updated build

Added comprehensive improvements to ClawdBox for better LLM agent experience:

- Tools: Added tree, tmux, htop, strace, file, less for enhanced debugging
- Python packages: httpie, pyyaml, requests, black, ipython pre-installed
- Persistent caching: pip/npm caches now survive container restarts
- Git config persistence: .gitconfig auto-links from /data volume
- Shell improvements: colored prompt, aliases (ll, k, dc), 10k line history
- Helper scripts: ConfigMap with disk-usage, health-check, clean-workspace, install-tools
- Environment variables: TERM, TZ, DEBIAN_FRONTEND for better compatibility
- Makefile: Common operations (build, deploy, logs, shell, health-check)
- Documentation: Comprehensive README with troubleshooting and workflows

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

Dockerfile

@@ -29,6 +29,12 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     ripgrep \
     ncdu \
     sudo \
+    tree \
+    tmux \
+    htop \
+    strace \
+    file \
+    less \
     && curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
     && apt-get install -y nodejs \
     && rm -rf /var/lib/apt/lists/*
@@ -44,6 +50,14 @@ RUN OC_VERSION="stable" && \
     tar -xvf /tmp/oc.tar.gz -C /usr/bin/ oc && \
     rm /tmp/oc.tar.gz && chmod +x /usr/bin/oc
 
+# Install Python tools for LLM work
+RUN pip3 install --no-cache-dir --break-system-packages \
+    httpie \
+    pyyaml \
+    requests \
+    black \
+    ipython
+
 # Setup SSH directory & Config for OpenShift (Random UID support)
 RUN mkdir -p /var/run/sshd && \
     chmod 775 /var/run/sshd
@@ -73,9 +87,9 @@ RUN useradd -m -s /bin/bash -u 1000 claw && \
 # Prepare volume mount point
 # Mount persistent storage here
 VOLUME /data
-RUN mkdir -p /data && \
-    chown claw:claw /data && \
-    chmod 775 /data
+RUN mkdir -p /data /data/.cache/pip /data/.cache/npm /data/.local && \
+    chown -R claw:claw /data && \
+    chmod -R 775 /data
 
 # Set working directory to the persistent volume
 WORKDIR /data
@@ -86,6 +100,20 @@ EXPOSE 2222
 # Switch to user 'claw' (UID 1000)
 USER claw
 
+# Link package managers to persistent storage
+ENV PIP_CACHE_DIR=/data/.cache/pip
+ENV npm_config_cache=/data/.cache/npm
+ENV XDG_CACHE_HOME=/data/.cache
+
+# Add better default shell experience
+RUN echo 'export PS1="\[\e[32m\]\u@clawdbox\[\e[m\]:\[\e[34m\]\w\[\e[m\]\$ "' >> /home/claw/.bashrc && \
+    echo 'alias ll="ls -lah"' >> /home/claw/.bashrc && \
+    echo 'alias k="kubectl"' >> /home/claw/.bashrc && \
+    echo 'alias dc="docker"' >> /home/claw/.bashrc && \
+    echo 'export HISTFILE=/data/.bash_history' >> /home/claw/.bashrc && \
+    echo 'export HISTSIZE=10000' >> /home/claw/.bashrc && \
+    echo 'export HISTFILESIZE=10000' >> /home/claw/.bashrc
+
 # Start SSH daemon
 # The keys are generated if they don't exist on the persistent volume
 CMD ["/bin/bash", "-c", "\
@@ -97,4 +125,5 @@ for keytype in rsa ecdsa ed25519; do \
     fi; \
 done && \
 chmod 600 /data/ssh/ssh_host_*_key && \
+if [ -f /data/.gitconfig ]; then ln -sf /data/.gitconfig ~/.gitconfig; fi && \
 /usr/sbin/sshd -D -e -f /etc/ssh/sshd_config"]

