scrum4me-docker/bin/run-agent.sh

#!/usr/bin/env bash
# run-agent.sh — daemon-loop
#
# Strategie:
#   - Eerst pre-flight token-check (eenmalig, blokkeert start bij faal)
#   - Loop: tsx /opt/agent/bin/run-one-job.ts (één geclaimde job per iteratie)
#   - Exit 0 → de queue was leeg of de job is afgerond, sleep kort, herhaal
#   - Exit 3 → run-one-job detecteerde TOKEN_EXPIRED in Claude-output
#   - Exit ≠ 0 → exponential backoff, log, schrijf state, herhaal
#   - Bij N opeenvolgende fouten → schrijf UNHEALTHY marker; health
#     endpoint gaat op 503, container blijft runnen voor diagnose
#   - Bij gedetecteerde token-expiry → schrijf TOKEN_EXPIRED marker
#     en exit (compose start opnieuw, maar entrypoint zal dezelfde
#     marker zien via health-server)
#
# Claim/exec-loop zit in bin/run-one-job.ts (Node + tsx); deze shell doet
# alleen daemon/backoff/health/log-rotation. Zie docs/plans/queue-loop-extraction.md
# in de Scrum4Me-repo.

set -uo pipefail   # let op: geen -e, we willen exit-codes inspecteren

source /opt/agent/bin/_lib.sh

: "${AGENT_MAX_FAILURES:=5}"
: "${AGENT_BACKOFF_START:=5}"
: "${AGENT_BACKOFF_FACTOR:=2}"
: "${AGENT_BACKOFF_MAX:=300}"

mkdir -p "${AGENT_LOG_DIR}/runs"

# ----- pre-flight -------------------------------------------------------
log "pre-flight token check"
if ! /opt/agent/bin/check-tokens.sh; then
    log "pre-flight failed — see check-tokens output above"
    write_state '{"status":"unhealthy","reason":"preflight-failed"}'
    touch "${AGENT_STATE_DIR}/UNHEALTHY"
    # Blijf hangen zodat health-endpoint debugbaar blijft, maar herstart
    # niet de hele compose service onnodig.
    sleep infinity
fi

rm -f "${AGENT_STATE_DIR}/UNHEALTHY" "${AGENT_STATE_DIR}/TOKEN_EXPIRED"

# Log-rotation eenmaal aan het begin, daarna elke iteratie.
/opt/agent/bin/rotate-logs.sh || true
/opt/agent/bin/log-cleanup.sh || true

# Geen seed-prompt en geen ALLOWED_TOOLS-string meer: per-job CLI-flags
# (incl. --model, --permission-mode, --effort, --allowedTools en de
# kind-specifieke prompt) worden door run-one-job.ts gebouwd uit
# JobConfig (resolved via PBI-67's resolveJobConfig).

CONSEC_FAILURES=0
BACKOFF=${AGENT_BACKOFF_START}

while true; do
    iteration_start=$(date -u +%Y-%m-%dT%H:%M:%SZ)
    run_log="${AGENT_LOG_DIR}/runs/$(date -u +%Y%m%dT%H%M%SZ).log"

    write_state "$(jq -n \
        --arg started "$iteration_start" \
        --argjson failures "$CONSEC_FAILURES" \
        '{status:"running", currentBatchStartedAt:$started, consecutiveFailures:$failures}')"

    log "starting iteration (log: ${run_log})"

    # Eén iteratie = één geclaimde job (of "geen job" → exit 0). De runner
    # claimt zelf via tryClaimJob, leest JobConfig (PBI-67), bouwt de
    # juiste Claude CLI-args, spawnt 'claude', wacht, sluit af.
    set +e
    tsx /opt/agent/bin/run-one-job.ts > "${run_log}" 2>&1
    exit_code=$?
    set -e

    iteration_end=$(date -u +%Y-%m-%dT%H:%M:%SZ)
    log "batch ended exit=${exit_code}"

    # Token-expiry detectie: run-one-job.ts retourneert exit 3 wanneer het
    # bekende auth-error-strings in Claude's output ziet. We checken óók de
    # log-tekst voor het geval een ander pad het patroon raakt (bv. Prisma-
    # connection-error met OAuth-expired in error-body).
    if [[ "$exit_code" -eq 3 ]] || grep -qE '(invalid_api_key|authentication.*failed|401.*unauthor|OAuth.*expired)' "${run_log}"; then
        log "AUTH FAILURE detected (exit=$exit_code or pattern in log) — marking TOKEN_EXPIRED"
        touch "${AGENT_STATE_DIR}/TOKEN_EXPIRED"
        write_state "$(jq -n \
            --arg endedAt "$iteration_end" \
            --argjson exit "$exit_code" \
            '{status:"token-expired", lastBatchAt:$endedAt, lastBatchExit:$exit}')"
        # Blijf hangen — geen herstart, gebruiker moet rebuild doen.
        sleep infinity
    fi

    if [[ "$exit_code" -eq 0 ]]; then
        CONSEC_FAILURES=0
        BACKOFF=${AGENT_BACKOFF_START}
        write_state "$(jq -n \
            --arg endedAt "$iteration_end" \
            '{status:"idle", lastBatchAt:$endedAt, lastBatchExit:0, consecutiveFailures:0}')"
        log "queue empty — sleep 2s"
        sleep 2
    else
        CONSEC_FAILURES=$((CONSEC_FAILURES + 1))
        write_state "$(jq -n \
            --arg endedAt "$iteration_end" \
            --argjson exit "$exit_code" \
            --argjson failures "$CONSEC_FAILURES" \
            '{status:"backoff", lastBatchAt:$endedAt, lastBatchExit:$exit, consecutiveFailures:$failures}')"

        if [[ "$CONSEC_FAILURES" -ge "$AGENT_MAX_FAILURES" ]]; then
            log "too many consecutive failures (${CONSEC_FAILURES}) — marking UNHEALTHY"
            touch "${AGENT_STATE_DIR}/UNHEALTHY"
            sleep infinity
        fi

        log "backing off ${BACKOFF}s before retry"
        sleep "$BACKOFF"
        BACKOFF=$(( BACKOFF * AGENT_BACKOFF_FACTOR ))
        if [[ "$BACKOFF" -gt "$AGENT_BACKOFF_MAX" ]]; then
            BACKOFF=$AGENT_BACKOFF_MAX
        fi
    fi

    /opt/agent/bin/rotate-logs.sh || true
    /opt/agent/bin/log-cleanup.sh || true
done