diff --git a/GramAddict/core/bot_flow.py b/GramAddict/core/bot_flow.py
index 011820c..be71e3d 100644
--- a/GramAddict/core/bot_flow.py
+++ b/GramAddict/core/bot_flow.py
@@ -444,8 +444,8 @@ def start_bot(**kwargs):
 
                         from GramAddict.core.llm_provider import query_llm
 
-                        model = getattr(configs.args, "ai_condenser_model", "llama3.2:1b")
-                        url = getattr(configs.args, "ai_condenser_url", "http://localhost:11434/api/generate")
+                        model = getattr(configs.args, "ai_condenser_model")
+                        url = getattr(configs.args, "ai_condenser_url")
 
                         response_dict = query_llm(url=url, model=model, prompt=prompt, format_json=True, timeout=120)
                         if response_dict and isinstance(response_dict, dict) and "persona" in response_dict:
diff --git a/GramAddict/core/compiler_engine.py b/GramAddict/core/compiler_engine.py
index b5a3e79..c3e81f6 100644
--- a/GramAddict/core/compiler_engine.py
+++ b/GramAddict/core/compiler_engine.py
@@ -30,13 +30,13 @@ class VLMCompilerEngine:
             extra={"color": "\x1b[1m\x1b[35m"},
         )
 
-        args = getattr(self.device, "args", None)
-        model = getattr(args, "ai_telepathic_model", "llama3.2:1b") if args else "llama3.2:1b"
-        url = (
-            getattr(args, "ai_telepathic_url", "http://localhost:11434/api/generate")
-            if args
-            else "http://localhost:11434/api/generate"
-        )
+        from GramAddict.core.config import Config
+
+        cfg = Config()
+        if not hasattr(cfg, "args"):
+            raise RuntimeError("Config().args not initialized — cannot resolve AI model. Fail Fast.")
+        model = getattr(cfg.args, "ai_telepathic_model")
+        url = getattr(cfg.args, "ai_telepathic_url")
         use_local = "11434" in url or "localhost" in url
 
         simplified_xml = self._simplify_xml(context_xml)
diff --git a/GramAddict/core/dm_engine.py b/GramAddict/core/dm_engine.py
index d219a5d..08ee457 100644
--- a/GramAddict/core/dm_engine.py
+++ b/GramAddict/core/dm_engine.py
@@ -152,8 +152,8 @@ def _run_zero_latency_dm_loop(device, zero_engine, nav_graph, configs, session_s
                     return "BOREDOM_CHANGE_FEED"
 
                 # Configure models
-                model = getattr(configs.args, "ai_condenser_model", "llama3.2:1b")
-                url = getattr(configs.args, "ai_condenser_url", "http://localhost:11434/api/generate")
+                model = getattr(configs.args, "ai_condenser_model")
+                url = getattr(configs.args, "ai_condenser_url")
 
                 # Generate response
                 prompt = f"You are replying to a direct message on Instagram. The last message you received was: '{context_text}'. Keep it short, casual, and friendly. Do not use hashtags."
diff --git a/GramAddict/core/interaction.py b/GramAddict/core/interaction.py
index a24ebda..12575c5 100644
--- a/GramAddict/core/interaction.py
+++ b/GramAddict/core/interaction.py
@@ -54,9 +54,9 @@ class LLMWriter:
             f"6. Reply with ONLY the comment text."
         )
 
-        model = getattr(self.args, "ai_writer_model", getattr(self.args, "ai_model", "llama3.2:1b"))
+        model = getattr(self.args, "ai_writer_model", getattr(self.args, "ai_model"))
         url = getattr(
-            self.args, "ai_writer_url", getattr(self.args, "ai_model_url", "http://localhost:11434/api/generate")
+            self.args, "ai_writer_url", getattr(self.args, "ai_model_url")
         )
 
         logger.info(f"✍️ [Writer] Generating comment for @{target_username} using {model}...")
diff --git a/GramAddict/core/llm_provider.py b/GramAddict/core/llm_provider.py
index 438c878..c7413f9 100644
--- a/GramAddict/core/llm_provider.py
+++ b/GramAddict/core/llm_provider.py
@@ -395,14 +395,11 @@ def query_llm(
             except Exception:
                 pass
 
