feat(gui): Add auto-scroll, blinking history, and reactive API events

ai_client.py

@@ -1266,15 +1266,18 @@ def send(
             return _send_anthropic(md_content, user_message, base_dir, file_items, discussion_history)
         raise ValueError(f"unknown provider: {_provider}")
 
-def get_history_bleed_stats() -> dict:
+def get_history_bleed_stats(md_content: str | None = None) -> dict:
     """
     Calculates how close the current conversation history is to the token limit.
+    If md_content is provided and no chat session exists, it estimates based on md_content.
     """
     if _provider == "anthropic":
         # For Anthropic, we have a robust estimator
         with _anthropic_history_lock:
             history_snapshot = list(_anthropic_history)
         current_tokens = _estimate_prompt_tokens([], history_snapshot)
+        if md_content:
+            current_tokens += max(1, int(len(md_content) / _CHARS_PER_TOKEN))
         limit_tokens = _ANTHROPIC_MAX_PROMPT_TOKENS
         percentage = (current_tokens / limit_tokens) * 100 if limit_tokens > 0 else 0
         return {
@@ -1287,21 +1290,42 @@ def get_history_bleed_stats() -> dict:
         if _gemini_chat:
             try:
                 _ensure_gemini_client()
-                history = _get_gemini_history_list(_gemini_chat)
-                if history:
-                    resp = _gemini_client.models.count_tokens(
-                        model=_model,
-                        contents=history
-                    )
-                    current_tokens = resp.total_tokens
-                    limit_tokens = _GEMINI_MAX_INPUT_TOKENS
-                    percentage = (current_tokens / limit_tokens) * 100 if limit_tokens > 0 else 0
-                    return {
-                        "provider": "gemini",
-                        "limit": limit_tokens,
-                        "current": current_tokens,
-                        "percentage": percentage,
-                    }
+                history = list(_get_gemini_history_list(_gemini_chat))
+                if md_content:
+                    # Prepend context as a user part for counting
+                    history.insert(0, types.Content(role="user", parts=[types.Part.from_text(text=md_content)]))
+                
+                resp = _gemini_client.models.count_tokens(
+                    model=_model,
+                    contents=history
+                )
+                current_tokens = resp.total_tokens
+                limit_tokens = _GEMINI_MAX_INPUT_TOKENS
+                percentage = (current_tokens / limit_tokens) * 100 if limit_tokens > 0 else 0
+                return {
+                    "provider": "gemini",
+                    "limit": limit_tokens,
+                    "current": current_tokens,
+                    "percentage": percentage,
+                }
+            except Exception:
+                pass
+        elif md_content:
+            try:
+                _ensure_gemini_client()
+                resp = _gemini_client.models.count_tokens(
+                    model=_model,
+                    contents=[types.Content(role="user", parts=[types.Part.from_text(text=md_content)])]
+                )
+                current_tokens = resp.total_tokens
+                limit_tokens = _GEMINI_MAX_INPUT_TOKENS
+                percentage = (current_tokens / limit_tokens) * 100 if limit_tokens > 0 else 0
+                return {
+                    "provider": "gemini",
+                    "limit": limit_tokens,
+                    "current": current_tokens,
+                    "percentage": percentage,
+                }
             except Exception:
                 pass