adiuvAI/api
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

chore(tests): remove Langfuse scoring from preprocess tests

Browse Source 
Scoring is only meaningful for LLM-backed steps. Preprocess tests are
deterministic Python, so scores add no value. Kept only for detect tests.

- test_preprocess: drop _lf_score call, simplify _run_assertions return type
- cases.yaml: remove score_name from all op=preprocess entries

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Roberto Musso
2026-04-07 11:21:42 +02:00
parent bf445ac2ce
commit 3cc32569d9
2 changed files with 4 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/fixtures/preprocessors/cases.yaml vendored
View File

@@ -66,7 +66,6 @@ cases:
- id: "1.5" - id: "1.5"
description: "Email: strip HTML tags" description: "Email: strip HTML tags"
score_name: preprocess.email_strip
file: email_action.html file: email_action.html
op: preprocess op: preprocess
input_content_type: email_html input_content_type: email_html
@@ -77,7 +76,6 @@ cases:
- id: "1.6" - id: "1.6"
description: "Email: extract metadata (Subject + From)" description: "Email: extract metadata (Subject + From)"
score_name: preprocess.email_metadata
file: email_action.html file: email_action.html
op: preprocess op: preprocess
input_content_type: email_html input_content_type: email_html
@@ -86,7 +84,6 @@ cases:
- id: "1.7" - id: "1.7"
description: "Email: split thread — solo ultimo messaggio" description: "Email: split thread — solo ultimo messaggio"
score_name: preprocess.email_thread
file: email_thread.html file: email_thread.html
op: preprocess op: preprocess
input_content_type: email_html input_content_type: email_html
@@ -96,7 +93,6 @@ cases:
- id: "1.8" - id: "1.8"
description: "Email: singolo messaggio senza thread" description: "Email: singolo messaggio senza thread"
score_name: preprocess.email_single
file: email_single.html file: email_single.html
op: preprocess op: preprocess
input_content_type: email_html input_content_type: email_html
@@ -105,7 +101,6 @@ cases:
- id: "1.9" - id: "1.9"
description: "Email: HTML pesante con table layout" description: "Email: HTML pesante con table layout"
score_name: preprocess.email_heavy_html
file: email_heavy.html file: email_heavy.html
op: preprocess op: preprocess
input_content_type: email_html input_content_type: email_html
@@ -118,7 +113,6 @@ cases:
- id: "1.10" - id: "1.10"
description: "Fallback: file sconosciuto → testo restituito" description: "Fallback: file sconosciuto → testo restituito"
score_name: preprocess.fallback
file: fallback.txt file: fallback.txt
op: preprocess op: preprocess
input_content_type: unknown input_content_type: unknown

15
tests/test_preprocessors.py
View File

@@ -75,11 +75,8 @@ def _lf_score(score_name: str, value: float, comment: str = "") -> None:
# ── Assertion engine ────────────────────────────────────────────────── # ── Assertion engine ──────────────────────────────────────────────────
def _run_assertions(assertions: dict[str, Any], result: Any, raw: str) -> tuple[float, list[str]]: def _run_assertions(assertions: dict[str, Any], result: Any, raw: str) -> list[str]:
"""Run all assertions declared in the YAML case. """Run all assertions declared in the YAML case. Returns failure messages."""
Returns (score 0.0–1.0, list of failure messages).
"""
failures: list[str] = [] failures: list[str] = []
if assertions.get("no_html_tags"): if assertions.get("no_html_tags"):
@@ -124,8 +121,7 @@ def _run_assertions(assertions: dict[str, Any], result: Any, raw: str) -> tuple[
f"content_type mismatch: expected {expected_ct!r}, got {result.content_type!r}" f"content_type mismatch: expected {expected_ct!r}, got {result.content_type!r}"
) )
score = 1.0 if not failures else 0.0 return failures
return score, failures
# ── Parametrized: detect ────────────────────────────────────────────── # ── Parametrized: detect ──────────────────────────────────────────────
@@ -167,10 +163,7 @@ def test_preprocess(case: dict) -> None:
result = preprocess(case["input_content_type"], raw) result = preprocess(case["input_content_type"], raw)
assertions = case.get("assertions", {}) assertions = case.get("assertions", {})
score, failures = _run_assertions(assertions, result, raw) failures = _run_assertions(assertions, result, raw)
comment = "; ".join(failures) if failures else f"len={len(result.clean_text)}"
_lf_score(case["score_name"], score, comment)
assert not failures, ( assert not failures, (
f"[{case['id']}] {case['description']} — {len(failures)} assertion(s) failed:\n" f"[{case['id']}] {case['description']} — {len(failures)} assertion(s) failed:\n"