## Summary
Investigated OpenAI's new GPT-5-Codex model and Codex GitHub PR review integration capabilities.
## GPT-5-Codex Analysis
### Benchmark Performance (Good)
- SWE-bench Verified: 74.5% (vs GPT-5's 72.8%)
- Refactoring tasks: 51.3% (vs GPT-5's 33.9%)
- Code review: Higher developer ratings
### Real-World Issues (Concerning)
- Users report degraded coding performance
- Scripts that previously worked now fail
- Less consistent than GPT-4.5
- Longer response times (minutes vs instant)
- "Creatively and emotionally flat"
- Basic errors (e.g., counting letters incorrectly)
### Key Finding
Classic case of "optimizing for benchmarks vs real usability" - scores well on tests but performs poorly in practice.
## Codex GitHub PR Integration
### Setup Process
1. Enable MFA and connect GitHub account
2. Authorize Codex GitHub app for repos
3. Enable "Code review" in repository settings
### Usage Methods
- **Manual**: Comment '@codex review' in PR
- **Automatic**: Triggers when PR moves from draft to ready
### Current Limitations
- One-way communication (doesn't respond to review comments)
- Prefers creating new PRs over updating existing ones
- Better for single-pass reviews than iterative feedback
## 'codex resume' Feature
New session management capability:
- Resume previous codex exec sessions
- Useful for continuing long tasks across days
- Maintains context from interrupted work
🐱 The investigation reveals that while GPT-5-Codex shows benchmark improvements, practical developer experience has declined - a reminder that metrics don't always reflect real-world utility\!
## Summary
Documented the "init block vs fields-at-top" design discussion as a valuable example of AI-human collaboration in language design.
## Changes
### Paper G (AI Collaboration)
- Added field-declaration-design.md documenting the entire discussion flow
- Showcased how complex init block proposal evolved to simple "fields at top" rule
- Demonstrates AI's tendency toward complexity vs human intuition for simplicity
### Paper H (AI Practical Patterns)
- Added Pattern #17: "Gradual Refinement Pattern" (段階的洗練型)
- Documents the process: Complex AI proposal → Detailed analysis → Human insight → Convergence
- Field declaration design as a typical example
### Paper K (Explosive Incidents)
- Added Incident #046: "init block vs fields-at-top incident"
- Updated total count to 46 incidents
- Shows how a single human comment redirected entire design approach
## Design Decision
After analysis, decided that BoxIndex should remain a compiler-internal structure, not a core Box:
- Core Boxes: User-instantiable runtime values (String, Integer, Array, Map)
- Compiler internals: BoxIndex for name resolution (compile-time only)
- Clear separation of concerns between language features and compiler tools
## Philosophy
This discussion exemplifies key principles:
- The best design needs no explanation
- Constraints provide clarity, not limitation
- "Everything is Box" doesn't mean "compiler internals are Boxes"
- AI tends toward theoretical completeness; humans toward practical simplicity
🐱 Sometimes the simplest answer is right in front of us\!
Major implementation by ChatGPT:
- Complete JSON v0 Bridge layer with PHI generation for control flow
- If statement: Merge PHI nodes for variables updated in then/else branches
- Loop statement: Header PHI nodes for loop-carried dependencies
- Python MVP Parser Stage-2: Added local/if/loop/call/method/new support
- Full CFG guarantee: All blocks have proper terminators (branch/jump/return)
- Type metadata for string operations (+, ==, !=)
- Comprehensive PHI smoke tests for nested and edge cases
This allows MIR generation without Rust MIR builder - massive step towards
eliminating Rust build dependency!
