mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-11-22 13:29:19 +08:00
fix: prevent HF tokenizer downloads in offline mode (#3783)
## Description `HEADROOM_OFFLINE=1` must not fall through from a cold HuggingFace tokenizer cache to a network download. This change applies the existing offline environment defaults before importing Transformers and returns to estimation after a cache miss when offline mode is active. Closes #3777 ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) - [ ] New feature (non-breaking change that adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - Apply `apply_offline_env()` before the Transformers import when `HEADROOM_OFFLINE` is enabled. - Skip the network fallback and use estimation after an offline cache miss. - Add regression coverage for cold-cache no-egress behavior, explicit offline-flag overrides, and warm-cache loading. ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check .`) - [x] Type checking passes (`mypy headroom`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text 22 passed in 1.09s 2 files already formatted All checks passed! Success: no issues found in 1 source file ``` ## Real Behavior Proof - Environment: Linux x86_64, Python 3.13.15, `uv` 0.12.15, Transformers 5.x, empty temporary `HF_HOME`, and a loopback HTTP server used as `HF_ENDPOINT`; no provider or HuggingFace credentials. - Exact command / steps: ran `env -u HF_HUB_OFFLINE -u TRANSFORMERS_OFFLINE PYTHONPATH=. uv run --no-project --with 'transformers>=5.5,<6' --with opentelemetry-api --with pydantic --with tiktoken --with click --with rich --with pyyaml --with tomlkit python -` with a script that started the loopback server, set `HF_HOME` to an empty temporary directory, set `HEADROOM_OFFLINE=1`, called `_load_tokenizer("Qwen/Qwen2.5-7B")`, and recorded requests and cache entries. - Observed result: `_load_tokenizer` returned `None` (estimation fallback), the loopback HuggingFace endpoint received no requests, the empty `HF_HOME` stayed empty, and both `HF_HUB_OFFLINE` and `TRANSFORMERS_OFFLINE` were set to `1`: ```text {"cache_entries": [], "hf_hub_offline": "1", "loader_http_requests": [], "result": null, "transformers_offline": "1"} ``` - Not tested: a real external `huggingface.co` endpoint, a full proxy request, or a real warm tokenizer cache; those paths are covered by the existing loader tests and the local proof isolates the changed behavior. ## Runtime Rollout Safety - Rollout-managed feature(s): HuggingFace tokenizer network fallback. - Minimum rollout channel: next patch release. - Stable/default behavior changed: only when `HEADROOM_OFFLINE` is enabled; online behavior remains unchanged. - Kill switch / disable path: unset `HEADROOM_OFFLINE` and restart the process; existing explicit `HF_HUB_OFFLINE` and `TRANSFORMERS_OFFLINE` overrides remain respected by `apply_offline_env()`. - Unsafe override required: none. - Qualification impact: no provider, model, or API qualification changes. - Rollback path: revert this PR. ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Checklist - [x] My code follows the project's style guidelines - [x] I have performed a self-review of my code - [x] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective - [x] New and existing unit tests pass locally with my changes - [x] I did **not** edit `CHANGELOG.md` — it is generated by release-please from my Conventional Commit PR title ## Screenshots (if applicable) Not applicable. ## Additional Notes No dependencies or generated files were added. The implementation reuses the existing offline-mode contract rather than introducing a second configuration switch. <!-- devin-review-badge-begin --> --- <a href="https://app.devin.ai/review/headroomlabs-ai/headroom/pull/3783" target="_blank"><picture><source media="(prefers-color-scheme: dark)" srcset="https://static.devin.ai/assets/gh-devin-review-dark.svg?v=4"><img src="https://static.devin.ai/assets/gh-devin-review-light.svg?v=4" alt="Devin Review"></picture></a> <!-- devin-review-badge-end --> --------- Co-authored-by: JD Davis <mxjerrett@gmail.com>
This commit is contained in:
@@ -226,6 +226,12 @@ def _load_tokenizer(tokenizer_name: str):
|
||||
# vetted, not a variant the caller chose.
|
||||
tokenizer_name = repo
|
||||
|
||||
from headroom.offline import apply_offline_env, is_offline
|
||||
|
||||
offline = is_offline()
|
||||
if offline:
|
||||
apply_offline_env()
|
||||
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
try:
|
||||
@@ -242,6 +248,13 @@ def _load_tokenizer(tokenizer_name: str):
|
||||
except Exception:
|
||||
pass # Not in the local cache — try the network below, bounded.
