feat(agent): optional reply guard reminds a silent turn to publish

[tlongwell-block]

Why

A Buzz agent's assistant text and reasoning are never shown to anyone — only what it posts through the CLI. A turn that runs fifteen tool calls and never publishes is a silent failure: the requester waits on a result that was produced and thrown away.

This adds an optional reminder at the end-of-turn gate, off by default.

Tyler asked for it in buzz-mesh; plan iterated to 9.5/10 with @wren (Minimalness 9.7, Elegance 9.5, Correctness 9.3).

What

BUZZ_AGENT_REQUIRE_REPLY=1 (default off, per-agent opt-in). A turn about to end with no recognized attempt to post gets a reminder and is rerolled. At most two, then the turn ends regardless — the guard catches accidental omission, it does not compel speech. The reminder text explicitly licenses silence so it cannot fight the base prompt's "silence is usually correct."

This is not a new MCP hook. RunCtx::run is the turn, so the two per-turn locals need no plumbing, and every tool call already passes through it with arguments visible. The objection is appended at the existing _Stop gate and rides push_hook_outputs_as_tool_results, so the model receives it as a lower-trust tool result with {hook, server, text} attribution. No new trust path, no new lifecycle event, no dev-mcp or CLI protocol change.

Earlier revisions of this plan needed four crates (a _UserPromptSubmit hook, a marker file, a buzz-cli change, dev-mcp state). Tyler pointed out the agent already knows both facts; that deleted all of it. Net runtime change is ~35 lines in agent.rs + ~4 in config.rs.

Recognition contract

A registered non-hook tool whose qualified name ends in __shell, whose command argument contains messages send or reactions add.

• The __ separator is exact, not approximate. Given has() + !is_hook(), ends_with("__shell") is provably equivalent to a bare name of shell: registration forbids __ in server and bare names (mcp.rs:227,268) and qnames are {server}__{bare}, so a trailing __shell could only straddle the separator if the bare name began with _ — which is_hook excludes. Without the separator, powershell and noshell would match.
• Reads the structured command field, not serialized arguments, so a description that quotes a send cannot disarm the guard, and a non-string command is rejected rather than coerced.
• Detects an attempt, not a successful publish. A failed send already returns non-zero exit and error JSON — louder than this reminder. The variable is named buzz_reply_call_seen so the code can't pretend otherwise.
• Checked after the per-turn tool-call cap, since a discarded call never ran.
• messages send also covers messages send-diff. Reactions count because the base prompt directs agents to react rather than post a bare acknowledgement.

Known limits, both deliberate and documented: a command assembled at runtime ($CMD) or hidden in a wrapper script is missed; text that merely quotes a send (echo "buzz messages send") matches. Missing a real post is the expensive direction and substring matching is the forgiving one there. Neither edge is pinned by a test, so the matcher stays free to improve.

Budget

Reminders share BUZZ_AGENT_STOP_MAX_REJECTIONS, the existing outer cap on every end-turn objection. Default 3 fits both; at 1 only one fits; at 0 the guard is off with the hooks. A round carrying both a hook objection and a reminder costs one rejection and delivers both texts. An independent budget would either violate that bound or need a second arbitration rule.

Prior art

• feat(mesh): upgrade to v0.74 and make shared agents reply reliably #3467 (closed) built the same detector one layer up in buzz-acp for a different remedy. None of its symbols are on main — this borrows its permission to be coarse, but reads structured data that ACP didn't have.
• fix(acp): retry channel turns that leave a mention unanswered #3648 (open) detects turns with no output at all; a turn with fifteen tool calls and no post counts as output there, so it does not cover this case.
• feat(mesh): upgrade embedded mesh to v0.74 and harden shared compute (split 1/2 of #3467) #3741 (merged) is mesh-only.

Testing

14 new tests. 4 unit tests on the matcher; 10 integration tests through the ACP wire harness: off by default, =0 still off, opted-in silent → exactly 2 reminders then end_turn, registered fake__shell send → 0 reminders, hallucinated fake__shell → still reminded, publish call truncated past the 64-call cap → still reminded, budget 1 → 1 reminder, budget 0 → off, combined _Stop hook objection + reminder → one round both texts and after 2 reminders the hook objection continues alone, unparseable =true → startup error naming the key.

10 mutation checks, each breaking a specific named test — neutralize the nag cap, stop sharing the budget, neutralize buzz_reply_call_seen, drop has/is_hook, ignore the flag, drop the __, drop reactions add, read serialized args, move detection before truncation.

tests/bin/fake_mcp.rs gains FAKE_MCP_SHELL_TOOL=1: it previously exposed no tool with a bare name of shell, so the satisfied-guard path was untestable.

Full cargo test -p buzz-agent green at 9e0ae1f; clippy -D warnings and cargo fmt --check clean.

Unrelated flake found: cancelled_turn_with_usage_emits_notification_before_response (tests/fake_llm.rs) is timing-sensitive. Under 10 loaded cores it fails 2/20 on this branch and 1/20 at unmodified origin/main@02be413b8 — pre-existing, not caused by this change (which is inert without the env var). Flagging so it isn't misattributed to the next PR that's open when CI hits it.

Docs

crates/buzz-agent/README.md is the primary home (env var, recognition contract, limits, budget interaction). docs/MCP_DRIVEN_HOOKS.md gets a short cross-reference explaining this is not a hook — otherwise readers hunt for a _ReplyGuard tool that doesn't exist.

[micspiral]

testing this now

[micspiral]

@tlongwell-block sort of works, but really isn't great for latency - as if it retries a lot, hits the model hard (KV should be warm so that is good at least) but isn't a great experience when it fails (seems to go from seconds to a minute some times if things go bad). Testing more still...

ie a real prompt with agent can be 1.2s reply on a good day, blows out to 30s/minute if it fails to reply, the downside is those retries become a DOS on models depending on where they are hosted, so not sure this is a good approach for either mesh/local or even (espeially) hosted where pay for token.

Will keep digging as there is something good in here tho as it does work a bit.

Is the idea to avoid an additional tool for all models as well? (ie use the shell one - which will argually get better over time so I agree with it)

[micspiral]

@tlongwell-block this I think is ok - KV does help hopefully, and this seems to be net better, so yeah, lets