Salon_Assistant/scripts/doctor.sh

#!/usr/bin/env bash
# scripts/doctor.sh — S6: Lumina product health checks
#
# Composes platform-layer health checks:
#   Docker · nemohermes · openshell · sandbox · policy · skills · inference
#
# Platform-first: wraps nemohermes / openshell / Docker. No parallel control API.
#
# Usage:
#   ./scripts/doctor.sh              # full check
#   ./scripts/doctor.sh --json       # machine-readable summary
#   ./scripts/doctor.sh --help

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"

# Source shared helpers
# shellcheck source=lib/common.sh
source "$SCRIPT_DIR/lib/common.sh"
# shellcheck source=lib/env.sh
source "$SCRIPT_DIR/lib/env.sh"

# ── Defaults ───────────────────────────────────────────────────────────────
JSON_OUTPUT=0

# ── Parse args ─────────────────────────────────────────────────────────────
while [[ $# -gt 0 ]]; do
  case "$1" in
    --help|-h)
      cat <<EOF
Usage: $(basename "$0") [OPTIONS]

S6: Lumina product health checks.

Checks:
  Docker daemon, nemohermes CLI, openshell CLI, sandbox status,
  policy overlays, skills directory, inference endpoint.

Options:
  --json    Machine-readable JSON summary
  --help    Show this help

Exit codes:
  0  All critical checks passed (warnings are non-fatal)
  1  One or more critical checks failed
EOF
      exit 0
      ;;
    --json)
      JSON_OUTPUT=1
      shift
      ;;
    *)
      log_error "Unknown argument: $1"
      exit 1
      ;;
  esac
done

# ── State tracking ─────────────────────────────────────────────────────────
CRITICAL_FAIL=0
WARN_COUNT=0
declare -a CHECK_RESULTS=()

# Strip ANSI escape codes from a string
strip_ansi() {
  sed 's/\x1b\[[0-9;]*m//g' <<< "$1"
}

# Record a check result: "group|label|status|detail"
record_check() {
  local group="$1" label="$2" status="$3" detail="$4"
  # Strip any ANSI codes that may have leaked from CLI output
  detail="$(strip_ansi "$detail")"
  CHECK_RESULTS+=("${group}|${label}|${status}|${detail}")
  if [[ "$status" == "FAIL" ]]; then
    CRITICAL_FAIL=1
  elif [[ "$status" == "WARN" ]]; then
    WARN_COUNT=$((WARN_COUNT + 1))
  fi
}

# ── Load .env (best-effort; warn if missing) ───────────────────────────────
if [[ $JSON_OUTPUT -eq 1 ]]; then
  load_env >/dev/null 2>&1 || true
else
  load_env 2>/dev/null || true
fi

SANDBOX_NAME="$(get_sandbox_name)"
SKILLS_DIR="$REPO_ROOT/skills"
POLICY_DIR="$REPO_ROOT/policy/openshell/overlays"

# ── Check: Docker ──────────────────────────────────────────────────────────
check_docker() {
  if ! cmd_exists docker; then
    record_check "Docker" "CLI" "FAIL" "docker command not found"
    return
  fi
  if ! docker info &>/dev/null; then
    record_check "Docker" "Daemon" "FAIL" "docker daemon not running or not accessible"
    return
  fi
  local version
  version="$(docker --version 2>/dev/null | sed 's/^Docker version //' | cut -d',' -f1 | tr -d ' ')"
  record_check "Docker" "Daemon" "OK" "running ($version)"
}

# ── Check: nemohermes CLI ──────────────────────────────────────────────────
check_nemohermes() {
  if ! cmd_exists nemohermes; then
    record_check "CLI" "nemohermes" "FAIL" "nemohermes not found — install NemoClaw platform"
    return
  fi
  local version
  version="$(nemohermes --version 2>/dev/null | head -1 | grep -oP 'v[\d.]+' || echo 'unknown')"
  record_check "CLI" "nemohermes" "OK" "$version"
}

# ── Check: openshell CLI ───────────────────────────────────────────────────
check_openshell() {
  if ! cmd_exists openshell; then
    record_check "CLI" "openshell" "FAIL" "openshell not found — install OpenShell"
    return
  fi
  local version
  version="$(openshell --version 2>/dev/null | head -1 | grep -oP '[\d.]+' || echo 'unknown')"
  record_check "CLI" "openshell" "OK" "$version"
}

