You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
[aw] Smoke Codex Auto reported incomplete result #65690
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: copilotmodel: 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.
Warning
Task Could Not Be Completed: The agent reported that the task could not be performed due to an infrastructure or tool failure.
Reasons:
Agent finished without emitting any valid safe outputs; task completion could not be confirmed.
[codex-harness] 2026-10-05T00:05:43.148Z starting: command=codex maxRetries=3 initialDelayMs=5000 backoffMultiplier=2 maxDelayMs=60000 nodeVersion=v24.21.0 platform=linux
[codex-harness] 2026-10-05T00:05:43.153Z secrets: CODEX_API_KEY=set (length=31) OPENAI_API_KEY=not set
[codex-harness] 2026-10-05T00:05:43.153Z awf-reflect: fetching (apiproxy/redacted) (timeout=60000ms)
[codex-harness] 2026-10-05T00:05:43.209Z awf-reflect: saved 32668B to /tmp/gh-aw/agent/awf-reflect.json
[codex-harness] 2026-10-05T00:05:43.210Z awf-reflect: provider=github mapped to endpoint provider=copilot baseUrl=(apiproxy/redacted)
[codex-harness] 2026-10-05T00:05:43.210Z configured OPENAI_BASE_URL from /reflect for provider=github: (apiproxy/redacted)
[codex-harness] 2026-10-05T00:05:43.211Z context-rebuild circuit breaker: enabled=true maxRebuildFactor=25 minCumulativeInputTokens=1000000 pollIntervalMs=15000
[codex-harness] 2026-10-05T00:05:43.214Z attempt 1: process started (pid=393)
[codex-harness] 2026-10-05T00:05:48.727Z attempt 1: process exit event exitCode=1
[codex-harness] 2026-10-05T00:05:48.728Z attempt 1: process closed exitCode=1 duration=5s stdout=684B stderr=454B hasOutput=true
[codex-harness] 2026-10-05T00:05:48.729Z attempt 1 failed: exitCode=1 watchdogFired=false runtimeGuardFired=false isRateLimitError=false isTokenPerMinuteRateLimitError=false isAuthenticationFailedError=false isMissingApiKeyError=false isServerError=false isInvalidModelError=true isUnsupportedModelToolsError=false isInvalidRequestError=true permissionDeniedCount=0 hasNumerousPermissionDenied=false hasOutput=true retriesRemaining=3
[codex-harness] 2026-10-05T00:05:48.730Z attempt 1: invalid/unsupported model configuration — not retrying (specify a valid engine model name in workflow frontmatter)
[codex-harness] 2026-10-05T00:05:48.730Z awf-reflect: fetching (apiproxy/redacted) (timeout=60000ms)
[codex-harness] 2026-10-05T00:05:48.739Z awf-reflect: saved 32668B to /tmp/gh-aw/agent/awf-reflect.json
[codex-harness] 2026-10-05T00:05:48.739Z done: exitCode=1 totalDuration=5s
{"type":"error","message":"{"error":{"message":"The requested model is not supported.","code":"model_not_supported","param":"model","type":"invalid_request_error"}}\n"}
{"error":{"message":"The requested model is not supported.","code":"model_not_supported","param":"model","type":"invalid_request_error"}}
The requested model is not supported.
{"type":"turn.failed","error":{"message":"{"error":{"message":"The requested model is not supported.","code":"model_not_supported","param":"model","type":"invalid_request_error"}}\n"}}
{"error":{"message":"The requested model is not supported.","code":"model_not_supported","param":"model","type":"invalid_request_error"}}
The requested model is not supported.
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.
Warning
Engine Failure: The codex engine terminated unexpectedly.
Driver exit code: 1
Last agent output:
WARNING: proceeding, even though we could not create PATH aliases: Refusing to create helper binaries under temporary dir "/tmp" (codex_home: AbsolutePathBuf("/tmp/gh-aw/mcp-config"))
2026-10-05T00:05:43.309050Z WARN codex_models_manager::model_info: Unknown model auto is used. This will use fallback model metadata.
{"type":"thread.started","thread_id":"01a10961-710c-7bd3-91d6-ea0d56cf69b6"}
2026-10-05T00:05:43.319986Z WARN codex_models_manager::model_info: Unknown model auto is used. This will use fallback model metadata.
{"type":"item.completed","item":{"id":"item_0","type":"error","message":"Model metadata for `auto` not found. Defaulting to fallback metadata; this can degrade performance and cause issues."}}
{"type":"turn.started"}
{"type":"error","message":"{\"error\":{\"message\":\"The requested model is not supported.\",\"code\":\"model_not_supported\",\"param\":\"model\",\"type\":\"invalid_request_error\"}}\n"}
{"type":"turn.failed","error":{"message":"{\"error\":{\"message\":\"The requested model is not supported.\",\"code\":\"model_not_supported\",\"param\":\"model\",\"type\":\"invalid_request_error\"}}\n"}}
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/37246028670
Manually invoke the agent
Debug this workflow failure using your favorite Agent CLI and the agentic-workflows prompt.
