mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-23 00:41:40 +00:00
d982aebe68
Bugbot flagged that `run_claude` placed the prompt as cmd[7] and then appended extra_args after it. `claude --print` takes the prompt as the final positional argument; flags appearing after it (e.g. `--allowed-tools Bash`, `--image <path>`) are swallowed by the prompt parser, which silently breaks the tool_use and vision cells. Build the flag list first, then append the prompt last. Add a unit test that pins the ordering. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| _builder_unit_tests | ||
| _driver_unit_tests | ||
| _pr_gate_unit_tests | ||
| basic_messaging_non_streaming | ||
| basic_messaging_streaming | ||
| cron_vm | ||
| extended_thinking | ||
| prompt_caching_5m | ||
| tool_use | ||
| vision | ||
| __init__.py | ||
| cli_driver.py | ||
| conftest.py | ||
| manifest.yaml | ||
| matrix_builder.py | ||
| pr_gate_version_resolver.py | ||
| sample_compatibility-matrix.json | ||
| test_config.yaml | ||