mirror of
https://github.com/ggozad/oterm.git
synced 2026-10-15 11:43:21 +02:00
97fd157160- rag_example: rewrite for current haiku.rag. The MCP server is `haiku-rag mcp` and opens the database read-only, so documents are added with the CLI; the page described `serve`, SQLite storage and add/delete tools that no longer exist. - mcp: stdio servers accept cwd and inherit HOME, LOGNAME, PATH, SHELL, TERM and USER. - app_config: each openaiCompatible endpoint is its own provider; XDG_DATA_HOME applies everywhere but Windows; list OTERM_OLLAMA_IMAGE_MODEL and everything under OTERM_DATA_DIR. - commands: add Copy message, an Images section and the command-line options; clicking a code block copies the whole message. - installation: document the speak extra and nix updates; drop the 0.13.1 tap note. - development: uv-based setup; docs are built with Zensical. - One H1 per page; no em dashes. - README points at the CHANGELOG; drop the stale announcement banner.
24 lines
821 B
Markdown
24 lines
821 B
Markdown
# Oracle: example oterm tool plugin
|
|
|
|
A minimal example of how to ship a Python package whose function is auto-discovered as an oterm tool.
|
|
|
|
The tool itself is trivial, `oracle(question)` always answers `"oterm"`, so you can focus on the packaging:
|
|
|
|
- `src/oracle/tool.py` defines the function. Its name, docstring, and type annotations are what oterm passes to the model.
|
|
- `pyproject.toml` registers the function under the `oterm.tools` entry-point group:
|
|
|
|
```toml
|
|
[project.entry-points."oterm.tools"]
|
|
oracle = "oracle.tool:oracle"
|
|
```
|
|
|
|
Install it into the same environment as oterm:
|
|
|
|
```bash
|
|
cd docs/oracle
|
|
uv pip install . # or: pip install .
|
|
```
|
|
|
|
After restart, the `oracle` tool appears in the new-chat tool selector.
|
|
|
|
See the [tools guide](https://ggozad.github.io/oterm/tools/) for the full walkthrough.
|