kyleandClaude Fable 5.1 66fa143524 M3a spec: a ledger module and a two-process end-to-end test ...

Both came out of planning the tasks. The three locked steps need a home
that is neither the connection handler nor the pending table. The
one-process end-to-end test would have made loopd dev-depend on
brokerd, which the crate-dependency gate forbids.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

2026-09-18 22:36:55 -07:00

config

Extend on-device verification to the agent loop

2026-09-18 20:38:56 -07:00

crates

Fix four review findings: busy release, poison recovery, core.md errors, chat loop

2026-09-18 21:06:58 -07:00

docs

M3a spec: a ledger module and a two-process end-to-end test

2026-09-18 22:36:55 -07:00

scripts

Make gate scripts handle table-form dependencies and fail closed

2026-09-17 10:14:22 -07:00

spike

Add M2b plan: ten tasks, tests, recordings and the first system prompt

2026-09-18 17:19:02 -07:00

tools

Add tools/run-plan.sh to run a plan's tasks in fresh OpenCode sessions

2026-09-17 14:02:49 -07:00

.gitignore

Add M1 plan, given tests and fixtures, AGENTS.md and implementer log

2026-09-17 01:22:43 -07:00

AGENTS.md

Review M2b: accept with one follow-up task; record lessons

2026-09-18 20:47:03 -07:00

Cargo.lock

Add bxctl chat

2026-09-18 20:24:26 -07:00

Cargo.toml

Add SHA-256 to proto, wrapping the emsha crate

2026-09-17 14:11:51 -07:00

CLAUDE.md

Specify M3a (the decision path) and write the runbook

2026-09-18 21:57:21 -07:00

deny.toml

Add Cargo workspace, crate skeletons and the gate

2026-09-17 06:45:02 -07:00

Makefile

Extend on-device verification to the agent loop

2026-09-18 20:38:56 -07:00

S

Description

sovereign personal agent harness

4.8 MiB

Languages

Rust 97.6%

Shell 1.1%

Python 1.1%

Nix 0.2%