[aw] Security Guard failed

[github-actions]

Workflow Failure

Workflow: Security Guard
Branch: copilot/fix-duplicate-token-usage-code
Run: https://github.com/github/gh-aw-firewall/actions/runs/26260067256
Pull Request: #3566

⚠️ Engine Failure: The claude engine terminated unexpectedly.

Last agent output:

2026-05-22T00:11:20.018Z [DEBUG] MCP server "safeoutputs": HTTP connection closed after 35s (cleanly)
2026-05-22T00:11:20.019Z [DEBUG] MCP server "safeoutputs": Cleared connection cache for reconnection
2026-05-22T00:11:20.022Z [DEBUG] LSP server manager shut down successfully
2026-05-22T00:11:20.022Z [DEBUG] Cleaned up session snapshot: /home/runner/.claude/shell-snapshots/snapshot-bash-1779408662369-h64sq0.sh
2026-05-22T00:11:20.022Z [DEBUG] MCP server "safeoutputs": HTTP connection dropped after 35s uptime
2026-05-22T00:11:20.022Z [DEBUG] MCP server "safeoutputs": Connection error: The operation was aborted.
2026-05-22T00:11:20.022Z [DEBUG] MCP server "safeoutputs": Terminal connection error 1/3
2026-05-22T00:11:20.022Z [DEBUG] MCP server "safeoutputs": HTTP connection dropped after 35s uptime
2026-05-22T00:11:20.022Z [DEBUG] MCP server "safeoutputs": Connection error: The operation was aborted.
2026-05-22T00:11:20.022Z [DEBUG] MCP server "safeoutputs": Terminal connection error 2/3

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-firewall/actions/runs/26260067256

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 prompt from .github/agents/agentic-workflows.agent.md or https://github.com/github/gh-aw/blob/main/.github/agents/agentic-workflows.agent.md
• Type debug the agentic workflow security-guard failure in https://github.com/github/gh-aw-firewall/actions/runs/26260067256

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 Security Guard · ● 442.7K · ◷

• expires on May 29, 2026, 12:11 AM UTC

[github-actions]

Agent job 26260025513 failed.

⚠️ Engine Failure: The claude engine terminated unexpectedly.

Last agent output:

{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01ABSma4CyVfzG2buesUA6RY","type":"tool_result","content":"fatal: invalid object name 'main'.","is_error":false}]},"parent_tool_use_id":null,"session_id":"17565ad9-6c05-4101-ab37-3435d55f6eda","uuid":"79041251-4c55-4f69-9b75-7f9b08abf8be","timestamp":"2026-05-22T00:11:31.933Z","tool_use_result":{"stdout":"fatal: invalid object name 'main'.","stderr":"","interrupted":false,"isImage":false,"returnCodeInterpretation":"No matches found","noOutputExpected":false}}
2026-05-22T00:11:31.934Z [DEBUG] LSP Diagnostics: getLSPDiagnosticAttachments called
2026-05-22T00:11:31.934Z [DEBUG] LSP Diagnostics: Checking registry - 0 pending
2026-05-22T00:11:31.934Z [DEBUG] Hooks: Found 0 total hooks in registry
2026-05-22T00:11:31.934Z [DEBUG] Hooks: checkForNewResponses returning 0 responses
{"type":"result","subtype":"error_max_turns","duration_ms":44210,"duration_api_ms":43861,"is_error":true,"num_turns":4,"stop_reason":"tool_use","session_id":"17565ad9-6c05-4101-ab37-3435d55f6eda","total_cost_usd":0.16331295,"usage":{"input_tokens":2213,"cache_creation_input_tokens":21627,"cache_read_input_tokens":99849,"output_tokens":2312,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":21627},"inference_geo":"","iterations":[],"speed":"standard"},"modelUsage":{"claude-sonnet-4-5":{"inputTokens":5804,"outputTokens":2323,"cacheReadInputTokens":99849,"cacheCreationInputTokens":21627,"webSearchRequests":0,"costUSD":0.16331295,"contextWindow":200000,"maxOutputTokens":32000}},"permission_denials":[],"terminal_reason":"max_turns","fast_mode_state":"off","uuid":"acba8a31-f716-4be7-86f4-19bad7a4be09","errors":["Reached maximum number of turns (3)"]}
2026-05-22T00:11:31.936Z [DEBUG] MCP server "safeoutputs": HTTP connection closed after 44s (cleanly)
2026-05-22T00:11:31.936Z [DEBUG] MCP server "safeoutputs": Cleared connection cache for reconnection
2026-05-22T00:11:31.939Z [DEBUG] LSP server manager shut down successfully
2026-05-22T00:11:31.939Z [DEBUG] Cleaned up session snapshot: /home/runner/.claude/shell-snapshots/snapshot-bash-1779408666858-r5w748.sh

Generated from Security Guard · ● 280.2K · ◷

[github-actions]

Agent job 26262311829 failed.

⚠️ Engine Failure: The claude engine terminated unexpectedly.

