feat(core): support customized tool result converter#413
Merged
AlbumenJ merged 26 commits intoagentscope-ai:mainfrom Jan 5, 2026
Merged
feat(core): support customized tool result converter#413AlbumenJ merged 26 commits intoagentscope-ai:mainfrom
AlbumenJ merged 26 commits intoagentscope-ai:mainfrom
Conversation
Change-Id: I45a7afebfa3bb4df854c7faa3dde3ad87a39aa25
Change-Id: I45a7afebfa3bb4df854c7faa3dde3ad87a39aa25
Change-Id: I3a2c8ceb6fab8703481cb4c3b293d3f4de10c6f7
Change-Id: I45a7afebfa3bb4df854c7faa3dde3ad87a39aa25
Change-Id: I3a2c8ceb6fab8703481cb4c3b293d3f4de10c6f7
Change-Id: I4d9b6876d08eb3c153c29bd8eec0623a28cb99f7
Codecov Report❌ Patch coverage is 📢 Thoughts on this report? Let us know! |
Change-Id: Ic21ee9c89dfca955bbaa7f6cf2ef31ce74ec37e9
Change-Id: I73929f25100b4e5fa5045a536e2554076d1aa7df
Change-Id: I01d05514198850608993e73dda9d3ff849c15b81
Change-Id: Ief21e7112db8385bab3fc74dc3e72e9afdca22c1
Change-Id: I0cbd30e71bc061cf8154112482be56262f3b1dbf
Change-Id: I18ea26e5ccb6f012fd75d54d233dc24fe514461d
Change-Id: Ib2eb22cfee9af20c34fee7e775d1ffb88cf0b52e
Change-Id: I716ca9f16da80da31b83e8a270e3da6429eb9c59
AlbumenJ
approved these changes
Jan 5, 2026
This was referenced Jan 11, 2026
Closed
AlbumenJ
pushed a commit
that referenced
this pull request
Jan 12, 2026
…o agentscope-all (#507) close #506 ## AgentScope-Java Version 1.0.7-SNAPSHOT ## Description The dependency was added to agentscope-core but not synced to agentscope-all, causing NoClassDefFoundError for users of the all-in-one artifact. ### Root Cause The `jackson-datatype-jsr310` dependency was added to `agentscope-core` in commit 5f19549 (#413), but was not synchronized to `agentscope-all/pom.xml`. Since `agentscope-core` is declared with `<optional>true</optional>` in `agentscope-all`, its transitive dependencies are not propagated to downstream users. ### Solution Add the missing `jackson-datatype-jsr310` dependency to `agentscope-distribution/agentscope-all/pom.xml`. ## Checklist Please check the following items before code is ready to be reviewed. - [x] Code has been formatted with `mvn spotless:apply` - [x] All tests are passing (`mvn test`) - [x] Javadoc comments are complete and follow project conventions - [x] Related documentation has been updated (e.g. links, examples, etc.) - [x] Code is ready for review
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.
AgentScope-Java Version
1.0.6-SNAPSHOT
Description
This PR introduces the ability for users to customize how tool execution results are converted and presented to LLMs by implementing custom ToolResultConverter classes. This enhancement provides businesses with greater control over tool output formatting, security, and LLM comprehension.
Previously, all tool results were serialized using a default JSON converter without customization options. This limitation made it difficult to:
Add schema descriptions: Provide structured metadata about return objects to improve LLM understanding beyond simple JSON serialization
Mask sensitive information: Centrally filter confidential data (keys, PII, internal IDs) from tool responses before sending to LLMs
Format outputs optimally: Customize result formatting for specific use cases (compression, summarization, formatting)
Add contextual metadata: Include additional information about tool execution (execution time, data sources, confidence scores)
Checklist
Please check the following items before code is ready to be reviewed.
mvn spotless:applymvn test)