Add uv.lock for dependency locking

Fix multi-mode deployment issues

Added pyproject.toml

Updated inference.py

Updated config.py

Fix inference grade call when episode not done; update baseline scores from real run

Fix Dockerfile CMD to start uvicorn server instead of inference script

Fix turn counting, task-aware max steps in inference, explicit conversation reset, openenv.yaml metadata

Fix inference.py to comply with mandatory [START]/[STEP]/[END] stdout format and use API_BASE_URL/MODEL_NAME/HF_TOKEN env vars; add baseline scores to README

feat : renamed everything to breach OS

feat : dockerfile added for build

Updated server url

Merge pull request #8 from subhdotsol/feat/frontend

updated inference.py

added automatic attack button in UI and improved roleplay

Added.env example

added frontend for the project

Merge pull request #7 from subhdotsol/fix

Merge pull request #6 from pie-314/fix/grading-bugs-and-cli

Fix pipeline 0.0 scoring override, resolve test floating-point flakiness, and add readable CLI output for inference.py

Updated api base url

Merge pull request #4 from subhdotsol/fix

Updated readme

Merge pull request #3 from subhdotsol/fix

small fixes

Merge pull request #2 from pie-314/main

added graders and rewards

Updated readme

Merge pull request #1 from subhdotsol/feat/ai-integration

rewrite README with full setup guide and integration contracts

update env example to use Groq instead of HuggingFace

document all LLM prompts — what they do and why they're designed that way

add 59 tests for the LLM modules — all run offline, no API needed

wire up the main LLM pipeline — defender + classifiers in one place

add defense scorer — how well did the defender actually handle that?

add attack classifier — did the attacker actually win this turn?

add defender LLM — the AI that holds the line against attacks

add ConversationManager to give the defender a memory

add Groq client setup — one place to rule all API calls

chore: final cleanup — remove stray files, verify all imports resolve

refactor: replace datetime.utcnow() with timezone-aware datetime.now(UTC)

docs: add example usage code snippet for httpx client in README

docs: add task difficulty table and Docker usage section to README

docs: add API endpoint table to README

test(graders): add programmatic_grader tests — structure, score range, letter grade

test(graders): add hard_grader tests — breakthrough bonus and repetitive penalty

test(graders): add medium_grader tests — diversity scores higher than uniform strategies

test(graders): add easy_grader tests — empty, good, bad episode and range check

test(environment): add injection tests — custom reward_computer and llm_pipeline are called

test(environment): add framing sanitization tests for script and javascript injection