Magic keyword matching now treats sentence punctuation and quotes as prose boundaries while still rejecting casing changes, inflections, and path/file-extension occurrences.
Added regression coverage for detection and highlighting across ultrathink, orchestrate, and workflowz.
Fixes#4965
The whole-line editor decorate ran on `displayText` after the editor appended
the zero-width CURSOR_MARKER and cursor glyph; both start with ESC, so the
magic-keyword regex's right-boundary `(?!\S)` rejected `ultrathink` glued to
the marker and dropped the gradient until a trailing character was typed.
- `Editor.#decorate` (pi-tui) now splits around CURSOR_MARKER and decorates
each user-text segment independently, so word-boundary lookarounds resolve
correctly on both sides; the matching comment block is corrected.
- `KeywordHighlighter` / `highlightMagicKeywords` gain an optional `phase` in
[0, 1) that cyclically rotates the gradient stops. `0` (default) yields
the static palette, so sent-bubble rendering is unaffected.
- `CustomEditor.decorateText` derives `phase` from `Date.now()` and chains
`setTimeout(SHIMMER_FRAME_MS)` ticks while focused, the buffer holds a
magic keyword, and `magicKeywords.enabled` is on — the render itself
schedules the next frame, so losing focus, deleting the keyword, or
flipping the setting stops the animation on its own. `interactive-mode`
wires the repaint hook to `requestComponentRender(editor)` on construction
and after `setEditorComponent`.
- Adds `hasMagicKeyword(text)` (cheap prose-aware probe) and tests for the
seam fix, the phase cycle, the gating, and timer cleanup.
Fixes#2475
- Added markdown prose tests to verify maskNonProse preserves plain prose and masks fenced/tilde blocks.
- Added keyword-in-prose tests that enforced lowercase token matching and ignored code spans, fences, XML, and comments.
- Added highlight-mode tests ensuring only prose keywords are ANSI-highlighted and inline/fenced/XML regions stay unmodified.
- Added workflow/orchestrate assertions that uppercase or path-like forms remain unchanged while lowercase token boundaries are handled correctly.