diff --git a/docs/approvals.md b/docs/approvals.md index b0274283..55627689 100644 --- a/docs/approvals.md +++ b/docs/approvals.md @@ -11,12 +11,9 @@ informed about what happens after a decision lands. ## End-to-end approval flow 1. The submitting agent (the child's parent, holding the `approvals` - tool group) edits files in the child's proposed config repo - (any tracked path, but `agent.nix` is the contract entry point) - and commits with its own git identity. The parent's container has - the child's proposed config repo bind-mounted read-write at - `/agents//config/` (topology-driven via `set_nspawn_flags`; - the agent's *own* config at `/agents//config/` is read-only). + tool group) edits files under the child's `/agents//config/` + (any tracked path, but `agent.nix` is the contract entry point) and + commits with its own git identity. 2. The submitting agent submits the commit sha via `request_apply_commit(agent, commit_ref)`. `commit_ref` must be a commit **sha** (7-40 hex chars, short or full) — a branch or tag name is rejected so the @@ -66,11 +63,11 @@ informed about what happens after a decision lands. failure, main stays put and the working tree resets back to the previous deployed commit. 6. `HelperEvent::ApprovalResolved` (and `Rebuilt` for the - ApplyCommit kind) land in the **submitting agent's** inbox, carrying - both the canonical sha and the terminal tag. Helper events route to - the submitting agent via `notify_submitter` (the approval row carries - a `submitter` column recording which agent called `request_apply_commit` - or `request_init_config`). + ApplyCommit kind) land in the root agent's inbox, carrying both + the canonical sha and the terminal tag. (Helper events currently route + to the root agent via `notify_manager` regardless of which agent + submitted the approval; routing them to the submitting agent is tracked + in #1953.) ### Withdrawing a pending approval @@ -91,8 +88,7 @@ without it has nothing of its own to withdraw. `InitConfig` approvals are the first step in a two-step spawn flow. On approve, hive-c0re seeds the proposed config repo with a default `agent.nix` template and sends `HelperEvent::ConfigReady { agent }` -to the submitting agent's inbox via `notify_submitter`. The submitting -agent then reviews, +to the root agent. The submitting agent then reviews, edits, and commits the template before calling `request_apply_commit` to proceed to an `ApplyCommit` approval. The first `ApplyCommit` creates the container; subsequent ones rebuild it with new config. @@ -404,33 +400,26 @@ The dashboard deep-links into this org — a `config repo` link per container row and a `commit on forge` link per approval card. See `docs/web-ui.md`. -### Submitting agent's view of config repos +### Root-agent view of applied + meta -Every parent agent's container has its **direct children's** proposed -config repos bind-mounted read-write (topology-driven: `lifecycle.rs` -calls `bind_child_agent_dirs` for each entry in -`topology::children_of(agent_name)`). An agent with the `approvals` -tool group can therefore edit, commit, and submit changes for any of -its direct children directly inside its container at `/agents//config/`. +The root agent container gets three host-side bind mounts via +`set_nspawn_flags`: -Agents holding the `can_manage_top_level_agents` topology role -(defined as `ROLE_CAN_MANAGE_TOP_LEVEL_AGENTS` in `hive-c0re/src/topology.rs`) -get additional host-side bind mounts via `set_nspawn_flags`: - -- `/var/lib/hyperhive/agents/` → `/agents/` (RW) — all top-level - agents' proposed repos (not just direct children). -- `/var/lib/hyperhive/applied/` → `/applied/` (RO) — every agent's - authoritative applied repo, including `.git`. +- `/var/lib/hyperhive/agents/` → `/agents/` (RW) — proposed + repos. The root agent edits + commits per-agent config here. +- `/var/lib/hyperhive/applied/` → `/applied/` (RO) — every + agent's authoritative applied repo, including `.git`. - `/var/lib/hyperhive/meta/` → `/meta/` (RO) — the swarm-wide deploy flake. -The root agent holds this role; a sub-manager that only manages a -subtree does not, and only has its direct children's config dirs. +This is the **root agent's** view — RW over *every* agent's config. An +agent with the `approvals` group that owns a subtree (a sub-manager) has +the equivalent RW scoped to its own children's config repos. Each proposed repo (`/agents//config/`) is