Repository navigation
[aw] Matt Pocock Skills Reviewer engine driver failed before emitting a terminal safe output #564
Description
Activity
Agent job 37550287286 failed.
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 (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.
Error details:
engine_driver_failure Agent finished without emitting a terminal safe output; task completion could not be confirmed. Driver exit code: 1. The engine driver exited before a terminal safe output was recorded. Engine error: Requested model is not supported (model_not_supported_error)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
copilotengine terminated unexpectedly.Error details:
Driver exit code: 1Review the workflow run logs for diagnostics. Raw agent output is omitted because it may contain secrets.
Generated from Matt Pocock Skills Reviewer · ◷
Agent job 37665973547 failed.
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 (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.
Error details:
engine_driver_failure Agent finished without emitting a terminal safe output; task completion could not be confirmed. Driver exit code: 1. The engine driver exited before a terminal safe output was recorded. Engine error: Requested model is not supported (model_not_supported_error)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
copilotengine terminated unexpectedly.Error details:
Driver exit code: 1Review the workflow run logs for diagnostics. Raw agent output is omitted because it may contain secrets.
Generated from Matt Pocock Skills Reviewer · ◷
Agent job 37673893185 failed.
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 (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.
Error details:
engine_driver_failure Agent finished without emitting a terminal safe output; task completion could not be confirmed. Driver exit code: 1. The engine driver exited before a terminal safe output was recorded. Engine error: Requested model is not supported (model_not_supported_error)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
copilotengine terminated unexpectedly.Error details:
Driver exit code: 1Review the workflow run logs for diagnostics. Raw agent output is omitted because it may contain secrets.
Generated from Matt Pocock Skills Reviewer · ◷
Workflow Failure
Workflow: Matt Pocock Skills Reviewer
Branch: pelikhan-landing-svg-overflow
Run: https://github.com/githubnext/rig/actions/runs/37537326413
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:
engine_driver_failure
Agent finished without emitting a terminal safe output; task completion could not be confirmed.
Driver exit code: 1. The engine driver exited before a terminal safe output was recorded.
[copilot-harness] starting: command=/home/runner/work/_temp/gh-aw/bin/copilot maxRetries=3 initialDelayMs=5000 backoffMultiplier=2 maxDelayMs=60000 nodeVersion=v22.23.3 platform=linux
[copilot-harness] pre-flight: command is accessible and executable: /home/runner/work/_temp/gh-aw/bin/copilot
[copilot-harness] awf-reflect: fetching (apiproxy/redacted) (timeout=60000ms)
[copilot-harness] awf-reflect: saved 28711B to /tmp/gh-aw/agent/awf-reflect.json
[copilot-harness] inference routing: mode=cli configuredModel="claude-sonnet-4.6" endpoint=managed-by-copilot-cli
[copilot-harness] attempt 1: process started (pid=402)
400 The requested model is not available for integrator "agentic-workflows". Available models: [gpt-4.1 claude-fable-5.1 claude-fable-5 claude-opus-4.8-fast claude-opus-4.8 claude-opus-5.5 claude-opus-5 claude-sonnet-5.5 claude-sonnet-5 copilot-search-a copilot-search-b copilot-search-c exec-agent-a exec-agent-b exec-agent-c gpt-5.3-codex gpt-5.4-mini gpt-5.4 gpt-5.5 gpt-5.6-luna gpt-5.6-sol gpt-5.6-terra gpt-5.6-luna-utility gpt-6.1-sol gpt-6-astra gpt-6-luna gpt-6-sol grok-4.5 grok-4.6 grok-4.7 kimi-k3 mai-code-1.1-flash trajectory-compaction gpt-5-mini gpt-3.5-turbo gpt-3.5-turbo-0613 gpt-4o-mini gpt-4o-mini-2024-07-18 gpt-4 gpt-4-0613 gpt-4o gpt-4o-2024-11-20 gpt-4o-2024-05-13 gpt-4-o-preview gpt-4o-2024-08-06 claude-haiku-4.5 gpt-4.1-2025-04-14 gpt-5.2]. Verify the correct Copilot-Integration-Id header is being sent.
