[rig-summarizer] Daily file summary — 2026-10-14
Los mantenedores suelen responder en 1 día
Nadie ha tomado este issue todavía.
Evaluación
- Dificultad
- 2/5
- Tiempo estimado
- Menos de una hora
- Aptitud para principiantes
- 12/100
- Tipo de issue
- Documentación
- Claridad
- Necesita aclaración
- Estado de actividad
- Activo
- Stack tecnológico
- typescript
- Área
- ai-infra-agents, devtools
Línea de trabajo
This is an automated daily summary of the repo's TypeScript files, and it asks for no change. The files it lists (rig.ts, the engines/ adapters, and the .github/fixtures/ three-judge workflow) are context only. Nothing here defines a done state, so a newcomer should pick a different issue that names a specific change.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
Global Summary
This project is Rig, a minimal TypeScript agent harness. The core runtime (rig.ts) provides typed schemas, prompt intents, sub-agent delegation, and a Copilot SDK runtime. Alternative engines (Anthropic, Codex, DeepSeek, Gemini, Pi) sit alongside it. Launcher and run helpers, CI drivers and fixtures that run a three-judge provider check, and integration tests complete the repo. Only the first 20 .ts files were listed.
Individual File Summaries
| File | Summary |
|---|---|
| ./.agents/skills/rig/engines/anthropic.ts | Engine adapter that runs Rig agents on the Anthropic SDK, with JSON-schema output and tool support. |
| ./.agents/skills/rig/engines/codex.ts | Engine adapter for the OpenAI Codex SDK, using thread options and normalized response schemas. |
| ./.agents/skills/rig/engines/deepseek.ts | Engine adapter for the DeepSeek harness SDK client. |
| ./.agents/skills/rig/engines/gemini.ts | Engine adapter that spawns the Gemini CLI as a subprocess to run agent turns. |
| ./.agents/skills/rig/engines/pi.ts | Engine adapter built on the Pi agent core and AI libraries, wrapping Rig tools as Pi tools. |
| ./.agents/skills/rig/engines/utils.ts | Shared engine helpers: an agent lifecycle with abort and no-concurrent-turns handling, plus tool schema and result utilities. |
| ./.agents/skills/rig/globals.ts | Ambient workflow helpers (call, pipeline, parallel) that delegate to the active workflow run. |
| ./.agents/skills/rig/launch-tool.ts | Creates a Copilot SDK tool that launches Rig programs through the launcher process. |
| ./.agents/skills/rig/rig.ts | Core Rig runtime (about 3,500 lines): schemas, prompt intents, agents, workflows, and the Copilot SDK runtime and launcher CLI. |
| ./.agents/skills/rig/run.ts | Small entry point that runs the installed skill's launcher CLI. |
| ./.github/drivers/codex-fixture-mcp.ts | Driver that serves the three-judge fixture over a local MCP HTTP server for Codex. |
| ./.github/drivers/copilot-sdk-driver.ts | Driver that sets up a Copilot SDK session with the Rig launch tool for CI runs. |
| ./.github/drivers/pi-rig-extension.ts | Pi extension that exposes a Rig fixture tool and validates its output. |
| ./.github/fixtures/assert-three-judges.ts | Assertions that validate the three-judge fixture result for a given engine. |
| ./.github/fixtures/pi-gateway.ts | Loads and validates the Pi aw-gateway provider configuration. |
| ./.github/fixtures/provider-fixture.ts | Builds the provider-specific three-judge fixture from environment config for the Codex, DeepSeek, Gemini, and Pi engines. |
| ./.github/fixtures/provider-three-judges.ts | Default export that creates the provider fixture. |
| ./.github/fixtures/three-judges.ts | Defines the three-judge Rig workflow, which judges a dummy request on clarity, safety, and feasibility. |
| ./scripts/haiku.integration.test.ts | Integration tests that run the haiku, sonnet, and complex samples through the launcher when credentials exist. |
| ./scripts/rig-launch-tool.integration.test.ts | Live integration test that runs the three-judge fixture via a harness-owned launch tool, gated by an env flag. |
Generated by Daily Rig File Summarizer · copilot · auto · 14.6 AIC · ⌖ 0.505 AIC · ⊞ 7.5K · ◷
- expires on Oct 21, 2026, 2:36 PM UTC
- Lenguaje dominante
- TypeScript
- Estrellas
- 14
- Forks
- 0
- Merge medio
- 3 h 38 min
- PR fusionados (30 d)
- 29
Preparar el entorno
Este proyecto no incluye contenedor de desarrollo, Dockerfile ni guía de contribución, así que la configuración corre por tu cuenta: empieza por su README y consulta nuestra guía para la primera contribución para los pasos generales.
Primeros pasos
- Lee el issue completo y luego la guía de contribución del proyecto.
- Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
- Haz un fork del repositorio y trabaja en una rama.
- Abre un pull request que haga referencia al número del issue.
Más de githubnext/rig
-
agentic-workflows
Dificultad 4/5 1-2 días Aptitud para principiantes 22/100
githubnext/rig#650 ·
Los mantenedores suelen responder en 1 día
-
ai-agent automation
Dificultad 3/5 Medio día Aptitud para principiantes 15/100
githubnext/rig#648 ·
Los mantenedores suelen responder en 1 día
-
agentic-workflows
Dificultad 3/5 Medio día Aptitud para principiantes 25/100
githubnext/rig#646 ·
Los mantenedores suelen responder en 1 día
-
ai-agent automation
Dificultad 4/5 1-2 días Aptitud para principiantes 15/100
githubnext/rig#645 ·
Los mantenedores suelen responder en 1 día
-
agentic-workflows
Dificultad 4/5 3-5 días Aptitud para principiantes 15/100
githubnext/rig#644 ·
Los mantenedores suelen responder en 1 día
Todos los issues de githubnext/rig
Issues similares
-
bug
Dificultad 2/5 1-3 horas Aptitud para principiantes 72/100
vercel/streamdown#673 · 1 reacción ·
Los mantenedores suelen responder en 1 día
-
docs(stream-protocol): document messageMetatadata on start/finish and the message-metadata chunkPosiblemente ocupada Un pull request vinculado a esta issue está abierto o ya se fusionó. Abiertofactory-active task-identify-harness-labels-done task-identify-issue-type-done
Dificultad 2/5 1-3 horas Aptitud para principiantes 82/100
vercel/ai#23375 · 1 comentario ·
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 72/100
agilepathway/label-checker#721 ·
Los mantenedores suelen responder en 1 día
-
CLI Empathy needs triage
Dificultad 2/5 1-3 horas Aptitud para principiantes 74/100
chromaui/chromatic-cli#1524 ·
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 72/100
Los mantenedores suelen responder en 1 día