[rig-summarizer] Daily file summary — 2026-10-24
Los mantenedores suelen responder en 1 día
Nadie ha tomado este issue todavía.
Evaluación
- Dificultad
- 1/5
- Tiempo estimado
- Menos de una hora
- Aptitud para principiantes
- 1/100
- Tipo de issue
- Documentación
- Claridad
- Necesita aclaración
- Estado de actividad
- Activo
- Stack tecnológico
- typescript
- Área
- tooling
Línea de trabajo
This issue contains an automatically generated file summary, but does not request a change or identify a task. Start by checking the repository's open issues for a follow-up request tied to this summary; done would require a specific change and acceptance criteria.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
Global Summary
Rig is a minimal TypeScript agent harness. The core runtime (rig.ts) provides typed schemas, prompt intents, addons, workflows and a Copilot SDK runtime. Pluggable engines (Anthropic, Codex, DeepSeek, Gemini, Pi) share lifecycle helpers. The repo also has launcher/tool utilities, CI drivers and fixtures for provider integration (a three-judges scenario), and integration tests.
Individual File Summaries
| File | Summary |
|---|---|
| ./.agents/skills/rig/engines/anthropic.ts | Anthropic SDK-based engine factory with JSON-schema output and tool support. |
| ./.agents/skills/rig/engines/codex.ts | Engine adapter for the OpenAI Codex SDK, using threads and response schemas. |
| ./.agents/skills/rig/engines/deepseek.ts | Engine adapter for the DeepSeek harness SDK client. |
| ./.agents/skills/rig/engines/gemini.ts | Gemini engine that spawns a CLI subprocess and manages turns. |
| ./.agents/skills/rig/engines/pi.ts | Engine adapter for the Pi agent core, converting tools to Pi tool schemas. |
| ./.agents/skills/rig/engines/utils.ts | Shared helpers: agent lifecycle (abort and no-concurrent-turn guard), tool schema and result conversion. |
| ./.agents/skills/rig/globals.ts | Ambient workflow helpers (call, pipeline, parallel) delegating to the active workflow run. |
| ./.agents/skills/rig/launch-tool.ts | Creates a Copilot SDK tool that launches a rig program via the launcher subprocess. |
| ./.agents/skills/rig/rig.ts | Core runtime (~3.5k lines): schemas, prompt intents, addons, workflows, Copilot SDK runtime and launcher CLI. |
| ./.agents/skills/rig/run.ts | Entry point that runs the installed skill's launcher CLI. |
| ./.github/drivers/codex-fixture-mcp.ts | Driver exposing the integration fixture launcher to Codex via an MCP HTTP server. |
| ./.github/drivers/copilot-sdk-driver.ts | Copilot SDK driver that runs the rig launch tool in CI. |
| ./.github/drivers/pi-rig-extension.ts | Pi extension tool that runs the three-judges fixture and validates output. |
| ./.github/fixtures/assert-three-judges.ts | Asserts the three-judges result has the expected engine, model and judgments. |
| ./.github/fixtures/pi-gateway.ts | Loads Pi gateway provider configuration for OpenAI-compatible APIs. |
| ./.github/fixtures/provider-fixture.ts | Builds provider fixtures across Codex, DeepSeek, Gemini and Pi engines. |
| ./.github/fixtures/provider-three-judges.ts | Default export of the provider three-judges fixture. |
| ./.github/fixtures/three-judges.ts | Defines three judge agents (clarity, safety, feasibility) in a workflow. |
| ./scripts/haiku.integration.test.ts | Integration tests running haiku/sonnet/complex samples against the live Copilot SDK. |
| ./scripts/rig-launch-tool.integration.test.ts | Live integration test running the three-judge fixture via a harness-owned launch tool. |
Note: summaries are based on file headers and imports; only the first 20 files (sorted) were included.
Generated by Daily Rig File Summarizer · copilot · auto · ~14 AIC · ⌖ ~1 AIC · ⊞ 3.9K · ◷
- expires on Oct 31, 2026, 2:32 PM UTC
- Lenguaje dominante
- TypeScript
- Estrellas
- 14
- Forks
- 0
- Merge medio
- 9 h 27 min
- PR fusionados (30 d)
- 34
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 5/5 Más de una semana Aptitud para principiantes 25/100
githubnext/rig#724 ·
Los mantenedores suelen responder en 1 día
-
ai-agent automation
Dificultad 1/5 Menos de una hora Aptitud para principiantes 1/100
githubnext/rig#723 ·
Los mantenedores suelen responder en 1 día
-
agentic-workflows
Dificultad 4/5 3-5 días Aptitud para principiantes 35/100
githubnext/rig#722 ·
Los mantenedores suelen responder en 1 día
-
ai-agent automation
Dificultad 1/5 Menos de una hora Aptitud para principiantes 10/100
githubnext/rig#721 ·
Los mantenedores suelen responder en 1 día
-
agentic-workflows
Dificultad 2/5 1-3 horas Aptitud para principiantes 38/100
githubnext/rig#720 ·
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 76/100
awslabs/visual-asset-management-system#804 ·
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 70/100
restatedev/sdk-typescript#813 ·
-
bug desktop P1 session XS
Dificultad 2/5 1-3 horas Aptitud para principiantes 82/100
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 62/100
Merit-Systems/x402scan#1312 ·
-
type:bug
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
Azure/apiops-cli#331 ·
Los mantenedores suelen responder en 3 días