Fix handling of text_message_outputs output structure in parallel translation example #1115
Conversation
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
…nslation example
**Problem**:
The code assumed `ItemHelpers.text_message_outputs()` returned a single string per result (e.g., `"Hola mundo"`), but it actually returns a **list of strings** (e.g., `["Hola", "Mundo"]`). This caused a `TypeError` when joining outputs.
**Example of Failure**:
```python
outputs = [
["Hola", "Mundo"], # From text_message_outputs
["Buenos días"],
["Cómo estás"],
]
translations = "\n\n".join(outputs) # ❌ TypeError: can't join list to str
```
**Changes**:
- Wrap `text_message_outputs(...)` with `" ".join(...)` to safely flatten each agent’s output into a single string:
```python
outputs = [
" ".join(ItemHelpers.text_message_outputs(res_1.new_items)),
" ".join(ItemHelpers.text_message_outputs(res_2.new_items)),
" ".join(ItemHelpers.text_message_outputs(res_3.new_items)),
]
```
**Benefits**:
- Prevents `TypeError` by ensuring all outputs are strings.
- Maintains consistent formatting for the final joined output.
- Makes the example robust and easier to understand for users.
This change ensures the parallel translation workflow works reliably, even when agent outputs vary in structure.
seratch
added
documentation
|
Thanks for reporting this. I don't think this is the fundamental solution as the helper method is supposed to return a single string: https://github.com/openai/openai-agents-python/blob/v0.1.0/src/agents/items.py#L277-L284 could you help us identify the cause of the unexpected behavior? |
|
This PR is stale because it has been open for 10 days with no activity. |
|
This PR was closed because it has been inactive for 7 days since being marked as stale. |
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.
Problem:
The code assumed
ItemHelpers.text_message_outputs()returned a single string per result (e.g.,"Hola mundo"), but it actually returns a list of strings (e.g.,["Hola", "Mundo"]). This caused aTypeErrorwhen joining outputs.Example of Failure:
Changes:
text_message_outputs(...)with" ".join(...)to safely flatten each agent’s output into a single string:Benefits:
TypeErrorby ensuring all outputs are strings.This change ensures the parallel translation workflow works reliably, even when agent outputs vary in structure.