feat(pets): crisp Kitty images in the TUI + reactive pet pane in the base CLI

The TUI now renders pets through Kitty's Unicode-placeholder protocol on
Kitty/Ghostty: the image transmits once per frame under a stable id and the
static placeholder grid (U+10EEEE + diacritics, image id in the fg color)
animates underneath without Ink ever repainting. Only Kitty is grid-safe in
Ink, so iTerm/Sixel/tmux/dashboard keep the half-block fallback.

The base CLI gains parity with the TUI's PetPane: a right-aligned half-block
sprite above the prompt, reactive to agent activity and animated by an
invalidate timer. Half-blocks only — raw image escapes can't survive
prompt_toolkit's patch_stdout output layer.

Also: right-align the pet in the TUI (justifyContent) and in `hermes pets
show` (graphics path), and render lone-opaque half-blocks fg-only so
transparent sprite edges stop painting black boxes.
This commit is contained in:
Brooklyn Nicholson 2026-06-15 01:27:40 -05:00
parent 2572617d5a
commit fdcfa44584
10 changed files with 743 additions and 57 deletions

View File

@ -178,33 +178,131 @@ def _png_bytes(frame) -> bytes:
return buf.getvalue()
def _kitty_apc(ctrl: str, data: str) -> str:
"""Emit a kitty APC escape for *data*, chunked into ≤4096-byte ``m`` pieces."""
chunk = 4096
if len(data) <= chunk:
return f"\x1b_G{ctrl},m=0;{data}\x1b\\"
out = [f"\x1b_G{ctrl},m=1;{data[:chunk]}\x1b\\"]
rest = data[chunk:]
while rest:
piece, rest = rest[:chunk], rest[chunk:]
out.append(f"\x1b_Gm={1 if rest else 0};{piece}\x1b\\")
return "".join(out)
def _encode_kitty(frame, *, cell_cols: int | None = None, cell_rows: int | None = None) -> str:
"""Encode one frame via the kitty graphics protocol (transmit + display).
Splits the base64 PNG into 4096-byte chunks per the protocol, using
``a=T`` (transmit & display at the cursor). ``c``/``r`` request a display
``a=T`` transmits & displays at the cursor; ``c``/``r`` request a display
box in terminal cells so successive frames overwrite the same area.
"""
data = base64.standard_b64encode(_png_bytes(frame)).decode("ascii")
extra = "f=100,a=T,q=2"
ctrl = "f=100,a=T,q=2"
if cell_cols:
extra += f",c={cell_cols}"
ctrl += f",c={cell_cols}"
if cell_rows:
extra += f",r={cell_rows}"
ctrl += f",r={cell_rows}"
return _kitty_apc(ctrl, base64.standard_b64encode(_png_bytes(frame)).decode("ascii"))
chunk = 4096
# ─────────────────────────────────────────────────────────────────────────
# kitty Unicode placeholders
#
# Ink (the TUI's React-for-terminal layer) owns the screen and measures every
# cell's width, so it can't host raw kitty image escapes (no width to count,
# clobbered on the next repaint). kitty's *Unicode placeholder* protocol is the
# grid-safe path: transmit the image once (q=2, virtual placement U=1), then the
# host app prints ordinary-width placeholder cells (U+10EEEE + diacritics) whose
# foreground color encodes the image id. Ink counts those as width-1 text, so
# layout stays correct and the terminal paints the image underneath.
# https://sw.kovidgoyal.net/kitty/graphics-protocol/#unicode-placeholders
# ─────────────────────────────────────────────────────────────────────────
_KITTY_PLACEHOLDER = "\U0010eeee"
# Row/column diacritics, in order (index → diacritic). Verbatim from kitty's
# gen/rowcolumn-diacritics.txt (Unicode 6.0.0, combining class 230). Index i is
# the diacritic that encodes the number i; we only ever need the row index.
_ROWCOL_DIACRITICS: tuple[int, ...] = (
0x0305, 0x030D, 0x030E, 0x0310, 0x0312, 0x033D, 0x033E, 0x033F, 0x0346, 0x034A,
0x034B, 0x034C, 0x0350, 0x0351, 0x0352, 0x0357, 0x035B, 0x0363, 0x0364, 0x0365,
0x0366, 0x0367, 0x0368, 0x0369, 0x036A, 0x036B, 0x036C, 0x036D, 0x036E, 0x036F,
0x0483, 0x0484, 0x0485, 0x0486, 0x0487, 0x0592, 0x0593, 0x0594, 0x0595, 0x0597,
0x0598, 0x0599, 0x059C, 0x059D, 0x059E, 0x059F, 0x05A0, 0x05A1, 0x05A8, 0x05A9,
0x05AB, 0x05AC, 0x05AF, 0x05C4, 0x0610, 0x0611, 0x0612, 0x0613, 0x0614, 0x0615,
0x0616, 0x0617, 0x0657, 0x0658, 0x0659, 0x065A, 0x065B, 0x065D, 0x065E, 0x06D6,
0x06D7, 0x06D8, 0x06D9, 0x06DA, 0x06DB, 0x06DC, 0x06DF, 0x06E0, 0x06E1, 0x06E2,
0x06E4, 0x06E7, 0x06E8, 0x06EB, 0x06EC, 0x0730, 0x0732, 0x0733, 0x0735, 0x0736,
0x073A, 0x073D, 0x073F, 0x0740, 0x0741, 0x0743, 0x0745, 0x0747, 0x0749, 0x074A,
0x07EB, 0x07EC, 0x07ED, 0x07EE, 0x07EF, 0x07F0, 0x07F1, 0x07F3, 0x0816, 0x0817,
0x0818, 0x0819, 0x081B, 0x081C, 0x081D, 0x081E, 0x081F, 0x0820, 0x0821, 0x0822,
0x0823, 0x0825, 0x0826, 0x0827, 0x0829, 0x082A, 0x082B, 0x082C, 0x082D, 0x0951,
0x0953, 0x0954, 0x0F82, 0x0F83, 0x0F86, 0x0F87, 0x135D, 0x135E, 0x135F, 0x17DD,
0x193A, 0x1A17, 0x1A75, 0x1A76, 0x1A77, 0x1A78, 0x1A79, 0x1A7A, 0x1A7B, 0x1A7C,
