mirror of
https://github.com/usestrix/strix.git
synced 2026-08-16 09:26:39 +02:00
Cap the size of every tool result so a single verbose command (recursive find, noisy scanner, full page dump) can't pin the conversation near the model's context window for the rest of a scan. - New ContextSettings config group with env-tunable caps. - Default the SDK shell tools' max_output_tokens so exec_command / write_stdin truncate head+tail instead of returning unbounded output. - Bound Strix's own FunctionTool/CustomTool results (line + UTF-8 byte head+tail preview with a truncation notice) and cap error strings.
47 lines
1.4 KiB
Python
47 lines
1.4 KiB
Python
"""Tests for per-tool-output bounding."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from strix.tools.output_store import bound_text
|
|
|
|
|
|
def test_small_output_passes_through_unchanged() -> None:
|
|
text = "line 1\nline 2\nline 3"
|
|
assert bound_text(text, max_lines=100, max_bytes=10_000) == text
|
|
|
|
|
|
def test_line_limit_keeps_head_and_tail() -> None:
|
|
text = "\n".join(str(i) for i in range(1000))
|
|
bounded = bound_text(text, max_lines=10, max_bytes=1_000_000)
|
|
|
|
assert bounded.startswith("0\n1\n2\n3\n4")
|
|
assert bounded.rstrip().endswith("999")
|
|
assert "truncated" in bounded
|
|
# Head + tail only, far fewer than the original 1000 lines.
|
|
assert len(bounded.splitlines()) < 30
|
|
|
|
|
|
def test_byte_limit_enforced_on_single_long_line() -> None:
|
|
text = "x" * 100_000
|
|
bounded = bound_text(text, max_lines=2_000, max_bytes=1_000)
|
|
|
|
assert "truncated" in bounded
|
|
assert len(bounded.encode("utf-8")) < 3_000
|
|
|
|
|
|
def test_multibyte_characters_not_split() -> None:
|
|
text = "😀" * 50_000
|
|
bounded = bound_text(text, max_lines=2_000, max_bytes=1_000)
|
|
|
|
# Must remain valid UTF-8 (no broken surrogate halves from a mid-char cut).
|
|
assert bounded == bounded.encode("utf-8").decode("utf-8")
|
|
assert "truncated" in bounded
|
|
|
|
|
|
def test_notice_reports_dropped_counts() -> None:
|
|
text = "\n".join("y" * 10 for _ in range(500))
|
|
bounded = bound_text(text, max_lines=10, max_bytes=1_000_000)
|
|
|
|
assert "lines" in bounded
|
|
assert "bytes" in bounded
|