marfrit 299719f4de repl: auto-summarize on :q into memory.jsonl (closes #102)
Closes #102 (FR-B from the 2026-05-17 German strategy analysis,
small-model improvement strategy 5: "History-Zusammenfassung via
local").

Today the `:memory summarize` distill flow is a manual meta — users
have to remember to run it before quitting. This commit wires the
same flow into shutdown_session under an opt-in cfg flag, so the
local fast model can absorb each non-trivial session into the
persistent memory.jsonl without user burden. Next-session startup's
[background] block picks the new entries up automatically (Phase 4).

Implementation:

- Extract the `:memory summarize` body into _do_memory_summarize(opts).
  opts.auto = true: skip the per-candidate readline keep?[y/N/edit]
  loop and auto-add every parsed candidate (trust the model + the
  explicit opt-in via cfg.memory.auto_summarize_on_quit). opts.min_turns
  is the silent-no-op cutoff. Status messages suppressed for fast-path
  no-ops so :q stays quiet on trivial sessions.
- :memory summarize meta now one line: _do_memory_summarize({ auto=false }).
- shutdown_session checks cfg.memory.auto_summarize_on_quit; if set,
  pcall(_do_memory_summarize, { auto=true, min_turns=N }). pcall so a
  broker failure NEVER blocks :q (memory is best-effort).

New config keys (all opt-in; default behavior unchanged):

  memory = {
    enabled = true,
    auto_summarize_on_quit = true,
    min_turns_for_summary  = 5,     -- skip trivial sessions
    summary_model          = "fast", -- cfg.memory.summarizer_model is
                                    -- still honored for back-compat
  }

E2E verified on hossenfelder:8082 with qwen-coder-7b as summary_model:

  3 user turns ("remember venus...", "remember mars...", "remember pluto..."):
    :q -> "[aish] summarizing session for memory via fast ..."
       -> "[aish] auto-summarize: added 3 memory items"
       -> memory.jsonl gained 3 fact: entries (correctly extracted)

  Below threshold (1 user turn, min=10):
    :q -> silent, no broker call, no memory.jsonl change

  Flag off (default behavior, 4 turns):
    :q -> silent, identical to pre-#102 behavior

Regression: 87/87 safety, 31/31 router_model, repl loads.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-17 09:18:02 +00:00

aish

aish — AI-augmented conversational shell.

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.

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 3 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

Component State
Repository skeleton in this commit
Phase 0 manifest 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

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 3+)
├── 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

Once Phase 0 ships:

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:

  • fastdirac.fritz.box:8081 (Qwen2.5-Coder-7B q4 8k ctx)
  • deepdirac.fritz.box:8080 (Qwen2.5-Coder-7B q4 32k ctx)
  • cloudhossenfelder.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

See CLAUDE.md for contribution conventions, commit style, and the phase-loop discipline this project follows.

S
Description
AI-augmented conversational shell — LuaJIT REPL with llama.cpp broker, shell executor, and routed AI inference.
Readme MIT 2.2 MiB
Languages
Lua 99.8%
Shell 0.2%