fix(advanced): tell the model only one eval may be in flight

[radu-mocanu]

Summary

• the code interpreter's eval description now says only one call may run at a time, and points at Promise.all for parallelism inside a single call

Why

the REPL is one interpreter with shared state, so overlapping calls are rejected rather than queued. nothing told the model that: the description is rendered upstream and does not mention it, and per-tool parallelism is not expressible in a tool schema since parallel_tool_calls is request-level. a model that batches two eval calls in one turn loses one to ConcurrentEvalError and burns a turn recovering.

this is a local workaround. the note belongs in the upstream description and can be deleted once it lands there.

[Copilot]

🟢 Approval recommended

The scoped change includes regression coverage and no blocking issues were identified.

Pull request overview

Updates the advanced code interpreter guidance to prevent overlapping eval calls.

Changes:

• Documents the single in-flight eval limitation.
• Recommends Promise.all for in-call parallelism.
• Adds regression coverage and bumps the version to 0.18.1.

File summaries

File	Summary
uv.lock	Synchronizes the package version.
tests/agent/advanced/test_code_interpreter.py	Verifies the rendered guidance.
src/uipath_langchain/agent/advanced/code_interpreter.py	Adds the concurrency note to the tool description.
pyproject.toml	Updates the package version.

Review details

• Files reviewed: 3/4 changed files
• Comments generated: 0
• Review effort level: Lite

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
91.7% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud