Add LLMExclude field annotation for agent tool results#210
Merged
Conversation
…t tool results Add LLMExclude marker class (used via Annotated[Type, LLMExclude()]) that lets Pydantic model fields be automatically stripped before tool results reach the LLM. This replaces manual dict cherry-picking in tool handlers. - New module: bluebox/utils/llm_serialization.py - LLMExclude marker, strip_llm_excluded() recursive stripper - serialize_tool_result() moved here from abstract_agent.py (now SerializedToolResult NamedTuple) - Cached _excluded_fields() per model class - Handles computed_field properties correctly - Hook in AbstractAgent._execute_tool() applies stripping automatically - Comprehensive tests: 68 unit tests + 6 integration tests Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
dimavrem22
approved these changes
Feb 27, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Updates include:
LLMExcludemarker for Pydantic fields that should be stripped before tool results reach the LLM. Use viaAnnotated[str, LLMExclude()]._execute_tool(). Tool handlers can return models directly instead of manually cherry-picking fields into dicts.@computed_fieldproperties.serialize_tool_resultto newbluebox/utils/llm_serialization.pymodule (now returnsSerializedToolResultnamed tuple)._execute_toolhook.