dongarandClaude Opus 5.5
e351d0a74e
A pure move; behaviour unchanged. - models (L9, L7): llm, catalog, probe, render, render_anthropic, context - log (L7, L6): canonical, views - state (L8): store (was state), reconcile, worker, cancel, dump - knowledge (L10, L6.4): vault, memory - conversation (L5): transport, matrix - execution (L13): ssh (was execution), testing - authority (P3, P4, L4): actions - gitea, oplog, envfile stay at the top until each gains a second module. Every import, monkeypatch target, script and doc reference rewritten. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
1.2 KiB
1.2 KiB
nisse-core
The shared library the Nisse agents sit on (Part L of the architecture). It never imports an agent. Packages follow the architecture's sections:
models(L9, L7):llm(the one client),catalogandprobe(what the models are),renderandrender_anthropic(request bodies from the log),context(fitting a request to its window, L6).log(L7, L6):canonical(the log's events),views(what each role is shown of the others).state(L8):store(an agent subclassesStateStorefor its own tables, roles and views),reconcile,worker,cancel,dump.knowledge(L10, L6.4):vault,memory.conversation(L5):transport,matrix.execution(L13):ssh(SSH to a tool VM);testing(a throwaway sshd for tests).authority(P3, P4, L4):actions(Action,Verdict, and static reading of shell commands, which each agent's fast-path rules build on;nisse-dev's are innisse_dev.loop.actions).- At the top, until each gains a second module:
gitea(the tracker and forge, L1),oplogandenvfile(L12).
The parts of a loop (loop) and shared configuration arrive with Development
Plan M7.2; each agent keeps its own scheduler.