solveit

# SolveIt Dialog Tools Manipulate **SolveIt dialogs** (similar to Jupyter notebooks) via CLI. A dialog contains **messages** (cells) of type `code`, `note` (markdown), `prompt` (AI prompt/response), or `raw`. Every command takes a **dialog URL** as its first argument and returns **JSON to stdout**. ## Invocation ```bash uv run {baseDir}/solveit_tools.py <command> [args...] ``` ## Commands ### read_dialog — Read all messages ```bash uv run {baseDir}/solveit_tools.py read_dialog "<url>" ``` Returns: ```json { "url": "...", "name": "my-project/experiment", "mode": "learning", "messages": [ {"id": "_ea386899", "type": "note", "index": 0, "content": "# Title"}, {"id": "_f70704ce", "type": "code", "index": 1, "content": "1+1", "output": "2"}, {"id": "_b3796dd8", "type": "prompt", "index": 2, "content": "explain this", "output": "Sure..."} ] } ``` Use `id` values to reference messages in other commands. The `output` field is omitted when empty. ### add_message — Add a new message ```bash # Append a code cell at the end (default) uv run {baseDir}/solveit_tools.py add_message "<url>" "print('hello')" # Add a note before a specific message uv run {baseDir}/solveit_tools.py add_message "<url>" "# Section 2" --type note --placement before --ref-id "_f70704ce" # Add a prompt after a specific message uv run {baseDir}/solveit_tools.py add_message "<url>" "explain the error above" --type prompt --placement after --ref-id "_f70704ce" ``` | Flag | Values...