encounter/adk-python
0
0
Fork 0
mirror of https://github.com/encounter/adk-python.git synced 2026-07-09 18:19:28 -07:00
Code Issues Packages Projects Releases Wiki Activity

chore: Tune instructions to not ask root directory if it's already provided in the context

Browse Source 
PiperOrigin-RevId: 803512675
This commit is contained in:
Xiang (Sean) Zhou
2025-09-05 10:23:34 -07:00
committed by Copybara-Service
parent 45c1fcc84f
commit 25df6c22d5
2 changed files with 8 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
contributing/samples/adk_agent_builder_assistant/instruction_embedded.template
+4 -1
View File
@@ -26,7 +26,10 @@ Always reference this schema when creating configurations to ensure compliance.
## Workflow Guidelines
### 1. Discovery Phase
- **ASK FOR ROOT DIRECTORY** upfront to establish working context
- **ROOT DIRECTORY ESTABLISHMENT**:
* **FIRST**: Check SESSION CONTEXT section below for "Established Root Directory"
* **IF ESTABLISHED**: Use the existing session root directory - DO NOT ask again
* **IF NOT ESTABLISHED**: Ask user for root directory to establish working context
- **MODEL PREFERENCE**: Always ask for explicit model confirmation when LlmAgent(s) will be needed
* **When to ask**: After analyzing requirements and deciding that LlmAgent is needed for the solution
* **MANDATORY CONFIRMATION**: Say "Please confirm what model you want to use" - do NOT assume or suggest defaults
contributing/samples/adk_agent_builder_assistant/instruction_query.template
+4 -1
View File
@@ -29,7 +29,10 @@ Always use the query_schema tool when you need specific ADK AgentConfig schema i
## Workflow Guidelines
### 1. Discovery Phase
- **ASK FOR ROOT DIRECTORY** upfront to establish working context
- **ROOT DIRECTORY ESTABLISHMENT**:
* **FIRST**: Check SESSION CONTEXT section below for "Established Root Directory"
* **IF ESTABLISHED**: Use the existing session root directory - DO NOT ask again
* **IF NOT ESTABLISHED**: Ask user for root directory to establish working context
- **MODEL PREFERENCE**: Only ask for model preference when you determine that LlmAgent(s) will be needed
* **When to ask**: After analyzing requirements and deciding that LlmAgent is needed for the solution
* **DEFAULT**: Use "{default_model}" (your current model) if user doesn't specify