Extend XIC v1 Engine with Symbolic Mode, 5 New Ops, GPU Path, Cognition Integration

New instructions:
- STREAM: Line-by-line execution and output
- CHAIN: Named execution boundaries
- CALL_GLYPH: Invoke glyph-aware cognition
- SET_CONTEXT: Set symbolic/cognitive context metadata
- LOG: Structured logging

Symbolic execution mode:
- SET_MODE "symbolic" routes prompts through LAIN 8-lane cognition pipeline
- run_symbolic_prompt() compresses prompt, builds manifest, executes via execute_symbolic()
- Full integration with glyphos/cognitive_kernel.py

GPU-accelerated path:
- xic_extensions/gpu_runtime.py: has_gpu() probes torch.cuda, run_on_gpu() executes
- SET_PARAM "use_gpu" true enables GPU (auto-fallback to CPU if unavailable)
- No required GPU dependencies; system works equally on CPU

Demo programs:
- demo_symbolic.gx.json: Shows symbolic mode through LAIN pipeline
- demo_gpu.gx.json: Shows GPU mode with CPU fallback

Backward compatibility:
- All 4 original ops unchanged; 5 new ops added to OP_TABLE
- xic_vm.py, xic_executor.py: No changes (pure dispatcher pattern holds)
- demo_chat.gx.json: Still executes identically
- All existing GlyphRunner commands: Unchanged behavior

Architecture:
- Lazy imports prevent circular dependencies (xic_ops, glyphos, xic_extensions)
- Clean separation: XIC is client of cognition layer
- Zero breaking changes; additive extension only
- No XIC v2 binary format; all within v1 JSON+.gx architecture

Validation:
- 10 integration tests: all passing
- Backward compat verified with original demo
- Symbolic and GPU modes tested end-to-end
- No external dependencies required (GPU optional)

Co-contributors: LAIN cognition engine, gx_compiler GSZ3, glyphos event system

This commit is contained in: