PyPI - solana-agent - Versions diffs - 19.0.0__tar.gz → 19.0.2__tar.gz - Mend

solana-agent 19.0.0tar.gz → 19.0.2tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (35) hide show

{solana_agent-19.0.0 → solana_agent-19.0.2}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: solana-agent
-Version: 19.0.0
+Version: 19.0.2
 Summary: Agentic IQ
 License: MIT
 Keywords: ai,openai,ai agents,agi
@@ -35,41 +35,36 @@ Description-Content-Type: text/markdown
 ## Agentic IQ
-Power your business using Solana Agent!
+Build your AI business in three lines of code!
-* **Brand:** AI agents will speak in your brand voice
-* **Expert:** The AI agent with the most expertise will answer your users' inquiries
-* **Extend:** Assign tools for your AI agents to perform actions
+## Why?
+* Three lines of code required
+* Multi-Modal Streaming
+* Conversational Memory & History
+* Intelligent Routing
+* Business Alignment
+* Extensible Tooling
+* Simple Business Definition
+* Tested & Secure
+* Built in Python
+* Deployed by [CometHeart](https://cometheart.com) & [WalletBubbles](https://walletbubbles.com)
 ## Features
 * Seamless text and audio streaming with real-time multi-modal processing
-* Persistent memory that preserves context across all agent interactions (optional)
+* Persistent memory that preserves context across all agent interactions
+* Streamlined message history for all agent interactions
 * Intelligent query routing to agents with optimal domain expertise
 * Unified value system ensuring brand-aligned agent responses
 * Powerful tool integration using standard Python packages and/or inline classes
 * Assigned tools are utilized by agents automatically and effectively
 * Simple business definition using JSON
-## Why?
-* Multi-Modal Streaming
-* Conversational Memory
-* Intelligent Routing
-* Business Alignment
-* Extensible Tooling
-* Simple Business Definition
-* Built using OOP & SOLID in Python - the language of AI
-* Batteries Included
-* Small Library: ~2,000 LOC of code & ~1,200 LOC of tests
-* Few Dependencies
-* Well Tested
-* Used in production by [CometHeart](https://cometheart.com) and [WalletBubbles](https://walletbubbles.com)
 ## Stack
 * [Python](https://python.org) - Programming Language
 * [OpenAI](https://openai.com) - LLMs
-* [MongoDB](https://mongodb.com) - Database
+* [MongoDB](https://mongodb.com) - Conversational History
 * [Zep](https://getzep.com) - Conversational Memory (optional)
 ## Installation
@@ -84,7 +79,7 @@ You can install Solana Agent using pip:
 from solana_agent import SolanaAgent
 config = {
-    "business": {
+    "business": { # optional
         "mission": "To provide users with a one-stop shop for their queries.",
         "values": {
             "Friendliness": "Users must be treated fairly, openly, and with friendliness.",
@@ -136,7 +131,7 @@ Plugins like Solana Agent Kit (sakit) integrate automatically with Solana Agent.
 from solana_agent import SolanaAgent
 config = {
-    "business": {
+    "business": { # optional
         "mission": "To provide users with a one-stop shop for their queries.",
         "values": {
             "Friendliness": "Users must be treated fairly, openly, and with friendliness.",
@@ -241,7 +236,7 @@ class TestTool(Tool):
             }
 config = {
-    "business": {
+    "business": { # optional
         "mission": "To provide users with a one-stop shop for their queries.",
         "values": {
             "Friendliness": "Users must be treated fairly, openly, and with friendliness.",

