fix(d-pi): remote_* tools return native AgentToolResult directly#48
Open
sheason2019 wants to merge 1 commit into
Open
fix(d-pi): remote_* tools return native AgentToolResult directly#48sheason2019 wants to merge 1 commit into
sheason2019 wants to merge 1 commit into
Conversation
remote_bash/remote_read/... were wrapping the executor result in a
JSON.stringify text block, creating double-nested JSON the LLM
could not parse. The executor runner already returns the native
tool's execute() return value (a valid AgentToolResult with content
+ details) — the remote wrapper just needs to pass it through.
Before: r.result = {content:[...], details:{...}}
return {content:[{text: JSON.stringify(r.result)}], details:{}}
→ LLM sees: {"content":[{"type":"text","text":"{\"content\":[...] }"}]}
After: r.result = {content:[...], details:{...}}
return r.result
→ LLM sees the native tool output directly
52485a8 to
b4f99d4
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
remote_bash/remote_read/... were wrapping the executor result in a JSON.stringify text block, creating double-nested JSON the LLM could not parse.
The executor runner already returns the native tool's execute() return value (a valid AgentToolResult with content + details). The remote wrapper just needs to pass it through.