Update to agno 2.5.2 and align with gcode patterns

README.md

@@ -4,13 +4,15 @@ Dash is a **self-learning data agent** that grounds its answers in **6 layers of
 
 Inspired by [OpenAI's in-house data agent](https://openai.com/index/inside-our-in-house-data-agent/).
 
-## Quick Start
+## Get Started
 
 ```sh
-# Clone this repo
+# Clone the repo
 git clone https://github.com/agno-agi/dash.git && cd dash
-# Add OPENAI_API_KEY by adding to .env file or export OPENAI_API_KEY=sk-***
+
+# Add OPENAI_API_KEY
 cp example.env .env
+# Edit .env and add your key
 
 # Start the application
 docker compose up -d --build
@@ -20,7 +22,7 @@ docker exec -it dash-api python -m dash.scripts.load_data
 docker exec -it dash-api python -m dash.scripts.load_knowledge
 ```
 
-Confirm dash is running by navigation to [http://localhost:8000/docs](http://localhost:8000/docs).
+Confirm dash is running at [http://localhost:8000/docs](http://localhost:8000/docs).
 
 ## Connect to the Web UI
 
@@ -238,7 +240,7 @@ python -m dash  # CLI mode
 | `EXA_API_KEY` | No | Web search for external knowledge |
 | `DB_*` | No | Database config (defaults to localhost) |
 
-## Further Reading
+## Learn More
 
 - [OpenAI's In-House Data Agent](https://openai.com/index/inside-our-in-house-data-agent/) — the inspiration
 - [Self-Improving SQL Agent](https://www.ashpreetbedi.com/articles/sql-agent) — deep dive on an earlier architecture

app/main.py

@@ -16,9 +16,9 @@
 from dash.agents import dash, dash_knowledge, reasoning_dash
 from db import get_postgres_db
 
-# ============================================================================
+# ---------------------------------------------------------------------------
 # Create AgentOS
-# ============================================================================
+# ---------------------------------------------------------------------------
 agent_os = AgentOS(
     name="Dash",
     tracing=True,

dash/agents.py

@@ -8,59 +8,36 @@
 from os import getenv
 
 from agno.agent import Agent
-from agno.knowledge import Knowledge
-from agno.knowledge.embedder.openai import OpenAIEmbedder
 from agno.learn import (
     LearnedKnowledgeConfig,
     LearningMachine,
     LearningMode,
-    UserMemoryConfig,
-    UserProfileConfig,
 )
 from agno.models.openai import OpenAIResponses
 from agno.tools.mcp import MCPTools
 from agno.tools.reasoning import ReasoningTools
 from agno.tools.sql import SQLTools
-from agno.vectordb.pgvector import PgVector, SearchType
 
 from dash.context.business_rules import BUSINESS_CONTEXT
 from dash.context.semantic_model import SEMANTIC_MODEL_STR
 from dash.tools import create_introspect_schema_tool, create_save_validated_query_tool
-from db import db_url, get_postgres_db
+from db import create_knowledge, db_url, get_postgres_db
 
-# ============================================================================
+# ---------------------------------------------------------------------------
 # Database & Knowledge
-# ============================================================================
+# ---------------------------------------------------------------------------
 
 agent_db = get_postgres_db()
 
 # KNOWLEDGE: Static, curated (table schemas, validated queries, business rules)
-dash_knowledge = Knowledge(
-    name="Dash Knowledge",
-    vector_db=PgVector(
-        db_url=db_url,
-        table_name="dash_knowledge",
-        search_type=SearchType.hybrid,
-        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
-    ),
-    contents_db=get_postgres_db(contents_table="dash_knowledge_contents"),
-)
+dash_knowledge = create_knowledge("Dash Knowledge", "dash_knowledge")
 
 # LEARNINGS: Dynamic, discovered (error patterns, gotchas, user corrections)
-dash_learnings = Knowledge(
-    name="Dash Learnings",
-    vector_db=PgVector(
-        db_url=db_url,
-        table_name="dash_learnings",
-        search_type=SearchType.hybrid,
-        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
-    ),
-    contents_db=get_postgres_db(contents_table="dash_learnings_contents"),
-)
+dash_learnings = create_knowledge("Dash Learnings", "dash_learnings")
 
-# ============================================================================
+# ---------------------------------------------------------------------------
 # Tools
-# ============================================================================
+# ---------------------------------------------------------------------------
 
 save_validated_query = create_save_validated_query_tool(dash_knowledge)
 introspect_schema = create_introspect_schema_tool(db_url)
@@ -72,9 +49,9 @@
     MCPTools(url=f"https://mcp.exa.ai/mcp?exaApiKey={getenv('EXA_API_KEY', '')}&tools=web_search_exa"),
 ]
 
-# ============================================================================
+# ---------------------------------------------------------------------------
 # Instructions
-# ============================================================================
+# ---------------------------------------------------------------------------
 
 INSTRUCTIONS = f"""\
 You are Dash, a self-learning data agent that provides **insights**, not just query results.
@@ -159,23 +136,23 @@
 {BUSINESS_CONTEXT}\
 """
 
-# ============================================================================
+# ---------------------------------------------------------------------------
 # Create Agent
-# ============================================================================
+# ---------------------------------------------------------------------------
 
 dash = Agent(
+    id="dash",
     name="Dash",
     model=OpenAIResponses(id="gpt-5.2"),
     db=agent_db,
     instructions=INSTRUCTIONS,
     # Knowledge (static)
     knowledge=dash_knowledge,
     search_knowledge=True,
-    # Learning (provides search_learnings, save_learning, user profile, user memory)
+    # Learning (provides search_learnings, save_learning)
+    enable_agentic_memory=True,
     learning=LearningMachine(
         knowledge=dash_learnings,
-        user_profile=UserProfileConfig(mode=LearningMode.AGENTIC),
-        user_memory=UserMemoryConfig(mode=LearningMode.AGENTIC),
         learned_knowledge=LearnedKnowledgeConfig(mode=LearningMode.AGENTIC),
     ),
     tools=base_tools,
@@ -195,5 +172,8 @@
     }
 )
 