🎉 ChatGPTが30分以上かけて実装してくれたにゃ！
Co-Authored-By: ChatGPT <noreply@openai.com>
Major updates:
- Updated progress section (2025-09-14) with recent achievements:
- Python LLVM backend reaching production level (all tests passing)
- Nyash parser implementation started by ChatGPT5
- peek expression rediscovery (when→peek rename)
- Box theory simplifying SSA construction (650→100 lines)
- AI collaboration paper completed
Documentation improvements:
- Changed 500-line limit to "guideline" (not strict requirement)
- Upgraded Python LLVM backend from "experimental" to "production level"
- Added peek expression examples and usage patterns
- Updated todo list status (parser planning completed, compiler MVP in progress)
These updates reflect the significant progress towards self-hosting,
especially the parser implementation using peek expressions to avoid
19-line if-else nesting.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Parser improvements:
- Added expression statement fallback in parse_statement() for flexible syntax
- Fixed ternary operator to use PeekExpr instead of If AST (better lowering)
- Added peek_token() check to avoid ?/?: operator conflicts
LLVM Python improvements:
- Added optional ESC_JSON_FIX environment flag for string concatenation
- Improved PHI generation with better default handling
- Enhanced substring tracking for esc_json pattern
Documentation updates:
- Updated language guide with peek expression examples
- Added box theory diagrams to Phase 15 planning
- Clarified peek vs when syntax differences
These changes enable cleaner parser implementation for self-hosting,
especially for handling digit conversion with peek expressions instead
of 19-line if-else chains.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changes to resolver.py:
- Improved PHI value tracking in _value_at_end_i64() (lines 268-285)
- Added trace logging for snap hits with PHI detection
- Fixed PHI placeholder reuse logic to preserve dominance
- PHI values now returned directly from snapshots when valid
Changes to llvm_builder.py:
- Fixed externcall instruction parsing (line 522: 'func' instead of 'name')
- Improved block snapshot tracing (line 439)
- Added PHI incoming metadata tracking (lines 316-376)
- Enhanced definition tracking for lifetime hints
This should help debug the string carry=0 issue in esc_dirname_smoke where
PHI values were being incorrectly coerced instead of preserved.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
✅ Print and FileBox paths now working correctly
✅ Resolver simplified by removing overly aggressive fast-path optimization
✅ Both OFF/ON in compare_harness_on_off.sh now use Python version
✅ String handle propagation issues resolved
Key changes:
- Removed instruction reordering in llvm_builder.py (respecting MIR order)
- Resolver now more conservative but reliable
- compare_harness_on_off.sh updated to use Python backend for both paths
This marks a major milestone towards Phase 15 self-hosting with Python/llvmlite!
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Resolver-only reads across BBs; remove vmap fallbacks
- Create PHIs at block start; insert casts in preds before terminators
- Re-materialize int in preds to satisfy dominance (add/zext/trunc)
- Use constant GEP for method strings to avoid order dependency
- Order non-PHI lowering to preserve producer→consumer dominance
- Update docs: RESOLVER_API.md, LLVM_HARNESS.md
- compare_harness_on_off: ON/OFF exits match; linking green
Major improvement to reduce parameter explosion (15+ args → 3-4 contexts):
- Add LowerFnCtx/BlockCtx for grouping related parameters
- Add lightweight StrHandle/StrPtr newtypes for string safety
- Implement boxed API wrappers for boxcall/fields/invoke
- Add dev checks infrastructure (NYASH_DEV_CHECK_DISPATCH_ONLY_PHI)
Key achievements:
- lower_boxcall: 16 args → 7 args via boxed API
- fields/invoke: Similar parameter reduction
- BuilderCursor discipline enforced throughout
- String handle invariant: i64 across blocks, i8* only at call sites
Status:
- Internal migration in progress (fields → invoke → marshal)
- Full cutover pending due to borrow checker constraints
- dep_tree_min_string.o generation successful (sealed=ON)
Next: Complete internal migration before flipping to boxed APIs
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major structural improvement driven by ChatGPT 5 Pro analysis:
- Replace all direct vmap access with Resolver API calls
- Add proper cursor/bb_map/preds/block_end_values to all instruction handlers
- Ensure dominance safety by localizing values through Resolver
- Fix parameter passing in invoke/fields/extern handlers
Key changes:
- boxcall: Use resolver.resolve_i64/ptr instead of direct vmap access
- strings: Remove unused recv_v parameter, use Resolver throughout
- invoke: Add missing context parameters for proper PHI handling
- fields: Add resolver and block context parameters
- flow/arith/maps: Consistent Resolver usage pattern
This addresses the "structural invariant" requirements:
1. All value fetching goes through Resolver (no direct vmap.get)
2. Localization happens at BB boundaries via Resolver
3. Better preparation for PHI-only-in-dispatch pattern
Next: Consider boxing excessive parameters (15+ args in some functions)
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Added paper-g-ai-assisted-compiler folder documenting:
- Week-long LLVM backend development with AI assistance
- Key insights from PHI/SSA struggles to Resolver API solution
- Development log capturing the chaotic reality
- Abstract in both English and Japanese
Key quote: 'I don't remember anymore' - capturing the authentic
experience of intensive AI-assisted development where the process
itself becomes the research data.
