2026-04-15 21:32:45 +00:00
|
|
|
variable "tls_secret_name" {
|
|
|
|
|
type = string
|
|
|
|
|
sensitive = true
|
|
|
|
|
}
|
|
|
|
|
|
[infra/beads-server] Wire BeadBoard to claude-agent-service
## Context
BeadBoard is the Next.js task visualization dashboard shipped in this
stack. We want users to trigger headless Claude agent runs directly from
a beads task row — "one-click dispatch" — instead of copy-pasting `bd`
IDs into a terminal. The agent runs in-cluster as claude-agent-service
(see stacks/claude-agent-service/), protected by a bearer token in
Vault at secret/claude-agent-service/api_bearer_token.
For BeadBoard to POST to /execute we need the service URL and the
bearer token available inside the pod as env vars. The URL is static
(cluster DNS); the token must come through External Secrets Operator
so rotation in Vault propagates without re-applying Terraform.
Secondary cleanup: the container was still pinned to :latest which
violates the 8-char-SHA convention and causes stale pulls through the
registry cache (see .claude/CLAUDE.md, Docker images). The image tag
is now variable-driven; the GHA pipeline will override the default
once it publishes the first SHA.
## This change
- Adds an ExternalSecret `beadboard-agent-service` in the
`beads-server` namespace, mirroring the pattern in
stacks/claude-agent-service/main.tf (same Vault path
`secret/claude-agent-service`, same `vault-kv` ClusterSecretStore,
same 15m refresh). Exposes exactly one key: `api_bearer_token`.
- Adds two env vars to the `beadboard` container:
- `CLAUDE_AGENT_SERVICE_URL` — static cluster URL
(`http://claude-agent-service.claude-agent.svc.cluster.local:8080`)
- `CLAUDE_AGENT_BEARER_TOKEN` — `secret_key_ref` pointing at the
ESO-managed Secret, key `api_bearer_token`
- Adds `reloader.stakater.com/auto = "true"` on the Deployment's
top-level metadata — matches the convention used by rybbit,
claude-memory, onlyoffice. When ESO refreshes the K8s Secret
because Vault rotated the token, Reloader restarts the pod so the
new token is picked up (env vars are read once at boot).
- Adds `variable "beadboard_image_tag"` (default `"latest"`, with a
one-line comment flagging the temporary default). The image
reference now interpolates `${var.beadboard_image_tag}`. No tfvars
file is touched — orchestrator will flip the default to the first
real 8-char SHA once GHA publishes it.
## What is NOT in this change
- No GHA workflow additions. The pipeline that builds
`registry.viktorbarzin.me:5050/beadboard` lives in the BeadBoard
repo and is out of scope here.
- No Vault-side changes. `secret/claude-agent-service/api_bearer_token`
already exists (it powers the claude-agent-service deployment
itself).
- No Terraform `apply`. Orchestrator applies.
## Data flow
Vault (secret/claude-agent-service)
│ refresh every 15m
▼
ESO → K8s Secret `beadboard-agent-service` (beads-server ns)
│ envFrom.secretKeyRef
▼
BeadBoard pod (CLAUDE_AGENT_BEARER_TOKEN env)
│ Authorization: Bearer <token>
▼
claude-agent-service.claude-agent.svc:8080 /execute
On Vault rotation: ESO picks up new value at next refresh → K8s
Secret data changes → Reloader sees annotation + referenced Secret
changed → rolling-recreates the beadboard pod with the new token.
## Test Plan
### Automated
- `terraform fmt -recursive stacks/beads-server/` — clean (formatted
the file once; subsequent run is a no-op).
- `terraform -chdir=stacks/beads-server validate` (after
`terraform init -backend=false`) — `Success! The configuration is
valid`. The 14 "Deprecated Resource" warnings are pre-existing
(`kubernetes_namespace` vs `_v1` etc.) and unrelated to this
change.
### Manual Verification
1. Orchestrator applies:
`scripts/tg -chdir=stacks/beads-server apply`
2. Verify the ExternalSecret synced:
`kubectl -n beads-server get externalsecret beadboard-agent-service`
Expected: `Ready=True`, `SyncedAt` recent.
3. Verify the K8s Secret exists with one key:
`kubectl -n beads-server get secret beadboard-agent-service -o jsonpath='{.data.api_bearer_token}' | base64 -d | head -c 8`
Expected: first 8 chars of the bearer token.
