v3.11.5: token-aware compaction, vision filter, universal adaptive compaction, smart-continue text detection

CHANGELOG.md

@@ -1,5 +1,29 @@
 # Changelog
 
+## v3.11.5 (2026-05-26)
+
+**Vision Filter, Token-Aware Compaction, Universal Adaptive Compaction, Smart-Continue Text Detection**
+
+### Critical Fixes
+
+- **Token-aware compaction for small-context models (FIX)**: `_crof_compact_for_retry()` had an early return at `len(input_data) <= limit` (item count) — if you had 25 items × 1600 tokens = 40K tokens, it skipped compaction entirely because 25 < 30 (the default item limit). Now also checks estimated token count vs learned model max, and compacts when either item count OR token count exceeds limits. Fixes repeated `context_length_exceeded` errors on models like 0G-GLM-5.1 (~35K token context).
+- **Proactive compaction now token-aware**: Previously only triggered when item count > 30. Now also triggers when estimated tokens exceed 80% of the model's learned token limit, even if item count is below the threshold. Prevents the first-request failure pattern on small-context models.
+- **Compaction aggression threshold**: Changed `est > max_tok` to `est >= max_tok * 0.9` to avoid edge case where estimated tokens exactly equal the limit and compaction is skipped.
+- **Removed all `crof.ai` gates from adaptive compaction**: Proactive compaction, `finish_reason=length` retry, `_crof_record`, and compaction logging were gated behind `"crof.ai" in TARGET_URL`. These gates prevented OpenAdapter and other providers from getting proactive/retry compaction, causing repeated `context_length_exceeded` failures. Now applies universally to ALL providers.
+
+### New Features
+
+- **Vision model detection + image stripping**: `_strip_images_from_input()` and `_model_supports_vision()` detect vision capability by model name pattern. Non-vision models (deepseek, glm, mixtral, llama, command, dbrx, qwen, phi-3) have `input_image`/`image_url` parts stripped and replaced with `[User attached image: filename — this model does not support vision]` text notice. Vision models (gpt-4o, gemini, claude, qwen-vl, glm-5v) keep images intact. Applied in 3 paths: main request, context_length_exceeded retry, smart-continue nudge.
+- **Token estimation and per-model limit learning**: `_estimate_tokens()`, `_estimate_input_tokens()`, `_get_model_max_tokens()`, `_set_model_max_tokens()`. Extracts `~N tokens` from `context_length_exceeded` error messages and stores per-model token limits. Used by proactive compaction and retry compaction to adjust `keep` count dynamically.
+- **Compaction aggression levels**: `_crof_compact_for_retry()` accepts `aggression` parameter (0=normal, 1=extreme). Extreme mode kicks in when estimated tokens > 1.5× the learned limit or on 2nd+ retry attempt. Reduces `keep` count to minimum, ensuring the compacted request fits within model limits.
+- **Smart-continue text-tool detection**: Removed hard requirement for `has_function_call_output(input_data)`. Added `_TOOL_CALL_TEXT_PATTERNS` and `_text_looks_like_tool_calls()` to trigger nudging when model outputs text matching tool-call patterns (e.g., `• (exec_command cmd ...)`, `write_to_file`, `exec_command`) even without prior `function_call_output` in context. Essential for models like 0G-GLM-5.1 that never emit real `function_call_output` items.
+- **Parenthesized tool call regex**: `_PAREN_TC_RE` pattern to match `• (name args...)` format from non-vision models that output tool calls as parenthesized text.
+
+### GUI Fixes
+
+- **Active endpoint sync**: Added `set_active_endpoint()` and `validate_active_endpoint()` to Linux GTK GUI. Syncs `.active-endpoint.json` with `config.toml` on every launch; auto-removes stale references to deleted providers. Fixed `"Error loading configuration: No such file or directory (os error 2)"` crash when active endpoint referenced a deleted provider.
+- **Config state**: `~/.codex/.active-endpoint.json` and `config.toml` model catalog path validated and auto-corrected on GUI startup.
+
 ## v3.11.0 (2026-05-26)
 
 **Cobra PR Merge + Smart Continuation + API Key Hot-Reload**

README.md

@@ -130,6 +130,10 @@ A three-component system:
 - **Response store TTL** — evicts stored responses older than 10 minutes, prevents memory leaks
 - **Bounded stream buffers** — 8MB cap prevents OOM on pathological responses
 - **Dual logging** — all proxy messages written to both stderr and `~/.cache/codex-proxy/proxy.log`
+- **Vision model detection** (v3.11.5) — automatically strips images for non-vision models (DeepSeek, GLM, Qwen, etc.) and replaces with text notice; vision-capable models (GPT-4o, Gemini, Claude, Qwen-VL) keep images intact
+- **Token-aware compaction** (v3.11.5) — learns per-model token limits from `context_length_exceeded` errors; proactively compacts when estimated tokens exceed 80% of limit; prevents repeated context overflow on small-context models (~35K tokens)
+- **Universal adaptive compaction** (v3.11.5) — compaction now works for ALL providers (was Crof.ai-only); proactive + retry compaction with aggression levels (normal/extreme)
+- **Smart-continue text detection** (v3.11.5) — triggers continuation nudging when model outputs text matching tool-call patterns, essential for text-only models that never emit real `function_call_output` items
 - Zero dependencies — pure Python stdlib
 
 ### Command Code Adapter

install.sh

@@ -3,13 +3,13 @@ set -e
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
 
-if [ -f "$SCRIPT_DIR/codex-launcher_3.11.0_all.deb" ]; then
-    echo "Installing codex-launcher_3.11.0_all.deb ..."
-    sudo dpkg -i "$SCRIPT_DIR/codex-launcher_3.11.0_all.deb"
+if [ -f "$SCRIPT_DIR/codex-launcher_3.11.5_all.deb" ]; then
+    echo "Installing codex-launcher_3.11.5_all.deb ..."
+    sudo dpkg -i "$SCRIPT_DIR/codex-launcher_3.11.5_all.deb"
 else
-    echo "WARNING: codex-launcher_3.11.0_all.deb not found; copying files manually."
+    echo "WARNING: codex-launcher_3.11.5_all.deb not found; copying files manually."
 fi
-echo "Installed v3.11.0 via .deb package."
+echo "Installed v3.11.5 via .deb package."
     echo "  translate-proxy.py   -> /usr/bin/translate-proxy.py"
     echo "  codex-launcher-gui   -> /usr/bin/codex-launcher-gui"
     echo "  cleanup-codex-stale  -> /usr/bin/cleanup-codex-stale.sh"

src/codex-launcher-gui

@@ -20,12 +20,22 @@ BGP_POOLS_FILE = HOME / ".codex/bgp-pools.json"
 LOG_DIR = HOME / ".cache/codex-desktop"
 LAUNCH_LOG = LOG_DIR / "launcher.log"
 PROXY_CONFIG_DIR = HOME / ".cache/codex-proxy"
+ACTIVE_ENDPOINT_FILE = HOME / ".codex/.active-endpoint.json"
 DEFAULT_CONFIG = """model = ""
 model_provider = ""
 model_catalog_json = ""
 """
 
 CHANGELOG = [
+    ("3.11.5", "2026-05-26", [
+        "Token-aware compaction: fixes context_length_exceeded on small-context models",
+        "Proactive compaction triggers on token count, not just item count",
+        "Universal adaptive compaction for all providers (removed crof.ai gates)",
+        "Vision model detection + image stripping for non-vision models",
+        "Per-model token limit learning from error messages",
+        "Smart-continue text-tool detection for text-only models",
+        "Active endpoint sync: auto-removes stale references on startup",
+    ]),
     ("3.11.0", "2026-05-26", [
         "Merge cobra PR: concurrency semaphore (max 3), auto-continue for truncated text",
         "SO_REUSEADDR on sticky port, proxy-stderr.log, stream diagnostics logging",
@@ -33,7 +43,7 @@ CHANGELOG = [
         "Restart Proxy button: only restarts proxy without killing Codex Desktop",
         "Tool call argument normalizer: fixes Arguments→arguments, strips markdown wrapping",
         "Smart-continue loop (2× retries): escalating nudges when model stops text-only mid-task",
-        "XML tool call extraction: parses <tool_call> patterns from text, injects as real calls",
+        "XML tool call extraction: parses <name> patterns from text, injects as real calls",
         "Auto-continue + smart-continue ordered with skip guard to avoid double-firing",
         "API key hot-reload with mtime tracking + /admin/reload + /admin/verify-key endpoints",
         "GUI hot-reload: auto-refreshes proxy key on endpoint edit, verifies with upstream",
@@ -923,6 +933,27 @@ def restore_config():
         shutil.copy2(str(CONFIG_BAK), str(tmp))
         os.replace(str(tmp), str(CONFIG))
 
+def set_active_endpoint(name):
+    ACTIVE_ENDPOINT_FILE.parent.mkdir(parents=True, exist_ok=True)
+    write_secure_text(ACTIVE_ENDPOINT_FILE, json.dumps({"active": name}, indent=2))
+
+def validate_active_endpoint(logfn=None):
+    if not ACTIVE_ENDPOINT_FILE.exists():
+        return
+    try:
+        d = json.loads(ACTIVE_ENDPOINT_FILE.read_text())
+        active = d.get("active", "")
+        if not active:
+            return
+        eps = load_endpoints()
+        names = {ep.get("name", "") for ep in eps}
+        if active not in names:
+            ACTIVE_ENDPOINT_FILE.unlink()
+            if logfn:
+                logfn(f"Removed stale active-endpoint '{active}' (provider no longer exists)")
+    except Exception:
+        pass
+
 def write_secure_text(path, text):
     path.parent.mkdir(parents=True, exist_ok=True)
     tmp = path.with_suffix(path.suffix + ".tmp")
@@ -1862,6 +1893,7 @@ class LauncherWin(Gtk.Window):
         self._proc = None
         self._endpoints_data = load_endpoints()
         recover_config_if_needed()
+        validate_active_endpoint()
 
         vbox = Gtk.Box(orientation=Gtk.Orientation.VERTICAL, spacing=8)
         self.add(vbox)
@@ -2607,6 +2639,8 @@ class LauncherWin(Gtk.Window):
                 begin_config_transaction(f"launch:{ep['name']}")
                 write_config_for_native(ep, model)
 
+            set_active_endpoint(ep["name"])
+
             if target == "desktop":
                 if needs_proxy:
                     _kill_existing_desktop(self.log)
@@ -2664,6 +2698,7 @@ class LauncherWin(Gtk.Window):
 
             begin_config_transaction(f"launch:bgp:{pool['name']}")
             write_config_for_translated(bgp_ep, model, port)
+            set_active_endpoint(pool["name"])
 
             if target == "desktop":
                 _kill_existing_desktop(self.log)

src/codex_launcher_lib.py

@@ -83,14 +83,24 @@ model_catalog_json = ""
 """
 
 CHANGELOG = [
+    ("3.11.5", "2026-05-26", [
+        "Token-aware compaction: fixes context_length_exceeded on small-context models (25 items × 1600 tokens)",
+        "Proactive compaction triggers on token count (>80% model limit), not just item count",
+        "Universal adaptive compaction: removed crof.ai-only gates, all providers get compaction",
+        "Vision model detection: strips images for non-vision models, keeps for vision-capable ones",
+        "Per-model token limit learning from context_length_exceeded error messages",
+        "Compaction aggression levels: normal vs extreme when tokens > 1.5× model limit",
+        "Smart-continue text-tool detection: triggers on tool-call text patterns, not just function_call_output",
+        "Active endpoint sync: GUI auto-removes stale endpoint references on startup",
+    ]),
     ("3.11.0", "2026-05-26", [
         "Merge cobra PR: concurrency semaphore (max 3), auto-continue for truncated text",
         "SO_REUSEADDR on sticky port, proxy-stderr.log, stream diagnostics logging",
         "Timeout/OSError handler sends response.failed SSE instead of silent drop",
         "Restart Proxy button: only restarts proxy without killing Codex Desktop",
-        "Tool call argument normalizer: fixes Arguments→arguments, strips markdown wrapping",
-        "Smart-continue loop (2× retries): escalating nudges when model stops text-only mid-task",
-        "XML tool call extraction: parses <tool_call> patterns from text, injects as real calls",
+        "Tool call argument normalizer: fixes Arguments->arguments, strips markdown wrapping",
+        "Smart-continue loop (2x retries): escalating nudges when model stops text-only mid-task",
+        "XML tool call extraction: parses patterns from text, injects as real calls",
         "Auto-continue + smart-continue ordered with skip guard to avoid double-firing",
         "API key hot-reload with mtime tracking + /admin/reload + /admin/verify-key endpoints",
         "GUI hot-reload: auto-refreshes proxy key on endpoint edit, verifies with upstream",

src/translate-proxy.py

@@ -787,6 +787,10 @@ _GEMINI_AGENT_GUARDRAIL = (
 )
 
 _LOG_FILE_LOCK = threading.Lock()
+_ANTIGRAVITY_LOOP_TRACKER = {}
+_ANTIGRAVITY_LOOP_TRACKER_LOCK = threading.Lock()
+def _antigravity_loop_key(session_id):
+    return f"ag:{session_id}"
 
 def _fetch_antigravity_version():
     cache_path = os.path.join(os.path.expanduser("~"), ".cache", "codex-proxy", "antigravity-version.json")
@@ -1469,6 +1473,53 @@ _CROF_ADAPTIVE = {
     "min_keep_recent": 6,
 }
 
+_model_max_tokens = {}
+_model_max_tokens_lock = threading.Lock()
+
+def _estimate_tokens(item):
+    if not isinstance(item, dict):
+        return 4
+    t = item.get("type", "")
+    if t == "message":
+        content = item.get("content", "")
+        if isinstance(content, str):
+            return max(4, len(content) // 4)
+        elif isinstance(content, list):
+            total = 4
+            for part in content:
+                pt = part.get("type", "")
+                if pt in ("input_text", "output_text"):
+                    total += max(4, len(part.get("text", "")) // 4)
+                elif pt == "input_image":
+                    total += 800
+                elif pt in ("function_call",):
+                    total += max(20, len(part.get("arguments", "{}")) // 2)
+                elif pt == "function_call_output":
+                    total += max(8, len(part.get("output", "")) // 4)
+            return total
+    elif t in ("function_call_output",):
+        return max(8, len(item.get("output", "")) // 4)
+    elif t == "function_call":
+        return max(20, len(item.get("arguments", "{}")) // 2)
+    return 4
+
+def _estimate_input_tokens(input_data):
+    if not isinstance(input_data, list):
+        return 0
+    return sum(_estimate_tokens(i) for i in input_data)
+
+def _get_model_max_tokens(model):
+    with _model_max_tokens_lock:
+        return _model_max_tokens.get(model)
+
+def _set_model_max_tokens(model, tokens):
+    if model and tokens:
+        with _model_max_tokens_lock:
+            existing = _model_max_tokens.get(model)
+            if existing is None or tokens < existing:
+                _model_max_tokens[model] = tokens
+                print(f"[ctx-limit] learned {model} max ~{tokens} tokens", file=sys.stderr)
+
 _BGP_STATS_PATH = os.path.join(_LOG_DIR, "bgp-route-stats.json")
 _bgp_stats_lock = threading.Lock()
 
@@ -1534,8 +1585,6 @@ def _sorted_bgp_routes():
     return sorted(BGP_ROUTES, key=lambda r: _score_route(r, stats))
 
 def _crof_record(model, n_items, success):
-    if TARGET_URL and "crof.ai" not in TARGET_URL:
-        return
     if not isinstance(n_items, int) or n_items < 1:
         return
     entry = {"model": model, "items": n_items, "ok": success}
@@ -1561,7 +1610,6 @@ def _crof_record(model, n_items, success):
             global_limit = v["limit"]
     _CROF_ADAPTIVE["global_item_limit"] = global_limit
 
-    if TARGET_URL and "crof.ai" in TARGET_URL:
     print(f"[crof-adaptive] model={model} items={n_items} {'OK' if success else 'FAIL'} -> limit={ml.get('limit',30)} global={global_limit}", file=sys.stderr)
 
 def _crof_item_limit(model):
@@ -1569,12 +1617,29 @@ def _crof_item_limit(model):
     per_model = ml.get("limit", 30)
     return min(per_model, _CROF_ADAPTIVE["global_item_limit"])
 
-def _crof_compact_for_retry(input_data, model):
+def _crof_compact_for_retry(input_data, model, aggression=0):
     limit = _crof_item_limit(model)
-    if not isinstance(input_data, list) or len(input_data) <= limit:
+    if not isinstance(input_data, list) or len(input_data) < 2:
+        return input_data
+
+    max_tok = _get_model_max_tokens(model)
+    est = _estimate_input_tokens(input_data)
+    over_item_limit = len(input_data) > limit
+    over_token_limit = max_tok and est >= max_tok * 0.9
+
+    if not over_item_limit and not over_token_limit:
         return input_data
 
     keep = max(_CROF_ADAPTIVE["min_keep_recent"], limit // 3)
+    if over_token_limit:
+        ratio = est / max_tok
+        if aggression >= 1 or ratio > 1.5:
+            keep = max(2, _CROF_ADAPTIVE["min_keep_recent"] // 2)
+        elif ratio > 1.2:
+            keep = max(3, keep // 2)
+        print(f"[ctx-limit] model={model} est={est}tok max={max_tok}tok ratio={ratio:.2f} -> keep={keep}", file=sys.stderr)
+    elif over_item_limit:
+        keep = max(keep, 6)
     head_end = 0
     for i, item in enumerate(input_data):
         t = item.get("type")
@@ -1607,8 +1672,7 @@ def _crof_compact_for_retry(input_data, model):
         summary_lines.append(_item_summary(item, max_len=120))
 
     summary_msg = {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "\n".join(summary_lines)}]}
-    if TARGET_URL and "crof.ai" in TARGET_URL:
-        print(f"[crof-adaptive] RETRY compact: {len(input_data)} -> {len(head)+1+len(tail)} (limit={limit}, keep={len(tail)})", file=sys.stderr)
+    print(f"[crof-adaptive] RETRY compact: {len(input_data)} -> {len(head)+1+len(tail)} (limit={limit}, keep={len(tail)}, agg={aggression})", file=sys.stderr)
     return head + [summary_msg] + tail
 
 def _item_summary(item, max_len=200):
@@ -2051,6 +2115,18 @@ def synthesize_tool_results_for_chat(input_items):
 def has_function_call_output(input_items):
     return isinstance(input_items, list) and any(i.get("type") == "function_call_output" for i in input_items)
 
