fix: Support 'args' key in response tool call argument extraction#138
Merged
ericapisani merged 1 commit intomainfrom Apr 10, 2026
Merged
Conversation
Some frameworks (e.g. LangGraph Python) return tool calls with an 'args' key instead of 'arguments'. Add 'args' as a fallback in checkResponseToolCalls so these tool calls are validated correctly. Refs PY-2281 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
🔴 AI SDK Integration Test ResultsStatus: 8 regressions detected Summary
🔴 RegressionsThese tests were passing on main but are now failing: cloudflare/langchain :: Basic LLM Test (blocking)Error: Test execution failed: Wrangler exited with code 1 cloudflare/langchain :: Multi-Turn LLM Test (blocking)Error: Test execution failed: Wrangler exited with code 1 cloudflare/langchain :: Basic Error LLM Test (blocking)Error: Test execution failed: Wrangler exited with code 1 cloudflare/langchain :: Vision LLM Test (blocking)Error: Test execution failed: Wrangler exited with code 1 python/google-genai :: Basic LLM Test (sync, blocking)Error: 2 check(s) failed: python/fastmcp :: MCP Resource Read Test (async, blocking, sse)Error: Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/fastmcp-mcp-2.3.4-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/fastmcp-mcp-2.3.4-sentry-latest/test-mcp-resource-read-test-async-blocking-sse.py python/mcp :: MCP Multiple Tool Calls Test (async, blocking, sse, highlevel)Error: Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/mcp-mcp-1.9.4-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/mcp-mcp-1.9.4-sentry-latest/test-mcp-multiple-tool-calls-test-async-blocking-sse-highlevel.py python/mcp :: MCP Resource Read Test (async, blocking, sse, highlevel)Error: Test execution failed: Command failed: /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/mcp-mcp-1.9.4-sentry-latest/.venv/bin/python /home/runner/work/testing-ai-sdk-integrations/testing-ai-sdk-integrations/runs/python/mcp-mcp-1.9.4-sentry-latest/test-mcp-resource-read-test-async-blocking-sse-highlevel.py ✅ FixedThese tests were failing on main but are now passing:
Test MatrixAgent Tests
Embedding Tests
LLM Tests
MCP Tests
Legend: ✅ Pass | ❌ Fail | ✅🔧 Fixed | ❌📉 Regressed | ✅🆕 New (pass) | ❌🆕 New (fail) | 🗑️ Removed | str=streaming blk=blocking a=async s=sync io=stdio sse=sse hi=highlevel lo=lowlevel Generated by AI SDK Integration Tests |
Collaborator
|
We the same issue for JS langgraph. My suggestion would have been to align in the SDK. EDIT: we decided to do this anyways |
constantinius
approved these changes
Apr 9, 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.
Add
foundCall.argsas a fallback when extracting arguments from toolcall response data in
checkResponseToolCalls.Some frameworks (e.g. LangGraph Python) return tool calls with an
argskey rather than
arguments:{"name": "read_file", "args": {"path": "/nonexistent/file.txt"}, "id": "call_...", "type": "tool_call"}The lookup chain is now:
arguments→args→function.arguments.Fixes PY-2281