From 64dc6b91b0ddd0cb80051b586597545fe2c79dd5 Mon Sep 17 00:00:00 2001
From: ethernet <arilotter@gmail.com>
Date: Fri, 26 Jun 2026 14:57:23 -0400
Subject: [PATCH] fix(pet): detect terminals more broadly

incl. windows terminal and ghostty
---
 agent/pet/render.py   | 45 +-------------------------
 agent/pet/terminal.py | 74 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+), 44 deletions(-)
 create mode 100644 agent/pet/terminal.py

diff --git a/agent/pet/render.py b/agent/pet/render.py
index 1618c0751d2..b4b9a3cd0a5 100644
--- a/agent/pet/render.py
+++ b/agent/pet/render.py
@@ -17,6 +17,7 @@ empty string rather than raising.
 """
 
 from __future__ import annotations
+from agent.pet.terminal import detect_terminal_graphics
 
 import base64
 import io
@@ -45,50 +46,6 @@ RENDER_MODES = ("auto", "kitty", "iterm", "sixel", "unicode", "off")
 # Terminal capability detection
 # ─────────────────────────────────────────────────────────────────────────
 
-def detect_terminal_graphics() -> str:
-    """Best-effort detection of the richest graphics protocol available.
-
-    Env-based (non-blocking — we never issue a DA1/terminal query that could
-    hang a pipe).  Returns one of ``kitty`` / ``iterm`` / ``sixel`` /
-    ``unicode``.  Conservative: unknown terminals get ``unicode``, which works
-    anywhere with truecolor.
-    """
-    term = os.environ.get("TERM", "").lower()
-    term_program = os.environ.get("TERM_PROGRAM", "").lower()
-
-    # The VS Code / Cursor integrated terminal sets TERM_PROGRAM=vscode
-    # authoritatively but does NOT scrub the terminal env vars it inherits when
-    # launched from another emulator (ITERM_SESSION_ID, KITTY_WINDOW_ID, …).
-    # Trusting those leaks emits an image protocol the embedded xterm.js can't
-    # display — you get a blank frame. Inline images there are opt-in
-    # (terminal.integrated.enableImages), so default to half-blocks, which
-    # always render in its truecolor grid. Users who enabled images can pin
-    # display.pet.render_mode explicitly.
-    if term_program == "vscode":
-        return "unicode"
-
-    # kitty graphics protocol
-    if os.environ.get("KITTY_WINDOW_ID") or "kitty" in term or "ghostty" in term:
-        return "kitty"
-    if term_program in {"ghostty"}:
-        return "kitty"
-
-    # WezTerm speaks both kitty and iterm; prefer kitty (richer placement).
-    if term_program == "wezterm" or os.environ.get("WEZTERM_PANE"):
-        return "kitty"
-
-    # iTerm2 inline images
-    if term_program == "iterm.app" or os.environ.get("ITERM_SESSION_ID"):
-        return "iterm"
-
-    # sixel-capable terminals (env heuristics only)
-    if term_program in {"mintty"} or "foot" in term or "mlterm" in term:
-        return "sixel"
-    if "sixel" in term:
-        return "sixel"
-
-    return "unicode"
-
 
 def resolve_mode(configured: str | None, *, stream=None) -> str:
     """Resolve the effective render mode from config + the environment.
diff --git a/agent/pet/terminal.py b/agent/pet/terminal.py
new file mode 100644
index 00000000000..71cea4ea844
--- /dev/null
+++ b/agent/pet/terminal.py
@@ -0,0 +1,74 @@
+from __future__ import annotations
+import os
+from dataclasses import dataclass, field
+
+
+RENDER_MODES = ("auto", "kitty", "iterm", "sixel", "unicode", "off")
+
+@dataclass(frozen=True)
+class TerminalProfile:
+    """Declarative description of a terminal's detection fingerprint."""
+    mode: str  # one of RENDER_MODES
+    # Any of these env vars being set (non-empty) is a match
+    env_vars: tuple[str, ...] = ()
+    # $TERM_PROGRAM must equal one of these (case-insensitive)
+    term_program_vals: tuple[str, ...] = ()
+    # Any of these strings appearing in $TERM is a match
+    term_substrings: tuple[str, ...] = ()
+
+    def matches(self) -> bool:
+        if any(os.environ.get(v) for v in self.env_vars):
+            return True
+        tp = os.environ.get("TERM_PROGRAM", "").lower()
+        if tp and tp in self.term_program_vals:
+            return True
+        term = os.environ.get("TERM", "").lower()
+        if any(s in term for s in self.term_substrings):
+            return True
+        return False
+
+
+# ── Registry (priority order — first match wins) ───────────────────────────
+#
+# VS Code / Cursor override comes first: their embedded xterm.js leaks
+# KITTY_WINDOW_ID / ITERM_SESSION_ID from the parent shell, so we must
+# short-circuit before any of the real-graphics entries.
+#
+_TERMINAL_PROFILES: tuple[TerminalProfile, ...] = (
+    TerminalProfile(
+        mode="unicode",
+        term_program_vals=("vscode",),
+    ),
+
+    TerminalProfile(
+        mode="kitty",
+        env_vars=("KITTY_WINDOW_ID","GHOSTTY_RESOURCES_DIR","WEZTERM_PANE",),
+        term_program_vals=("kitty", "ghostty",),
+        term_substrings=("kitty","ghostty","wezterm", ),
+    ),
+    TerminalProfile(
+        mode="iterm",
+        env_vars=("ITERM_SESSION_ID",),
+        term_program_vals=("iterm.app",),
+    ),
+    TerminalProfile(
+        mode="sixel",
+        env_vars=("WT_SESSION",),
+        term_substrings=("mlterm","contour","sixel",),
+        term_program_vals=("mintty","foot","contour",),
+    ),
+)
+
+
+def detect_terminal_graphics() -> str:
+    """Return the richest graphics mode available in the current terminal.
+
+    Non-blocking — no DA1/terminal query is issued, as those can break pipes
+    in strange ways.
+    Walks ``_TERMINAL_PROFILES` in priority order; returns the first match's mode, or ``"unicode"`` as the
+    safe universal fallback.
+    """
+    for profile in _TERMINAL_PROFILES:
+        if profile.matches():
+            return profile.mode
+    return "unicode"
\ No newline at end of file