Last agent output:

{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01TY6kAp2GChQKAt32ytG6SA","type":"tool_result","content":"'use strict';\n\nconst { ET_WARNING_THRESHOLDS } = require('./effective-token-guard');\nconst { parsePositiveInteger } = require('./guard-utils');\n\nconst TIMEOUT_STEERING_MESSAGES = {\n  80: 'You have used 80% of your allotted run time. Begin planning to wrap up your current work.',\n  90: 'You have used 90% of your allotted run time. Complete your current task and prepare final output.',\n  95: 'You have used 95% of your allotted run time. Finalize and submit your work now.',\n  99: 'You have used 99% of your allotted run time. You are about to time out. Submit immediately.',\n};\n\nfunction createTimeoutSteeringState(configKey = null, startTimeMs = Date.now()) {\n  return {\n    configKey,\n    startTimeMs,\n    emittedThresholds: new Set(),\n    uninjectedThresholds: new Set(),\n  };\n}\n\nlet timeoutSteeringState = createTimeoutSteeringState();\n\nconst timeoutSteeringConfigCache = {\n  rawMinutes: undefined,\n  parsedMinutes: null,\n};\n\nfunction getTimeoutSteeringConfig() {\n  const rawMinutes = process.env.AWF_AGENT_TIMEOUT_MINUTES;\n  if (timeoutSteeringConfigCache.rawMinutes === rawMinutes) {\n    return timeoutSteeringConfigCache.parsedMinutes;\n  }\n  timeoutSteeringConfigCache.rawMinutes = rawMinutes;\n  timeoutSteeringConfigCache.parsedMinutes = parsePositiveInteger(rawMinutes);\n  return timeoutSteeringConfigCache.parsedMinutes;\n}\n\nfunction getTimeoutSteeringState(timeoutMinutes) {\n  if (!timeoutMinutes) return null;","is_error":false}]},"parent_tool_use_id":null,"session_id":"64037eaf-8a42-4045-9e6c-0c407c2cb688","uuid":"eed7f361-4a4d-4f3a-9a41-4c39641391aa","timestamp":"2026-05-22T01:07:08.791Z","tool_use_result":{"stdout":"'use strict';\n\nconst { ET_WARNING_THRESHOLDS } = require('./effective-token-guard');\nconst { parsePositiveInteger } = require('./guard-utils');\n\nconst TIMEOUT_STEERING_MESSAGES = {\n  80: 'You have used 80% of your allotted run time. Begin planning to wrap up your current work.',\n  90: 'You have used 90% of your allotted run time. Complete your current task and prepare final output.',\n  95: 'You have used 95% of your allotted run time. Finalize and submit your work now.',\n  99: 'You have used 99% of your allotted run time. You are about to time out. Submit immediately.',\n};\n\nfunction createTimeoutSteeringState(configKey = null, startTimeMs = Date.now()) {\n  return {\n    configKey,\n    startTimeMs,\n    emittedThresholds: new Set(),\n    uninjectedThresholds: new Set(),\n  };\n}\n\nlet timeoutSteeringState = createTimeoutSteeringState();\n\nconst timeoutSteeringConfigCache = {\n  rawMinutes: undefined,\n  parsedMinutes: null,\n};\n\nfunction getTimeoutSteeringConfig() {\n  const rawMinutes = process.env.AWF_AGENT_TIMEOUT_MINUTES;\n  if (timeoutSteeringConfigCache.rawMinutes === rawMinutes) {\n    return timeoutSteeringConfigCache.parsedMinutes;\n  }\n  timeoutSteeringConfigCache.rawMinutes = rawMinutes;\n  timeoutSteeringConfigCache.parsedMinutes = parsePositiveInteger(rawMinutes);\n  return timeoutSteeringConfigCache.parsedMinutes;\n}\n\nfunction getTimeoutSteeringState(timeoutMinutes) {\n  if (!timeoutMinutes) return null;","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false}}
2026-05-22T01:07:08.793Z [DEBUG] LSP Diagnostics: getLSPDiagnosticAttachments called
2026-05-22T01:07:08.793Z [DEBUG] LSP Diagnostics: Checking registry - 0 pending
2026-05-22T01:07:08.793Z [DEBUG] Hooks: Found 0 total hooks in registry
2026-05-22T01:07:08.793Z [DEBUG] Hooks: checkForNewResponses returning 0 responses
{"type":"result","subtype":"error_max_turns","duration_ms":68758,"duration_api_ms":68381,"is_error":true,"num_turns":4,"stop_reason":"tool_use","session_id":"64037eaf-8a42-4045-9e6c-0c407c2cb688","total_cost_usd":0.26665215,"usage":{"input_tokens":23,"cache_creation_input_tokens":47269,"cache_read_input_tokens":79348,"output_tokens":3639,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":47269},"inference_geo":"","iterations":[],"speed":"standard"},"modelUsage":{"claude-sonnet-4-5":{"inputTokens":3613,"outputTokens":3650,"cacheReadInputTokens":79348,"cacheCreationInputTokens":47269,"webSearchRequests":0,"costUSD":0.26665215,"contextWindow":200000,"maxOutputTokens":32000}},"permission_denials":[],"terminal_reason":"max_turns","fast_mode_state":"off","uuid":"199412d7-6c87-4a55-bc3c-4fa5d6c7ce00","errors":["Reached maximum number of turns (3)"]}
2026-05-22T01:07:08.795Z [DEBUG] MCP server "safeoutputs": HTTP connection closed after 68s (cleanly)
2026-05-22T01:07:08.795Z [DEBUG] MCP server "safeoutputs": Cleared connection cache for reconnection
2026-05-22T01:07:08.797Z [DEBUG] LSP server manager shut down successfully
2026-05-22T01:07:08.798Z [DEBUG] Cleaned up session snapshot: /home/runner/.claude/shell-snapshots/snapshot-bash-1779411990423-fi3v87.sh

Generated from Security Guard · ● 440.5K · ◷