Makefile

@@ -0,0 +1,83 @@
+.PHONY: build push deploy redeploy logs shell disk-usage clean-cache health-check help
+
+# Use podman if docker is not available
+DOCKER := $(shell which docker 2>/dev/null || which podman 2>/dev/null)
+
+IMAGE_NAME=default-route-openshift-image-registry.apps.lab.apilab.us/clawdbox/clawdbox:latest
+NAMESPACE=clawdbox
+SSH_HOST=clawdbox.apps.lab.apilab.us
+SSH_PORT=2222
+SSH_USER=claw
+
+help:
+	@echo "ClawdBox Makefile - Common Operations"
+	@echo ""
+	@echo "Build & Deploy:"
+	@echo "  make build        - Build Docker image"
+	@echo "  make push         - Build and push image to registry"
+	@echo "  make deploy       - Deploy all manifests to cluster"
+	@echo "  make redeploy     - Push image and restart deployment"
+	@echo ""
+	@echo "Operations:"
+	@echo "  make logs         - Stream pod logs"
+	@echo "  make shell        - SSH into container"
+	@echo "  make disk-usage   - Check /data disk usage"
+	@echo "  make clean-cache  - Clear pip/npm caches"
+	@echo "  make health-check - Run comprehensive health diagnostics"
+	@echo ""
+	@echo "Debugging:"
+	@echo "  make describe     - Describe deployment"
+	@echo "  make events       - Show namespace events"
+	@echo "  make restart      - Restart deployment (without push)"
+
+build:
+	$(DOCKER) build -t $(IMAGE_NAME) .
+
+push: build
+	$(DOCKER) push $(IMAGE_NAME)
+
+deploy:
+	kubectl apply -f manifests/
+
+redeploy: push
+	kubectl rollout restart deployment/clawdbox -n $(NAMESPACE)
+	@echo "Waiting for rollout to complete..."
+	kubectl rollout status deployment/clawdbox -n $(NAMESPACE)
+
+restart:
+	kubectl rollout restart deployment/clawdbox -n $(NAMESPACE)
+	kubectl rollout status deployment/clawdbox -n $(NAMESPACE)
+
+logs:
+	kubectl logs -f -n $(NAMESPACE) deployment/clawdbox
+
+shell:
+	ssh -p $(SSH_PORT) $(SSH_USER)@$(SSH_HOST)
+
+disk-usage:
+	@ssh -p $(SSH_PORT) $(SSH_USER)@$(SSH_HOST) "df -h /data && echo '' && echo 'Top 10 Largest Directories:' && du -h /data 2>/dev/null | sort -rh | head -10"
+
+clean-cache:
+	@ssh -p $(SSH_PORT) $(SSH_USER)@$(SSH_HOST) "rm -rf /data/.cache/pip/* /data/.cache/npm/* && echo 'Package caches cleared'"
+
+health-check:
+	@ssh -p $(SSH_PORT) $(SSH_USER)@$(SSH_HOST) "/data/scripts/health-check.sh"
+
+describe:
+	kubectl describe deployment/clawdbox -n $(NAMESPACE)
+
+events:
+	kubectl get events -n $(NAMESPACE) --sort-by='.lastTimestamp'
+
+status:
+	@echo "=== Deployment Status ==="
+	@kubectl get deployment -n $(NAMESPACE)
+	@echo ""
+	@echo "=== Pod Status ==="
+	@kubectl get pods -n $(NAMESPACE)
+	@echo ""
+	@echo "=== Service Status ==="
+	@kubectl get svc -n $(NAMESPACE)
+	@echo ""
+	@echo "=== Route Status ==="
+	@kubectl get route -n $(NAMESPACE) 2>/dev/null || echo "No routes found (not on OpenShift?)"

README.md

@@ -10,11 +10,14 @@ This container provides a stable, tool-rich environment for the AI agent to:
 - Use tools that aren't available in the minimal agent environment.
 
 ## Tools Included
-- **Core:** curl, wget, git, jq, yq, unzip, tar, vim/nano
-- **Dev:** python3 (pip/venv), build-essential, nodejs, npm
-- **Network:** ping, dnsutils, net-tools
+- **Core:** curl, wget, git, jq, yq, unzip, tar, vim/nano, tree, less
+- **Dev:** python3 (pip/venv), build-essential, nodejs (v20), npm
+- **Python Libraries:** httpie, pyyaml, requests, black, ipython
+- **Network:** ping, dnsutils, net-tools, openssh-server/client, sshpass
 - **Media:** ffmpeg
-- **Access:** openssh-server
+- **Monitoring:** htop, tmux, ncdu, strace
+- **Kubernetes:** OpenShift CLI (oc)
+- **Search:** ripgrep (fast grep alternative)
 
 ## Deployment (OpenShift / K8s)
 
@@ -47,4 +50,244 @@ This container provides a stable, tool-rich environment for the AI agent to:
    ```
 
 ## Access
-Connect via SSH using the `claw` user (passwordless sudo enabled).
+Connect via SSH using the `claw` user (passwordless sudo enabled):
+```bash
+ssh -p 2222 claw@clawdbox.apps.lab.apilab.us
+# or
+make shell
+```
+
+## Persistent Storage Structure
+
+The `/data` volume preserves data across container restarts:
+
+```
+/data/
+├── ssh/                  # SSH host keys (auto-generated on first run)
+├── scripts/              # Helper scripts (from ConfigMap, read-only)
+│   ├── disk-usage.sh
+│   ├── health-check.sh
+│   ├── clean-workspace.sh
+│   └── install-tools.sh
+├── .cache/
+│   ├── pip/             # Python package cache (persisted)
+│   └── npm/             # Node package cache (persisted)
+├── .local/              # User-installed Python packages (pip install --user)
+├── .gitconfig           # Git configuration (create to persist)
+├── .bash_history        # Command history (persistent)
+└── [your workspace]     # Your work files
+```
+
+**Storage:** 10Gi PersistentVolumeClaim (ReadWriteOnce)
+
+## Common Tasks
+
+### Quick Operations (Using Makefile)
+```bash
+make help         # Show all available commands
+make logs         # Stream container logs
+make shell        # SSH into container
+make disk-usage   # Check storage usage
+make clean-cache  # Clear package caches
+make redeploy     # Rebuild, push, and restart
+```
+
+### Install Python Packages
+Packages are cached in `/data/.cache/pip` and survive restarts:
+```bash
+pip3 install --user pandas numpy scikit-learn
+# Installs to /data/.local/lib/python3.*/site-packages/
+```
+
+### Install Node Packages Globally
+```bash
+npm install -g typescript ts-node
+# Cached in /data/.cache/npm
+```
+
+### Persist Git Configuration
+```bash
+# Inside the container:
+git config --global user.name "Your Name"
+git config --global user.email "you@example.com"
+# Save to persistent storage:
+cp ~/.gitconfig /data/.gitconfig
+# (Will auto-link on next restart)
+```
+
+### Check Disk Usage
+```bash
+# Quick overview:
+df -h /data
+
+# Use helper script for detailed report:
+/data/scripts/disk-usage.sh
+
+# Interactive explorer:
+ncdu /data
+
+# Top 10 largest directories:
+du -h /data | sort -rh | head -10
+```
+
+### Helper Scripts
+Pre-loaded scripts available in `/data/scripts/`:
+
+```bash
+# Comprehensive health check:
+/data/scripts/health-check.sh
+
+# Disk usage report:
+/data/scripts/disk-usage.sh
+
+# Interactive workspace cleanup:
+/data/scripts/clean-workspace.sh
+
+# Install common tools:
+/data/scripts/install-tools.sh
+```
+
+### Shell Features
+The shell includes several quality-of-life improvements:
+
+- **Colored prompt:** `claw@clawdbox:/data$` (green user, blue path)
+- **Persistent history:** Command history saved to `/data/.bash_history`
+- **Useful aliases:**
+  - `ll` - detailed file listing (`ls -lah`)
+  - `k` - kubectl shortcut
+  - `dc` - docker shortcut
+- **10,000 line history:** Never lose your commands
