Refine XIC v1 to Symbolic Extension Only (No GPU Code)

Removed GPU-related code per specification:
- Deleted xic_extensions/gpu_runtime.py
- Removed GPU logic from op_RUN_PROMPT and op_STREAM
- Removed demo_gpu.gx.json

Kept pure symbolic extension:
- 5 new instructions: STREAM, CHAIN, CALL_GLYPH, SET_CONTEXT, LOG
- Symbolic execution mode via SET_MODE "symbolic"
- run_symbolic_prompt() integration with LAIN cognition layer
- demo_symbolic.gx.json for testing

Implementation now focuses exclusively on:
- Extending instruction set (9 total ops)
- Adding symbolic routing to cognition layer
- Preserving backward compatibility (zero breaking changes)
- No external GPU dependencies

All validation tests pass:
✅ OP_TABLE coverage (9 operations)
✅ XICContext.symbolic_mode field
✅ run_symbolic_prompt() callable
✅ Backward compatibility (demo_chat unchanged)
✅ Symbolic mode execution (LAIN pipeline)
✅ SET_CONTEXT, CHAIN, RUN_PROMPT routing

Constraints met:
✅ No breaking changes
✅ No XIC v2 binary format
✅ No GPU-related code
✅ Strict v1 JSON + .gx architecture

xic_ops.py

@@ -45,7 +45,7 @@ def op_RUN_PROMPT(ctx: XICContext, *args):
     """RUN_PROMPT <prompt>: Execute prompt against loaded model or symbolic cognition.
 
     If ctx.symbolic_mode is True, routes through glyphos/cognitive_kernel.py.
-    Otherwise, routes to execute_gx() with optional GPU acceleration.
+    Otherwise, routes to execute_gx() for compressed execution.
     """
     if not args:
         raise ValueError("RUN_PROMPT requires a prompt argument")
@@ -63,24 +63,11 @@ def op_RUN_PROMPT(ctx: XICContext, *args):
         raise ValueError("No model loaded. Use LOAD_MODEL first.")
 
     try:
-        if ctx.params.get("use_gpu"):
-            from xic_extensions.gpu_runtime import has_gpu, run_on_gpu
-            if has_gpu():
-                print(f"[XIC-GPU] Running on GPU: {ctx.model_path}")
-                execution_context = run_on_gpu(ctx.model_path, ctx.params)
-            else:
-                print(f"[XIC-GPU] No GPU detected, falling back to CPU")
-                execution_context = execute_gx(
-                    ctx.model_path,
-                    trace=ctx.params.get("trace", False),
-                    profile=ctx.params.get("profile", False)
-                )
-        else:
-            execution_context = execute_gx(
-                ctx.model_path,
-                trace=ctx.params.get("trace", False),
-                profile=ctx.params.get("profile", False)
-            )
+        execution_context = execute_gx(
+            ctx.model_path,
+            trace=ctx.params.get("trace", False),
+            profile=ctx.params.get("profile", False)
+        )
 
         print(f"[XIC] Execution complete")
         print(f"[XIC] Result: {getattr(execution_context, 'result', 'OK')}")
@@ -95,7 +82,10 @@ def op_RUN_PROMPT(ctx: XICContext, *args):
 
 
 def op_STREAM(ctx: XICContext, *args):
-    """STREAM <prompt>: Execute and stream output line by line."""
+    """STREAM <prompt>: Execute and stream output line by line.
+
+    In symbolic mode, stream symbolic result. In compressed mode, stream compressed output.
+    """
     if not args:
         raise ValueError("STREAM requires a prompt argument")
     prompt = str(args[0])
@@ -103,7 +93,7 @@ def op_STREAM(ctx: XICContext, *args):
     if ctx.symbolic_mode:
         from glyphos.cognitive_kernel import run_symbolic_prompt
         result = run_symbolic_prompt(prompt, context=ctx.params.get("context"))
-        for chunk in result.split("\n"):
+        for chunk in str(result).split("\n"):
             if chunk.strip():
                 print(f"[XIC-STREAM] {chunk}")
         ctx._state["last_symbolic_result"] = result
@@ -112,27 +102,23 @@ def op_STREAM(ctx: XICContext, *args):
     if not ctx.model_path:
         raise ValueError("No model loaded. Use LOAD_MODEL first.")
 
-    use_gpu = ctx.params.get("use_gpu")
-    if use_gpu:
-        from xic_extensions.gpu_runtime import has_gpu, run_on_gpu
-        if has_gpu():
-            print(f"[XIC-GPU] Streaming on GPU: {ctx.model_path}")
-            exec_ctx = run_on_gpu(ctx.model_path, ctx.params)
-        else:
-            print(f"[XIC-GPU] No GPU detected, falling back to CPU")
-            exec_ctx = execute_gx(ctx.model_path,
-                                  trace=ctx.params.get("trace", False),
-                                  profile=ctx.params.get("profile", False))
-    else:
-        exec_ctx = execute_gx(ctx.model_path,
-                              trace=ctx.params.get("trace", False),
-                              profile=ctx.params.get("profile", False))
-
-    result_text = str(getattr(exec_ctx, "result", "OK"))
-    for chunk in result_text.split("\n"):
-        if chunk.strip():
-            print(f"[XIC-STREAM] {chunk}")
-    ctx._state["last_result"] = exec_ctx
+    try:
+        exec_ctx = execute_gx(
+            ctx.model_path,
+            trace=ctx.params.get("trace", False),
+            profile=ctx.params.get("profile", False),
+        )
+        result_text = str(getattr(exec_ctx, "result", "OK"))
+        for chunk in result_text.split("\n"):
+            if chunk.strip():
+                print(f"[XIC-STREAM] {chunk}")
+        ctx._state["last_result"] = exec_ctx
+    except ExecutionError as e:
+        print(f"[XIC] Execution error: {e}")
+        raise
+    except Exception as e:
+        print(f"[XIC] Unexpected error: {e}")
+        raise
 
 
 def op_CHAIN(ctx: XICContext, *args):
@@ -165,8 +151,10 @@ def op_SET_CONTEXT(ctx: XICContext, *args):
         raise ValueError("SET_CONTEXT requires key and value")
     if "context" not in ctx.params:
         ctx.params["context"] = {}
-    ctx.params["context"][str(args[0])] = args[1]
-    print(f"[XIC] Context {args[0]} = {args[1]}")
+    key = str(args[0])
+    value = args[1]
+    ctx.params["context"][key] = value
+    print(f"[XIC] Context {key} = {value}")
 
 
 def op_LOG(ctx: XICContext, *args):