[aw] Daily Sub-Agent Model Resolution Audit failed

Workflow Failure

Workflow: Daily Sub-Agent Model Resolution Audit
Branch: main
Run: https://github.com/github/gh-aw/actions/runs/33052587612

Warning

Invalid or Unsupported Model: The agent failed because the configured model name is invalid, unknown, or unavailable for this engine/account.

This is a configuration issue, not a transient error — retrying will not help.

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).

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.

Warning

Engine Failure: The copilot engine terminated unexpectedly.

Last agent output:

[copilot-sdk-driver] [sdk-driver] serialising SDK events to /tmp/gh-aw/sandbox/agent/logs/copilot-session-state/212937a5-fa2f-4fe7-ad7f-5052ec146422/events.jsonl
[copilot-sdk-driver] [sdk-driver] sending prompt...
{"type":"user.message","timestamp":"2026-08-27T08:10:34.203Z","data":{}}
{"type":"assistant.message","timestamp":"2026-08-27T08:10:37.506Z","data":{"content":"I’ll pull recent run artifacts, then inspect the sampled runs for sub-agent dispatches and verify any model-size mismatches against workflow declarations."}}
{"type":"tool.execution_start","timestamp":"2026-08-27T08:10:37.507Z","data":{"toolName":"task","mcpServerName":""}}
{"type":"subagent.started","timestamp":"2026-08-27T08:10:37.514Z","data":{"agentName":"general-purpose","agentDisplayName":"General Purpose Agent","toolCallId":"call_CQF5zljcYZAEs6wbAdGIW5OA"}}
{"type":"tool.execution_complete","timestamp":"2026-08-27T08:10:37.520Z","data":{"toolName":"task","mcpServerName":"","success":true,"result":{"content":"Agent started in background with agent_id: model-resolution-audit-agent. You'll be notified when it completes. Tell the user you're waiting and end your response, or continue unrelated work until notified. The agent supports multi-turn conversations — use write_agent to send follow-up messages.","detailedContent":"Prompt to general-purpose agent (model-resolution-audit-agent):\nYou are analyzing a downloaded run artifact directory for a GitHub Actions agentic workflow audit.\n\nTask:\nInspect the provided run directory and return a JSON object with these fields:\n- run_id\n- has_subagents (boolean)\n- dispatches: array of {agent_name, declared_alias_or_model, stdio_snippet}\n- token_models: array of {request_id_or_index, model}\n- mismatches: array of {agent_name, declared_alias_or_model, observed_model, classification_note}\n- notes\n\nRules:\n- Use agent-stdio.log to detect dispatches of the form <agent-name>(<model-id-or-alias>).\n- Use sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl as the authoritative observed model source.\n- Classify size using /(mini|haiku|flash|nano)/i as small, everything else as large.\n- If there are no sub-agent dispatches or no usable logs, return has_subagents=false and explain in notes.\n\nInput:\nrun_dir: /tmp/gh-aw/aw-mcp/logs/run-<id>\n\nReturn only JSON."}}}
[copilot-sdk-driver] [sdk-driver] error: Execution failed: Error: No model available. Check policy enablement under GitHub Settings > Copilot
{"type":"subagent.completed","timestamp":"2026-08-27T08:10:37.557Z","data":{"agentName":"general-purpose","toolCallId":"call_CQF5zljcYZAEs6wbAdGIW5OA"}}
{"type":"subagent.completed","timestamp":"2026-08-27T08:10:37.582Z","data":{"agentName":"general-purpose","toolCallId":"call_CQF5zljcYZAEs6wbAdGIW5OA"}}

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/github/gh-aw/actions/runs/33052587612

Manually invoke the agent

Debug this workflow failure using your favorite Agent CLI and the agentic-workflows prompt.

Start your agent
Load the agentic-workflows skill from .github/skills/agentic-workflows/SKILL.md or https://github.com/github/gh-aw/blob/main/.github/skills/agentic-workflows/SKILL.md
Type debug the agentic workflow daily-model-resolution failure in https://github.com/github/gh-aw/actions/runs/33052587612

Tip

Stop reporting this workflow as a failure

To stop a workflow from creating failure issues, set report-failure-as-issue: false in its frontmatter:

safe-outputs:
  report-failure-as-issue: false

Generated from Daily Sub-Agent Model Resolution Audit · copilot · 0.463 AIC · ◷

expires on Aug 27, 2026, 8:12 PM UTC