feat: add comprehensive agent system with memory, planning, and tool use

This commit introduces a full-featured agent architecture including persistent memory storage using vector embeddings, multi-step planning capabilities with dynamic replanning, and an extensible tool registry supporting custom function definitions. The agent now maintains conversation history with summarization, supports parallel tool execution, and includes a feedback loop for self-correction on failed actions.

.env.example

@@ -0,0 +1,28 @@
+# Copy to .env and adjust. Loaded by docker-compose (env_file) and by the app
+# at startup (python-dotenv). .env is git-ignored; this example is committed.
+
+# Session signing key. CHANGE THIS for any real deployment.
+SECRET_KEY=change-me
+
+# Database. Leave unset to use the shared project-root devplace.db (the Docker
+# app container bind-mounts ./ to /app, so it reads and writes the same file as
+# `make dev`). Set only to point at a different SQLite file.
+# DEVPLACE_DATABASE_URL=sqlite:////app/devplace.db
+
+# Public origin for absolute URLs (SEO, canonical links, push). Empty = derive
+# from the request.
+DEVPLACE_SITE_URL=
+
+# Host port the nginx front door binds.
+PORT=10500
+
+# nginx upload ceiling. Must be >= the admin-configurable max_upload_size_mb.
+NGINX_MAX_BODY_SIZE=50m
+
+# Optional nginx micro-cache for proxied GETs.
+NGINX_CACHE_ENABLED=false
+NGINX_CACHE_MAX_SIZE=1g
+
+# Run the app container as this host user so shared files keep dev ownership.
+DEVPLACE_UID=1000
+DEVPLACE_GID=1000