Refactor test execution and enhance documentation for integration tests

- Simplified test execution commands in CLAUDE.md and quickstart.md for better usability.
- Added instructions for running tests from the project root and clarified the process for executing the complete Robot Framework test suite.
- Introduced a new Docker service for the Deepgram streaming worker in docker-compose-test.yml to improve testing capabilities.
- Updated system_admin_tests.robot to use a defined default prompt for restoration, enhancing test reliability and clarity.

Author: AnkushMalaker

CLAUDE.md

@@ -114,16 +114,8 @@ cp .env.template .env  # Configure API keys
 # Run full integration test suite
 ./run-test.sh
 
-# Manual test execution (for debugging)
-source .env && export DEEPGRAM_API_KEY && export OPENAI_API_KEY
-uv run robot --outputdir test-results --loglevel INFO ../../tests/integration/integration_test.robot
-
 # Leave test containers running for debugging (don't auto-cleanup)
-CLEANUP_CONTAINERS=false source .env && export DEEPGRAM_API_KEY && export OPENAI_API_KEY
-uv run robot --outputdir test-results --loglevel INFO ../../tests/integration/integration_test.robot
-
-# Manual cleanup when needed
-docker compose -f docker-compose-test.yml down -v
+CLEANUP_CONTAINERS=false ./run-test.sh
 ```
 
 #### Test Configuration Flags

Docs/getting-started.md

@@ -175,11 +175,16 @@ PARAKEET_ASR_URL=http://host.docker.internal:8080
 
 After configuration, verify everything works with the integration test suite:
 ```bash
+# From backends/advanced directory
 ./run-test.sh
 
-# Alternative: Manual test with detailed logging
-source .env && export DEEPGRAM_API_KEY OPENAI_API_KEY && \
-  uv run robot --outputdir ../../test-results --loglevel INFO ../../tests/integration/integration_test.robot
+# Or run all tests from project root
+cd ../..
+./run-test.sh advanced-backend
+
+# Or run complete Robot Framework test suite
+cd tests
+./run-robot-tests.sh
 ```
 This end-to-end test validates the complete audio processing pipeline using Robot Framework.
 

backends/advanced/Docs/quickstart.md

@@ -173,11 +173,16 @@ PARAKEET_ASR_URL=http://host.docker.internal:8080
 
 After configuration, verify everything works with the integration test suite:
 ```bash
+# From backends/advanced directory
 ./run-test.sh
 
-# Alternative: Manual test with detailed logging
-source .env && export DEEPGRAM_API_KEY OPENAI_API_KEY && \
-  uv run robot --outputdir ../../test-results --loglevel INFO ../../tests/integration/integration_test.robot
+# Or run all tests from project root
+cd ../..
+./run-test.sh advanced-backend
+
+# Or run complete Robot Framework test suite
+cd tests
+./run-robot-tests.sh
 ```
 This end-to-end test validates the complete audio processing pipeline using Robot Framework.
 

backends/advanced/docker-compose-test.yml

@@ -200,6 +200,39 @@ services:
         condition: service_healthy
     restart: unless-stopped
 
+  deepgram-streaming-worker-test:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    command: >
+      uv run python -m advanced_omi_backend.workers.audio_stream_deepgram_streaming_worker
+    volumes:
+      - ./src:/app/src
+      - ./data/test_data:/app/data
+      - ${CONFIG_FILE:-../../config/config.yml}:/app/config.yml
+      - ${PLUGINS_CONFIG:-../../config/plugins.yml}:/app/plugins.yml
+    environment:
+      - DEEPGRAM_API_KEY=${DEEPGRAM_API_KEY}
+      - REDIS_URL=redis://redis-test:6379/0
+      - HA_TOKEN=${HA_TOKEN}
+      - MONGODB_URI=mongodb://mongo-test:27017/test_db
+      - QDRANT_BASE_URL=qdrant-test
+      - QDRANT_PORT=6333
+      - DEBUG_DIR=/app/debug_dir
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
+      - GROQ_API_KEY=${GROQ_API_KEY}
+      - AUTH_SECRET_KEY=test-jwt-signing-key-for-integration-tests
+      - ADMIN_PASSWORD=test-admin-password-123
+      - ADMIN_EMAIL=test-admin@example.com
+      - TRANSCRIPTION_PROVIDER=${TRANSCRIPTION_PROVIDER:-deepgram}
+      - MEMORY_PROVIDER=${MEMORY_PROVIDER:-chronicle}
+    depends_on:
+      redis-test:
+        condition: service_started
+      mongo-test:
+        condition: service_healthy
+    restart: unless-stopped
+
   # Mycelia - AI memory and timeline service (test environment)
   # mycelia-backend-test:
   #   build:

tests/endpoints/system_admin_tests.robot

@@ -190,9 +190,8 @@ Save And Retrieve Chat Configuration Test
     [Documentation]    Test saving and retrieving chat configuration
     [Tags]    infra	permissions
 
-    # Get original prompt to restore later
-    ${response}=       GET On Session    api    /api/admin/chat/config
-    ${original_prompt}=    Set Variable    ${response.text}
+    # Define known default prompt for restoration (from system_controller.py and chat_service.py)
+    ${default_prompt}=    Set Variable    You are a helpful AI assistant with access to the user's personal memories and conversation history.
 
     # Save custom prompt
     ${custom_prompt}=  Set Variable    You are a specialized AI assistant for technical support and troubleshooting.
@@ -210,9 +209,9 @@ Save And Retrieve Chat Configuration Test
     ${retrieved}=      Set Variable    ${response.text}
     Should Be Equal    ${retrieved}    ${custom_prompt}    msg=Retrieved prompt should match saved prompt
 
-    # Restore original prompt to avoid test interference
+    # Restore default prompt to avoid test interference
     ${response}=       POST On Session    api    /api/admin/chat/config
-    ...                data=${original_prompt}
+    ...                data=${default_prompt}
     ...                headers=${headers}
     Should Be Equal As Integers    ${response.status_code}    200