Workflow Failure
Workflow: Smoke Codex Auto
Branch: main
Run: https://github.com/github/gh-aw/actions/runs/37246028670
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:
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 (tasktool) dispatch requesting a model that the policy does not allow, even when the main agent's model is enabled.Warning
Task Could Not Be Completed: The agent reported that the task could not be performed due to an infrastructure or tool failure.
Reasons:
Agent finished without emitting any valid safe outputs; task completion could not be confirmed.
[codex-harness] 2026-10-05T00:05:43.148Z starting: command=codex maxRetries=3 initialDelayMs=5000 backoffMultiplier=2 maxDelayMs=60000 nodeVersion=v24.21.0 platform=linux
[codex-harness] 2026-10-05T00:05:43.153Z secrets: CODEX_API_KEY=set (length=31) OPENAI_API_KEY=not set
[codex-harness] 2026-10-05T00:05:43.153Z awf-reflect: fetching (apiproxy/redacted) (timeout=60000ms)
[codex-harness] 2026-10-05T00:05:43.209Z awf-reflect: saved 32668B to /tmp/gh-aw/agent/awf-reflect.json
[codex-harness] 2026-10-05T00:05:43.210Z awf-reflect: provider=github mapped to endpoint provider=copilot baseUrl=(apiproxy/redacted)
[codex-harness] 2026-10-05T00:05:43.210Z configured OPENAI_BASE_URL from /reflect for provider=github: (apiproxy/redacted)
[codex-harness] 2026-10-05T00:05:43.211Z context-rebuild circuit breaker: enabled=true maxRebuildFactor=25 minCumulativeInputTokens=1000000 pollIntervalMs=15000
[codex-harness] 2026-10-05T00:05:43.214Z attempt 1: process started (pid=393)
[codex-harness] 2026-10-05T00:05:48.727Z attempt 1: process exit event exitCode=1
[codex-harness] 2026-10-05T00:05:48.728Z attempt 1: process closed exitCode=1 duration=5s stdout=684B stderr=454B hasOutput=true
[codex-harness] 2026-10-05T00:05:48.729Z attempt 1 failed: exitCode=1 watchdogFired=false runtimeGuardFired=false isRateLimitError=false isTokenPerMinuteRateLimitError=false isAuthenticationFailedError=false isMissingApiKeyError=false isServerError=false isInvalidModelError=true isUnsupportedModelToolsError=false isInvalidRequestError=true permissionDeniedCount=0 hasNumerousPermissionDenied=false hasOutput=true retriesRemaining=3
[codex-harness] 2026-10-05T00:05:48.730Z attempt 1: invalid/unsupported model configuration — not retrying (specify a valid engine model name in workflow frontmatter)
[codex-harness] 2026-10-05T00:05:48.730Z awf-reflect: fetching (apiproxy/redacted) (timeout=60000ms)
[codex-harness] 2026-10-05T00:05:48.739Z awf-reflect: saved 32668B to /tmp/gh-aw/agent/awf-reflect.json
[codex-harness] 2026-10-05T00:05:48.739Z done: exitCode=1 totalDuration=5s
{"type":"error","message":"{"error":{"message":"The requested model is not supported.","code":"model_not_supported","param":"model","type":"invalid_request_error"}}\n"}
{"error":{"message":"The requested model is not supported.","code":"model_not_supported","param":"model","type":"invalid_request_error"}}
The requested model is not supported.
{"type":"turn.failed","error":{"message":"{"error":{"message":"The requested model is not supported.","code":"model_not_supported","param":"model","type":"invalid_request_error"}}\n"}}
{"error":{"message":"The requested model is not supported.","code":"model_not_supported","param":"model","type":"invalid_request_error"}}
The requested model is not supported.
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.Warning
Engine Failure: The
codexengine terminated unexpectedly.Driver exit code: 1
Last agent output:
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.):
Manually invoke the agent
Debug this workflow failure using your favorite Agent CLI and the
agentic-workflowsprompt.agentic-workflowsskill from.github/skills/agentic-workflows/SKILL.mdor https://github.com/github/gh-aw/blob/main/.github/skills/agentic-workflows/SKILL.mddebug the agentic workflow smoke-codex-auto failure in https://github.com/github/gh-aw/actions/runs/37246028670Tip
Stop reporting this workflow as a failure
To stop a workflow from creating failure issues, set
report-failure-as-issue: falsein its frontmatter: