litellm: fix direct_* model IDs — gemini 2.5, drop o3-mini

Verified the direct_* providers end-to-end after billing was enabled.
- OpenAI direct_gpt-4o / direct_gpt-4o-mini: working.
- Gemini: gemini-2.0-flash 404s (LiteLLM 1.55.10 rewrites it to a retired
  experimental name) and gemini-1.5-pro is retired -> switch to the current GA
  gemini-2.5-flash / gemini-2.5-pro (both verified).
- Drop direct_o3-mini: o-series needs max_completion_tokens, which 1.55.10 won't
  translate from the max_tokens clients (Open WebUI) send -> 400. Re-add after a
  LiteLLM bump.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

vars/main.yml

@@ -108,25 +108,28 @@ litellm_models:
     backend: anthropic/claude-opus-4-7
     api_base: "http://127.0.0.1:{{ meridian_port }}"
   # ---- direct_* → public provider APIs, METERED, keys from Infisical /meridian ----
-  # SCAFFOLDED 2026-06-05 with NO real keys: these 401 on call until
-  # OPENAI_API_KEY / GEMINI_API_KEY land in Infisical /meridian and deploy.sh
-  # pulls them (litellm.env carries a placeholder so the proxy still boots).
+  # LIVE 2026-06-05 (OpenAI + Gemini keys verified end-to-end). Keys come from
+  # Infisical /meridian via deploy.sh; litellm.env carries a placeholder so the
+  # proxy still boots if a key is absent (that provider's models then 401).
   # No api_base → LiteLLM uses each provider's default endpoint; routing is by
   # the backend's provider prefix (openai/, gemini/).
+  #
+  # Gemini must be CURRENT model IDs: LiteLLM 1.55.10 rewrites gemini-2.0-flash
+  # to a retired experimental name (404) and gemini-1.5-pro is itself retired.
+  # 2.5-flash / 2.5-pro pass through clean. o-series (o3-mini) is intentionally
+  # absent: it needs max_completion_tokens, which 1.55.10 won't translate from
+  # the max_tokens that clients (Open WebUI) send → 400. Re-add after a bump.
   - name: direct_gpt-4o
     backend: openai/gpt-4o
     api_key: os.environ/OPENAI_API_KEY
   - name: direct_gpt-4o-mini
     backend: openai/gpt-4o-mini
     api_key: os.environ/OPENAI_API_KEY
-  - name: direct_o3-mini
-    backend: openai/o3-mini
-    api_key: os.environ/OPENAI_API_KEY
-  - name: direct_gemini-2.0-flash
-    backend: gemini/gemini-2.0-flash
+  - name: direct_gemini-2.5-flash
+    backend: gemini/gemini-2.5-flash
     api_key: os.environ/GEMINI_API_KEY
-  - name: direct_gemini-1.5-pro
-    backend: gemini/gemini-1.5-pro
+  - name: direct_gemini-2.5-pro
+    backend: gemini/gemini-2.5-pro
     api_key: os.environ/GEMINI_API_KEY
 # Master key is required by LiteLLM. Pulled at deploy time from Infisical
 # /meridian/vault_litellm_master_key and passed via -e on the playbook