Kova OpenClaw Runtime Findings

Run: kova-2026-05-03T130708Z
Target: local-build:/home/runner/_work/openclaw/openclaw
Mode: execution
Platform: linux 6.5.13 (x64)

Failure Brief

Decision: FAIL
Primary blocker: agent-cold-warm-message/mock-openai-provider
Why: ocm @'kova-agent-cold-warm-message-mock-openai-provider-r1-kova-2026-05-03t130708z' -- agent --local --agent main --session-id kova-agent-cold-warm --message 'Reply with exact ASCII text KOVA_AGENT_OK only.' --thinking off --timeout 120 --json took 79507ms, over threshold 45000ms
Evidence:
- peakRssMb: 1241.5
- cpuPercentMax: 262.3
- coldAgentTurnMs: 79507
- warmAgentTurnMs: 57328
- agentColdWarmDeltaMs: 22179
- cold provider was fast (2ms), but OpenClaw spent 79332ms before provider work.
- agent-cli: 1241.5MB RSS, 262.3% CPU
- agent-process: 1241.5MB RSS, 262.3% CPU
Likely owner: OpenClaw
Paste to fixer:
Investigate OpenClaw release gate failure agent-cold-warm-message/mock-openai-provider. Kova decision was FAIL on linux-x64. Primary evidence: ocm @'kova-agent-cold-warm-message-mock-openai-provider-r1-kova-2026-05-03t130708z' -- agent --local --agent main --session-id kova-agent-cold-warm --message 'Reply with exact ASCII text KOVA_AGENT_OK only.' --thinking off --timeout 120 --json took 79507ms, over threshold 45000ms. Measurements: peakRssMb: 1241.5; cpuPercentMax: 262.3; coldAgentTurnMs: 79507; warmAgentTurnMs: 57328; agentColdWarmDeltaMs: 22179; cold provider was fast (2ms), but OpenClaw spent 79332ms before provider work.; agent-cli: 1241.5MB RSS, 262.3% CPU; agent-process: 1241.5MB RSS, 262.3% CPU. Dependency/plugin load errors were zero, so focus on startup, memory, CPU, gateway readiness, runtime deps staging, provider/model load, and UI asset initialization. Likely owner area: OpenClaw.

Recommended next scenario

Reason: ocm @'kova-agent-cold-warm-message-mock-openai-provider-r1-kova-2026-05-03t130708z' -- agent --local --agent main --session-id kova-agent-cold-warm --message 'Reply with exact ASCII text KOVA_AGENT_OK only.' --thinking off --timeout 120 --json took 79507ms, over threshold 45000ms
Command: node bin/kova.mjs run --target local-build:/home/runner/_work/openclaw/openclaw --scenario agent-cold-warm-message --state mock-openai-provider --execute --profile-on-failure --retain-on-failure --json

Scenario: agent-cold-warm-message
Result: FAIL
Cleanup: destroyed
Measurements:
- startup: listening unknown; health unknown; readiness unknown; gateway disabled; restarts 0
- resources: peak RSS 1241.5 MB; max CPU 262.3%; samples 171; roles agent-cli 1241.5MB/262.3%, agent-process 1241.5MB/262.3%, command-tree 1241.5MB/262.3%, status-cli 630.1MB/140.8%
- agent: turn 79507ms; cold/warm 79507ms/57328ms; cold-warm delta 22179ms; pre-provider 79332ms; provider 2ms; cleanup unknown; diagnosis pre-provider-stall; leaks 0
- plugins/runtime: missing deps 0; plugin failures 0; runtime deps unknown; warm restages unknown; warm reuse unknown
- diagnostics: timeline unavailable; slowest span unknown unknown; embedded traces 0; liveness warnings 0; open spans 0 (0 required); node CPU/heap/trace 0/0/0
Violations:
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r1-kova-2026-05-03t130708z' -- agent --local --agent main --session-id kova-agent-cold-warm --message 'Reply with exact ASCII text KOVA_AGENT_OK only.' --thinking off --timeout 120 --json took 79507ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r1-kova-2026-05-03t130708z' -- agent --local --agent main --session-id kova-agent-cold-warm --message 'Reply with exact ASCII text KOVA_AGENT_OK only.' --thinking off --timeout 120 --json took 57328ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r1-kova-2026-05-03t130708z' -- status took 21660ms, over threshold 10000ms
- peak RSS 1241.5 MB exceeded threshold 900 MB
- agent-cli peak RSS 1241.5 MB exceeded threshold 900 MB
- agent-process peak RSS 1241.5 MB exceeded threshold 900 MB
- OpenClaw diagnostics timeline was required for profile 'diagnostic' on target kind 'local-build' but was not emitted
- cold agent spent 79332ms before provider work, over threshold 10000ms
- warm agent spent 57213ms before provider work, over threshold 10000ms
- cold agent turn took 79507ms, over threshold 45000ms
- warm agent turn took 57328ms, over threshold 15000ms
- cold pre-provider latency was 79332ms, over threshold 10000ms
- warm pre-provider latency was 57213ms, over threshold 10000ms
- cold provider was fast (2ms), but OpenClaw spent 79332ms before provider work.

