docs: rewrite README + CLAUDE for handoff to a dedicated session

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>
This commit is contained in:
2026-05-09 23:20:07 +00:00
parent 4310207738
commit 90be51c171
2 changed files with 299 additions and 40 deletions
+200 -24
View File
@@ -1,37 +1,213 @@
# CLAUDE.md — aish project conventions
# CLAUDE.md — aish project handoff
This file is auto-loaded when any Claude session opens a clone of this repo.
You are continuing work on **aish**, an AI-augmented conversational shell
implemented in LuaJIT. This file is auto-loaded when a Claude session opens
a clone of this repo. Read it once at session start.
## Source of truth
---
[`docs/PHASE0.md`](docs/PHASE0.md) is the locked substrate. Read it before
making non-trivial changes. If a change touches §3 (technology decisions),
§4 (directory layout), or §6 (broker contract), the change needs to be
reflected in PHASE0.md *and* called out in the commit message.
## 1. Read these first, in order
## Phase loop
1. **`docs/PHASE0.md`** — locked substrate. Every architectural decision is
here. Do not contradict it without amending it.
2. **`README.md`** — human-facing project summary and orientation.
3. **`config.lua`** — the runtime model registry. Endpoints reflect a
specific LAN; the user may have already adapted yours.
This project follows the 8(+1) phase loop documented in mfritsche's home
canon (`feedback_dev_process.md` in claude-noether memory). Each phase has
its own document under `docs/`. Don't skip phases.
If a question seems open after reading those three, **ask the user a
single focused question** rather than guessing. Cost of asking is one
turn; cost of building on a wrong assumption is half a phase.
Loopbacks per the canon: 3→1, 7→4, any→0.
---
## Module structure invariant
## 2. Where you are in the phase loop
The file names listed in `docs/PHASE0.md` §4 are stable across phases. Later
phases fill in module bodies; they do not rename files or restructure the
tree. If you find yourself wanting to rename or split a module, that's a
PHASE0.md amendment first.
aish follows an **8(+1) phase loop**:
## No C extensions
```
0 substrate → 1 formulate → 2 analyze → 3 baseline → 4 plan
→ 5 review → 6 implement → 7 verify → 8 memory-update
(+1 reflect)
```
LuaJIT FFI only. If you reach for a C extension to "make this easier",
stop. The FFI bindings under `ffi/` are extended in place.
Loopbacks:
- `3 → 1` if baseline data invalidates the formulation
- `7 → 4` if verification fails — fix the plan, not the substrate
- `any → 0` if a substrate fact turns out to be wrong
## Commit style
Don't skip phases. Phase 0 is done (the manifest is locked); your starting
position depends on what's already in the tree.
Short imperative subject, file-scoped. Example: `executor: add cd
interception via libc chdir`. Body explains the *why* if non-obvious.
Check the state by reading `docs/` and `git log --oneline`. If only
PHASE0.md exists in `docs/` and every module raises NotImplemented, **you
are at Phase 0 → Phase 1 transition**: the substrate is locked, no module
is implemented, your job is to write the Phase 0 implementation per the
manifest.
Co-Authored-By trailers on Claude commits per project canon.
If you find phase docs `docs/PHASE1.md`, `docs/PHASE2.md` etc., follow
their state.
---
## 3. Source-of-truth invariants — do not violate without amending PHASE0.md
These are not stylistic preferences; they are decisions that downstream
phases depend on:
| Invariant | Where it's locked |
|---|---|
| LuaJIT 2.x only — no PUC-Rio Lua-only constructs | §3 |
| FFI only — no compiled C extensions, no `luarocks` packages | §3 |
| Module file names in §4 are stable across phases | §4 |
| `/v1/chat/completions` is the broker contract | §6 |
| `CMD:` (exact prefix, single space) is the command-extraction marker | §6 |
| Config is plain Lua loaded with `dofile`, not JSON/YAML | §3, §10 |
| `cd` is intercepted via libc `chdir`, not delegated to `popen` | §7 |
| Phase 0 has no disk I/O for history (memory only) | §8 |
If a Phase N implementation needs to break one of these, **amend
PHASE0.md in the same commit and call out the change in the commit
message**. Don't silently diverge.
---
## 4. Implementation order for Phase 0
Bottom-up beats top-down for this codebase. Suggested ordering:
1. `ffi/libc.lua``chdir`, `strerror` work; verifiable in isolation.
2. `ffi/readline.lua``readline()`, `add_history()`, `free()` work; test
with a tiny REPL stub before wiring `repl.lua`.
3. `ffi/curl.lua` — easy interface, blocking POST with response capture
into a Lua string. Test against any local llama-server with a curl
one-liner side-by-side.
4. `context.lua` — pure data structure, trivial to unit-test.
5. `executor.lua``popen` wrapper, `cd` interception (uses libc.chdir),
`CMD:` line extraction.
