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: claude -p met seed-prompt
#   - Exit 0 → de queue was leeg, sleep kort, herhaal
#   - 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)

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

# ----- seed prompt ------------------------------------------------------
SEED_PROMPT='Pak de volgende job uit de Scrum4Me-queue en draai de queue leeg volgens de loop in /opt/agent/CLAUDE.md. Niet stoppen tussen jobs door. Sluit pas af zodra wait_for_job na de volledige block-time terugkomt zonder claim.'

# Tools-allowlist: alle MCP-tools die scrum4me-mcp aanbiedt + standaard
# file/bash-tools. Geen WebFetch, geen WebSearch — de agent heeft die
# niet nodig en uitsluiting verkleint het surface.
ALLOWED_TOOLS='Read,Edit,Write,Bash,Grep,Glob,mcp__scrum4me__health,mcp__scrum4me__list_products,mcp__scrum4me__get_claude_context,mcp__scrum4me__wait_for_job,mcp__scrum4me__check_queue_empty,mcp__scrum4me__update_job_status,mcp__scrum4me__update_task_status,mcp__scrum4me__update_task_plan,mcp__scrum4me__log_implementation,mcp__scrum4me__log_test_result,mcp__scrum4me__log_commit,mcp__scrum4me__create_pbi,mcp__scrum4me__create_story,mcp__scrum4me__create_task,mcp__scrum4me__create_todo,mcp__scrum4me__ask_user_question,mcp__scrum4me__get_question_answer,mcp__scrum4me__list_open_questions,mcp__scrum4me__cancel_question'

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 batch (log: ${run_log})"

    # claude -p met onze MCP-config en allowlist.
    # cwd = /opt/agent zodat onze CLAUDE.md auto-geladen wordt.
    #
    # --permission-mode bypassPermissions: alle resterende permission-
    # prompts uit. Veilig in deze container omdat (1) we draaien als
    # non-root agent-user, (2) geen push-credentials, (3) writes
    # gelimiteerd tot /tmp/job-*. De allowlist hierboven blijft als
    # belt-and-braces second filter.
    set +e
    claude -p "${SEED_PROMPT}" \
        --mcp-config /opt/agent/mcp-config.json \
        --allowedTools "${ALLOWED_TOOLS}" \
        --permission-mode bypassPermissions \
        --output-format text \
        > "${run_log}" 2>&1
    exit_code=$?
    set -e

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

    # Token-expiry detectie: parse stderr/stdout op bekende strings.
    if grep -qE '(invalid_api_key|authentication.*failed|401.*unauthor|OAuth.*expired)' "${run_log}"; then
        log "AUTH FAILURE detected in run log — marking TOKEN_EXPIRED"
        touch "${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
done