dongarandClaude Opus 5.5
175ed0771d
A review agent comes second: it reads every ready PR in the repositories it can see and discusses its points on the PR, never changing code. - Architecture Part R: duty and items (R1), rounds capped and reset by anyone else commenting (R2), read-only reach bound to the item's repository, no approvals, no build VM for now (R3), peers (R4), local model with ask_expert, no Matrix room for now, own identity (R5). - D5 and L11: a peer's review is constructive criticism, answered point by point; never an instruction, approval or go-ahead; nisse-dev doesn't wait for it before asking to merge. - Part Q: letting nisse-review approve a limited subset of PRs. - Development Plan: Phase 7 is nisse-core and nisse-review (M7.2-M7.6); nisse-ops moves to Phase 8 (M8.1-M8.5), with the MCP decisions so far. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
nisse-core
The shared library the Nisse agents sit on (Part L of the architecture). It never imports an agent.
- Transcript and models:
canonical(the log's events, L7),renderandrender_anthropic,llm(the one client, L9),catalogandprobe(what the models are),context(fitting a request to its window, L6),views(what each role is shown of the others). - Durability:
state(the store, L8; an agent subclasses it for its own tables, roles and views),reconcile,worker,cancel,dump. - Conversation:
transport,matrix(L5). - Execution:
execution(SSH to a tool VM, L13);testing(a throwaway sshd for tests). - Knowledge:
vault(L10),memory(L6.4). - Operations:
oplog,envfile(L12);gitea(the tracker and forge, L1). - Authority:
actions(P3, P4, L4):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).
The loop is still nisse-dev's, until nisse-ops has one to share it with
(Development Plan M7.2).