hi"}))
+    file_ops.execute(action)
+    assert target.read_text() == "hi"

tests/test_monitors.py

@@ -0,0 +1,169 @@
+"""Screen layout logic — resolving `petctl jump` targets and describing the
+setup. Pure: the monitor list is normally published by the UI, so none of this
+needs a display."""
+
+import sys
+from pathlib import Path
+
+import pytest
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from bolt_pet import monitors as m
+
+
+def grid():
+    """The 2x2 setup this was built against: four 1080p screens.
+
+        [1 HDMI-0] [2 HDMI-1]
+        [3 DP-0  ] [4 DP-2  ]
+    """
+    return [
+        m.Monitor(0, "HDMI-0", 0, 0, 1920, 1080, primary=False),
+        m.Monitor(1, "HDMI-1", 1920, 0, 1920, 1080, primary=False),
+        m.Monitor(2, "DP-0", 0, 1080, 1920, 1080, primary=True),
+        m.Monitor(3, "DP-2", 1920, 1080, 1920, 1080, primary=False),
+    ]
+
+
+def two():
+    return [
+        m.Monitor(0, "eDP-1", 0, 0, 1920, 1080, primary=True),
+        m.Monitor(1, "HDMI-1", 1920, 0, 2560, 1440),
+    ]
+
+
+def test_numbers_shown_to_humans_are_one_based():
+    left, right = two()
+    assert left.index == 0 and left.number == 1
+    assert right.index == 1 and right.number == 2
+    assert "1: eDP-1 1920x1080 (primary)" == left.label
+
+
+def test_geometry_helpers():
+    screen = m.Monitor(1, "HDMI-1", 1920, 0, 1920, 1080)
+    assert screen.right == 3840 and screen.bottom == 1080
+    assert screen.center == (2880, 540)
+    assert screen.contains(1920, 0)
+    assert screen.contains(3839, 1079)
+    assert not screen.contains(3840, 0)  # right edge is exclusive
+    assert not screen.contains(1919, 0)
+
+
+def test_monitor_containing_and_nearest():
+    screens = grid()
+    assert m.monitor_containing(screens, 100, 100).name == "HDMI-0"
+    assert m.monitor_containing(screens, 2000, 1500).name == "DP-2"
+    assert m.monitor_containing(screens, -50, -50) is None
+    # off the desktop entirely still resolves to something
+    assert m.nearest_monitor(screens, -500, -500).name == "HDMI-0"
+
+
+def test_resolve_by_number():
+    screens = grid()
+    assert m.resolve(screens, "3").name == "DP-0"
+    with pytest.raises(ValueError, match="no monitor 9"):
+        m.resolve(screens, "9")
+    with pytest.raises(ValueError):
+        m.resolve(screens, "0")
+
+
+def test_resolve_next_and_prev_wrap():
+    screens = grid()
+    assert m.resolve(screens, "next", current=3).number == 1
+    assert m.resolve(screens, "prev", current=0).number == 4
+    assert m.resolve(screens, "next", current=0).number == 2
+
+
+def test_resolve_primary_and_other():
+    screens = grid()
+    assert m.resolve(screens, "primary", current=0).name == "DP-0"
+    # "other" on a two-screen setup is genuinely the other one
+    pair = two()
+    assert m.resolve(pair, "other", current=0).number == 2
+    assert m.resolve(pair, "other", current=1).number == 1
+
+
+def test_resolve_directions_on_a_grid():
+    screens = grid()
+    # from top-left (HDMI-0)
+    assert m.resolve(screens, "right", current=0).name == "HDMI-1"
+    assert m.resolve(screens, "down", current=0).name == "DP-0"
+    # from bottom-right (DP-2)
+    assert m.resolve(screens, "left", current=3).name == "DP-0"
+    assert m.resolve(screens, "up", current=3).name == "HDMI-1"
+
+
+def test_direction_prefers_the_best_aligned_screen():
+    screens = grid()
+    # "right" from DP-0 (bottom-left) must pick DP-2 (same row), not HDMI-1,
+    # even though both are to the right.
+    assert m.resolve(screens, "right", current=2).name == "DP-2"
+
+
+def test_resolve_direction_with_nothing_there():
+    screens = grid()
+    with pytest.raises(ValueError, match="no monitor to the left"):
+        m.resolve(screens, "left", current=0)
+
+
+def test_resolve_by_name_is_fuzzy_but_refuses_ambiguity():
+    screens = grid()
+    assert m.resolve(screens, "dp-2").name == "DP-2"
+    assert m.resolve(screens, "HDMI-0").name == "HDMI-0"
+    with pytest.raises(ValueError, match="matches several"):
+        m.resolve(screens, "hdmi")
+
+
+def test_resolve_unknown_spec_lists_the_options():
+    screens = two()
+    with pytest.raises(ValueError) as excinfo:
+        m.resolve(screens, "the big one")
+    assert "eDP-1" in str(excinfo.value) and "HDMI-1" in str(excinfo.value)
+
+
+def test_resolve_without_a_current_screen_falls_back_to_primary():
+    screens = grid()
+    # primary is index 2, so "next" from nowhere is index 3
+    assert m.resolve(screens, "next", current=None).number == 4
+    # an out-of-range current is treated the same way rather than exploding
+    assert m.resolve(screens, "next", current=99).number == 4
+
+
+def test_resolve_needs_monitors():
+    with pytest.raises(ValueError, match="no monitors"):
+        m.resolve([], "next")
+    with pytest.raises(ValueError, match="needs a target"):
+        m.resolve(grid(), "")
+
+
+def test_random_always_moves_somewhere_else():
+    screens = grid()
+    for current in range(4):
+        assert m.resolve(screens, "random", current=current).index != current
+
+
+def test_summary_is_one_line_and_marks_where_the_pet_is():
+    line = m.summary(grid(), current=1)
+    assert "\n" not in line
+    assert line.startswith("4 monitors:")
+    assert "Bolt is on 2" in line
+    assert m.summary([]) is None
+    assert "Bolt is on" not in m.summary(grid(), current=None)
+
+
+def test_annotate_matches_the_screen_context_style():
+    out = m.annotate("what's on the other screen?", grid(), current=0)
+    assert out.startswith("what's on the other screen?")
+    assert "[4 monitors:" in out
+    # nothing to say, nothing added
+    assert m.annotate("hello", [], None) == "hello"
+    assert m.annotate("", grid(), 0) == ""
+
+
+def test_describe_lists_every_screen_and_flags_the_pet():
+    text = m.describe(grid(), current=2)
+    assert text.count("\n") == 4  # header + 4 screens
+    assert "DP-0" in text and "+0+1080" in text
+    assert text.count("Bolt is here") == 1
+    assert m.describe([]) == "[pet] no monitor information available"