-        # Last resort defaults
+        # Last resort: If no fallback config exists, don't silently use hardcoded defaults.
+        # Config() defines these via argparse defaults — if they're missing, there's nothing to fallback to.
         if not f_model or not f_url:
-            if is_openai_compat:
-                f_model = f_model or "llama3.2:1b"
-                f_url = f_url or "http://localhost:11434/api/generate"
-            else:
-                f_model = f_model or "llama3.2:1b"
-                f_url = f_url or "http://localhost:11434/api/generate"
+            logger.warning("⚠️ [Circuit Breaker] No fallback model/URL configured. Cannot retry.")
+            return None
 
         # Circuit Breaker: If fallback is identical to primary, don't waste time retrying
         if f_model == model and f_url == url:
@@ -458,11 +455,12 @@ def query_telepathic_llm(
 
             try:
                 args = Config().args
-                target_url = getattr(args, "ai_fallback_url", "http://localhost:11434/api/generate")
-                target_model = getattr(args, "ai_fallback_model", "llama3.2:1b")
+                target_url = getattr(args, "ai_fallback_url")
+                target_model = getattr(args, "ai_fallback_model")
             except Exception:
-                target_url = "http://localhost:11434/api/generate"
-                target_model = "llama3.2:1b"
+                raise RuntimeError(
+                    "Config().args not initialized — cannot resolve fallback AI model. Fail Fast."
+                )
 
     is_local = "localhost" in target_url or "127.0.0.1" in target_url
     calc_timeout = 180 if is_local else 45
diff --git a/GramAddict/core/navigation/brain.py b/GramAddict/core/navigation/brain.py
index 66d4a42..4880aa0 100644
--- a/GramAddict/core/navigation/brain.py
+++ b/GramAddict/core/navigation/brain.py
@@ -15,12 +15,10 @@ def ask_brain_for_action(
         return None
 
     cfg = Config()
-    url = (
-        getattr(cfg.args, "ai_model_url", "http://localhost:11434/api/generate")
-        if hasattr(cfg, "args")
-        else "http://localhost:11434/api/generate"
-    )
-    model = getattr(cfg.args, "ai_model", "qwen3.5:latest") if hasattr(cfg, "args") else "qwen3.5:latest"
+    if not hasattr(cfg, "args"):
+        raise RuntimeError("Config().args not initialized — cannot resolve AI model. Fail Fast.")
+    url = getattr(cfg.args, "ai_model_url")
+    model = getattr(cfg.args, "ai_model")
 
     prompt = (
         f"You are an autonomous Instagram agent. Your ultimate goal is: '{goal}'.\n"
diff --git a/GramAddict/core/perception/intent_resolver.py b/GramAddict/core/perception/intent_resolver.py
index 47a8c6b..16804d2 100644
--- a/GramAddict/core/perception/intent_resolver.py
+++ b/GramAddict/core/perception/intent_resolver.py
@@ -661,8 +661,8 @@ class IntentResolver:
         self.last_box_map = box_map
 
         cfg = Config()
-        model = getattr(cfg.args, "ai_telepathic_model", "llava:latest")
-        url = getattr(cfg.args, "ai_telepathic_url", "http://localhost:11434/api/generate")
+        model = getattr(cfg.args, "ai_telepathic_model")
+        url = getattr(cfg.args, "ai_telepathic_url")
 
         # Build a compact legend of what each box contains
         box_legend_lines = []
@@ -785,8 +785,8 @@ class IntentResolver:
             filtered_candidates = [n for n in candidates if n.area < 500000]
 
         cfg = Config()
-        model = getattr(cfg.args, "ai_telepathic_model", "qwen3.5:latest")
-        url = getattr(cfg.args, "ai_telepathic_url", "http://localhost:11434/api/generate")
+        model = getattr(cfg.args, "ai_telepathic_model")
+        url = getattr(cfg.args, "ai_telepathic_url")
 
         node_context = []
         for i, node in enumerate(filtered_candidates):
diff --git a/GramAddict/core/perception/screen_identity.py b/GramAddict/core/perception/screen_identity.py
index 2073b69..b527384 100644
--- a/GramAddict/core/perception/screen_identity.py
+++ b/GramAddict/core/perception/screen_identity.py
@@ -276,12 +276,10 @@ class ScreenIdentity:
         from GramAddict.core.llm_provider import query_telepathic_llm
 
         cfg = Config()
-        url = (
-            getattr(cfg.args, "ai_telepathic_url", "http://localhost:11434/api/generate")
-            if hasattr(cfg, "args")
-            else "http://localhost:11434/api/generate"
-        )
-        model = getattr(cfg.args, "ai_telepathic_model", "llava:latest") if hasattr(cfg, "args") else "llava:latest"
+        if not hasattr(cfg, "args"):
+            raise RuntimeError("Config().args not initialized — cannot resolve AI model. Fail Fast.")
+        url = getattr(cfg.args, "ai_telepathic_url")
+        model = getattr(cfg.args, "ai_telepathic_model")
 
