code

feat(grader): add task-aware grading with new metrics and composite scoring

fix(inference): refine scaling and rerouting rules and action behavior

reward finalisation

fix(inference): add debugging and error handling for env.step action calls

perf(environment): improve cost model with three-tier capacity pricing

refactor(simulator): add feedback on action effects and enforce capacity discipline

better task 3

Task 3 fixes

fixes

feat(client): add new node and reward related metrics to observations

Merge branch 'integrate/k8s-tennodes' of https://github.com/PranavKK1201/Anti-Atropos into integrate/k8s-tennodes

reward tuning

graph modelling

model changes

fix: PromQL queries use by (node_id) so VM telemetry resolves correctly

fixed envs

fixed

str

fix: Grafana 404 — Prometheus datasource missing route-prefix

CLRF

feat: HF Spaces live mode with VM IP baked in

feat(monitoring): add local Prometheus and Grafana setup for AntiAtropos

consolidate

Enhance Kubernetes executor and deployment configurations

fix reqs

droplet

chore(kubernetes): support unbounded max replicas and enhance local setup

deploy

feat: implement Kubernetes executor for automated cluster scaling and infrastructure management

chore: remove generated artifacts and ignore local caches

merge ten_nodes into kubernetes

feat(deploy): add comprehensive AWS EKS infrastructure deployment script and improve bash deploy script

run this to see if the loss and rewards are beheving okay

increased ramp-up to be proportional to 10 nodes

upgraded to 10 nodes

agent.md and claude.md

script for sanity check of all 3 tasks and training environment

feat(curriculum): add progressive training curriculum management

docs(deploy): add detailed architecture guide and update k8s workloads

feat(aws): add complete AWS infrastructure deployment with sample workloads and autoscaling

feat(deploy): add AWS deployment scripts and configurations for AntiAtropos

model name fix

fixed env vars

updated inference.py

inference

update readme.md

updated grader

fixed openenv

docs: reframe README around AIOps and autonomous DevOps