Fetching metadata from the HF Docker repository...
-
Fix skeptic LLM: add User-Agent header to bypass Cloudflare WAF (was getting 403 error code 1010)
-
Fix demo_pagerduty: default to Groq Llama (was OpenAI gpt-4o-mini), show cross-platform shell hints
-
Quick Reproduction: add Windows PowerShell + cmd.exe variants alongside bash
-
Clean up: add .gitignore, remove __pycache__ tracking, remove test artifacts
-
Updated pagerduty_importer.py
-
Add live Slack bot demo + YouTube video + BLOG section on production deployment
-
Add live Slack bot demo + YouTube video + BLOG section on production deployment
-
Add LICENSE, Datadog + Splunk importers, Quick Reproduction section in README
-
Final polish: fix WORKERS default in README
-
Final polish: consistent baseline numbers (0.857), update BLOG title (drop 3AM), add V1+V2 loss curves to BLOG, fix README baseline chart
-
Update baseline numbers: medium=0.970 (was 0.985), avg=0.857 (was 0.861) - reflects latest live HF run
-
README: fix tools/samples 404 in submission table, standardize all artifact URLs to GitHub, Blog
-
Fix README URLs (tools/samples folders, env/models.py path, Colab links) + remove credits mention from BLOG
-
Rewrite BLOG
-
Add comprehensive URL/links section - all judge-accessible URLs
-
Update README + BLOG: two-stage training, multi-agent, PagerDuty integration
-
Pitch deck v3 - multi-agent + PagerDuty slides + two-stage training
-
V2 training results - multi-agent coverage (+1.9%)
-
Phase 3: PagerDuty integration - importer, demo, sample incidents with real-world format
-
Phase 1b: Multi-agent inference script - primary + skeptic + revise flow
-
Phase 1: Multi-agent extension - REQUEST_REVIEW + REVISE_SECTION + skeptic agent
-
Resolve merge conflict: keep updated README with embedded charts
-
Add pitch deck (LFS) and embed charts in README
-
Update README for Round 2 — Theme #3.1 positioning + training results
Jeevan2798
Expanded the README to include details about the Grand Finale submission and training results. -
Update README for Round 2 — Theme #3.1 positioning + training results
-
Add Round 2 blog post with training results
Jeevan2798
-
Add Round 2 training artifacts: reward charts and results JSON
Jeevan2798
-
Add Round 2 blog post with training results
-
Add Round 2 training artifacts: reward charts and results JSON
-
Update baseline scores to match live Space output
-
FINAL: stdout format + README updated + expert scenario + all fixes
-
Add expert scenario - security breach, 4-level difficulty, updated README and openenv.yaml
-
Fix: upgrade openai>=2.7.2 compatible with openenv-core
-
Fix pre-submission validator - pyproject, uv.lock, main(), openenv-core
-
Add pyproject.toml and demo.py — fix pre-submission validation
-
README: add Why This Is Challenging section + determinism note
-
Fix: WORKERS=1 to prevent shared state across workers
-
README - add Key Innovations, determinism note, baseline explanation
-
Fix README - add HuggingFace metadata header
-
final - README + grader fixes + service_match bug fix
-
Remove venv from tracking, add gitignore
-
Initial deployment — Incident Post-Mortem Writer OpenEnv
-
initial commit
