[rig-summarizer] Daily file summary — 2026-10-30
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
- 15/100
- Tipo di issue
- Documentazione
- Chiarezza
- Da chiarire
- Stato di attività
- Attiva
- Stack tecnologico
- typescript
- Ambito
- tooling
Direzione di ricerca
This issue is an automatically generated file summary, not a specific change request. Start by reviewing the listed files, such as .agents/skills/rig/rig.ts and the fixture files under .github/fixtures; no completion criterion is stated, so ask the maintainers what work they want before proceeding.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
Global Summary
The first 20 TypeScript files (sorted) in Rig are the core runtime and its provider engines (.agents/skills/rig), CI driver and fixture code (.github/drivers, .github/fixtures), and integration tests (scripts). The core rig.ts (about 3.4k lines) provides schemas, prompt intents, addons and the Copilot SDK runtime. Separate engine adapters wrap Anthropic, Codex, DeepSeek, Gemini and Pi behind a shared lifecycle helper. The fixtures and drivers run a "three judges" workflow against each provider.
Note: summaries were produced directly from file headers and structure, not via the sub-agent delegation, because the rig launcher could not be run here.
Individual File Summaries
| File | Summary |
|---|---|
| ./.agents/skills/rig/engines/anthropic.ts | Anthropic engine adapter that builds an AgentFactory on the Anthropic SDK, with JSON-schema output and tool support. |
| ./.agents/skills/rig/engines/codex.ts | Codex engine adapter using the OpenAI Codex SDK threads, with response-schema normalization. |
| ./.agents/skills/rig/engines/deepseek.ts | DeepSeek engine adapter wrapping the DeepSeek harness client for agent turns. |
| ./.agents/skills/rig/engines/gemini.ts | Gemini engine adapter that spawns the Gemini CLI process and manages sessions. |
| ./.agents/skills/rig/engines/pi.ts | Pi engine adapter built on pi-agent-core, mapping Rig tools to Pi agent tools. |
| ./.agents/skills/rig/engines/utils.ts | Shared engine helpers: turn lifecycle with abort and concurrency guarding, 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 via the launcher process with a timeout. |
| ./.agents/skills/rig/rig.ts | Core Rig runtime: typed schemas, prompt intents, addons, workflows, Copilot SDK engine and launcher CLI. |
| ./.agents/skills/rig/run.ts | Entry script that invokes the Rig launcher CLI for the installed skill. |
| ./.github/drivers/codex-fixture-mcp.ts | Driver that runs the three-judge fixture for Codex through an HTTP MCP server and launcher. |
| ./.github/drivers/copilot-sdk-driver.ts | Copilot SDK driver that wires the Rig launch tool into a CI session using harness-provided environment. |
| ./.github/drivers/pi-rig-extension.ts | Pi extension exposing a Rig tool that runs the fixture and asserts the three-judge result. |
| ./.github/fixtures/assert-three-judges.ts | Asserts the three-judge fixture output has the expected engine, model and judgments. |
| ./.github/fixtures/pi-gateway.ts | Parses the harness-provisioned Pi aw-gateway provider config into a Pi model setup. |
| ./.github/fixtures/provider-fixture.ts | Builds the provider-specific three-judge fixture using engine, model and environment variables. |
| ./.github/fixtures/provider-three-judges.ts | Default-exports the provider fixture. |
| ./.github/fixtures/three-judges.ts | Defines the three-judge workflow (clarity, safety, feasibility) over a dummy request. |
| ./scripts/haiku.integration.test.ts | Integration tests that run the haiku, sonnet and complex samples through the launcher when a token is present. |
| ./scripts/rig-launch-tool.integration.test.ts | Live integration test running the three-judge fixture through a harness-owned launch tool. |
Generated by Daily Rig File Summarizer · copilot · auto · ~15 AIC · ⌖ ~1 AIC · ⊞ 3.9K · ◷
- expires on Nov 6, 2026, 2:32 PM UTC
- Lingua principale
- TypeScript
- Stelle
- 14
- Fork
- 0
- Merge medio
- 9h 15m
- PR unite (30g)
- 35
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
-
agentic-workflows
Difficoltà 4/5 1-2 giorni Idoneità per principianti 15/100
githubnext/rig#769 ·
I maintainer di solito rispondono entro 1 giorno
-
agentic-workflows
Difficoltà 3/5 Mezza giornata Idoneità per principianti 18/100
githubnext/rig#768 ·
I maintainer di solito rispondono entro 1 giorno
-
agentic-workflows
Difficoltà 3/5 Mezza giornata Idoneità per principianti 30/100
githubnext/rig#767 ·
I maintainer di solito rispondono entro 1 giorno
-
agentic-workflows
Difficoltà 3/5 1-2 giorni Idoneità per principianti 30/100
githubnext/rig#766 ·
I maintainer di solito rispondono entro 1 giorno
-
ai-agent automation
Difficoltà 3/5 Mezza giornata Idoneità per principianti 20/100
githubnext/rig#764 ·
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di githubnext/rig
Issue simili
-
Report: Mooz Dance SDApertacheck:passed streams:remove
Difficoltà 1/5 Meno di un'ora Idoneità per principianti 62/100
I maintainer di solito rispondono entro 1 giorno
-
bug needs triage
Difficoltà 2/5 1-3 ore Idoneità per principianti 62/100
actions/setup-node#1659 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 78/100
vercel-labs/wterm#267 ·
I maintainer di solito rispondono entro 2 giorni
-
bug
Difficoltà 2/5 1-3 ore Idoneità per principianti 75/100
microsoft/AI-Engineering-Coach#355 · 1 reazione ·
I maintainer di solito rispondono entro 4 giorni
-
level1 nsoc26
Difficoltà 2/5 1-3 ore Idoneità per principianti 70/100
GauravKarakoti/SecureFlow#1501 ·
I maintainer di solito rispondono entro 1 giorno