tests/test_pet_window_features.py

@@ -15,7 +15,10 @@ sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
 
 from bolt_pet import config
 from bolt_pet.state import PetState
-from bolt_pet.ui.pet_window import _EMOTE_TICKS, PetWindow, emote_transform
+from bolt_pet.ui.pet_window import (
+    _EMOTE_TICKS, _WALK_PIXELS_PER_FRAME, PetWindow, emote_transform,
+)
+from bolt_pet.ui.sprite import WALK
 
 
 @pytest.fixture(scope="module")
@@ -179,3 +182,153 @@ def test_click_through_toggles_mouse_transparency(pet):
 
     pet.set_click_through(False)
     assert pet.testAttribute(Qt.WA_TransparentForMouseEvents) is False
+
+
+# ── monitors ────────────────────────────────────────────────────────────────
+
+def test_window_publishes_a_monitor_list(pet):
+    """Whatever the test host's screen setup is, the window must describe it
+    in the shape the controller expects."""
+    monitors = pet.monitors()
+    assert monitors, "offscreen Qt still reports at least one screen"
+    assert [m.index for m in monitors] == list(range(len(monitors)))
+    assert all(m.width > 0 and m.height > 0 for m in monitors)
+    assert all(m.name for m in monitors)
+    assert sum(1 for m in monitors if m.primary) <= 1
+
+
+def test_publish_monitors_re_emits_when_forced(pet):
+    """ui/app.py relies on this: the window is built before the controller
+    exists, so its constructor's publish reaches nobody and has to be redone."""
+    seen = []
+    pet.monitors_changed.connect(seen.append)
+    pet.publish_monitors()  # force defaults to True
+    assert len(seen) == 1
+    pet.publish_monitors(force=False)  # nothing changed -> stays quiet
+    assert len(seen) == 1
+
+
+def test_pet_reports_which_monitor_it_is_on(pet):
+    seen = []
+    pet.pet_monitor_changed.connect(seen.append)
+    pet.publish_monitors()
+    assert seen and seen[-1] == pet.current_monitor_index()
+    assert 0 <= seen[-1] < len(pet.monitors())
+
+
+def test_jump_moves_the_window_onto_the_target_screen(pet):
+    monitors = pet.monitors()
+    target = len(monitors) - 1
+    pet.apply_action({"action": "jump", "monitor": target})
+    assert pet.current_monitor_index() == target
+    # a jump lands with a hop rather than sliding there
+    assert pet._emote == "hop"
+
+
+def test_jump_cancels_a_stroll_so_it_does_not_walk_back(pet):
+    pet.apply_action({"action": "move", "anchor": "top-left"})
+    assert pet._wander_target is not None
+    pet.apply_action({"action": "jump", "monitor": 0})
+    assert pet._wander_target is None
+    assert pet._commanded_move is False
+
+
+def test_jump_to_a_bogus_index_is_a_no_op(pet):
+    before = pet.pos()
+    pet.apply_action({"action": "jump", "monitor": 99})
+    pet.apply_action({"action": "jump", "monitor": -1})
+    assert pet.pos() == before
+
+
+# ── walk cycle ──────────────────────────────────────────────────────────────
+
+def test_walk_art_loads_as_a_non_state_animation(pet):
+    """Walking is a property of movement, not a PetState, so it lives outside
+    the state machine but still loads like any other animation."""
+    assert pet.sprites.has(WALK)
+    assert len(pet.sprites.get(WALK).frames) == 8
+    assert pet.sprites.get("nonsense") is pet.sprites.get(PetState.IDLE)
+    assert not pet.sprites.has("nonsense")
+
+
+def test_walking_overrides_the_state_animation(pet):
+    assert pet._animation_key() == pet._current_state
+    pet._advance_walk(50, 0, 1.0)
+    assert pet._animation_key() == WALK
+
+
+def test_walk_cycle_advances_by_distance_not_by_the_clock(pet):
+    """The planted paw tracks backwards at the speed the window moves
+    forwards; drive it off the animation timer instead and the feet skate."""
+    anim = pet.sprites.get(WALK)
+    anim.reset()
+    pet._advance_walk(100, 0, _WALK_PIXELS_PER_FRAME * 3)
+    assert anim._index == 3
+    # a step too small to cross the threshold banks the distance instead
+    pet._advance_walk(100, 0, _WALK_PIXELS_PER_FRAME * 0.5)
+    assert anim._index == 3
+    pet._advance_walk(100, 0, _WALK_PIXELS_PER_FRAME * 0.5)
+    assert anim._index == 4
+
+
+def test_the_animation_timer_does_not_double_step_the_walk(pet):
+    anim = pet.sprites.get(WALK)
+    pet._advance_walk(50, 0, 1.0)
+    anim.reset()
+    pet._advance_frame()
+    assert anim._index == 0
+
+
+def test_facing_follows_horizontal_travel(pet):
+    pet._advance_walk(50, 0, 1.0)
+    assert pet._facing == 1
+    pet._advance_walk(-50, 0, 1.0)
+    assert pet._facing == -1
+
+
+def test_a_near_vertical_stroll_does_not_flip_him(pet):
+    """Rounding noise on dx would otherwise flip him back and forth every
+    tick on a straight-up walk."""
+    pet._facing = 1
+    pet._advance_walk(0.4, 60, 1.0)
+    assert pet._facing == 1
+
+
+def test_walking_left_paints_a_mirrored_frame(pet):
+    frame = pet.sprites.get(WALK).current()
+    pet._facing = 1
+    assert pet._oriented(frame) is frame  # art is drawn facing right
+    pet._facing = -1
+    flipped = pet._oriented(frame)
+    assert flipped is not frame
+    assert flipped.size() == frame.size()
+    assert pet._oriented(frame) is flipped  # cached, not re-flipped per paint
+
+
+def test_stopping_resets_the_cycle_to_a_standing_frame(pet):
+    pet._advance_walk(50, 0, _WALK_PIXELS_PER_FRAME * 2)
+    assert pet._walking
+    pet._stop_walking()
+    assert not pet._walking
+    assert pet._walk_distance == 0.0
+    assert pet.sprites.get(WALK)._index == 0
+    assert pet._animation_key() == pet._current_state
+
+
+def test_walk_art_suppresses_the_hard_coded_bob(pet):
+    """The frames carry their own weight shift — bobbing the window as well
+    would double it up."""
+    pet._advance_walk(50, 0, 5.0)
+    assert pet._bob_offset == 0
+
+
+def test_without_walk_art_it_falls_back_to_the_old_bob(qt_app, tmp_path):
+    window = PetWindow(sprite_dir=tmp_path)
+    try:
+        assert not window.sprites.has(WALK)
+        window._advance_walk(50, 0, 5.0)
+        assert window._walking
+        assert window._animation_key() == window._current_state
+        assert window._bob_offset < 0  # still visibly moving
+    finally:
+        window.close()