0x1B6B, 0x1B6D, 0x1B6E, 0x1B6F, 0x1B70, 0x1B71, 0x1B72, 0x1B73, 0x1CD0, 0x1CD1,
0x1CD2, 0x1CDA, 0x1CDB, 0x1CE0, 0x1DC0, 0x1DC1, 0x1DC3, 0x1DC4, 0x1DC5, 0x1DC6,
0x1DC7, 0x1DC8, 0x1DC9, 0x1DCB, 0x1DCC, 0x1DD1, 0x1DD2, 0x1DD3, 0x1DD4, 0x1DD5,
0x1DD6, 0x1DD7, 0x1DD8, 0x1DD9, 0x1DDA, 0x1DDB, 0x1DDC, 0x1DDD, 0x1DDE, 0x1DDF,
0x1DE0, 0x1DE1, 0x1DE2, 0x1DE3, 0x1DE4, 0x1DE5, 0x1DE6, 0x1DFE, 0x20D0, 0x20D1,
0x20D4, 0x20D5, 0x20D6, 0x20D7, 0x20DB, 0x20DC, 0x20E1, 0x20E7, 0x20E9, 0x20F0,
0x2CEF, 0x2CF0, 0x2CF1, 0x2DE0, 0x2DE1, 0x2DE2, 0x2DE3, 0x2DE4, 0x2DE5, 0x2DE6,
0x2DE7, 0x2DE8, 0x2DE9, 0x2DEA, 0x2DEB, 0x2DEC, 0x2DED, 0x2DEE, 0x2DEF, 0x2DF0,
0x2DF1, 0x2DF2, 0x2DF3, 0x2DF4, 0x2DF5, 0x2DF6, 0x2DF7, 0x2DF8, 0x2DF9, 0x2DFA,
0x2DFB, 0x2DFC, 0x2DFD, 0x2DFE, 0x2DFF, 0xA66F, 0xA67C, 0xA67D, 0xA6F0, 0xA6F1,
0xA8E0, 0xA8E1, 0xA8E2, 0xA8E3, 0xA8E4, 0xA8E5, 0xA8E6, 0xA8E7, 0xA8E8, 0xA8E9,
0xA8EA, 0xA8EB, 0xA8EC, 0xA8ED, 0xA8EE, 0xA8EF, 0xA8F0, 0xA8F1, 0xAAB0, 0xAAB2,
0xAAB3, 0xAAB7, 0xAAB8, 0xAABE, 0xAABF, 0xAAC1, 0xFE20, 0xFE21, 0xFE22, 0xFE23,
0xFE24, 0xFE25, 0xFE26, 0x10A0F, 0x10A38, 0x1D185, 0x1D186, 0x1D187, 0x1D188,
0x1D189, 0x1D1AA, 0x1D1AB, 0x1D1AC, 0x1D1AD, 0x1D242, 0x1D243, 0x1D244,
)
def kitty_image_id(slug: str) -> int:
"""Stable per-pet image id in ``[1, 0x7FFF]``.
The id is encoded in the placeholder's 24-bit foreground color, so it must
be non-zero and fit comfortably under ``0xFFFFFF``. A small CRC keeps it
deterministic per slug (so re-renders reuse the same terminal-side image)
while making collisions between two different pets unlikely.
"""
import zlib
return (zlib.crc32(slug.encode("utf-8")) % 0x7FFE) + 1
def kitty_color_hex(image_id: int) -> str:
"""Hex foreground color (``#rrggbb``) that encodes *image_id* for kitty."""
return "#%06x" % (image_id & 0xFFFFFF)
def kitty_placeholder_rows(cols: int, rows: int) -> list[str]:
"""Build the placeholder text grid for an *rows*×*cols* image.
Each line is one row of the grid: the first cell carries the row diacritic
(column defaults to 0), and the remaining ``cols-1`` bare placeholders let
the terminal auto-increment the column. The foreground color (the image id)
is applied by the caller / Ink, not embedded here.
"""
cols = max(1, cols)
out: list[str] = []
if len(data) <= chunk:
out.append(f"\x1b_G{extra},m=0;{data}\x1b\\")
else:
first = data[:chunk]
out.append(f"\x1b_G{extra},m=1;{first}\x1b\\")
rest = data[chunk:]
while rest:
piece, rest = rest[:chunk], rest[chunk:]
more = 1 if rest else 0
out.append(f"\x1b_Gm={more};{piece}\x1b\\")
return "".join(out)
for r in range(max(1, rows)):
idx = min(r, len(_ROWCOL_DIACRITICS) - 1)
first = _KITTY_PLACEHOLDER + chr(_ROWCOL_DIACRITICS[idx])
out.append(first + _KITTY_PLACEHOLDER * (cols - 1))
return out
def _encode_kitty_virtual(frame, *, image_id: int, cols: int, rows: int) -> str:
"""Transmit a frame as a kitty *virtual* placement for Unicode placeholders.
``a=T`` transmits and creates the placement in one shot; ``U=1`` marks it
virtual (no on-screen output, cursor untouched); ``q=2`` suppresses the
terminal's OK/error replies that would otherwise corrupt the host app's
output. Re-sending with the same ``i`` replaces the image, so the static
placeholder cells animate underneath.
"""
ctrl = f"a=T,U=1,i={image_id},c={cols},r={rows},f=100,q=2"
return _kitty_apc(ctrl, base64.standard_b64encode(_png_bytes(frame)).decode("ascii"))
def _encode_iterm(frame, *, cell_cols: int | None = None, cell_rows: int | None = None) -> str:
@ -391,6 +489,36 @@ class PetRenderer:
frame = frames[index % len(frames)]
return _downscale_cells(frame, target_cols=cols or self.unicode_cols)
def kitty_cell_rows(self, cols: int) -> int:
"""Cell height that mirrors the half-block footprint for *cols* wide.
Keeps the kitty image and the unicode fallback occupying the same area
so swapping renderers doesn't shift the layout.
"""
aspect = self.frame_h / max(1, self.frame_w)
return max(1, round(cols * aspect * 0.5))
def kitty_payload(self, state: PetState | str, *, cols: int, image_id: int) -> dict | None:
"""Build the kitty Unicode-placeholder payload for one state.
Returns ``{cols, rows, placeholder, frames}`` where ``frames`` is a
list of transmit escapes (one per animation frame, all reusing
``image_id``) and ``placeholder`` is the static text grid Ink paints.
``None`` when no frame is available.
"""
frames = self._frames(state)
if not frames:
return None
rows = self.kitty_cell_rows(cols)
return {
"cols": cols,
"rows": rows,
"placeholder": kitty_placeholder_rows(cols, rows),
"frames": [
_encode_kitty_virtual(f, image_id=image_id, cols=cols, rows=rows) for f in frames
],
}
def frame(self, state: PetState | str, index: int) -> str:
"""Return the encoded escape string for one frame, or ``""``.

