atlas-iac/services/hermes/execution-coordinator-patch.yaml
Hermes Agent 7a55b259bf hermes: add the fenced three-node distributed execution pool
Three fenced worker Pods claim Hermes Kanban runs through a coordinator that
owns every state transition, with per-ordinal HMAC authority, a mediated
broker-only SCM path, and durable per-ordinal workspaces.

Content is the reviewed head of PR #18 (689bcb6e) with PR 16's and PR 19's
contributions removed: they were merged in only to validate co-existence and are
not prerequisites, so this branch no longer carries them as ancestors. Only PR 14
and PR 15 remain, because the broker boundary and the cli_lane_* decomposition
are load-bearing for two of the fixed P0 boundaries.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-17 16:31:15 +00:00

67 lines
2.9 KiB
YAML

apiVersion: apps/v1
kind: Deployment
metadata:
name: hermes-agent
namespace: hermes
spec:
template:
metadata:
annotations:
vault.hashicorp.com/agent-inject-secret-execution-pool-key: kv/data/atlas/hermes/agent-tokens
vault.hashicorp.com/agent-inject-perms-execution-pool-key: "0600"
vault.hashicorp.com/agent-inject-template-execution-pool-key: |
{{- with secret "kv/data/atlas/hermes/agent-tokens" -}}
{{ printf "hermes-execution-pool-root-v2:%s" .Data.data.agent_api_key | sha256sum }}
{{- end }}
spec:
containers:
- name: cli-lane-runner
env:
- {name: HERMES_CLI_LANE_OWNED_WORKSPACES_ONLY, value: "true"}
- {name: HERMES_CLI_LANE_CONCURRENCY, value: "1"}
- name: execution-pool-coordinator
image: registry.bstein.dev/bstein/hermes-agent@sha256:81970563e542f0720773e72297810b3a844b83e381e278f25c0916c78d930107
imagePullPolicy: IfNotPresent
command: [/opt/hermes/.venv/bin/python, /opt/coordinator/execution_pool_coordinator.py]
env:
- {name: HERMES_HOME, value: /opt/data}
- {name: HOME, value: /opt/data/home}
- {name: PYTHONPATH, value: /opt/hermes}
- {name: HERMES_EXECUTION_POOL_KEY_FILE, value: /pool-access/execution-pool-key}
- {name: PATH, value: /opt/coordinator:/opt/hermes/.venv/bin:/usr/local/bin:/usr/bin:/bin}
securityContext:
allowPrivilegeEscalation: false
capabilities: {drop: [ALL]}
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 10000
runAsGroup: 10000
seccompProfile: {type: RuntimeDefault}
volumeMounts:
- {name: home, mountPath: /opt/data}
- {name: runtime-access, mountPath: /pool-access/execution-pool-key, subPath: execution-pool-key, readOnly: true}
- {name: execution-pool-code, mountPath: /opt/coordinator, readOnly: true}
- {name: auth-patch, mountPath: /opt/hermes/hermes_cli/auth.py, subPath: auth.py}
- {name: tmp, mountPath: /tmp}
ports:
- {name: execution-pool, containerPort: 9007, protocol: TCP}
startupProbe:
httpGet: {path: /ready, port: execution-pool}
periodSeconds: 5
failureThreshold: 60
readinessProbe:
httpGet: {path: /ready, port: execution-pool}
periodSeconds: 10
livenessProbe:
httpGet: {path: /ready, port: execution-pool}
initialDelaySeconds: 30
periodSeconds: 30
resources:
requests: {cpu: 50m, memory: 128Mi}
limits: {cpu: 500m, memory: 512Mi}
volumes:
- name: execution-pool-code
configMap:
name: hermes-execution-pool
defaultMode: 0555