tests/test_screen_text.py

@@ -0,0 +1,168 @@
+"""OCR plumbing for `petctl read` — engine selection and output cleanup.
+
+Only the pure half is covered, per the testing conventions: capture and the
+OCR call itself need a real screen and a real engine. Engine probes are
+injected so these pass on a machine with a different set installed (or none).
+"""
+
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from bolt_pet import screen_text
+from bolt_pet.monitors import Monitor
+
+
+def probes(modules=(), binaries=()):
+    return (lambda name: name in modules), (
+        lambda name: f"/usr/bin/{name}" if name in binaries else None
+    )
+
+
+def test_prefers_tesseract_when_fully_installed():
+    has_module, which = probes({"pytesseract"}, {"tesseract"})
+    assert screen_text.resolve_engine(has_module, which) == ("pytesseract", "")
+
+
+def test_falls_back_to_rapidocr_when_tesseract_binary_is_absent():
+    has_module, which = probes({"pytesseract", "rapidocr_onnxruntime"}, set())
+    engine, reason = screen_text.resolve_engine(has_module, which)
+    assert engine == "rapidocr"
+    assert reason == ""
+
+
+def test_pytesseract_without_the_binary_says_which_half_is_missing():
+    """The commonest broken setup: `pip install pytesseract` and stop, not
+    realising the actual engine is a system package."""
+    has_module, which = probes({"pytesseract"}, set())
+    engine, reason = screen_text.resolve_engine(has_module, which)
+    assert engine is None
+    assert "tesseract binary" in reason
+    assert "apt install tesseract-ocr" in reason
+
+
+def test_nothing_installed_explains_how_to_fix_it():
+    has_module, which = probes(set(), set())
+    engine, reason = screen_text.resolve_engine(has_module, which)
+    assert engine is None
+    assert "pip install" in reason
+
+
+def test_capture_availability_follows_mss():
+    assert screen_text.capture_available(lambda name: name == "mss")
+    assert not screen_text.capture_available(lambda name: False)
+
+
+def test_clean_drops_ocr_noise_and_blank_runs():
+    raw = "Firefox\n\n\n |\n  .\nBuild failed\n~\n"
+    assert screen_text.clean_ocr_text(raw) == "Firefox\nBuild failed"
+
+
+def test_clean_collapses_whitespace_but_keeps_line_structure():
+    raw = "  File     edit   view  \nline\ttwo  "
+    assert screen_text.clean_ocr_text(raw) == "File edit view\nline two"
+
+
+def test_clean_drops_consecutive_duplicates_only():
+    raw = "Terminal\nTerminal\nEditor\nTerminal"
+    assert screen_text.clean_ocr_text(raw) == "Terminal\nEditor\nTerminal"
+
+
+def test_clean_keeps_short_but_real_tokens():
+    # two alphanumerics is the bar — "ok" and "42" survive, "-" doesn't
+    assert screen_text.clean_ocr_text("ok\n-\n42") == "ok\n42"
+
+
+def test_clean_truncates_and_says_so():
+    out = screen_text.clean_ocr_text("word " * 500, max_chars=100)
+    assert out.endswith("[truncated]")
+    # the cap applies to the text, before the marker is appended
+    assert len(out.split("\n[truncated]")[0]) <= 100
+
+
+def test_clean_handles_empty_input():
+    assert screen_text.clean_ocr_text("") == ""
+    assert screen_text.clean_ocr_text(None) == ""
+
+
+def test_format_reading_names_the_monitor():
+    monitor = Monitor(1, "HDMI-1", 1920, 0, 1920, 1080)
+    out = screen_text.format_reading(monitor, "Build failed")
