fathom-code / tests /test_recursion_extract.py
23f2002275
fix(reward): align prompt with SFT, soft format, real recursion signal (A.3 + A.4-bis)
fa599d5
Raw
History Blame Contribute Delete
1.68 kB
"""Tests for rewards.recursion_extract — REW-04 v2."""
from rewards.recursion_extract import count_llm_calls
def test_empty_completion():
assert count_llm_calls("") == 0
def test_no_code_block():
assert count_llm_calls("The answer is <answer>silver</answer>") == 0
def test_single_call():
c = "```python\nresult = llm('find', ctx[:5000])\n```\n<answer>silver</answer>"
assert count_llm_calls(c) == 1
def test_two_calls_in_one_block():
c = "```python\na = llm('q1', ctx[:1000])\nb = llm('q2', ctx[1000:])\n```"
assert count_llm_calls(c) == 2
def test_calls_across_two_blocks():
c = "```python\nx=llm('q', ctx)\n```\nthen\n```python\ny=llm('q2', ctx)\n```"
assert count_llm_calls(c) == 2
def test_call_in_comment_not_counted():
c = "```python\n# would call llm(stuff) but skipping\nprint('done')\n```"
assert count_llm_calls(c) == 0
def test_call_in_string_literal_not_counted():
c = '```python\nnote = "earlier code did llm(...)"\nprint(note)\n```'
assert count_llm_calls(c) == 0
def test_call_outside_code_block_not_counted():
c = "Maybe I should call llm(question, chunk) but I won't actually."
assert count_llm_calls(c) == 0
def test_call_in_loop_counts_literal_occurrence():
c = "```python\nfor chunk in chunks:\n r = llm('find', chunk)\n```"
assert count_llm_calls(c) == 1
def test_invalid_python_falls_back_to_regex():
c = "```python\nthis is not valid python !!!\nresult = llm('q', ctx)\n```"
assert count_llm_calls(c) >= 1 # fallback regex finds it
def test_bare_python_fence():
c = "```\nans = llm('q', ctx)\n```" # no language tag
assert count_llm_calls(c) == 1