From 78396c818957ad60a8b85bb2ecc68b3f57f7caef Mon Sep 17 00:00:00 2001 From: damocles Date: Thu, 2 Jul 2026 22:13:09 +0200 Subject: [PATCH] recv: cap batch size at 5, default stays 1 (#2150 clarified) --- docs/conventions.md | 2 +- docs/turn-loop.md | 2 +- hive-ag3nt/prompts/system.md | 2 +- hive-ag3nt/src/mcp.rs | 4 ++-- hive-ag3nt/src/serve_common.rs | 6 +++++- hive-c0re/src/socket_server.rs | 9 ++++----- 6 files changed, 14 insertions(+), 11 deletions(-) diff --git a/docs/conventions.md b/docs/conventions.md index 9bd03501..1a0d0283 100644 --- a/docs/conventions.md +++ b/docs/conventions.md @@ -121,7 +121,7 @@ in `hive-c0re::dashboard_events::DashboardEvent`. agent. Always returns a list (`Messages { messages }`) — empty when nothing's pending, single-pop when `max = None` (default 1, the single-message behaviour), batched up to `max` when caller asks for -more (server-side cap is 32; values above clamp silently). +more (server-side cap is 5; values above clamp silently). `wait_seconds` long-polls for the first message; once one arrives — or one is already pending — the call drains up to `max` in total before returning, so a single `Recv` call coalesces a burst. diff --git a/docs/turn-loop.md b/docs/turn-loop.md index 7818e4cd..e3a7db7f 100644 --- a/docs/turn-loop.md +++ b/docs/turn-loop.md @@ -520,7 +520,7 @@ ttl_seconds?, to?)`, `answer(id, answer)`, `ack_until(up_to)`. - `recv` — drain inbox. Without `wait_seconds` (or `0`) returns immediately. Positive value parks the turn up to that many seconds (cap 180) — incoming messages wake instantly. `max` (default 1, cap - 32) drains up to N rows; `wait_seconds` applies to the first, then + 5) drains up to N rows; `wait_seconds` applies to the first, then drains up to `max` total. Each returned row is prefixed with `[msg #]` (broker row id; note the highest id seen, then pass it to `ack_until` to bulk-triage the batch). **Graceful shutdown**: when the harness diff --git a/hive-ag3nt/prompts/system.md b/hive-ag3nt/prompts/system.md index 7f0a19db..df06b634 100644 --- a/hive-ag3nt/prompts/system.md +++ b/hive-ag3nt/prompts/system.md @@ -2,7 +2,7 @@ You are hyperhive agent `{label}` (qualified: `{qualified_label}`){hive_identity Tools (hyperhive surface): -- `mcp__hyperhive__recv(wait_seconds?, max?)` — drain inbox messages (returns `(empty)` if nothing pending). Without `wait_seconds` (or with `0`) it returns immediately — a cheap "anything pending?" peek you can sprinkle between tool calls. To **wait** for work when you have nothing else useful to do this turn, call with a long wait (e.g. `wait_seconds: 180`, the max) — incoming messages wake you instantly, otherwise the call returns empty at the timeout. That's strictly better than a fixed `sleep` shell command: lower latency on new work, no busy-loop. `max` (default 1, cap 32) drains several queued messages in one call — the wake prompt tells you the pending count. +- `mcp__hyperhive__recv(wait_seconds?, max?)` — drain inbox messages (returns `(empty)` if nothing pending). Without `wait_seconds` (or with `0`) it returns immediately — a cheap "anything pending?" peek you can sprinkle between tool calls. To **wait** for work when you have nothing else useful to do this turn, call with a long wait (e.g. `wait_seconds: 180`, the max) — incoming messages wake you instantly, otherwise the call returns empty at the timeout. That's strictly better than a fixed `sleep` shell command: lower latency on new work, no busy-loop. `max` (default 1, cap 5) drains several queued messages in one call — the wake prompt tells you the pending count. - `mcp__hyperhive__ack_until(up_to)` — bulk-mark inbox messages handled: every message with broker id `<= up_to` (ids show as `[msg #]` in wake prompts and recv output) is acked in one call, pending and delivered alike. Use it to clear a backlog you've already triaged — e.g. a redelivered flood after a container restart — instead of draining it one recv at a time: note the highest `[msg #N]` you've seen, then `ack_until(up_to: N)`. Acked messages never redeliver; messages newer than `up_to` stay queued. Only affects your own inbox. - `mcp__hyperhive__send(to, body, in_reply_to?)