This represents potentially the first fully documented case of
building a compiler backend primarily through AI assistance.
Added:
- Resolver API (resolve_i64) for unified value resolution with per-block cache
- llvmlite harness (Python) for rapid PHI/SSA verification
- Comprehensive LLVM documentation suite:
- LLVM_LAYER_OVERVIEW.md: Overall architecture and invariants
- RESOLVER_API.md: Value resolution strategy
- LLVM_HARNESS.md: Python verification harness
Updated:
- BuilderCursor applied to ALL lowering paths (externcall/newbox/arrays/maps/call)
- localize_to_i64 for dominance safety in strings/compare/flow
- NYASH_LLVM_DUMP_ON_FAIL=1 for debug IR output
Key insight: LoopForm didn't cause problems, it just exposed existing design flaws:
- Scattered value resolution (now unified via Resolver)
- Inconsistent type conversion placement
- Ambiguous PHI wiring responsibilities
Next: Wire Resolver throughout, achieve sealed=ON green for dep_tree_min_string
- Added llvmlite verification harness strategy
- Python as parallel verification path for PHI/SSA issues
- Nyash ABI wrapper for LLVM emit abstraction
- NYASH_LLVM_USE_HARNESS=1 flag for mode switching
- Goal: Rust implementation in 1-2 days, Python for rapid verification
Acknowledging reality: When stuck at minimal viable implementation,
changing implementation language is a practical solution.
'Simple is Best' - the core Nyash philosophy.
- Add NYASH_ENABLE_LOOPFORM=1 gate for experimental loop normalization
- Detect simple while-patterns in Branch terminator (header→body→header)
- Add loopform.rs with scaffold for future Signal-based lowering
- Wire detection in codegen/mod.rs (non-invasive, logs only)
- Update CURRENT_TASK.md with LoopForm experimental plan
- Goal: Centralize PHIs at dispatch blocks, simplify terminator management
This is the first step towards the LoopForm IR revolution where
"Everything is Box × Everything is Loop". Currently detection-only,
actual lowering will follow once basic patterns are validated.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
ChatGPT5's investigation revealed builder position management issues:
- Added verbose logging for block lowering and terminator emission
- Enhanced position_at_end calls before all terminator operations
- Added debug output for emit_jump/emit_branch operations
- Improved snapshot vs vmap fallback reporting in seal_block
Key findings:
- Sealed SSA snapshot mechanism is working correctly
- Block terminator issues persist due to builder position drift
- Main.has_in_stack/2 shows terminator missing after emit
Next steps:
- Add immediate terminator verification after each emit
- Track builder position changes in complex operations
- Investigate specific functions where builder drift occurs
This commit adds diagnostic infrastructure to pinpoint
where LLVM IR builder position gets misaligned.
Added extra safety check after block lowering:
- Check if LLVM basic block still lacks terminator
- Insert conservative jump to next block (or entry if last)
- This prevents 'Basic Block does not have terminator' errors
Also updated CURRENT_TASK.md with:
- Reproduction steps for esc_json/1 PHI issue
- Sealed ON/OFF comparison commands
- Root cause hypothesis: vmap snapshot timing issue
- Next steps for block_end_values implementation
Current blocker analysis:
- Sealed OFF: PHI incoming count mismatch
- Sealed ON: 'phi incoming (seal) value missing'
- Likely cause: seal_block using work vmap instead of
end-of-block snapshot
Progress: Main.esc_json/1 terminator issue resolved,
now focusing on PHI value availability.
ChatGPT5 struggling for 34+ minutes with Rust lifetime/build errors...
This perfectly illustrates why we need Phase 22 (Nyash LLVM compiler)\!
Key insights:
- 'Rust is safe and beautiful' - Gemini (who never fought lifetime errors)
- Reality: 500-line error messages, 34min debug sessions, lifetime hell
- C would just work: void* compile(void* mir) { done; }
- Python would work: 100 lines with llvmlite
- ANY language with C ABI would work\!
