fix(workflows): adjust Codex CLI flag for full-auto mode

- Corrected the placement of the `--full-auto` flag in `codex.yml`.
- Ensures proper execution of the Codex CLI command with the intended
  configuration for full-auto approval mode.

Author: hazadus

.github/workflows/codex.yml

@@ -43,7 +43,7 @@ jobs:
           export OPENAI_BASE_URL=https://models.github.ai/inference
 
           # any provider string would work here, it's just so codex knows it's using a custom model
-          codex --provider github --model openai/gpt-4.1 "$INSTRUCTION" -- --approval-mode full-auto
+          codex --provider github --model openai/gpt-4.1 --full-auto "$INSTRUCTION"
           
           if [[ -n $(git status --porcelain) ]]; then
             git config user.name "GitHub Models Codex Bot"