diff --git a/examples/gitflic_ci/README.md b/examples/gitflic_ci/README.md
index 9f36ce73..3d052b45 100644
--- a/examples/gitflic_ci/README.md
+++ b/examples/gitflic_ci/README.md
@@ -39,7 +39,7 @@ Go to **Settings → CI/CD → Variables** and add:
 | `OCR_LLM_URL` | Yes | LLM API endpoint URL |
 | `OCR_LLM_AUTH_TOKEN` | Yes | LLM API authentication token |
 | `GITFLIC_TOKEN` | Yes | GitFlic access token used to post discussions |
-| `OCR_LLM_MODEL` | No | Model name (e.g., `gpt-4o`) |
+| `OCR_LLM_MODEL` | Yes | Model name (e.g., `gpt-4o`) — OCR has no built-in default model and fails when this is unset |
 | `GITFLIC_API_URL` | No | REST API base URL for self-hosted GitFlic (default: `https://api.gitflic.ru`) |
 
 > **Note:** GitFlic CI/CD does not accept variables with values shorter than 8 characters, so `use_anthropic` cannot be set as a CI variable. The pipeline sets it to `false`; to use Anthropic Claude models, edit `gitflic-ci.yaml` directly.
diff --git a/examples/gitlab_ci/.gitlab-ci.yml b/examples/gitlab_ci/.gitlab-ci.yml
index e8c3f784..9b9d6f81 100644
--- a/examples/gitlab_ci/.gitlab-ci.yml
+++ b/examples/gitlab_ci/.gitlab-ci.yml
@@ -7,9 +7,10 @@
 # Required CI/CD Variables (Settings → CI/CD → Variables):
 #   OCR_LLM_URL        - LLM API endpoint (e.g., https://api.openai.com/v1/chat/completions)
 #   OCR_LLM_AUTH_TOKEN - Authentication token for the LLM API (mark as "Masked")
+#   OCR_LLM_MODEL      - Model name (e.g., gpt-4o). OCR has no built-in default model; the
+#                        pipeline fails fast if this is unset.
 #
 # Optional CI/CD Variables:
-#   OCR_LLM_MODEL      - Model name (default: gpt-4o)
 #   GITLAB_API_TOKEN   - GitLab Personal/Project Access Token with "api" scope
 #                        (falls back to CI_JOB_TOKEN if not set)
 #
@@ -48,12 +49,14 @@ code-review:
     - echo "OpenCodeReview installed with version:" && ocr version || true
 
     # Configure OCR
-    - mkdir -p ~/.open-code-review
     # Gitlab CI/CD does not support configuring variables with value length less than 8, so you can't set use_anthropic as a CI variable
     - |
-      ocr config set llm.url $OCR_LLM_URL
-      ocr config set llm.auth_token $OCR_LLM_AUTH_TOKEN
-      ocr config set llm.model $OCR_LLM_MODEL
+      : "${OCR_LLM_URL:?set OCR_LLM_URL in Settings -> CI/CD -> Variables}"
+      : "${OCR_LLM_AUTH_TOKEN:?set OCR_LLM_AUTH_TOKEN in Settings -> CI/CD -> Variables}"
+      : "${OCR_LLM_MODEL:?set OCR_LLM_MODEL in Settings -> CI/CD -> Variables}"
+      ocr config set llm.url "$OCR_LLM_URL"
+      ocr config set llm.auth_token "$OCR_LLM_AUTH_TOKEN"
+      ocr config set llm.model "$OCR_LLM_MODEL"
       ocr config set llm.use_anthropic false
       ocr config set llm.extra_body '{"thinking": {"type": "disabled"}}'
 
diff --git a/examples/gitlab_ci/README.md b/examples/gitlab_ci/README.md
index ab9461fa..70ac144a 100644
--- a/examples/gitlab_ci/README.md
+++ b/examples/gitlab_ci/README.md
@@ -38,7 +38,7 @@ Go to your project's **Settings → CI/CD → Variables** and add:
 |----------|----------|--------|-------------|
 | `OCR_LLM_URL` | Yes | No | LLM API endpoint URL (e.g., `https://api.openai.com/v1/chat/completions`) |
 | `OCR_LLM_AUTH_TOKEN` | Yes | Yes | API authentication token |
-| `OCR_LLM_MODEL` | No | No | Model name (defaults to `gpt-4o`) |
+| `OCR_LLM_MODEL` | Yes | No | Model name (e.g., `gpt-4o`) — OCR has no built-in default model and fails when this is unset |
 | `GITLAB_API_TOKEN` | No | Yes | GitLab access token with `api` scope (falls back to `CI_JOB_TOKEN` if not set) |
 
 > **Note:** GitLab CI/CD does not support variables with values shorter than 8 characters, so `use_anthropic` cannot be set as a CI variable. The pipeline sets it to `false` by default. If you need to use Anthropic Claude models, you'll need to modify the `.gitlab-ci.yml` script directly.
@@ -145,11 +145,13 @@ script:
   - npm install -g @alibaba-group/open-code-review
 
   # Configure OCR
-  - mkdir -p ~/.open-code-review
   - |
-    ocr config set llm.url $OCR_LLM_URL
-    ocr config set llm.auth_token $OCR_LLM_AUTH_TOKEN
-    ocr config set llm.model $OCR_LLM_MODEL
+    : "${OCR_LLM_URL:?set OCR_LLM_URL in Settings -> CI/CD -> Variables}"
+    : "${OCR_LLM_AUTH_TOKEN:?set OCR_LLM_AUTH_TOKEN in Settings -> CI/CD -> Variables}"
+    : "${OCR_LLM_MODEL:?set OCR_LLM_MODEL in Settings -> CI/CD -> Variables}"
+    ocr config set llm.url "$OCR_LLM_URL"
+    ocr config set llm.auth_token "$OCR_LLM_AUTH_TOKEN"
+    ocr config set llm.model "$OCR_LLM_MODEL"
     ocr config set llm.use_anthropic false
     ocr config set llm.extra_body '{"thinking": {"type": "disabled"}}'