+
+## Troubleshooting
+
+### SSH Connection Refused
+**Problem:** Cannot connect via SSH
+
+**Diagnosis:**
+```bash
+# Check if pod is running:
+kubectl get pods -n clawdbox
+
+# Check pod logs:
+make logs
+# or
+kubectl logs -n clawdbox deployment/clawdbox
+```
+
+**Common causes:**
+- Pod still starting (wait for startup probe to pass)
+- SSH keys not mounted correctly (check secret exists)
+- Route not configured (check `kubectl get route -n clawdbox`)
+
+### Out of Disk Space
+**Problem:** `/data` volume is full
+
+**Diagnosis:**
+```bash
+make disk-usage
+# or
+ssh -p 2222 claw@clawdbox.apps.lab.apilab.us "df -h /data"
+```
+
+**Solutions:**
+```bash
+# Clear package caches:
+make clean-cache
+
+# Find large directories:
+ncdu /data
+
+# Clear specific caches manually:
+rm -rf /data/.cache/pip/*
+rm -rf /data/.cache/npm/*
+```
+
+### Slow Package Installs
+**Problem:** `pip install` or `npm install` is slow
+
+**Diagnosis:**
+Check if cache directories are properly configured:
+```bash
+ssh -p 2222 claw@clawdbox.apps.lab.apilab.us
+echo $PIP_CACHE_DIR        # Should show: /data/.cache/pip
+echo $npm_config_cache     # Should show: /data/.cache/npm
+ls -la /data/.cache/
+```
+
+**Solution:**
+If environment variables are missing, rebuild the container:
+```bash
+make redeploy
+```
+
+### Pod Stuck in CrashLoopBackOff
+**Problem:** Container won't start
+
+**Diagnosis:**
+```bash
+kubectl describe pod -n clawdbox -l app=clawdbox
+kubectl logs -n clawdbox -l app=clawdbox --previous
+```
+
+**Common causes:**
+- PVC not bound (check `kubectl get pvc -n clawdbox`)
+- SSH host key generation failed (check logs for errors)
+- Resource limits too low (increase in deployment.yaml)
+
+### Deployment Status
+**Quick health check:**
+```bash
+make status
+# Shows: deployment, pods, services, routes
+```
+
+## Development Workflow
+
+### Local Development
+```bash
+# 1. Make changes to Dockerfile or manifests
+vim Dockerfile
+
+# 2. Build and test locally (optional)
+docker build -t clawdbox:test .
+
+# 3. Deploy to cluster
+make redeploy
+
+# 4. Watch for successful rollout
+make logs
+```
+
+### Adding New Tools
+Edit the Dockerfile and add to the `apt-get install` section:
+```dockerfile
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    # ... existing tools ...
+    your-new-tool \
+    && rm -rf /var/lib/apt/lists/*
+```
+
+Then:
+```bash
+make redeploy
+```
+
+## Security Notes
+
+- **Non-root:** Container runs as UID 1000 (`claw` user)
+- **SSH:** Public key authentication only (no passwords)
+- **Sudo:** Passwordless sudo available for `claw` user
+- **Capabilities:** All capabilities dropped except `NET_BIND_SERVICE`
+- **Network:** Ingress restricted to SSH port (2222)
+
+## Resource Limits
+
+**Requests:**
+- CPU: 500m
+- Memory: 256Mi
+
+**Limits:**
+- CPU: 2000m (2 cores)
+- Memory: 2Gi
+
+Adjust in `manifests/deployment.yaml` if needed for heavy workloads.