4. Verify the deployment picked up the env vars:
`kubectl -n beads-server get deploy beadboard -o yaml | grep -A2 CLAUDE_AGENT`
Expected: both env entries present, bearer via `secretKeyRef`.
5. Verify the reloader annotation is on the Deployment metadata:
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.metadata.annotations.reloader\.stakater\.com/auto}'`
Expected: `true`.
6. Verify the image tag resolved to the variable default (for now):
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.spec.template.spec.containers[0].image}'`
Expected: `registry.viktorbarzin.me:5050/beadboard:latest`
(will become `...:<sha>` once `beadboard_image_tag` default is
updated).
7. Smoke-test the env var inside the pod:
`kubectl -n beads-server exec deploy/beadboard -- sh -c 'printenv CLAUDE_AGENT_SERVICE_URL; printenv CLAUDE_AGENT_BEARER_TOKEN | head -c 8'`
Expected: URL printed, first 8 chars of token printed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 13:53:51 +00:00
|
|
|
variable "beadboard_image_tag" {
|
|
|
|
|
type = string
|
2026-04-18 19:24:37 +00:00
|
|
|
default = "17a38e43"
|
[infra/beads-server] Wire BeadBoard to claude-agent-service
## Context
BeadBoard is the Next.js task visualization dashboard shipped in this
stack. We want users to trigger headless Claude agent runs directly from
a beads task row — "one-click dispatch" — instead of copy-pasting `bd`
IDs into a terminal. The agent runs in-cluster as claude-agent-service
(see stacks/claude-agent-service/), protected by a bearer token in
Vault at secret/claude-agent-service/api_bearer_token.
For BeadBoard to POST to /execute we need the service URL and the
bearer token available inside the pod as env vars. The URL is static
(cluster DNS); the token must come through External Secrets Operator
so rotation in Vault propagates without re-applying Terraform.
Secondary cleanup: the container was still pinned to :latest which
violates the 8-char-SHA convention and causes stale pulls through the
registry cache (see .claude/CLAUDE.md, Docker images). The image tag
is now variable-driven; the GHA pipeline will override the default
once it publishes the first SHA.
## This change
- Adds an ExternalSecret `beadboard-agent-service` in the
`beads-server` namespace, mirroring the pattern in
stacks/claude-agent-service/main.tf (same Vault path
`secret/claude-agent-service`, same `vault-kv` ClusterSecretStore,
same 15m refresh). Exposes exactly one key: `api_bearer_token`.
- Adds two env vars to the `beadboard` container:
- `CLAUDE_AGENT_SERVICE_URL` — static cluster URL
(`http://claude-agent-service.claude-agent.svc.cluster.local:8080`)
- `CLAUDE_AGENT_BEARER_TOKEN` — `secret_key_ref` pointing at the
ESO-managed Secret, key `api_bearer_token`
- Adds `reloader.stakater.com/auto = "true"` on the Deployment's
top-level metadata — matches the convention used by rybbit,
claude-memory, onlyoffice. When ESO refreshes the K8s Secret
because Vault rotated the token, Reloader restarts the pod so the
new token is picked up (env vars are read once at boot).
- Adds `variable "beadboard_image_tag"` (default `"latest"`, with a
one-line comment flagging the temporary default). The image
reference now interpolates `${var.beadboard_image_tag}`. No tfvars
file is touched — orchestrator will flip the default to the first
real 8-char SHA once GHA publishes it.
## What is NOT in this change
- No GHA workflow additions. The pipeline that builds
`registry.viktorbarzin.me:5050/beadboard` lives in the BeadBoard
repo and is out of scope here.
- No Vault-side changes. `secret/claude-agent-service/api_bearer_token`
already exists (it powers the claude-agent-service deployment
itself).
- No Terraform `apply`. Orchestrator applies.
## Data flow
Vault (secret/claude-agent-service)
│ refresh every 15m
▼
ESO → K8s Secret `beadboard-agent-service` (beads-server ns)
│ envFrom.secretKeyRef
▼
BeadBoard pod (CLAUDE_AGENT_BEARER_TOKEN env)
│ Authorization: Bearer <token>
▼
claude-agent-service.claude-agent.svc:8080 /execute
On Vault rotation: ESO picks up new value at next refresh → K8s
Secret data changes → Reloader sees annotation + referenced Secret
changed → rolling-recreates the beadboard pod with the new token.
