Initial commit

Signed-off-by: Ilan Bigio <ilan@openai.com>

codex-cli/examples/camerascii/run.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+
+# run.sh — Create a new run_N directory for a Codex task, optionally bootstrapped from a template,
+# then launch Codex with the task description from task.yaml.
+#
+# Usage:
+#   ./run.sh                  # Prompts to confirm new run
+#   ./run.sh --auto-confirm   # Skips confirmation
+#
+# Assumes:
+#   - yq and jq are installed
+#   - ../task.yaml exists (with .name and .description fields)
+#   - ../template/ exists (optional, for bootstrapping new runs)
+
+# Enable auto-confirm mode if flag is passed
+auto_mode=false
+[[ "$1" == "--auto-confirm" ]] && auto_mode=true
+
+# Create the runs directory if it doesn't exist
+mkdir -p runs
+
+# Move into the working directory
+cd runs || exit 1
+
+# Grab task name for logging
+task_name=$(yq -o=json '.' ../task.yaml | jq -r '.name')
+echo "Checking for runs for task: $task_name"
+
+# Find existing run_N directories
+shopt -s nullglob
+run_dirs=(run_[0-9]*)
+shopt -u nullglob
+
+if [ ${#run_dirs[@]} -eq 0 ]; then
+  echo "There are 0 runs."
+  new_run_number=1
+else
+  max_run_number=0
+  for d in "${run_dirs[@]}"; do
+    [[ "$d" =~ ^run_([0-9]+)$ ]] && (( ${BASH_REMATCH[1]} > max_run_number )) && max_run_number=${BASH_REMATCH[1]}
+  done
+  new_run_number=$((max_run_number + 1))
+  echo "There are $max_run_number runs."
+fi
+
+# Confirm creation unless in auto mode
+if [ "$auto_mode" = false ]; then
+  read -p "Create run_$new_run_number? (Y/N): " choice
+  [[ "$choice" != [Yy] ]] && echo "Exiting." && exit 1
+fi
+
+# Create the run directory
+mkdir "run_$new_run_number"
+
+# Check if the template directory exists and copy its contents
+if [ -d "../template" ]; then
+  cp -r ../template/* "run_$new_run_number"
+  echo "Initialized run_$new_run_number from template/"
+else
+  echo "Template directory does not exist. Skipping initialization from template."
+fi
+
+cd "run_$new_run_number"
+
+# Launch Codex
+echo "Launching..."
+description=$(yq -o=json '.' ../../task.yaml | jq -r '.description')
+codex "$description"

codex-cli/examples/camerascii/task.yaml

@@ -0,0 +1,5 @@
+name: "camerascii"
+description: |
+  Take a look at the screenshot details and implement a webpage that uses webcam
+  to style the video feed accordingly (i.e. as ASCII art). Add some of the relevant features
+  from the screenshot to the webpage in index.html.

codex-cli/examples/camerascii/template/screenshot_details.md

@@ -0,0 +1,34 @@
+### Screenshot Description
+
+The image is a full–page screenshot of a single post on the social‑media site X (formerly Twitter).
+
+1. **Header row**
+   * At the very top‑left is a small circular avatar.  The photo shows the side profile of a person whose face is softly lit in bluish‑purple tones; only the head and part of the neck are visible.
+   * In the far upper‑right corner sit two standard X / Twitter interface icons: a circle containing a diagonal line (the “Mute / Block” indicator) and a three‑dot overflow menu.
+
+2. **Tweet body text**
+   * Below the header, in regular type, the author writes:
+
+     “Okay, OpenAI’s o3 is insane. Spent an hour messing with it and built an image‑to‑ASCII art converter, the exact tool I’ve always wanted. And it works so well”
+
+3. **Embedded media**
+   * The majority of the screenshot is occupied by an embedded 12‑second video of the converter UI.  The video window has rounded corners and a dark theme.
+   * **Left panel (tool controls)** – a slim vertical sidebar with the following labeled sections and blue–accented UI controls:
+     * Theme selector (“Dark” is chosen).
+     * A small checkbox labeled “Ignore White”.
+     * **Upload Image** button area that shows the chosen file name.
+     * **Image Processing** sliders:
+       * “ASCII Width” (value ≈ 143)
+       * “Brightness” (‑65)
+       * “Contrast” (58)
+       * “Blur (px)” (0.5)
+       * A square checkbox for “Invert Colors”.
+     * **Dithering** subsection with a checkbox (“Enable Dithering”) and a dropdown for the algorithm (value: “Noise”).
+     * **Character Set** dropdown (value: “Detailed (Default)”).
+     * **Display** slider labeled “Zoom (%)” (value ≈ 170) and a “Reset” button.
+
+   * **Main preview area (right side)** – a dark gray canvas that renders the selected image as white ASCII characters.  The preview clearly depicts a stylized **palm tree**: a skinny trunk rises from the bottom centre, and a crown of splayed fronds fills the upper right quadrant.
+   * A small black badge showing **“0:12”** overlays the bottom‑left corner of the media frame, indicating the video’s duration.
+   * In the top‑right area of the media window are two pill‑shaped buttons: a heart‑shaped “Save” button and a cog‑shaped “Settings” button.
+
+Overall, the screenshot shows the user excitedly announcing the success of their custom “Image to ASCII” converter created with OpenAI’s “o3”, accompanied by a short video demonstration of the tool converting a palm‑tree photo into ASCII art.