unsloth/tests/python/test_construct_chat_template_validation.py
Vineeth Sai d42256a5c5
Some checks are pending
Core / Core (HF=default + TRL=default) (push) Waiting to run
Core / Core (HF=4.57.6 + TRL<1) (push) Waiting to run
Core / Core (HF=latest + TRL=latest) (push) Waiting to run
Core / llama.cpp build + smoke (push) Waiting to run
Lint CI / Source lint (Python + shell + YAML + JSON + safety nets) (push) Waiting to run
MLX CI on Mac M1 / dispatch (push) Waiting to run
Security audit / advisory audit (pip + npm + cargo) (push) Waiting to run
Security audit / pip scan-packages :: extras (push) Waiting to run
Security audit / pip scan-packages :: studio (push) Waiting to run
Security audit / pip scan-packages :: hf-stack (push) Waiting to run
Security audit / npm scan-packages (Studio frontend tarballs) (push) Waiting to run
Security audit / workflow-trigger lint (pull_request_target / cache-poisoning) (push) Waiting to run
Security audit / pytest tests/security (push) Waiting to run
Security audit / npm provenance + new install-script diff (push) Waiting to run
Studio API CI / Studio API & Auth Tests (push) Waiting to run
Backend CI / (Python 3.10) (push) Waiting to run
Backend CI / (Python 3.11) (push) Waiting to run
Backend CI / (Python 3.12) (push) Waiting to run
Backend CI / (Python 3.13) (push) Waiting to run
Backend CI / Repo tests (CPU) (push) Waiting to run
Frontend CI / Frontend build + bundle sanity (push) Waiting to run
Studio GGUF CI / OpenAI, Anthropic API tests (push) Waiting to run
Studio GGUF CI / Tool calling Tests (push) Waiting to run
Studio GGUF CI / JSON, images (push) Waiting to run
Mac Studio API CI / Studio API & Auth Tests (push) Waiting to run
Mac Studio GGUF CI / OpenAI, Anthropic API tests (push) Waiting to run
Mac Studio GGUF CI / Tool calling Tests (push) Waiting to run
Mac Studio GGUF CI / JSON, images (push) Waiting to run
Mac Studio Install Matrix CI / Install + load (macos-14) (push) Waiting to run
Mac Studio Install Matrix CI / Install + load (macos-15) (push) Waiting to run
Mac Studio Install Matrix CI / Install + load (macos-26) (push) Waiting to run
Mac Studio Install Matrix CI / Install + load (macos-15-intel) (push) Waiting to run
Mac Studio Install Matrix CI / Install + load (macos-26-intel) (push) Waiting to run
Mac Studio UI CI / Chat UI Tests (push) Waiting to run
Mac Studio Update CI / Studio Updating Tests (push) Waiting to run
Studio Tauri CI / Tauri Linux debug build (no codesign) (push) Waiting to run
Studio UI CI / Chat UI Tests (push) Waiting to run
Studio Update CI / Studio Updating Tests (push) Waiting to run
Windows Studio API CI / Studio API & Auth Tests (push) Waiting to run
Windows Studio GGUF CI / OpenAI, Anthropic API tests (push) Waiting to run
Windows Studio GGUF CI / Tool calling Tests (push) Waiting to run
Windows Studio GGUF CI / JSON, images (push) Waiting to run
Windows Studio GGUF CI / Studio install + inference without Visual Studio (push) Waiting to run
Windows Studio GGUF CI / GPU prebuilt resolves without Visual Studio (push) Waiting to run
Windows Studio GGUF CI / setup.ps1 unit tests (VS 2026 / CMake guard) (push) Waiting to run
Windows Studio GGUF CI / real-VS detection (VS 2022) (push) Waiting to run
Windows Studio GGUF CI / real-VS detection (VS 2026) (push) Waiting to run
Windows Studio GGUF CI / VC++ runtime detect + install round-trip (windows-2025-vs2026) (push) Waiting to run
Windows Studio GGUF CI / VC++ runtime detect + install round-trip (windows-latest) (push) Waiting to run
Windows Studio UI CI / Chat UI Tests (push) Waiting to run
Windows Studio Update CI / Studio Updating Tests (push) Waiting to run
Wheel CI / Wheel build + content sanity + import smoke (push) Waiting to run
Fix construct_chat_template leaking {INPUT}/{OUTPUT} sentinel into the chat template (#6531)
* Fix construct_chat_template leaking {INPUT}/{OUTPUT} sentinel into the template

In construct_chat_template's inner process() helper, the branch handling a
section that starts with the {INPUT}/{OUTPUT} sentinel sliced the part from
part.find(which) (which is 0 in that branch), so the literal sentinel was
re-included in the generated Jinja chat template. The endswith branch already
slices correctly with part[:part.find(which)]; this slices past the sentinel
with part[len(which):], so a template whose input or output section begins
with the sentinel (for example a user turn that starts with {INPUT}) renders
correctly instead of emitting a literal {INPUT}/{OUTPUT}.

