solana-agent 28.1.1__py3-none-any.whl → 28.2.1__py3-none-any.whl

solana_agent/services/knowledge_base.py

@@ -1,3 +1,4 @@
+import logging
 from datetime import datetime as dt
 from typing import Dict, List, Any, Optional, Union
 import uuid
@@ -16,6 +17,9 @@ from solana_agent.interfaces.services.knowledge_base import (
     KnowledgeBaseService as KnowledgeBaseInterface,
 )
 
+# Setup logger for this module
+logger = logging.getLogger(__name__)
+
 
 class KnowledgeBaseService(KnowledgeBaseInterface):
     """
@@ -76,8 +80,8 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                 raise ValueError(
                     f"Cannot determine dimension for unknown OpenAI model '{openai_model_name}' and Pinecone dimension not configured."
                 )
-            print(
-                f"Warning: Unknown OpenAI model '{openai_model_name}'. Using dimension {openai_dimensions} from Pinecone config. Ensure this is correct."
+            logger.warning(  # Use logger.warning
+                f"Unknown OpenAI model '{openai_model_name}'. Using dimension {openai_dimensions} from Pinecone config. Ensure this is correct."
             )
 
         # Instantiate OpenAIEmbedding
@@ -90,7 +94,7 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                 # embed_batch_size=10 # Optional: Adjust batch size if needed
             )
         except Exception as e:
-            print(f"Error initializing OpenAIEmbedding: {e}")
+            logger.error(f"Error initializing OpenAIEmbedding: {e}")  # Use logger.error
             raise
 
         self.semantic_splitter = SemanticSplitterNodeParser(
@@ -108,7 +112,9 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
         """Set up MongoDB collection with appropriate indexes."""
         if not self.mongo.collection_exists(self.collection):
             self.mongo.create_collection(self.collection)
-            print(f"Created MongoDB collection: {self.collection}")
+            logger.info(
+                f"Created MongoDB collection: {self.collection}"
+            )  # Use logger.info
 
         # Indexes for retrieval and filtering
         self.mongo.create_index(self.collection, [("document_id", 1)], unique=True)
@@ -117,7 +123,9 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
         self.mongo.create_index(self.collection, [("created_at", -1)])
         self.mongo.create_index(self.collection, [("tags", 1)])
         self.mongo.create_index(self.collection, [("is_chunk", 1)])
-        print(f"Ensured indexes exist for MongoDB collection: {self.collection}")
+        logger.info(
+            f"Ensured indexes exist for MongoDB collection: {self.collection}"
+        )  # Use logger.info
 
     async def add_document(
         self,
@@ -156,7 +164,9 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
         try:
             self.mongo.insert_one(self.collection, mongo_doc)
         except Exception as e:
-            print(f"Error inserting document {doc_id} into MongoDB: {e}")
+            logger.error(
+                f"Error inserting document {doc_id} into MongoDB: {e}"
+            )  # Use logger.error
             raise
 
         # Embed text using OpenAIEmbedding
@@ -164,7 +174,7 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
         try:
             embedding = await embed_model.aget_text_embedding(text)
         except Exception as e:
-            print(
+            logger.error(  # Use logger.error
                 f"Error embedding document {doc_id} using {self.openai_model_name}: {e}"
             )
             # Decide how to handle - Mongo insert succeeded, embedding failed
@@ -190,7 +200,9 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                 namespace=namespace,
             )
         except Exception as e:
-            print(f"Error upserting vector for {doc_id} to Pinecone: {e}")
+            logger.error(
+                f"Error upserting vector for {doc_id} to Pinecone: {e}"
+            )  # Use logger.error
             # Decide how to handle - Mongo insert succeeded, Pinecone failed
             raise  # Re-raise for now
 
