revert: drop the e2e gateway config

Keeps a single source of truth in the deployment overlay; the per-SHA e2e
run will read that config at orchestration time instead.

tests/e2e/gateway/litellm-config.yml

@@ -1,74 +0,0 @@
-general_settings:
-  store_prompts_in_spend_logs: true
-  forward_client_headers_to_llm_api: false
-  maximum_spend_logs_retention_period: 3h
-  maximum_spend_logs_cleanup_cron: 0 1 * * *
-  proxy_config_reload_interval_seconds: 10
-  proxy_budget_rescheduler_min_time: 15
-  proxy_budget_rescheduler_max_time: 20
-litellm_settings:
-  drop_params: true
-  default_redis_ttl: 20
-  json_logs: true
-  store_audit_logs: true
-  cache: true
-  cache_params:
-    type: redis
-    host: os.environ/REDIS_HOST
-    port: os.environ/REDIS_PORT
-  callbacks:
-  - datadog
-  - prometheus
-  - otel
-  require_auth_for_metrics_endpoint: false
-router_settings:
-  fallbacks:
-  - gpt-5.5:
-    - gpt-5.6-luna
-    - gpt-5.2
-  - claude-haiku-4-5:
-    - gemini-2.5-flash
-    - gpt-5.6-luna
-  routing_strategy: simple-shuffle
-  num_retries: 3
-model_list:
-- model_name: gpt-5.5
-  litellm_params:
-    model: openai/gpt-5.5
-    api_key: os.environ/OPENAI_API_KEY
-- model_name: gpt-5.6-luna
-  litellm_params:
-    model: openai/gpt-5.6-luna
-    api_key: os.environ/OPENAI_API_KEY
-- model_name: gpt-5.2
-  litellm_params:
-    model: openai/gpt-5.2
-    api_key: os.environ/OPENAI_API_KEY
-- model_name: claude-haiku-4-5
-  litellm_params:
-    model: anthropic/claude-haiku-4-5
-    api_key: os.environ/ANTHROPIC_API_KEY
-- model_name: azure-foundry-claude-haiku
-  litellm_params:
-    model: azure_ai/claude-haiku-4-5
-    api_base: os.environ/AZURE_AI_API_BASE
-    api_key: os.environ/AZURE_AI_API_KEY
-- model_name: gemini-2.5-flash-vertex
-  litellm_params:
-    model: vertex_ai/gemini-2.5-flash
-    vertex_project: os.environ/VERTEXAI_PROJECT
-    vertex_location: us-central1
-    vertex_credentials: os.environ/VERTEXAI_CREDENTIALS
-- model_name: gemini-2.5-flash
-  litellm_params:
-    model: gemini/gemini-2.5-flash
-    api_key: os.environ/GEMINI_API_KEY
-- model_name: gemini-2.5-flash
-  litellm_params:
-    model: gemini/gemini-2.5-flash
-    api_key: os.environ/GEMINI_API_KEY
-mcp_servers:
-  devin:
-    url: https://mcp.devin.ai/mcp
-    auth_type: api_key
-    auth_value: os.environ/DEVIN_API_KEY