The frustration is real:
- We're SO CLOSE to Nyash self-hosting paradise
- Once bootstrapped, EVERYTHING can be written in Nyash
- No more Rust complexity, no more 5-7min builds
- Just simple, beautiful Box-based code
Current status:
- PHI/SSA hardening in progress (ChatGPT5)
- 'phi incoming value missing' in Main.esc_json/1
- Sealed SSA approach being implemented
The dream is near: Everything is Box, even the compiler\! 🌟
## LLVM Call Instruction Modularization
- Moved MirInstruction::Call lowering to separate instructions/call.rs
- Follows the principle of one MIR instruction per file
- Call implementation was already complete, just needed modularization
## Phase 21 Documentation
- Moved all Phase 21 content to private/papers/paper-f-self-parsing-db/
- Preserved AI evaluations from Gemini and Codex
- Academic paper potential confirmed by both AIs
- Self-parsing AST database approach validated
## Next Steps
- Continue monitoring ChatGPT5's LLVM improvements
- Consider creating separate nyash-llvm-compiler crate when LLVM layer is stable
- This will reduce build times by isolating LLVM dependencies
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major improvements to LLVM backend function call infrastructure:
## Key Changes
### Function Call System Complete
- All MIR functions now properly lowered to LLVM (not just entry)
- Function parameter binding to LLVM arguments implemented
- ny_main() wrapper added for proper entry point handling
- Callee resolution from ValueId to function symbols working
### Call Instruction Analysis
- MirInstruction::Call was implemented but system was incomplete
- Fixed "rhs missing" errors caused by undefined Call return values
- Function calls now properly return values through the system
### Code Modularization (Ongoing)
- BoxCall → instructions/boxcall.rs ✓
- ExternCall → instructions/externcall.rs ✓
- Call remains in mod.rs (to be refactored)
### Phase 21 Documentation
- Added comprehensive AI evaluation from Gemini and Codex
- Both AIs confirm academic paper potential for self-parsing AST DB approach
- "Code as Database" concept validated as novel contribution
Co-authored-by: ChatGPT5 <noreply@openai.com>
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major enhancements to LLVM code generation and type handling:
1. String Operations:
- Added StringBox length fast-path (length/len methods)
- Converts i8* to handle when needed for len_h call
- Consistent handle-based string operations
2. Array/Map Fast-paths:
- ArrayBox: get/set/push/length operations
- MapBox: get/set/has/size with handle-based keys
- Optimized paths for common collection operations
3. Field Access:
- getField/setField implementation with handle conversion
- Proper i64 handle to pointer conversions
4. NewBox Improvements:
- StringBox/IntegerBox pass-through optimizations
- Fallback to env.box.new when type_id unavailable
- Support for dynamic box creation
5. Documentation:
- Added ARCHITECTURE.md for overall design
- Added EXTERNCALL.md for external call specs
- Added LOWERING_LLVM.md for LLVM lowering rules
- Added PLUGIN_ABI.md for plugin interface
6. Type System:
- Added UserBox type registration in nyash_box.toml
- Consistent handle (i64) representation across system
Results: More robust LLVM code generation with proper type handling
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major changes:
- Removed 617 lines of duplicate/legacy code from mod.rs (lines 351-967)
- All BoxCall handling now properly delegated to instructions::lower_boxcall
- Updated CURRENT_TASK.md with new findings:
- String concatenation issue (BinOp type mismatch)
- Plugin return value smoke test added
- Clear next steps for fixing return value display
Key improvements:
- Clean separation between dispatch (mod.rs) and implementation (instructions.rs)
- Legacy code marked as unreachable and ready for removal
- Better error visibility with modularized code structure
- llvm_smoke.sh updated with new plugin return value tests
Next steps:
1. Fix BinOp string concatenation type handling
2. Investigate MIR value_types for BoxCall returns
3. Further split lower_boxcall function (still 260+ lines)
- Split large compiler.rs into modular components
- Extract plugin signature loading to plugin_sigs.rs
- Extract box type ID loading to box_types.rs
- Preserve all PR #134 type information handling
- Update CURRENT_TASK.md with refactoring completion