197
cli.py
View File

@ -60,7 +60,7 @@ from prompt_toolkit.history import FileHistory
from prompt_toolkit.styles import Style as PTStyle
from prompt_toolkit.patch_stdout import patch_stdout
from prompt_toolkit.application import Application
from prompt_toolkit.layout import Layout, HSplit, Window, FormattedTextControl, ConditionalContainer
from prompt_toolkit.layout import Layout, HSplit, Window, FormattedTextControl, ConditionalContainer, WindowAlign
from prompt_toolkit.layout.processors import Processor, Transformation, PasswordProcessor, ConditionalProcessor
from prompt_toolkit.filters import Condition
from prompt_toolkit.layout.dimension import Dimension
@ -3567,6 +3567,20 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
self._last_scrollback_tool: str = "" # last tool name printed to scrollback (for "new" dedup)
self._command_running = False
self._command_status = ""
# Petdex mascot (opt-in via display.pet). The base CLI mirrors the TUI's
# PetPane: a half-block sprite above the prompt that reacts to agent
# activity. Lazily resolved; an invalidate timer drives the animation.
self._pet_renderer = None # agent.pet.render.PetRenderer | None
self._pet_slug: str = ""
self._pet_enabled: bool = False
self._pet_cols: int = 18
self._pet_scale: float = 0.7
self._pet_frames_cache: dict = {} # state -> list[grid]
self._pet_frame_idx: int = 0
self._pet_lock = threading.Lock()
self._pet_cfg_checked: float = 0.0
self._pet_anim_running: bool = False
self._pet_anim_thread = None
self._attached_images: list[Path] = []
self._image_counter = 0
self.preloaded_skills: list[str] = []
@ -4107,6 +4121,173 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
return f" {txt} ({elapsed_str})"
return f" {txt}"
# ── Petdex mascot (base-CLI pet pane) ───────────────────────────────
#
# Parity with the TUI: a half-block sprite rendered as a prompt_toolkit
# window above the prompt, reacting to agent state and animated by a timer
# that calls ``app.invalidate()``. Half-blocks only — the crisp Kitty image
# protocol can't coexist with prompt_toolkit's patch_stdout output layer
# (raw image escapes get swallowed/mangled), so we use truecolor styled
# text, which prompt_toolkit renders natively in any 24-bit terminal.
_PET_FRAME_INTERVAL = 0.16
_PET_CFG_INTERVAL = 2.5
def _pet_resolve_config(self) -> None:
"""(Re)resolve the active pet from config — picks up live enable/disable/
switch made via ``/pet`` or ``hermes pets`` without a restart, mirroring
the TUI's steady poll. Cheap and fail-open: any problem disables the pet.
"""
try:
from agent.pet import constants, store
from agent.pet.render import PetRenderer
from hermes_cli.config import load_config
cfg = load_config()
display = cfg.get("display", {}) if isinstance(cfg.get("display"), dict) else {}
pet_cfg = display.get("pet", {}) if isinstance(display.get("pet"), dict) else {}
enabled = bool(pet_cfg.get("enabled"))
slug = str(pet_cfg.get("slug", "") or "")
cols = int(pet_cfg.get("unicode_cols", 18) or 18)
scale = float(pet_cfg.get("scale", constants.DEFAULT_SCALE) or constants.DEFAULT_SCALE)
if not enabled:
with self._pet_lock:
self._pet_enabled = False
self._pet_renderer = None
self._pet_frames_cache.clear()
return
pet = store.resolve_active_pet(slug)
if pet is None or not pet.exists:
with self._pet_lock:
self._pet_enabled = False
self._pet_renderer = None
self._pet_frames_cache.clear()
return
with self._pet_lock:
# Rebuild only when the resolved pet or geometry changes.
if (
self._pet_renderer is None
or self._pet_slug != pet.slug
or self._pet_cols != cols
or self._pet_scale != scale
):
self._pet_renderer = PetRenderer(
str(pet.spritesheet), mode="unicode", scale=scale, unicode_cols=cols
)
self._pet_slug = pet.slug
self._pet_cols = cols
self._pet_scale = scale
self._pet_frames_cache.clear()
self._pet_frame_idx = 0
self._pet_enabled = True
except Exception:
with self._pet_lock:
self._pet_enabled = False
self._pet_renderer = None
def _derive_pet_state(self) -> str:
"""Map current CLI activity to a pet animation state (mirrors the TUI)."""
if getattr(self, "_agent_running", False):
return "run"
return "idle"
def _pet_frames_for(self, state: str) -> list:
