feat: add theme management with light and dark modes

- Implemented a new composable `useTheme` for managing theme state.
- Added functions to read and write theme preference to local storage.
- Applied theme styles to the DOM based on user preference.
- Introduced a toggle function to switch between light and dark themes.

refactor: enhance copilot plugin functionality

- Improved request handling with sequence and document versioning.
- Refactored ghost text handling to improve clarity and efficiency.
- Updated markdown insertion logic to handle parsed content more robustly.
- Enhanced error handling and logging for better debugging.

style: update global styles for light and dark themes

- Defined CSS variables for light and dark themes to streamline styling.
- Improved overall styling consistency and responsiveness.
- Added transitions for smoother theme changes and interactions.

backend/prompt.py

@@ -1,9 +1,5 @@
 from typing import Tuple
 
-MAX_PREFIX_CHARS = 12000
-MAX_SUFFIX_CHARS = 4000
-
-
 def _sanitize_language_id(language_id: str) -> str:
     if not language_id:
         return "markdown"
@@ -18,12 +14,12 @@ def _sanitize_language_id(language_id: str) -> str:
 def _prepare_context(prefix: str, suffix: str) -> Tuple[str, str]:
     """
     Prepare prefix/suffix for model completion context.
-    Keep the historical one-char lookahead behavior to reduce boundary drift.
     """
-    if suffix:
-        prefix = prefix + suffix[0]
-        suffix = suffix[1:]
-    return prefix[-MAX_PREFIX_CHARS:], suffix[:MAX_SUFFIX_CHARS]
+    return prefix, suffix
+
+
+def prepare_prompt_context(prefix: str, suffix: str) -> Tuple[str, str]:
+    return _prepare_context(prefix, suffix)
 
 
 def build_prompt(prefix: str, suffix: str, language_id: str = "markdown") -> str:
@@ -50,8 +46,8 @@ Hard rules:
    Do NOT repeat text that already appears at the start of SUFFIX.
 3. Balanced length:
    Prefer concise but meaningful continuation, not ultra-short fragments.
-   Default target is 20-120 characters and 1-3 lines.
-   You may go shorter only when syntax requires it.
+   Default target is 20-120 characters and 1-3 lines for plain prose.
+   You may be longer when structure requires it (lists, tables, code blocks, math blocks).
 4. Avoid trivial output:
    Do not output only punctuation or filler such as ".", ",", ";", ":".
    Do not output just one token unless it is structurally necessary.
@@ -60,10 +56,12 @@ Hard rules:
 6. Markdown awareness:
    Continue active list/checkbox/ordered-list patterns when applicable.
    Preserve indentation in nested list/code contexts.
+   You may output full markdown structures when context needs them: headings, lists, tables, fenced code blocks, blockquotes, and LaTeX ($...$ / $$...$$).
    Close obvious unclosed inline markdown markers only when needed to bridge.
 7. Strict output format:
    Output insertion text only.
-   No explanations, labels, quotes, or code fences.
+   No explanations, labels, or wrapper quotes around the whole output.
+   Markdown syntax is allowed when it is the intended insertion (including fenced code blocks and LaTeX).
 
 Decision policy:
 - If PREFIX already connects naturally to SUFFIX, add a brief but useful continuation when possible.
@@ -91,3 +89,6 @@ Now produce the insertion.
 Output:"""
 
     return prompt.strip()
+
+
+