vinzenz/hyperhive
0
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
hyperhive/TODO.md

6.8 KiB
Raw Blame History

TODO

Pick anything from here when relevant. Cross-cutting design notes live in CLAUDE.md; high-level project intro in README.md.

Turn loop

  • recv with no wait_seconds should return immediately. Today omitting the argument falls through to the 30s default long-poll (RECV_LONG_POLL_DEFAULT in hive-c0re/src/agent_server.rs); a manager that wants a cheap "anything in the inbox right now?" peek has to explicitly pass wait_seconds: 0. Flip the semantics so None = no sleep, returning None (or the empty inbox shape) right away. The agent opts into the long-poll by setting a positive value. Update both AgentRequest::Recv and ManagerRequest::Recv handlers + the prompt language in prompts/{agent,manager}.md. Tighten the cap (180s) too — only meaningful when the agent is choosing to wait.

Permissions / policy

  • Per-agent send allow-list. Today any agent can send to any other recipient (peer, manager, operator). Add a per-agent policy that constrains the to field — declared in agent.nix, e.g. hyperhive.allowedRecipients = [ "manager" "alice" ]. Broker rejects with an Err { message } when the policy denies. Default: unrestricted (back-compat). The manager can still always send anywhere. Useful for sandboxing untrusted sub-agents so they can only talk to the manager, not other sub-agents.

Security

  • Unprivileged containers (userns mapping). Today the nspawn container runs as a fully privileged root. Goal: PrivateUsersChown=yes (or the nixos-container equivalent) so uid 0 inside maps to an unprivileged uid on the host, and a container-root compromise lands the attacker on an ordinary user account, not the host's root. Requires per-agent state dirs to be chown'd to that uid on the host side. The per-agent git identity (currently injected via programs.git.config.user against the root user in setup_applied's generated flake) also needs to be provisioned for whatever non-root user claude runs as, or commits the manager makes against /agents/<n>/config will fall back to a generic nixos@… identity.
  • Bash command allow-list. Replace the blanket Bash allow with a pattern allow-list (Bash(git *), Bash(nix build .*), etc.) per claude-code's --allowedTools extended grammar. Likely lives in agent.nix so each agent can scope its own shell surface.

Per-agent extension

  • Custom per-agent MCP tools. Today every sub-agent gets the same fixed MCP surface (send, recv). To move bitburner-agent (and anything else with rich domain tooling) into hyperhive, an agent needs a way to ship its own tools alongside hyperhive's. Sketch: agent.nix declares a list of extra MCP servers (command + args + env), each registered into the agent's --mcp-config blob at flake-render time. The harness MCP server remains the hyperhive surface; new servers slot in as additional entries under mcpServers.<name> so claude sees them as mcp__<name>__<tool>. Per-agent tool whitelist (allowedTools) derived from the same config so the operator stays in control of what's exposed.

Bugs

  • Pending question doesn't always appear on the dashboard. Repro: manager calls ask_operator, tool result is question queued (id=N) (so the row is in sqlite), but the M1ND H4S QU3STI0NS section keeps showing "no pending questions". Last seen with id=5. Suspected paths:
    • OperatorQuestions::pending() returns Err and the unwrap_or_default() in api_state hides it. Surface the error (warn-log) and check.
    • serialization: a new field in OpQuestion (e.g. deadline_at: Option<i64>) deserializes wrong against an old row whose columns don't match the new SELECT order → row.get(N)? panics for that row, the whole iterator errors, pending() returns Err. Diagnose by curl /api/state | jq '.questions' and compare with sqlite counts.
    • dashboard JS swallows a render error. Open browser console and look for exceptions during renderQuestions.

UI / UX

  • Web UI for config repos. Browse history, diffs, tags (proposed + approval/* + applied/*) per agent, all from the dashboard. Something lighter than a full forge — read-only log + diff + raw-file view is enough. Pairs naturally with the upcoming config-repo overhaul (tags become the audit trail; UI surfaces them).

  • xterm.js terminal embedded per-agent, attached to a PTY exposed by the harness. Pairs well with the unprivileged-container work — would let the operator drop into the container without nixos-container root-login.

Telemetry

  • Harness stats per agent in sqlite, charted on the agent page. bitburner-agent samples 18 series; for hyperhive the generally-applicable ones are:
    • turns/min, tool calls/turn, turn duration p50/p95
    • claude exit code distribution (ok vs --compact-retry vs failure)
    • inbox depth (current + max-over-window)
    • messages sent/received per turn (split by recipient: peer / operator / manager / system)
    • approval queue length (across all agents — dashboard-level)
    • per-tool usage counts (Read/Edit/Bash/send/recv/…)
    • time-since-last-turn (helps spot stuck agents)
    • notes file size growth (cues compaction) Backend: a stats table with (agent, ts, key, value) written from the harness on TurnEnd; GET /api/stats?since=… returns the series; agent page renders with a small chart lib (uPlot is light).

Spawn flow

  • Two-step spawn. Today request_spawn(name) is one shot: manager asks → operator approves → container is created with a default agent.nix and empty /state/. Manager has no way to pre-stage per-agent prompt material, package additions, or initial notes before the agent first wakes. Split into:
    1. request_spawn_draft(name) — host creates the per-agent proposed/ repo (initial commit) and state/ dir with no container; manager now has /agents/<name>/{config,state}/ to edit + commit just like an existing agent.
    2. request_spawn_commit(name, commit_ref) — submits the queued approval; operator sees the diff in the dashboard like a normal apply_commit; on approve the container is created from that commit. Backwards-compat: keep the existing one-shot request_spawn for trivial agents (operator can still type a name in the dashboard). Surface "drafts" as a new section between K3PT ST4T3 and approvals.

Loop substance

  • Notes compaction. /state/ is bind-mounted persistently and agents are told (in the system prompt) to keep /state/notes.md for durable knowledge — but we don't currently nudge them to compact when notes grow. Bitburner-agent's pattern: a short-lived secondary claude session that takes the existing notes + a "compact this" prompt and rewrites them in place. Add when the notes start bloating.