"""Return (and cache) the half-block grids for one state."""
cached = self._pet_frames_cache.get(state)
if cached is not None:
return cached
renderer = self._pet_renderer
if renderer is None:
return []
try:
count = renderer.frame_count(state) or 1
grids = [renderer.cells(state, i, cols=self._pet_cols) for i in range(count)]
except Exception:
grids = []
self._pet_frames_cache[state] = grids
return grids
def _pet_fragments(self):
"""Return prompt_toolkit FormattedText for the current pet frame, or []."""
with self._pet_lock:
if not self._pet_enabled or self._pet_renderer is None:
return []
state = self._derive_pet_state()
grids = self._pet_frames_for(state)
if not grids:
return []
grid = grids[self._pet_frame_idx % len(grids)]
frags = []
for y, row in enumerate(grid):
if y:
frags.append(("", "\n"))
for top, bottom in row:
tr, tg, tb, ta = top
br, bg, bb, ba = bottom
top_op = ta >= 32
bot_op = ba >= 32
if not top_op and not bot_op:
frags.append(("", " "))
elif top_op and bot_op:
frags.append((f"fg:#{tr:02x}{tg:02x}{tb:02x} bg:#{br:02x}{bg:02x}{bb:02x}", ""))
elif top_op:
# Upper half only — leave the lower half the terminal's bg
# instead of painting it black (cleaner on light themes).
frags.append((f"fg:#{tr:02x}{tg:02x}{tb:02x}", ""))
else:
frags.append((f"fg:#{br:02x}{bg:02x}{bb:02x}", ""))
return frags
def _pet_widget_height(self) -> int:
"""Visible rows for the pet window — 0 collapses it when no pet shows."""
with self._pet_lock:
if not self._pet_enabled or self._pet_renderer is None:
return 0
grids = self._pet_frames_for(self._derive_pet_state())
if not grids or not grids[0]:
return 0
return len(grids[0])
def _pet_anim_loop(self) -> None:
"""Advance the frame + invalidate on a timer while a pet is enabled."""
while self._pet_anim_running:
time.sleep(self._PET_FRAME_INTERVAL)
now = time.monotonic()
if now - self._pet_cfg_checked >= self._PET_CFG_INTERVAL:
self._pet_cfg_checked = now
self._pet_resolve_config()
if not self._pet_enabled:
continue
with self._pet_lock:
self._pet_frame_idx += 1
app = getattr(self, "_app", None)
if app is not None:
try:
app.invalidate()
except Exception:
pass
def _pet_start_anim(self) -> None:
if self._pet_anim_running:
return
self._pet_resolve_config()
self._pet_anim_running = True
self._pet_anim_thread = threading.Thread(target=self._pet_anim_loop, daemon=True)
self._pet_anim_thread.start()
def _pet_stop_anim(self) -> None:
self._pet_anim_running = False
thread = self._pet_anim_thread
if thread is not None:
thread.join(timeout=0.3)
self._pet_anim_thread = None
def _voice_record_key_label(self) -> str:
"""Return the configured voice push-to-talk key formatted for UI.
@ -10917,6 +11098,7 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
spinner_widget,
spacer,
*self._get_extra_tui_widgets(),
getattr(self, "_pet_widget", None),
status_bar,
input_rule_top,
image_bar,
@ -12258,6 +12440,16 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
wrap_lines=True,
)
# Petdex mascot — right-aligned half-block sprite above the prompt,
# mirroring the TUI's PetPane. Collapses to height 0 when no pet is
# enabled, so it's a no-op for everyone else. The _pet_anim_loop thread
# advances frames + invalidates; align=RIGHT pins it to the edge.
self._pet_widget = Window(
content=FormattedTextControl(self._pet_fragments),
height=self._pet_widget_height,
align=WindowAlign.RIGHT,
)
spacer = Window(
content=FormattedTextControl(get_hint_text),
height=get_hint_height,
@ -13270,6 +13462,8 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
# The app enables focus reporting + mouse tracking; record that
# so _run_cleanup resets them on exit (#36823).
_mark_tui_input_modes_active()
# Drive the petdex mascot animation (no-op when no pet enabled).
self._pet_start_anim()
app.run()
except (EOFError, KeyboardInterrupt, BrokenPipeError):
pass
@ -13296,6 +13490,7 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
raise
finally:
self._should_exit = True
self._pet_stop_anim()
# Interrupt the agent immediately so its daemon thread stops making
# API calls and exits promptly (agent_thread is daemon, so the
# process will exit once the main thread finishes, but interrupting

