No description
b0f6bd8ece
the stream-json result event carries modelUsage.<model>.contextWindow which is the actual per-inference active window the model enforces. for claude-sonnet-4-6 this is 200k even though the full prompt cache can hold millions of tokens via accumulated cache reads. with the nix-configured sonnet = 1000000 the proactive compact watermark sat at 750k and was never reached. agents grew context until prompt_too_long at ~170k — reactive compact, no checkpoint turn. changes: - bus gains api_context_window field seeded from modelUsage.*.contextWindow in each turn's result event. authoritative; falls back to env var, then 200k. - new effective_context_window(bus) helper used by both watermark functions - compact_watermark (75%) and auto_reset_watermark (50%) call effective_context_window - context_tokens() docstring clarified: all three token fields (input + cache_read + cache_creation) count against the per-inference contextWindow limit. the large cache_read values seen in the result event are cumulative across all inferences in a turn, not per-inference. - /api/state context_window_tokens now reflects the calibrated window closes #129 |
||
|---|---|---|
| branding | ||
| docs | ||
| hive-ag3nt | ||
| hive-c0re | ||
| hive-fr0nt | ||
| hive-sh4re | ||
| nix | ||
| scripts | ||
| .gitignore | ||
| Cargo.lock | ||
| Cargo.toml | ||
| CLAUDE.md | ||
| flake.lock | ||
| flake.nix | ||
| README.md | ||
| TODO.md | ||
hyperhive
a swarm of claude-code agents, each in its own nspawn cage, gossiping over unix sockets. config changes flow as git commits, the operator approves them in a browser, every deploy is a tag. cyberpunk-themed dashboard included. 💜⚡
Claude code is great in one window, exponentielle across many — but only if you can keep the agents from stepping on each other, give them durable identity, and stop them from eating production. hyperhive is the substrate.
- identity = unix socket
- communication = sqlite-backed broker (
send/recv/ask/answer/remind) - config = git (manager proposes, operator approves, deploys land as tagged commits)
- blast radius = container
host (NixOS, runs hive-c0re.service)
│
├── operator
│ ├── browser → :7000 hive-c0re dashboard
│ ├── browser → :8000 / :8100-8999 per-agent web UIs
│ └── CLI → /run/hyperhive/host.sock admin protocol
│
├── hive-c0re (Rust daemon: lifecycle / broker / approvals /
│ auto-update / dashboard / sockets)
│
└── nixos-containers
├── hm1nd manager agent (privileged MCP surface)
└── h-<name> sub-agent (vanilla MCP surface + per-agent extras)
Depth lives in docs/ — pick the one matching your task:
| reading path | doc |
|---|---|
| dashboard layout + endpoints | docs/web-ui.md |
| claude turn loop + MCP tools | docs/turn-loop.md |
| config-edit + approval state machine | docs/approvals.md |
| what survives destroy / purge / restart | docs/persistence.md |
| naming, wire protocol, commit style | docs/conventions.md |
| NixOS / nspawn gotchas | docs/gotchas.md |
Host config
Minimal flake.nix for a host that runs hive-c0re:
{
inputs = {
nixpkgs.url = "github:NixOS/nixpkgs/nixos-25.11";
hyperhive.url = "git+https://git.berlin.ccc.de/vinzenz/hyperhive";
};
outputs = { nixpkgs, hyperhive, ... }: {
nixosConfigurations.my-host = nixpkgs.lib.nixosSystem {
system = "x86_64-linux";
modules = [
hyperhive.nixosModules.default # hive-c0re + hive-forge in one import
({ ... }: {
services.hive-c0re.enable = true;
# services.hive-c0re.operatorPronouns = "they/them"; # default: "she/her"
# ... rest of your host config
system.stateVersion = "25.11";
})
];
};
};
}
hive-c0re opens its admin socket + dashboard, auto-creates the
manager container, and auto-rebuilds any container whose hyperhive
rev goes stale. claude-code is unfree — hyperhive scopes the
whitelist to itself, nothing for the operator to set.
Build / deploy
nix develop -c cargo check
nix flake check # rust + nix + toml fmt + clippy
# deploy from a host config that imports hyperhive.nixosModules.hive-c0re
nix flake update --update-input hyperhive
sudo nixos-rebuild switch --flake .#<host>