@@ -234,9 +246,13 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
             reader = pypdf.PdfReader(io.BytesIO(pdf_bytes))
             extracted_text = "".join(page.extract_text() or "" for page in reader.pages)
             if not extracted_text.strip():
-                print(f"Warning: No text extracted from PDF {parent_doc_id}.")
+                logger.warning(
+                    f"No text extracted from PDF {parent_doc_id}."
+                )  # Use logger.warning
         except Exception as e:
-            print(f"Error reading or extracting text from PDF {parent_doc_id}: {e}")
+            logger.error(
+                f"Error reading or extracting text from PDF {parent_doc_id}: {e}"
+            )  # Use logger.error
             raise
 
         # --- 2. Store Full PDF and Metadata in MongoDB ---
@@ -254,16 +270,18 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
         }
         try:
             self.mongo.insert_one(self.collection, mongo_parent_doc)
-            print(f"Stored full PDF {parent_doc_id} in MongoDB.")
+            logger.info(
+                f"Stored full PDF {parent_doc_id} in MongoDB."
+            )  # Use logger.info
         except Exception as e:  # pragma: no cover
-            print(
+            logger.error(  # Use logger.error
                 f"Error inserting parent PDF {parent_doc_id} into MongoDB: {e}"
             )  # pragma: no cover
             raise  # pragma: no cover
 
         # --- 3. Semantic Chunking ---
         if not extracted_text.strip():
-            print(
+            logger.info(  # Use logger.info
                 f"Skipping chunking for PDF {parent_doc_id} due to no extracted text."
             )
             return parent_doc_id
@@ -274,16 +292,22 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
             nodes = await asyncio.to_thread(
                 self.semantic_splitter.get_nodes_from_documents, [llama_doc]
             )
-            print(f"Generated {len(nodes)} semantic chunks for PDF {parent_doc_id}.")
+            logger.info(
+                f"Generated {len(nodes)} semantic chunks for PDF {parent_doc_id}."
+            )  # Use logger.info
         except Exception as e:
-            print(f"Error during semantic chunking for PDF {parent_doc_id}: {e}")
+            logger.error(
+                f"Error during semantic chunking for PDF {parent_doc_id}: {e}"
+            )  # Use logger.error
             raise
 
         # --- 4. Embed Chunks and Batch Upsert to Pinecone ---
         if not nodes:
             return parent_doc_id  # No chunks generated
 
-        print(f"Embedding {len(nodes)} chunks using {self.openai_model_name}...")
+        logger.info(
+            f"Embedding {len(nodes)} chunks using {self.openai_model_name}..."
+        )  # Use logger.info
         chunk_texts = [node.get_content() for node in nodes]
         embed_model: OpenAIEmbedding = self.semantic_splitter.embed_model
         all_chunk_embeddings = []
@@ -297,10 +321,14 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                 chunk_texts, show_progress=True
             )
         except Exception as e:
-            print(f"Error embedding chunks for PDF {parent_doc_id}: {e}")
+            logger.error(
+                f"Error embedding chunks for PDF {parent_doc_id}: {e}"
+            )  # Use logger.error
             raise  # Stop if embedding fails
 
-        print("Embedding complete. Preparing vectors for Pinecone.")
+        logger.info(
+            "Embedding complete. Preparing vectors for Pinecone."
+        )  # Use logger.info
         pinecone_vectors = []
         for i, node in enumerate(nodes):
             chunk_id = f"{parent_doc_id}_chunk_{i}"
@@ -325,7 +353,7 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
             )
 
         # Upsert vectors in batches using the generic upsert method
-        print(
+        logger.info(  # Use logger.info
             f"Upserting {len(pinecone_vectors)} vectors to Pinecone in batches of {chunk_batch_size}..."
         )
         upsert_tasks = []
@@ -344,10 +372,12 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
         # Check for errors during upsert
         for idx, result in enumerate(results):
             if isinstance(result, Exception):
-                print(f"Error upserting vector batch {idx + 1} to Pinecone: {result}")
+                logger.error(
+                    f"Error upserting vector batch {idx + 1} to Pinecone: {result}"
+                )  # Use logger.error
                 # Decide on error handling: log, raise, etc.
 
