Last #716 hotspot — scrub-only batch. All substantive prose is
already documented in docs/turn-loop.md::MCP surface (Sub-agent
tools, Manager tools, Tool whitelist, Tool envelope), so the 10
cookies in mcp.rs come out without prose extraction.
- format_agent_meta rustdoc: drop #432 attribution, add docs pointer
for the running=false / status_text-stale rationale
- get_agent_meta hive/swarm comment: drop #710 attribution
- AgentServer + ManagerServer add-tool warnings: drop #511 attribution
twice (kept the lockstep invariant)
- edit_schedule description: drop #474 + #478 cookies in user-facing
tool text
- cancel_loose_end description: drop #250 cookie in user-facing text
- Manager allow-list block: drop the long #444/#235/#467/#472/#474/
#478/#509 attribution roll, keep the lockstep invariant
- check_send_allowed (<parent> branch): drop #692, replace with the
actual semantics ("falls back to operator for root agents")
- prompts/system.md: drop #474 cookie from edit_schedule line
- Cargo.toml [[bin]]: drop #598 pre-/post- split history, add docs
pointer to docs/turn-loop.md::Harness binary shape
cargo check + 56 tests pass.
Closes#716 (last cookie hotspot).
First chunk of #589 v0 phase A: plumbing the hive-qualified
'name@hive' form through the per-agent surfaces that the harness
itself owns. Broker from/to + dashboard rendering + container_view
follow in subsequent PRs once damocles ships the HYPERHIVE_HIVE_DOMAIN
env var in harness-base.nix.
- new hive_ag3nt::identity module: label() / hive_domain() /
qualified_label() / qualify(label). Reads HYPERHIVE_HIVE_DOMAIN
(set by hive-c0re.nix module from hyperhive.domain) — when unset
or empty, qualified_label degrades to just the short label so
existing single-hive deployments are unchanged. Six unit tests
cover the set / unset / empty / arbitrary-label paths.
- prompt::render gains {qualified_label} substitution alongside
the existing {label}. system.md template uses both: the agent
intro now reads 'You are hyperhive agent iris (qualified:
iris@darkest.space) in a multi-agent system. ... When you're
talking to or about a peer on a different hive, use the
qualified form (name@hive) so the operator + the manager can
disambiguate'. Manager flavor gets the same treatment.
- /api/state gains qualified_label: String. Always present, equals
label when no domain is configured.
- frontend setHeader takes the qualified_label, drives the browser
tab title (so two tabs from different hives are
distinguishable in the tab bar) while the glyphic #title stays
short for the cinematic header.
Gated on env var presence — no behaviour change for single-hive
deployments. Pairs with damocles's upcoming harness-base.nix
HYPERHIVE_HIVE_DOMAIN ship; safe to land in either order.
PR #119 changed get_loose_ends to default to the manager's own items
and accept an optional agent arg ("*" = hive-wide, "<name>" = one
agent), but the manager system prompt still described it as
"hive-wide ... no args". docs/turn-loop.md was already updated;
only manager.md was missed.
sub-agent containers post-refactor bind their state at
/agents/<name>/state (manager keeps the legacy /state — see
lifecycle.rs:751). agent.md still said /state/forge-token; corrected
to /agents/{label}/state/forge-token (template-substituted at
boot). tea-login systemd unit now walks both candidates so the same
harness module works for the manager and sub-agents.
system prompts now describe the hyperhive Forgejo at localhost:3000,
the per-agent user, the pre-configured tea CLI, and the REST API
fallback with /state/forge-token. todo gains the shared docs/skills
RO-repo follow-up (org-shared + per-agent read membership).
claude-code rejects --dangerously-skip-permissions / defaultMode=
bypassPermissions when running as root, which all hyperhive
containers do. revert to the previous explicit allow-list plumbing
(per-flavor list spliced into permissions.allow + --tools enable
list), keep TodoWrite out of the built-in allow set, and keep the
deny list (TodoWrite, WebFetch, WebSearch, Task) as belt-and-braces
in case anything sneaks past the allow gate.
claude-settings.json now sets permissions.defaultMode=bypassPermissions
with a small deny list (WebFetch, WebSearch, Task, TodoWrite). The
per-flavor allow list and --tools / --allowedTools CLI flags are gone
— anything not denied auto-approves. mcp.rs loses ALLOWED_BUILTIN_TOOLS,
builtin_tools_arg, allow_list, allowed_mcp_tools. The extraMcpServers
allowedTools field is parsed for back-compat but no longer wired
anywhere; restrict via permissions.deny instead.
