Replace hardcoded global API URL variables with getter functions that check the R_BASE_URL environment variable, falling back to the static defaults. Introduce a joinpath utility in utils.h to safely concatenate a base URL with a path segment, handling trailing slashes and leading path slashes. Remove conditional compilation blocks for RD and OLLAMA backends, consolidating all API URL logic into the new get_completions_api_url and get_models_api_url functions. Update all call sites in openai.h to use the new getter functions instead of direct global variable access.
Introduce conditional compilation via OLLAMA preprocessor flag to switch between OpenAI and Ollama API endpoints, model names, and URLs. Add `build_free` and `run_free` Makefile targets for the Ollama variant. Enhance REPL with `!models` command to list available models, improve error handling in `openai_process_chat_message`, and fix history line addition logic.
Add a new `message_add_object` function in messages.h that appends a json_object to the global message list. Modify openai_chat in openai.h to call this function after processing a chat completion, ensuring the assistant's response object is stored. Also comment out the previous `message_add_tool_call` call to avoid duplicate message storage when tool calls are present, and add a missing `continue` in main.c's repl loop after the dump command to prevent fallthrough.
Implement tool calling infrastructure including tools.h with http_fetch function description and execution, message_add_tool_call and message_add_tool_result helpers in messages.h, tool descriptions injection into user messages and chat_json, http header parsing utilities in http.h, curl_get function in http_curl.h, and tool call execution loop in openai_chat that recursively processes tool results.
Add `http_curl.h` providing `curl_post` function using libcurl, update `openai.h` to call `curl_post` instead of `https_post` in both `openai_system` and `openai_chat`, add missing `#ifndef`/`#endif` include guard to `auth.h`, increase HTTP buffer size from 4096 to 1MB, add explicit `(char *)` casts to `malloc`/`realloc` calls in `http.h`, and link `-lcurl` in both `build` and `build_free` Makefile targets.
Add initial project structure including .gitignore for build artifacts,
Makefile with gcc build and run targets, README placeholder, cgi-bin
directory with gpt.py and gpt_template.html, and core C headers for
chat, http, line input, markdown rendering, and messages.
