#!/usr/bin/env bash
# scripts/install/s2-models.sh — S2: model + aux vision config
#
# Configures inference via openshell/nemohermes and runs vision smoke test.
# Platform-first: all mutations through nemohermes/openshell CLIs.
#
# Usage:
#   ./scripts/install/s2-models.sh
#   (called by install.sh --stage s2)

set -euo pipefail

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

# Source shared helpers (common.sh sets REPO_ROOT via git rev-parse)
# shellcheck source=../lib/common.sh
source "$SCRIPT_DIR/../lib/common.sh"
# shellcheck source=../lib/env.sh
source "$SCRIPT_DIR/../lib/env.sh"
# shellcheck source=../lib/vision_smoke.sh
source "$SCRIPT_DIR/../lib/vision_smoke.sh"

log_section "S2: Model + vision configuration"

# ── Load .env ──────────────────────────────────────────────────────────────
load_env

# ── Validate required keys ─────────────────────────────────────────────────
validate_env || exit 1

# ── Check CLI prerequisites ────────────────────────────────────────────────
require_cmd openshell "Install OpenShell CLI (part of NemoClaw platform)"
require_cmd nemohermes "Install nemohermes CLI (part of NemoClaw platform)"

# ── Verify inference endpoint is reachable ─────────────────────────────────
# LUMINA_INFERENCE_BASE_URL includes /v1 (e.g. http://host:port/v1)
log_info "Verifying inference endpoint: $LUMINA_INFERENCE_BASE_URL"
if ! curl -sf --max-time 15 "${LUMINA_INFERENCE_BASE_URL}/models" &>/dev/null; then
  log_error "Inference endpoint unreachable at $LUMINA_INFERENCE_BASE_URL"
  log_error "Check that the model server is running and the URL is correct."
  log_error "Fix LUMINA_INFERENCE_BASE_URL in .env and re-run."
  exit 1
fi
log_info "Inference endpoint reachable."

# ── Configure inference via openshell ──────────────────────────────────────
# Only set if the gateway is connected and we can reach it.
# If the gateway is not yet set up, we validate the endpoint and skip
# the openshell write (S3+ will handle full gateway config).
log_info "Checking OpenShell gateway status…"
if openshell status &>/dev/null 2>&1; then
  log_info "Gateway connected — configuring inference route…"

  # Use openshell inference set to configure the main model.
  # openshell inference set takes --provider and --model but NOT --url.
  # The gateway resolves the endpoint URL from its own metadata (the
  # compatible-endpoint provider reads the URL from the gateway config).
  # --no-verify skips the endpoint verification that openshell does internally
  # since we already verified above.
  if openshell inference set \
      --provider compatible-endpoint \
      --model "$LUMINA_INFERENCE_MODEL" \
      --no-verify 2>&1; then
    log_info "Inference route configured via openshell."
  else
    log_warn "openshell inference set returned non-zero."
    log_warn "The gateway may already have this route configured, or the gateway"
    log_warn "requires a different provider name. Check with: openshell inference get"
  fi
else
  log_warn "OpenShell gateway not connected — skipping inference route configuration."
  log_warn "Inference will be configured when the gateway is available (S3+)."
  log_warn "Ensure LUMINA_INFERENCE_BASE_URL and LUMINA_INFERENCE_MODEL are correct in .env."
fi

# ── Vision smoke test ──────────────────────────────────────────────────────
vision_smoke || {
  log_error "Vision smoke test FAILED."
  log_error "The inference endpoint does not appear to support multimodal/vision."
  log_error "Check:"
  log_error "  1. LUMINA_VISION_MODEL points to a vision-capable model"
  log_error "  2. The model server supports multimodal inputs"
  log_error "  3. LUMINA_INFERENCE_BASE_URL is correct"
  exit 1
}

log_info "S2 complete: model configured, vision smoke passed."