+    assert "monitor 2 (HDMI-1)" in out
+    assert out.endswith("Build failed")
+
+
+def test_format_reading_when_nothing_was_recognised():
+    monitor = Monitor(0, "DP-0", 0, 0, 1920, 1080)
+    assert "no text recognised" in screen_text.format_reading(monitor, "   ")
+
+
+def test_read_monitor_never_raises_without_an_engine(monkeypatch):
+    """Its return value goes back to the server as command output, so every
+    failure has to come back as a sentence rather than an exception."""
+    monkeypatch.setattr(screen_text, "capture_available", lambda *a, **k: True)
+    monkeypatch.setattr(
+        screen_text, "resolve_engine", lambda *a, **k: (None, "no engine here")
+    )
+    out = screen_text.read_monitor(Monitor(0, "DP-0", 0, 0, 1920, 1080))
+    assert out.startswith("[pet]")
+    assert "no engine here" in out
+
+
+def test_read_monitor_reports_a_failed_capture(monkeypatch):
+    monkeypatch.setattr(screen_text, "capture_available", lambda *a, **k: True)
+    monkeypatch.setattr(screen_text, "resolve_engine", lambda *a, **k: ("pytesseract", ""))
+    monkeypatch.setattr(screen_text, "capture", lambda monitor: None)
+    out = screen_text.read_monitor(Monitor(0, "DP-0", 0, 0, 1920, 1080))
+    assert "couldn't capture" in out and "Wayland" in out
+
+
+def test_read_monitor_survives_an_exploding_engine(monkeypatch):
+    monkeypatch.setattr(screen_text, "capture_available", lambda *a, **k: True)
+    monkeypatch.setattr(screen_text, "resolve_engine", lambda *a, **k: ("pytesseract", ""))
+    monkeypatch.setattr(screen_text, "capture", lambda monitor: object())
+    monkeypatch.setattr(
+        screen_text, "_ocr", lambda image, engine: (_ for _ in ()).throw(RuntimeError("boom"))
+    )
+    out = screen_text.read_monitor(Monitor(0, "DP-0", 0, 0, 1920, 1080))
+    assert "OCR failed" in out and "boom" in out
+
+
+def test_read_monitors_splits_the_budget(monkeypatch):
+    seen = []
+
+    def fake_read(monitor, max_chars):
+        seen.append((monitor.number, max_chars))
+        return f"screen {monitor.number}"
+
+    monkeypatch.setattr(screen_text, "read_monitor", fake_read)
+    screens = [
+        Monitor(0, "A", 0, 0, 100, 100),
+        Monitor(1, "B", 100, 0, 100, 100),
+        Monitor(2, "C", 200, 0, 100, 100),
+    ]
+    out = screen_text.read_monitors(screens, 3000)
+    assert [n for n, _ in seen] == [1, 2, 3]
+    assert all(limit == 1000 for _, limit in seen)
+    assert out.count("screen ") == 3
+
+
+def test_read_monitors_keeps_a_floor_on_the_budget(monkeypatch):
+    monkeypatch.setattr(
+        screen_text, "read_monitor", lambda monitor, max_chars: str(max_chars)
+    )
+    screens = [Monitor(i, str(i), 0, 0, 10, 10) for i in range(20)]
+    # 100/20 would be 5 characters per screen, which is useless — floor wins
+    assert "400" in screen_text.read_monitors(screens, 100)
+
+
+def test_read_monitors_with_one_screen_uses_the_whole_budget(monkeypatch):
+    monkeypatch.setattr(
+        screen_text, "read_monitor", lambda monitor, max_chars: str(max_chars)
+    )
+    assert screen_text.read_monitors([Monitor(0, "A", 0, 0, 10, 10)], 4000) == "4000"
+
+
+def test_read_monitors_with_no_screens():
+    assert "no monitor information" in screen_text.read_monitors([], 4000)