## Test Plan
### Automated
- `terraform fmt -recursive stacks/beads-server/` — clean (formatted
the file once; subsequent run is a no-op).
- `terraform -chdir=stacks/beads-server validate` (after
`terraform init -backend=false`) — `Success! The configuration is
valid`. The 14 "Deprecated Resource" warnings are pre-existing
(`kubernetes_namespace` vs `_v1` etc.) and unrelated to this
change.
### Manual Verification
1. Orchestrator applies:
`scripts/tg -chdir=stacks/beads-server apply`
2. Verify the ExternalSecret synced:
`kubectl -n beads-server get externalsecret beadboard-agent-service`
Expected: `Ready=True`, `SyncedAt` recent.
3. Verify the K8s Secret exists with one key:
`kubectl -n beads-server get secret beadboard-agent-service -o jsonpath='{.data.api_bearer_token}' | base64 -d | head -c 8`
Expected: first 8 chars of the bearer token.
4. Verify the deployment picked up the env vars:
`kubectl -n beads-server get deploy beadboard -o yaml | grep -A2 CLAUDE_AGENT`
Expected: both env entries present, bearer via `secretKeyRef`.
5. Verify the reloader annotation is on the Deployment metadata:
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.metadata.annotations.reloader\.stakater\.com/auto}'`
Expected: `true`.
6. Verify the image tag resolved to the variable default (for now):
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.spec.template.spec.containers[0].image}'`
Expected: `registry.viktorbarzin.me:5050/beadboard:latest`
(will become `...:<sha>` once `beadboard_image_tag` default is
updated).
7. Smoke-test the env var inside the pod:
`kubectl -n beads-server exec deploy/beadboard -- sh -c 'printenv CLAUDE_AGENT_SERVICE_URL; printenv CLAUDE_AGENT_BEARER_TOKEN | head -c 8'`
Expected: URL printed, first 8 chars of token printed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 13:53:51 +00:00
|
|
|
}
|
|
|
|
|
|
[beads-server] Auto-dispatch agent beads via CronJobs
## Context
Until now, handing work to the in-cluster `beads-task-runner` agent required
opening BeadBoard and clicking the manual Dispatch button on each bead. We
want users to be able to describe work as a bead, set `assignee=agent`, and
have the agent pick it up within a couple of minutes — no clicks.
The existing pieces already provide everything we need:
- `claude-agent-service` exposes `/execute` with a single-slot `asyncio.Lock`
- BeadBoard's `/api/agent-dispatch` builds the prompt and forwards the bearer
- BeadBoard's `/api/agent-status` reports `busy` via a cached `/health` poll
- Dolt stores beads and is already in-cluster at `dolt.beads-server:3306`
So the only missing component is a poller that ties them together. This
commit adds that poller as two Kubernetes CronJobs — matching the existing
infra pattern (OpenClaw task-processor, certbot-renewal, backups) rather than
introducing n8n or in-service polling.
## Flow
```
user: bd assign <id> agent
│
▼
Dolt @ dolt.beads-server.svc:3306 ◄──── every 2 min ────┐
│ │
▼ │
CronJob: beads-dispatcher │
1. GET beadboard/api/agent-status (busy? skip) │
2. bd query 'assignee=agent AND status=open' │
3. bd update -s in_progress (claim) │
4. POST beadboard/api/agent-dispatch │
5. bd note "dispatched: job=…" │
│ │
▼ │
claude-agent-service /execute │
beads-task-runner agent runs; notes/closes bead │
│ │
▼ │
done ──► next tick picks up the next bead ───────────────┘
CronJob: beads-reaper (every 10 min)
for bead (assignee=agent, status=in_progress, updated_at > 30 min):
bd note "reaper: no progress for Nm — blocking"
bd update -s blocked
```
## Decisions
- **Sentinel assignee `agent`** — free-form, no Beads schema change. Any bd
client can set it (`bd assign <id> agent`).
- **Sequential dispatch** — matches the service's `asyncio.Lock`. With a
2-min poll cadence and ~5-min average run, throughput is ~12 beads/hour.
