Fetching metadata from the HF Docker repository...
-
Harden: skip wildcard models, make LLM errors non-fatal per step
-
Fix model discovery: skip wildcard '*' model IDs from LiteLLM proxy
-
Fix MODEL_NAME=None: auto-discover from proxy /models endpoint, fallback to gpt-4o-mini
-
Critical Fix: Align internal port to 8000 to satisfy OpenEnv library requirements
-
Compliance Fix: Resolver setup timeout with lazy Gradio and extended 120s wait
-
Fix proxy test: exit with 1 on API failure so validator sees the error; fallback to HF_TOKEN if API_KEY is empty
-
Compliance Hardening: Remove silent fallbacks to force proxy usage
-
Final Polish: Task-aware fallbacks and surgical refinement
-
Compliance fix: strictly use API_KEY and API_BASE_URL to avoid proxy bypass
-
Fix structured output: ensure logging always runs and format matches validator
-
Fix inference.py: async OpenEnv pattern, from_docker_image, proper error handling
-
Final Expert Tier (0.9+) Candidate — Groq Baseline Verified
-
feat: add reward evolution chart to Gradio dashboard
-
final: comprehensive 0.9+ strategic agent upgrades and infrastructure refactor
-
hackathon: final submission candidate (removes binary image for HF compatibility)
-
fix: Synchronize inference port to 7860 for standardized local testing
-
Revert default LLM back to Llama-3.3-70B-Instruct for optimal general scoring
-
Configure NVIDIA-Nemotron-3-Super-120B as the default LLM engine
-
Fix imports for flat deployment structure in HF Spaces
-
Initial commit of PolicyEvolverEnv - Meta Hackathon