{solana_agent-19.0.0 → solana_agent-19.0.2}/README.md RENAMED Viewed

@@ -12,41 +12,36 @@
 ## Agentic IQ
-Power your business using Solana Agent!
+Build your AI business in three lines of code!
-* **Brand:** AI agents will speak in your brand voice
-* **Expert:** The AI agent with the most expertise will answer your users' inquiries
-* **Extend:** Assign tools for your AI agents to perform actions
+## Why?
+* Three lines of code required
+* Multi-Modal Streaming
+* Conversational Memory & History
+* Intelligent Routing
+* Business Alignment
+* Extensible Tooling
+* Simple Business Definition
+* Tested & Secure
+* Built in Python
+* Deployed by [CometHeart](https://cometheart.com) & [WalletBubbles](https://walletbubbles.com)
 ## Features
 * Seamless text and audio streaming with real-time multi-modal processing
-* Persistent memory that preserves context across all agent interactions (optional)
+* Persistent memory that preserves context across all agent interactions
+* Streamlined message history for all agent interactions
 * Intelligent query routing to agents with optimal domain expertise
 * Unified value system ensuring brand-aligned agent responses
 * Powerful tool integration using standard Python packages and/or inline classes
 * Assigned tools are utilized by agents automatically and effectively
 * Simple business definition using JSON
-## Why?
-* Multi-Modal Streaming
-* Conversational Memory
-* Intelligent Routing
-* Business Alignment
-* Extensible Tooling
-* Simple Business Definition
-* Built using OOP & SOLID in Python - the language of AI
-* Batteries Included
-* Small Library: ~2,000 LOC of code & ~1,200 LOC of tests
-* Few Dependencies
-* Well Tested
-* Used in production by [CometHeart](https://cometheart.com) and [WalletBubbles](https://walletbubbles.com)
 ## Stack
 * [Python](https://python.org) - Programming Language
 * [OpenAI](https://openai.com) - LLMs
-* [MongoDB](https://mongodb.com) - Database
+* [MongoDB](https://mongodb.com) - Conversational History
 * [Zep](https://getzep.com) - Conversational Memory (optional)
 ## Installation
@@ -61,7 +56,7 @@ You can install Solana Agent using pip:
 from solana_agent import SolanaAgent
 config = {
-    "business": {
+    "business": { # optional
         "mission": "To provide users with a one-stop shop for their queries.",
         "values": {
             "Friendliness": "Users must be treated fairly, openly, and with friendliness.",
@@ -113,7 +108,7 @@ Plugins like Solana Agent Kit (sakit) integrate automatically with Solana Agent.
 from solana_agent import SolanaAgent
 config = {
-    "business": {
+    "business": { # optional
         "mission": "To provide users with a one-stop shop for their queries.",
         "values": {
             "Friendliness": "Users must be treated fairly, openly, and with friendliness.",
@@ -218,7 +213,7 @@ class TestTool(Tool):
             }
 config = {
-    "business": {
+    "business": { # optional
         "mission": "To provide users with a one-stop shop for their queries.",
         "values": {
             "Friendliness": "Users must be treated fairly, openly, and with friendliness.",

{solana_agent-19.0.0 → solana_agent-19.0.2}/pyproject.toml RENAMED Viewed

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "solana-agent"
-version = "19.0.0"
+version = "19.0.2"
 description = "Agentic IQ"
 authors = ["Bevan Hunt <bevan@bevanhunt.com>"]
 license = "MIT"

{solana_agent-19.0.0 → solana_agent-19.0.2}/solana_agent/services/agent.py RENAMED Viewed

@@ -267,13 +267,16 @@ class AgentService(AgentServiceInterface):
                                 json_chunk=json_buffer
                             )
-                            system_prompt = self.get_agent_system_prompt(agent_name) + \
+                            system_prompt = system_prompt + \
                                 "\n DO NOT make any tool calls or return JSON."
+                            user_prompt = f"\n USER QUERY: {query_text} \n"
+                            user_prompt += f"\n TOOL RESPONSE: {response_text} \n"
                             # Collect all processed text first
                             processed_text = ""
                             async for processed_chunk in self.llm_provider.generate_text(
-                                prompt=response_text,
+                                prompt=user_prompt,
                                 system_prompt=system_prompt,
                             ):
                                 processed_text += processed_chunk