Parallelism is a separate plan.
- **Fixed agent `beads-task-runner`** — read-only rails, matches the manual
Dispatch button. Broader-privilege agents stay manual via BeadBoard UI.
- **Image reuse** — the claude-agent-service image already ships `bd`, `jq`,
`curl`; a new CronJob-specific image would duplicate 400MB of infra tooling.
Mirror `claude_agent_service_image_tag` locally; bump on rebuild.
- **ConfigMap-mounted `metadata.json`** — declarative TF rather than reusing
the image-seeded file. The script copies it into `/tmp/.beads/` because bd
may touch the parent dir and ConfigMap mounts are read-only.
- **Kill switch (`beads_dispatcher_enabled`)** — single bool, default true.
When false, `suspend: true` on both CronJobs; manual Dispatch keeps working.
- **Reaper threshold 30 min** — `bd note` bumps `updated_at`, so a well-behaved
`beads-task-runner` never trips the reaper. Failures trip it; pod crashes
(in-memory job state lost) also trip it.
## What is NOT in this change
- No Terraform apply — requires Vault OIDC + cluster access. Apply manually:
`cd infra/stacks/beads-server && scripts/tg apply`
- No change to `claude-agent-service/` (already ships bd/jq/curl)
- No change to `beadboard/` (`/api/agent-dispatch` + `/api/agent-status` reused)
- No change to the `beads-task-runner` agent definition (rails unchanged)
- Parallelism: single-slot is MVP; multi-slot dispatch is a separate plan.
## Deviations from plan
Minor, documented in code comments:
- Reaper uses `.updated_at` instead of the plan's `.notes[].created_at`. bd
serializes `notes` as a string (not an array), and every `bd note` bumps
`updated_at` — equivalent for the reaper's purpose.
- ISO-8601 parsed via `python3`, not `date -d` — Alpine's busybox lacks GNU
`-d` and the image has python3.
- `HOME=/tmp` set as a safety net — bd may try to write state/lock files.
## Test plan
### Automated
```
$ cd infra/stacks/beads-server && terraform init -backend=false
Terraform has been successfully initialized!
$ terraform validate
Warning: Deprecated Resource (kubernetes_namespace → v1) # pre-existing, unrelated
Success! The configuration is valid, but there were some validation warnings as shown above.
$ terraform fmt stacks/beads-server/main.tf
# (no output — already formatted)
```
### Manual verification
1. **Apply**
```
vault login -method=oidc
cd infra/stacks/beads-server
scripts/tg apply
```
Expect: `kubernetes_config_map.beads_metadata`,
`kubernetes_cron_job_v1.beads_dispatcher`, `kubernetes_cron_job_v1.beads_reaper`
created. No changes to existing resources.
2. **CronJobs exist with right schedule**
```
kubectl -n beads-server get cronjob
```
Expect `beads-dispatcher */2 * * * *` and `beads-reaper */10 * * * *`,
both with `SUSPEND=False`.
3. **End-to-end smoke**
```
bd create "auto-dispatch smoke test" \
-d "Read /etc/hostname inside the agent sandbox and close." \
--acceptance "bd note includes 'hostname=' line and bead is closed."
bd assign <new-id> agent
# within 2 min:
bd show <new-id> --json | jq '{status, notes}'
```
Expect notes to contain `auto-dispatcher claimed at …` and
`dispatched: job=<uuid>`, status `in_progress`.
4. **Reaper smoke**
Assign + dispatch a long bead, then
`kubectl -n claude-agent delete pod -l app=claude-agent-service`. Within
30 min + one reaper tick, `bd show <id>` shows `blocked` with a
`reaper: no progress for Nm — blocking` note.
5. **Kill switch**
```
cd infra/stacks/beads-server
scripts/tg apply -var=beads_dispatcher_enabled=false
kubectl -n beads-server get cronjob
```
Expect `SUSPEND=True` on both CronJobs. Assign a bead to `agent`; verify
nothing happens within 5 min. Re-apply with `=true` to re-enable.
Runbook with all above plus reaper semantics + design choices at
`infra/docs/runbooks/beads-auto-dispatch.md`.
Closes: code-8sm
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 22:35:46 +00:00
|
|
|
# Mirrors `local.image_tag` in stacks/claude-agent-service/main.tf — keep in
|
|
|
|
|
# sync when the claude-agent-service image is rebuilt. Reused here because the
|
|
|
|
|
# dispatcher + reaper CronJobs only need bd, curl, and jq, which that image
|
|
|
|
|
# already ships.
|
|
|
|
|
variable "claude_agent_service_image_tag" {
|
|
|
|
|
type = string
|
2026-04-19 23:16:34 +00:00
|
|
|
default = "2fd7670d"
|
[beads-server] Auto-dispatch agent beads via CronJobs
## Context
Until now, handing work to the in-cluster `beads-task-runner` agent required
opening BeadBoard and clicking the manual Dispatch button on each bead. We
want users to be able to describe work as a bead, set `assignee=agent`, and
have the agent pick it up within a couple of minutes — no clicks.
The existing pieces already provide everything we need:
- `claude-agent-service` exposes `/execute` with a single-slot `asyncio.Lock`
- BeadBoard's `/api/agent-dispatch` builds the prompt and forwards the bearer
- BeadBoard's `/api/agent-status` reports `busy` via a cached `/health` poll
- Dolt stores beads and is already in-cluster at `dolt.beads-server:3306`
So the only missing component is a poller that ties them together. This
commit adds that poller as two Kubernetes CronJobs — matching the existing
infra pattern (OpenClaw task-processor, certbot-renewal, backups) rather than
introducing n8n or in-service polling.
## Flow
```
user: bd assign <id> agent
│
▼
Dolt @ dolt.beads-server.svc:3306 ◄──── every 2 min ────┐
│ │
▼ │
CronJob: beads-dispatcher │
1. GET beadboard/api/agent-status (busy? skip) │
2. bd query 'assignee=agent AND status=open' │
3. bd update -s in_progress (claim) │
4. POST beadboard/api/agent-dispatch │
5. bd note "dispatched: job=…" │
│ │
▼ │
claude-agent-service /execute │
beads-task-runner agent runs; notes/closes bead │
│ │
▼ │
done ──► next tick picks up the next bead ───────────────┘
CronJob: beads-reaper (every 10 min)
for bead (assignee=agent, status=in_progress, updated_at > 30 min):
bd note "reaper: no progress for Nm — blocking"
bd update -s blocked
```
## Decisions
- **Sentinel assignee `agent`** — free-form, no Beads schema change. Any bd
client can set it (`bd assign <id> agent`).
- **Sequential dispatch** — matches the service's `asyncio.Lock`. With a
2-min poll cadence and ~5-min average run, throughput is ~12 beads/hour.
Parallelism is a separate plan.
- **Fixed agent `beads-task-runner`** — read-only rails, matches the manual
Dispatch button. Broader-privilege agents stay manual via BeadBoard UI.
- **Image reuse** — the claude-agent-service image already ships `bd`, `jq`,
`curl`; a new CronJob-specific image would duplicate 400MB of infra tooling.
Mirror `claude_agent_service_image_tag` locally; bump on rebuild.
- **ConfigMap-mounted `metadata.json`** — declarative TF rather than reusing
the image-seeded file. The script copies it into `/tmp/.beads/` because bd
may touch the parent dir and ConfigMap mounts are read-only.
- **Kill switch (`beads_dispatcher_enabled`)** — single bool, default true.
When false, `suspend: true` on both CronJobs; manual Dispatch keeps working.
- **Reaper threshold 30 min** — `bd note` bumps `updated_at`, so a well-behaved
`beads-task-runner` never trips the reaper. Failures trip it; pod crashes
(in-memory job state lost) also trip it.
## What is NOT in this change
- No Terraform apply — requires Vault OIDC + cluster access. Apply manually:
`cd infra/stacks/beads-server && scripts/tg apply`
- No change to `claude-agent-service/` (already ships bd/jq/curl)
- No change to `beadboard/` (`/api/agent-dispatch` + `/api/agent-status` reused)
- No change to the `beads-task-runner` agent definition (rails unchanged)
- Parallelism: single-slot is MVP; multi-slot dispatch is a separate plan.
## Deviations from plan
Minor, documented in code comments:
- Reaper uses `.updated_at` instead of the plan's `.notes[].created_at`. bd
serializes `notes` as a string (not an array), and every `bd note` bumps
`updated_at` — equivalent for the reaper's purpose.
