Skip to content

fix(components): reuse extracted response content for ConditionAgent JSON parsing #6072

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
HenryHengZJ merged 3 commits into from
Apr 1, 2026
Merged

fix(components): reuse extracted response content for ConditionAgent JSON parsing #6072

Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
85757d5
fix: normalize conditionagent response content before parsing
Mar 28, 2026
d065b45
fix(components): reuse normalized response content in ConditionAgent
Mar 28, 2026
e8700ed
Merge branch 'main' into bugfix/fix-conditionagent-response-content-n…
jslim-23 Apr 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 5 additions & 7 deletions packages/components/nodes/agentflow/ConditionAgent/ConditionAgent.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -391,11 +391,12 @@ class ConditionAgent_Agentflow implements INode {
// Calculate execution time
const endTime = Date.now()
const timeDelta = endTime - startTime
const responseContent = extractResponseContent(response)

// End analytics tracking (pass structured output with usage metadata)
if (analyticHandlers && llmIds) {
const analyticsOutput: any = {
content: extractResponseContent(response)
content: responseContent
}
// Include usage metadata if available
if (response.usage_metadata) {
Expand All @@ -407,19 +408,16 @@ class ConditionAgent_Agentflow implements INode {
}
await analyticHandlers.onLLMEnd(llmIds, analyticsOutput, { model: modelName, provider: model })
}

let calledOutputName: string
try {
const parsedResponse = this.parseJsonMarkdown(response.content as string)
const parsedResponse = this.parseJsonMarkdown(responseContent)
if (!parsedResponse.output || typeof parsedResponse.output !== 'string') {
throw new Error('LLM response is missing the "output" key or it is not a string.')
}
calledOutputName = parsedResponse.output
} catch (error) {
throw new Error(
`Failed to parse a valid scenario from the LLM's response. Please check if the model is capable of following JSON output instructions. Raw LLM Response: "${
response.content as string
}"`
`Failed to parse a valid scenario from the LLM's response. Please check if the model is capable of following JSON output instructions. Raw LLM Response: "${responseContent}"`
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Mar 28, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For better readability in error logs, it's a good practice to truncate long raw responses. The responseContent could be quite large, making the error message difficult to read. Consider truncating it if it exceeds a certain length, similar to how it's done in parseJsonBody.

Suggested change
`Failed to parse a valid scenario from the LLM's response. Please check if the model is capable of following JSON output instructions. Raw LLM Response: "${responseContent}"`
"Failed to parse a valid scenario from the LLM's response. Please check if the model is capable of following JSON output instructions. Raw LLM Response: \"" + responseContent.substring(0, 200) + (responseContent.length > 200 ? "..." : "") + "\""
References
  1. Prioritize code readability and understandability over conciseness. Truncating large blobs in logs improves the readability and utility of error messages for debugging.

)
}

Expand Down Expand Up @@ -472,7 +470,7 @@ class ConditionAgent_Agentflow implements INode {

const output: any = {
conditions,
content: extractResponseContent(response),
content: responseContent,
timeMetadata: {
start: startTime,
end: endTime,
Expand Down
Loading