Raise the `buzz-dev-mcp` shell timeout ceiling to 1,200,000 ms (20
minutes) while keeping the omitted-value default at 120,000 ms (2
minutes), and align the two outer timeout layers that bound every MCP
tool call.
## What changed
**`crates/buzz-dev-mcp`** — shell timeout cap raised to 1,200,000 ms;
tool and parameter descriptions updated to match.
**`crates/buzz-agent`** — `BUZZ_AGENT_TOOL_TIMEOUT_SECS` default raised
from 660 s to 1,260 s (20-min cap + 60 s cleanup headroom). The old 660
s default would have killed the MCP server at 11 min, before a 20-min
shell call could finish. README updated.
**`crates/buzz-acp`** — `DEFAULT_IDLE_TIMEOUT_SECS` raised from 900 s to
1,500 s and its doc comment updated (1,200 s max shell + 300 s breathing
room). The old value was documented as "600 s max shell + 300 s" — stale
arithmetic.
## Tests
- Existing boundary tests in `buzz-dev-mcp` (default, exact-cap,
over-cap, `u64::MAX`) all pass.
- `default_idle_timeout_is_1500_seconds` — pinned constant replaces old
900 s assertion.
- `default_tool_timeout_is_1260_seconds` — new pinned constant in
`buzz-agent`.
-
`budget_ordering_invariant_shell_cap_plus_headroom_fits_within_idle_timeout`
— new const assertion in `buzz-acp` that encodes the full three-layer
ordering: shell cap (1,200 s) ≤ agent tool timeout (1,260 s) < ACP idle
timeout (1,500 s) < max turn duration. A future edit that inverts any
tier fails to compile.
---------
Signed-off-by: Alia <d32955ad69077062930cc46cfe2df30ca9aaf6f8e76422681265e9e9af704d78@buzz.block.builderlab.xyz>
Signed-off-by: Will Pfleger <pfleger.will@gmail.com>
Co-authored-by: Alia <d32955ad69077062930cc46cfe2df30ca9aaf6f8e76422681265e9e9af704d78@buzz.block.builderlab.xyz>
Co-authored-by: Hayt <9e1c23a3fd83f61da34420e4e88ff1b16e45cafcc0cd9019eb07d4ecfa8ca9b0@buzz.block.builderlab.xyz>
## Why
The `todo` tool description does not say when the tool is unnecessary,
so agents use it for single-turn bookkeeping. Scoping it to cross-turn
persistence reduces avoidable control calls while preserving the
checklist for compaction and genuinely multi-turn work.
## What
- Scope `todo` to work that must continue across turns or survive
context compaction
- Tell agents not to use it for work they can finish in the current turn
- Preserve read/replace semantics and the `_Stop` hook behavior
## Risk Assessment
Low to medium — this changes agent tool-selection guidance, not the tool
name, schema, or implementation. The benchmark covers single-turn
completion but not restart, compaction, or long-lived multi-turn
recovery.
## References
- Companion base-prompt change: https://github.com/block/buzz/pull/6186
- Combined benchmark (PR 6186 prompt plus this description): 22/22 pass;
active time 0.3438h → 0.2680h (-22.0%); tool calls 216 → 173 (-19.9%);
todo calls 45 → 0
- Against PR 6186's prompt-only condition: active time 0.2926h → 0.2680h
(-8.4%); tool calls 198 → 173 (-12.6%)
- Results are directional because model and tool behavior is stochastic.
Generated with Codex
Signed-off-by: Salman Mohammed <smohammed@squareup.com>
