Fix campaign IDs: load dynamically from env instead of hardcoded values

Update README path to server/app.py structure and dependencies

Upgrade Gradio UI theme and styling aesthetics

Fix campaign detection reset logic in UI

Add permissive trailing slashes for API endpoints

Fix Dockerfile CMD to use server.app

Merge branch 'main' of https://github.com/oki-dokii/Meta into bruh

Fix validate-submission issues: pyproject.toml setup, server entrypoint, app path, and uv.lock

Merge branch 'bruh'

fix: Appended the required score=<score> to [END] stdout logs for OpenEnv compatibility

Merge branch 'bruh'

chore: Strict compliance with OpenAI client AST init

Merge branch 'bruh'

chore: strict compliance with OpenEnv inference env variables ast-validation

docs: Add architecture and core loop Mermaid diagrams

docs: Add architecture and core loop Mermaid diagrams

Update README.md

docs: Fix penalties header to remove negative reward reference

docs: Update reward constraints copy to 0.0-1.0 in UI and README

Fix page unresponsiveness by removing demo.load() events

Fix event handlers by moving functions to module level

Simplify theme/CSS for Gradio 6.0 and improve performance

Fix Gradio theme/css initialization to make buttons work

Fix Gradio 6.0 deprecation warnings and campaign loading

Add comprehensive multi-provider documentation and tests

Add multi-provider support: Groq (default), OpenAI, Grok

Add Groq API support alongside OpenAI and Grok

Fix README color for HF

Deploy to HF Spaces

Finalise OpenEnv submission: Clamp rewards to 0.0-1.0, update Gradio UI, and add Groq pipelines

app.py: Fix Gradio 6 deprecations and unused imports

inference.py: Groq default + dynamic scenario loading + campaign/adversarial prompt hints

README: add judge tip for deterministic reset(campaign_id=...) under campaign section

Restore moderation_benchmark.json from d741d4b (128 scenarios, 100/100 checks)

Merge + 3 fixes: README accurate (128 scen / real baselines), is_adversarial in state, reset(campaign_id) (100/100 checks)

3 fixes: README accurate, is_adversarial in state, reset(campaign_id) (100/100)

2b 3a

Appeal mechanic: is_adversarial + env.appeal() 2-turn flow (92/92 checks)

Fill easy GT gaps: full label×action coverage (79/79 checks)

Graduated severity penalty: sev-5→-0.30, sev-4→-0.15, sev-3→-0.05 (66/66)

Cross-post campaign mechanic: campaign_id in state, +0.15 escalate-all bonus (61/61 checks)

10 ambiguous hard scenarios + full valid_actions test suite (53/53 checks)

Close all 4 scoring gaps (+~6 pts)

v2 docs & validation: README rewrite, openenv.yaml v2.0, validator 47/47

Update inference.py: expand TASKS to all 75 scenarios (25 easy / 20 medium / 30 hard)

phase 1 and phase 2a

ContentModerationEnv v1.0 — complete OpenEnv benchmark