golangLAKEHOUSE/scripts/doctor.sh

#!/usr/bin/env bash
# Dependency probe for golangLAKEHOUSE.
# Sprint 0 / S0.1 — surfaces every cold-start dep as a structured
# checklist. With --json, emits machine-readable shape for CI.
#
# Exit 0 = all green. Exit 1 = at least one missing dep.

set -uo pipefail

# Mode: text (default) or json
JSON=0
for arg in "$@"; do
    case "$arg" in
        --json) JSON=1 ;;
        -h|--help)
            echo "Usage: $0 [--json]"
            echo "  Probes Go, gcc, MinIO, Ollama, secrets-go.toml."
            echo "  Default output is human-readable; --json emits structured findings."
            exit 0 ;;
    esac
done

# Findings accumulator. Each entry: <name>|<status>|<detail>|<fix>
# status ∈ {ok, missing, wrong-version, unreachable}
findings=()

probe() {
    findings+=("$1|$2|$3|$4")
}

# 1. Go ≥1.25 (arrow-go pulled the floor up — see ADR-001 §1.x)
if go_path="$(command -v go 2>/dev/null)"; then
    go_ver="$(go version 2>/dev/null | awk '{print $3}' | sed 's/^go//')"
    case "$go_ver" in
        1.25*|1.26*|1.27*) probe "go" "ok" "$go_ver at $go_path" "" ;;
        *)                 probe "go" "wrong-version" "$go_ver at $go_path (need ≥1.25)" \
                                  "curl -L https://go.dev/dl/go1.25.0.linux-amd64.tar.gz | sudo tar -C /usr/local -xz" ;;
    esac
else
    probe "go" "missing" "not in PATH" \
          "curl -L https://go.dev/dl/go1.25.0.linux-amd64.tar.gz | sudo tar -C /usr/local -xz && export PATH=\$PATH:/usr/local/go/bin"
fi

# 2. gcc (DuckDB cgo binding per ADR-001 §1.1)
if gcc_path="$(command -v gcc 2>/dev/null)"; then
    gcc_ver="$(gcc --version 2>/dev/null | head -1 | awk '{print $NF}')"
    probe "gcc" "ok" "$gcc_ver at $gcc_path" ""
else
    probe "gcc" "missing" "not in PATH" "sudo apt install -y build-essential"
fi

# 3. MinIO at :9000 with bucket lakehouse-go-primary
if curl -sf --max-time 2 http://localhost:9000/minio/health/live >/dev/null 2>&1; then
    # bucket existence — use mc if available, else fall back to noting it
    if command -v mc >/dev/null 2>&1; then
        if mc ls local/lakehouse-go-primary >/dev/null 2>&1; then
            probe "minio" "ok" "live at :9000, bucket lakehouse-go-primary present" ""
        else
            probe "minio" "missing" "live at :9000 but bucket lakehouse-go-primary absent" \
                  "mc mb local/lakehouse-go-primary"
        fi
    else
        probe "minio" "ok" "live at :9000 (bucket presence not verified — install mc to check)" ""
    fi
else
    probe "minio" "unreachable" "no /minio/health/live response on :9000" \
          "sudo systemctl start minio  # or restart"
fi

# 4. Ollama at :11434 with nomic-embed-text loaded (G2 default model)
if ollama_resp="$(curl -sf --max-time 3 http://localhost:11434/api/tags 2>/dev/null)"; then
    if echo "$ollama_resp" | grep -q '"name":"nomic-embed-text:latest"'; then
        probe "ollama" "ok" "live at :11434, nomic-embed-text loaded" ""
    else
        probe "ollama" "missing" "live at :11434 but nomic-embed-text not loaded" \
              "ollama pull nomic-embed-text"
    fi
else
    probe "ollama" "unreachable" "no /api/tags response on :11434" \
          "sudo systemctl start ollama"
fi

# 5. /etc/lakehouse/secrets-go.toml
if [ -f /etc/lakehouse/secrets-go.toml ]; then
    if [ -r /etc/lakehouse/secrets-go.toml ]; then
        if grep -q '\[s3.primary\]' /etc/lakehouse/secrets-go.toml 2>/dev/null; then
            probe "secrets" "ok" "/etc/lakehouse/secrets-go.toml present, contains [s3.primary]" ""
        else
            probe "secrets" "missing" "/etc/lakehouse/secrets-go.toml missing [s3.primary] section" \
                  "edit /etc/lakehouse/secrets-go.toml to add [s3.primary] with access_key_id + secret_access_key"
        fi
    else
        probe "secrets" "missing" "/etc/lakehouse/secrets-go.toml exists but unreadable by current user" \
              "sudo chmod 0644 /etc/lakehouse/secrets-go.toml  # or run as the user that can read it"
    fi
else
    probe "secrets" "missing" "/etc/lakehouse/secrets-go.toml not present" \
          "sudo install -m 0644 /dev/stdin /etc/lakehouse/secrets-go.toml < secrets-go.toml.example"
fi

# Summarize
exit_code=0
for f in "${findings[@]}"; do
    case "$(echo "$f" | cut -d'|' -f2)" in
        ok) ;;
        *) exit_code=1 ;;
    esac
done

if [ "$JSON" -eq 1 ]; then
    printf '{\n'
    printf '  "deps": [\n'
    last=$((${#findings[@]} - 1))
    for i in "${!findings[@]}"; do
        IFS='|' read -r name status detail fix <<< "${findings[$i]}"
        printf '    {"name":"%s","status":"%s","detail":"%s","fix":"%s"}' \
               "$name" "$status" \
               "$(echo "$detail" | sed 's/"/\\"/g')" \
               "$(echo "$fix" | sed 's/"/\\"/g')"
        [ "$i" -lt "$last" ] && printf ','
        printf '\n'
    done
    printf '  ],\n'
    printf '  "ok": %s\n' "$([ $exit_code -eq 0 ] && echo true || echo false)"
    printf '}\n'
else
    echo "[doctor] dependency probe:"
    for f in "${findings[@]}"; do
        IFS='|' read -r name status detail fix <<< "$f"
        case "$status" in
            ok)              printf "  ✓ %-7s  %s\n" "$name" "$detail" ;;
            missing)         printf "  ✗ %-7s  %s\n" "$name" "$detail"
                             [ -n "$fix" ] && printf "      fix: %s\n" "$fix" ;;
            wrong-version)   printf "  ⚠ %-7s  %s\n" "$name" "$detail"
                             [ -n "$fix" ] && printf "      fix: %s\n" "$fix" ;;
            unreachable)     printf "  ✗ %-7s  %s\n" "$name" "$detail"
                             [ -n "$fix" ] && printf "      fix: %s\n" "$fix" ;;
        esac
    done
    if [ "$exit_code" -eq 0 ]; then
        echo "[doctor] all dependencies green"
    else
        echo "[doctor] one or more dependencies need attention"
    fi
fi

exit "$exit_code"