github/genai-toolbox
1
0
Fork 0
mirror of https://github.com/googleapis/genai-toolbox.git synced 2026-02-03 11:45:10 -05:00
Code Issues Packages Projects Releases 14 Wiki Activity

Highlight tool level processing

Browse Source
This commit is contained in:
Twisha Bansal
2026-01-29 13:00:07 +05:30
parent ca6f31a192
commit 3a150c77ca
1 changed files with 6 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
docs/en/samples/pre_post_processing/_index.md
View File

@@ -28,25 +28,18 @@ Post-processing occurs after a tool has executed or the model has generated a re
## Processing Scopes
Processing logic can be applied at different levels of the application:
While processing logic can be applied at various levels (Agent, Model, Tool), this guide primarily focuses on **Tool Level** processing, which is most relevant for granular control over tool execution.
### Tool Level
### Tool Level (Primary Focus)
Wraps individual tool executions. This is best for logic specific to a single tool or a set of tools.
- **Scope**: Intercepts the raw inputs (arguments) to a tool and its outputs.
- **Use Cases**: Argument validation, output formatting, specific privacy rules for sensitive tools.
### Model Level
### Comparison with Other Levels
Intercepts individual calls to the Large Language Model (LLM).
It is helpful to understand how tool-level processing differs from other scopes:
- **Scope**: Intercepts the list of messages (prompt) sent to the model and the generation (response) received.
- **Use Cases**: Global PII redaction (across all tools/chat), prompt engineering/injection, token usage tracking, and hallucination detection.
### Agent Level
Wraps the high-level agent execution loop (e.g., a "turn" in the conversation).
- **Scope**: Intercepts the initial user input and the final agent response, enveloping one or more model calls and tool executions.
- **Use Cases**: User authentication, rate limiting, session management, and end-to-end audit logging.
- **Model Level**: Intercepts individual calls to the LLM (prompts and responses). Unlike tool-level, this applies globally to all text sent/received, making it better for global PII redaction or token tracking.
- **Agent Level**: Wraps the high-level execution loop (e.g., a "turn" in the conversation). Unlike tool-level, this envelopes the entire turn (user input to final response), making it suitable for session management or end-to-end auditing.