69c97e125a
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
2026-05-21 01:19:40 -04:00
4bc49c90b3
Implement LAIN ↔ Supercharged Glyph Bridge
...
New module:
- gx_lain/lain_glyph_bridge.py: Bridge connecting LedoGlyph600 to LAIN cognition
Functions:
- load_glyph_context(manifest, context): Load relevant glyph from registry
- inject_glyph_metadata_into_lane(lane_result, glyph_context): Add glyph fields to lane
- compute_glyph_resonance(glyph_context): Calculate glyph resonance metrics
- augment_fused_symbol_with_glyphs(fused_symbol, glyph_context): Add glyph to final output
Modified:
- gx_lain/runtime.py: Integrate glyph bridge into execute_with_lain()
* Load glyph context as step 1 of cognition
* Inject glyph metadata into each lane result
* Augment fused symbol with glyph context
* Add glyph_resonance to diagnostics
* Track glyph loading in cognition_trace
Tests:
- tests/test_lain_glyph_bridge.py: 10 comprehensive tests
* Context loading (with/without glyph)
* Metadata injection (preserves existing fields)
* Resonance computation (4-component metric)
* Symbol augmentation
* Full integration test
Features:
- Glyph metadata: id, name, category, score, period, band
- Frequency signatures: praw (P, R, A, W)
- Activation envelopes: mode, score
- Lineage: signature, inheritance weight
- Symbolic anatomy: power, complexity, resonance, stability, connectivity, affinity
- Resonance profile: activation + frequency + symbolic metrics (0.0-1.0)
All 18 integration tests still passing (no regressions).
2026-05-20 17:41:47 -04:00
93ac2003b3
Implement real LAIN cognition engine with 8 lane processors
...
New modules:
- gx_lain/lane_processors.py: 8 symbolic lane processors
* Lane 0: structural_logic (control flow, constraints)
* Lane 1: semantic_flow (core meaning, narrative)
* Lane 2: compression_residue (artifacts, hints)
* Lane 3: symbolic_metadata (tags, annotations)
* Lane 4: execution_hints (runtime guards, priorities)
* Lane 5: predictive_scaffolding (hypotheses, priors)
* Lane 6: contributor_imprint (author style, bias)
* Lane 7: epoch_resonance (temporal context)
- gx_lain/runtime.py (updated): Real cognition loop
* execute_with_lain(): Process all 8 lanes, capture timings
* fuse_lanes(): Merge lane results into final symbol
* compute_resonance(): Per-lane resonance metrics
* render_output_text(): Mode-based output formatting
Features:
- Structured lane processing with error recovery
- Cognition trace with per-lane timing
- Resonance metrics (1.0 if lane has content)
- Fused symbol with deduplication
- Mode-aware output (ANALYZE vs SYNTHESIZE)
- No mutations, deterministic execution
All 18 integration tests pass unchanged.
2026-05-20 14:54:56 -04:00
af1265d2b2
Implement GX→LAIN runtime interface v1.0
...
Core pipeline: load_gx() → normalize_segments() → map_lanes() → build_envelope() → execute_with_lain()
Features:
- Load .gx files and extract manifest, segments, payload
- Normalize raw segments into canonical schema (id, start_line, end_line, text, symbolic_lane, semantic_role)
- Map segments into 8 symbolic lanes (structural_logic, semantic_flow, compression_residue, symbolic_metadata, execution_hints, predictive_scaffolding, contributor_imprint, epoch_resonance)
- Build ExecutionEnvelope with manifest, lanes, payload, context
- Stub LAIN execution with cognition_trace, fused_symbol, output_text, diagnostics
- Structured error handling via make_error()
- Interface versioning and deterministic execution
All integration tests still pass (18/18).
Main entry point: execute_gx_path(gx_path, context=None)
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com >
2026-05-20 13:54:33 -04:00
GlyphRunner System