fix(crew): keep the call id when a parallel tool fails

[CaptainAni187]

When a tool fails in parallel mode, the error ToolResult is built with no id and no name:

results = await asyncio.gather(*tasks, return_exceptions=True)

for result in results:
    if isinstance(result, BaseException):
        final_results.append(
            ToolResult(tool_call_id="", name="", content=str(result), is_error=True)
        )

The call it belongs to is right there in tool_calls, and gather preserves input order, so the pairing is available and just not used.

That matters because these go straight back to the model as tool messages. A tool message has to name the call it answers, so an empty tool_call_id makes the request malformed rather than merely uninformative:

tool_call_id='call_aaa' name='fine'  is_error=False
tool_call_id=''         name=''      is_error=True

the LLM messages these become:
   {'role': 'tool', 'tool_call_id': 'call_aaa', 'name': 'fine', 'content': '"ok"'}
   {'role': 'tool', 'tool_call_id': '', 'name': '', 'content': ''}

Note the content is empty too. str() on an exception constructed without a message is "", so the model is handed a tool message with nothing in it at all.

How you reach that branch

Worth being precise, because it is narrower than it looks. _execute_single already catches every Exception and returns a proper ToolResult with tool_call_id=call.id, so ordinary tool failures never get here. Only a BaseException does, and in practice that means asyncio.CancelledError.

Which is the second half of this. Converting a CancelledError into a ToolResult means a cancelled turn does not stop: it carries on and reports a result for a call that never completed. For a voice agent, where an interruption cancelling in-flight work is routine rather than exceptional, that is the wrong end state.

The change

zip(tool_calls, results) so an error result carries the id and name of its own call, and fall back to the exception's type name when str() on it is empty.

CancelledError is re-raised rather than converted. Cancellation should propagate.

If you would rather not change the cancellation behaviour, the zip alone still fixes the malformed message and I am happy to drop the re-raise.

Tests

tests/custom/test_tool_registry_parallel_errors.py, six cases. Four fail on main: the id and name survive, the content is never blank, results stay aligned with their calls across a mixed success/failure batch, and cancellation propagates. The other two pin what must not change, an ordinary Exception still becoming a tool result with the right id, and the sequential path behaving as before.

src/smallestai/atoms/crew/** is .fernignored, so a regen keeps this.

[crim-app]

crim doesn't review pull requests automatically here.

Comment crim review on this pull request whenever you want a review.

[CaptainAni187]

crim review

[crim-app]

crim is reviewing this pull request. Findings will be posted shortly.

[crim-app]

LGTM

One-sentence assessment: A clean, well-tested bug fix that correctly preserves the tool call id/name on the parallel error path and re-raises cancellation instead of masking it.

What this PR does: In _execute_parallel, when asyncio.gather(return_exceptions=True) surfaces a BaseException (which _execute_single does not already convert to a ToolResult), the fallback previously built a ToolResult with tool_call_id="" and name="", producing a malformed tool message the LLM cannot match to its call. The fix zips each result back to its originating call to carry the real id/name, falls back to the exception type name when the message is empty, and re-raises asyncio.CancelledError so a cancelled turn does not proceed with a fabricated result. A new regression test covers all of these paths.

Findings: No issues found.

[crim-app]

Good to merge

A fix that gives orphaned error results their id back and stops pretending a cancelled turn finished cleanly, with tests for every branch it touches. The empty-string tool_call_id can finally rest in peace.

[abhishekmishragithub]

Superseded by #120 (re-homed onto an upstream branch so CI could run; your commit is included with authorship preserved, and the test type-check gaps for #112/#118 were fixed there). Shipping in 5.12.1.

[abhishekmishragithub]

@CaptainAni187 still thank you for raising this! 🙌🏼