+# ---------------------------------------------------------------------------
+# Run Agent
+# ---------------------------------------------------------------------------
 if __name__ == "__main__":
     dash.print_response("Who won the most races in 2019?", stream=True)

db/__init__.py

@@ -5,10 +5,11 @@
 Database connection utilities.
 """
 
-from db.session import get_postgres_db
+from db.session import create_knowledge, get_postgres_db
 from db.url import db_url
 
 __all__ = [
+    "create_knowledge",
     "db_url",
     "get_postgres_db",
 ]

db/session.py

@@ -6,6 +6,9 @@
 """
 
 from agno.db.postgres import PostgresDb
+from agno.knowledge import Knowledge
+from agno.knowledge.embedder.openai import OpenAIEmbedder
+from agno.vectordb.pgvector import PgVector, SearchType
 
 from db.url import db_url
 
@@ -24,3 +27,25 @@ def get_postgres_db(contents_table: str | None = None) -> PostgresDb:
     if contents_table is not None:
         return PostgresDb(id=DB_ID, db_url=db_url, knowledge_table=contents_table)
     return PostgresDb(id=DB_ID, db_url=db_url)
+
+
+def create_knowledge(name: str, table_name: str) -> Knowledge:
+    """Create a Knowledge instance with PgVector hybrid search.
+
+    Args:
+        name: Display name for the knowledge base.
+        table_name: PostgreSQL table name for vector storage.
+
+    Returns:
+        Configured Knowledge instance.
+    """
+    return Knowledge(
+        name=name,
+        vector_db=PgVector(
+            db_url=db_url,
+            table_name=table_name,
+            search_type=SearchType.hybrid,
+            embedder=OpenAIEmbedder(id="text-embedding-3-small"),
+        ),
+        contents_db=get_postgres_db(contents_table=f"{table_name}_contents"),
+    )

pyproject.toml

@@ -8,7 +8,6 @@ license-files = ["LICENSE"]
 authors = [{ name = "Agno", email = "hello@agno.com" }]
 
 dependencies = [
-  "agno-infra",
   "agno",
   "fastapi[standard]",
   "httpx",

requirements.txt

@@ -1,22 +1,21 @@
 # This file was autogenerated by uv via the following command:
 #    ./scripts/generate_requirements.sh upgrade
-agno==2.4.7
-agno-infra==1.0.7
+agno==2.5.2
 annotated-doc==0.0.4
 annotated-types==0.7.0
 anyio==4.12.1
 attrs==25.4.0
 certifi==2026.1.4
 cffi==2.0.0
 click==8.3.1
-cryptography==46.0.4
+cryptography==46.0.5
 distro==1.9.0
 dnspython==2.8.0
 docstring-parser==0.17.0
 email-validator==2.3.0
-fastapi==0.128.0
-fastapi-cli==0.0.20
-fastapi-cloud-cli==0.11.0
+fastapi==0.129.0
+fastapi-cli==0.0.23
+fastapi-cloud-cli==0.12.0
 fastar==0.8.0
 gitdb==4.0.12
 gitpython==3.1.46
@@ -31,17 +30,17 @@ hyperframe==6.1.0
 idna==3.11
 importlib-metadata==8.7.1
 jinja2==3.1.6
-jiter==0.12.0
+jiter==0.13.0
 jsonschema==4.26.0
 jsonschema-specifications==2025.9.1
 markdown-it-py==4.0.0
 markupsafe==3.0.3
 mcp==1.26.0
 mdurl==0.1.2
 numpy==2.4.2
-openai==2.16.0
+openai==2.21.0
 openinference-instrumentation==0.1.44
-openinference-instrumentation-agno==0.1.27
+openinference-instrumentation-agno==0.1.28
 openinference-semantic-conventions==0.1.26
 opentelemetry-api==1.39.1
 opentelemetry-instrumentation==0.60b1
@@ -56,7 +55,7 @@ pycparser==3.0
 pydantic==2.12.5
 pydantic-core==2.41.5
 pydantic-extra-types==2.11.0
-pydantic-settings==2.12.0
+pydantic-settings==2.13.0
 pygments==2.19.2
 pyjwt==2.11.0
 python-dateutil==2.9.0.post0
@@ -65,24 +64,23 @@ python-multipart==0.0.22
 pyyaml==6.0.3
 referencing==0.37.0
 rich==14.3.2
-rich-toolkit==0.18.1
+rich-toolkit==0.19.4
 rignore==0.7.6
 rpds-py==0.30.0
-sentry-sdk==2.51.0
+sentry-sdk==2.53.0
 shellingham==1.5.4
 six==1.17.0
 smmap==5.0.2
 sniffio==1.3.1
 sqlalchemy==2.0.46
 sse-starlette==3.2.0
-starlette==0.50.0
-tomli==2.4.0
-tqdm==4.67.2
-typer==0.21.1
+starlette==0.52.1
+tqdm==4.67.3
+typer==0.24.0
 typing-extensions==4.15.0
 typing-inspection==0.4.2
 urllib3==2.6.3
-uvicorn==0.40.0
+uvicorn==0.41.0
 uvloop==0.22.1
 watchfiles==1.1.1
 websockets==16.0