tests/test_screens_feature.py

@@ -0,0 +1,233 @@
+"""End-to-end wiring for the multi-monitor features: `petctl jump`, `petctl
+monitors`, `petctl read`, and the screen-layout note that rides along with
+each utterance.
+
+Needs a QApplication (signals), so run with QT_QPA_PLATFORM=offscreen.
+"""
+
+import sys
+from pathlib import Path
+
+import pytest
+from PySide6.QtWidgets import QApplication
+
+from bolt_pet import controller as controller_mod
+from bolt_pet import pet_actions
+from bolt_pet.monitors import Monitor
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+_app = QApplication.instance() or QApplication(["test"])
+
+
+@pytest.fixture(autouse=True)
+def no_screen_probes(monkeypatch):
+    monkeypatch.setattr(controller_mod.screen_context, "is_fullscreen_active", lambda: False)
+    monkeypatch.setattr(controller_mod.screen_context, "context_for", lambda text: text)
+
+
+@pytest.fixture
+def ctrl():
+    controller = controller_mod.PetController()
+    controller.set_monitors(
+        [
+            Monitor(0, "HDMI-0", 0, 0, 1920, 1080),
+            Monitor(1, "HDMI-1", 1920, 0, 1920, 1080),
+            Monitor(2, "DP-0", 0, 1080, 1920, 1080, primary=True),
+        ]
+    )
+    controller.set_pet_monitor(0)
+    return controller
+
+
+def _capture(signal):
+    events = []
+    signal.connect(lambda *a: events.append(a[0] if len(a) == 1 else a))
+    return events
+
+
+# ── parsing ─────────────────────────────────────────────────────────────────
+
+def test_jump_parses_without_validating_the_target():
+    """Which monitors exist is a runtime fact, so the pure parser passes the
+    spec through and monitors.resolve() judges it later."""
+    assert pet_actions.parse("petctl jump 2") == {"action": "jump", "target": "2"}
+    assert pet_actions.parse("petctl jump next") == {"action": "jump", "target": "next"}
+    assert pet_actions.parse("petctl monitor left") == {"action": "jump", "target": "left"}
+    assert pet_actions.parse("petctl screen HDMI-1") == {"action": "jump", "target": "HDMI-1"}
+    # a nonsense target is still parsed — it fails at resolve time, with a
+    # message listing the real monitors
+    assert pet_actions.parse("petctl jump sideways") == {
+        "action": "jump", "target": "sideways",
+    }
+
+
+def test_jump_needs_a_target():
+    with pytest.raises(pet_actions.ActionError, match="needs a monitor"):
+        pet_actions.parse("petctl jump")
+
+
+def test_read_defaults_to_the_current_screen():
+    assert pet_actions.parse("petctl read") == {"action": "read", "target": "here"}
+    assert pet_actions.parse("petctl read all") == {"action": "read", "target": "all"}
+    assert pet_actions.parse("petctl look 2") == {"action": "read", "target": "2"}
+    assert pet_actions.parse("petctl see here") == {"action": "read", "target": "here"}
+
+
+def test_monitors_verb():
+    for spelling in ("monitors", "screens", "displays"):
+        assert pet_actions.parse(f"petctl {spelling}") == {"action": "monitors"}
+
+
+def test_help_mentions_the_new_verbs():
+    assert "petctl jump" in pet_actions.HELP
+    assert "petctl read" in pet_actions.HELP
+    assert "petctl monitors" in pet_actions.HELP
+
+
+# ── jump ────────────────────────────────────────────────────────────────────
+
+def test_jump_resolves_to_an_index_before_reaching_the_window(ctrl):
+    """The controller resolves and emits a concrete index, so the window can't
+    re-resolve the spec against a different screen ordering."""
+    actions = _capture(ctrl.action)
+    out = ctrl._handle_command("petctl jump next")
+    assert actions == [{"action": "jump", "monitor": 1}]
+    assert "monitor 2: HDMI-1" in out
+
+
+def test_jump_by_direction_uses_the_published_layout(ctrl):
+    actions = _capture(ctrl.action)
+    ctrl._handle_command("petctl jump down")
+    assert actions == [{"action": "jump", "monitor": 2}]
+
+
+def test_jump_tracks_where_the_pet_actually_is(ctrl):
+    ctrl.set_pet_monitor(1)
+    actions = _capture(ctrl.action)
+    ctrl._handle_command("petctl jump left")
+    assert actions == [{"action": "jump", "monitor": 0}]
+
+
+def test_jump_to_a_nonexistent_monitor_reports_back_and_moves_nothing(ctrl):
+    actions = _capture(ctrl.action)
