refactor(prompt): simplify Buzz agent guidance (#6340)

## Why
The Buzz agent prompt carries verbose agent-draft instructions that add
prompt weight without improving benchmark correctness. Buzz-native
channel trials also showed agents creating permanent channels while
claiming they had applied a one-hour TTL. The static CLI inventory
remains for efficient command discovery by smaller agents.

## What
- Retain the static Buzz CLI command table and direct agents to use
`--help` for full usage
- Compact the owner-reviewed agent-draft guidance without changing its
workflow
- Clarify that `buzz channels create` is permanent unless `--ttl` is
provided

## Benchmark Results
- Terminal-Bench retained 22/22 correctness in the initial no-table
candidate while reducing prompt size, input tokens, tool calls, and
cost; total active time was effectively flat.
- Across two Buzz-native runs, the non-channel cases tied at 26/30; the
CLI clarification directly addresses the observed TTL omission.

## Update — 2026-08-20
- Restored the CLI command table following review feedback about
multistep discovery with smaller agents. The restored-table candidate
has not been re-benchmarked.

Signed-off-by: Salman Mohammed <smohammed@squareup.com>
This commit is contained in:
Salman Mohammed
2026-08-20 10:59:57 -04:00
committed by GitHub
parent 2b7be9340d
commit 2a236e4137
2 changed files with 5 additions and 8 deletions

View File

@@ -582,8 +582,9 @@ pub enum ChannelsCmd {
/// Channel description
#[arg(long)]
description: Option<String>,
/// Make the channel ephemeral: lifetime in seconds. The relay archives
/// it once this many seconds pass without a new message.
/// Make the channel temporary/ephemeral: idle lifetime in seconds. If
/// omitted, the channel is permanent. The relay archives it once this
/// many seconds pass without a new message.
#[arg(long, value_name = "SECONDS")]
ttl: Option<i64>,
/// Apply a desktop-local channel template by name (case-insensitive):