-        print(f"Finished processing PDF {parent_doc_id}.")
+        logger.info(f"Finished processing PDF {parent_doc_id}.")  # Use logger.info
         return parent_doc_id
 
     async def query(
@@ -383,7 +413,9 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
         try:
             query_vector = await embed_model.aget_query_embedding(query_text)
         except Exception as e:
-            print(f"Error embedding query text '{query_text}': {e}")
+            logger.error(
+                f"Error embedding query text '{query_text}': {e}"
+            )  # Use logger.error
             return []
 
         # --- Query Pinecone using the vector ---
@@ -399,7 +431,7 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                 include_metadata=True,  # Need metadata for linking
             )
         except Exception as e:
-            print(f"Error querying Pinecone: {e}")
+            logger.error(f"Error querying Pinecone: {e}")  # Use logger.error
             return []
 
         if not pinecone_results:
@@ -433,7 +465,9 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                 )
                 mongo_docs_map = {doc["document_id"]: doc for doc in mongo_docs}
             except Exception as e:
-                print(f"Error fetching documents from MongoDB: {e}")
+                logger.error(
+                    f"Error fetching documents from MongoDB: {e}"
+                )  # Use logger.error
                 # Proceed with potentially missing Mongo data
 
         # --- Combine Results ---
@@ -520,7 +554,7 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
         Returns:
             True if deletion was successful (or partially successful).
         """
-        print(
+        logger.info(  # Use logger.info
             f"Attempting to delete document and associated data for ID: {document_id}"
         )
         mongo_deleted_count = 0
@@ -548,8 +582,8 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
             for doc in docs_to_delete_mongo:
                 mongo_ids_to_delete.add(doc["document_id"])
         except Exception as e:
-            print(
-                f"Warning: Error finding documents in MongoDB for deletion ({document_id}): {e}. Proceeding with main ID only."
+            logger.warning(  # Use logger.warning
+                f"Error finding documents in MongoDB for deletion ({document_id}): {e}. Proceeding with main ID only."
             )
 
         pinecone_ids_to_delete = list(mongo_ids_to_delete)
@@ -560,12 +594,14 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                 await self.pinecone.delete(
                     ids=pinecone_ids_to_delete, namespace=namespace
                 )
-                print(
+                logger.info(  # Use logger.info
                     f"Deleted {len(pinecone_ids_to_delete)} vectors from Pinecone for parent {document_id}."
                 )
                 pinecone_deleted = True
             except Exception as e:
-                print(f"Error deleting vectors from Pinecone for {document_id}: {e}")
+                logger.error(
+                    f"Error deleting vectors from Pinecone for {document_id}: {e}"
+                )  # Use logger.error
 
         # --- 3. Delete from MongoDB ---
         # Use the IDs confirmed to be in Mongo
@@ -576,11 +612,13 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                     self.collection, {"document_id": {"$in": mongo_ids_found_in_db}}
                 )
                 mongo_deleted_count = delete_result.deleted_count
-                print(
+                logger.info(  # Use logger.info
                     f"Deleted {mongo_deleted_count} documents from MongoDB for parent {document_id}."
                 )
             except Exception as e:
-                print(f"Error deleting documents from MongoDB for {document_id}: {e}")
+                logger.error(
+                    f"Error deleting documents from MongoDB for {document_id}: {e}"
+                )  # Use logger.error
 
         return pinecone_deleted or mongo_deleted_count > 0
 
@@ -606,14 +644,20 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
         """
         current_doc = self.mongo.find_one(self.collection, {"document_id": document_id})
         if not current_doc:
-            print(f"Document {document_id} not found for update.")
+            logger.warning(
+                f"Document {document_id} not found for update."
+            )  # Use logger.warning
             return False
 
         if current_doc.get("is_chunk"):
-            print(f"Cannot update chunk {document_id} directly.")
+            logger.warning(
+                f"Cannot update chunk {document_id} directly."
+            )  # Use logger.warning
             return False
         if current_doc.get("pdf_data") and text is not None:
-            print("Cannot update PDF content via this method. Delete and re-add.")
+            logger.warning(
+                "Cannot update PDF content via this method. Delete and re-add."
+            )  # Use logger.warning
             return False
 