+    out = ctrl._handle_command("petctl jump 7")
+    assert actions == []
+    assert "no monitor 7" in out
+    assert "you have 3" in out
+
+
+def test_jump_never_reaches_the_shell(monkeypatch, ctrl):
+    ran = []
+    monkeypatch.setattr(controller_mod.server_client, "run_local_command", ran.append)
+    ctrl._handle_command("petctl jump 2")
+    ctrl._handle_command("petctl monitors")
+    ctrl._handle_command("petctl read")
+    assert ran == []
+
+
+# ── monitors ────────────────────────────────────────────────────────────────
+
+def test_monitors_lists_the_layout_and_where_the_pet_is(ctrl):
+    ctrl.set_pet_monitor(2)
+    out = ctrl._handle_command("petctl monitors")
+    assert "3 monitor(s)" in out
+    assert "HDMI-0" in out and "DP-0" in out
+    assert out.count("Bolt is here") == 1
+
+
+def test_monitors_before_the_ui_has_published_anything():
+    fresh = controller_mod.PetController()
+    assert "no monitor information" in fresh._handle_command("petctl monitors")
+
+
+# ── read ────────────────────────────────────────────────────────────────────
+
+def test_read_here_uses_the_pets_own_screen(monkeypatch, ctrl):
+    seen = []
+    monkeypatch.setattr(
+        controller_mod.screen_text, "read_monitor",
+        lambda monitor, limit: seen.append(monitor.number) or "text",
+    )
+    ctrl.set_pet_monitor(1)
+    assert ctrl._handle_command("petctl read") == "text"
+    assert seen == [2]
+
+
+def test_read_a_named_screen(monkeypatch, ctrl):
+    seen = []
+    monkeypatch.setattr(
+        controller_mod.screen_text, "read_monitor",
+        lambda monitor, limit: seen.append(monitor.name) or "text",
+    )
+    ctrl._handle_command("petctl read DP-0")
+    assert seen == ["DP-0"]
+
+
+def test_read_all_goes_through_the_multi_screen_path(monkeypatch, ctrl):
+    seen = []
+    monkeypatch.setattr(
+        controller_mod.screen_text, "read_monitors",
+        lambda monitors, limit: seen.append(len(monitors)) or "everything",
+    )
+    assert ctrl._handle_command("petctl read all") == "everything"
+    assert seen == [3]
+
+
+def test_read_an_unknown_screen_explains_rather_than_raising(ctrl):
+    out = ctrl._handle_command("petctl read 9")
+    assert out.startswith("[pet]")
+    assert "no monitor 9" in out
+
+
+def test_read_respects_the_kill_switch(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "SCREEN_TEXT", False)
+    called = []
+    monkeypatch.setattr(
+        controller_mod.screen_text, "read_monitor",
+        lambda *a, **k: called.append(1) or "text",
+    )
+    out = ctrl._handle_command("petctl read")
+    assert called == []
+    assert "disabled" in out and "SCREEN_TEXT" in out
+
+
+def test_read_passes_the_character_cap_through(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "SCREEN_TEXT_MAX_CHARS", 123)
+    seen = []
+    monkeypatch.setattr(
+        controller_mod.screen_text, "read_monitor",
+        lambda monitor, limit: seen.append(limit) or "text",
+    )
+    ctrl._handle_command("petctl read")
+    assert seen == [123]
+
+
+# ── per-turn context ────────────────────────────────────────────────────────
+
+def test_layout_rides_along_with_each_utterance(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "MONITOR_CONTEXT", True)
+    out = ctrl._with_context("what's on the other screen?")
+    assert out.startswith("what's on the other screen?")
+    assert "3 monitors:" in out
+    assert "Bolt is on 1" in out
+
+
+def test_layout_context_can_be_switched_off(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "MONITOR_CONTEXT", False)
+    assert ctrl._with_context("hello") == "hello"
+
+
+def test_screen_text_never_rides_along_automatically(monkeypatch, ctrl):
+    """The layout is free; the *contents* cost an OCR pass and a lot of
+    privacy, so they only ever move on an explicit petctl read."""
+    monkeypatch.setattr(controller_mod.config, "MONITOR_CONTEXT", True)
+    called = []
+    monkeypatch.setattr(
+        controller_mod.screen_text, "read_monitor", lambda *a, **k: called.append(1)
+    )
+    monkeypatch.setattr(
+        controller_mod.screen_text, "read_monitors", lambda *a, **k: called.append(1)
+    )
+    ctrl._with_context("hello")
+    assert called == []

