Address PR review comments from Copilot code review

- workflow_hitl.py: Remove stale approval_mode comments (English + Spanish)
- agent_knowledge_pg.py: Fix extend_messages(self) -> extend_messages(self.source_id)
- agent_supervisor.py: Change logger level from DEBUG to INFO for consistency
- README.md: Add PostgreSQL setup instructions for local environment (English + Spanish)
- sqlite_viewer.py: Fix --db help text to say chat_history.sqlite3
- sqlite_viewer.py: Replace thread_id with session_id in SQL queries (English + Spanish)
- agent_summarization.py: Use HISTORY_STATE_KEY constant instead of hard-coded 'memory'
- agent_memory_redis.py: Fix print title RedisProvider -> RedisContextProvider
- docker-compose.yml: Add REDIS_URL and POSTGRES_URL env vars for dev container

Author: pamelafox

.devcontainer/docker-compose.yml

@@ -9,6 +9,8 @@ services:
     environment:
       - OTEL_EXPORTER_OTLP_ENDPOINT=http://aspire-dashboard:18889
       - OTEL_EXPORTER_OTLP_PROTOCOL=grpc
+      - REDIS_URL=redis://redis:6379
+      - POSTGRES_URL=postgresql://admin:LocalPasswordOnly@db:5432/postgres
 
   db:
     image: pgvector/pgvector:pg17

.github/prompts/review_slides.prompt.md

@@ -7,4 +7,4 @@ Review the given slides for consistency with the code samples in the repository.
 Use the markitdown skill to convert the PDF to markdown first.
 
 Point out any errors, inconsistencies, or areas that may need clarification. Provide specific feedback on how to improve the slides to better align with the code and concepts presented in the repository.
-Make sure all URLs/filenames are valid.
+Make sure all URLs/filenames are valid.

README.md

@@ -87,6 +87,12 @@ The dev container includes a Redis server, which is used by the `agent_history_r
     docker run -d -p 6379:6379 redis:7-alpine
     ```
 
+5. *Optional:* To run the PostgreSQL examples (`agent_knowledge_postgres.py`, `agent_knowledge_pg.py`, `agent_knowledge_pg_rewrite.py`), you need PostgreSQL with pgvector running locally:
+
+    ```shell
+    docker run -d -p 5432:5432 -e POSTGRES_USER=admin -e POSTGRES_PASSWORD=LocalPasswordOnly pgvector/pgvector:pg17
+    ```
+
 ## Configuring model providers
 
 These examples can be run with Azure AI Foundry, OpenAI.com, or GitHub Models, depending on the environment variables you set. All the scripts reference the environment variables from a `.env` file, and an example `.env.sample` file is provided. Host-specific instructions are below.

examples/agent_knowledge_pg.py

@@ -311,7 +311,7 @@ async def before_run(
 
         knowledge_text = "\n".join(knowledge_lines)
         context.extend_messages(
-            self,
+            self.source_id,
             [Message(role="system", text=knowledge_text)],
         )
 

examples/agent_memory_redis.py

@@ -67,7 +67,7 @@ async def example_agent_with_memory() -> None:
 
     Requires Redis Stack (with RediSearch module) — see docker-compose.yaml.
     """
-    print("\n[bold]=== Agent with Redis Memory (RedisProvider) ===[/bold]")
+    print("\n[bold]=== Agent with Redis Memory (RedisContextProvider) ===[/bold]")
 
     user_id = str(uuid.uuid4())
 

examples/agent_summarization.py

@@ -186,7 +186,7 @@ async def process(
 
         # Before the agent runs: check if we should compact the history
         if session and self.context_tokens > self.token_threshold:
-            history = session.state["memory"]["messages"]
+            history = session.state.get(self.HISTORY_STATE_KEY, {}).get("messages", [])
             if len(history) > 2:
                 logger.info(
                     "[📝 Summarization] Token usage (%d) exceeds threshold (%d). "
@@ -204,7 +204,7 @@ async def process(
                 )
 
                 # Replace session history with a single summary message
-                session.state["memory"]["messages"] = [
+                session.state[self.HISTORY_STATE_KEY]["messages"] = [
                     Message(role="assistant", text=f"[Summary of earlier conversation]\n{summary_text}"),
                 ]
 

examples/agent_supervisor.py

@@ -18,7 +18,7 @@
 handler = RichHandler(show_path=False, rich_tracebacks=True, show_level=False)
 logging.basicConfig(level=logging.WARNING, handlers=[handler], force=True, format="%(message)s")
 logger = logging.getLogger(__name__)
-logger.setLevel(logging.DEBUG)
+logger.setLevel(logging.INFO)
 
 # Configure OpenAI client based on environment
 load_dotenv(override=True)

examples/spanish/README.md

@@ -88,6 +88,12 @@ El dev container incluye un servidor Redis, que se usa en el ejemplo `agent_hist
     docker run -d -p 6379:6379 redis:7-alpine
     ```
 
+5. *Opcional:* Para ejecutar los ejemplos de PostgreSQL (`agent_knowledge_postgres.py`, `agent_knowledge_pg.py`, `agent_knowledge_pg_rewrite.py`), necesitas PostgreSQL con pgvector corriendo localmente:
+
+    ```shell
+    docker run -d -p 5432:5432 -e POSTGRES_USER=admin -e POSTGRES_PASSWORD=LocalPasswordOnly pgvector/pgvector:pg17
+    ```
+
 ## Configurar proveedores de modelos
 
 Estos ejemplos se pueden ejecutar con Azure AI Foundry, OpenAI.com o GitHub Models, dependiendo de las variables de entorno que configures. Todos los scripts hacen referencia a las variables de entorno de un archivo `.env`, y se proporciona un archivo de ejemplo `.env.sample`. Las instrucciones específicas de cada proveedor se encuentran a continuación.

examples/spanish/agent_knowledge_pg.py

@@ -311,7 +311,7 @@ async def before_run(
 
         knowledge_text = "\n".join(knowledge_lines)
         context.extend_messages(
-            self,
+            self.source_id,
             [Message(role="system", text=knowledge_text)],
         )
 

examples/spanish/agent_memory_redis.py

@@ -67,7 +67,7 @@ async def example_agent_with_memory() -> None:
 
     Requiere Redis Stack (con el módulo RediSearch): revisa docker-compose.yaml.
     """
-    print("\n[bold]=== Agente con memoria en Redis (RedisProvider) ===[/bold]")
+    print("\n[bold]=== Agente con memoria en Redis (RedisContextProvider) ===[/bold]")
 
     user_id = str(uuid.uuid4())