[rig-summarizer] Daily file summary — 2026-10-16
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
- ai-infra-agents
Direzione di ricerca
This issue contains generated summaries of Rig files but does not request a change or define an outcome. If taking it up, first identify whether any listed summary is inaccurate or what documentation work is intended; there is no completion criterion or test to run in the issue.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
Global Summary
Rig is a minimal TypeScript agent harness. The core runtime (.agents/skills/rig/rig.ts, ~3.5k lines) provides typed schemas, prompt intents, sub-agent delegation and workflows on top of the Copilot SDK. Around it are pluggable provider engines (Anthropic, Codex, DeepSeek, Gemini, Pi), shared engine utilities, a launch tool and runner, CI drivers and fixtures for a "three judges" provider integration test, and vitest integration tests for the samples and launch tool.
Individual File Summaries
| File | Summary |
|---|---|
| ./.agents/skills/rig/engines/anthropic.ts | Anthropic engine factory for Rig using the Anthropic SDK, with JSON-schema output and tool support, configurable max tokens and iterations. |
| ./.agents/skills/rig/engines/codex.ts | Codex engine factory using the OpenAI Codex SDK threads; it rejects Rig tools. |
| ./.agents/skills/rig/engines/deepseek.ts | DeepSeek engine factory using the DeepSeek harness client; it rejects Rig tools and takes a string system message. |
| ./.agents/skills/rig/engines/gemini.ts | Gemini engine that spawns the Gemini CLI as a subprocess, with session ids, approval modes and JSON output parsing. |
| ./.agents/skills/rig/engines/pi.ts | Pi engine factory wrapping the Pi agent core with built-in models and Rig tool adaptation. |
| ./.agents/skills/rig/engines/utils.ts | Shared engine helpers: agent lifecycle (abortable, non-concurrent turns) and 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 run_rig Copilot tool that runs a trusted Rig program through the launcher as a subprocess with a timeout. |
| ./.agents/skills/rig/rig.ts | Core runtime with typed schemas, prompt intents, agent and sub-agent delegation, workflows and the Copilot SDK engine. |
| ./.agents/skills/rig/run.ts | Entry point that runs the Rig launcher CLI when executed directly. |
| ./.github/drivers/codex-fixture-mcp.ts | Local MCP server and launcher that runs the three-judge fixture once for the Codex engine. |
| ./.github/drivers/copilot-sdk-driver.ts | Copilot SDK driver that configures the provider, tools and permissions for the workflow and exposes the Rig launch tool. |
| ./.github/drivers/pi-rig-extension.ts | Pi extension tool that runs the Rig fixture and validates the result with the three-judge assertions. |
| ./.github/fixtures/assert-three-judges.ts | Assertions that validate three-judge fixture output (engine, model, criteria decisions) per provider. |
| ./.github/fixtures/pi-gateway.ts | Builds the Pi gateway provider and models from harness-provisioned config. |
| ./.github/fixtures/provider-fixture.ts | Selects and configures the engine (Codex, DeepSeek, Gemini, Pi) for the three-judge fixture from environment variables. |
| ./.github/fixtures/provider-three-judges.ts | Default export of the provider fixture created from the environment. |
| ./.github/fixtures/three-judges.ts | Defines the three-judge workflow evaluating a dummy request on clarity, safety and feasibility. |
| ./scripts/haiku.integration.test.ts | Vitest integration tests that run the haiku, sonnet and complex samples through the launcher when credentials are available. |
| ./scripts/rig-launch-tool.integration.test.ts | Opt-in live test running the three-judge fixture through the harness-owned launch tool without credential env vars. |
Generated by Daily Rig File Summarizer · copilot · auto · 15.3 AIC · ⌖ 0.507 AIC · ⊞ 7.5K · ◷
- expires on Oct 23, 2026, 2:36 PM UTC
- Lingua principale
- TypeScript
- Stelle
- 14
- Fork
- 0
- Merge medio
- 3h 38m
- PR unite (30g)
- 29
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 25/100
githubnext/rig#666 ·
I maintainer di solito rispondono entro 1 giorno
-
agentic-workflows
Difficoltà 4/5 3-5 giorni Idoneità per principianti 38/100
githubnext/rig#665 ·
I maintainer di solito rispondono entro 1 giorno
-
ai-agent automation
Difficoltà 1/5 Meno di un'ora Idoneità per principianti 15/100
githubnext/rig#664 ·
I maintainer di solito rispondono entro 1 giorno
-
ai-agent automation
Difficoltà 4/5 3-5 giorni Idoneità per principianti 42/100
githubnext/rig#663 ·
I maintainer di solito rispondono entro 1 giorno
-
agentic-workflows
Difficoltà 3/5 1-2 giorni Idoneità per principianti 55/100
githubnext/rig#662 ·
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di githubnext/rig
Issue simili
-
backend priority:P3 privacy-fix
Difficoltà 2/5 1-3 ore Idoneità per principianti 78/100
I maintainer di solito rispondono entro 1 giorno
-
[Bug]: 【优化】对话消息底部增加发送时间展示Apertabug desktop v3 windows
Difficoltà 2/5 1-3 ore Idoneità per principianti 65/100
esengine/DeepSeek-Reasonix#13697 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
area:security documentation effort:S priority:P2
Difficoltà 2/5 1-3 ore Idoneità per principianti 65/100
I maintainer di solito rispondono entro 1 giorno
-
app:web meta:ops
Difficoltà 2/5 Mezza giornata Idoneità per principianti 78/100
osu-tournament-rating/otr#1113 ·
I maintainer di solito rispondono entro 1 giorno
-
bug
Difficoltà 2/5 1-3 ore Idoneità per principianti 82/100