Spaces:
Sleeping
Sleeping
Commit History
-
Fix blog post reward formula
Verified signature465032a -
Add Hugging Face blog post
Verified signature0358845 -
fix(docker): include llm_integration in image and wheel
thewildofficialMade-with: Cursoraba0bf3 -
chore: drop poster from git (Hub rejects non-Xet binaries); ignore local copy
thewildofficialMade-with: Cursor55a7432 -
fix(docker): two-phase uv sync; drop Dockerfile from wheel includes
thewildofficialHatch force-include for Dockerfile (and other paths) only exists after full COPY; use --no-install-project for the deps layer, then install the project after source is present. Remove Dockerfile from package metadata; it is not a wheel asset. Made-with: Cursor350c411 -
fix(docker): build without pre-existing uv.lock in context
thewildofficialMade-with: Cursor8faae12 -
fix(space): add SDK version and app_port to README for Hugging Face
thewildofficialMade-with: Cursorf796eab -
Fix Spaces config: app_file at root, add app.py wrapper
thewildofficialbbc4b4d -
Fix HF Space URL to correct deployment
thewildofficialab77723 -
Resolve merge conflict: keep our version
thewildofficialb30498f -
Merge: use origin/main README with updated HF Space links
thewildofficial47221d7 -
Add HF Space URL to README
thewildofficialf58b1c3 -
feat: unified full-stack architecture (React + FastAPI + Docker)
30596cf -
Merge feature/option-a-critical-auto-fund-8fmz: docs amendments 02 & 03
thewildofficial4bb4bff -
docs: Amendment 02 framing + Amendment 03 training doc
thewildofficial- Reframe README and specs as centralized planning (not multi-agent) - Document training pipeline alignment for Option A (see PR description) Made-with: Cursor05a5901 -
Merge pull request #18 from Kr0issant/feature/option-a-critical-auto-fund-8fmz
Abanfeat: Option A — auto-fund critical, discretionary proposals, remove CRITICAL_FAILURE70c0df4 -
feat(game): Option A auto-critical, discretionary proposals, remove CRITICAL_FAILURE
thewildofficial- Auto-fund critical in Phase 5; bankruptcy if treasury < sum(Critical) - Remove critical invariant termination and CRITICAL_FAILURE reward penalty - Parliament: drop ProposalAbstention adapter types - Server: remove ABSTAIN_FROM_PROPOSAL from action mapping - Direct allocation: return observation snapshot before next round reset - Sync specs 02,03,04,05,07,09,10 with Option A - Update tests and reward fixtures; add PR_DESCRIPTION_OPTION_A.md Made-with: Cursore4666d9 -
(train) pre-test train
Kr0issantf72fde9 -
Merge branch 'main' into train
Kr0issantaf4ea9c -
Add proposed amendment for training spec alignment
thewildofficialDocuments how the GRPO training pipeline (reward_fn, prompts, dataset generation, benchmarks) must change to work with each game-mechanic option from 01-critical-threshold-abstention-voting-fix.md. Includes detailed compatibility matrix, change order, and implementation estimates. Defers actual training work to post-amendment PRs.5b5a0b2 -
Add proposed amendments for critical threshold and README veracity
thewildofficial- 01-critical-threshold-abstention-voting-fix.md: Options A-F for resolving abstention/rejection/critical contradictions in game mechanics. Recommends Option A (auto-fund critical + discretionary proposals). - 02-readme-veracity-and-theme-alignment.md: Reframe project as centralized planning with parliamentary narrative wrapper. Aligns with hackathon themes #2 (long-horizon planning) and #3.1 (world modeling).dd79c42
-
(visualizer) some fixes maybe?
Kr0issant662788d -
Merge branch 'train' of github.com:Kr0issant/communism-optimizer-rl into train
Kr0issante4c9878 -
(visualizer) implement the whole thing
Kr0issantf2e28ca -
Fixed Small bugs causing large errors
e05d1f4 -
feat: Fix voting deadlocks with Targeted Voting and rebalance rewards
fdbb991 -
readme and benchmark.png updated
c9db071 -
changes in event handling and rewards
9cfcf69 -
Fix wastage ratio and add path robustness for remote training
697d449 -
training loop v1
Kr0issantdec56a6 -
Merge pull request #17 from Kr0issant/feature/llm-adapters
Modularize LLM integration and restructure parliamentary adapters8dbc364 -
Merge branch 'main' into feature/llm-adapters
a53ab00 -
Modularize LLM integration and restructure parliamentary adapters
006886d -
Merge pull request #13 from Kr0issant/cursor/98ae47e2
AbanAdd OpenEnv server slice4d3361f -
docs: remove dead links to missing specification/PROBLEM_STATEMENT/
thewildofficial07969f8 -
Merge origin/main; resolve test_game_loop (no force_advance in VOTING) and tests for linear reward, empty reset info
thewildofficialMade-with: Cursor15cc6aa -
Align tests and game with debate gating, log rewards, and OpenEnv reset info
thewildofficialMade-with: Cursor773fb23 -
Merge pull request #14 from Kr0issant/cursor/4fd59b38
AbanAdd baseline benchmark evidence pipelined1178ac -
Merge main and fix benchmark adapter review issues
thewildofficialResolve the main-branch merge conflicts, keep the benchmark plotter artifacts, and make rule-based baselines cast only valid non-duplicate votes so CI and benchmark evidence reflect legal policy behavior. Made-with: Cursor046ac0f -
Add OpenEnv server slice
thewildofficialWrap NationGame in a pinned OpenEnv/FastAPI server with Space-ready manifest, Docker entrypoint, typed models, and integration smoke coverage. Made-with: Cursorf0d0d63 -
Fix baseline adapter voting validity
thewildofficialBind random vote candidates by value and make rule-based baselines skip self-votes so benchmark invalid-action counts reflect genuine policy behavior. Made-with: Cursorba3f404 -
Merge pull request #16 from Kr0issant/spec-13-issue-fix
Spec 13 issue fix766fe5c -
fixes #11
Kr0issant5da6027 -
Merge branch 'main' of https://github.com/Kr0issant/communism-optimizer-rl
165929d -
add spec 13
Kr0issantce5b90a -
Environment Testing phase done done
0fc5daf -
Merge pull request #12 from Kr0issant/cursor/36b706fc
AbanAdd LLM policy adapters with telemetryf67eb52 -
ci: enable uv cache to cut CI time from ~14m to ~1m
thewildofficialThe setup-uv@v5 action does not cache by default. Without it, every CI run re-downloads all 483 locked packages across both Python versions in the matrix. enable-cache: true persists the uv cache between runs so sync becomes a no-op on cache hit.4db267f -
fix(server): repair OpenEnv contract tests and environment reset
thewildofficial- Fix server/environment.py reset() which had step() logic pasted in - Add NationAction back to server/models.py for legacy test compatibility - Update test_openenv_contract.py to use ParliamentaryAction/Observation - Remove assertions on info keys that don't exist in new API - Resolve merge conflicts with main branch Fixes CI failure: ImportError for NationAction/NationState from server.models3582e50 -
fix(server): repair OpenEnv contract tests and environment reset
thewildofficial- Fix server/environment.py reset() which had step() logic pasted in - Add NationAction back to server/models.py for legacy test compatibility - Update test_openenv_contract.py to use ParliamentaryAction/Observation - Remove assertions on info keys that don't exist in new API Fixes CI failure: ImportError for NationAction/NationState from server.models8244647