Rho-plugins owns reusable functional capabilities: documents/code, files and artifacts, runtime adapters and object inspection, requirements, tables, media, charts and Agent integration. Each capability owns its behavior, native preconditions, resources, results and checks. Project analysis workflows compose these capabilities; they are not plugins.
Rho-core supplies the execution foundation. Rho assembles components into an application. A component can serve headless callers and application users through optional CLI, Skills, MCP or UI entries to the same functionality.
The reusable plugin model defines capability ownership, headless and UI entries, resource/selection contracts and extraction acceptance. A plugin can contribute several views over one state owner. Rho selects and arranges those entries; a workflow's dataset, method choices and sequencing stay in project code or an example. The 0.4 implementation ships those capabilities as eight independent npm plugins; browser entries remain separate work.
| Implementation | Available behavior | Acceptance |
|---|---|---|
| Eight headless plugins 0.4 | Shared documents, explicit R execution/requirements, declared files/tables/media/object snapshots, keyed comparisons and MCP | Component and integration scope |
| Agent evaluation | Separate development tool: isolated public Core CLI trials, domain-owned checks and offline regrading | Recorded execution |
The paired airway analysis is a scientific
example and acceptance consumer: DESeq2 analysis, donor sensitivity, simulations
and artifact checks. Its scientific/execution record
is retained. Neither it nor the ordinary base-R project
is shipped in any capability package. Both explicitly declare scripts, requirements,
artifacts and checks to the same r.execute capability.
The Python/R consumers and eight Node capability packages run today. Editor, table, plot and Agent UI entries remain independent work. Status records that boundary.
Evaluation uses Python's standard library. Core trials take an explicitly
selected public rho-core binary. Model trials also require the configured
Claude Code CLI and model gateway described in the consumer documentation.
The R recipe uses existing R packages and ordinary files.
npm ci
npm test
npm run test:examples
npm run pack:plugins -- --destination /absolute/plugin-tarballs
npm run test:install -- /absolute/plugin-tarballs
python3 plugins/agent-eval/run.py --help
python3 plugins/agent-eval/run.py core-agent --binary /absolute/rho-core --baseline --trials 1
python3 plugins/agent-eval/run.py r-artifacts /absolute/airway/artifacts
python3 -m unittest discover -s plugins/agent-eval -p 'test_*.py' -v
RHO_EVAL_CORE_BINARY=/absolute/rho-core python3 -m unittest discover -s plugins/agent-eval/core-agent -p 'test_*.py' -vEach evaluation writes a new evidence directory. Retained artifact checks and regrading do not invoke a model or rerun the scientific analysis. Read each consumer's prerequisites, limits and evidence scope before execution.
Scientific code/data/plots, freely composed views and Agent-driven interaction evolve in one application flow. Rho first delivers an npm local backend, then a React/TypeScript, Vite and Dockview WebUI in one browser window. Electron and cross-window movement follow later. Selected views use CodeMirror 6, AG Grid Community and ECharts. Agent-composed UI uses a typed json-render catalog; independent HTML views may use isolated MCP Apps when needed.
Architecture defines component responsibilities and the Action, Resource, Selection and View boundaries. The selected 0.4 plugin composition uses declared types, entity namespaces and fields without scientific workflow branches. Both R projects have passed actual headless execution in Rho. Browser rendering, input and layout remain selected work. Roadmap defines the first integrated flow. The headless plugins documents the implemented entries and actual Rho composition checks. There is no universal component loader.
Execution completion, artifact completeness, domain checks and model judgments are distinct facts. Existing authorization is checked at the actual boundary; models and retrieved content cannot broaden its scope.
See Privacy, Security and contribution instructions. Source is licensed under AGPL-3.0.