Added a regression test covering {INPUT}-leading and {OUTPUT}-leading sections.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-06-24 00:40:53 -07:00

106 lines
3.9 KiB
Python

"""Negative-path validation tests for unsloth.chat_templates.construct_chat_template.
Regression coverage for the no-match guards added in the PR #5763 follow-up:
missing placeholders or unrecoverable two-example structures must raise
RuntimeError with a clear message (not IndexError/AttributeError) and must
not silently drop the last char via s[:-1]. A minimal fake tokenizer keeps
the cases CPU-only (no HF_TOKEN, no gated download).
"""
from types import SimpleNamespace
import pytest
from unsloth.chat_templates import construct_chat_template
class _FakeTokenizer:
"""Minimal surface construct_chat_template touches before the guards fire."""
name_or_path = "fake/tokenizer"
eos_token = "</s>"
def get_vocab(self):
return {"</s>": 0}
@pytest.mark.parametrize(
"template, expected_in_message",
[
("only {INPUT} here, no output marker", "{OUTPUT}"),
("only {OUTPUT} here, no input marker", "{INPUT}"),
("neither sentinel here, just literal text", "{INPUT}"),
("neither sentinel here, just literal text", "{OUTPUT}"),
],
)
def test_missing_placeholder_in_chat_template_raises(template, expected_in_message):
with pytest.raises(RuntimeError) as exc_info:
construct_chat_template(
tokenizer = _FakeTokenizer(),
chat_template = template,
extra_eos_tokens = ["</s>"],
)
assert expected_in_message in str(exc_info.value)
def test_single_pair_template_raises_clear_error_not_attribute_error():
"""A single {INPUT}/{OUTPUT} pair must raise RuntimeError, not the old
AttributeError on `found.group(1)` when the loop broke without setting `found`."""
template = "user: {INPUT}\nassistant: {OUTPUT}\n"
with pytest.raises(RuntimeError):
construct_chat_template(
tokenizer = _FakeTokenizer(),
chat_template = template,
extra_eos_tokens = ["</s>"],
)
def test_error_message_excerpt_is_bounded():
"""Error messages must include a bounded excerpt of the offending
template, not dump arbitrarily large content into the traceback."""
huge = ("garbage " * 5000) + "{INPUT}" # ~40 KB, missing {OUTPUT}
with pytest.raises(RuntimeError) as exc_info:
construct_chat_template(
tokenizer = _FakeTokenizer(),
chat_template = huge,
extra_eos_tokens = ["</s>"],
)
msg = str(exc_info.value)
# Excerpt is capped well under the template length.
assert len(msg) < 1000
assert "{OUTPUT}" in msg
class _SuccessFakeTokenizer(_FakeTokenizer):
"""Adds the surface construct_chat_template touches on the success path."""
bos_token = "<s>"
bos_token_id = 1
added_tokens_decoder: dict = {}
def __call__(self, text):
# input_ids[0] must differ from bos_token_id so the BOS-handling branch is skipped.
return SimpleNamespace(input_ids = [5])
@pytest.mark.parametrize(
"chat_template",
[
# User turn begins with {INPUT} (no prefix before the sentinel).
"{INPUT} [/INST] {OUTPUT}</s>{INPUT} [/INST] {OUTPUT}</s>",
# Assistant turn begins with {OUTPUT} (no prefix before the sentinel).
"User: {INPUT}\n{OUTPUT}</s>User: {INPUT}\n{OUTPUT}</s>",
],
)
def test_chat_template_does_not_leak_sentinel_when_section_starts_with_it(chat_template):
"""When an input/output section begins with the {INPUT}/{OUTPUT} sentinel, the
generated Jinja template must not keep the literal sentinel text. The `startswith`
branch in the internal `process()` helper used to slice from `find()` (which is 0
here) instead of past the sentinel, re-including the literal `{INPUT}`/`{OUTPUT}`."""
_, jinja_template, _, _ = construct_chat_template(
tokenizer = _SuccessFakeTokenizer(),
chat_template = chat_template,
extra_eos_tokens = ["</s>"],
)
assert "{INPUT}" not in jinja_template
assert "{OUTPUT}" not in jinja_template