[aw] Daily Rig Task Generator has model/endpoint mismatch
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 3/5
- 预计耗时
- 半天
- 新手友好度
- 22/100
- Issue 类型
- 缺陷
- 描述清晰度
- 需要澄清
- 活跃度
- 活跃
- 技术栈
- github-actions, markdown, yaml
- 领域
- ci-cd
调研方向
The failing workflow is .github/workflows/daily-rig-task-generator.md; its frontmatter sets the engine, model and timeout-minutes, which the issue says are the places to look. The fix depends on Copilot model policy for the repository, which the issue does not show, so first confirm which model is rejected and whether it is enabled. Done means the workflow run completes without the model-not-supported error and within its timeout.
由索引模型根据 Issue 内容生成。
描述
Workflow Failure
Workflow: Daily Rig Task Generator
Branch: main
Run: https://github.com/githubnext/rig/actions/runs/38407366470
[!WARNING]
Model Not Supported: The requested model was rejected by the provider for this request.
This may be an invalid model name, a policy or access restriction for this token/repository, or a change in provider availability. Retrying the same session will not resolve a model that remains unavailable.
How to fix this
Specify a valid model for the selected engine in the workflow frontmatter:
---
engine: copilot
model: gpt-5-mini
---
To find valid models, check your engine/provider documentation (for Copilot see supported models) and the model catalog returned for the failing token/context.
If the model previously worked with the same workflow and token type, compare the successful and failing runs' model catalogs and request context. If the catalog changed, share sanitized timestamps, repository/organization context, and Copilot service request IDs with the Copilot model-access support team. Do not share tokens.
If the error text is No model available. Check policy enablement under GitHub Settings > Copilot, the model is not disabled in the workflow but by Copilot policy. Enable the model under GitHub Settings > Copilot > Policies for the org/repo, or pick a model that is already enabled. This can also be triggered by a subagent (task tool) dispatch requesting a model that the policy does not allow, even when the main agent's model is enabled.
Failure Diagnostics
Agent job: agent
Agent job conclusion: cancelled
The model/endpoint mismatch above is the classified cause.
Only runtime metadata is shown; agent-generated text is excluded.
Agent Timed Out: The agent job exceeded the maximum allowed execution time (60 minutes).
To increase the timeout, add or update the timeout-minutes setting in your workflow's frontmatter:
---
timeout-minutes: 70
---
Action Required
Assign this issue to an agent to debug and fix the issue.
Optimize token consumption
This failure was triggered by a guardrail limit (max-turns / timeout). Use this prompt with any coding agent (GitHub Copilot, Claude, Gemini, etc.) to analyze token usage and reduce costs:
Optimize the agentic workflow token consumption using https://raw.githubusercontent.com/github/gh-aw/main/optimize.md
The workflow run is at https://github.com/githubnext/rig/actions/runs/38407366470
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/38407366470
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-task-generator failure in https://github.com/githubnext/rig/actions/runs/38407366470
[!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 Task Generator · copilot · 786.9 AIC · ◷
- expires on Oct 20, 2026, 2:48 PM UTC
- 主要语言
- TypeScript
- 星标
- 14
- 派生
- 0
- 平均合并
- 9 小时 49 分钟
- 30 天内合并 PR
- 32
环境准备
这个项目没有提供开发容器、Dockerfile 或贡献指南,环境需要你自己搭建:先看它的 README,通用步骤见我们的新手贡献指南。
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
githubnext/rig 的其他 Issue
-
agentic-workflows
难度 4/5 3-5 天 新手友好度 25/100
githubnext/rig#676 ·
维护者通常 1 天内回复
-
agentic-workflows
难度 2/5 1-3 小时 新手友好度 48/100
githubnext/rig#675 · 1 条评论 ·
维护者通常 1 天内回复
-
ai-agent automation
难度 2/5 1-3 小时 新手友好度 35/100
githubnext/rig#674 ·
维护者通常 1 天内回复
-
agentic-workflows
难度 4/5 3-5 天 新手友好度 25/100
githubnext/rig#673 ·
维护者通常 1 天内回复
-
agentic-workflows
难度 4/5 3-5 天 新手友好度 35/100
githubnext/rig#671 ·
维护者通常 1 天内回复
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 74/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 65/100
OpenPetsHQ/openpets#273 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 76/100
fritzprix/libr-agent#2161 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 83/100
blackboardsh/electrobun#581 ·
-
backlog-skill effort:xs frontend infra ready-for-agent
难度 2/5 1-3 小时 新手友好度 74/100
LucasSantana-Dev/Lucky#2862 ·
维护者通常 1 天内回复