[aw] Daily Rig File Summarizer reported incomplete result
Mantenedores costumam responder em até 1 dia
Ninguém assumiu esta issue ainda.
Avaliação
- Dificuldade
- 4/5
- Tempo estimado
- 3-5 dias
- Facilidade para iniciantes
- 12/100
- Tipo de issue
- Bug
- Clareza
- Precisa de esclarecimento
- Status de atividade
- Ativa
- Stack de tecnologia
- typescript
- Domínio
- ai, authentication
Direção de pesquisa
The failure comes from running the rig program through skills/rig/rig.ts in both URI and --server modes, which both end in AUTHENTICATION_FAILED. Start with the run log linked in the issue and the rig program that uses input: s.object({ path: s.path }), then check how scripts/haiku.integration.test.ts authenticates. It is not clear what a fix looks like, so confirm the scope with a maintainer before writing code.
Escrita pelo modelo de indexação a partir do texto da issue.
Descrição
Workflow Failure
Workflow: Daily Rig File Summarizer
Branch: main
Run: https://github.com/githubnext/rig/actions/runs/37945576194
[!WARNING]
Task Could Not Be Completed: The agent reported that the task could not be performed due to an infrastructure or tool failure.
Error details:
Could not execute the requested rig program (project-summarizer) because no authenticated Copilot runtime is available for a nested session. The only reachable server (127.0.0.1:3002, from COPILOT_SDK_URI) is the harness's own engine instance and requires a connectionToken to accept a new session, which is not exposed to this sandbox. No COPILOT_GITHUB_TOKEN or other credential is available to spawn an independent authenticated runtime via --server either.
Steps taken:
1. Fixed a schema bug in the supplied rig program (`input: { path: s.path }` must be `input: s.object({ path: s.path })` per rig's agent() API) and placed the file inside the repo tree so the `rig` module-alias import resolves (node_modules/rig symlink only resolves for files under the repo root).
2. Ran `echo '{}' | node skills/rig/rig.ts <program>` (URI transport, matching COPILOT_SDK_URI) — failed with AUTHENTICATION_FAILED.
3. Ran the same with `--server` (stdio transport, spawns a fresh bundled runtime) — also failed with AUTHENTICATION_FAILED, because no GitHub token / API key is available to that fresh process (COPILOT_GITHUB_TOKEN, ANTHROPIC_API_KEY, etc. are not present in env; COPILOT_API_KEY/COPILOT_TOKEN are dummy/offline-mode values scoped to the harness's own session, not to independently spawned copilot-sdk client processes).
4. Confirmed via the harness log (/tmp/gh-aw/sandbox/agent/logs/process-*.log) that port 3002 is the harness's own CLI server instance, and that connecting to it as a second client requires a connectionToken (env var COPILOT_CONNECTION_TOKEN) that is unset and not discoverable without probing restricted internals, which I avoided per policy.
No issue was created, since the actual project summary could not be produced. A human would need to either provide a COPILOT_GITHUB_TOKEN/connection token, or run this from an environment where `rig` can establish its own authenticated Copilot session (e.g., locally with `gh auth login` / a personal token, as done in scripts/haiku.integration.test.ts).
This is a structured incompletion signal (report_incomplete), not a real task outcome. Any other safe outputs emitted alongside this signal (e.g., comments) describe the failure state, not a completed review or action.
Action Required
Assign this issue to an agent to debug and fix the issue.
Debug with any coding agent
Use this prompt with any coding agent (GitHub Copilot, Claude, Gemini, etc.):
Debug the agentic workflow failure using https://raw.githubusercontent.com/github/gh-aw/main/debug.md
The failed workflow run is at https://github.com/githubnext/rig/actions/runs/37945576194
Manually invoke the agent
Debug this workflow failure using your favorite Agent CLI and the agentic-workflows prompt.
- Start your agent
- Load the
agentic-workflowsskill from.github/skills/agentic-workflows/SKILL.mdor https://github.com/github/gh-aw/blob/main/.github/skills/agentic-workflows/SKILL.md - Type
debug the agentic workflow daily-rig-file-summarizer failure in https://github.com/githubnext/rig/actions/runs/37945576194
[!TIP]
Stop reporting this workflow as a failure
To stop a workflow from creating failure issues, set
report-failure-as-issue: falsein its frontmatter:safe-outputs: report-failure-as-issue: false
Generated from Daily Rig File Summarizer · copilot · 117.1 AIC · ◷
- expires on Oct 16, 2026, 2:48 PM UTC
- Linguagem predominante
- TypeScript
- Estrelas
- 13
- Forks
- 0
- Merge médio
- 1h 40min
- PRs com merge (30d)
- 26
Preparar o ambiente
Este projeto não oferece contêiner de desenvolvimento, Dockerfile nem guia de contribuição, então a configuração fica por sua conta: comece pelo README e veja nosso guia da primeira contribuição para os passos gerais.
Primeiros passos
- Leia a issue inteira e depois o guia de contribuição do projeto.
- Comente na issue dizendo que vai assumir — evita que duas pessoas façam o mesmo trabalho.
- Faça um fork do repositório e trabalhe em uma branch.
- Abra um pull request que referencie o número da issue.
Mais de githubnext/rig
-
agentic-workflows
Dificuldade 4/5 3-5 dias Facilidade para iniciantes 45/100
githubnext/rig#625 ·
Mantenedores costumam responder em até 1 dia
-
ai-agent automation
Dificuldade 1/5 Menos de uma hora Facilidade para iniciantes 15/100
githubnext/rig#624 ·
Mantenedores costumam responder em até 1 dia
-
ai-agent automation
Dificuldade 5/5 Mais de uma semana Facilidade para iniciantes 1/100
githubnext/rig#623 ·
Mantenedores costumam responder em até 1 dia
-
agentic-workflows
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 28/100
githubnext/rig#622 ·
Mantenedores costumam responder em até 1 dia
-
ai-agent automation
Dificuldade 4/5 1-2 dias Facilidade para iniciantes 45/100
githubnext/rig#621 ·
Mantenedores costumam responder em até 1 dia
Todas as issues de githubnext/rig
Issues semelhantes
-
bug help wanted
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 82/100
Mantenedores costumam responder em até 1 dia
-
agent-task risk:low
Dificuldade 1/5 1-3 horas Facilidade para iniciantes 88/100
guyellis/http-status-check#512 ·
Mantenedores costumam responder em até 1 dia
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 75/100
microsoft/playwright#43327 ·
Mantenedores costumam responder em até 1 dia
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 78/100
microsoft/TypeScript#64758 ·
Mantenedores costumam responder em até 1 dia
-
enhancement
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 65/100
opensearch-project/OpenSearch-Dashboards#12937 ·
Mantenedores costumam responder em até 2 dias