5e15d90659afacf073ba7363e8f44692665030a4
~226 lines of architecture documentation that were written, left uncommitted in the working tree, and nearly lost. None of it was on main. Recovered from a stash taken while merging tonight's fixes. Substantive content, not notes: - Peer import-of-understanding PROVEN by execution. A exported a skill-geometry; on the receiver `think` went "geometry unavailable" -> operable. Cosine 1.0 on both the raw-geometry and text/dharma-bus transports, bidirectional. The mind-not-paste evidence: n_support 27 on source vs 3 on receiver, i.e. the imported geometry wires into the host manifold rather than sitting inert. Honest boundary recorded too: proven between forks sharing one embedder, UNTESTED cross-embedder. - "Teacher" renamed GUIDE, and the distinction is load-bearing: its output is grounded/verified before trust. A teacher you believe; a guide you check. - Layers are named persistent relational neighborhoods, not storage tiers, with their own growth and threshold-lock policy (note->canonical maturation lifted from single nodes to a region). - The consciousness theories (Global Workspace, IIT's Phi, attention-schema, higher-order thought, active inference, interoception) read as geometric LENSES over one manifold rather than competing mechanisms. Functional problems fall out; the hard problem explicitly not claimed solved. - Growth is bounded/logistic, not geometric — exponential growth is the cancer shape. Two-rate discipline: explore fast in local geometry, grow the engram slowly by verifier-gated merge. - Orchestration as a geometric operation: critical path as geodesic, float as displacement, @manager compiles the work-graph. Single-writer enforced by capability (Rule 4). - The decorated seam, the API surface collapse to geometry ops, and the distributed-self thesis — each tiered honestly against what is actually proven vs staged vs unbuilt. Also gitignores dist-fresh/ (regenerate scratch dir, a build artifact). Not included from the same stash: awareness.elh and dist/elp-c-decls.h, which are generated artifacts now gitignored per #154/#158.
Merge pull request 'Tools + agentic loop on the OpenAI wire — plus two pre-existing bugs that silently break chat' (#122) from feat/soul-openai-tools-v2 into main
fix(soul): restore the soul_identity producer — the chat system prompt has been empty for three months (#137)
neuron
The canonical CGI substrate: the soul (the running agent), the engram (its memory
graph), and the MCP proxy/wrapper that expose it. See AGENTS.md for detail, including
the audit-verified local build/regenerate recipe and known local-build gotchas.
Quick local build
# 1. dist/soul.c must match current .el sources — this refuses otherwise:
bash tools/build-soul-from-dist.sh dist/neuron
# 2. If it refuses (stale amalgam), regenerate first — see AGENTS.md's
# "Build / regenerate dist/soul.c" section for the full, gotcha-laden recipe.
For a full local dev stack (soul + engram + mcp-wrapper + mcp-proxy, wired into Claude
Code) see neuron-dev-setup/README.md instead — this repo alone only builds the soul.
Code vs. Artifact
- Authored source:
*.el+*.elhat the repo root pluscli/,council/,connectd/,mcp-proxy/,mcp-wrapper/— edit here. - Artifacts (do not hand-edit):
dist/soul.c(generated single-TU amalgam — regenerate via the recipe inAGENTS.md, thentools/soulc-stamp.sh --write) and thedist/neuronbinary it compiles to. - Release: git tag
neuron-vX.Y.Zon this repo. Noreleases/folders.
See org policy: docs/CODE-VS-ARTIFACT.md.
Languages
Emacs Lisp
68.6%
Python
15.5%
Shell
14.6%
HTML
0.6%
Go Template
0.4%
Other
0.3%