View File

@ -176,13 +176,19 @@ def _cmd_show(args) -> int:
is_unicode = renderer.mode == "unicode"
frame_delay = max(0.05, (LOOP_MS / 1000.0) / max(1, renderer.frame_count(states[0]) or 1))
# Right-align the half-block sprite against the terminal's right edge.
# Right-align the sprite against the terminal's right edge — half-blocks by
# indenting each row, graphics protocols by padding the cursor to the right
# column before the image draws (kitty/iTerm/sixel all render at the cursor).
import shutil
term_cols = shutil.get_terminal_size((80, 24)).columns
indent = ""
g_indent = ""
if is_unicode:
term_cols = shutil.get_terminal_size((80, 24)).columns
indent = " " * max(0, term_cols - cols - 1)
else:
cell_cols = max(1, int(renderer.frame_w * renderer.scale) // 8)
g_indent = " " * max(0, term_cols - cell_cols - 1)
out = sys.stdout
out.write("\x1b[?25l") # hide cursor
@ -209,6 +215,8 @@ def _cmd_show(args) -> int:
else:
out.write("\x1b[2J\x1b[3J\x1b[H") # clear for image protocols
out.write(f"{pet.display_name} [{state}]\n")
if g_indent:
out.write(g_indent)
out.write(encoded)
out.write("\n")
out.flush()

View File

@ -147,6 +147,66 @@ def test_cells_grid_shape(boba_like):
assert render.PetRenderer(str(sprite.parent / "missing.webp"), mode="unicode").cells("idle", 0) == []
# ─────────────────────────────────────────────────────────────────────────
# render — kitty Unicode placeholders (TUI graphics path)
# ─────────────────────────────────────────────────────────────────────────
def test_kitty_image_id_stable_bounded_nonzero():
# Deterministic per slug so re-renders reuse the same terminal-side image,
# and always a valid 24-bit-encodable, non-zero id.
a = render.kitty_image_id("boba")
assert a == render.kitty_image_id("boba")
assert 1 <= a <= 0x7FFF
def test_kitty_color_hex_decodes_to_id():
# The placeholder's foreground color IS the image id (24-bit). The terminal
# reconstructs id = (r<<16)|(g<<8)|b, so the hex must round-trip.
for slug in ("boba", "clawd", "pixel-fox"):
image_id = render.kitty_image_id(slug)
h = render.kitty_color_hex(image_id)
assert h.startswith("#") and len(h) == 7
assert int(h[1:], 16) == image_id
def test_kitty_placeholder_rows_grid_contract():
cols, rows = 18, 10
grid = render.kitty_placeholder_rows(cols, rows)
assert len(grid) == rows
placeholder = "\U0010eeee"
for r, row in enumerate(grid):
# Each line is exactly `cols` placeholder cells (combining diacritics
# are zero-width, so this is the rendered width Ink must measure).
assert row.count(placeholder) == cols
# First cell carries this row's diacritic; the rest inherit row + col.
assert row.startswith(placeholder + chr(render._ROWCOL_DIACRITICS[r]))
def test_kitty_payload_structure(boba_like):
sprite = store.load_pet("boba").spritesheet
image_id = render.kitty_image_id("boba")
r = render.PetRenderer(str(sprite), mode="kitty", scale=0.4, unicode_cols=18)
payload = r.kitty_payload("run", cols=18, image_id=image_id)
assert payload is not None
assert payload["cols"] == 18
assert payload["rows"] == r.kitty_cell_rows(18) >= 1
# placeholder grid matches the requested geometry
assert len(payload["placeholder"]) == payload["rows"]
# one transmit escape per animation frame, each a kitty virtual placement
assert len(payload["frames"]) == r.frame_count("run")
for esc in payload["frames"]:
assert esc.startswith("\x1b_G")
assert esc.endswith("\x1b\\")
assert f"i={image_id}" in esc
assert "a=T" in esc and "U=1" in esc
assert f"c={payload['cols']}" in esc and f"r={payload['rows']}" in esc
def test_kitty_payload_none_when_no_frames(tmp_path):
r = render.PetRenderer(str(tmp_path / "missing.webp"), mode="kitty")
assert r.kitty_payload("idle", cols=18, image_id=1) is None
def test_off_mode_and_missing_sheet_degrade(tmp_path):
# off mode never emits
r_off = render.PetRenderer(str(tmp_path / "nope.webp"), mode="off")