Scenario: agent-cold-warm-message
Result: FAIL
Cleanup: destroyed
Measurements:
- startup: listening unknown; health unknown; readiness unknown; gateway disabled; restarts 0
- resources: peak RSS 1229.6 MB; max CPU 176.6%; samples 170; roles agent-cli 1229.6MB/176.6%, agent-process 1229.6MB/176.6%, command-tree 1229.6MB/176.6%, status-cli 634.5MB/136.7%
- agent: turn 77243ms; cold/warm 77243ms/56453ms; cold-warm delta 20790ms; pre-provider 77091ms; provider 2ms; cleanup unknown; diagnosis pre-provider-stall; leaks 0
- plugins/runtime: missing deps 0; plugin failures 0; runtime deps unknown; warm restages unknown; warm reuse unknown
- diagnostics: timeline unavailable; slowest span unknown unknown; embedded traces 0; liveness warnings 0; open spans 0 (0 required); node CPU/heap/trace 0/0/0
Violations:
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r2-kova-2026-05-03t130708z' -- agent --local --agent main --session-id kova-agent-cold-warm --message 'Reply with exact ASCII text KOVA_AGENT_OK only.' --thinking off --timeout 120 --json took 77243ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r2-kova-2026-05-03t130708z' -- agent --local --agent main --session-id kova-agent-cold-warm --message 'Reply with exact ASCII text KOVA_AGENT_OK only.' --thinking off --timeout 120 --json took 56453ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r2-kova-2026-05-03t130708z' -- status took 23127ms, over threshold 10000ms
- peak RSS 1229.6 MB exceeded threshold 900 MB
- agent-cli peak RSS 1229.6 MB exceeded threshold 900 MB
- agent-process peak RSS 1229.6 MB exceeded threshold 900 MB
- OpenClaw diagnostics timeline was required for profile 'diagnostic' on target kind 'local-build' but was not emitted
- cold agent spent 77091ms before provider work, over threshold 10000ms
- warm agent spent 56391ms before provider work, over threshold 10000ms
- cold agent turn took 77243ms, over threshold 45000ms
- warm agent turn took 56453ms, over threshold 15000ms
- cold pre-provider latency was 77091ms, over threshold 10000ms
- warm pre-provider latency was 56391ms, over threshold 10000ms
- cold provider was fast (2ms), but OpenClaw spent 77091ms before provider work.

Scenario: agent-cold-warm-message
Result: FAIL
Cleanup: destroyed
Measurements:
- startup: listening unknown; health unknown; readiness unknown; gateway disabled; restarts 0
- resources: peak RSS 1182.1 MB; max CPU 179.4%; samples 171; roles agent-cli 1182.1MB/179.4%, agent-process 1182.1MB/179.4%, command-tree 1182.1MB/179.4%, status-cli 566.8MB/152.6%
- agent: turn 80197ms; cold/warm 80197ms/56852ms; cold-warm delta 23345ms; pre-provider 80090ms; provider 2ms; cleanup unknown; diagnosis pre-provider-stall; leaks 0
- plugins/runtime: missing deps 0; plugin failures 0; runtime deps unknown; warm restages unknown; warm reuse unknown
- diagnostics: timeline unavailable; slowest span unknown unknown; embedded traces 0; liveness warnings 0; open spans 0 (0 required); node CPU/heap/trace 0/0/0
Violations:
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r3-kova-2026-05-03t130708z' -- agent --local --agent main --session-id kova-agent-cold-warm --message 'Reply with exact ASCII text KOVA_AGENT_OK only.' --thinking off --timeout 120 --json took 80197ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r3-kova-2026-05-03t130708z' -- agent --local --agent main --session-id kova-agent-cold-warm --message 'Reply with exact ASCII text KOVA_AGENT_OK only.' --thinking off --timeout 120 --json took 56852ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r3-kova-2026-05-03t130708z' -- status took 21898ms, over threshold 10000ms
- peak RSS 1182.1 MB exceeded threshold 900 MB
- agent-cli peak RSS 1182.1 MB exceeded threshold 900 MB
- agent-process peak RSS 1182.1 MB exceeded threshold 900 MB
- OpenClaw diagnostics timeline was required for profile 'diagnostic' on target kind 'local-build' but was not emitted
- cold agent spent 80090ms before provider work, over threshold 10000ms
- warm agent spent 56760ms before provider work, over threshold 10000ms
- cold agent turn took 80197ms, over threshold 45000ms
- warm agent turn took 56852ms, over threshold 15000ms
- cold pre-provider latency was 80090ms, over threshold 10000ms
- warm pre-provider latency was 56760ms, over threshold 10000ms
- cold provider was fast (2ms), but OpenClaw spent 80090ms before provider work.