         update_text = text is not None and not current_doc.get("pdf_data")
@@ -637,7 +681,9 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                 )
                 mongo_updated = update_result.modified_count > 0
             except Exception as e:
-                print(f"Error updating document {document_id} in MongoDB: {e}")
+                logger.error(
+                    f"Error updating document {document_id} in MongoDB: {e}"
+                )  # Use logger.error
                 # Decide if we should proceed to Pinecone update if Mongo failed
                 return False  # Return False if Mongo update fails
 
@@ -649,7 +695,9 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
             try:
                 embedding = await embed_model.aget_text_embedding(text_content)
             except Exception as e:
-                print(f"Error embedding updated text for {document_id}: {e}")
+                logger.error(
+                    f"Error embedding updated text for {document_id}: {e}"
+                )  # Use logger.error
                 # Mongo update might have succeeded, but embedding failed
                 return mongo_updated  # Return based on Mongo success
 
@@ -685,7 +733,7 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                 )
                 pinecone_updated = True
             except Exception as e:
-                print(
+                logger.error(  # Use logger.error
                     f"Error upserting updated vector in Pinecone for {document_id}: {e}"
                 )
                 # Mongo update succeeded, Pinecone failed
@@ -750,7 +798,7 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                 try:
                     self.mongo.insert_many(self.collection, mongo_batch)
                 except Exception as e:
-                    print(
+                    logger.error(  # Use logger.error
                         f"Error inserting batch {i // batch_size + 1} into MongoDB: {e}"
                     )
                     # Decide if we should skip Pinecone for this batch
@@ -762,7 +810,7 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                     batch_texts, show_progress=True
                 )
             except Exception as e:
-                print(
+                logger.error(  # Use logger.error
                     f"Error embedding batch {i // batch_size + 1} using {self.openai_model_name}: {e}"
                 )
                 continue  # Skip Pinecone upsert for this batch
@@ -795,7 +843,7 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
                         vectors=pinecone_vectors, namespace=namespace
                     )
                 except Exception as e:
-                    print(
+                    logger.error(  # Use logger.error
                         f"Error upserting vector batch {i // batch_size + 1} to Pinecone: {e}"
                     )
 
@@ -818,5 +866,7 @@ class KnowledgeBaseService(KnowledgeBaseInterface):
         try:
             return self.mongo.find_one(self.collection, {"document_id": document_id})
         except Exception as e:
-            print(f"Error retrieving full document {document_id} from MongoDB: {e}")
+            logger.error(
+                f"Error retrieving full document {document_id} from MongoDB: {e}"
+            )  # Use logger.error
             return None

solana_agent/services/routing.py

@@ -5,6 +5,7 @@ This service manages query routing to appropriate agents based on
 specializations and query analysis.
 """
 
+import logging
 from typing import Dict, List, Optional, Any
 from solana_agent.interfaces.services.routing import (
     RoutingService as RoutingServiceInterface,
@@ -13,6 +14,9 @@ from solana_agent.interfaces.services.agent import AgentService
 from solana_agent.interfaces.providers.llm import LLMProvider
 from solana_agent.domains.routing import QueryAnalysis
 
+# Setup logger for this module
+logger = logging.getLogger(__name__)
+
 
 class RoutingService(RoutingServiceInterface):
     """Service for routing queries to appropriate agents."""
@@ -67,19 +71,19 @@ class RoutingService(RoutingServiceInterface):
 
         prompt = f"""
         Analyze this user query and determine which agent would be best suited to answer it.
-        
+
         AVAILABLE AGENTS AND THEIR SPECIALIZATIONS:
         {specializations_text}
-        
+
         USER QUERY: {query}
-        
+
         Please determine:
         1. Which agent is the primary best match for this query (must be one of the listed agents)
         2. Any secondary agents that might be helpful (must be from the listed agents)
         3. The complexity level (1-5, where 5 is most complex)
         4. Any key topics or technologies mentioned
-        
-        Think carefully about whether the query is more technical/development-focused or more 
+
+        Think carefully about whether the query is more technical/development-focused or more
         financial/market-focused to match with the appropriate agent.
         """
 
@@ -101,7 +105,7 @@ class RoutingService(RoutingServiceInterface):
                 "confidence": analysis.confidence,
             }
         except Exception as e:
-            print(f"Error analyzing query: {e}")
+            logger.error(f"Error analyzing query: {e}")  # Use logger.error
             # Return default analysis on error
             return {
                 "primary_specialization": list(agents.keys())[0]
@@ -125,8 +129,9 @@ class RoutingService(RoutingServiceInterface):
         # If only one agent - use that agent
         agents = self.agent_service.get_all_ai_agents()
         if len(agents) == 1:
-            print(f"Only one agent available: {next(iter(agents.keys()))}")
-            return next(iter(agents.keys()))
+            agent_name = next(iter(agents.keys()))
+            logger.info(f"Only one agent available: {agent_name}")  # Use logger.info
+            return agent_name
 
         # Analyze query
         analysis = await self._analyze_query(query)
@@ -190,7 +195,7 @@ class RoutingService(RoutingServiceInterface):
 
         # Sort by score
         agent_scores.sort(key=lambda x: x[1], reverse=True)
-        print(f"Agent scores: {agent_scores}")
+        logger.debug(f"Agent scores: {agent_scores}")  # Use logger.debug
 
         # Return the highest scoring agent, if any
         if agent_scores and agent_scores[0][1] > 0:

{solana_agent-28.1.1.dist-info → solana_agent-28.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: solana-agent
-Version: 28.1.1
+Version: 28.2.1
 Summary: AI Agents for Solana
 License: MIT
 Keywords: solana,solana ai,solana agent,ai,ai agent,ai agents
@@ -23,7 +23,9 @@ Requires-Dist: pinecone (>=6.0.2,<7.0.0)
 Requires-Dist: pydantic (>=2)
 Requires-Dist: pymongo (>=4.12.0,<5.0.0)
 Requires-Dist: pypdf (>=5.4.0,<6.0.0)
+Requires-Dist: rich (>=13)
 Requires-Dist: scrubadub (>=2.0.1,<3.0.0)
+Requires-Dist: typer (>=0.15.2,<0.16.0)
 Requires-Dist: zep-cloud (>=2.10.1,<3.0.0)
 Project-URL: Documentation, https://docs.solana-agent.com
 Project-URL: Homepage, https://solana-agent.com
@@ -284,6 +286,47 @@ async for response in solana_agent.process("user123", audio_content, audio_input
     print(response, end="")
 ```
 
+### Command Line Interface (CLI)
+
+Solana Agent includes a command-line interface (CLI) for text-based chat using a configuration file.
+
+Ensure you have a valid configuration file (e.g., `config.json`) containing at least your OpenAI API key and agent definitions.
+
+**./config.json**
+```json
+{
+    "openai": {
+        "api_key": "your-openai-api-key"
+    },
+    "agents": [
+        {
+            "name": "default_agent",
+            "instructions": "You are a helpful AI assistant.",
+            "specialization": "general"
+        }
+    ]
+}
+```
+
+Also ensure that you have `pip install uv` to call `uvx`.
+
+```bash
+uvx solana-agent [OPTIONS]
+
+Options:
+
+--user-id TEXT: The user ID for the conversation (default: cli_user).
+--config TEXT: Path to the configuration JSON file (default: config.json).
+--prompt TEXT: Optional system prompt override for the agent.
+--help: Show help message and exit.
+
+# Using default config.json and user_id
+uvx solana-agent
+
+# Specifying user ID and config path
+uvx solana-agent --user-id my_cli_session --config ./my_agent_config.json
+```
+
 ## Optional Feature Configs
 
 ### Business Alignment
@@ -542,7 +585,7 @@ config = {
             "rpc_url": "your-solana-rpc-url",
         },
     },
-    "ai_agents": [
+    "agents": [
         {
             "name": "solana_expert",
             "instructions": "You are an expert Solana blockchain assistant. You always use the Solana tool to perform actions on the Solana blockchain.",

{solana_agent-28.1.1.dist-info → solana_agent-28.2.1.dist-info}/RECORD

@@ -1,15 +1,16 @@
 solana_agent/__init__.py,sha256=g83qhMOCwcWL19V4CYbQwl0Ykpb0xn49OUh05i-pu3g,1001
 solana_agent/adapters/__init__.py,sha256=tiEEuuy0NF3ngc_tGEcRTt71zVI58v3dYY9RvMrF2Cg,204
 solana_agent/adapters/mongodb_adapter.py,sha256=0KWIa6kaFbUFvtKUzuV_0p0RFlPPGKrDVIEU2McVY3k,2734
-solana_agent/adapters/openai_adapter.py,sha256=iDAOKZkN4x2yNarDIrS71w6ufjKnC-wlT3iZFOXCoY4,12099
-solana_agent/adapters/pinecone_adapter.py,sha256=SDbf_XJMuFDKhNfF25_VXaYG3vrmYyPIo2SyhaniEwg,23048
+solana_agent/adapters/openai_adapter.py,sha256=rSa1yYYIpr5ES3Zw0DZm7iGp59p0WYBQXH0EQ1UDAB4,13594
+solana_agent/adapters/pinecone_adapter.py,sha256=XlfOpoKHwzpaU4KZnovO2TnEYbsw-3B53ZKQDtBeDgU,23847
+solana_agent/cli.py,sha256=FGvTIQmKLp6XsQdyKtuhIIfbBtMmcCCXfigNrj4bzMc,4704
 solana_agent/client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 solana_agent/client/solana_agent.py,sha256=jUGWxYJL9ZWxGsVX9C6FrRQyX7r6Cep0ijcfm7cbkJI,10098
 solana_agent/domains/__init__.py,sha256=HiC94wVPRy-QDJSSRywCRrhrFfTBeHjfi5z-QfZv46U,168
 solana_agent/domains/agent.py,sha256=3Q1wg4eIul0CPpaYBOjEthKTfcdhf1SAiWc2R-IMGO8,2561
 solana_agent/domains/routing.py,sha256=1yR4IswGcmREGgbOOI6TKCfuM7gYGOhQjLkBqnZ-rNo,582
 solana_agent/factories/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-solana_agent/factories/agent_factory.py,sha256=_tBCzx-QIAkGg0v47GiGaQIH7xjlF_5zAt7VFEyqu6k,12273
+solana_agent/factories/agent_factory.py,sha256=kduhtCMAxiPmCW_wx-hGGlhehRRGt4OBKY8r-R-LZnI,13246
 solana_agent/guardrails/pii.py,sha256=FCz1IC3mmkr41QFFf5NaC0fwJrVkwFsxgyOCS2POO5I,4428
 solana_agent/interfaces/__init__.py,sha256=IQs1WIM1FeKP1-kY2FEfyhol_dB-I-VAe2rD6jrVF6k,355
 solana_agent/interfaces/client/client.py,sha256=hsvaQiQdz3MLMNc77oD6ocvvnyl7Ez2n087ptFDA19M,3687
@@ -24,18 +25,19 @@ solana_agent/interfaces/services/knowledge_base.py,sha256=HsU4fAMc_oOUCqCX2z76_I
 solana_agent/interfaces/services/query.py,sha256=QfpBA3hrv8pQdNbK05hbu3Vh3-53F46IFcoUjwj5J9w,1568
 solana_agent/interfaces/services/routing.py,sha256=Qbn3-DQGVSQKaegHDekSFmn_XCklA0H2f0XUx9-o3wA,367
 solana_agent/plugins/__init__.py,sha256=coZdgJKq1ExOaj6qB810i3rEhbjdVlrkN76ozt_Ojgo,193
-solana_agent/plugins/manager.py,sha256=Rrpom5noR5XCcDDAE9C8H_ITJDfj5gdkQF1dmgi5Eu0,5040
-solana_agent/plugins/registry.py,sha256=0Bx3e_4fq20FtI0vbCTQanwK0AashQOr4vsqR26Jql8,3631
+solana_agent/plugins/manager.py,sha256=mO_dKSVJ8GToD3wZflMcpKDEBXRoaaMRtY267HENCI0,5542
+solana_agent/plugins/registry.py,sha256=VAG0BWdUUIsEE-VpATtHi8qat7ziPuh7pKuzGXauwgc,4173
 solana_agent/plugins/tools/__init__.py,sha256=VDjJxvUjefIy10VztQ9WDKgIegvDbIXBQWsHLhxdZ3o,125
 solana_agent/plugins/tools/auto_tool.py,sha256=uihijtlc9CCqCIaRcwPuuN7o1SHIpWL2GV3vr33GG3E,1576
 solana_agent/repositories/__init__.py,sha256=fP83w83CGzXLnSdq-C5wbw9EhWTYtqE2lQTgp46-X_4,163
-solana_agent/repositories/memory.py,sha256=YYpCyiDVi3a5ZOFYFkzBS6MDjo9g2TnwbEZ5KKfKbII,7204
+solana_agent/repositories/memory.py,sha256=e-27ju6wmurxSxULzr_uDHxxdnvw8KrJt9NWyvAz-i4,7684
 solana_agent/services/__init__.py,sha256=iko0c2MlF8b_SA_nuBGFllr2E3g_JowOrOzGcnU9tkA,162
 solana_agent/services/agent.py,sha256=9FB1Tj7v8JwJVVmZwK8IOSrBbgbV4iFZOtFHzw3gcEs,41780
-solana_agent/services/knowledge_base.py,sha256=J9V8dNoCCcko3EasiGwK2JJ_A_oG_e-Ni9pgNg0T6wA,33486
+solana_agent/services/knowledge_base.py,sha256=D4QNGC3Z8E7iX-CEGpRks0lW4wWJt-WorO3J8mu6ayU,35318
 solana_agent/services/query.py,sha256=bAoUfe_2EBVEVeh99-2E9KZ0zaHUzf7Lqel3rlHyNX8,17459
-solana_agent/services/routing.py,sha256=-0fNIKDtCn0-TLUYDFYAE4jPLMeI_jCXIpgtgWDpdf8,6986
-solana_agent-28.1.1.dist-info/LICENSE,sha256=BnSRc-NSFuyF2s496l_4EyrwAP6YimvxWcjPiJ0J7g4,1057
-solana_agent-28.1.1.dist-info/METADATA,sha256=JKmf9tN-lKJpjdBzP8UTY8S-yUTo_IrPAW2iAemnnD0,27150
-solana_agent-28.1.1.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
-solana_agent-28.1.1.dist-info/RECORD,,
+solana_agent/services/routing.py,sha256=C5Ku4t9TqvY7S8wlUPMTC04HCrT4Ib3E8Q8yX0lVU_s,7137
+solana_agent-28.2.1.dist-info/LICENSE,sha256=BnSRc-NSFuyF2s496l_4EyrwAP6YimvxWcjPiJ0J7g4,1057
+solana_agent-28.2.1.dist-info/METADATA,sha256=2tCGkpcfk_gc4uK-0yk5xUIVwUmlWpDIvYgeX45N-9E,28283
+solana_agent-28.2.1.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+solana_agent-28.2.1.dist-info/entry_points.txt,sha256=-AuT_mfqk8dlZ0pHuAjx1ouAWpTRjpqvEUa6YV3lmc0,53
+solana_agent-28.2.1.dist-info/RECORD,,

solana_agent-28.2.1.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+solana-agent=solana_agent.cli:app
+