View File

@ -0,0 +1,117 @@
"""The base-CLI petdex pane: reactive half-block sprite above the prompt.
Mirrors the TUI's PetPane. The methods are tested in isolation via __new__ so
we don't pay the full HermesCLI.__init__ cost; a synthetic spritesheet exercises
the real engine decode + half-block fragment building.
"""
from __future__ import annotations
import threading
import pytest
from agent.pet import store
from agent.pet.constants import FRAME_H, FRAME_W
from agent.pet.render import PetRenderer
from cli import HermesCLI
@pytest.fixture
def boba_like(tmp_path, monkeypatch):
"""Install a synthetic pet into a temp HERMES_HOME and return its slug."""
from PIL import Image
home = tmp_path / ".hermes"
home.mkdir()
monkeypatch.setenv("HERMES_HOME", str(home))
cols, rows = 8, 9
sheet = Image.new("RGBA", (FRAME_W * cols, FRAME_H * rows), (0, 0, 0, 0))
for r in range(rows):
color = (20 + r * 25, 60, 120, 255)
for c in range(cols):
block = Image.new("RGBA", (FRAME_W, FRAME_H), color)
sheet.paste(block, (c * FRAME_W, r * FRAME_H))
pet_dir = store.pets_dir() / "boba"
pet_dir.mkdir(parents=True, exist_ok=True)
sheet.save(pet_dir / "spritesheet.webp")
(pet_dir / "pet.json").write_text(
'{"id":"boba","displayName":"Boba","description":"d","spritesheetPath":"spritesheet.webp"}'
)
return "boba"
def _make_cli():
cli_obj = HermesCLI.__new__(HermesCLI)
cli_obj._app = None
cli_obj._pet_lock = threading.Lock()
cli_obj._pet_enabled = False
cli_obj._pet_renderer = None
cli_obj._pet_slug = ""
cli_obj._pet_cols = 18
cli_obj._pet_scale = 0.7
cli_obj._pet_frames_cache = {}
cli_obj._pet_frame_idx = 0
cli_obj._agent_running = False
return cli_obj
def test_pet_state_tracks_agent_running():
cli_obj = _make_cli()
assert cli_obj._derive_pet_state() == "idle"
cli_obj._agent_running = True
assert cli_obj._derive_pet_state() == "run"
def test_pet_pane_collapsed_when_disabled():
# No renderer resolved → the window reports zero height and no fragments,
# so it's invisible for users without a pet.
cli_obj = _make_cli()
assert cli_obj._pet_widget_height() == 0
assert cli_obj._pet_fragments() == []
def test_pet_fragments_render_half_blocks(boba_like):
cli_obj = _make_cli()
cli_obj._pet_renderer = PetRenderer(
str(store.load_pet("boba").spritesheet), mode="unicode", scale=0.4, unicode_cols=14
)
cli_obj._pet_cols = 14
cli_obj._pet_enabled = True
height = cli_obj._pet_widget_height()
assert height > 0
frags = cli_obj._pet_fragments()
assert frags, "expected fragments for an enabled pet"
# Each fragment is a (style, text) pair; glyphs are half-blocks or blanks.
glyphs = {text for _, text in frags}
assert glyphs <= {"", "", " ", "\n"}
# Opaque cells carry a truecolor foreground style.
assert any(text == "" and "fg:#" in style for style, text in frags)
# Row count in the fragment stream matches the reported window height.
assert sum(1 for _, text in frags if text == "\n") == height - 1
def test_pet_resolve_config_enables_and_disables(boba_like):
from hermes_cli.config import load_config, save_config
cli_obj = _make_cli()
cfg = load_config()
cfg.setdefault("display", {}).setdefault("pet", {})
cfg["display"]["pet"].update({"enabled": True, "slug": "boba"})
save_config(cfg)
cli_obj._pet_resolve_config()
assert cli_obj._pet_enabled is True
assert cli_obj._pet_renderer is not None
assert cli_obj._pet_slug == "boba"
cfg["display"]["pet"]["enabled"] = False
save_config(cfg)
cli_obj._pet_resolve_config()
assert cli_obj._pet_enabled is False
assert cli_obj._pet_renderer is None

View File

@ -176,9 +176,11 @@ _LONG_HANDLERS = frozenset(
{
"browser.manage",
"cli.exec",
# Pet RPCs hit the network (manifest fetch / spritesheet download): inline
# they serialize on the reader thread, so picker previews trickle in one at
# a time. On the pool they fetch concurrently and stop blocking other RPCs.
# Pet RPCs hit the network (manifest fetch / spritesheet download) or do
# per-frame PNG decode/encode (pet.cells): inline they serialize on the
# reader thread, so picker previews trickle in one at a time and the
# animation poll stutters. On the pool they run concurrently.
"pet.cells",
"pet.gallery",
"pet.select",
"pet.thumb",
@ -4880,7 +4882,7 @@ def _(rid, params: dict) -> dict:
Fail-open: ``enabled=False`` on any problem.
"""
try:
from agent.pet import constants, store
from agent.pet import constants, render, store
from agent.pet.render import PetRenderer
try:
@ -4901,11 +4903,47 @@ def _(rid, params: dict) -> dict:
state = str(params.get("state") or constants.PetState.IDLE.value)
cols = int(params.get("cols") or pet_cfg.get("unicode_cols", 18) or 18)
scale = float(pet_cfg.get("scale", constants.DEFAULT_SCALE) or constants.DEFAULT_SCALE)
# Graphics path: when the TUI is attached to a real TTY (``graphics``)
# and the terminal speaks the kitty protocol, return a Unicode-
# placeholder payload for a crisp image instead of half-blocks. Env
# detection (KITTY_WINDOW_ID / TERM / TERM_PROGRAM) is shared with the
# Ink process since it spawns us; the dashboard PTY (xterm.js) has no
# such env, so it falls through to half-blocks automatically. Only
# kitty is grid-safe in Ink — iTerm/sixel stay on the fallback.
if params.get("graphics"):
configured = str(pet_cfg.get("render_mode", "auto") or "auto").lower()
gmode = render.detect_terminal_graphics() if configured in ("", "auto") else configured
if gmode == "kitty":
image_id = render.kitty_image_id(pet.slug)
payload = PetRenderer(
str(pet.spritesheet), mode="kitty", scale=scale, unicode_cols=cols
).kitty_payload(state, cols=cols, image_id=image_id)
if payload:
kcount = len(payload["frames"]) or 1
return _ok(
rid,
{
"enabled": True,
"slug": pet.slug,
"displayName": pet.display_name,
"state": state,
"graphics": "kitty",
"imageId": image_id,
"color": render.kitty_color_hex(image_id),
"cols": payload["cols"],
"rows": payload["rows"],
"placeholder": payload["placeholder"],
"frames": payload["frames"],
"frameMs": constants.LOOP_MS / max(1, kcount),
},
)
renderer = PetRenderer(
str(pet.spritesheet),
mode="unicode",
scale=float(pet_cfg.get("scale", constants.DEFAULT_SCALE) or constants.DEFAULT_SCALE),
scale=scale,
unicode_cols=cols,
)
count = renderer.frame_count(state) or 1