tests/test_server_client.py

@@ -84,3 +84,47 @@ def test_check_health_returns_parsed_json():
         get.return_value = _mock_response({"ok": True, "service": "bolt-desk-api"})
         result = server_client.check_health()
     assert result == {"ok": True, "service": "bolt-desk-api"}
+
+
+def test_list_outbox_files_returns_the_queue():
+    with patch.object(server_client.requests, "get") as get:
+        get.return_value = _mock_response(
+            {"files": [{"id": "abc", "name": "report.pdf", "size": 9}]}
+        )
+        result = server_client.list_outbox_files()
+    assert result == [{"id": "abc", "name": "report.pdf", "size": 9}]
+    args, kwargs = get.call_args
+    assert args[0] == "http://test-server:5002/desk/files"
+    assert kwargs["params"] == {"session_id": "pet-test"}
+    assert kwargs["headers"] == {"X-Desk-Api-Key": "test-key"}
+
+
+def test_list_outbox_files_defaults_to_empty_list():
+    with patch.object(server_client.requests, "get") as get:
+        get.return_value = _mock_response({})
+        assert server_client.list_outbox_files() == []
+
+
+def test_list_outbox_files_raises_server_error_when_unreachable():
+    with patch.object(server_client.requests, "get", side_effect=ConnectionError("no route")):
+        with pytest.raises(server_client.ServerError):
+            server_client.list_outbox_files()
+
+
+def test_download_outbox_file_returns_raw_bytes():
+    with patch.object(server_client.requests, "get") as get:
+        resp = _mock_response({})
+        resp.content = b"%PDF fake bytes"
+        get.return_value = resp
+        result = server_client.download_outbox_file("abc")
+    assert result == b"%PDF fake bytes"
+    args, kwargs = get.call_args
+    assert args[0] == "http://test-server:5002/desk/files/abc"
+    assert kwargs["params"] == {"session_id": "pet-test"}
+
+
+def test_download_outbox_file_raises_server_error_on_http_failure():
+    with patch.object(server_client.requests, "get") as get:
+        get.return_value = _mock_response({}, ok=False)
+        with pytest.raises(server_client.ServerError, match="abc"):
+            server_client.download_outbox_file("abc")

tests/test_speech_text.py

@@ -6,7 +6,7 @@ from pathlib import Path
 
 sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
 
-from bolt_pet.speech_text import for_display, for_speech
+from bolt_pet.speech_text import for_display, for_speech, is_question
 
 
 def test_bold_markers_are_not_spoken():
@@ -57,3 +57,23 @@ def test_blank_and_symbol_only_input():
 def test_display_keeps_emoji_but_drops_markdown():
     assert for_display("**Done** ✅") == "Done ✅"
     assert for_display("* one\n* two") == "• one • two"
+
+
+def test_is_question_only_fires_on_a_trailing_question():
+    assert is_question("Ready to run a command or start a project?")
+    assert is_question("It's 7:15 AM. Want me to set a timer?")
+    assert not is_question("It's 7:15 AM on July 23, 2026.")
+    assert not is_question("What time is it? It's 7:15 AM.")  # asked in passing
+
+
+def test_is_question_ignores_trailing_decoration():
+    assert is_question("Ready to go? 🚀")
+    assert is_question('Shall I continue?"')
+    assert is_question("Want me to fix it? **")
+
+
+def test_is_question_ignores_question_marks_that_are_not_spoken():
+    # The '?' here is inside a URL query string, which for_speech strips.
+    assert not is_question("Docs are at https://example.com/x?y=1")
+    assert not is_question("")
+    assert not is_question(None)