+_TOOL_CALL_TEXT_PATTERNS = re.compile(
+    r'(?:^|\n)[\s•\-\*]*\(?'
+    r'(?:exec_command|write_to_file|exec_bash|bash|run_command|shell|edit_file|read_file|search_files|list_files)'
+    r'[\s:]',
+    re.I | re.MULTILINE
+)
+
+def _text_looks_like_tool_calls(text):
+    if not text or len(text) < 6:
+        return False
+    return bool(_TOOL_CALL_TEXT_PATTERNS.search(text))
+
 # ═══════════════════════════════════════════════════════════════════
 # Log redaction
 # ═══════════════════════════════════════════════════════════════════
@@ -2233,9 +2309,14 @@ def _normalize_tool_args(raw_args):
     except json.JSONDecodeError:
         return raw_args
 
-_XML_TC_RE = re.compile(r'<tool_call>(\w+)(.*?)</tool_call>', re.DOTALL)
+_XML_TC_RE = re.compile(r'exec_command(.*?)</invoke>', re.DOTALL)
 _XML_ARG_VALUE_RE = re.compile(r'</?arg_value>\s*')
 
+_PAREN_TC_RE = re.compile(
+    r'(?:^|[\n•\-\*]\s*)\(\s*(exec_command|write_to_file|exec_bash|bash|run_command|shell|edit_file|read_file|search_files|list_files)\b\s*(.*?)\)',
+    re.DOTALL | re.I
+)
+
 def _extract_xml_tool_calls(text):
     if not text:
         return []
@@ -2262,6 +2343,68 @@ def _extract_xml_tool_calls(text):
         results.append({"name": name, "args": args_str, "call_id": f"xml_{len(results)}"})
     return results
 
+_NON_VISION_MODEL_PATTERNS = re.compile(
+    r'\b(deepseek|glm|mixtral|llama\b(?!.*vision)|command|dbrx|qwen\b(?!.*vl)|phi-?3(?!.*vision))',
+    re.I
+)
+
+_vision_fail_cache = set()
+_vision_fail_lock = threading.Lock()
+
+def _model_supports_vision(model):
+    if not model:
+        return True
+    with _vision_fail_lock:
+        if model in _vision_fail_cache:
+            return False
+    if _NON_VISION_MODEL_PATTERNS.search(model):
+        return False
+    return True
+
+def _mark_vision_fail(model):
+    if model:
+        with _vision_fail_lock:
+            _vision_fail_cache.add(model)
+
+def _strip_images_from_input(input_data, model):
+    if not isinstance(input_data, list) or _model_supports_vision(model):
+        return input_data
+    modified = False
+    result = []
+    for item in input_data:
+        if item.get("type") != "message":
+            result.append(item)
+            continue
+        content = item.get("content", [])
+        if isinstance(content, str):
+            result.append(item)
+            continue
+        new_content = []
+        has_img = False
+        for part in content:
+            if isinstance(part, str):
+                new_content.append(part)
+                continue
+            pt = part.get("type", "")
+            if pt in ("input_image", "image_url"):
+                if not has_img:
+                    fname = part.get("image_url", {}).get("url", part.get("url", "image.png"))
+                    if fname.startswith("data:"):
+                        fname = "screenshot.png"
+                    new_content.append({"type": "output_text", "text": f"[User attached image: {fname} — this model does not support vision]"})
+                    has_img = True
+                    modified = True
+            else:
+                new_content.append(part)
+        if modified:
+            result.append({**item, "content": new_content})
+        else:
+            result.append(item)
+    if modified:
+        print(f"[vision-filter] stripped {sum(1 for i in input_data if i.get('type')=='message' and any(c.get('type') in ('input_image','image_url') for c in (i.get('content') or []) if isinstance(c,dict)))} images for model={model}", file=sys.stderr)
+        return result
+    return input_data
+
 def oa_input_to_messages(input_data):
     msgs = []
     tool_name_by_id = {}
@@ -4889,13 +5032,26 @@ class Handler(http.server.BaseHTTPRequestHandler):
             body["input"] = input_data
 
         crof_limit = _crof_item_limit(model)
-        _crof_eligible = TARGET_URL and "crof.ai" in TARGET_URL
-        if _crof_eligible and not compacted and isinstance(input_data, list) and len(input_data) > crof_limit:
-            print(f"[crof-adaptive] proactive compact: {len(input_data)} items > limit {crof_limit}", file=sys.stderr)
-            input_data = _crof_compact_for_retry(input_data, model)
+        _crof_eligible = True
+        if _crof_eligible and not compacted and isinstance(input_data, list):
+            _needs_compact = len(input_data) > crof_limit
+            max_tok = _get_model_max_tokens(model)
+            est_tok = _estimate_input_tokens(input_data) if max_tok else 0
+            if not _needs_compact and max_tok and est_tok > max_tok * 0.8:
+                _needs_compact = True
+            if _needs_compact:
+                _agg = 0
+                if max_tok and est_tok > max_tok:
+                    _agg = 1
+                print(f"[crof-adaptive] proactive compact: {len(input_data)} items, est={est_tok}tok max={max_tok}tok agg={_agg}", file=sys.stderr)
+                input_data = _crof_compact_for_retry(input_data, model, aggression=_agg)
                 body = dict(body)
                 body["input"] = input_data
 
+        # Strip images for non-vision models
+        input_data = _strip_images_from_input(input_data, model)
+        body["input"] = input_data
+
         messages = oa_input_to_messages(input_data)
         messages = _inject_stored_reasoning(messages)
         instructions = body.get("instructions", "").strip()
@@ -4927,14 +5083,19 @@ class Handler(http.server.BaseHTTPRequestHandler):
                 except urllib.error.HTTPError as e:
                     err_body = e.read().decode()
                     if "context_length_exceeded" in err_body and attempt < max_retries:
-                        print(f"[{self._session_id}] context_length_exceeded (attempt {attempt+1}/{max_retries}), retrying with extreme compaction!", file=sys.stderr)
+                        import re as _re
+                        _tok_m = _re.search(r'~?(\d+)\s*tokens', err_body)
+                        if _tok_m:
+                            _set_model_max_tokens(model, int(_tok_m.group(1)))
+                        print(f"[{self._session_id}] context_length_exceeded (attempt {attempt+1}/{max_retries}), retrying with compaction (agg={attempt})!", file=sys.stderr)
                         policy = provider_policy()
                         if isinstance(input_data, list):
-                            print(f"[{self._session_id}] applying extreme compaction to {len(input_data)} items", file=sys.stderr)
-                            input_data = _crof_compact_for_retry(input_data, model)
+                            est = _estimate_input_tokens(input_data)
+                            print(f"[{self._session_id}] applying compaction to {len(input_data)} items ~{est}tok", file=sys.stderr)
+                            input_data = _crof_compact_for_retry(input_data, model, aggression=attempt)
                             body = dict(body)
                             body["input"] = input_data
-                            messages = oa_input_to_messages(input_data)
+                            messages = oa_input_to_messages(_strip_images_from_input(input_data, model))
                             messages = _inject_stored_reasoning(messages)
                             instructions = body.get("instructions", "").strip()
                             if instructions:
@@ -5267,22 +5428,26 @@ class Handler(http.server.BaseHTTPRequestHandler):
             if not is_latest_simple:
                 contents.insert(0, {"role": "user", "parts": [{"text": _GEMINI_AGENT_GUARDRAIL}]})
 