# ── Check: Sandbox status ──────────────────────────────────────────────────
check_sandbox() {
  # Skip if nemohermes is missing (already flagged)
  if ! cmd_exists nemohermes; then
    record_check "Sandbox" "Status" "FAIL" "skipped — nemohermes not available"
    return
  fi

  # Run nemohermes doctor for the sandbox — this is the authoritative platform check
  local doctor_output
  doctor_output="$(nemohermes "$SANDBOX_NAME" doctor 2>&1)" || true

  # Check for summary line
  if echo "$doctor_output" | grep -qi "Summary: healthy"; then
    record_check "Sandbox" "Doctor" "OK" "$SANDBOX_NAME healthy"
  elif echo "$doctor_output" | grep -qi "Summary:.*warning"; then
    record_check "Sandbox" "Doctor" "WARN" "$SANDBOX_NAME has warnings"
  elif echo "$doctor_output" | grep -qi "Summary:.*unhealthy\|Summary:.*critical"; then
    record_check "Sandbox" "Doctor" "FAIL" "$SANDBOX_NAME unhealthy"
  else
    # Fallback: check status command
    if nemohermes "$SANDBOX_NAME" status &>/dev/null; then
      record_check "Sandbox" "Status" "OK" "$SANDBOX_NAME reachable"
    else
      record_check "Sandbox" "Status" "FAIL" "$SANDBOX_NAME not found or not reachable"
    fi
  fi
}

# ── Check: Policy overlays ─────────────────────────────────────────────────
check_policy() {
  # Skip if nemohermes is missing
  if ! cmd_exists nemohermes; then
    record_check "Policy" "Overlays" "FAIL" "skipped — nemohermes not available"
    return
  fi

  # Check that policy overlay files exist in the repo
  local inference_policy="$POLICY_DIR/inference.yaml"
  if [[ ! -f "$inference_policy" ]]; then
    record_check "Policy" "Overlay files" "WARN" "inference.yaml not found in $POLICY_DIR"
  fi

  # Check that lumina-inference preset is applied in the sandbox
  local policy_list
  policy_list="$(nemohermes "$SANDBOX_NAME" policy-list 2>&1)" || {
    record_check "Policy" "policy-list" "FAIL" "could not list policy presets"
    return
  }

  if echo "$policy_list" | grep -q "lumina-inference"; then
    record_check "Policy" "lumina-inference" "OK" "preset applied"
  else
    record_check "Policy" "lumina-inference" "WARN" "preset not found in sandbox — run S5 or: nemohermes $SANDBOX_NAME policy-add --from-file $inference_policy --yes"
  fi
}

# ── Check: Skills ──────────────────────────────────────────────────────────
check_skills() {
  if [[ ! -d "$SKILLS_DIR" ]]; then
    record_check "Skills" "Directory" "FAIL" "skills directory not found at $SKILLS_DIR"
    return
  fi

  # Count skill directories (exclude _lib and hidden)
  local skill_count=0
  local skill_with_md=0
  for skill_dir in "$SKILLS_DIR"/*/; do
    [[ -d "$skill_dir" ]] || continue
    local name
    name="$(basename "$skill_dir")"
    [[ "$name" == "_lib" ]] && continue
    [[ "$name" == "README.md" ]] && continue
    skill_count=$((skill_count + 1))
    if [[ -f "$skill_dir/SKILL.md" ]]; then
      skill_with_md=$((skill_with_md + 1))
    fi
  done

  if [[ $skill_count -eq 0 ]]; then
    record_check "Skills" "Pack" "WARN" "no skill directories found in $SKILLS_DIR"
  elif [[ $skill_with_md -lt $skill_count ]]; then
    record_check "Skills" "Pack" "WARN" "$skill_with_md/$skill_count skills have SKILL.md"
  else
    record_check "Skills" "Pack" "OK" "$skill_count skills with SKILL.md"
  fi
}

# ── Check: Inference endpoint ──────────────────────────────────────────────
check_inference() {
  # Check .env has the required keys
  local env_file="${REPO_ROOT}/.env"
  if [[ ! -f "$env_file" ]]; then
    record_check "Inference" "Config" "FAIL" ".env not found — run S1 first"
    return
  fi

  # Source .env to get variables (already done by load_env, but verify)
  local base_url="${LUMINA_INFERENCE_BASE_URL:-}"
  local model="${LUMINA_INFERENCE_MODEL:-}"

  if [[ -z "$base_url" ]]; then
    record_check "Inference" "Endpoint URL" "FAIL" "LUMINA_INFERENCE_BASE_URL not set in .env"
    return
  fi

  if [[ -z "$model" ]]; then
    record_check "Inference" "Model" "FAIL" "LUMINA_INFERENCE_MODEL not set in .env"
    return
  fi

  # Check endpoint reachability
  local url="$base_url"
  # Ensure URL ends with /v1 for the models endpoint
  if [[ "$url" != */v1 && "$url" != */v1/* ]]; then
    url="${url%/}/v1"
  fi

  if curl -sf --max-time 15 "${url}/models" &>/dev/null; then
    record_check "Inference" "Endpoint" "OK" "reachable ($base_url)"
  else
    record_check "Inference" "Endpoint" "FAIL" "unreachable at $base_url"
  fi

  # Check openshell inference config (optional — gateway may not be connected)
  if cmd_exists openshell; then
    local inf_output
    inf_output="$(openshell inference get 2>&1)" || true
    if echo "$inf_output" | grep -q "Provider:"; then
      local provider
      # Strip ANSI escape codes and whitespace
      provider="$(echo "$inf_output" | grep "Provider:" | head -1 | sed 's/.*Provider: *//' | sed 's/\x1b\[[0-9;]*m//g' | tr -d '[:space:]')"
      record_check "Inference" "Gateway route" "OK" "configured ($provider)"
    else
      record_check "Inference" "Gateway route" "WARN" "not configured via openshell"
    fi
  fi
}

# ── Run all checks ─────────────────────────────────────────────────────────
if [[ $JSON_OUTPUT -eq 0 ]]; then
  log_section "Lumina Doctor (S6)"
fi

check_docker
check_nemohermes
check_openshell
check_sandbox
check_policy
check_skills
check_inference

# ── Output results ─────────────────────────────────────────────────────────
if [[ $JSON_OUTPUT -eq 1 ]]; then
  # Machine-readable JSON summary
  checks_json="["
  first=1
  for entry in "${CHECK_RESULTS[@]}"; do
    IFS='|' read -r group label status detail <<< "$entry"
    if [[ $first -eq 1 ]]; then
      first=0
    else
      checks_json+=","
    fi
    # Escape backslashes first, then double quotes (JSON-safe)
    detail="${detail//\\/\\\\}"
    detail="${detail//\"/\\\"}"
    checks_json+="{\"group\":\"$group\",\"label\":\"$label\",\"status\":\"$status\",\"detail\":\"$detail\"}"
  done
  checks_json+="]"

  overall="healthy"
  [[ $CRITICAL_FAIL -eq 1 ]] && overall="unhealthy"

  cat <<EOF
{
  "product": "Lumina",
  "stage": "S6",
  "sandbox": "$SANDBOX_NAME",
  "overall": "$overall",
  "critical_failures": $CRITICAL_FAIL,
  "warnings": $WARN_COUNT,
  "checks": $checks_json
}
EOF
else
  # Human-readable summary
  log_section "Results"

  ok_count=0
  warn_count=0
  fail_count=0

  for entry in "${CHECK_RESULTS[@]}"; do
    IFS='|' read -r group label status detail <<< "$entry"
    case "$status" in
      OK)   printf "  \033[0;32m[OK]\033[0m   %-12s %s — %s\n" "$group" "$label" "$detail" ;;
      WARN) printf "  \033[1;33m[WARN]\033[0m %-12s %s — %s\n" "$group" "$label" "$detail" ;;
      FAIL) printf "  \033[0;31m[FAIL]\033[0m %-12s %s — %s\n" "$group" "$label" "$detail" ;;
    esac
    case "$status" in
      OK)   ok_count=$((ok_count + 1)) ;;
      WARN) warn_count=$((warn_count + 1)) ;;
      FAIL) fail_count=$((fail_count + 1)) ;;
    esac
  done

  log_section "Summary"
  printf "  Checks: %d OK, %d WARN, %d FAIL\n" "$ok_count" "$warn_count" "$fail_count"

  if [[ $CRITICAL_FAIL -eq 1 ]]; then
    printf "  Overall: \033[0;31mUNHEALTHY\033[0m\n"
  elif [[ $WARN_COUNT -gt 0 ]]; then
    printf "  Overall: \033[1;33mHEALTHY (with warnings)\033[0m\n"
  else
    printf "  Overall: \033[0;32mHEALTHY\033[0m\n"
  fi
fi

# ── Exit code ──────────────────────────────────────────────────────────────
if [[ $CRITICAL_FAIL -eq 1 ]]; then
  exit 1
fi
exit 0