Conversation
Unlike everyrow_agent (which processes many CSV rows), this tool dispatches a single agent to research one question, optionally with context data via input_data dict and a structured response_schema. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
![sentry[bot]](https://avatars.githubusercontent.com/in/12637?s=60&v=4){kind=small}
Two tests: with input_data + response_schema, and a pure question with no context. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Contributor
Author
|
@claude code review |
jackwildman
approved these changes
Feb 20, 2026
Comment on lines
+146
to
+148
| - "Find the current CEO of Apple and their background" | ||
| - "Research the latest funding round for this company" (with input_data: {"company": "Stripe"}) | ||
| - "What are the pricing tiers for this product?" (with input_data: {"product": "Snowflake"}) |
Contributor
There was a problem hiding this comment.
These aren't especially good examples. We'd mostly use single agent for expand operations, so most of the examples would be better as "give me a list of ..."
Contributor
Author
There was a problem hiding this comment.
I think this can be fixed-forward.
Comment on lines
49
to
+55
| "name": "everyrow_agent", | ||
| "description": "Run web research agents on each row of a CSV file." | ||
| }, | ||
| { | ||
| "name": "everyrow_single_agent", | ||
| "description": "Run a single web research agent on a task, optionally with context data." | ||
| }, |
Contributor
There was a problem hiding this comment.
Not for this PR, but I do think it's a bit off in our interface that we distinguish agent and single_agent, rather than single_agent being a special case of agent/agent-map. Might be something for us to consider later
The API returns a single object (TaskResultResponseDataType1) for single_agent results instead of a list. Without this, everyrow_results returned "Task result has no table data" for all single agent tasks. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
3 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.
Summary
everyrow_single_agentMCP tool that dispatches a single web research agent on a task (unlikeeveryrow_agentwhich processes many CSV rows)input_datadict for context andresponse_schemafor structured outputSingleAgentInputmodel, manifest entry, server re-exports, and unit testsTest plan
uv run pytest tests/ -x -q— 39 passed, 5 skipped)🤖 Generated with Claude Code