-        if OAUTH_PROVIDER == "google-antigravity" and isinstance(input_data, list):
-            _EDIT_WORDS = ("change", "fix", "update", "redesign", "rewrite", "modify", "improve", "replace", "edit", "make it", "add", "remove", "delete", "rename", "move", "convert")
-            latest_lower = ""
-            for item in reversed(input_data):
-                if item.get("type") == "message" and item.get("role") == "user":
-                    c = item.get("content", "")
-                    if isinstance(c, str): latest_lower = c.lower()
-                    elif isinstance(c, list): latest_lower = " ".join(p.get("text", p.get("input_text", "")) for p in c if isinstance(p, dict)).lower()
-                    break
-            if latest_lower and any(w in latest_lower for w in _EDIT_WORDS):
-                n_tool_calls = sum(1 for it in input_data if isinstance(it, dict) and it.get("type") == "function_call")
-                contents.append({"role": "user", "parts": [{"text": "!!! ABSOLUTELY NO PLANNING - EMIT THE TOOL CALL NOW !!! IMPORTANT: The user is requesting a modification to existing files. You MUST use tools (exec_command, read_files, write, etc.) to make the changes RIGHT NOW. Do NOT just describe what to do — actually CALL THE TOOLS IN THIS RESPONSE. IMMEDIATELY INSPECT THE FILE OR LIST FILES USING exec_command TOOL CALL."}]})
-                print(f"[antigravity] edit-intent detected; injected tool-use nudge", file=sys.stderr)
+        if OAUTH_PROVIDER == "google-antigravity":
+            import hashlib
+            ag_key = _antigravity_loop_key(self._session_id)
+            with _ANTIGRAVITY_LOOP_TRACKER_LOCK:
+                if ag_key not in _ANTIGRAVITY_LOOP_TRACKER:
+                    _ANTIGRAVITY_LOOP_TRACKER[ag_key] = {
+                        "latest_user_hash": None,
+                        "nudge_injected": False,
+                        "latest_user_appended": False,
+                        "tool_calls_for_request": 0,
+                        "repeated_tool": False,
+                        "force_finalize": False,
+                        "last_tool": None,
+                        "last_tool_count": 0,
+                    }
+                ag_state = _ANTIGRAVITY_LOOP_TRACKER[ag_key]
 
-        if OAUTH_PROVIDER == "google-antigravity" and isinstance(input_data, list):
             latest_user = ""
+            latest_user_hash = None
+            if isinstance(input_data, list):
                 for item in reversed(input_data):
                     if item.get("type") == "message" and item.get("role") == "user":
                         c = item.get("content", "")
@@ -5292,6 +5457,59 @@ class Handler(http.server.BaseHTTPRequestHandler):
                             latest_user = "\n".join(p.get("text", p.get("input_text", "")) for p in c if isinstance(p, dict))
                         break
                 if latest_user:
+                    latest_norm = " ".join(latest_user.strip().split())[:200]
+                    latest_user_hash = hashlib.sha256(latest_norm.encode()).hexdigest()[:16]
+                    if latest_user_hash != ag_state["latest_user_hash"]:
+                        ag_state["latest_user_hash"] = latest_user_hash
+                        ag_state["nudge_injected"] = False
+                        ag_state["latest_user_appended"] = False
+                        ag_state["tool_calls_for_request"] = 0
+                        ag_state["repeated_tool"] = False
+                        ag_state["force_finalize"] = False
+                        ag_state["last_tool"] = None
+                        ag_state["last_tool_count"] = 0
+
+            if isinstance(input_data, list):
+                n_tool_calls = sum(1 for it in input_data if isinstance(it, dict) and it.get("type") == "function_call")
+                ag_state["tool_calls_for_request"] = n_tool_calls
+                last_tool_key = None
+                for item in reversed(input_data):
+                    if isinstance(item, dict) and item.get("type") == "function_call":
+                        fname = item.get("name", "")
+                        args_str = json.dumps(item.get("arguments", {}), sort_keys=True)[:100]
+                        last_tool_key = f"{fname}:{args_str}"
+                        break
+                if last_tool_key:
+                    if last_tool_key == ag_state["last_tool"]:
+                        ag_state["last_tool_count"] += 1
+                        if ag_state["last_tool_count"] >= 5:
+                            ag_state["repeated_tool"] = True
+                            ag_state["force_finalize"] = True
+                    else:
+                        ag_state["last_tool"] = last_tool_key
+                        ag_state["last_tool_count"] = 1
+
+            _EDIT_WORDS = ("change", "fix", "update", "redesign", "rewrite", "modify", "improve", "replace", "edit", "make it", "add", "remove", "delete", "rename", "move", "convert")
+            latest_lower = ""
+            if isinstance(input_data, list):
+                for item in reversed(input_data):
+                    if item.get("type") == "message" and item.get("role") == "user":
+                        c = item.get("content", "")
+                        if isinstance(c, str): latest_lower = c.lower()
+                        elif isinstance(c, list): latest_lower = " ".join(p.get("text", p.get("input_text", "")) for p in c if isinstance(p, dict)).lower()
+                        break
+
+            if ag_state["force_finalize"]:
+                contents.append({"role": "user", "parts": [{"text": "STOP CALLING TOOLS. APPLY THE FINAL EDIT OR SUMMARIZE WHAT BLOCKED YOU. DO NOT CALL ANY MORE TOOLS. DO NOT PRODUCE ANY MORE PLANNING TEXT. DO NOT PRODUCE ANY MORE EXPLORATORY TOOL CALLS. PRODUCE A FINAL ANSWER OR A CLEAR STATEMENT OF WHAT IS PREVENTING YOU FROM COMPLETING THE TASK."}]})
+            elif latest_lower and any(w in latest_lower for w in _EDIT_WORDS) and not ag_state["nudge_injected"] and not ag_state["force_finalize"]:
+                contents.append({"role": "user", "parts": [{"text": "!!! ABSOLUTELY NO PLANNING - EMIT THE TOOL CALL NOW !!! IMPORTANT: The user is requesting a modification to existing files. You MUST use tools (exec_command, read_files, write, etc.) to make the changes RIGHT NOW. Do NOT just describe what to do — actually CALL THE TOOLS IN THIS RESPONSE. IMMEDIATELY INSPECT THE FILE OR LIST FILES USING exec_command TOOL CALL."}]})
+                ag_state["nudge_injected"] = True
+                print(f"[antigravity] edit-intent detected; injected tool-use nudge (first time for this request)", file=sys.stderr)
+            else:
+                if ag_state["nudge_injected"]:
+                    print(f"[antigravity] edit-intent nudge already injected, skipping", file=sys.stderr)
+
+            if latest_user and not ag_state["latest_user_appended"] and not ag_state["force_finalize"]:
                 latest_norm = " ".join(latest_user.strip().split())[:160]
                 final_text = ""
                 if contents:
@@ -5299,10 +5517,20 @@ class Handler(http.server.BaseHTTPRequestHandler):
                     if last.get("role") == "user":
                         final_text = " ".join(json.dumps(last.get("parts", []), ensure_ascii=False).split())
                 if latest_norm[:120] not in final_text:
-                    print(f"[antigravity] latest user instruction was not final turn; appending", file=sys.stderr)
+                    print(f"[antigravity] latest user instruction was not final turn; appending (first time for this request)", file=sys.stderr)
                     contents.append({"role": "user", "parts": [{"text": latest_user}]})
+                    ag_state["latest_user_appended"] = True
                 else:
                     print(f"[antigravity] latest user instruction is final turn", file=sys.stderr)
+            else:
+                if ag_state["latest_user_appended"]:
+                    print(f"[antigravity] latest user instruction already appended, skipping", file=sys.stderr)
+
+            print(f"[antigravity-loop] latest_user_hash={latest_user_hash}", file=sys.stderr)
+            print(f"[antigravity-loop] tool_calls_for_request={ag_state['tool_calls_for_request']}", file=sys.stderr)
+            print(f"[antigravity-loop] repeated_tool={ag_state['repeated_tool']}", file=sys.stderr)
+            print(f"[antigravity-loop] nudge_injected={ag_state['nudge_injected']}", file=sys.stderr)
+            print(f"[antigravity-loop] force_finalize={ag_state['force_finalize']}", file=sys.stderr)
             print(f"[{self._session_id}] [antigravity-debug] input_items={len(input_data) if isinstance(input_data, list) else 1} contents={len(contents)} latest={latest_user[:80]!r}", file=sys.stderr)
             if contents:
                 last_c = contents[-1]
@@ -5725,9 +5953,11 @@ class Handler(http.server.BaseHTTPRequestHandler):
             last_status = None
             finish_reason = None
             has_content = False
+            has_message = False
+            has_tool_call = False
 
             def _observe_event(event):
-                nonlocal last_resp_id, last_output, last_status, finish_reason, has_content
+                nonlocal last_resp_id, last_output, last_status, finish_reason, has_content, has_message, has_tool_call
                 for line in event.strip().split("\n"):
                     if line.startswith("data: "):
                         try:
@@ -5737,7 +5967,9 @@ class Handler(http.server.BaseHTTPRequestHandler):
                                 last_output = d.get("response", {}).get("output", [])
                                 last_status = d.get("response", {}).get("status")
                                 finish_reason = "length" if last_status == "incomplete" else "stop"
-                                has_content = any(o.get("type") == "message" for o in (last_output or []))
+                                has_tool_call = any(o.get("type") == "function_call" for o in (last_output or []))
+                                has_message = any(o.get("type") == "message" for o in (last_output or []))
+                                has_content = has_message or has_tool_call
                         except Exception:
                             pass
 
