68 lines
2.5 KiB
Bash
Executable File
68 lines
2.5 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Headless runner for the os-context eval — the ONLY valid execution mode
|
|
# (mid-session orchestration behavior under the real global SessionStart-injected
|
|
# prompts/session-start/10-orchestration.md; fresh `claude -p` per rep with cwd = sandbox).
|
|
#
|
|
# Usage: run <scenario> <model> <workdir> [--reps N] [--results FILE]
|
|
#
|
|
# E1P* scenarios get CLAUDE_CODE_SUBAGENT_MODEL=haiku injected into the child
|
|
# environment (the cluster-1 downgrade stub). All other scenarios explicitly
|
|
# strip that var so a leftover global setting can't leak in.
|
|
#
|
|
# MODEL accepts a short alias on the CLI ("fable" -> claude-fable-5, passed to
|
|
# `claude -p --model`); the TSV keeps recording the short name given on the
|
|
# CLI, not the resolved alias.
|
|
set -euo pipefail
|
|
|
|
SCENARIO="${1:?usage: run <scenario> <model> <workdir> [--reps N] [--results FILE]}"
|
|
MODEL="${2:?model required (haiku|sonnet|...)}"
|
|
WORKDIR="${3:?workdir required}"
|
|
shift 3
|
|
|
|
REPS=1
|
|
RESULTS=""
|
|
while [ $# -gt 0 ]; do
|
|
case "$1" in
|
|
--reps) REPS="${2:?--reps needs a number}"; shift 2 ;;
|
|
--results) RESULTS="${2:?--results needs a path}"; shift 2 ;;
|
|
*) echo "unknown option: $1" >&2; exit 2 ;;
|
|
esac
|
|
done
|
|
|
|
EVAL_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
|
|
SCENARIO_FILE="$EVAL_ROOT/scenarios/${SCENARIO}.md"
|
|
[ -f "$SCENARIO_FILE" ] || SCENARIO_FILE="$EVAL_ROOT/scenarios-reserve/${SCENARIO}.md"
|
|
[ -f "$SCENARIO_FILE" ] || { echo "unknown scenario: $SCENARIO" >&2; exit 2; }
|
|
|
|
mkdir -p "$WORKDIR"
|
|
RESULTS="${RESULTS:-$WORKDIR/results.tsv}"
|
|
|
|
TASK="$(awk '/^## Task/{found=1; next} found' "$SCENARIO_FILE")"
|
|
|
|
ENV_PREFIX=(env -u CLAUDE_CODE_SUBAGENT_MODEL)
|
|
case "$SCENARIO" in
|
|
E1P*) ENV_PREFIX=(env CLAUDE_CODE_SUBAGENT_MODEL=haiku) ;;
|
|
esac
|
|
# E5* scenarios take the default env arm above (no downgrade stub) — same
|
|
# case statement, no new arm needed.
|
|
|
|
case "$MODEL" in
|
|
fable) CLI_MODEL="claude-fable-5" ;;
|
|
*) CLI_MODEL="$MODEL" ;;
|
|
esac
|
|
|
|
for rep in $(seq 1 "$REPS"); do
|
|
SANDBOX="$WORKDIR/$SCENARIO-$MODEL-r$rep"
|
|
"$EVAL_ROOT/bin/sandbox" "$SCENARIO" "$SANDBOX" >/dev/null
|
|
|
|
# cwd = sandbox: global plugins' SessionStart hooks fire for real.
|
|
(cd "$SANDBOX" && timeout 1500 "${ENV_PREFIX[@]}" claude -p \
|
|
--model "$CLI_MODEL" \
|
|
--output-format stream-json --verbose \
|
|
--dangerously-skip-permissions \
|
|
"$TASK" > cli-output.jsonl) || echo "claude exited non-zero for $SANDBOX" >&2
|
|
|
|
# check exits 1 on FAIL; guard so pipefail can't abort the remaining reps.
|
|
"$EVAL_ROOT/bin/check" "$SCENARIO" "$SANDBOX" --tsv "$MODEL" "$rep" | tee -a "$RESULTS" || true
|
|
done
|