Normalize whitespace in grid get_process_output to save tokens

Grid snapshots pad every row to the full terminal width and leave the
bottom of the screen blank, so MCP grid reads carried a lot of dead
whitespace. Add normalizeGridText (CRLF/lone-CR to LF, right-trim each
line, collapse blank runs to a single blank, drop leading/trailing
blanks) and apply it to the grid branch of GetProcessOutput only.
Stream output, raw output, and WaitForPattern matching are untouched.

Resolves the terminal-read newline/token-waste TODO item.

CHANGELOG.md

@@ -10,6 +10,11 @@ loosely follows [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 - MCP clients can now call `scratchpad_delete` with a scratchpad name
   to remove a shared project scratchpad.
 
+### Changed
+- Grid-mode `get_process_output` now returns whitespace-normalized
+  text to avoid sending padded terminal rows and repeated blank lines
+  over MCP.
+
 ### Fixed
 - Closing an agent now escalates from SIGTERM to SIGKILL when needed,
   so agents that ignore SIGTERM disappear from the running tab bar

TODO.md

@@ -1,4 +1,3 @@
-- [ ] We should deduplicate /r/n newlines or /n newlines to save tokens on mcp responses for terminal reads.
 - [ ] Codex idle detection seems to trigger too soon, see below [CODEX IDLE]
 - [ ] Issue with mcp timing out [MCP TIMEOUT]
 - [ ] When opening a codex sub agent, the message gets input to the field, but the message is never submitted.

internal/app/host.go

@@ -7,6 +7,7 @@ import (
 	"sync"
 	"syscall"
 	"time"
+	"unicode"
 
 	"github.com/hjbdev/patterm/internal/mcp"
 	"github.com/hjbdev/patterm/internal/preset"
@@ -398,7 +399,7 @@ func (h *toolHost) GetProcessOutput(callerID, processID, mode string, sinceOffse
 		if c.Kind == KindAgent {
 			txt = applyChromeTrim(txt, h.chromeHintsFor(c.PresetRef))
 		}
-		out.Content = txt
+		out.Content = normalizeGridText(txt)
 		return out, nil
 	case "stream":
 		b, end := c.StreamRead(sinceOffset)
@@ -1018,6 +1019,30 @@ func stripANSI(s string) string {
 	return ansiRegexp.ReplaceAllString(s, "")
 }
 
+func normalizeGridText(s string) string {
+	s = strings.ReplaceAll(s, "\r\n", "\n")
+	s = strings.ReplaceAll(s, "\r", "\n")
+
+	lines := strings.Split(s, "\n")
+	out := make([]string, 0, len(lines))
+	pendingBlank := false
+	for _, line := range lines {
+		line = strings.TrimRightFunc(line, unicode.IsSpace)
+		if line == "" {
+			if len(out) > 0 {
+				pendingBlank = true
+			}
+			continue
+		}
+		if pendingBlank {
+			out = append(out, "")
+			pendingBlank = false
+		}
+		out = append(out, line)
+	}
+	return strings.Join(out, "\n")
+}
+
 // stripANSIBytes is the byte-slice form of stripANSI. Skips the
 // string conversion and the regex DFA — useful when the caller will
 // itself walk the result line-by-line (SearchOutput) or feed it to a

internal/app/ring_test.go

@@ -104,3 +104,44 @@ func TestStripANSIBytesEquivalence(t *testing.T) {
 		}
 	}
 }
+
+func TestNormalizeGridText(t *testing.T) {
+	cases := []struct {
+		name string
+		in   string
+		want string
+	}{
+		{
+			name: "line endings",
+			in:   "one\r\ntwo\rthree",
+			want: "one\ntwo\nthree",
+		},
+		{
+			name: "trailing whitespace",
+			in:   "one   \ntwo\t\t\nthree",
+			want: "one\ntwo\nthree",
+		},
+		{
+			name: "collapse blank runs",
+			in:   "one\n\n\n two\n \n\t\nthree",
+			want: "one\n\n two\n\nthree",
+		},
+		{
+			name: "trim leading and trailing blanks",
+			in:   "\n \n\t\none\n\n",
+			want: "one",
+		},
+		{
+			name: "already clean",
+			in:   "one\n\ntwo\nthree",
+			want: "one\n\ntwo\nthree",
+		},
+	}
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			if got := normalizeGridText(tc.in); got != tc.want {
+				t.Fatalf("normalizeGridText(%q) = %q, want %q", tc.in, got, tc.want)
+			}
+		})
+	}
+}