         layout_context = (
             f"Selected Tab: {selected_tab}\nResource IDs: {list(ids)}\nVisible Texts context: {texts[:10]}\n"
diff --git a/GramAddict/core/perception/semantic_evaluator.py b/GramAddict/core/perception/semantic_evaluator.py
index 2bdfbc7..caeacd3 100644
--- a/GramAddict/core/perception/semantic_evaluator.py
+++ b/GramAddict/core/perception/semantic_evaluator.py
@@ -28,8 +28,8 @@ class SemanticEvaluator:
             logger.warning("👁️ [Vision Core] No config available. Cannot query VLM.")
             return None
 
-        model = getattr(self.args, "ai_telepathic_model", "llama3.2-vision")
-        url = getattr(self.args, "ai_telepathic_url", "http://localhost:11434/api/generate")
+        model = getattr(self.args, "ai_telepathic_model")
+        url = getattr(self.args, "ai_telepathic_url")
 
         try:
             res = query_telepathic_llm(
diff --git a/GramAddict/core/qdrant_memory.py b/GramAddict/core/qdrant_memory.py
index cc31eaf..c4232a2 100644
--- a/GramAddict/core/qdrant_memory.py
+++ b/GramAddict/core/qdrant_memory.py
@@ -112,8 +112,8 @@ class QdrantBase:
         args = self._cached_args
 
         # Pull specific embedding config or fallback to defaults
-        model = getattr(args, "ai_embedding_model", "nomic-embed-text")
-        url = getattr(args, "ai_embedding_url", "http://localhost:11434/api/embeddings")
+        model = getattr(args, "ai_embedding_model")
+        url = getattr(args, "ai_embedding_url")
 
         try:
             # Generate embeddings
diff --git a/GramAddict/core/resonance_engine.py b/GramAddict/core/resonance_engine.py
index aed9ea4..e2569e8 100644
--- a/GramAddict/core/resonance_engine.py
+++ b/GramAddict/core/resonance_engine.py
@@ -386,8 +386,8 @@ class ResonanceEngine:
             "Set 'keep' to false only for clear spam, bots, UI buttons, or blacklist violations.\n"
         )
 
-        model = getattr(configs.args, "ai_condenser_model", "llama3.2:1b")
-        url = getattr(configs.args, "ai_condenser_url", "http://localhost:11434/api/generate")
+        model = getattr(configs.args, "ai_condenser_model")
+        url = getattr(configs.args, "ai_condenser_url")
 
         try:
             import json
diff --git a/tests/unit/__pycache__/test_sae_zero_maintenance.cpython-311-pytest-8.3.5.pyc b/tests/unit/__pycache__/test_sae_zero_maintenance.cpython-311-pytest-8.3.5.pyc
index 9c6988e..952472c 100644
Binary files a/tests/unit/__pycache__/test_sae_zero_maintenance.cpython-311-pytest-8.3.5.pyc and b/tests/unit/__pycache__/test_sae_zero_maintenance.cpython-311-pytest-8.3.5.pyc differ
diff --git a/tests/unit/__pycache__/test_structural_hardening.cpython-311-pytest-8.3.5.pyc b/tests/unit/__pycache__/test_structural_hardening.cpython-311-pytest-8.3.5.pyc
index eaed113..538e2a4 100644
Binary files a/tests/unit/__pycache__/test_structural_hardening.cpython-311-pytest-8.3.5.pyc and b/tests/unit/__pycache__/test_structural_hardening.cpython-311-pytest-8.3.5.pyc differ
diff --git a/tests/unit/test_sae_zero_maintenance.py b/tests/unit/test_sae_zero_maintenance.py
index b86fc9d..3961168 100644
--- a/tests/unit/test_sae_zero_maintenance.py
+++ b/tests/unit/test_sae_zero_maintenance.py
@@ -164,6 +164,97 @@ class TestSAEContainsNoHardcodedModelDefaults:
         )
 