[copilot-harness] attempt 1: process exit event exitCode=1
[copilot-harness] attempt 1: process closed exitCode=1 duration=1s stdout=0B stderr=933B hasOutput=true
[copilot-harness] attempt 1 failed: exitCode=1 failureClass=partial_execution isCAPIError400=false isModelRoutingFailure=false isCAPIQuotaExceededError=false isInvocationCapExceeded=false apiProxyGuardRejection=none isMCPPolicyError=false isModelNotSupportedError=false isHTTP400ResponseError=false isToolCallIdSchemaError=false isNullTypeToolCallError=false isSDKSessionIdleTimeoutError=false isMCPGatewayShutdownError=false isConnectionRefusedError=false isAuthError=false isAuthenticationFailedError=false permissionDeniedCount=0 hasNumerousPermissionDenied=false hasOutput=true tokenCount=0 attemptDurationMs=1613 retriesRemaining=3
[copilot-harness] attempt 1: partial execution — will retry with --continue (attempt 2/4)
[copilot-harness] retry 1/3: sleeping 5000ms before next attempt (--continue)
[copilot-harness] retry 1/3: woke up, next delay will be 10000ms
[copilot-harness] attempt 2: process started (pid=473)
400 The requested model is not available for integrator "agentic-workflows". Available models: [gpt-4.1 claude-fable-5.1 claude-fable-5 claude-opus-4.8-fast claude-opus-4.8 claude-opus-5.5 claude-opus-5 claude-sonnet-5.5 claude-sonnet-5 copilot-search-a copilot-search-b copilot-search-c exec-agent-a exec-agent-b exec-agent-c gpt-5.3-codex gpt-5.4-mini gpt-5.4 gpt-5.5 gpt-5.6-luna gpt-5.6-sol gpt-5.6-terra gpt-5.6-luna-utility gpt-6.1-sol gpt-6-astra gpt-6-luna gpt-6-sol grok-4.5 grok-4.6 grok-4.7 kimi-k3 mai-code-1.1-flash trajectory-compaction gpt-5-mini gpt-3.5-turbo gpt-3.5-turbo-0613 gpt-4o-mini gpt-4o-mini-2024-07-18 gpt-4 gpt-4-0613 gpt-4o gpt-4o-2024-11-20 gpt-4o-2024-05-13 gpt-4-o-preview gpt-4o-2024-08-06 claude-haiku-4.5 gpt-4.1-2025-04-14 gpt-5.2]. Verify the correct Copilot-Integration-Id header is being sent.
[copilot-harness] attempt 2: process exit event exitCode=1
[copilot-harness] attempt 2: process closed exitCode=1 duration=2s stdout=0B stderr=933B hasOutput=true
[copilot-harness] attempt 2 failed: exitCode=1 failureClass=partial_execution isCAPIError400=false isModelRoutingFailure=false isCAPIQuotaExceededError=false isInvocationCapExceeded=false apiProxyGuardRejection=none isMCPPolicyError=false isModelNotSupportedError=false isHTTP400ResponseError=false isToolCallIdSchemaError=false isNullTypeToolCallError=false isSDKSessionIdleTimeoutError=false isMCPGatewayShutdownError=false isConnectionRefusedError=false isAuthError=false isAuthenticationFailedError=false permissionDeniedCount=0 hasNumerousPermissionDenied=false hasOutput=true tokenCount=0 attemptDurationMs=2341 retriesRemaining=2
[copilot-harness] attempt 2: partial execution — will retry with --continue (attempt 3/4)
[copilot-harness] retry 2/3: sleeping 10000ms before next attempt (--continue)
[copilot-harness] retry 2/3: woke up, next delay will be 20000ms
[copilot-harness] attempt 3: process started (pid=596)
400 The requested model is not available for integrator "agentic-workflows". Available models: [gpt-4.1 claude-fable-5.1 claude-fable-5 claude-opus-4.8-fast claude-opus-4.8 claude-opus-5.5 claude-opus-5 claude-sonnet-5.5 claude-sonnet-5 copilot-search-a copilot-search-b copilot-search-c exec-agent-a exec-agent-b exec-agent-c gpt-5.3-codex gpt-5.4-mini gpt-5.4 gpt-5.5 gpt-5.6-luna gpt-5.6-sol gpt-5.6-terra gpt-5.6-luna-utility gpt-6.1-sol gpt-6-astra gpt-6-luna gpt-6-sol grok-4.5 grok-4.6 grok-4.7 kimi-k3 mai-code-1.1-flash trajectory-compaction gpt-5-mini gpt-3.5-turbo gpt-3.5-turbo-0613 gpt-4o-mini gpt-4o-mini-2024-07-18 gpt-4 gpt-4-0613 gpt-4o gpt-4o-2024-11-20 gpt-4o-2024-05-13 gpt-4-o-preview gpt-4o-2024-08-06 claude-haiku-4.5 gpt-4.1-2025-04-14 gpt-5.2]. Verify the correct Copilot-Integration-Id header is being sent.
