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/model_metadata.py

@@ -1439,79 +1439,9 @@ def estimate_tokens_rough(text: str) -> int:
 
 
 def estimate_messages_tokens_rough(messages: List[Dict[str, Any]]) -> int:
-    """Rough token estimate for a message list (pre-flight only).
-
-    Image parts (base64 PNG/JPEG) are counted as a flat ~1500 tokens per
-    image — the Anthropic pricing model — instead of counting raw base64
-    character length. Without this, a single ~1MB screenshot would be
-    estimated at ~250K tokens and trigger premature context compression.
-    """
-    _IMAGE_TOKEN_COST = 1500
-    total_chars = 0
-    image_tokens = 0
-    for msg in messages:
-        total_chars += _estimate_message_chars(msg)
-        image_tokens += _count_image_tokens(msg, _IMAGE_TOKEN_COST)
-    return ((total_chars + 3) // 4) + image_tokens
-
-
-def _count_image_tokens(msg: Dict[str, Any], cost_per_image: int) -> int:
-    """Count image-like content parts in a message; return their token cost."""
-    count = 0
-    content = msg.get("content") if isinstance(msg, dict) else None
-    if isinstance(content, list):
-        for part in content:
-            if not isinstance(part, dict):
-                continue
-            ptype = part.get("type")
-            if ptype in ("image", "image_url", "input_image"):
-                count += 1
-    stashed = msg.get("_anthropic_content_blocks") if isinstance(msg, dict) else None
-    if isinstance(stashed, list):
-        for part in stashed:
-            if isinstance(part, dict) and part.get("type") == "image":
-                count += 1
-    # Multimodal tool results that haven't been converted yet.
-    if isinstance(content, dict) and content.get("_multimodal"):
-        inner = content.get("content")
-        if isinstance(inner, list):
-            for part in inner:
-                if isinstance(part, dict) and part.get("type") in ("image", "image_url"):
-                    count += 1
-    return count * cost_per_image
-
-
-def _estimate_message_chars(msg: Dict[str, Any]) -> int:
-    """Char count for token estimation, excluding base64 image data.
-
-    Base64 images are counted via `_count_image_tokens` instead; including
-    their raw chars here would massively overestimate token usage.
-    """
-    if not isinstance(msg, dict):
-        return len(str(msg))
-    shadow: Dict[str, Any] = {}
-    for k, v in msg.items():
-        if k == "_anthropic_content_blocks":
-            continue
-        if k == "content":
-            if isinstance(v, list):
-                cleaned = []
-                for part in v:
-                    if isinstance(part, dict):
-                        if part.get("type") in ("image", "image_url", "input_image"):
-                            cleaned.append({"type": part.get("type"), "image": "[stripped]"})
-                        else:
-                            cleaned.append(part)
-                    else:
-                        cleaned.append(part)
-                shadow[k] = cleaned
-            elif isinstance(v, dict) and v.get("_multimodal"):
-                shadow[k] = v.get("text_summary", "")
-            else:
-                shadow[k] = v
-        else:
-            shadow[k] = v
-    return len(str(shadow))
+    """Rough token estimate for a message list (pre-flight only)."""
+    total_chars = sum(len(str(msg)) for msg in messages)
+    return (total_chars + 3) // 4
 
 
 def estimate_request_tokens_rough(
@@ -1525,14 +1455,13 @@ def estimate_request_tokens_rough(
     Includes the major payload buckets Hermes sends to providers:
     system prompt, conversation messages, and tool schemas.  With 50+
     tools enabled, schemas alone can add 20-30K tokens — a significant
-    blind spot when only counting messages. Image content is counted
-    at a flat per-image cost (see estimate_messages_tokens_rough).
+    blind spot when only counting messages.
     """
-    total = 0
+    total_chars = 0
     if system_prompt:
-        total += (len(system_prompt) + 3) // 4
+        total_chars += len(system_prompt)
     if messages:
-        total += estimate_messages_tokens_rough(messages)
+        total_chars += sum(len(str(msg)) for msg in messages)
     if tools:
-        total += (len(str(tools)) + 3) // 4
-    return total
+        total_chars += len(str(tools))
+    return (total_chars + 3) // 4