Kova OpenClaw Runtime Findings

Run: kova-2026-05-03T130718Z
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-2026-05-03t130718z' -- 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 71210ms, over threshold 45000ms
Evidence:
- peakRssMb: 1124.5
- cpuPercentMax: 171.6
- coldAgentTurnMs: 71210
- warmAgentTurnMs: 48668
- agentColdWarmDeltaMs: 22542
- cold provider was fast (1ms), but OpenClaw spent 71031ms before provider work.
- agent-cli: 1124.5MB RSS, 171.6% CPU
- agent-process: 1124.5MB RSS, 171.6% 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-2026-05-03t130718z' -- 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 71210ms, over threshold 45000ms. Measurements: peakRssMb: 1124.5; cpuPercentMax: 171.6; coldAgentTurnMs: 71210; warmAgentTurnMs: 48668; agentColdWarmDeltaMs: 22542; cold provider was fast (1ms), but OpenClaw spent 71031ms before provider work.; agent-cli: 1124.5MB RSS, 171.6% CPU; agent-process: 1124.5MB RSS, 171.6% 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-2026-05-03t130718z' -- 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 71210ms, 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 1124.5 MB; max CPU 171.6%; samples 148; roles agent-cli 1124.5MB/171.6%, agent-process 1124.5MB/171.6%, command-tree 1124.5MB/171.6%, status-cli 532.9MB/131.9%
- agent: turn 71210ms; cold/warm 71210ms/48668ms; cold-warm delta 22542ms; pre-provider 71031ms; 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-r1-kova-2026-05-03t130718z' -- 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 71210ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r1-kova-2026-05-03t130718z' -- 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 48668ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r1-kova-2026-05-03t130718z' -- status took 16010ms, over threshold 10000ms
- peak RSS 1124.5 MB exceeded threshold 900 MB
- agent-cli peak RSS 1124.5 MB exceeded threshold 900 MB
- agent-process peak RSS 1124.5 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 71031ms before provider work, over threshold 10000ms
- warm agent spent 48595ms before provider work, over threshold 10000ms
- cold agent turn took 71210ms, over threshold 45000ms
- warm agent turn took 48668ms, over threshold 15000ms
- cold pre-provider latency was 71031ms, over threshold 10000ms
- warm pre-provider latency was 48595ms, over threshold 10000ms
- cold provider was fast (1ms), but OpenClaw spent 71031ms 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 1147.7 MB; max CPU 182.7%; samples 142; roles agent-cli 1147.7MB/182.7%, agent-process 1147.7MB/182.7%, command-tree 1147.7MB/182.7%, status-cli 530.6MB/138.8%
- agent: turn 70095ms; cold/warm 70095ms/47095ms; cold-warm delta 23000ms; pre-provider 69940ms; 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-2026-05-03t130718z' -- 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 70095ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r2-kova-2026-05-03t130718z' -- 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 47095ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r2-kova-2026-05-03t130718z' -- status took 13676ms, over threshold 10000ms
- peak RSS 1147.7 MB exceeded threshold 900 MB
- agent-cli peak RSS 1147.7 MB exceeded threshold 900 MB
- agent-process peak RSS 1147.7 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 69940ms before provider work, over threshold 10000ms
- warm agent spent 47028ms before provider work, over threshold 10000ms
- cold agent turn took 70095ms, over threshold 45000ms
- warm agent turn took 47095ms, over threshold 15000ms
- cold pre-provider latency was 69940ms, over threshold 10000ms
- warm pre-provider latency was 47028ms, over threshold 10000ms
- cold provider was fast (2ms), but OpenClaw spent 69940ms 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 1127.8 MB; max CPU 191%; samples 147; roles agent-cli 1127.8MB/191%, agent-process 1127.8MB/191%, command-tree 1127.8MB/191%, status-cli 534.4MB/134.9%
- agent: turn 73060ms; cold/warm 73060ms/48981ms; cold-warm delta 24079ms; pre-provider 72951ms; 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-2026-05-03t130718z' -- 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 73060ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r3-kova-2026-05-03t130718z' -- 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 48981ms, over threshold 45000ms
- ocm @'kova-agent-cold-warm-message-mock-openai-provider-r3-kova-2026-05-03t130718z' -- status took 13886ms, over threshold 10000ms
- peak RSS 1127.8 MB exceeded threshold 900 MB
- agent-cli peak RSS 1127.8 MB exceeded threshold 900 MB
- agent-process peak RSS 1127.8 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 72951ms before provider work, over threshold 10000ms
- warm agent spent 48899ms before provider work, over threshold 10000ms
- cold agent turn took 73060ms, over threshold 45000ms
- warm agent turn took 48981ms, over threshold 15000ms
- cold pre-provider latency was 72951ms, over threshold 10000ms
- warm pre-provider latency was 48899ms, over threshold 10000ms
- cold provider was fast (2ms), but OpenClaw spent 72951ms before provider work.
