revert: computer-use cua-driver (PR #16919) (#16927)

Reverts PR #16919 (commits dad10a78d, 413ee1a28, b4a8031b2, afb958829)
which was merged prematurely. Restoring the pre-merge state so #14817
and #15328 can be revisited as standing PRs.

Reverted commits:
- afb958829 fix(computer-use): harden image-rejection fallback + AUTHOR_MAP
- b4a8031b2 fix(computer-use): unwrap _multimodal tool results
- 413ee1a28 feat(computer-use): background focus-safe backend
- dad10a78d feat(computer-use): cua-driver backend, universal any-model schema

Co-authored-by: teknium1 <teknium@users.noreply.github.com>

agent/context_compressor.py

@@ -148,31 +148,6 @@ def _append_text_to_content(content: Any, text: str, *, prepend: bool = False) -
     return text + rendered if prepend else rendered + text
 
 
-def _strip_image_parts_from_parts(parts: Any) -> Any:
-    """Strip image parts from an OpenAI-style content-parts list.
-
-    Returns a new list with image_url / image / input_image parts replaced
-    by a text placeholder, or None if the list had no images (callers
-    skip the replacement in that case). Used by the compressor to prune
-    old computer_use screenshots.
-    """
-    if not isinstance(parts, list):
-        return None
-    had_image = False
-    out = []
-    for part in parts:
-        if not isinstance(part, dict):
-            out.append(part)
-            continue
-        ptype = part.get("type")
-        if ptype in ("image", "image_url", "input_image"):
-            had_image = True
-            out.append({"type": "text", "text": "[screenshot removed to save context]"})
-        else:
-            out.append(part)
-    return out if had_image else None
-
-
 def _truncate_tool_call_args_json(args: str, head_chars: int = 200) -> str:
     """Shrink long string values inside a tool-call arguments JSON blob while
     preserving JSON validity.
@@ -591,11 +566,9 @@ class ContextCompressor(ContextEngine):
             if msg.get("role") != "tool":
                 continue
             content = msg.get("content") or ""
-            # Multimodal content — dedupe by the text summary if available.
+            # Skip multimodal content (list of content blocks)
             if isinstance(content, list):
                 continue
-            if isinstance(content, dict) and content.get("_multimodal"):
-                continue
             if len(content) < 200:
                 continue
             h = hashlib.md5(content.encode("utf-8", errors="replace")).hexdigest()[:12]
@@ -612,20 +585,8 @@ class ContextCompressor(ContextEngine):
             if msg.get("role") != "tool":
                 continue
             content = msg.get("content", "")
-            # Multimodal content (base64 screenshots etc.): strip the image
-            # payload — keep a lightweight text placeholder in its place.
-            # Without this, an old computer_use screenshot (~1MB base64 +
-            # ~1500 real tokens) survives every compression pass forever.
+            # Skip multimodal content (list of content blocks)
             if isinstance(content, list):
-                stripped = _strip_image_parts_from_parts(content)
-                if stripped is not None:
-                    result[i] = {**msg, "content": stripped}
-                    pruned += 1
-                continue
-            if isinstance(content, dict) and content.get("_multimodal"):
-                summary = content.get("text_summary") or "[screenshot removed to save context]"
-                result[i] = {**msg, "content": f"[screenshot removed] {summary[:200]}"}
-                pruned += 1
                 continue
             if not content or content == _PRUNED_TOOL_PLACEHOLDER:
                 continue