feat(org): add LiteLLM usage stats to organization dashboard

Replace mock token usage with real data from LiteLLM free-tier APIs
(global/activity, global/activity/model, global/spend/models). Adds
per-model breakdown table, loading/error states, usage data models
with serde tests, and i18n keys for all five languages.

Also includes: replace Ollama with LiteLLM proxy, update config,
docker-compose, and provider infrastructure.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

assets/i18n/en.json

@@ -144,6 +144,16 @@
     "email_address": "Email Address",
     "email_placeholder": "colleague@company.com",
     "send_invite": "Send Invite",
+    "total_spend": "Total Spend",
+    "total_tokens": "Total Tokens",
+    "model_usage": "Usage by Model",
+    "model": "Model",
+    "tokens": "Tokens",
+    "spend": "Spend",
+    "usage_unavailable": "Usage data unavailable",
+    "loading_usage": "Loading usage data...",
+    "prompt_tokens": "Prompt Tokens",
+    "completion_tokens": "Completion Tokens",
     "pricing_title": "Pricing",
     "pricing_subtitle": "Choose the plan that fits your organization"
   },