View File

@ -1,3 +1,4 @@
import { useStdout } from '@hermes/ink'
import { useCallback, useEffect, useRef, useState } from 'react'
import type { PetGrid } from '../components/petSprite.js'
@ -34,35 +35,69 @@ export function derivePetState({ busy, toolRunning, reasoning }: PetActivity): P
return 'idle'
}
// A kitty Unicode-placeholder frame set: a static placeholder grid (painted by
// Ink in the image-id color) plus per-frame transmit escapes written straight
// to the terminal out-of-band.
interface KittyView {
color: string
placeholder: string[]
}
interface PetCellsResult {
color?: string
enabled?: boolean
frameMs?: number
frames?: PetGrid[]
// unicode mode: cell grids; kitty mode: transmit-escape strings.
frames?: PetGrid[] | string[]
graphics?: string
imageId?: number
placeholder?: string[]
slug?: string
state?: string
}
type CacheEntry =
| { kind: 'cells'; frameMs: number; frames: PetGrid[] }
| { kind: 'kitty'; frameMs: number; frames: string[]; placeholder: string[]; color: string }
const FRAME_MS = 160
const POLL_MS = 2500
// Only the standalone TUI owns a real terminal it can splat image escapes into;
// when piped (or running under the dashboard PTY the gateway resolves to
// half-blocks anyway) we never ask for graphics.
const IS_TTY = Boolean(process.stdout?.isTTY)
export interface PetRender {
enabled: boolean
grid: PetGrid | null
kitty: KittyView | null
}
/**
* Drives the TUI pet: derives the live state from the turn/ui stores, fetches
* each (slug, state)'s half-block frames via the `pet.cells` RPC (cached), and
* animates the frame index. Returns the grid to paint, or null when no pet is
* enabled/installed.
* Drives the TUI pet. Fetches each (slug, state)'s frames via the `pet.cells`
* RPC (cached) and animates the frame index. Two render paths:
*
* A steady `pet.cells` poll keeps it reactive to config changes made elsewhere
* `/pet`, the picker, `hermes pets select` so adopting, switching, or
* disabling a pet takes effect live (no restart). The frame cache is keyed by
* slug so a switch re-pulls the new sprite instead of showing the old one.
* - **kitty** (Ghostty/kitty): the engine returns a static placeholder grid +
* per-frame transmit escapes. We paint the placeholder with Ink and write the
* current frame's escape to the terminal out-of-band, so the image animates
* underneath without Ink ever repainting.
* - **cells** (everywhere else): truecolor half-block grids painted by Ink.
*
* A steady poll keeps it reactive to config changes made elsewhere (`/pet`, the
* picker, `hermes pets select`) so adopting/switching/disabling takes effect
* live. The frame cache is keyed by `slug:state` so a switch re-pulls cleanly.
*/
export function usePet(): { enabled: boolean; grid: PetGrid | null } {
export function usePet(): PetRender {
const { rpc } = useGateway()
const { write } = useStdout()
const [enabled, setEnabled] = useState(false)
const [grid, setGrid] = useState<PetGrid | null>(null)
const [kitty, setKitty] = useState<KittyView | null>(null)
const cache = useRef<Map<string, { frameMs: number; frames: PetGrid[] }>>(new Map())
const cache = useRef<Map<string, CacheEntry>>(new Map())
const slugRef = useRef('')
const imageIdRef = useRef(0)
const stateRef = useRef<PetState>('idle')
const frameRef = useRef(0)
@ -97,22 +132,36 @@ export function usePet(): { enabled: boolean; grid: PetGrid | null } {
}
}, [])
// Free the terminal-side image when the pet goes away or the hook unmounts.
const releaseKitty = useCallback(() => {
if (imageIdRef.current) {
try {
write(`\x1b_Ga=d,d=i,i=${imageIdRef.current},q=2\x1b\\`)
} catch {
// best-effort cleanup
}
imageIdRef.current = 0
}
}, [write])
// Fetch + cache one (slug, state). `pet.cells` resolves the active pet from
// config, so its `slug`/`enabled` are the source of truth: a changed slug
// invalidates the cache, a disabled pet clears everything.
// config, so its `slug`/`enabled` are the source of truth.
const sync = useCallback(
async (state: PetState) => {
try {
const res = (await rpc('pet.cells', { state })) as PetCellsResult | null
const res = (await rpc('pet.cells', { graphics: IS_TTY, state })) as PetCellsResult | null
if (!res) {
return
}
if (!res.enabled) {
releaseKitty()
slugRef.current = ''
cache.current.clear()
setGrid(null)
setKitty(null)
setEnabled(false)
return
@ -121,13 +170,27 @@ export function usePet(): { enabled: boolean; grid: PetGrid | null } {
const slug = res.slug ?? ''
if (slug !== slugRef.current) {
releaseKitty()
slugRef.current = slug
cache.current.clear()
frameRef.current = 0
}
if (res.frames?.length) {
cache.current.set(`${slug}:${state}`, { frameMs: res.frameMs ?? FRAME_MS, frames: res.frames })
if (res.graphics === 'kitty' && res.frames?.length && res.placeholder?.length) {
imageIdRef.current = res.imageId ?? 0
cache.current.set(`${slug}:${state}`, {
color: res.color ?? '#000001',
frameMs: res.frameMs ?? FRAME_MS,
frames: res.frames as string[],
kind: 'kitty',
placeholder: res.placeholder
})
} else if (res.frames?.length) {
cache.current.set(`${slug}:${state}`, {
frameMs: res.frameMs ?? FRAME_MS,
frames: res.frames as PetGrid[],
kind: 'cells'
})
}
setEnabled(true)
@ -135,7 +198,7 @@ export function usePet(): { enabled: boolean; grid: PetGrid | null } {
// cosmetic — ignore RPC failures
}
},
[rpc]
[rpc, releaseKitty]
)
// Pull frames whenever the state changes (if not already cached for the
@ -150,6 +213,8 @@ export function usePet(): { enabled: boolean; grid: PetGrid | null } {
return () => clearInterval(timer)
}, [petState, sync])
useEffect(() => releaseKitty, [releaseKitty])
// Animation timer.
useEffect(() => {
if (!enabled) {
@ -164,15 +229,36 @@ export function usePet(): { enabled: boolean; grid: PetGrid | null } {
}
const idx = frameRef.current % entry.frames.length
setGrid(entry.frames[idx] ?? null)
frameRef.current = idx + 1
if (entry.kind === 'kitty') {
// Transmit this frame's image under the shared id; the static
// placeholder cells (set below) render it. No Ink repaint needed.
try {
write(entry.frames[idx] ?? '')
} catch {
// ignore transmit failures
}
setGrid(null)
setKitty(prev =>
prev && prev.color === entry.color && prev.placeholder === entry.placeholder
? prev
: { color: entry.color, placeholder: entry.placeholder }
)
return
}
setKitty(null)
setGrid(entry.frames[idx] ?? null)
}
tick()
const interval = setInterval(tick, FRAME_MS)
return () => clearInterval(interval)
}, [enabled, petState])
}, [enabled, petState, write])
return { enabled, grid }
return { enabled, grid, kitty }
}