@@ -5749,7 +5981,7 @@ class Handler(http.server.BaseHTTPRequestHandler):
                         break
                     collected_events.append(event)
                     _observe_event(event)
-                print(f"[{self._session_id}] stream ended: events={len(collected_events)} finish={finish_reason} has_content={has_content} elapsed={time.time()-t0:.1f}s", file=sys.stderr)
+                print(f"[{self._session_id}] stream ended: events={len(collected_events)} finish={finish_reason} has_content={has_content} has_message={has_message} has_tool_call={has_tool_call} elapsed={time.time()-t0:.1f}s", file=sys.stderr)
             except (ConnectionResetError, BrokenPipeError, ConnectionAbortedError):
                 print("[translate-proxy] client disconnected during stream", file=sys.stderr)
                 _crof_record(model, n_items, False)
@@ -5805,6 +6037,8 @@ class Handler(http.server.BaseHTTPRequestHandler):
                         last_resp_id = last_output = last_status = None
                         finish_reason = None
                         has_content = False
+                        has_message = False
+                        has_tool_call = False
                         for event in oa_stream_to_sse(retry_upstream, model, body.get("request_id") or body.get("id")):
                             collected_events.append(event)
                             _observe_event(event)
@@ -5813,7 +6047,7 @@ class Handler(http.server.BaseHTTPRequestHandler):
                         print(f"[provider-sensor] synthetic retry failed: {e}", file=sys.stderr)
 
             # Auto-retry on finish_reason=length with no content due to too much context.
-            if finish_reason == "length" and not has_content and isinstance(input_data, list) and len(input_data) > 5 and TARGET_URL and "crof.ai" in TARGET_URL:
+            if finish_reason == "length" and not has_content and isinstance(input_data, list) and len(input_data) > 5:
                 print(f"[crof-adaptive] RETRY: finish_reason=length with no content, compacting {n_items} items", file=sys.stderr)
                 new_input = _crof_compact_for_retry(input_data, model)
                 if len(new_input) < len(input_data):
@@ -5836,6 +6070,8 @@ class Handler(http.server.BaseHTTPRequestHandler):
                         last_resp_id = last_output = last_status = None
                         finish_reason = None
                         has_content = False
+                        has_message = False
+                        has_tool_call = False
                         for event in oa_stream_to_sse(retry_upstream, model, body.get("request_id") or body.get("id")):
                             collected_events.append(event)
                             _observe_event(event)
@@ -5943,9 +6179,17 @@ class Handler(http.server.BaseHTTPRequestHandler):
                 _smart_attempt = 0
                 while _smart_attempt < _smart_max:
                     _has_tool_calls_in_output = any(o.get("type") == "function_call" for o in (last_output or []))
+                    last_text = ""
+                    for o in (last_output or []):
+                        if o.get("type") == "message":
+                            for c in (o.get("content") or []):
+                                if isinstance(c, dict) and c.get("type") == "output_text":
+                                    last_text += c.get("text", "")
+                    _looks_like_tools = _text_looks_like_tool_calls(last_text)
+                    _has_prior_tool_ctx = has_function_call_output(input_data)
                     if not (finish_reason == "stop" and has_content and not _has_tool_calls_in_output
                             and isinstance(input_data, list) and len(input_data) >= 3
-                            and has_function_call_output(input_data)):
+                            and (_has_prior_tool_ctx or _looks_like_tools)):
                         break
                     _smart_attempt += 1
                     _nudges = [
@@ -5954,12 +6198,6 @@ class Handler(http.server.BaseHTTPRequestHandler):
                     ]
                     nudge_text = _nudges[min(_smart_attempt - 1, len(_nudges) - 1)]
                     # Try extracting XML tool calls from text as fallback before nudging
-                    last_text = ""
-                    for o in (last_output or []):
-                        if o.get("type") == "message":
-                            for c in (o.get("content") or []):
-                                if isinstance(c, dict) and c.get("type") == "output_text":
-                                    last_text += c.get("text", "")
                     xml_fc = _extract_xml_tool_calls(last_text)
                     if xml_fc:
                         print(f"[{self._session_id}] [smart-continue] extracted {len(xml_fc)} XML tool calls from text, injecting and retrying", file=sys.stderr)
@@ -5979,6 +6217,8 @@ class Handler(http.server.BaseHTTPRequestHandler):
                             last_resp_id = last_output = last_status = None
                             finish_reason = None
                             has_content = False
+                            has_message = False
+                            has_tool_call = False
                             for event in oa_stream_to_sse(retry_upstream, model, body.get("request_id") or body.get("id")):
                                 collected_events.append(event)
                                 _observe_event(event)
@@ -5988,19 +6228,21 @@ class Handler(http.server.BaseHTTPRequestHandler):
                             print(f"[{self._session_id}] [smart-continue] XML injection retry failed: {e}", file=sys.stderr)
                             break
                     _nudge_msg = {"role": "user", "content": nudge_text}
-                    nudge_messages = oa_input_to_messages(input_data) + [_nudge_msg]
+                    nudge_messages = oa_input_to_messages(_strip_images_from_input(input_data, model)) + [_nudge_msg]
                     instructions = body.get("instructions", "").strip()
                     if instructions:
                         nudge_messages.insert(0, {"role": "system", "content": instructions})
                     nudge_chat_body = self._build_chat_body(model, nudge_messages, body, stream)
                     nudge_req = urllib.request.Request(target, data=json.dumps(nudge_chat_body).encode(), headers=fwd)
-                    print(f"[{self._session_id}] [smart-continue] attempt {_smart_attempt}/{_smart_max}: model stopped mid-task, nudging", file=sys.stderr)
+                    print(f"[{self._session_id}] [smart-continue] attempt {_smart_attempt}/{_smart_max}: model stopped mid-task (prior_ctx={_has_prior_tool_ctx} text_tools={_looks_like_tools}), nudging", file=sys.stderr)
                     try:
                         retry_upstream = urllib.request.urlopen(nudge_req, timeout=_upstream_timeout(body, True))
                         collected_events = []
                         last_resp_id = last_output = last_status = None
                         finish_reason = None
                         has_content = False
+                        has_message = False
+                        has_tool_call = False
                         for event in oa_stream_to_sse(retry_upstream, model, body.get("request_id") or body.get("id")):
                             collected_events.append(event)
                             _observe_event(event)

translate-proxy.py

@@ -787,6 +787,10 @@ _GEMINI_AGENT_GUARDRAIL = (
 )
 
 _LOG_FILE_LOCK = threading.Lock()
+_ANTIGRAVITY_LOOP_TRACKER = {}
+_ANTIGRAVITY_LOOP_TRACKER_LOCK = threading.Lock()
+def _antigravity_loop_key(session_id):
+    return f"ag:{session_id}"
 
 def _fetch_antigravity_version():
     cache_path = os.path.join(os.path.expanduser("~"), ".cache", "codex-proxy", "antigravity-version.json")
@@ -1469,6 +1473,53 @@ _CROF_ADAPTIVE = {
     "min_keep_recent": 6,
 }
 
+_model_max_tokens = {}
+_model_max_tokens_lock = threading.Lock()
+
+def _estimate_tokens(item):
+    if not isinstance(item, dict):
+        return 4
+    t = item.get("type", "")
+    if t == "message":
+        content = item.get("content", "")
+        if isinstance(content, str):
+            return max(4, len(content) // 4)
+        elif isinstance(content, list):
+            total = 4
+            for part in content:
+                pt = part.get("type", "")
+                if pt in ("input_text", "output_text"):
+                    total += max(4, len(part.get("text", "")) // 4)
+                elif pt == "input_image":
+                    total += 800
+                elif pt in ("function_call",):
+                    total += max(20, len(part.get("arguments", "{}")) // 2)
+                elif pt == "function_call_output":
+                    total += max(8, len(part.get("output", "")) // 4)
+            return total
+    elif t in ("function_call_output",):
+        return max(8, len(item.get("output", "")) // 4)
+    elif t == "function_call":
+        return max(20, len(item.get("arguments", "{}")) // 2)
+    return 4
+
+def _estimate_input_tokens(input_data):
+    if not isinstance(input_data, list):
+        return 0
+    return sum(_estimate_tokens(i) for i in input_data)
+
+def _get_model_max_tokens(model):
+    with _model_max_tokens_lock:
+        return _model_max_tokens.get(model)
+
+def _set_model_max_tokens(model, tokens):
+    if model and tokens:
+        with _model_max_tokens_lock:
+            existing = _model_max_tokens.get(model)
+            if existing is None or tokens < existing:
+                _model_max_tokens[model] = tokens
+                print(f"[ctx-limit] learned {model} max ~{tokens} tokens", file=sys.stderr)
+
 _BGP_STATS_PATH = os.path.join(_LOG_DIR, "bgp-route-stats.json")
 _bgp_stats_lock = threading.Lock()
 
@@ -1534,8 +1585,6 @@ def _sorted_bgp_routes():
     return sorted(BGP_ROUTES, key=lambda r: _score_route(r, stats))
 
 def _crof_record(model, n_items, success):
-    if TARGET_URL and "crof.ai" not in TARGET_URL:
-        return
     if not isinstance(n_items, int) or n_items < 1:
         return
     entry = {"model": model, "items": n_items, "ok": success}
@@ -1561,7 +1610,6 @@ def _crof_record(model, n_items, success):
             global_limit = v["limit"]
     _CROF_ADAPTIVE["global_item_limit"] = global_limit
 
-    if TARGET_URL and "crof.ai" in TARGET_URL:
     print(f"[crof-adaptive] model={model} items={n_items} {'OK' if success else 'FAIL'} -> limit={ml.get('limit',30)} global={global_limit}", file=sys.stderr)
 
 def _crof_item_limit(model):
@@ -1569,12 +1617,29 @@ def _crof_item_limit(model):
     per_model = ml.get("limit", 30)
     return min(per_model, _CROF_ADAPTIVE["global_item_limit"])
 
-def _crof_compact_for_retry(input_data, model):
+def _crof_compact_for_retry(input_data, model, aggression=0):
     limit = _crof_item_limit(model)
-    if not isinstance(input_data, list) or len(input_data) <= limit:
+    if not isinstance(input_data, list) or len(input_data) < 2:
+        return input_data
+
+    max_tok = _get_model_max_tokens(model)
+    est = _estimate_input_tokens(input_data)
+    over_item_limit = len(input_data) > limit
+    over_token_limit = max_tok and est >= max_tok * 0.9
+
+    if not over_item_limit and not over_token_limit:
         return input_data
 
     keep = max(_CROF_ADAPTIVE["min_keep_recent"], limit // 3)
+    if over_token_limit:
+        ratio = est / max_tok
+        if aggression >= 1 or ratio > 1.5:
+            keep = max(2, _CROF_ADAPTIVE["min_keep_recent"] // 2)
+        elif ratio > 1.2:
+            keep = max(3, keep // 2)
+        print(f"[ctx-limit] model={model} est={est}tok max={max_tok}tok ratio={ratio:.2f} -> keep={keep}", file=sys.stderr)
+    elif over_item_limit:
+        keep = max(keep, 6)
     head_end = 0
     for i, item in enumerate(input_data):
         t = item.get("type")
@@ -1607,8 +1672,7 @@ def _crof_compact_for_retry(input_data, model):
         summary_lines.append(_item_summary(item, max_len=120))
 
     summary_msg = {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "\n".join(summary_lines)}]}
-    if TARGET_URL and "crof.ai" in TARGET_URL:
-        print(f"[crof-adaptive] RETRY compact: {len(input_data)} -> {len(head)+1+len(tail)} (limit={limit}, keep={len(tail)})", file=sys.stderr)
+    print(f"[crof-adaptive] RETRY compact: {len(input_data)} -> {len(head)+1+len(tail)} (limit={limit}, keep={len(tail)}, agg={aggression})", file=sys.stderr)
     return head + [summary_msg] + tail
 
 def _item_summary(item, max_len=200):
@@ -2051,6 +2115,18 @@ def synthesize_tool_results_for_chat(input_items):
 def has_function_call_output(input_items):
     return isinstance(input_items, list) and any(i.get("type") == "function_call_output" for i in input_items)
 
+_TOOL_CALL_TEXT_PATTERNS = re.compile(
+    r'(?:^|\n)[\s•\-\*]*\(?'
+    r'(?:exec_command|write_to_file|exec_bash|bash|run_command|shell|edit_file|read_file|search_files|list_files)'
+    r'[\s:]',
+    re.I | re.MULTILINE
+)
+
+def _text_looks_like_tool_calls(text):
+    if not text or len(text) < 6:
+        return False
+    return bool(_TOOL_CALL_TEXT_PATTERNS.search(text))
+
 # ═══════════════════════════════════════════════════════════════════
 # Log redaction
 # ═══════════════════════════════════════════════════════════════════
@@ -2233,9 +2309,14 @@ def _normalize_tool_args(raw_args):
     except json.JSONDecodeError:
         return raw_args
 
-_XML_TC_RE = re.compile(r'<tool_call>(\w+)(.*?)</tool_call>', re.DOTALL)
+_XML_TC_RE = re.compile(r'exec_command(.*?)</invoke>', re.DOTALL)
 _XML_ARG_VALUE_RE = re.compile(r'</?arg_value>\s*')
 
+_PAREN_TC_RE = re.compile(
+    r'(?:^|[\n•\-\*]\s*)\(\s*(exec_command|write_to_file|exec_bash|bash|run_command|shell|edit_file|read_file|search_files|list_files)\b\s*(.*?)\)',
+    re.DOTALL | re.I
+)
+
 def _extract_xml_tool_calls(text):
     if not text:
         return []
@@ -2262,6 +2343,68 @@ def _extract_xml_tool_calls(text):
         results.append({"name": name, "args": args_str, "call_id": f"xml_{len(results)}"})
     return results
 
+_NON_VISION_MODEL_PATTERNS = re.compile(
+    r'\b(deepseek|glm|mixtral|llama\b(?!.*vision)|command|dbrx|qwen\b(?!.*vl)|phi-?3(?!.*vision))',
+    re.I
+)
+
+_vision_fail_cache = set()
+_vision_fail_lock = threading.Lock()
+
+def _model_supports_vision(model):
+    if not model:
+        return True
+    with _vision_fail_lock:
+        if model in _vision_fail_cache:
+            return False
+    if _NON_VISION_MODEL_PATTERNS.search(model):
+        return False
+    return True
+
+def _mark_vision_fail(model):
+    if model:
+        with _vision_fail_lock:
+            _vision_fail_cache.add(model)
+
+def _strip_images_from_input(input_data, model):
+    if not isinstance(input_data, list) or _model_supports_vision(model):
+        return input_data
+    modified = False
+    result = []
+    for item in input_data:
+        if item.get("type") != "message":
+            result.append(item)
+            continue
+        content = item.get("content", [])
+        if isinstance(content, str):
+            result.append(item)
+            continue
+        new_content = []
+        has_img = False
+        for part in content:
+            if isinstance(part, str):
+                new_content.append(part)
+                continue
+            pt = part.get("type", "")
+            if pt in ("input_image", "image_url"):
+                if not has_img:
+                    fname = part.get("image_url", {}).get("url", part.get("url", "image.png"))
+                    if fname.startswith("data:"):
+                        fname = "screenshot.png"
+                    new_content.append({"type": "output_text", "text": f"[User attached image: {fname} — this model does not support vision]"})
+                    has_img = True
+                    modified = True
+            else:
+                new_content.append(part)
+        if modified:
+            result.append({**item, "content": new_content})
+        else:
+            result.append(item)
+    if modified:
+        print(f"[vision-filter] stripped {sum(1 for i in input_data if i.get('type')=='message' and any(c.get('type') in ('input_image','image_url') for c in (i.get('content') or []) if isinstance(c,dict)))} images for model={model}", file=sys.stderr)
+        return result
+    return input_data
+
 def oa_input_to_messages(input_data):
     msgs = []
     tool_name_by_id = {}
@@ -4889,13 +5032,26 @@ class Handler(http.server.BaseHTTPRequestHandler):
             body["input"] = input_data
 
         crof_limit = _crof_item_limit(model)
-        _crof_eligible = TARGET_URL and "crof.ai" in TARGET_URL
-        if _crof_eligible and not compacted and isinstance(input_data, list) and len(input_data) > crof_limit:
-            print(f"[crof-adaptive] proactive compact: {len(input_data)} items > limit {crof_limit}", file=sys.stderr)
-            input_data = _crof_compact_for_retry(input_data, model)
+        _crof_eligible = True
+        if _crof_eligible and not compacted and isinstance(input_data, list):
+            _needs_compact = len(input_data) > crof_limit
+            max_tok = _get_model_max_tokens(model)
+            est_tok = _estimate_input_tokens(input_data) if max_tok else 0
+            if not _needs_compact and max_tok and est_tok > max_tok * 0.8:
+                _needs_compact = True
+            if _needs_compact:
+                _agg = 0
+                if max_tok and est_tok > max_tok:
+                    _agg = 1
+                print(f"[crof-adaptive] proactive compact: {len(input_data)} items, est={est_tok}tok max={max_tok}tok agg={_agg}", file=sys.stderr)
+                input_data = _crof_compact_for_retry(input_data, model, aggression=_agg)
                 body = dict(body)
                 body["input"] = input_data
 
