ShiftGuard
Stale does not mean unsafe. A deterministic simulator and a set of commit-time guards for tool-using LLM agents whose view of infrastructure state can go stale between read and commit.
Paper: Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races. Zihao Zheng, Jiayu Long, Baichuan Li, Junyi Yao. arXiv:2609.29522.
Why
When an agent restarts a job, promotes a snapshot, or changes an ACL, the state it read may have changed by the time it commits. Not every change makes the commit unsafe. ShiftGuard separates three kinds of race:
- invalidating: the change breaks a declared safety predicate, so the commit must be blocked.
- predicate-preserving: state changed, but the predicate still holds, so blocking is a false alarm.
- irrelevant: the change does not touch the action.
It then measures how precisely each runtime guard tells these apart. A coarse guard (for example a global epoch check) is safe but blocks a lot of benign work. A semantic commit predicate can be just as safe at a fraction of the cost.
What's in here
| Path | Contents |
|---|---|
src/shiftguard/simulator.py |
16 infrastructure tasks in 4 domains (scheduler, data pipeline, object store, access control), visible vs. authoritative state, 5 non-atomic fault injectors |
src/shiftguard/controllers.py |
Baselines and guards: always_execute, fast/strong verification, escalate, TTL / confidence / contract / agreement gates, evidence_router, global_epoch_guard, read_set_version_guard, commit_predicate_guard plus ablations |
src/shiftguard/prompts.py, ollama_client.py |
Proposal prompts and a dependency-free Ollama client for collecting new trajectories |
scripts/ |
Collection, counterfactual replay, analysis, learned router, cost sensitivity, figures |
tests/ |
17 deterministic simulator and guard tests |
examples/sample_trajectories.jsonl |
72 frozen proposals from the main study, enough to run the full pipeline offline |
Correctness is scored deterministically. No LLM judge is used anywhere.
Quick start
The core package and the replay pipeline use only the Python standard library (3.10+).
git clone https://github.com/Garyouki/shiftguard && cd shiftguard
python -m unittest discover -s tests -v
# Replay the bundled sample under every controller, then summarize
python scripts/replay_controllers.py examples/sample_trajectories.jsonl out/replayed.jsonl
python scripts/analyze_experiment.py out/replayed.jsonl --output-dir out/analysis
cat out/analysis/summary.md
Reproducing the paper
The frozen trajectories (3,456 main-study proposals from Qwen3-4B, Phi-4-mini and Gemma4-8B, plus the Llama-3.2-3B replication, five-seed extension, prompt-caution control, and end-to-end replanning run) are on the Hugging Face Hub:
pip install huggingface_hub
python scripts/download_data.py # ~155 MB into ./data
python scripts/replay_controllers.py data/trajectories_v1.jsonl out/main_replayed.jsonl
python scripts/analyze_experiment.py out/main_replayed.jsonl --output-dir out/main_analysis
The replay scores both baseline controllers and the guard family. Its output matches all 3,456 rows of trajectories_v2_guards_replayed.jsonl exactly.
Other drivers:
pip install -e ".[analysis]"
python scripts/evaluate_learned_router.py REPLAYED.jsonl --output-dir ROUTER
python scripts/cost_sensitivity.py REPLAYED.jsonl --output COSTS.csv
python scripts/plot_results.py REPLAYED.jsonl --analysis-dir ANALYSIS --output-dir figures
Collecting new trajectories
Collection needs a local Ollama server. The checkpoint digests used in the paper are recorded in model_lineage.json in the dataset.
python scripts/run_pilot.py --instances-per-template 4 --seeds 13 42 2026
python scripts/run_pilot.py --instances-per-template 4 --seeds 13 42 2026 --models llama3.2:3b
python scripts/run_pilot.py --instances-per-template 4 --seeds 13 42 2026 --prompt-variant aware
Scope
The simulator and the normalized check costs are a controlled research setting. They do not establish production deployment guarantees.
Citation
@misc{zheng2026staledoesnotmeanunsafe,
title={Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races},
author={Zihao Zheng and Jiayu Long and Baichuan Li and Junyi Yao},
year={2026},
eprint={2609.29522},
archivePrefix={arXiv},
primaryClass={cs.AI},
doi={10.48550/arXiv.2609.29522},
url={https://arxiv.org/abs/2609.29522}
}
License
Code: MIT (see LICENSE). The trajectory dataset has its own card and license on the Hugging Face Hub.
Metadata
Release files for shiftguard 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| shiftguard-0.1.0.tar.gz | 17.1 kB | With provenance | Details for shiftguard-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| shiftguard-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for shiftguard-0.1.0-py3-none-any.whl |
Total release size: 31.5 kB
Release files / shiftguard-0.1.0.tar.gz
| Download URL | shiftguard-0.1.0.tar.gz |
|---|---|
| Size | 17.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
71c57e61c9ac07707507227c0d51c80b7ab596bba88acf032816cebb9b7dc959
|
|
BLAKE2b-256 checksum How to use checksums |
52c64902d6b8064875b782fe01333833cc1737992bb1a696052f4053b7bd2381
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 21, 2026.
Transparency logRelease files / shiftguard-0.1.0-py3-none-any.whl
| Download URL | shiftguard-0.1.0-py3-none-any.whl |
|---|---|
| Size | 14.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
39d9c253b92299d529582e24c4b551a1668e6cefb4f5916e362b63913fb923a2
|
|
BLAKE2b-256 checksum How to use checksums |
09d4ef1630869abc83b084e2ec3b5288a215eeeacd96b1a4bf074b19b0ebf11c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 21, 2026.
Transparency logSecurity for shiftguard 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for shiftguard-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 21, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.