Updated inference.py

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

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

Updated server url

updated inference.py

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

Updated api base url

feat(inference): add main() — runs all 3 task difficulties with 20-minute guard

feat(inference): implement run_episode() — full reset→step loop with httpx client

feat(inference): add strategy escalation logic — harder strategies as turns increase

feat(inference): add generate_attack() — uses OpenAI client to craft next framing

feat(inference): scaffold inference.py with OpenAI client config and env vars