[prassu017]

Link to Issue or Description of Change

1. Link to an existing issue (if applicable):

• Closes: displays Ollama/Qwen3 thought text as part of the final answer #8102

Problem:
The human-readable printers in cli.py (_print_event for adk run, and run_input_file for adk run --replay) join the text of every part in an event. LiteLlm maps a reasoning model's thinking / reasoning_content to Part(text=..., thought=True), so the reasoning is printed glued to the answer: [assistant]: <thought text><final answer>.

Solution:
Skip parts with thought=True in both printers, so only the answer is shown. JSONL output (--jsonl) is unchanged and still carries the thought parts. Showing thoughts separately behind a flag, which the issue also mentions, is left out.

Testing Plan

Unit Tests:

• I have added or updated unit tests for my change.
• All unit tests pass locally.

New test_print_event_hides_thought_parts and test_run_input_file_hides_thought_parts. On main (9620b42) both fail, e.g. assert ['[agent]: thinking...Hi!'] == ['[agent]: Hi!']; with the fix:

pytest tests/unittests/cli/utils/test_cli.py
37 passed

The test file's fake Part classes gained a thought attribute, which the real types.Part always has. test_cli_tools_click.py has the same 27 failures with and without this change (optional deps such as sqlalchemy not installed in my environment). The full suite and tox were not run. pyink --check and isort --check-only pass on both files (Python 3.13).

Manual End-to-End (E2E) Tests:

Not run (no local Ollama). The unit tests feed the printers an event with a thought part and an answer part.

Checklist

• I have read the CONTRIBUTING.md document.
• I have performed a self-review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.
• I have manually tested my changes end-to-end.
• Any dependent changes have been merged and published in downstream modules.

Additional context

AI-assisted; tests run locally.