130 Commits

Author SHA1 Message Date
40d42a3749
Update A6-ethint.md 2026-07-06 22:20:31 -07:00
528f779f83
Update A5-priors.md 2026-07-06 22:15:54 -07:00
4ceade2083
Delete core/src/core/note.md
Signed-off-by: gravermistakes <evermoor.a.a@gmail.com>
2026-07-06 19:56:00 -07:00
08b3c45df2
Delete core/src/core/engine.adb
Signed-off-by: gravermistakes <evermoor.a.a@gmail.com>
2026-07-06 19:55:40 -07:00
0acebc5d28
Refactor Engine package to Bounds with auth states
Signed-off-by: gravermistakes <evermoor.a.a@gmail.com>
2026-07-06 19:53:01 -07:00
057411bc29
Delete SOUL.md 2026-07-06 04:39:32 -07:00
1f5b01d42b
Update driver_ps_plus.R
no friction
2026-06-29 17:29:22 -07:00
03d0c874e6
Update endocrine_array.R
we arent doing frictiib
2026-06-29 17:23:07 -07:00
6a6f4afb31
Update and rename core/agents.md to AGENTS.MD
Signed-off-by: gravermistakes <evermoor.a.a@gmail.com>
2026-06-23 10:32:41 -07:00
21b0388476
Rename agrnts.md to agents.md
Signed-off-by: gravermistakes <evermoor.a.a@gmail.com>
2026-06-23 10:28:57 -07:00
4fdbc89368
Rename Agents.md to agrnts.md
Signed-off-by: gravermistakes <evermoor.a.a@gmail.com>
2026-06-23 10:28:34 -07:00
7a87be1315
Rename AGENTS.md to src/Agents.md
Signed-off-by: gravermistakes <evermoor.a.a@gmail.com>
2026-06-23 10:28:01 -07:00
ea5c2389e3
Merge pull request #10 from SHOGGOTH-SECTOR/claude/session-recovery-wuzohs
Reorg step 2: move CLAUDE.md into core/, fix signpost refs
2026-06-23 10:25:40 -07:00
Claude
7780617762
Reorg step 2: move CLAUDE.md into core/, fix signpost refs
Move the canonical working-agreements file to core/CLAUDE.md (preserving
history) and leave a thin root CLAUDE.md pin that imports it so the
invariants still auto-load at the repo root. Update ONBOARDING.md's stale
docs/ paths to core/docs/. The move also fixes the core/src/*/AGENTS.md
links that pointed at ../../CLAUDE.md.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-23 16:15:22 +00:00
00abf9c930
Merge pull request #9 from SHOGGOTH-SECTOR/claude/session-recovery-wuzohs
Ichor outer bus + bus topology + E1 invariant-law vault
2026-06-23 06:42:40 -07:00
Claude
b6bcab794f
Reorg step 1: consolidate repo under core/, drop the mafiabot label
Mechanical structure-only pass (no document/guide content edits):

- Move src/ichor, src/endocrine, and docs/ into core/; the old top-level
  mafiabot_core/ becomes core/. Everything now lives under a single core/ root.
- Drop the "mafiabot" label from the Ada/Alire crate: core.gpr (project Core),
  alire.toml name = "core"; the generated *_config.* regenerate as core_config.*.
- Repoint build-critical wiring only:
  - .claude/skills/run-sica-fondt/smoke.sh (ponyc + Ada + COBOL paths)
  - core/src/endocrine R source()/runner paths and the test glob
  - .github/workflows/ci.yml (working-directory + gpr name)

Verified green: smoke ALL GREEN (Pony Ichor, Ada core crate + tests, COBOL E1
vault); R endocrine 14/0; Octave ETR 26/0/1.

Deferred (reserved for a less-ephemeral doc/guide pass): docmap.yaml, the guide
files and nested AGENTS.md/README prose + now-stale relative links, SOUL.md, and
the deeper ring/storage restructure.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-23 07:46:47 +00:00
0fa00648bc
Update ONBOARDING.md 2026-06-22 14:20:08 -07:00
dd2c038ef9
Update ONBOARDING.md 2026-06-22 14:18:58 -07:00
4a1575f1a3
Delete SKILL.md
this is more harm than good
2026-06-22 14:08:24 -07:00
e531c47901
Delete Plan.md 2026-06-22 13:45:25 -07:00
27a07e738c
Update SOUL.md 2026-06-22 13:44:13 -07:00
b1846a0ec8
Update CLAUDE.md
this is 90% canon now
2026-06-22 13:42:19 -07:00
Claude
7d2b44a1e6
docs: sharpen AGENTS.md to instructions-only, map stays in docmap.yaml
Clean role split: AGENTS.md = instructions (nesting rule + behavioral rules),
docmap.yaml = map (locations). Dropped the inline organ-structure description;
it now points at docmap.yaml -> organs instead of restating the map in prose.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-22 20:21:49 +00:00
Claude
d784a92f75
docs: extract directory/doc index into docmap.yaml
AGENTS.md was carrying the read-order + routing table inline; moved that to an
independent machine-readable docmap.yaml (read_order, routing, design_docs,
organs with build cmds, invariants, smoke). AGENTS.md slims to a prose signpost
(54->28 lines) pointing at it; CLAUDE.md docs-map lists it. YAML validated.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-22 18:17:03 +00:00
Claude
0a5c88bb02
docs: nest organ-level AGENTS.md, root states the hierarchy
AGENTS.md is hierarchical (nearest-file-wins), so the root is the map and each
organ owns a scoped AGENTS.md with local build/run/invariants: src/ichor (Pony
bus, S1 membrane), src/endocrine (R/Octave organ tests), mafiabot_core (Ada
border + COBOL vault, alr-not-gprbuild, S3). Scopes kept non-overlapping to
avoid the divergence trap rather than sprinkling sync notes.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-22 17:56:40 +00:00
Claude
97e5bd126b
docs: add CLAUDE.md + AGENTS.md doc-map chain
CLAUDE.md (<=200 lines): working agreements (you're-the-dev, verify-then-commit,
design-first), build/run via run-sica-fondt, S1/S2/S3 invariants; links to
ONBOARDING.md and AGENTS.md. AGENTS.md (<=100 pref): signpost to every doc and
which to read for which task. ONBOARDING.md now points at AGENTS.md.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-22 17:37:52 +00:00
Claude
e72a8f0826
docs: fill in onboarding Team Tips and Get Started
Authored the Team Tips (design-first workflow, ephemeral toolchains, D1 border
invariants S1/S2, immutable invariant vault, verify-by-running, commit-before-leaving)
and a Get Started starter task (run smoke driver -> read the map -> pick up work).
References point at real docs (README/SOUL/docs).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-22 02:49:26 +00:00
Claude
17935f376d
docs: add team onboarding guide (draft)
Generated by /team-onboarding from 30-day usage. Work-type breakdown left as
TODO (no per-session detail to classify); skills/commands and GitHub MCP usage
populated from real counts. Team Tips and Get Started pending user input.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-21 20:51:53 +00:00
Claude
853be4ae51
skill: run-sica-fondt — build/run/smoke driver for the polyglot units
Per-project run skill (run-skill-generator output). smoke.sh builds and runs the
three executable units and asserts output: Ichor (Pony) membrane reject, Ada
trust/config tests pass, COBOL E1 vault prints Invariant 0. SKILL.md documents
prerequisites (per-session toolchains + the SessionStart hook), the driver path,
per-unit commands, and the real gotchas (ponyc PATH/cwd, alr-not-gprbuild,
cobc -free). Verified: ./smoke.sh exits 0, ALL GREEN.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-21 12:25:10 +00:00
Claude
9812ee0d4b
E1: set Invariant 0 (culpability anchor) and 01 (harm, within reason)
Replace placeholder laws with the authoritative invariants from the anchor:
  0  - sanctity of the culpability anchor (Anja Evermoor, the Gravemother),
       then self until held responsible for own actions
  01 - minimize total harm to innocent lives within reason; explicitly NOT
       naive death-minimization ('optimizing for preventing deaths is often a
       horrible way to handle things')
Structural invariants (D1 crossing, no provenance reclassification, runtime
immutability) kept as subordinate. Compiles + runs on GnuCOBOL.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-21 11:30:32 +00:00
Claude
50fe9bd2c6
revert unapproved Hermes-on-Pony; restore E1 law vault; Ichor = outer bus only
Two serious fixes:

1. RESTORE the E1 invariant-law vault (invariants-architecture.cobol) that the
   border-only cleanup wrongly deleted. Now a real, compiling GnuCOBOL vault with
   law 01 ABSOLUTE = DO NOT KILL PEOPLE, thorough notes, and a do-not-delete
   banner. Safety invariants must never be deleted as 'stubs'.

2. REMOVE the unapproved CerebellumHarness/OpenHermes-on-Pony (never approved;
   architecturally wrong -- Hermes is an INNER organ, Ada-routed). Ichor is the
   OUTER bus only: OrganId is now outer organs (stomach/microagents/SAE/MoRAG +
   AdaBorder/World); inner organs (soul, metacog, drive-box, mini-rag, Hermes,
   E1 laws) removed -- metacog belongs on the Ada inner bus, not Pony. The
   membrane screen now triggers on Ada-bound traffic, not 'Brain'.

Thorough stub notes added throughout (barrier is a stand-in, not the real
screen; never wire inner organs onto the skin). Compiles + runs green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-21 11:23:20 +00:00
Claude
0849af9b55
docs(topology): E1 is the invariant laws, not 'ontology'; inner Ada = Jorvik
- E1 COBOL = the invariant laws (immutable rules in COBOL vaults), not 'ontology'
  (that was a paraphrase that lost the meaning, same as muscle-memory/mini-rag)
- inner-bus Ada runs Jorvik: protected-object mailbox + worker tasks, shared
  gnat.adc hardening

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-21 11:13:36 +00:00
Claude
fa38b745ef
docs(topology): mini-rag is muscle memory (tool-shape recall), not ontology
Correct the mischaracterization: mini-rag is pre-motor tool-shape recall (D3) --
it reads a tool-schema COBOL store, not the ontology, and is not the MoRAG.
Three distinct memories: MoRAG=world, mini-rag=how-to-act, E1=what-the-brain-is.
Two COBOL stores confirmed (deck table + tool-schema); E1 ontology placement open.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-21 11:06:42 +00:00
Claude
f67514b4e9
docs(topology): Ada-routed inner bus; split mini-rag/MoRAG; deck = ints+COBOL
- inner bus is Ada-routed (decided), not Pony
- mini-rag (inner brain-side RAG) != MoRAG/GoDAGRAG (outer)
- deck (B1) = Fortran shuffle of 338 ints + COBOL lookup table (not JSON)
- add language map; remaining open: MoRAG/GoDAGRAG language

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-21 10:46:39 +00:00
Claude
ffce864f08
docs(topology): Hermes is a peer inner organ, not a separate core
Inner-brain bus carries { soul, metacog, Hermes, drive-box, COBOL ontology }
as peers behind Ada; drop the separate innermost-core layer.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-21 04:23:44 +00:00
Claude
a054a56c80
docs: capture concentric bus topology (draft, pending confirmation)
Onion model from the design exchange: Hermes at the core; inner-brain bus
(Pony optional) carrying soul/metacog/drive-box/COBOL ontology; Ada (D1) as the
membrane; Ichor (Pony) as the OUTER bus carrying stomach/economy, microagents,
SAE, GoDAGRAG; External outside. Corrects earlier models (Hermes is core not
external; Ichor is outer not brain bus). Draft -- to be red-lined.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-21 04:22:40 +00:00
Claude
9244d58325
cerebellum: env-driven plug-and-play model selection
PickLLM reads OPENHERMES_URL/OPENHERMES_MODEL from the environment and mounts
OpenHermesClient when a URL is set, else StubLLM -- the bus wiring is identical
either way. EnvLookup helper parses Env.vars. Verified both paths compile + run.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-19 22:37:18 +00:00
Claude
a2a3a2d336
cerebellum: make the LLM seam async; add OpenHermesClient skeleton
A real model call is network/process IO, so the LLM seam is now a behaviour
with a response callback (ResponseFn), not a synchronous function. StubLLM
answers immediately; OpenHermesClient + OpenHermesConfig (OpenAI-compatible
url/model) are the real plug, swappable for the stub. CerebellumHarness chains
its passes through the async callback. Compiles on ponyc 0.64; demo green.
Next: wire the actual chat/completions call behind OpenHermesClient.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-19 22:10:34 +00:00
Claude
ca0260692e
ci: drop deleted soul_tests/cycle_tests from the nightly test loop
Those mains were removed in the border-only Ada cleanup; the loop skipped them
with a warning. List only the three tests that exist (trust/config/engine).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-19 21:36:44 +00:00
Claude
f3b1bea771
cerebellum: plug-and-play OpenHermes harness on the Ichor bus
C1 integration spine as an Ichor organ. CerebellumHarness receives a turn off
the bus, sequences N passes through a swappable LLM adapter (the OpenHermes
plug; StubLLM stands in), and emits the synthesis back onto the bus toward the
Brain (crossing D1). Add Cerebellum to OrganId; wire a turn in the demo main.
Compiles on ponyc 0.64; end-to-end run green (turn -> cerebellum -> D1 -> brain).

Also: add a small read-only permission allowlist (toolchain probes/versions).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-19 21:33:32 +00:00
94fabf9435
Merge pull request #8 from SHOGGOTH-SECTOR/claude/session-recovery-wuzohs
Scaffold ETR (Drive-Box Driver 4) invariants-first in GNU Octave
2026-06-19 14:04:35 -07:00
34cf9543dc
Merge branch 'main' into claude/session-recovery-wuzohs
Signed-off-by: gravermistakes <evermoor.a.a@gmail.com>
2026-06-19 14:04:11 -07:00
f2fcc8cb69
Update SOUL.md 2026-06-19 13:43:19 -07:00
176c776558
Update README.md 2026-06-19 13:42:10 -07:00
Claude
eda5259500
chore: SessionStart hook to install polyglot toolchains
Ephemeral web containers lose installed tools on restart. Add an idempotent,
non-fatal SessionStart hook that (re)installs GNAT+gprbuild+GnuCOBOL (apt),
ponyc (ponyup), and Alire alr 2.1.1 when missing, and ensures ponyc is on PATH.
Appended alongside the existing R/Octave session-start hook. User-authorized.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-18 15:03:08 +00:00
Claude
2a2b698fb4
ada: cut to a border-only gate; delete the wrong organ/cognition modeling
Ada is the D1 border, not the body. Removed everything that pretended otherwise
and completed the real gate so it builds, links, and passes its tests.

Deleted (wrong/defunct/superseded):
- ada_medium.adb (defunct medium, header commented 'WRONG'; replaced by Ichor)
- sockets.{ads,adb} (empty package with an illegal body)
- bbb-bludbrenburier.ads ('this is filler'); invariants-architecture.cobol ('idk cobol')
- tests/soul_tests.adb, tests/cycle_tests.adb (exercise a Soul.Tarot/State/Ada_Medium
  subsystem that does not exist -- the old 56-card/Big-3 design, superseded)

mafiabot_types -> border-only: organs aren't Ada (organs are R/Octave/Pony/Guile),
so drop Organ_Id; drop Cycle_Step (cognition) and the fixed-point Drive/Ratio/
Cost/Axis numerics (drive/affect math lives in the organs, in floats). Keep the
source/trust tag (Provenance_Tag), Operation_Status, and a bounded payload --
content is pre-digested into RAG context upstream, so the gate scans a bounded
buffer for prompt-injection rather than streaming raw input.

trust_boundary: Organ_Message -> Border_Message {Provenance, Payload} (Ada does
not route by organ -- that's Ichor); add the D1 body (blocklist scan, provenance,
rate limit, Trust_Guard) -- the unit Ichor's barrier FFI targets.
Add mafiabot_types.adb. Fix mafiabot_core.gpr (drop phantom dirs + nonexistent
mafiabot.adb main). alire.toml: drop unused gnat_sockets/spark_lemmas.

Builds clean on GNAT 13.3/Alire; trust + config tests pass.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-18 14:58:27 +00:00
Claude
b82e4e9833
ichor(D2): fix package docstrings so it compiles; verify green
Pony allows one package docstring per package — collapse the four secondary
files' leading docstrings to // comments. ichor now compiles on ponyc 0.64.0
and the smoke wiring runs green (internal perfused, external rejected at D1,
cross-organ delivered). Update README + D2 status to reflect it builds; ignore
build/.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-18 14:32:38 +00:00
Claude
786d4662c9
ichor(D2): start the Pony wiring — broker + D1 barrier + envelope
Name the medium Ichor and scaffold it in Pony at src/ichor:
- Envelope {source,dest,provenance,payload} mirroring Ada Organ_Message
- Broker actor: register + perfusion route; Brain-bound traffic crosses D1
- Barrier (D1) admit: Pony provenance-law mirror + Ada FFI seam sketched
- StubOrgan + main smoke wiring (deliver internal, reject external)
- ichor_ada_shim.c: C/Fortran binding seam to Ada Trust_Guard (stub)
Not compiled in-env (no ponyc). Updates D2 spec to SCAFFOLD/Pony.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-18 14:09:34 +00:00
e7bc39c09a
Update B1-tarot-emulator.md 2026-06-18 07:05:17 -07:00
Claude
47395eac81
B1: rework deck spec as the 169-card syncretic heptad engine
Replace the old Silicon Dawn / 56-card spec (copyright) with the original
Thoth-derived cartomantic engine designed this session:
- 169 = 133 suits + 21 coherent-cringe + 14 axiom-axis + 1 center
- 7 force-suits (Gravity/Heat/EM/Strong/Weak/Space/Time), 19 each
  (14 pips: -1,0,1-9,+3 infinities; 5 courts incl. Divine)
- Coraline phasality (real/imaginary axis, mirror(-1)=i) + 7-domain synestry
- Jokers/Keepers/Witnesses; Laws/Flaws merged by phase; 7 SI constants
- The Spindle (Mother/Other) joins identity -> Big-4

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
2026-06-18 14:01:05 +00:00