2ccfdb2db4
Salvage of #63862. is_output_cap_error() returns False for vLLM/LM Studio error messages that contain 'prompt contains ... input tokens' (treated as input-overflow signal). But parse_available_output_tokens_from_error() CAN extract a valid available_tokens from those same messages. The compression-disabled guard only checked is_output_cap_error(), so vLLM/LM Studio users with compression off still got a terminal failure instead of the max-tokens retry. Fix: also exempt when parse_available_output_tokens_from_error() returns a value — that function determines whether the retry path can actually handle the error, so it's the right predicate for the exemption. Added test: verify vLLM-format error with compression_disabled=False still triggers the max-tokens retry path. Co-authored-by: dmabry <dmabry@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| ci | ||
| lib | ||
| tests | ||
| whatsapp-bridge | ||
| LIVETEST_README.md | ||
| analyze_livetest.py | ||
| benchmark_browser_eval.py | ||
| build_model_catalog.py | ||
| build_skills_index.py | ||
| check-windows-footguns.py | ||
| check_subprocess_stdin.py | ||
| contributor_audit.py | ||
| dev-sandbox.sh | ||
| discord-voice-doctor.py | ||
| docker_config_migrate.py | ||
| docker_rebootstrap_nous_session.py | ||
| hermes-gateway | ||
| install.cmd | ||
| install.ps1 | ||
| install.sh | ||
| install_psutil_android.py | ||
| keystroke_diagnostic.py | ||
| kill_modal.sh | ||
| lint_diff.py | ||
| profile-tui.py | ||
| release.py | ||
| run_tests.sh | ||
| run_tests_parallel.py | ||
| sample_and_compress.py | ||
| tool_search_livetest.py | ||