Captures two carve-outs to aish's "non-PR-flow repo" default:
- Feature requests and bugs go to git.reauktion.de/marfrit/aish/issues
rather than direct-implement-in-band. Tag `architecture` for cross-
phase concerns. Aligns with the fleet-wide bug-filing convention from
the `his` cheatsheet; this row extends it to features for aish.
- Review-required iteration opens a PR (authored as claude-<host>,
marfrit reviews, self-approval forbidden). PR #1 was the precedent.
Both are opt-in; direct-to-main remains the default for autonomous
work that doesn't need a feedback loop.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Captures three findings from the review of 013c625 ("phase0 amendment:
insert MCP phase 2"). Opening as a PR rather than direct-to-main: the
non-PR-flow convention works fine for autonomous work, but feedback-
required iteration needs a readable medium that isn't the Claude Code
transcript.
§11 phase 2 row: spell out two scope items the original row left implicit —
the system-prompt rewrite to declare the tools schema (Phase 0's `CMD:`
contract is hard-coded into the prompt) and `safety.lua` extension to
gate tool calls (per Q8).
§13 Q6: explicit note that choosing "retire `CMD:`" requires a §3
invariant amendment in the same commit — keeps the substrate-vs-phase
boundary honest. Adds (§3 if retiring) to the impact column.
§13 Q9 (new): MCP system-prompt augmentation locus — static block in
broker.lua / per-request assembly from connected servers / hybrid.
Real architectural call with token-cost tradeoff per option.
§13 Q10 (new): tool-call streaming vs the Phase 1 SSE substrate —
phase-ordering question. Either Phase 2 lands on the blocking Phase 0
broker and refits when SSE arrives, or Phase 1 SSE moves before MCP
so tool-call deltas stream from day one.
MCP/tool-calling lands as a distinct phase, before Norris mode so the
autonomous planner has tools as substrate. lmcp speaks MCP standard
JSON-RPC 2.0 over HTTP/SSE — fits the existing libcurl FFI plan; tool
calls ride the OpenAI-compatible `tools` field on /v1/chat/completions,
so the §6 broker contract is unchanged at the transport level.
§8: tokenization concern bumped Phase 2 → Phase 3 (still tracks Norris).
§11: Norris→3, memory→4, routing→5, tree-sitter→6.
§13: Q1/Q2/Q3/Q5 phase numbers tracked the renumber; added Q6 (CMD: vs
tools coexistence), Q7 (server discovery), Q8 (tool-call auth gate).
No §3 invariant broken. No code touched — Phase 0 implementation per
the locked manifest is still the next move.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
README is now self-contained for a human reader landing on the repo cold:
project value-prop, status, quick-orientation reading order, directory
layout, build/runtime deps, run + config invocation, and a pointer to
CLAUDE.md for contribution norms.
CLAUDE.md is rewritten as the substrate a fresh Claude session needs to
pick up Phase 0→1 implementation without prior conversation context:
- Reading order (PHASE0.md → README → config.lua)
- Phase-loop discipline (8+1 with loopbacks)
- Eight invariants from PHASE0.md called out as non-negotiable without
manifest amendment
- Bottom-up implementation order for Phase 0 (libc → readline → curl →
context → executor → router → broker → renderer → repl → main)
- Testing approach without a test framework
- Open question on JSON library (dkjson recommended; needs §3 amendment)
- Ambiguity handling pattern (ask vs log-in-§13 vs stop-and-ask)
- Commit style + Co-Authored-By trailer template
- Model-class caveat: small Q4 coder models have output variance, validate
before exec, confirm_cmd defaults exist for this reason
- Push credential note for sessions without ssh-keys-on-Gitea
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- README, .gitignore, CLAUDE.md (project conventions)
- docs/PHASE0.md — full Phase 0 manifest (locked substrate)
- 10 root .lua modules + 4 ffi/ bindings, all stubs raising NotImplemented
with module-scoped responsibilities matching the manifest
- config.lua wired to current dirac/hossenfelder endpoints (qwen-coder-7b
snappy/32k + cloud via OpenRouter through hossenfelder)
File names match docs/PHASE0.md §4 exactly. Module bodies fill in across
later phases; the tree shape is locked.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
marfrit
claude-noether