- ISO-8601 parsed via `python3`, not `date -d` — Alpine's busybox lacks GNU
`-d` and the image has python3.
- `HOME=/tmp` set as a safety net — bd may try to write state/lock files.
## Test plan
### Automated
```
$ cd infra/stacks/beads-server && terraform init -backend=false
Terraform has been successfully initialized!
$ terraform validate
Warning: Deprecated Resource (kubernetes_namespace → v1) # pre-existing, unrelated
Success! The configuration is valid, but there were some validation warnings as shown above.
$ terraform fmt stacks/beads-server/main.tf
# (no output — already formatted)
```
### Manual verification
1. **Apply**
```
vault login -method=oidc
cd infra/stacks/beads-server
scripts/tg apply
```
Expect: `kubernetes_config_map.beads_metadata`,
`kubernetes_cron_job_v1.beads_dispatcher`, `kubernetes_cron_job_v1.beads_reaper`
created. No changes to existing resources.
2. **CronJobs exist with right schedule**
```
kubectl -n beads-server get cronjob
```
Expect `beads-dispatcher */2 * * * *` and `beads-reaper */10 * * * *`,
both with `SUSPEND=False`.
3. **End-to-end smoke**
```
bd create "auto-dispatch smoke test" \
-d "Read /etc/hostname inside the agent sandbox and close." \
--acceptance "bd note includes 'hostname=' line and bead is closed."
bd assign <new-id> agent
# within 2 min:
bd show <new-id> --json | jq '{status, notes}'
```
Expect notes to contain `auto-dispatcher claimed at …` and
`dispatched: job=<uuid>`, status `in_progress`.
4. **Reaper smoke**
Assign + dispatch a long bead, then
`kubectl -n claude-agent delete pod -l app=claude-agent-service`. Within
30 min + one reaper tick, `bd show <id>` shows `blocked` with a
`reaper: no progress for Nm — blocking` note.
5. **Kill switch**
```
cd infra/stacks/beads-server
scripts/tg apply -var=beads_dispatcher_enabled=false
kubectl -n beads-server get cronjob
```
Expect `SUSPEND=True` on both CronJobs. Assign a bead to `agent`; verify
nothing happens within 5 min. Re-apply with `=true` to re-enable.
Runbook with all above plus reaper semantics + design choices at
`infra/docs/runbooks/beads-auto-dispatch.md`.
Closes: code-8sm
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 22:35:46 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# Kill switch for auto-dispatch. When false, both CronJobs are suspended. The
|
|
|
|
|
# manual BeadBoard Dispatch button keeps working either way.
|
|
|
|
|
variable "beads_dispatcher_enabled" {
|
|
|
|
|
type = bool
|
|
|
|
|
default = true
|
|
|
|
|
}
|
|
|
|
|
|
chore: add untracked stacks, scripts, and agent configs
- New stacks: beads-server, hermes-agent
- Terragrunt tiers.tf for infra, phpipam, status-page
- Secrets symlinks for vault, phpipam, hermes-agent
- Scripts: cluster_manager, image_pull, containerd pullthrough setup
- Frigate config, audiblez-web app source, n8n workflows dir
- Claude agent: service-upgrade, reference: upgrade-config.json
- Removed: claudeception skill, excalidraw empty submodule, temp listings
[ci skip]
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 09:33:06 +00:00
|
|
|
resource "kubernetes_namespace" "beads" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "beads-server"
|
|
|
|
|
labels = {
|
|
|
|
|
tier = local.tiers.aux
|
|
|
|
|
}
|
|
|
|
|
}
|
[infra] Suppress Goldilocks vpa-update-mode label drift on all namespaces [ci skip]
## Context
Wave 3B-continued: the Goldilocks VPA dashboard (stacks/vpa) runs a Kyverno
ClusterPolicy `goldilocks-vpa-auto-mode` that mutates every namespace with
`metadata.labels["goldilocks.fairwinds.com/vpa-update-mode"] = "off"`. This
is intentional — Terraform owns container resource limits, and Goldilocks
should only provide recommendations, never auto-update. The label is how
Goldilocks decides per-namespace whether to run its VPA in `off` mode.
