Repository navigation
[aw] Smoke Service Ports reported incomplete result #65721
Description
Workflow Failure
Workflow: Smoke Service Ports
Branch: main
Run: https://github.com/github/gh-aw/actions/runs/37249403628
Warning
Task Could Not Be Completed: The agent reported that the task could not be performed due to an infrastructure or tool failure.
Reasons:
-
infrastructure_error
All 2 Pi provider requests failed before safe outputs were emitted. Last provider failure: HTTP 400; message="{"message":"model \"gpt-5.3-codex\" is not accessible via the /chat/completions endpoint","code":"unsupported_api_for_model"}".
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.
Failure Diagnostics
Failing step: Execute Pi CLI
Warning
Engine Failure: The pi engine terminated unexpectedly.
Driver exit code: 1
Last agent output:
{"type":"message_end","message":{"role":"assistant","content":[],"api":"openai-completions","provider":"aw-gateway","model":"gpt-5.3-codex","usage":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"totalTokens":0,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"error","timestamp":1791161897444,"errorMessage":"400: {\"message\":\"model \\\"gpt-5.3-codex\\\" is not accessible via the /chat/completions endpoint\",\"code\":\"unsupported_api_for_model\"}","thinkingLevel":"medium"}}
{"type":"turn_end","message":{"role":"assistant","content":[],"api":"openai-completions","provider":"aw-gateway","model":"gpt-5.3-codex","usage":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"totalTokens":0,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"error","timestamp":1791161897444,"errorMessage":"400: {\"message\":\"model \\\"gpt-5.3-codex\\\" is not accessible via the /chat/completions endpoint\",\"code\":\"unsupported_api_for_model\"}","thinkingLevel":"medium"},"toolResults":[]}
{"type":"agent_end","messages":[{"role":"user","content":[{"type":"text","text":"⚠️ 5 minute(s) remaining. Please wrap up your current task and start writing your final output."}],"timestamp":1791161897429},{"role":"assistant","content":[],"api":"openai-completions","provider":"aw-gateway","model":"gpt-5.3-codex","usage":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"totalTokens":0,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"error","timestamp":1791161897444,"errorMessage":"400: {\"message\":\"model \\\"gpt-5.3-codex\\\" is not accessible via the /chat/completions endpoint\",\"code\":\"unsupported_api_for_model\"}","thinkingLevel":"medium"}],"willRetry":false}
[gh-aw/pi-provider] 2026-10-05T00:58:17.910Z awf-reflect: fetching http://api-proxy:10000/reflect (timeout=60000ms)
[gh-aw/pi-provider] 2026-10-05T00:58:17.917Z awf-reflect: saved 32668B to /tmp/gh-aw/agent/awf-reflect.json
[gh-aw/pi-provider] 2026-10-05T00:58:18.174Z report_incomplete emitted via safeoutputs CLI: /home/runner/work/_temp/gh-aw/safeoutputs/outputs.jsonl
{"type":"agent_settled"}
[pi-harness] attempt 1: process exit event exitCode=1
[pi-harness] attempt 1: process closed exitCode=1 duration=4s stdout=99777B stderr=720B hasOutput=true
{"type":"result","num_turns":2,"usage":{"input_tokens":0,"output_tokens":0,"cache_read_input_tokens":0,"cache_creation_input_tokens":0,"total_tokens":0,"input_tokens_include_cache":false}}
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/37249403628
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 smoke-service-ports failure in https://github.com/github/gh-aw/actions/runs/37249403628
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: falseGenerated from Smoke Service Ports · ◷
- expires on Oct 5, 2026, 1:01 PM UTC
Activity
github-actions commentedon Oct 5, 2026
This issue was automatically closed because it expired on 2026-10-05T13:01:10.694Z.