Kova OpenClaw Runtime Findings

Run: kova-2026-05-03T130721Z
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-2026-05-03t130721z' -- 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 49609ms, over threshold 45000ms
Evidence:
- peakRssMb: 985.6
- cpuPercentMax: 173.5
- coldAgentTurnMs: 49609
- warmAgentTurnMs: 26813
- agentColdWarmDeltaMs: 22796
- cold provider was fast (2ms), but OpenClaw spent 49388ms before provider work.
- agent-cli: 985.6MB RSS, 173.5% CPU
- agent-process: 985.6MB RSS, 173.5% 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-2026-05-03t130721z' -- 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 49609ms, over threshold 45000ms. Measurements: peakRssMb: 985.6; cpuPercentMax: 173.5; coldAgentTurnMs: 49609; warmAgentTurnMs: 26813; agentColdWarmDeltaMs: 22796; cold provider was fast (2ms), but OpenClaw spent 49388ms before provider work.; agent-cli: 985.6MB RSS, 173.5% CPU; agent-process: 985.6MB RSS, 173.5% 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-2026-05-03t130721z' -- 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 49609ms, 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 985.6 MB; max CPU 173.5%; samples 91; roles agent-cli 985.6MB/173.5%, agent-process 985.6MB/173.5%, command-tree 985.6MB/173.5%, status-cli 586.8MB/144.7%
- agent: turn 49609ms; cold/warm 49609ms/26813ms; cold-warm delta 22796ms; pre-provider 49388ms; 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-2026-05-03t130721z' -- 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 49609ms, over threshold 45000ms
- peak RSS 985.6 MB exceeded threshold 900 MB
- agent-cli peak RSS 985.6 MB exceeded threshold 900 MB
- agent-process peak RSS 985.6 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 49388ms before provider work, over threshold 10000ms
- warm agent spent 26702ms before provider work, over threshold 10000ms
- cold agent turn took 49609ms, over threshold 45000ms
- warm agent turn took 26813ms, over threshold 15000ms
- cold pre-provider latency was 49388ms, over threshold 10000ms
- warm pre-provider latency was 26702ms, over threshold 10000ms
- cold provider was fast (2ms), but OpenClaw spent 49388ms 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 995.5 MB; max CPU 173%; samples 88; roles agent-cli 995.5MB/173%, agent-process 995.5MB/173%, command-tree 995.5MB/173%, status-cli 579.6MB/145.7%
- agent: turn 48069ms; cold/warm 48069ms/25443ms; cold-warm delta 22626ms; pre-provider 47947ms; 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-2026-05-03t130721z' -- 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 48069ms, over threshold 45000ms
- peak RSS 995.5 MB exceeded threshold 900 MB
- agent-cli peak RSS 995.5 MB exceeded threshold 900 MB
- agent-process peak RSS 995.5 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 47947ms before provider work, over threshold 10000ms
- warm agent spent 25364ms before provider work, over threshold 10000ms
- cold agent turn took 48069ms, over threshold 45000ms
- warm agent turn took 25443ms, over threshold 15000ms
- cold pre-provider latency was 47947ms, over threshold 10000ms
- warm pre-provider latency was 25364ms, over threshold 10000ms
- cold provider was fast (2ms), but OpenClaw spent 47947ms 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 1024.3 MB; max CPU 157.5%; samples 86; roles agent-cli 1024.3MB/157.5%, agent-process 1024.3MB/157.5%, command-tree 1024.3MB/157.5%, status-cli 580.2MB/144.7%
- agent: turn 46585ms; cold/warm 46585ms/25069ms; cold-warm delta 21516ms; pre-provider 46464ms; 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-2026-05-03t130721z' -- 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 46585ms, over threshold 45000ms
- peak RSS 1024.3 MB exceeded threshold 900 MB
- agent-cli peak RSS 1024.3 MB exceeded threshold 900 MB
- agent-process peak RSS 1024.3 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 46464ms before provider work, over threshold 10000ms
- warm agent spent 24976ms before provider work, over threshold 10000ms
- cold agent turn took 46585ms, over threshold 45000ms
- warm agent turn took 25069ms, over threshold 15000ms
- cold pre-provider latency was 46464ms, over threshold 10000ms
- warm pre-provider latency was 24976ms, over threshold 10000ms
- cold provider was fast (2ms), but OpenClaw spent 46464ms before provider work.