|
||||
|
||||
if offline:
|
||||
logger.warning(
|
||||
f"Tokenizer {tokenizer_name} not in local HF cache and network "
|
||||
f"loading is disabled (HEADROOM_OFFLINE); using estimation"
|
||||
)
|
||||
return None
|
||||
|
||||
timeout = _load_timeout_secs()
|
||||
if timeout <= 0:
|
||||
logger.warning(
|
||||
|
||||
@@ -29,7 +29,10 @@ from headroom.tokenizers.huggingface import (
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _fresh_cache():
|
||||
def _fresh_cache(monkeypatch: pytest.MonkeyPatch):
|
||||
monkeypatch.delenv("HEADROOM_OFFLINE", raising=False)
|
||||
monkeypatch.delenv("HF_HUB_OFFLINE", raising=False)
|
||||
monkeypatch.delenv("TRANSFORMERS_OFFLINE", raising=False)
|
||||
_load_tokenizer.cache_clear()
|
||||
yield
|
||||
_load_tokenizer.cache_clear()
|
||||
@@ -106,6 +109,41 @@ def test_timeout_zero_disables_network_loading(monkeypatch: pytest.MonkeyPatch)
|
||||
assert _load_tokenizer("google/gemma-7b") is None
|
||||
|
||||
|
||||
def test_offline_mode_prevents_network_loading(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
calls: list[dict[str, Any]] = []
|
||||
|
||||
def fake_from_pretrained(name: str, **kwargs: Any):
|
||||
calls.append(kwargs)
|
||||
if kwargs.get("local_files_only"):
|
||||
raise OSError("not in cache")
|
||||
raise AssertionError("network load attempted in offline mode")
|
||||
|
||||
_install_fake_transformers(monkeypatch, fake_from_pretrained)
|
||||
monkeypatch.setenv("HEADROOM_OFFLINE", "1")
|
||||
monkeypatch.setenv("HF_HUB_OFFLINE", "0")
|
||||
monkeypatch.setenv("TRANSFORMERS_OFFLINE", "0")
|
||||
monkeypatch.setenv("HEADROOM_HF_TOKENIZER_LOAD_TIMEOUT_SECS", "5")
|
||||
|
||||
assert _load_tokenizer("Qwen/Qwen2.5-7B") is None
|
||||
assert len(calls) == 1
|
||||
assert calls[0].get("local_files_only") is True
|
||||
|
||||
|
||||
def test_offline_mode_allows_cached_tokenizer(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
calls: list[dict[str, Any]] = []
|
||||
|
||||
def fake_from_pretrained(name: str, **kwargs: Any):
|
||||
calls.append(kwargs)
|
||||
return "cached-tokenizer"
|
||||
|
||||
_install_fake_transformers(monkeypatch, fake_from_pretrained)
|
||||
monkeypatch.setenv("HEADROOM_OFFLINE", "1")
|
||||
|
||||
assert _load_tokenizer("Qwen/Qwen2.5-7B") == "cached-tokenizer"
|
||||
assert len(calls) == 1
|
||||
assert calls[0].get("local_files_only") is True
|
||||
|
||||
|
||||
def test_count_messages_fails_open_to_estimation(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
def fake_from_pretrained(name: str, **kwargs: Any):
|
||||
raise OSError("unavailable")
|
||||
|
||||
Reference in New Issue
Block a user