bce6b6fa37435d546e076a56adc97b7d13cc7557
2 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 GlyphRunner System
|
bce6b6fa37 |
Implement XIC v1.5 glyph resonance awareness upgrade (Phase 3-4)
This commit completes the comprehensive glyph resonance awareness upgrade
with queryable resonance metrics, new instruction, and formal specification.
## Changes
### Phase 3: New GET_GLYPH_RESONANCE Instruction
- Added op_GET_GLYPH_RESONANCE to xic_ops.py for querying glyph resonance data
- Supports metrics: report, global, dominant, weight, lineage, contributor, frequency, grammar
- Results printed with [XIC-RESONANCE] prefix and stored in ctx._state
- Handles both full pipeline result (preferred) and fallback to resonance_metrics dict
- Updated OP_TABLE to include 10th operation
### Phase 4: Formal Specification & Demo
#### XIC_SEMANTICS_v1_5.md Updates
- Added comprehensive "Glyph Resonance Structure" section documenting:
- FusedSymbol dataclass with summary, glyph_ids, resonance_map
- GlyphResonanceMap with resonances dict and utility methods
- GlyphResonanceMetrics (weight, lineage_score, contributor_score, frequency_score, grammar_score)
- Example JSON structure from LAIN cognition
- Added "GET_GLYPH_RESONANCE" instruction semantics with:
- Signature and preconditions/postconditions
- Metric table describing all query types
- Detailed side effects and remarks
- Data access patterns
#### New Demo Program
- Created programs/demo_glyph_resonance.gx.json
- Two-chain demonstration:
- Chain 1: compression_theory glyph with report, global, dominant, weight queries
- Chain 2: neural_dynamics glyph with individual metric queries (lineage, contributor, frequency, grammar)
- Full instrumentation with CHAIN markers and LOG statements
#### Comprehensive Report
- Created XIC_GLYPH_RESONANCE_REPORT.md documenting:
- Executive summary of resonance awareness upgrade
- Detailed explanation of all components
- Architecture and data flow diagrams
- All 10 validation test results
- Usage examples and design decisions
- Backward compatibility guarantees
- Future extensibility notes
## Implementation Details
### Enhanced Data Structures (glyphos/symbolic_pipeline.py)
- GlyphResonanceMetrics: 5-dimensional resonance scoring
- GlyphResonanceMap: with get_glyph_resonance(), get_top_glyphs(), get_average_resonance()
- FusedSymbol.from_lain_result(): parses LAIN output structure
### Glyph Resonance Utilities
- extract_glyph_resonances(): extract per-glyph metrics from pipeline result
- get_dominant_glyphs(n): rank glyphs by weight
- format_glyph_resonance_report(): human-readable resonance output
### Enhanced CALL_GLYPH
- Now stores comprehensive resonance data in ctx._state["glyph_{glyph_id}"]
- Captures output_text, fused_symbol, resonance_metrics, global_resonance_score, steps
- Also stores full SymbolicPipelineResult for direct access
### New op_GET_GLYPH_RESONANCE
- Query stored resonance metrics with flexible metric selection
- Integrates with symbolic_pipeline utilities for full introspection
- Prints results and stores in ctx._state for programmatic access
## Exports (glyphos/__init__.py)
- GlyphResonanceMetrics
- GlyphResonanceMap
- extract_glyph_resonances
- get_dominant_glyphs
- format_glyph_resonance_report
## Testing
All 10 validation tests pass:
✅ GlyphResonanceMetrics instantiation
✅ GlyphResonanceMap methods (get_glyph_resonance, get_top_glyphs, get_average_resonance)
✅ FusedSymbol.from_lain_result() parsing
✅ extract_glyph_resonances() functionality
✅ get_dominant_glyphs() ranking
✅ format_glyph_resonance_report() generation
✅ OP_TABLE has GET_GLYPH_RESONANCE
✅ op_GET_GLYPH_RESONANCE callable
✅ demo_glyph_resonance.gx.json valid
✅ All exports available from glyphos
## Backward Compatibility
- Zero breaking changes
- All XIC v1 and v1.5 programs work unchanged
- New resonance features are additive
- Existing instruction signatures preserved
- Compressed mode execution unaffected
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
|
||
|
GlyphRunner System
|
6e0a586f51 |
Implement XIC v1.5: Symbolic Pipeline Abstraction with Glyph-Aware Transformations
Implements all phases of the symbolic pipeline extension: **Phase 1: Symbolic Pipeline Abstraction** - Created glyphos/symbolic_pipeline.py with: - SymbolicStep: tracks individual pipeline steps (name, kind, payload, context) - SymbolicPipelineResult: complete pipeline execution result (steps, output_text, fused_symbol) - run_symbolic_pipeline(prompt, context, glyph_id): high-level pipeline entrypoint - Integrated with glyphos/__init__.py exports **Phase 2: Glyph-Aware Transformations** - Updated glyphos/cognitive_kernel.py: - run_symbolic_prompt() now thin wrapper around pipeline - Maintains backward compatibility - Updated xic_ops.py operations: - op_RUN_PROMPT: uses pipeline in symbolic mode - op_STREAM: uses pipeline with line-by-line output - op_CALL_GLYPH: routes through pipeline with explicit glyph_id parameter - Context propagation: glyph_id automatically injected into LAIN context **Phase 3: XIC Instruction Semantics v1.5** - Created XIC_SEMANTICS_v1_5.md: - Formal specification of all 9 XIC instructions - Complete semantics: preconditions, postconditions, side effects - Symbolic vs compressed behavior for each op - Context model and pipeline semantics - Execution paths (compressed vs symbolic) - Backward compatibility guarantees **Phase 4: Demo Program & Validation** - Created programs/demo_symbolic_pipeline.gx.json - Demonstrates symbolic pipeline with glyph-aware cognition - Uses CALL_GLYPH, RUN_PROMPT, SET_CONTEXT, CHAIN, LOG - All 7 validation tests pass: ✅ Pipeline module imports ✅ Pipeline execution ✅ Glyph-aware transformations ✅ Demo program ✅ CALL_GLYPH result storage ✅ Backward compatibility ✅ run_symbolic_prompt() wrapper **Phase 5: Final Report** - Created XIC_SYMBOLIC_PIPELINE_REPORT.md - Architecture and module hierarchy - Integration points and data flow - Design decisions and rationale - Usage examples Key Features: - Step-level introspection: full SymbolicPipelineResult with step history - Glyph-aware: explicit glyph_id routing through LAIN kernel - Formal semantics: complete specification for tool builders - Backward compatible: all v1 programs work unchanged - No breaking changes: compressed execution path untouched Constraints Met: ✅ No GPU code ✅ No XIC v2 binary container ✅ No .gx format changes ✅ Full backward compatibility |