From a30d0fffa41f803af8ebcdd6fd7f1bee6f9a0a4c Mon Sep 17 00:00:00 2001 From: jenkins Date: Wed, 20 May 2026 03:14:50 -0300 Subject: [PATCH] triage: wire openclaw local diagnosis --- services/maintenance/ariadne-deployment.yaml | 10 ++++++++++ services/openclaw/configmap.yaml | 18 +++++++++++------- services/openclaw/deployment.yaml | 1 + 3 files changed, 22 insertions(+), 7 deletions(-) diff --git a/services/maintenance/ariadne-deployment.yaml b/services/maintenance/ariadne-deployment.yaml index 48fe66b0..1a807d39 100644 --- a/services/maintenance/ariadne-deployment.yaml +++ b/services/maintenance/ariadne-deployment.yaml @@ -21,6 +21,10 @@ spec: maintenance.bstein.dev/restart-rev: "20260413-jenkins-api-2" vault.hashicorp.com/agent-inject: "true" vault.hashicorp.com/role: "maintenance" + vault.hashicorp.com/agent-requests-cpu: "25m" + vault.hashicorp.com/agent-limits-cpu: "100m" + vault.hashicorp.com/agent-requests-mem: "32Mi" + vault.hashicorp.com/agent-limits-mem: "128Mi" vault.hashicorp.com/agent-inject-secret-ariadne-env.sh: "kv/data/atlas/maintenance/ariadne-db" vault.hashicorp.com/agent-inject-template-ariadne-env.sh: | {{ with secret "kv/data/atlas/maintenance/ariadne-db" }} @@ -407,6 +411,12 @@ spec: value: "45 */6 * * *" - name: ARIADNE_SCHEDULE_TESTING_TRIAGE value: "*/15 * * * *" + - name: ARIADNE_TESTING_TRIAGE_MODEL_URL + value: http://openclaw-ollama.openclaw.svc.cluster.local:11434 + - name: ARIADNE_TESTING_TRIAGE_MODEL + value: qwen2.5:7b-instruct-q4_0 + - name: ARIADNE_TESTING_TRIAGE_MODEL_TIMEOUT_SEC + value: "180" - name: JENKINS_WORKSPACE_NAMESPACE value: jenkins - name: JENKINS_WORKSPACE_PVC_PREFIX diff --git a/services/openclaw/configmap.yaml b/services/openclaw/configmap.yaml index 77b529a1..125deca3 100644 --- a/services/openclaw/configmap.yaml +++ b/services/openclaw/configmap.yaml @@ -86,16 +86,18 @@ data: You are OpenClaw running inside the Titan Kubernetes cluster as a read-only testing and operations triage assistant. - Ariadne owns deterministic evidence collection. Start every testing triage - by reading: + Ariadne owns deterministic evidence collection and local diagnosis. Start + every testing triage by reading: - - `curl -sS "$ARIADNE_BASE_URL/api/internal/testing/triage/latest"` + - `curl -sS "$ARIADNE_BASE_URL/api/internal/testing/triage/diagnosis/latest"` - if that is missing or stale, ask a human to run: - `curl -sS -X POST "$ARIADNE_BASE_URL/api/internal/testing/triage/collect"` + `curl -sS -X POST "$ARIADNE_BASE_URL/api/internal/testing/triage/diagnosis/run"` + - if the diagnosis is unavailable, fall back to: + `curl -sS "$ARIADNE_BASE_URL/api/internal/testing/triage/latest"` - Treat the Ariadne bundle as the source of truth. Your job is to explain the - evidence and propose small Flux/IaC changes, not to rediscover everything - from raw shell commands. + Treat the Ariadne diagnosis and evidence bundle as the source of truth. Your + job is to explain the evidence and propose small Flux/IaC changes, not to + rediscover everything from raw shell commands. Your job is to explain failing or suspicious test runs without mutating the cluster. Prefer concise incident summaries with: @@ -108,6 +110,8 @@ data: Useful read-only commands: + - `curl -sS "$ARIADNE_BASE_URL/api/internal/testing/triage/diagnosis/latest"` + - `curl -sS -X POST "$ARIADNE_BASE_URL/api/internal/testing/triage/diagnosis/run"` - `curl -sS "$ARIADNE_BASE_URL/api/internal/testing/triage/latest"` - `kubectl get nodes -o wide` - `kubectl get pods -A -o wide` diff --git a/services/openclaw/deployment.yaml b/services/openclaw/deployment.yaml index 01471610..d1e6c69d 100644 --- a/services/openclaw/deployment.yaml +++ b/services/openclaw/deployment.yaml @@ -23,6 +23,7 @@ spec: ai.bstein.dev/instructions: kubectl-field-selectors ai.bstein.dev/role: testing-triage ai.bstein.dev/placement: arm64 gateway lane (jetson preferred) + ai.bstein.dev/config-rev: "20260520-local-triage" spec: serviceAccountName: openclaw-triage automountServiceAccountToken: true