 
+# ══════════════════════════════════════════════════════════
+# 2b. NO HARDCODED MODEL/URL DEFAULTS IN ANY MODULE (codebase-wide)
+# ══════════════════════════════════════════════════════════
+
+
+class TestCodebaseContainsNoHardcodedModelDefaults:
+    """
+    CODEBASE-WIDE enforcement: No Python module in GramAddict/core/ may contain
+    hardcoded model names or localhost URLs as getattr() default values.
+
+    The ONLY file allowed to define these defaults is config.py (the SSOT).
+    Every other module must read from Config().args WITHOUT providing a fallback literal.
+    If Config().args is missing, the system must crash (Fail Fast) — not silently
+    degrade to a potentially wrong model.
+    """
+
+    # These are the exact default-value patterns that are FORBIDDEN outside config.py.
+    # They indicate a getattr(..., "ai_xxx", "HARDCODED_DEFAULT") anti-pattern.
+    FORBIDDEN_DEFAULT_PATTERNS = [
+        r'getattr\([^)]*,\s*["\']ai_[^"\']*["\']\s*,\s*["\']http://localhost:11434',
+        r'getattr\([^)]*,\s*["\']ai_[^"\']*["\']\s*,\s*["\']llava:',
+        r'getattr\([^)]*,\s*["\']ai_[^"\']*["\']\s*,\s*["\']qwen3\.',
+        r'getattr\([^)]*,\s*["\']ai_[^"\']*["\']\s*,\s*["\']llama3\.',
+        r'getattr\([^)]*,\s*["\']ai_[^"\']*["\']\s*,\s*["\']llama3\.2-vision',
+        r'getattr\([^)]*,\s*["\']ai_[^"\']*["\']\s*,\s*["\']nomic-embed-text',
+    ]
+
+    # Files that are ALLOWED to have these defaults (SSOT only)
+    ALLOWED_FILES = {"config.py"}
+
+    def _get_all_core_python_files(self):
+        import os
+
+        core_dir = os.path.join(os.path.dirname(__file__), "..", "..", "GramAddict", "core")
+        core_dir = os.path.normpath(core_dir)
+        files = []
+        for root, _dirs, filenames in os.walk(core_dir):
+            for f in filenames:
+                if f.endswith(".py") and f not in self.ALLOWED_FILES:
+                    files.append(os.path.join(root, f))
+        return files
+
+    def test_no_getattr_with_hardcoded_model_defaults_outside_config(self):
+        """
+        No module except config.py may use getattr(args, 'ai_xxx', 'HARDCODED_DEFAULT').
+        The correct pattern is: getattr(cfg.args, 'ai_xxx') — no default, crash if missing.
+        """
+        import os
+
+        violations = []
+        for filepath in self._get_all_core_python_files():
+            with open(filepath) as f:
+                content = f.read()
+            for pattern in self.FORBIDDEN_DEFAULT_PATTERNS:
+                matches = re.findall(pattern, content)
+                if matches:
+                    basename = os.path.basename(filepath)
+                    violations.append(f"{basename}: {len(matches)}x pattern '{pattern[:60]}...'")
+
+        assert len(violations) == 0, (
+            f"Found {len(violations)} file(s) with hardcoded model/URL defaults outside config.py!\n"
+            f"Config() is the SSOT. Remove default values from getattr() calls.\n"
+            + "\n".join(f"  ❌ {v}" for v in violations)
+        )
+
+    def test_no_bare_localhost_url_string_literals_outside_config(self):
+        """
+        No module except config.py and llm_provider.py (routing logic) may contain
+        'http://localhost:11434' as a bare string literal used as a fallback value.
+        """
+        import os
+
+        allowed = {"config.py", "llm_provider.py"}
+        violations = []
+        core_dir = os.path.join(os.path.dirname(__file__), "..", "..", "GramAddict", "core")
+        core_dir = os.path.normpath(core_dir)
+
+        for root, _dirs, filenames in os.walk(core_dir):
+            for f in filenames:
+                if f.endswith(".py") and f not in allowed:
+                    path = os.path.join(root, f)
+                    with open(path) as fh:
+                        for i, line in enumerate(fh, 1):
+                            if "localhost:11434" in line and not line.strip().startswith("#"):
+                                violations.append(f"{f}:{i}: {line.strip()[:100]}")
+
+        assert len(violations) == 0, (
+            f"Found {len(violations)} hardcoded localhost:11434 references outside config.py/llm_provider.py!\n"
+            + "\n".join(f"  ❌ {v}" for v in violations)
+        )
+
 # ══════════════════════════════════════════════════════════
 # 3. GOAP SMART UI STABILIZATION (Poll instead of static sleep)
 # ══════════════════════════════════════════════════════════