result=$(gemini "query" --output-format json)
total=$(echo "$result" | jq '.stats.models | to_entries | map(.value.tokens.total) | add // 0')
cached=$(echo "$result" | jq '.stats.models | to_entries | map(.value.tokens.cached) | add // 0')
billable=$((total - cached))
savings=$((cached * 100 / total))

echo "Total: $total tokens"
echo "Cached: $cached tokens ($savings% savings)"
echo "Billable: $billable tokens"

# Bulk file analysis - use Flash
for file in src/*.ts; do
  gemini "List all exports" -m gemini-2.5-flash --output-format json < "$file"
done

# Security audit - use Pro for quality
gemini "Deep security analysis" -m gemini-2.5-pro --output-format json < critical-auth.ts

# Cost tracking with model info
result=$(gemini "query" --output-format json)
model=$(echo "$result" | jq -r '.stats.models | keys[0]')
tokens=$(echo "$result" | jq '.stats.models | to_entries[0].value.tokens.total')
echo "Used $model: $tokens tokens"

# Instead of N separate calls
# Do one call with all files
cat src/*.ts | gemini "Analyze all TypeScript files for patterns" --output-format json

# Combine related questions
gemini "Answer these questions about the codebase:
1. What is the main architecture pattern?
2. How is authentication handled?
3. What database is used?" --output-format json

# First pass: Quick overview with Flash
overview=$(cat src/*.ts | gemini "List all modules" -m gemini-2.5-flash --output-format json)

# Second pass: Deep dive critical areas with Pro
echo "$overview" | jq -r '.response' | grep "auth\|security" | while read module; do
  gemini "Deep analysis of $module" -m gemini-2.5-pro --output-format json
done

result=$(gemini "query" --output-format json)

# Extract all cost-relevant stats
total_tokens=$(echo "$result" | jq '.stats.models | to_entries | map(.value.tokens.total) | add // 0')
cached_tokens=$(echo "$result" | jq '.stats.models | to_entries | map(.value.tokens.cached) | add // 0')
models_used=$(echo "$result" | jq -r '.stats.models | keys | join(", ")')
tool_calls=$(echo "$result" | jq '.stats.tools.totalCalls // 0')
latency=$(echo "$result" | jq '.stats.models | to_entries | map(.value.api.totalLatencyMs) | add // 0')

echo "$(date): tokens=$total_tokens cached=$cached_tokens models=$models_used tools=$tool_calls latency=${latency}ms" >> usage.log

# Track cumulative usage across a session
total_session_tokens=0
total_session_cached=0
total_session_calls=0

track_usage() {
  local result="$1"
  local tokens=$(echo "$result" | jq '.stats.models | to_entries | map(.value.tokens.total) | add // 0')
  local cached=$(echo "$result" | jq '.stats.models | to_entries | map(.value.tokens.cached) | add // 0')

  total_session_tokens=$((total_session_tokens + tokens))
  total_session_cached=$((total_session_cached + cached))
  total_session_calls=$((total_session_calls + 1))
}

# Use in workflow
result=$(gemini "query 1" --output-format json)
track_usage "$result"

result=$(gemini "query 2" --output-format json)
track_usage "$result"

echo "Session total: $total_session_tokens tokens ($total_session_cached cached) in $total_session_calls calls"

# Use Flash for bulk
gemini "query" -m gemini-2.5-flash --output-format json

# Check cache effectiveness
gemini "query" --output-format json | jq '{total: .stats.models | to_entries | map(.value.tokens.total) | add, cached: .stats.models | to_entries | map(.value.tokens.cached) | add}'

# Minimal output (fewer output tokens)
gemini "Answer in one sentence: {question}" --output-format json