[rig-summarizer] Daily file summary — 2026-10-18
I maintainer di solito rispondono entro 1 giorno
Nessuno ha ancora preso questa issue.
Valutazione
- Difficoltà
- 5/5
- Tempo stimato
- Più di una settimana
- Idoneità per principianti
- 1/100
- Tipo di issue
- Documentazione
- Chiarezza
- Da chiarire
- Stato di attività
- Attiva
- Stack tecnologico
- typescript
- Ambito
- tooling
Direzione di ricerca
This is an automatically generated daily summary of repository files, not a request to change anything. No files, tests, or completion criteria are identified; first check the repository's issue list for a concrete task before attempting work.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
Global Summary
This repository is Rig, a minimal TypeScript agent harness. The core runtime (rig.ts) provides typed agent construction, prompt intents and workflows, with pluggable engines for Anthropic, Codex, DeepSeek, Gemini, Pi and Copilot. The listed files also include launcher tooling, CI fixtures and drivers for the three-judge provider integration test, and integration tests for the haiku sample and the launch tool.
Individual File Summaries
| File | Summary |
|---|---|
| ./.agents/skills/rig/engines/anthropic.ts | Anthropic engine factory built on the Anthropic SDK, with beta JSON-schema output and tool support. |
| ./.agents/skills/rig/engines/codex.ts | Codex engine adapter that runs agent turns via the Codex SDK threads and normalizes the response schema. |
| ./.agents/skills/rig/engines/deepseek.ts | DeepSeek engine adapter using the DeepSeek harness client to run agent turns. |
| ./.agents/skills/rig/engines/gemini.ts | Gemini engine that spawns the Gemini CLI as a subprocess to run agent turns. |
| ./.agents/skills/rig/engines/pi.ts | Pi engine adapter using the pi-agent-core Agent and pi-ai models, exposing tools. |
| ./.agents/skills/rig/engines/utils.ts | Shared engine helpers: turn lifecycle with abort handling and a no-concurrent-turns guard, 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 a rig program by spawning the launcher process. |
| ./.agents/skills/rig/rig.ts | Core runtime (about 3,500 lines): schemas, agents, prompt intents, workflows, addons and the launcher CLI. |
| ./.agents/skills/rig/run.ts | Small entry point that runs the installed skill's launcher CLI. |
| ./.github/drivers/codex-fixture-mcp.ts | Serves the three-judge fixture to Codex over an MCP HTTP server, launching it once. |
| ./.github/drivers/copilot-sdk-driver.ts | Copilot SDK driver that provisions the rig launch tool for integration workflows. |
| ./.github/drivers/pi-rig-extension.ts | Pi extension exposing the rig three-judge fixture as a tool and asserting its result. |
| ./.github/fixtures/assert-three-judges.ts | Assertions validating the three-judge fixture output per engine and model. |
| ./.github/fixtures/pi-gateway.ts | Builds the Pi provider and models from the harness-provisioned aw-gateway configuration. |
| ./.github/fixtures/provider-fixture.ts | Creates the provider integration fixture selecting the Codex, DeepSeek, Gemini or Pi engine from environment config. |
| ./.github/fixtures/provider-three-judges.ts | Default-exports the provider three-judge fixture. |
| ./.github/fixtures/three-judges.ts | Defines the three-judge agent workflow scoring 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 test running the three-judge fixture through the harness-owned launch tool, skipped unless enabled. |
Generated by Daily Rig File Summarizer · copilot · auto · 14.7 AIC · ⌖ 0.506 AIC · ⊞ 7.5K · ◷
- expires on Oct 25, 2026, 2:31 PM UTC
- Lingua principale
- TypeScript
- Stelle
- 14
- Fork
- 0
- Merge medio
- 9h 49m
- PR unite (30g)
- 32
Preparare l'ambiente
Questo progetto non fornisce container di sviluppo, Dockerfile né guida per i contributori, quindi l'ambiente è a tuo carico: parti dal suo README e consulta la nostra guida al primo contributo per i passaggi generali.
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di githubnext/rig
-
ai-agent automation
Difficoltà 3/5 1-2 giorni Idoneità per principianti 52/100
githubnext/rig#683 ·
I maintainer di solito rispondono entro 1 giorno
-
agentic-workflows
Difficoltà 4/5 1-2 giorni Idoneità per principianti 42/100
githubnext/rig#682 ·
I maintainer di solito rispondono entro 1 giorno
-
ai-agent automation
Difficoltà 1/5 Meno di un'ora Idoneità per principianti 1/100
githubnext/rig#681 ·
I maintainer di solito rispondono entro 1 giorno
-
agentic-workflows
Difficoltà 2/5 1-3 ore Idoneità per principianti 55/100
githubnext/rig#680 ·
I maintainer di solito rispondono entro 1 giorno
-
agentic-workflows
Difficoltà 5/5 Più di una settimana Idoneità per principianti 20/100
githubnext/rig#679 ·
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di githubnext/rig
Issue simili
-
engine-rs P3 review-deferral wasm
Difficoltà 2/5 1-3 ore Idoneità per principianti 77/100
maniator/verticopolis#1154 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 85/100
I maintainer di solito rispondono entro 1 giorno
-
Bug
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
telerik/kendo-react#3861 ·
I maintainer di solito rispondono entro 1 giorno
-
[bug]: use-mobile.ts uses pixel logic, causing UI state de-sync with Tailwind CSS rem breakpointsApertabug
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
I maintainer di solito rispondono entro 1 giorno
-
task
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100