View File

@ -26,7 +26,7 @@ import { Banner, Panel, SessionPanel } from './branding.js'
import { FpsOverlay } from './fpsOverlay.js'
import { HelpHint } from './helpHint.js'
import { MessageLine } from './messageLine.js'
import { PetSprite } from './petSprite.js'
import { PetKitty, PetSprite } from './petSprite.js'
import { QueuedMessages } from './queuedMessages.js'
import { LiveTodoPanel, StreamingAssistant } from './streamingAssistant.js'
import { TextInput, type TextInputMouseApi } from './textInput.js'
@ -35,15 +35,16 @@ import { TextInput, type TextInputMouseApi } from './textInput.js'
// nothing unless a pet is installed + enabled (`hermes pets select <slug>`),
// so it's a no-op for everyone else.
const PetPane = memo(function PetPane() {
const { enabled, grid } = usePet()
const { enabled, grid, kitty } = usePet()
if (!enabled || !grid) {
if (!enabled || (!grid && !kitty)) {
return null
}
return (
<NoSelect alignItems="flex-end" flexShrink={0} paddingX={1} width="100%">
<PetSprite grid={grid} />
<NoSelect flexShrink={0} justifyContent="flex-end" paddingX={1} width="100%">
{kitty ? <PetKitty color={kitty.color} placeholder={kitty.placeholder} /> : null}
{!kitty && grid ? <PetSprite grid={grid} /> : null}
</NoSelect>
)
})

View File

@ -6,7 +6,8 @@ import { memo } from 'react'
export type PetCell = number[]
export type PetGrid = PetCell[][]
const HALF_BLOCK = '▀'
const UPPER_HALF = '▀'
const LOWER_HALF = '▄'
const hex = (r: number, g: number, b: number) =>
`#${[r, g, b].map(v => Math.max(0, Math.min(255, v | 0)).toString(16).padStart(2, '0')).join('')}`
@ -27,12 +28,31 @@ export const PetSprite = memo(function PetSprite({ grid }: { grid: PetGrid }) {
<Box key={y}>
{row.map((cell, x) => {
const [tr, tg, tb, ta, br, bg, bb, ba] = cell
if ((ta ?? 0) < 32 && (ba ?? 0) < 32) {
const top = (ta ?? 0) >= 32
const bot = (ba ?? 0) >= 32
if (!top && !bot) {
return <Text key={x}> </Text>
}
return (
<Text backgroundColor={hex(br, bg, bb)} color={hex(tr, tg, tb)} key={x}>
{HALF_BLOCK}
// Both halves opaque → fg=top over bg=bottom. One half opaque →
// draw it fg-only so the other stays the terminal bg (no black
// boxes bleeding around transparent sprite edges).
if (top && bot) {
return (
<Text backgroundColor={hex(br, bg, bb)} color={hex(tr, tg, tb)} key={x}>
{UPPER_HALF}
</Text>
)
}
return top ? (
<Text color={hex(tr, tg, tb)} key={x}>
{UPPER_HALF}
</Text>
) : (
<Text color={hex(br, bg, bb)} key={x}>
{LOWER_HALF}
</Text>
)
})}
@ -41,3 +61,33 @@ export const PetSprite = memo(function PetSprite({ grid }: { grid: PetGrid }) {
</Box>
)
})
/**
* Renders a kitty Unicode-placeholder grid: each line is a row of U+10EEEE
* cells whose foreground color encodes the image id. The actual pixels are
* drawn by the terminal (the frame image is transmitted out-of-band by
* `usePet`); this only emits the placeholder text Ink can measure as width-1
* cells. Truecolor-only the color must reach the terminal verbatim for the
* id to decode, which Ghostty/kitty support.
*/
export const PetKitty = memo(function PetKitty({
color,
placeholder
}: {
color: string
placeholder: string[]
}) {
if (!placeholder.length) {
return null
}
return (
<Box flexDirection="column">
{placeholder.map((row, y) => (
<Text color={color} key={y}>
{row}
</Text>
))}
</Box>
)
})

View File

@ -156,7 +156,10 @@ declare module '@hermes/ink' {
readonly setSelectionBgColor: (color: string) => void
}
export function useHasSelection(): boolean
export function useStdout(): { readonly stdout?: NodeJS.WriteStream }
export function useStdout(): {
readonly stdout?: NodeJS.WriteStream
readonly write: (data: string) => boolean
}
export function useTerminalFocus(): boolean
export function useTerminalTitle(title: string | null): void
export function useDeclaredCursor(args: {