+        # Strip images for non-vision models
+        input_data = _strip_images_from_input(input_data, model)
+        body["input"] = input_data
+
         messages = oa_input_to_messages(input_data)
         messages = _inject_stored_reasoning(messages)
         instructions = body.get("instructions", "").strip()
@@ -4927,14 +5083,19 @@ class Handler(http.server.BaseHTTPRequestHandler):
                 except urllib.error.HTTPError as e:
                     err_body = e.read().decode()
                     if "context_length_exceeded" in err_body and attempt < max_retries:
-                        print(f"[{self._session_id}] context_length_exceeded (attempt {attempt+1}/{max_retries}), retrying with extreme compaction!", file=sys.stderr)
+                        import re as _re
+                        _tok_m = _re.search(r'~?(\d+)\s*tokens', err_body)
+                        if _tok_m:
+                            _set_model_max_tokens(model, int(_tok_m.group(1)))
+                        print(f"[{self._session_id}] context_length_exceeded (attempt {attempt+1}/{max_retries}), retrying with compaction (agg={attempt})!", file=sys.stderr)
                         policy = provider_policy()
                         if isinstance(input_data, list):
-                            print(f"[{self._session_id}] applying extreme compaction to {len(input_data)} items", file=sys.stderr)
-                            input_data = _crof_compact_for_retry(input_data, model)
+                            est = _estimate_input_tokens(input_data)
+                            print(f"[{self._session_id}] applying compaction to {len(input_data)} items ~{est}tok", file=sys.stderr)
+                            input_data = _crof_compact_for_retry(input_data, model, aggression=attempt)
                             body = dict(body)
                             body["input"] = input_data
-                            messages = oa_input_to_messages(input_data)
+                            messages = oa_input_to_messages(_strip_images_from_input(input_data, model))
                             messages = _inject_stored_reasoning(messages)
                             instructions = body.get("instructions", "").strip()
                             if instructions:
@@ -5267,22 +5428,26 @@ class Handler(http.server.BaseHTTPRequestHandler):
             if not is_latest_simple:
                 contents.insert(0, {"role": "user", "parts": [{"text": _GEMINI_AGENT_GUARDRAIL}]})
 
-        if OAUTH_PROVIDER == "google-antigravity" and isinstance(input_data, list):
-            _EDIT_WORDS = ("change", "fix", "update", "redesign", "rewrite", "modify", "improve", "replace", "edit", "make it", "add", "remove", "delete", "rename", "move", "convert")
-            latest_lower = ""
-            for item in reversed(input_data):
-                if item.get("type") == "message" and item.get("role") == "user":
-                    c = item.get("content", "")
-                    if isinstance(c, str): latest_lower = c.lower()
-                    elif isinstance(c, list): latest_lower = " ".join(p.get("text", p.get("input_text", "")) for p in c if isinstance(p, dict)).lower()
-                    break
-            if latest_lower and any(w in latest_lower for w in _EDIT_WORDS):
-                n_tool_calls = sum(1 for it in input_data if isinstance(it, dict) and it.get("type") == "function_call")
-                contents.append({"role": "user", "parts": [{"text": "!!! ABSOLUTELY NO PLANNING - EMIT THE TOOL CALL NOW !!! IMPORTANT: The user is requesting a modification to existing files. You MUST use tools (exec_command, read_files, write, etc.) to make the changes RIGHT NOW. Do NOT just describe what to do — actually CALL THE TOOLS IN THIS RESPONSE. IMMEDIATELY INSPECT THE FILE OR LIST FILES USING exec_command TOOL CALL."}]})
-                print(f"[antigravity] edit-intent detected; injected tool-use nudge", file=sys.stderr)
+        if OAUTH_PROVIDER == "google-antigravity":
+            import hashlib
+            ag_key = _antigravity_loop_key(self._session_id)
+            with _ANTIGRAVITY_LOOP_TRACKER_LOCK:
+                if ag_key not in _ANTIGRAVITY_LOOP_TRACKER:
+                    _ANTIGRAVITY_LOOP_TRACKER[ag_key] = {
+                        "latest_user_hash": None,
+                        "nudge_injected": False,
+                        "latest_user_appended": False,
+                        "tool_calls_for_request": 0,
+                        "repeated_tool": False,
+                        "force_finalize": False,
+                        "last_tool": None,
+                        "last_tool_count": 0,
+                    }
+                ag_state = _ANTIGRAVITY_LOOP_TRACKER[ag_key]
 
-        if OAUTH_PROVIDER == "google-antigravity" and isinstance(input_data, list):
             latest_user = ""
+            latest_user_hash = None
+            if isinstance(input_data, list):
                 for item in reversed(input_data):
                     if item.get("type") == "message" and item.get("role") == "user":
                         c = item.get("content", "")
@@ -5292,6 +5457,59 @@ class Handler(http.server.BaseHTTPRequestHandler):
                             latest_user = "\n".join(p.get("text", p.get("input_text", "")) for p in c if isinstance(p, dict))
                         break
                 if latest_user:
+                    latest_norm = " ".join(latest_user.strip().split())[:200]
+                    latest_user_hash = hashlib.sha256(latest_norm.encode()).hexdigest()[:16]
+                    if latest_user_hash != ag_state["latest_user_hash"]:
+                        ag_state["latest_user_hash"] = latest_user_hash
+                        ag_state["nudge_injected"] = False
+                        ag_state["latest_user_appended"] = False
+                        ag_state["tool_calls_for_request"] = 0
+                        ag_state["repeated_tool"] = False
+                        ag_state["force_finalize"] = False
+                        ag_state["last_tool"] = None
+                        ag_state["last_tool_count"] = 0
+
+            if isinstance(input_data, list):
+                n_tool_calls = sum(1 for it in input_data if isinstance(it, dict) and it.get("type") == "function_call")
+                ag_state["tool_calls_for_request"] = n_tool_calls
+                last_tool_key = None
+                for item in reversed(input_data):
+                    if isinstance(item, dict) and item.get("type") == "function_call":
+                        fname = item.get("name", "")
+                        args_str = json.dumps(item.get("arguments", {}), sort_keys=True)[:100]
+                        last_tool_key = f"{fname}:{args_str}"
+                        break
+                if last_tool_key:
+                    if last_tool_key == ag_state["last_tool"]:
+                        ag_state["last_tool_count"] += 1
+                        if ag_state["last_tool_count"] >= 5:
+                            ag_state["repeated_tool"] = True
+                            ag_state["force_finalize"] = True
+                    else:
+                        ag_state["last_tool"] = last_tool_key
+                        ag_state["last_tool_count"] = 1
+
+            _EDIT_WORDS = ("change", "fix", "update", "redesign", "rewrite", "modify", "improve", "replace", "edit", "make it", "add", "remove", "delete", "rename", "move", "convert")
+            latest_lower = ""
+            if isinstance(input_data, list):
+                for item in reversed(input_data):
+                    if item.get("type") == "message" and item.get("role") == "user":
+                        c = item.get("content", "")
+                        if isinstance(c, str): latest_lower = c.lower()
+                        elif isinstance(c, list): latest_lower = " ".join(p.get("text", p.get("input_text", "")) for p in c if isinstance(p, dict)).lower()
+                        break
+
+            if ag_state["force_finalize"]:
+                contents.append({"role": "user", "parts": [{"text": "STOP CALLING TOOLS. APPLY THE FINAL EDIT OR SUMMARIZE WHAT BLOCKED YOU. DO NOT CALL ANY MORE TOOLS. DO NOT PRODUCE ANY MORE PLANNING TEXT. DO NOT PRODUCE ANY MORE EXPLORATORY TOOL CALLS. PRODUCE A FINAL ANSWER OR A CLEAR STATEMENT OF WHAT IS PREVENTING YOU FROM COMPLETING THE TASK."}]})
+            elif latest_lower and any(w in latest_lower for w in _EDIT_WORDS) and not ag_state["nudge_injected"] and not ag_state["force_finalize"]:
+                contents.append({"role": "user", "parts": [{"text": "!!! ABSOLUTELY NO PLANNING - EMIT THE TOOL CALL NOW !!! IMPORTANT: The user is requesting a modification to existing files. You MUST use tools (exec_command, read_files, write, etc.) to make the changes RIGHT NOW. Do NOT just describe what to do — actually CALL THE TOOLS IN THIS RESPONSE. IMMEDIATELY INSPECT THE FILE OR LIST FILES USING exec_command TOOL CALL."}]})
+                ag_state["nudge_injected"] = True
+                print(f"[antigravity] edit-intent detected; injected tool-use nudge (first time for this request)", file=sys.stderr)
+            else:
+                if ag_state["nudge_injected"]:
+                    print(f"[antigravity] edit-intent nudge already injected, skipping", file=sys.stderr)
+
+            if latest_user and not ag_state["latest_user_appended"] and not ag_state["force_finalize"]:
                 latest_norm = " ".join(latest_user.strip().split())[:160]
                 final_text = ""
                 if contents:
@@ -5299,10 +5517,20 @@ class Handler(http.server.BaseHTTPRequestHandler):
                     if last.get("role") == "user":
                         final_text = " ".join(json.dumps(last.get("parts", []), ensure_ascii=False).split())
                 if latest_norm[:120] not in final_text:
-                    print(f"[antigravity] latest user instruction was not final turn; appending", file=sys.stderr)
+                    print(f"[antigravity] latest user instruction was not final turn; appending (first time for this request)", file=sys.stderr)
                     contents.append({"role": "user", "parts": [{"text": latest_user}]})
+                    ag_state["latest_user_appended"] = True
                 else:
                     print(f"[antigravity] latest user instruction is final turn", file=sys.stderr)
+            else:
+                if ag_state["latest_user_appended"]:
+                    print(f"[antigravity] latest user instruction already appended, skipping", file=sys.stderr)
+
+            print(f"[antigravity-loop] latest_user_hash={latest_user_hash}", file=sys.stderr)
+            print(f"[antigravity-loop] tool_calls_for_request={ag_state['tool_calls_for_request']}", file=sys.stderr)
+            print(f"[antigravity-loop] repeated_tool={ag_state['repeated_tool']}", file=sys.stderr)
+            print(f"[antigravity-loop] nudge_injected={ag_state['nudge_injected']}", file=sys.stderr)
+            print(f"[antigravity-loop] force_finalize={ag_state['force_finalize']}", file=sys.stderr)
             print(f"[{self._session_id}] [antigravity-debug] input_items={len(input_data) if isinstance(input_data, list) else 1} contents={len(contents)} latest={latest_user[:80]!r}", file=sys.stderr)
             if contents:
                 last_c = contents[-1]
@@ -5725,9 +5953,11 @@ class Handler(http.server.BaseHTTPRequestHandler):
             last_status = None
             finish_reason = None
             has_content = False
+            has_message = False
+            has_tool_call = False
 
