Root pyproject.toml uses uv features (extra in sources, conflicts)
that caused uv sync to fail in CI. Fix by:
1. Replace pip install uv==0.4.30 with astral-sh/setup-uv@v4 (latest)
2. Add --no-workspace flag so services don't inherit root config
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds GitHub Actions workflows for per-service CI (paths-filter gated),
dev image builds to ECR via OIDC, RC*-tag UAT promotion with image
re-tagging and Helm deploy, v*-tag blue/green prod release with smoke
test + ingress swap, and a nightly docker-compose integration suite.
Ships a Helm umbrella chart (dev/uat/prod values) with Deployments,
ClusterIP Services, ALB Ingress (samosachaat.art + grafana host), HPAs
for chat-api/inference in prod, PDBs, ConfigMap/Secret wiring, and an
alembic db-migrate Helm hook job.
Wires commitlint + husky for Conventional Commits at the repo root.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The KV cache was hardcoded to float32 on non-CUDA devices, but the model
weights are loaded in bfloat16 via NANOCHAT_DTYPE env var. This caused a
RuntimeError in scaled_dot_product_attention. Now uses COMPUTE_DTYPE from
common.py which respects the env var.
Also broadened CI/CD path triggers to nanochat/**.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Deploys to EC2 on push to master when UI/server files change.
Uses appleboy/ssh-action with stored secrets.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