[copilot-harness] attempt 3: process exit event exitCode=1
[copilot-harness] attempt 3: process closed exitCode=1 duration=1s stdout=0B stderr=934B hasOutput=true
[copilot-harness] attempt 3 failed: exitCode=1 failureClass=partial_execution isCAPIError400=false isModelRoutingFailure=false isCAPIQuotaExceededError=false isInvocationCapExceeded=false apiProxyGuardRejection=none isMCPPolicyError=false isModelNotSupportedError=false isHTTP400ResponseError=false isToolCallIdSchemaError=false isNullTypeToolCallError=false isSDKSessionIdleTimeoutError=false isMCPGatewayShutdownError=false isConnectionRefusedError=false isAuthError=false isAuthenticationFailedError=false permissionDeniedCount=0 hasNumerousPermissionDenied=false hasOutput=true tokenCount=0 attemptDurationMs=1103 retriesRemaining=1
[copilot-harness] attempt 3: partial execution — will retry with --continue (attempt 4/4)
[copilot-harness] retry 3/3: sleeping 20000ms before next attempt (--continue)
[copilot-harness] retry 3/3: woke up, next delay will be 40000ms
[copilot-harness] attempt 4: process started (pid=767)
400 The requested model is not available for integrator "agentic-workflows". Available models: [gpt-4.1 claude-fable-5.1 claude-fable-5 claude-opus-4.8-fast claude-opus-4.8 claude-opus-5.5 claude-opus-5 claude-sonnet-5.5 claude-sonnet-5 copilot-search-a copilot-search-b copilot-search-c exec-agent-a exec-agent-b exec-agent-c gpt-5.3-codex gpt-5.4-mini gpt-5.4 gpt-5.5 gpt-5.6-luna gpt-5.6-sol gpt-5.6-terra gpt-5.6-luna-utility gpt-6.1-sol gpt-6-astra gpt-6-luna gpt-6-sol grok-4.5 grok-4.6 grok-4.7 kimi-k3 mai-code-1.1-flash trajectory-compaction gpt-5-mini gpt-3.5-turbo gpt-3.5-turbo-0613 gpt-4o-mini gpt-4o-mini-2024-07-18 gpt-4 gpt-4-0613 gpt-4o gpt-4o-2024-11-20 gpt-4o-2024-05-13 gpt-4-o-preview gpt-4o-2024-08-06 claude-haiku-4.5 gpt-4.1-2025-04-14 gpt-5.2]. Verify the correct Copilot-Integration-Id header is being sent.
[copilot-harness] attempt 4: process exit event exitCode=1
[copilot-harness] attempt 4: process closed exitCode=1 duration=1s stdout=0B stderr=934B hasOutput=true
[copilot-harness] attempt 4 failed: exitCode=1 failureClass=partial_execution isCAPIError400=false isModelRoutingFailure=false isCAPIQuotaExceededError=false isInvocationCapExceeded=false apiProxyGuardRejection=none isMCPPolicyError=false isModelNotSupportedError=false isHTTP400ResponseError=false isToolCallIdSchemaError=false isNullTypeToolCallError=false isSDKSessionIdleTimeoutError=false isMCPGatewayShutdownEr
[Content t
[Content truncated due to length]
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
copilotengine 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 mattpocock-skills-reviewer failure in https://github.com/githubnext/rig/actions/runs/37537326413Tip
Stop reporting this workflow as a failure
To stop a workflow from creating failure issues, set
report-failure-as-issue: falsein its frontmatter: