Give opencode real timeout headroom in Local Agent Guides CI (#7235)
* Raise the opencode invoke timeout in Local Agent Guides CI
The connection (opencode) cell flakes with a 600s timeout reported as guide drift, but it is not a hang: in a passing run the same opencode run finishes in ~482s (08:12:31 to 08:20:33), right against the shared AGENT_INVOKE_TIMEOUT of 600s, so about one run in six drifts past the cap.
opencode is the slow outlier. The print-mode agents (claude -p, codex exec) run one turn against a minimal injected system prompt, while opencode run runs its own full turn with opencode's large system prompt plus a separate small_model call to name the session (start.py pins small_model to the same 4B the server hosts). On a CPU-served gemma-4-E4B that is about 8 minutes, leaving no margin under 600s.
Double opencode's per-invoke timeout in agent-guides-drive.sh and keep the tight 600s cap for the fast agents, so a genuine headless-TTY hang still fails quickly. 1200s stays well under the 40-minute job budget.
* Normalize the agent invoke timeout before doubling it for opencode
Strip an optional trailing 's' from AGENT_INVOKE_TIMEOUT so the opencode
arithmetic, and the "${TIMEOUT}s" timeout message, stay valid if a
timeout(1)-style suffix is ever configured.
* Only double the opencode timeout for a bare-integer seconds value
Guard the arithmetic so a GNU timeout(1) duration suffix (s/m/h/d, including
floats like 0.5s) is passed through unchanged instead of breaking the
expansion; timeout(1) parses those directly. Bare seconds still double.
---------
Co-authored-by: danielhanchen <unslothai@gmail.com>
This commit is contained in:
parent
5f1f30ec82
commit
03590f696e
1 changed files with 17 additions and 0 deletions
17
.github/scripts/agent-guides-drive.sh
vendored
17
.github/scripts/agent-guides-drive.sh
vendored
|
|
@ -36,6 +36,23 @@ AGENT="${2:?usage: agent-guides-drive.sh <mode> <agent>}"
|
|||
# Determinism (seed/temp) is applied at the server level by
|
||||
# serve-unsloth-run.sh --extra; agents inherit it through the API.
|
||||
TIMEOUT="${AGENT_INVOKE_TIMEOUT:-180}"
|
||||
# opencode is the slow outlier. Unlike the print-mode agents (claude -p, codex
|
||||
# exec) it runs a full turn AND a separate small_model call to name the session,
|
||||
# so one connection reply takes ~8 min on a CPU-served 4B -- right at the shared
|
||||
# 600s cap, so the cell flaked when a run drifted past a ~480s success. Give it
|
||||
# headroom (still well under the 40-min job budget); the fast agents keep the
|
||||
# tight cap that still catches a real headless-TTY hang.
|
||||
case "$AGENT" in
|
||||
opencode)
|
||||
# Double it, but only for a bare-integer seconds value. A GNU timeout(1)
|
||||
# duration suffix (s/m/h/d, including floats like 0.5s) is left unchanged so
|
||||
# the arithmetic never sees a non-number; timeout(1) parses it directly.
|
||||
case "$TIMEOUT" in
|
||||
*[!0-9]*) ;;
|
||||
*) TIMEOUT=$(( TIMEOUT * 2 )) ;;
|
||||
esac
|
||||
;;
|
||||
esac
|
||||
|
||||
# Claude refuses --dangerously-skip-permissions outside a sandbox; the CI runner
|
||||
# IS the sandbox, so declare it (mirrors unslothai/scripts launcher.sh). Harmless
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue