Kova OpenClaw Runtime Findings

Run: kova-2026-05-03T132810Z
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-2026-05-03t132810z' -- status took 10388ms, over threshold 10000ms
Evidence:
- peakRssMb: 1068.9
- cpuPercentMax: 250.4
- coldAgentTurnMs: 28659
- warmAgentTurnMs: 17847
- agentColdWarmDeltaMs: 10812
- cold provider was fast (2ms), but OpenClaw spent 28498ms before provider work.
- agent-cli: 1068.9MB RSS, 239.4% CPU
- agent-process: 1068.9MB RSS, 239.4% 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-2026-05-03t132810z' -- status took 10388ms, over threshold 10000ms. Measurements: peakRssMb: 1068.9; cpuPercentMax: 250.4; coldAgentTurnMs: 28659; warmAgentTurnMs: 17847; agentColdWarmDeltaMs: 10812; cold provider was fast (2ms), but OpenClaw spent 28498ms before provider work.; agent-cli: 1068.9MB RSS, 239.4% CPU; agent-process: 1068.9MB RSS, 239.4% 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-2026-05-03t132810z' -- status took 10388ms, over threshold 10000ms
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 1068.9 MB; max CPU 250.4%; samples 69; roles agent-cli 1068.9MB/239.4%, agent-process 1068.9MB/239.4%, command-tree 1068.9MB/250.4%, status-cli 1001.8MB/250.4%
- agent: turn 28659ms; cold/warm 28659ms/17847ms; cold-warm delta 10812ms; pre-provider 28498ms; 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-2026-05-03t132810z' -- status took 10388ms, over threshold 10000ms
- peak RSS 1068.9 MB exceeded threshold 900 MB
- agent-cli peak RSS 1068.9 MB exceeded threshold 900 MB
- agent-process peak RSS 1068.9 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 28498ms before provider work, over threshold 10000ms
- warm agent spent 17774ms before provider work, over threshold 10000ms
- warm agent turn took 17847ms, over threshold 15000ms
- cold pre-provider latency was 28498ms, over threshold 10000ms
- warm pre-provider latency was 17774ms, over threshold 10000ms
- cold provider was fast (2ms), but OpenClaw spent 28498ms 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 794 MB; max CPU 161.9%; samples 62; roles agent-cli 794MB/161.9%, agent-process 794MB/161.9%, command-tree 794MB/161.9%, status-cli 697.4MB/156.6%
- agent: turn 21613ms; cold/warm 21613ms/18811ms; cold-warm delta 2802ms; pre-provider 21496ms; 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-2026-05-03t132810z' -- status took 10027ms, over threshold 10000ms
- OpenClaw diagnostics timeline was required for profile 'diagnostic' on target kind 'local-build' but was not emitted
- cold agent spent 21496ms before provider work, over threshold 10000ms
- warm agent spent 18737ms before provider work, over threshold 10000ms
- warm agent turn took 18811ms, over threshold 15000ms
- cold pre-provider latency was 21496ms, over threshold 10000ms
- warm pre-provider latency was 18737ms, over threshold 10000ms
- cold provider was fast (2ms), but OpenClaw spent 21496ms 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 810.8 MB; max CPU 167.4%; samples 64; roles agent-cli 810.8MB/167.4%, agent-process 810.8MB/167.4%, command-tree 810.8MB/167.4%, status-cli 796.2MB/162.6%
- agent: turn 22314ms; cold/warm 22314ms/18917ms; cold-warm delta 3397ms; pre-provider 22246ms; provider 1ms; 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-2026-05-03t132810z' -- status took 10169ms, over threshold 10000ms
- OpenClaw diagnostics timeline was required for profile 'diagnostic' on target kind 'local-build' but was not emitted
- cold agent spent 22246ms before provider work, over threshold 10000ms
- warm agent spent 18846ms before provider work, over threshold 10000ms
- warm agent turn took 18917ms, over threshold 15000ms
- cold pre-provider latency was 22246ms, over threshold 10000ms
- warm pre-provider latency was 18846ms, over threshold 10000ms
- cold provider was fast (1ms), but OpenClaw spent 22246ms before provider work.