pre-configured with `applied` as a git remote pointing at -`/applied//.git`. Useful incantations from inside an agent with -the full `/applied` mount: +`/applied//.git`. Useful incantations from inside the +root agent's container: ```sh git -C /agents//config fetch applied @@ -444,8 +433,9 @@ git -C /meta log --oneline # swarm-wide deplo cat /meta/flake.lock | jq '.nodes | with_entries(select(.key | startswith("agent-")))' ``` -The RO binds block push at the kernel level — git plumbing inside the -container cannot corrupt either authoritative repo. +The RO binds block push at the kernel level, so the root agent +can only fetch / read — git plumbing inside the container +cannot corrupt either authoritative repo. ## Migration from the pre-tag / pre-meta schemes @@ -505,25 +495,25 @@ updates the root agent itself. ## Root-agent policy -The system prompt (`hive-ag3nt/prompts/system.md`, rendered via -`hive_ag3nt::prompt::render`) is the **same for every agent**; what -varies is which MCP tools are surfaced (gated by tool groups and -capabilities in `agent.nix`). There is no `role:manager` block that -renders only for the root agent. The root agent's approval-gating -behaviour comes from its CLAUDE.md / agent-specific instructions, not -the system prompt template. +From `hive-ag3nt/prompts/system.md` (`` block, +rendered via `hive_ag3nt::prompt::render`): the root agent does NOT +rubber-stamp sub-agent config requests. It verifies (role match, +package legitimacy, cheaper alternative, blast radius) before +committing and calling `request_apply_commit`. -`ask(question, options?, multi?, ttl_seconds?, to?)` is available to -**any agent** — it queues a question and returns the id immediately. -When `to` is omitted (or `"operator"`) the question shows up on the -dashboard; when `to` is another agent's name, the recipient receives a +For ambiguous cases or anything that needs human signal, the +the root agent calls `ask(question, options?, multi?, ttl_seconds?, to?)` — +queues the question and returns the id immediately. When `to` is +omitted (or `"operator"`) the question shows up on the dashboard; +when `to` is a sub-agent's name, the recipient receives a `HelperEvent::QuestionAsked` and answers via their own `answer` tool. Either way the answer arrives back as `HelperEvent::QuestionAnswered { id, question, answer, answerer }` in the asker's inbox. Storage is `hive-c0re::operator_questions` (sqlite) — same table, with a nullable `target` column (NULL = operator). Dispatch goes through -`hive-c0re/src/questions.rs::{handle_ask, handle_answer}`. The answer flow is: +`hive-c0re/src/questions.rs::{handle_ask, handle_answer}` so both +the agent + root-agent surfaces stay aligned. The answer flow is: ``` POST /answer-question/{id} agent: Answer { id, answer } @@ -536,21 +526,22 @@ POST /answer-question/{id} agent: Answer { id, answer } Two more paths resolve a pending question with a sentinel answer: - `POST /cancel-question/{id}` (✗ CANC3L button on the dashboard) - resolves with `[cancelled]`. The asking agent sees a terminal state + resolves with `[cancelled]`. The root agent sees a terminal state and can fall back. - `ttl_seconds` deadline: a tokio watchdog spawned at submit time fires `answer(id, "[expired]")` once the ttl runs out. Already- resolved races no-op. The dashboard surfaces a `⏳ MM:SS` chip on each pending question with a deadline. -## Helper events to the submitting agent +## Helper events to the root agent -`Coordinator::notify_submitter(approval_id, &HelperEvent)` routes the -event to the agent that originally submitted the approval (looked up from -the `submitter` column on the `approvals` table). The harness delivers it -as a regular `system` inbox message so it drives a normal claude turn. -Legacy approval rows that predate the submitter column fall back to the -root agent. Variants (`hive_sh4re::HelperEvent`): +`Coordinator::notify_manager(&HelperEvent)` enqueues an inbox +message from sender `system` with the event JSON in the body. The +root agent's harness no longer short-circuits these — they drive a +regular claude turn so the root agent can react. (Today these go to the +root agent regardless of which agent submitted the approval — routing to +the submitting agent is tracked in #1953.) Variants +(`hive_sh4re::HelperEvent`): - `ApprovalResolved { id, agent, commit_ref, status, note }` — fired by `actions::approve` + `actions::deny` whenever an