2db8b81854
Two robustness fixes for the `_HAS_ANSWER_ARTIFACT` regex from the parent commit, both caught by a thorough simulation suite covering Linux/Mac/Windows line-ending portability and adversarial inputs. 1. **CRLF line endings.** The original `\n` literals missed Windows- authored or CRLF-converted content (model echoing a pasted prompt, etc.). Replaced with `\r?\n` everywhere a newline is required, so closed code fences, numbered lists, and end-to-end re-prompt decisions all work on `\r\n` as well as `\n`. 2. **Catastrophic backtracking on whitespace spam.** The numbered-list alternative `(?:^|\r?\n)\s*\d+\.\s+\S.*?\r?\n\s*\d+\.` was O(n^2) on long whitespace runs: `\s*` greedy + `\d+` failing + `\s` matching `\r\n` led to repeated backtracking through the newline characters. Measured at ~630ms for 10KB of `\r\n` repeats. Fix: restrict the post-newline indent to `[ \t]*` (spaces / tabs only). After `\r?\n` we are at column 0 and only spaces / tabs are a sensible leading indent for a list item; greedy whitespace was never needed. New worst case on the same input: <1ms (1000x speedup). Added 5 in-tree tests: - test_artifact_regex_handles_crlf_code_fence - test_artifact_regex_handles_crlf_numbered_list - test_artifact_regex_handles_mixed_lf_crlf - test_no_backtrack_on_crlf_spam (asserts <50ms on 10KB \r\n) - test_no_reprompt_on_crlf_complete_python_game All 18 reprompt-guard tests pass. All 253 llama_cpp-related tests pass. Out-of-tree simulation suite (84 tests) passes on both Python 3.12 and Python 3.13 inside isolated uv venvs. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| _html_to_md.py | ||
| anthropic_compat.py | ||
| audio_codecs.py | ||
| chat_template_helpers.py | ||
| defaults.py | ||
| external_provider.py | ||
| inference.py | ||
| key_exchange.py | ||
| llama_cpp.py | ||
| llama_server_args.py | ||
| mlx_inference.py | ||
| orchestrator.py | ||
| pricing.py | ||
| providers.py | ||
| safetensors_agentic.py | ||
| tool_call_parser.py | ||
| tools.py | ||
| worker.py | ||