             def _observe_event(event):
-                nonlocal last_resp_id, last_output, last_status, finish_reason, has_content
+                nonlocal last_resp_id, last_output, last_status, finish_reason, has_content, has_message, has_tool_call
                 for line in event.strip().split("\n"):
                     if line.startswith("data: "):
                         try:
@@ -5737,7 +5967,9 @@ class Handler(http.server.BaseHTTPRequestHandler):
                                 last_output = d.get("response", {}).get("output", [])
                                 last_status = d.get("response", {}).get("status")
                                 finish_reason = "length" if last_status == "incomplete" else "stop"
-                                has_content = any(o.get("type") == "message" for o in (last_output or []))
+                                has_tool_call = any(o.get("type") == "function_call" for o in (last_output or []))
+                                has_message = any(o.get("type") == "message" for o in (last_output or []))
+                                has_content = has_message or has_tool_call
                         except Exception:
                             pass
 
@@ -5749,7 +5981,7 @@ class Handler(http.server.BaseHTTPRequestHandler):
                         break
                     collected_events.append(event)
                     _observe_event(event)
-                print(f"[{self._session_id}] stream ended: events={len(collected_events)} finish={finish_reason} has_content={has_content} elapsed={time.time()-t0:.1f}s", file=sys.stderr)
+                print(f"[{self._session_id}] stream ended: events={len(collected_events)} finish={finish_reason} has_content={has_content} has_message={has_message} has_tool_call={has_tool_call} elapsed={time.time()-t0:.1f}s", file=sys.stderr)
             except (ConnectionResetError, BrokenPipeError, ConnectionAbortedError):
                 print("[translate-proxy] client disconnected during stream", file=sys.stderr)
                 _crof_record(model, n_items, False)
@@ -5805,6 +6037,8 @@ class Handler(http.server.BaseHTTPRequestHandler):
                         last_resp_id = last_output = last_status = None
                         finish_reason = None
                         has_content = False
+                        has_message = False
+                        has_tool_call = False
                         for event in oa_stream_to_sse(retry_upstream, model, body.get("request_id") or body.get("id")):
                             collected_events.append(event)
                             _observe_event(event)
@@ -5813,7 +6047,7 @@ class Handler(http.server.BaseHTTPRequestHandler):
                         print(f"[provider-sensor] synthetic retry failed: {e}", file=sys.stderr)
 
             # Auto-retry on finish_reason=length with no content due to too much context.
-            if finish_reason == "length" and not has_content and isinstance(input_data, list) and len(input_data) > 5 and TARGET_URL and "crof.ai" in TARGET_URL:
+            if finish_reason == "length" and not has_content and isinstance(input_data, list) and len(input_data) > 5:
                 print(f"[crof-adaptive] RETRY: finish_reason=length with no content, compacting {n_items} items", file=sys.stderr)
                 new_input = _crof_compact_for_retry(input_data, model)
                 if len(new_input) < len(input_data):
@@ -5836,6 +6070,8 @@ class Handler(http.server.BaseHTTPRequestHandler):
                         last_resp_id = last_output = last_status = None
                         finish_reason = None
                         has_content = False
+                        has_message = False
+                        has_tool_call = False
                         for event in oa_stream_to_sse(retry_upstream, model, body.get("request_id") or body.get("id")):
                             collected_events.append(event)
                             _observe_event(event)
@@ -5943,9 +6179,17 @@ class Handler(http.server.BaseHTTPRequestHandler):
                 _smart_attempt = 0
                 while _smart_attempt < _smart_max:
                     _has_tool_calls_in_output = any(o.get("type") == "function_call" for o in (last_output or []))
+                    last_text = ""
+                    for o in (last_output or []):
+                        if o.get("type") == "message":
+                            for c in (o.get("content") or []):
+                                if isinstance(c, dict) and c.get("type") == "output_text":
+                                    last_text += c.get("text", "")
+                    _looks_like_tools = _text_looks_like_tool_calls(last_text)
+                    _has_prior_tool_ctx = has_function_call_output(input_data)
                     if not (finish_reason == "stop" and has_content and not _has_tool_calls_in_output
                             and isinstance(input_data, list) and len(input_data) >= 3
-                            and has_function_call_output(input_data)):
+                            and (_has_prior_tool_ctx or _looks_like_tools)):
                         break
                     _smart_attempt += 1
                     _nudges = [
@@ -5954,12 +6198,6 @@ class Handler(http.server.BaseHTTPRequestHandler):
                     ]
                     nudge_text = _nudges[min(_smart_attempt - 1, len(_nudges) - 1)]
                     # Try extracting XML tool calls from text as fallback before nudging
-                    last_text = ""
-                    for o in (last_output or []):
-                        if o.get("type") == "message":
-                            for c in (o.get("content") or []):
-                                if isinstance(c, dict) and c.get("type") == "output_text":
-                                    last_text += c.get("text", "")
                     xml_fc = _extract_xml_tool_calls(last_text)
                     if xml_fc:
                         print(f"[{self._session_id}] [smart-continue] extracted {len(xml_fc)} XML tool calls from text, injecting and retrying", file=sys.stderr)
@@ -5979,6 +6217,8 @@ class Handler(http.server.BaseHTTPRequestHandler):
                             last_resp_id = last_output = last_status = None
                             finish_reason = None
                             has_content = False
+                            has_message = False
+                            has_tool_call = False
                             for event in oa_stream_to_sse(retry_upstream, model, body.get("request_id") or body.get("id")):
                                 collected_events.append(event)
                                 _observe_event(event)
@@ -5988,19 +6228,21 @@ class Handler(http.server.BaseHTTPRequestHandler):
                             print(f"[{self._session_id}] [smart-continue] XML injection retry failed: {e}", file=sys.stderr)
                             break
                     _nudge_msg = {"role": "user", "content": nudge_text}
-                    nudge_messages = oa_input_to_messages(input_data) + [_nudge_msg]
+                    nudge_messages = oa_input_to_messages(_strip_images_from_input(input_data, model)) + [_nudge_msg]
                     instructions = body.get("instructions", "").strip()
                     if instructions:
                         nudge_messages.insert(0, {"role": "system", "content": instructions})
                     nudge_chat_body = self._build_chat_body(model, nudge_messages, body, stream)
                     nudge_req = urllib.request.Request(target, data=json.dumps(nudge_chat_body).encode(), headers=fwd)
-                    print(f"[{self._session_id}] [smart-continue] attempt {_smart_attempt}/{_smart_max}: model stopped mid-task, nudging", file=sys.stderr)
+                    print(f"[{self._session_id}] [smart-continue] attempt {_smart_attempt}/{_smart_max}: model stopped mid-task (prior_ctx={_has_prior_tool_ctx} text_tools={_looks_like_tools}), nudging", file=sys.stderr)
                     try:
                         retry_upstream = urllib.request.urlopen(nudge_req, timeout=_upstream_timeout(body, True))
                         collected_events = []
                         last_resp_id = last_output = last_status = None
                         finish_reason = None
                         has_content = False
+                        has_message = False
+                        has_tool_call = False
                         for event in oa_stream_to_sse(retry_upstream, model, body.get("request_id") or body.get("id")):
                             collected_events.append(event)
                             _observe_event(event)