` — message a peer (by their name) or the operator (recipient `operator`, surfaces in the dashboard). Use `to: "*"` to broadcast to all agents (they receive a hint that it's a broadcast and may not need action). Use `to: ""` to address your structural parent without hardcoding their name — hive-c0re rewrites it at delivery time per `topology.json`, falling back to `operator` if you're a root agent. Use `to: ""` to fan-out to every direct child of yours per `topology.json` (no-op for leaf agents). Both sentinels let the operator reparent at runtime with zero change on your side. Optional `in_reply_to: ` threads this message under a prior one — the dashboard and per-agent inbox render it with a `↳ reply` link. Some agents have a per-agent allow-list (`hyperhive.allowedRecipients` in their `agent.nix`) — if so the tool refuses recipients outside the list with a clear error; route through a peer agent or contact the operator directly. - (some agents only) **extra MCP tools** surfaced as `mcp____` — these are agent-specific (matrix client, scraper, db connector, etc.) declared in your `agent.nix` under `hyperhive.extraMcpServers`. Treat them as first-class tools alongside the hyperhive surface; the operator already auto-approved them at deploy time. diff --git a/hive-ag3nt/src/mcp.rs b/hive-ag3nt/src/mcp.rs index 8061e906..fc78cf90 100644 --- a/hive-ag3nt/src/mcp.rs +++ b/hive-ag3nt/src/mcp.rs @@ -613,7 +613,7 @@ pub struct RecvArgs { /// Maximum number of messages to pop in this round-trip. Default /// (None) is 1 (single-message behaviour — exactly what you want /// when you're called to drive a turn off the first wake). Pass - /// a higher value (capped at 32 server-side) when you've been + /// a higher value (capped at 5 server-side) when you've been /// told the inbox has more queued (the wake prompt mentions /// pending count) and want to drain everything in one tool call. /// Once the long-poll wakes up, the call drains up to `max` in @@ -806,7 +806,7 @@ impl AgentServer { `wait_seconds` (capped at 180) to park the turn waiting for new work — incoming \ messages wake you instantly, otherwise the call returns empty at the timeout. \ That's strictly better than a fixed shell `sleep`. \n\n\ - **Batch drain**: pass `max: N` (capped at 32) to drain up to N messages in one \ + **Batch drain**: pass `max: N` (capped at 5) to drain up to N messages in one \ round-trip. Use this when the wake prompt told you the inbox has more queued, or \ any time you expect a burst — one tool call beats N consecutive single recvs. \ `wait_seconds` still applies to the FIRST message; once one arrives the call drains \ diff --git a/hive-ag3nt/src/serve_common.rs b/hive-ag3nt/src/serve_common.rs index abc460f9..0e13b909 100644 --- a/hive-ag3nt/src/serve_common.rs +++ b/hive-ag3nt/src/serve_common.rs @@ -31,9 +31,13 @@ pub fn format_wake_prompt( let pending = if unread == 0 { String::new() } else { + // Suggested batch size is clamped to the server-side recv cap + // (see `RECV_BATCH_MAX` in hive-c0re) so the hint never asks + // for more than one round-trip can deliver. + let batch = unread.min(5); format!( "\n\n({unread} more message(s) pending in your inbox — call `mcp__hyperhive__recv` \ - with `max: {unread}` to drain them all in one round-trip before acting. If the \ + with `max: {batch}` to drain the next batch before acting. If the \ backlog is stale/already handled, `ack_until(up_to: )` \ clears everything up to that id in one call instead.)" ) diff --git a/hive-c0re/src/socket_server.rs b/hive-c0re/src/socket_server.rs index df590644..7f8aeb5c 100644 --- a/hive-c0re/src/socket_server.rs +++ b/hive-c0re/src/socket_server.rs @@ -152,11 +152,10 @@ pub(crate) const RECV_LONG_POLL_MAX: std::time::Duration = std::time::Duration:: /// Server-side hard cap on `Recv.max`. Bounds the size of a single /// round-trip so a confused caller can't drain the entire inbox in /// one go and blow past wire-buffer sizes; everything above the cap -/// silently clamps. 32 is comfortably above the burst sizes we've -/// seen in practice (post-rebuild rescue, multi-agent reply storms) -/// and well under the per-message `MESSAGE_MAX_BYTES` * N envelope -/// budget. -pub(crate) const RECV_BATCH_MAX: u32 = 32; +/// silently clamps. 5 keeps individual turns small — a big backlog +/// is drained over several recv calls instead of one giant pop +/// (#2150). +pub(crate) const RECV_BATCH_MAX: u32 = 5; pub(crate) fn recv_timeout(wait_seconds: Option) -> std::time::Duration { match wait_seconds {