- Finalized Reflection Loop: Injected deterministic rejection traces back into LLM prompts.
- Hardened Actuators: Added path-traversal guards and enforced Merkle snapshots on AST edits.
- Refactored Lisp Utils: Merged validator/repair into a unified utility skill with whitelist Ast-walking.
- Fixed Build: Resolved all 30+ syntax, scoping, and package visibility errors.
- Verified: Full pass (100%) on all 5 core test suites.
- Hardened actuators: Fixed path-traversal vulnerabilities in file I/O tools and blocked .org files from regex replacements to force AST usage. Enforced Merkle snapshots on AST edits.
- Implemented Reflection Loops: Injected rejection traces from deterministic gates back into the LLM context to enable autonomous self-correction.
- Finalized tool permission tiers (ask/allow/deny) with proper LLM prompt filtering.
- Updated all 150+ :tangle headers across harness/ and skills/ to use elisp (expand-file-name) to target INSTALL_DIR dynamically.
- Cleaned up environment/ directory depth by moving memory-image.lisp to state/.
- Moved test scripts to tests/ and deleted redundant chat scripts.
- Add test suites inline in harness/communication.org
- Add test suites inline in harness/perceive.org, reason.org, act.org
- Add test suites inline in harness/skills.org, memory.org, loop.org
- Tests now live alongside code, not in separate .lisp files
- Each test block has prose explaining its purpose
Test results: 84/84 pass (100%)
- loop.org: Explain metabolic pipeline, error recovery, heartbeat
- reason.org: Document dual-engine architecture (probabilistic + deterministic)
- act.org: Detail actuation, actuator pattern, feedback loop
- perceive.org: Explain signal normalization, async vs sync processing
- manifest.org: Add ASDF system design, boundary contract
Each function now has its own code block with detailed docstrings explaining:
- What the function does
- Why it was designed that way
- How it fits into the larger system
- Parameter descriptions
- Return values