tests/test_sudo_askpass.py

@@ -0,0 +1,122 @@
+"""Graphical sudo prompts: command rewriting and helper resolution.
+Pure logic — no display, no sudo, no password."""
+
+import sys
+from pathlib import Path
+
+import pytest
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from bolt_pet import sudo_askpass
+
+
+# ── rewriting ────────────────────────────────────────────────────────────────
+
+
+@pytest.mark.parametrize(
+    "command,expected",
+    [
+        ("sudo apt update", "sudo -A apt update"),
+        ("sudo  apt update", "sudo -A  apt update"),  # spacing preserved
+        ("apt update && sudo apt upgrade", "apt update && sudo -A apt upgrade"),
+        ("ls; sudo reboot", "ls; sudo -A reboot"),
+        ("echo hi | sudo tee /etc/motd", "echo hi | sudo -A tee /etc/motd"),
+        ("sudo systemctl restart x\nsudo systemctl status x",
+         "sudo -A systemctl restart x\nsudo -A systemctl status x"),
+    ],
+)
+def test_bare_sudo_gets_the_askpass_flag(command, expected):
+    assert sudo_askpass.add_askpass_flag(command) == expected
+
+
+@pytest.mark.parametrize(
+    "command",
+    [
+        "sudo -n apt update",     # explicitly non-interactive
+        "sudo -A apt update",     # already asking
+        "sudo -u bob whoami",     # the caller was explicit
+        "ls -la",                 # no sudo at all
+        "echo 'run sudo later'",  # inside a quoted string
+        "pseudo --version",       # not the word sudo
+    ],
+)
+def test_commands_that_must_not_be_rewritten(command):
+    assert sudo_askpass.add_askpass_flag(command) == command
+
+
+def test_blank_input():
+    assert sudo_askpass.add_askpass_flag("") == ""
+    assert sudo_askpass.add_askpass_flag(None) == ""
+
+
+@pytest.mark.parametrize(
+    "command,expected",
+    [
+        ("sudo apt update", True),
+        ("ls && sudo reboot", True),
+        ("ls -la", False),
+        ("echo 'sudo'", False),
+        ("", False),
+    ],
+)
+def test_which_commands_get_the_longer_timeout(command, expected):
+    assert sudo_askpass.needs_password_prompt(command) is expected
+
+
+# ── helper resolution ────────────────────────────────────────────────────────
+
+
+def test_a_configured_helper_wins():
+    found = sudo_askpass.find_helper(
+        configured="/opt/my-askpass", is_executable=lambda p: p == "/opt/my-askpass",
+    )
+    assert found == "/opt/my-askpass"
+
+
+def test_a_configured_helper_that_is_not_executable_is_not_silently_replaced():
+    """Better to have sudo fail than to quietly prompt with something the
+    user didn't choose."""
+    assert sudo_askpass.find_helper(
+        configured="/opt/typo", is_executable=lambda p: False, which=lambda t: "/usr/bin/zenity",
+    ) is None
+
+
+def test_a_real_askpass_binary_beats_a_generated_wrapper():
+    found = sudo_askpass.find_helper(
+        configured="", is_executable=lambda p: p == "/usr/bin/ksshaskpass",
+        which=lambda tool: "/usr/bin/zenity",
+    )
+    assert found == "/usr/bin/ksshaskpass"
+
+
+def test_falls_back_to_wrapping_a_dialog_tool(tmp_path):
+    found = sudo_askpass.find_helper(
+        configured="", is_executable=lambda p: False,
+        which=lambda tool: "/usr/bin/zenity" if tool == "zenity" else None,
+        cache_dir=tmp_path,
+    )
+    script = tmp_path / "askpass.sh"
+    assert found == str(script)
+    assert "zenity --password" in script.read_text()
+    assert script.stat().st_mode & 0o777 == 0o700  # nobody else edits the password box
+
+
+def test_no_helper_available_at_all():
+    assert sudo_askpass.find_helper(
+        configured="", is_executable=lambda p: False, which=lambda tool: None,
+    ) is None
+
+
+def test_the_wrapper_passes_sudos_prompt_through():
+    """sudo hands the helper its prompt as $1 — it names the account the
+    password is for, which is worth showing in the dialog."""
+    script = sudo_askpass.helper_script("/usr/bin/zenity")
+    assert script.startswith("#!/bin/sh")
+    assert '"$1"' in script
+
+
+def test_environment_points_sudo_at_the_helper():
+    env = sudo_askpass.environment("/tmp/askpass.sh", base={"PATH": "/usr/bin"})
+    assert env["SUDO_ASKPASS"] == "/tmp/askpass.sh"
+    assert env["PATH"] == "/usr/bin"  # the rest of the environment survives

tests/test_updater.py

@@ -67,12 +67,15 @@ class FakeGit:
     *failures* maps a leading-args tuple to the (code, output) it should
     return, so a test can make exactly one command fail."""
 
-    def __init__(self, ref="main", dirty=False, failures=None, requirements_changed=False):
+    def __init__(self, ref="main", dirty=False, failures=None, requirements_changed=False,
+                 head="abc1234", tag_commit="def5678"):
         self.calls = []
         self._ref = ref
         self._dirty = dirty
         self._failures = failures or {}
         self._requirements_changed = requirements_changed
+        self._head = head
+        self._tag_commit = tag_commit  # equal to head = "already on this tag"
 
     def __call__(self, args):
         self.calls.append(list(args))
@@ -87,7 +90,7 @@ class FakeGit:
         if head == "symbolic-ref":
             return (0, self._ref) if self._ref else (1, "")
         if head == "rev-parse":
-            return 0, "abc1234"
+            return 0, self._tag_commit if args[1].startswith("tags/") else self._head
         if head == "diff":
             return 0, "requirements.txt" if self._requirements_changed else ""
         return 0, ""
@@ -160,6 +163,26 @@ def test_a_verify_that_raises_something_unexpected_still_rolls_back(tmp_path):
     assert ["checkout", "--force", "main"] in git.calls
 
 
+def test_a_release_tagged_without_bumping_the_version_does_not_loop(tmp_path):
+    """Cut a release but forget to bump __version__ in the tagged commit and
+    every check would see the same "newer" tag: check out (a no-op), restart,
+    read the old version, repeat — a restart loop every check interval."""
+    git = FakeGit(head="same1234", tag_commit="same1234")
+
+    with pytest.raises(updater.UpdateError, match="bump it in the tagged commit"):
+        updater.apply_update("v0.2.1", run=git, repo=tmp_path, install_deps=False,
+                             verify=lambda repo: None)
+
+    assert "checkout" not in git.commands()  # nothing moved, so nothing to restart into
+
+
+def test_an_unknown_tag_is_not_mistaken_for_being_already_on_it(tmp_path):
+    git = FakeGit(failures={("rev-parse", "tags/"): (128, "unknown revision")})
+    # The failure key matches by prefix, so make it explicit that a tag we
+    # can't resolve means "not there yet" rather than "already applied".
+    assert updater.already_at_tag(git, "v9.9.9") is False
+
+
 def test_a_failed_fetch_never_moves_the_checkout(tmp_path):
     git = FakeGit(failures={("fetch",): (1, "could not resolve host")})
     with pytest.raises(updater.UpdateError, match="git fetch failed"):