manifests/configmap.yaml

@@ -0,0 +1,189 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: clawdbox-scripts
+  namespace: clawdbox
+  labels:
+    app: clawdbox
+data:
+  disk-usage.sh: |
+    #!/bin/bash
+    # Quick disk usage report for /data volume
+
+    echo "=== Data Volume Usage ==="
+    df -h /data
+
+    echo -e "\n=== Top 10 Largest Directories ==="
+    du -h /data 2>/dev/null | sort -rh | head -10
+
+    echo -e "\n=== Cache Sizes ==="
+    if [ -d /data/.cache/pip ]; then
+      echo "pip cache: $(du -sh /data/.cache/pip 2>/dev/null | cut -f1)"
+    fi
+    if [ -d /data/.cache/npm ]; then
+      echo "npm cache: $(du -sh /data/.cache/npm 2>/dev/null | cut -f1)"
+    fi
+
+  health-check.sh: |
+    #!/bin/bash
+    # Comprehensive health diagnostics for troubleshooting
+
+    echo "=== ClawdBox Health Check ==="
+    echo "Timestamp: $(date)"
+    echo ""
+
+    echo "=== SSH Daemon Status ==="
+    if ps aux | grep -v grep | grep sshd > /dev/null; then
+      echo "✓ SSH daemon is running"
+      ps aux | grep sshd | grep -v grep
+    else
+      echo "✗ SSH daemon is NOT running"
+    fi
+    echo ""
+
+    echo "=== Disk Space ==="
+    df -h /data
+    echo ""
+
+    echo "=== Memory Usage ==="
+    free -h
+    echo ""
+
+    echo "=== Network Connectivity ==="
+    if ping -c 1 8.8.8.8 > /dev/null 2>&1; then
+      echo "✓ Internet connectivity OK"
+    else
+      echo "✗ No internet connectivity"
+    fi
+    echo ""
+
+    echo "=== Environment Variables ==="
+    echo "PIP_CACHE_DIR: $PIP_CACHE_DIR"
+    echo "npm_config_cache: $npm_config_cache"
+    echo "HISTFILE: $HISTFILE"
+    echo ""
+
+    echo "=== Persistent Directories ==="
+    ls -lah /data/.cache/ 2>/dev/null || echo "No .cache directory"
+    echo ""
+
+    echo "=== Current Working Directory ==="
+    pwd
+    echo ""
+
+    echo "=== User Information ==="
+    whoami
+    id
+
+  clean-workspace.sh: |
+    #!/bin/bash
+    # Interactive workspace cleanup helper
+
+    echo "=== ClawdBox Workspace Cleanup ==="
+    echo ""
+
+    # Show current usage
+    echo "Current disk usage:"
+    df -h /data
+    echo ""
+
+    # Offer cleanup options
+    echo "What would you like to clean?"
+    echo "1) Package caches (pip + npm)"
+    echo "2) Temporary files"
+    echo "3) Both caches and temp files"
+    echo "4) Show what's using space (no deletion)"
+    echo "5) Cancel"
+    echo ""
+
+    read -p "Enter choice [1-5]: " choice
+
+    case $choice in
+      1)
+        echo "Cleaning package caches..."
+        rm -rf /data/.cache/pip/* /data/.cache/npm/*
+        echo "✓ Package caches cleared"
+        ;;
+      2)
+        echo "Cleaning temporary files..."
+        find /data -type f -name "*.tmp" -delete 2>/dev/null
+        find /data -type f -name "*.log" -mtime +7 -delete 2>/dev/null
+        echo "✓ Temporary files cleaned"
+        ;;
+      3)
+        echo "Cleaning caches and temporary files..."
+        rm -rf /data/.cache/pip/* /data/.cache/npm/*
+        find /data -type f -name "*.tmp" -delete 2>/dev/null
+        find /data -type f -name "*.log" -mtime +7 -delete 2>/dev/null
+        echo "✓ All cleaned"
+        ;;
+      4)
+        echo "Analyzing disk usage..."
+        du -h /data | sort -rh | head -20
+        ;;
+      5)
+        echo "Cleanup cancelled"
+        exit 0
+        ;;
+      *)
+        echo "Invalid choice"
+        exit 1
+        ;;
+    esac
+
+    echo ""
+    echo "New disk usage:"
+    df -h /data
+
+  install-tools.sh: |
+    #!/bin/bash
+    # Helper script to install common additional tools
+
+    echo "=== ClawdBox Additional Tools Installer ==="
+    echo ""
+    echo "This script helps install commonly requested tools."
+    echo "All installations are temporary and will be lost on container restart."
+    echo ""
+
+    echo "Available tool categories:"
+    echo "1) Data science (pandas, numpy, matplotlib)"
+    echo "2) Web scraping (beautifulsoup4, selenium)"
+    echo "3) CLI tools (fzf, bat, fd-find)"
+    echo "4) Custom (specify packages)"
+    echo "5) Exit"
+    echo ""
+
+    read -p "Enter choice [1-5]: " choice
+
+    case $choice in
+      1)
+        echo "Installing data science packages..."
+        pip3 install --user pandas numpy matplotlib scipy
+        ;;
+      2)
+        echo "Installing web scraping packages..."
+        pip3 install --user beautifulsoup4 selenium requests-html
+        ;;
+      3)
+        echo "Installing CLI tools..."
+        echo "Note: These require sudo and apt-get"
+        sudo apt-get update
+        sudo apt-get install -y fzf bat fd-find
+        ;;
+      4)
+        read -p "Enter package names (space-separated): " packages
+        echo "Installing: $packages"
+        pip3 install --user $packages
+        ;;
+      5)
+        echo "Exiting"
+        exit 0
+        ;;
+      *)
+        echo "Invalid choice"
+        exit 1
+        ;;
+    esac
+
+    echo ""
+    echo "✓ Installation complete"

manifests/deployment.yaml

@@ -51,6 +51,13 @@ spec:
           ports:
             - containerPort: 2222
               name: ssh
+          env:
+            - name: TERM
+              value: xterm-256color
+            - name: DEBIAN_FRONTEND
+              value: noninteractive
+            - name: TZ
+              value: UTC
           startupProbe:
             tcpSocket:
               port: ssh
@@ -77,6 +84,8 @@ spec:
               name: ssh-working
             - mountPath: /home/claw/.kube
               name: kubeconfig-secret
+            - mountPath: /data/scripts
+              name: helper-scripts
           resources:
             limits:
               memory: "2Gi"
@@ -103,3 +112,7 @@ spec:
             secretName: kube
         - name: ssh-working
           emptyDir: {}
+        - name: helper-scripts
+          configMap:
+            name: clawdbox-scripts
+            defaultMode: 0755