mirror of
https://github.com/boshu2/agentops.git
synced 2026-09-14 15:08:13 +08:00
Claude
41c71f54d6
The 2026-04-22 nightly-dream-cycle learning (.agents/learnings/2026-04-22-close-loop-citation-gate-deadlock.md) lists three corrective actions for the chicken-and-egg promotion deadlock that silently zeroed throughput for weeks: 1. Split admission gates by path — DONE (b69a00f) 2. Parameterize shared helpers (requireCitations bool) — DONE (b69a00f) 3. Fail loudly if ingested > 0 && promoted == 0 — this commit Prior to this commit, scripts/nightly-dream-cycle.sh reported both numbers in the summary but never asserted their relationship, so the deadlock surfaced only in downstream metrics (sigma=0, escape_velocity=false) — exactly the "quietly posting another zero-throughput status issue" pattern the learning warns against. Changes: - scripts/check-dream-throughput.sh (new): standalone gate consuming 'ao flywheel close-loop --json'. Exits 1 on the deadlock pattern (added > 0 && promoted == 0), 0 on healthy / no-op, 2 on bad input. Uses the same pattern as the sibling check-compile-*.sh gates. - scripts/nightly-dream-cycle.sh: invokes the gate after the summary artifacts are written (so uploads still succeed) and exits non-zero when a stall is detected. NIGHTLY_DREAM_STRICT=0 downgrades to warn for diagnostic runs. The summary.json grows a close_loop.throughput_stalled bool; the summary.md renders a banner above the stage table when the stall fires, so the auto-filed "Nightly dream cycle status" issue leads with it. - tests/scripts/check-dream-throughput.bats (new): 8 cases covering healthy, empty-run, deadlock, missing input, no-arg, non-integer input, and missing keys. Verified locally against all 8 cases via direct bash invocation (bats is not available in this environment); shell syntax validated with 'bash -n' on both scripts.
60 lines
1.9 KiB
Bash
Executable File
60 lines
1.9 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# check-dream-throughput.sh — Gate: dream-cycle close-loop pipeline produced
|
|
# non-zero throughput for the candidates it ingested.
|
|
#
|
|
# Guards against the chicken-and-egg gate deadlock documented in
|
|
# .agents/learnings/2026-04-22-close-loop-citation-gate-deadlock.md: when
|
|
# fresh candidates were ingested but none reached auto-promotion, the pipeline
|
|
# is stalled regardless of how "clean" each stage looks in isolation.
|
|
#
|
|
# Consumes the JSON shape emitted by `ao flywheel close-loop --json`:
|
|
# {"ingest":{"added":N},"auto_promote":{"promoted":M}}
|
|
#
|
|
# Exit codes:
|
|
# 0 PASS — either no ingest this run, or promoted > 0
|
|
# 1 FAIL — ingest.added > 0 && auto_promote.promoted == 0 (stall)
|
|
# 2 ERROR — missing/invalid input
|
|
#
|
|
# Usage: check-dream-throughput.sh <close-loop.json>
|
|
set -euo pipefail
|
|
|
|
INPUT="${1:-}"
|
|
if [[ -z "$INPUT" ]]; then
|
|
echo "usage: $0 <close-loop.json>" >&2
|
|
exit 2
|
|
fi
|
|
if [[ ! -f "$INPUT" ]]; then
|
|
echo "ERROR: $INPUT not found" >&2
|
|
exit 2
|
|
fi
|
|
if ! command -v jq >/dev/null 2>&1; then
|
|
echo "ERROR: jq not found" >&2
|
|
exit 2
|
|
fi
|
|
|
|
added="$(jq -r '.ingest.added // 0' "$INPUT" 2>/dev/null || echo "")"
|
|
promoted="$(jq -r '.auto_promote.promoted // 0' "$INPUT" 2>/dev/null || echo "")"
|
|
|
|
if ! [[ "$added" =~ ^[0-9]+$ ]] || ! [[ "$promoted" =~ ^[0-9]+$ ]]; then
|
|
echo "ERROR: could not parse .ingest.added / .auto_promote.promoted as integers in $INPUT" >&2
|
|
exit 2
|
|
fi
|
|
|
|
if (( added > 0 && promoted == 0 )); then
|
|
cat >&2 <<EOF
|
|
FAIL: dream close-loop throughput stall
|
|
ingest.added=$added but auto_promote.promoted=0
|
|
A nonzero ingest with zero promotions is a deadlocked pipeline, not a
|
|
steady state. See .agents/learnings/2026-04-22-close-loop-citation-gate-deadlock.md.
|
|
EOF
|
|
exit 1
|
|
fi
|
|
|
|
if (( added == 0 )); then
|
|
echo "OK: no candidates ingested this run (ingest.added=0); nothing to promote"
|
|
exit 0
|
|
fi
|
|
|
|
echo "PASS: auto_promote.promoted=$promoted / ingest.added=$added"
|
|
exit 0
|