[fix] Add cache token capture for Droid OpenAI endpoint

The _parseOpenAIUsageFromSSE method was not capturing cache-related
tokens (cache_read_input_tokens, cache_creation_input_tokens) from
OpenAI format responses, while the Anthropic endpoint correctly
captured them.

This fix adds extraction of:
- cached_tokens from input_tokens_details
- cache_creation_input_tokens from both input_tokens_details and
  top-level usage object

This ensures proper cache statistics tracking and cost calculation
for OpenAI models (like GPT-5/Codex) when using the Droid provider.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

src/services/droidRelayService.js

@@ -737,6 +737,14 @@ class DroidRelayService {
                 currentUsageData.output_tokens = 0
               }
 
+              // Capture cache tokens from OpenAI format
+              currentUsageData.cache_read_input_tokens =
+                data.usage.input_tokens_details?.cached_tokens || 0
+              currentUsageData.cache_creation_input_tokens =
+                data.usage.input_tokens_details?.cache_creation_input_tokens ||
+                data.usage.cache_creation_input_tokens ||
+                0
+
               logger.debug('📊 Droid OpenAI usage:', currentUsageData)
             }
 
@@ -758,6 +766,14 @@ class DroidRelayService {
                 currentUsageData.output_tokens = 0
               }
 
+              // Capture cache tokens from OpenAI Response API format
+              currentUsageData.cache_read_input_tokens =
+                usage.input_tokens_details?.cached_tokens || 0
+              currentUsageData.cache_creation_input_tokens =
+                usage.input_tokens_details?.cache_creation_input_tokens ||
+                usage.cache_creation_input_tokens ||
+                0
+
               logger.debug('📊 Droid OpenAI response usage:', currentUsageData)
             }
           } catch (parseError) {