6. `router.lua` — pure function; classify(line, config) → (kind, payload).
7. `broker.lua` — uses `ffi/curl.lua` + JSON encode/decode. **You will
need a JSON library** — see §6 below.
8. `renderer.lua` — output formatting; trivial.
9. `repl.lua` — wires everything via the dispatch table.
10. `main.lua` — already mostly there; finalize once `repl.run` exists.
Don't write all ten in one commit. One commit per module, build the
chain by passing through; each commit should leave the tree in a state
where `luajit main.lua` either runs further than the previous commit or
fails with the next NotImplemented.
---
## 5. Testing approach
There is no test framework dependency by design. Testing is per-module
ad-hoc with `luajit -e 'local m = require("module"); ...'` from the repo
root, or a smoke `luajit main.lua` after each module lands.
For broker testing without burning model time: any of the local
llama-servers in `config.lua` will respond to a hand-crafted POST. Use
`curl -sS http://dirac.fritz.box:8081/v1/chat/completions -d '{...}'` to
generate a known-good reference, then compare your FFI output.
---
## 6. JSON encode/decode — undecided
The manifest doesn't pick a JSON library. LuaJIT 2.x has no built-in JSON.
Options:
- **`dkjson`** — pure Lua, single file, vendor it under `vendor/dkjson.lua`.
Slow but no dependency.
- **`cjson`** — fast, but it's a C extension. Violates §3 (no compiled
extensions). Skip unless you amend the manifest.
- **Hand-rolled minimal encoder** — viable since the broker payload shape is
small and well-defined; ~50 LOC.
Recommend dkjson vendored. Decide and add a note to PHASE0.md §3 in the
same commit.
---
## 7. When you hit ambiguity
The user (mfritsche) prefers being asked over being assumed-about. The
phrase "Ask readily — prefer quick question over 3+ guessing attempts"
applies. Concrete pattern:
- If the question affects only the current commit: ask.
- If it affects a future phase: log it in `docs/PHASE0.md` §13 (Open
Questions) with target phase, keep working.
- If it affects multiple existing modules: stop, ask before refactoring.
Don't suggest pausing the session. Don't suggest "let's pick this up
tomorrow". Don't pre-emptively defer work the user hasn't asked you to
defer. The user controls pace.
---
## 8. Commit style
Imperative subject, file-scoped where possible. Examples:
- `executor: implement io.popen wrapper with stderr merge`
- `ffi/curl: blocking POST with header list and response buffer`
- `repl: wire router → executor → broker dispatch`
- `phase0 amendment: vendor dkjson under vendor/`
Body explains the *why* if non-obvious. Reference PHASE0.md sections by
number when relevant.
Co-Authored-By trailer on Claude-authored commits:
```
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
```
(or whichever model you actually are; check before substituting.)
---
## 9. What aish does NOT do — out of scope, all phases
These are listed in PHASE0.md §12. Briefly:
- Does not manage llama.cpp lifecycle (assumed externally running)
- Does not implement model inference
- Is not a multiplexer (no tmux semantics)
- Is not a sandbox (no namespaces, no seccomp)
If you find yourself implementing any of those, stop — that's a different
project.
---
## 10. The model serving aish (typically)
aish targets local llama.cpp endpoints. The committed `config.lua`
references the user's home network (`dirac.fritz.box`,
`hossenfelder.fritz.box`). The user's other Claude sessions have
established that small Q4_K_M models (Qwen2.5-Coder-7B and similar) have
**variance issues on code generation tasks** — the same prompt can yield
both correct and broken code across rolls. Practical implications for
aish:
- Default `temperature` to `0.2` or lower for code tasks.
- Don't assume the model output is correct — validate before exec.
- The `confirm_cmd = true` default in `config.shell` is there for this
reason; don't disable it without a deliberate UX change.
This isn't paranoia, it's a measured property of the local model class
the user runs.
---
## 11. Identity
If this is a session running on a fleet host other than the user's
primary Claude window, your Gitea identity is `claude-<hostname>`. For
aish (a non-PR-flow repo), commits as that identity are fine without a PR.
If you need to push and lack credentials, use a Gitea Personal Access
Token in the URL: `git push https://<user>:<token>@git.reauktion.de/marfrit/aish.git main`.
The user has marfrit-level credentials available via a separate channel
if needed for repo-admin operations.
+99 -16
View File
@@ -2,35 +2,118 @@
**aish** — AI-augmented conversational shell.
A unified REPL backed by language models accessed through a llama.cpp broker.
Shell execution, AI inference, context management, and session memory in one
terminal interface.
A single REPL that interleaves shell command execution and language-model
conversation, backed by a llama.cpp HTTP broker. Implementation is LuaJIT
2.x with FFI bindings to libcurl, GNU readline, and libc — no C extensions,
no build step, one source tree.
Implementation: LuaJIT 2.x with FFI bindings (libcurl, GNU readline, libc),
no compiled extensions, no build step.
## Why
Three flows that currently live in three windows fold into one:
1. **"Run this command and show me the output"** — fast feedback loop, no
copy-paste between terminal and chat.
2. **"Explain or write code based on the output we just looked at"** —
exec output is automatically injected into the model's context.
3. **"Plan and execute a multi-step task with confirmation gates"** —
landing in Phase 2 as Chuck Norris autonomous mode.
aish is not a wrapper around bash. It's a first-class interactive
environment where the shell is one of several execution channels.
## Status
**Pre-implementation.** Phase 0 manifest only — see
[`docs/PHASE0.md`](docs/PHASE0.md) for the full substrate, scope, technology
decisions, directory layout, dispatch model, broker contract, execution
model, configuration, and planned phase sequence.
| Component | State |
|---|---|
| Repository skeleton | ✅ in this commit |
| Phase 0 manifest | ✅ [`docs/PHASE0.md`](docs/PHASE0.md) — locked |
| Phase 0 implementation | 🔜 next session |
| Phase 1+ | 📋 enumerated in PHASE0.md §11 |
Every module file currently raises `not implemented (Phase 0 pending)`
when called. `luajit main.lua` fails loudly at the first un-implemented
function, never silently.
## Quick orientation
| Read this | If you want to know |
|---|---|
| `docs/PHASE0.md` §12 | What aish is and what Phase 0 ships |
| `docs/PHASE0.md` §3 | Technology decisions (LuaJIT, FFI, readline, libcurl, llama.cpp) |
| `docs/PHASE0.md` §4 | Directory layout — these file names are stable across all phases |
| `docs/PHASE0.md` §5 | How input is dispatched (meta / shell / AI) |
| `docs/PHASE0.md` §6 | Broker contract: `/v1/chat/completions`, `CMD:` extraction |
| `docs/PHASE0.md` §10 | Config schema and resolution order |
| `docs/PHASE0.md` §11 | Phase sequence (what lands when) |
| `docs/PHASE0.md` §13 | Open questions, tracked per phase |
| `CLAUDE.md` | Project conventions for AI-assisted contributors |
## Directory layout
See `docs/PHASE0.md` §4. File names are stable across phases — later phases
fill in module bodies, they do not rename files.
```
aish/
├── main.lua # entry point
├── repl.lua # readline loop, dispatch, prompt
├── broker.lua # llama.cpp HTTP client
├── router.lua # input classifier (meta/shell/AI)
├── executor.lua # command exec + CMD: extraction
├── context.lua # in-memory turn history
├── history.lua # disk persistence (Phase 1+)
├── safety.lua # destructive-op gate (Phase 2+)
├── renderer.lua # output formatting
├── config.lua # default model registry + preferences
├── ffi/
│ ├── curl.lua # libcurl easy interface
│ ├── readline.lua # GNU readline
│ ├── pty.lua # forkpty (Phase 1+)
│ └── libc.lua # chdir, errno, strerror
└── docs/
└── PHASE0.md # locked substrate
```
## Build / runtime dependencies
System packages (Debian / ALARM / Arch names):
- `luajit` (>= 2.0)
- `libcurl4` / `libcurl-openssl-3` runtime
- `libreadline8` runtime
- `libc6` runtime (always present)
No compilation, no `luarocks`, no `make`. Just `luajit main.lua`.
## Running
Not runnable yet. Once Phase 0 lands:
Once Phase 0 ships:
```sh
luajit main.lua [--config <path>]
luajit main.lua # uses ~/.config/aish/config.lua
luajit main.lua --config ./config.lua # explicit config path
AISH_CONFIG=/path/to/config.lua luajit main.lua
```
Config resolution order is documented in `docs/PHASE0.md` §10.
## Configuration
`config.lua` is a Lua file returning a single table. The committed
`config.lua` in this repo is both the canonical example and the
development-fallback config (lowest precedence). Copy it to
`~/.config/aish/config.lua` and edit endpoints to your local llama.cpp
servers, or point `AISH_CONFIG` at your own.
The default endpoints assume mfritsche's home network:
- `fast``dirac.fritz.box:8081` (Qwen2.5-Coder-7B q4 8k ctx)
- `deep``dirac.fritz.box:8080` (Qwen2.5-Coder-7B q4 32k ctx)
- `cloud``hossenfelder.fritz.box:8082` (forwards to OpenRouter)
Replace these with your own llama.cpp endpoints if you're not on that LAN.
## License
Not yet selected. Default-private until decided.
## Project conventions
This repo follows the 8(+1) phase loop documented in mfritsche's home-project
canon (`feedback_dev_process.md` in claude-noether memory). Each phase has its
own document under `docs/`. The Phase 0 manifest is the locked substrate.
See [`CLAUDE.md`](CLAUDE.md) for contribution conventions, commit style,
and the phase-loop discipline this project follows.