|
.pi
|
docs(dev): add lean agent guidance and prototype hardening research
|
2026-09-22 15:16:33 +07:00 |
|
capture
|
Add reference game-state captures
|
2026-09-22 00:02:24 +07:00 |
|
dataset
|
feat(dataset): migrate game history and captures into a trainable corpus
|
2026-09-22 06:09:16 +07:00 |
|
docs
|
docs(policy): document composite scoring boundaries and limitations
|
2026-09-23 14:56:41 +07:00 |
|
policy
|
feat(policy): add opt-in composite reward scoring with audit tests
|
2026-09-23 14:56:41 +07:00 |
|
ui/JevOverlay
|
docs(ui): document overlay setup and verification
|
2026-09-23 13:40:02 +07:00 |
|
utils
|
fix(policy): reconcile session-owned action memory with game observations
|
2026-09-22 15:18:00 +07:00 |
|
vendor
|
Vendor STS2MCP mod source and 0.4.0 release DLL
|
2026-09-22 00:01:30 +07:00 |
|
.gitignore
|
feat(recording): link session observations proposals and action results
|
2026-09-22 15:53:14 +07:00 |
|
ab_card_skip.sh
|
fix(eval): end each A/B session with its run, and attribute runs to arms
|
2026-09-22 06:09:16 +07:00 |
|
AGENTS.md
|
feat(recording): link session observations proposals and action results
|
2026-09-22 15:53:14 +07:00 |
|
brain.py
|
refactor(policy): extract combat selection and context modules
|
2026-09-22 15:18:00 +07:00 |
|
capture.py
|
Add STS2MCP HTTP client and state capture tool
|
2026-09-22 00:01:44 +07:00 |
|
CONTEXT.md
|
feat(recording): link session observations proposals and action results
|
2026-09-22 15:53:14 +07:00 |
|
eval_batch.sh
|
Add batch eval and card-skip A/B scripts
|
2026-09-22 00:02:18 +07:00 |
|
facts.py
|
feat(state): scope card evidence and policy memory by reported run identity
|
2026-09-22 15:18:00 +07:00 |
|
jev.py
|
fix(bot): correct combat estimates and enforce client and runner failures
|
2026-09-22 15:18:00 +07:00 |
|
migrate.py
|
feat(dataset): migrate game history and captures into a trainable corpus
|
2026-09-22 06:09:16 +07:00 |
|
recording.py
|
feat(recording): link session observations proposals and action results
|
2026-09-22 15:53:14 +07:00 |
|
run.py
|
feat(policy): add opt-in composite reward scoring with audit tests
|
2026-09-23 14:56:41 +07:00 |
|
run_state.py
|
feat(state): scope card evidence and policy memory by reported run identity
|
2026-09-22 15:18:00 +07:00 |
|
sts2.py
|
fix(bot): correct combat estimates and enforce client and runner failures
|
2026-09-22 15:18:00 +07:00 |
|
test_brain.py
|
feat(policy): add opt-in composite reward scoring with audit tests
|
2026-09-23 14:56:41 +07:00 |
|
test_facts.py
|
fix(bot): correct combat estimates and enforce client and runner failures
|
2026-09-22 15:18:00 +07:00 |
|
test_run.py
|
fix(policy): unblock upgrade confirmation after card selection
|
2026-09-23 13:40:02 +07:00 |