Effect on Terraform: every `kubernetes_namespace` resource shows the label
as pending-removal (`-> null`) on every `scripts/tg plan`. Dawarich survey
2026-04-18 confirmed the drift. Cluster-side count: 88 namespaces carry the
label (`kubectl get ns -o json | jq ... | wc -l`). Every TF-managed namespace
is affected.
This commit brings the intentional admission drift under the same
`# KYVERNO_LIFECYCLE_V1` discoverability marker introduced in c9d221d5 for
the ndots dns_config pattern. The marker now stands generically for any
Kyverno admission-webhook drift suppression; the inline comment records
which specific policy stamps which specific field so future grep audits
show why each suppression exists.
## This change
107 `.tf` files touched — every stack's `resource "kubernetes_namespace"`
resource gets:
```hcl
lifecycle {
# KYVERNO_LIFECYCLE_V1: goldilocks-vpa-auto-mode ClusterPolicy stamps this label on every namespace
ignore_changes = [metadata[0].labels["goldilocks.fairwinds.com/vpa-update-mode"]]
}
```
Injection was done with a brace-depth-tracking Python pass (`/tmp/add_goldilocks_ignore.py`):
match `^resource "kubernetes_namespace" ` → track `{` / `}` until the
outermost closing brace → insert the lifecycle block before the closing
brace. The script is idempotent (skips any file that already mentions
`goldilocks.fairwinds.com/vpa-update-mode`) so re-running is safe.
Vault stack picked up 2 namespaces in the same file (k8s-users produces
one, plus a second explicit ns) — confirmed via file diff (+8 lines).
## What is NOT in this change
- `stacks/trading-bot/main.tf` — entire file is `/* … */` commented out
(paused 2026-04-06 per user decision). Reverted after the script ran.
- `stacks/_template/main.tf.example` — per-stack skeleton, intentionally
minimal. User keeps it that way. Not touched by the script (file
has no real `resource "kubernetes_namespace"` — only a placeholder
comment).
- `.terraform/` copies (e.g. `stacks/metallb/.terraform/modules/...`) —
gitignored, won't commit; the live path was edited.
- `terraform fmt` cleanup of adjacent pre-existing alignment issues in
authentik, freedify, hermes-agent, nvidia, vault, meshcentral. Reverted
to keep the commit scoped to the Goldilocks sweep. Those files will
need a separate fmt-only commit or will be cleaned up on next real
apply to that stack.
## Verification
Dawarich (one of the hundred-plus touched stacks) showed the pattern
before and after:
```
$ cd stacks/dawarich && ../../scripts/tg plan
Before:
Plan: 0 to add, 2 to change, 0 to destroy.
# kubernetes_namespace.dawarich will be updated in-place
(goldilocks.fairwinds.com/vpa-update-mode -> null)
# module.tls_secret.kubernetes_secret.tls_secret will be updated in-place
(Kyverno generate.* labels — fixed in 8d94688d)
After:
No changes. Your infrastructure matches the configuration.
```
Injection count check:
```
$ rg -c 'KYVERNO_LIFECYCLE_V1: goldilocks-vpa-auto-mode' stacks/ | awk -F: '{s+=$2} END {print s}'
108
```
## Reproduce locally
1. `git pull`
2. Pick any stack: `cd stacks/<name> && ../../scripts/tg plan`
3. Expect: no drift on the namespace's goldilocks.fairwinds.com/vpa-update-mode label.
Closes: code-dwx
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 21:15:27 +00:00
|
|
|
lifecycle {
|
|
|
|
|
# KYVERNO_LIFECYCLE_V1: goldilocks-vpa-auto-mode ClusterPolicy stamps this label on every namespace
|
|
|
|
|
ignore_changes = [metadata[0].labels["goldilocks.fairwinds.com/vpa-update-mode"]]
|
|
|
|
|
}
|
chore: add untracked stacks, scripts, and agent configs
- New stacks: beads-server, hermes-agent
- Terragrunt tiers.tf for infra, phpipam, status-page
- Secrets symlinks for vault, phpipam, hermes-agent
- Scripts: cluster_manager, image_pull, containerd pullthrough setup
- Frigate config, audiblez-web app source, n8n workflows dir
- Claude agent: service-upgrade, reference: upgrade-config.json
- Removed: claudeception skill, excalidraw empty submodule, temp listings
[ci skip]
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 09:33:06 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_persistent_volume_claim" "dolt_data" {
|
|
|
|
|
wait_until_bound = false
|
|
|
|
|
metadata {
|
|
|
|
|
name = "dolt-data"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
annotations = {
|
|
|
|
|
"resize.topolvm.io/threshold" = "80%"
|
|
|
|
|
"resize.topolvm.io/increase" = "100%"
|
|
|
|
|
"resize.topolvm.io/storage_limit" = "10Gi"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
access_modes = ["ReadWriteOnce"]
|
|
|
|
|
storage_class_name = "proxmox-lvm"
|
|
|
|
|
resources {
|
|
|
|
|
requests = { storage = "2Gi" }
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_config_map" "dolt_init" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "dolt-init"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
data = {
|
|
|
|
|
"01-create-beads-user.sql" = <<-EOT
|
|
|
|
|
CREATE USER IF NOT EXISTS 'beads'@'%' IDENTIFIED BY '';
|
|
|
|
|
GRANT ALL PRIVILEGES ON *.* TO 'beads'@'%' WITH GRANT OPTION;
|
|
|
|
|
EOT
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_deployment" "dolt" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "dolt"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "dolt"
|
|
|
|
|
tier = local.tiers.aux
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
replicas = 1
|
|
|
|
|
strategy {
|
|
|
|
|
type = "Recreate"
|
|
|
|
|
}
|
|
|
|
|
selector {
|
|
|
|
|
match_labels = {
|
|
|
|
|
app = "dolt"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
template {
|
|
|
|
|
metadata {
|
|
|
|
|
labels = {
|
|
|
|
|
app = "dolt"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
container {
|
|
|
|
|
name = "dolt"
|
|
|
|
|
image = "dolthub/dolt-sql-server:latest"
|
|
|
|
|
|
|
|
|
|
port {
|
|
|
|
|
name = "mysql"
|
|
|
|
|
container_port = 3306
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
env {
|
|
|
|
|
name = "DOLT_ROOT_HOST"
|
|
|
|
|
value = "%"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "dolt-data"
|
|
|
|
|
mount_path = "/var/lib/dolt"
|
|
|
|
|
}
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "init-scripts"
|
|
|
|
|
mount_path = "/docker-entrypoint-initdb.d"
|
|
|
|
|
read_only = true
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
startup_probe {
|
|
|
|
|
tcp_socket {
|
|
|
|
|
port = 3306
|
|
|
|
|
}
|
|
|
|
|
failure_threshold = 30
|
|
|
|
|
period_seconds = 2
|
|
|
|
|
}
|
|
|
|
|
liveness_probe {
|
|
|
|
|
tcp_socket {
|
|
|
|
|
port = 3306
|
|
|
|
|
}
|
|
|
|
|
initial_delay_seconds = 10
|
|
|
|
|
period_seconds = 30
|
|
|
|
|
}
|
|
|
|
|
readiness_probe {
|
|
|
|
|
tcp_socket {
|
|
|
|
|
port = 3306
|
|
|
|
|
}
|
|
|
|
|
initial_delay_seconds = 5
|
|
|
|
|
period_seconds = 10
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resources {
|
|
|
|
|
requests = {
|
|
|
|
|
memory = "256Mi"
|
|
|
|
|
cpu = "50m"
|
|
|
|
|
}
|
|
|
|
|
limits = {
|
|
|
|
|
memory = "512Mi"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
volume {
|
|
|
|
|
name = "dolt-data"
|
|
|
|
|
persistent_volume_claim {
|
|
|
|
|
claim_name = kubernetes_persistent_volume_claim.dolt_data.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
volume {
|
|
|
|
|
name = "init-scripts"
|
|
|
|
|
config_map {
|
|
|
|
|
name = kubernetes_config_map.dolt_init.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
lifecycle {
|
|
|
|
|
ignore_changes = [
|
[infra] Establish KYVERNO_LIFECYCLE_V1 drift-suppression convention [ci skip]
## Context
Phase 1 of the state-drift consolidation audit (plan Wave 3) identified that
the entire repo leans on a repeated `lifecycle { ignore_changes = [...dns_config] }`
snippet to suppress Kyverno's admission-webhook dns_config mutation (the ndots=2
override that prevents NxDomain search-domain flooding). 27 occurrences across
19 stacks. Without this suppression, every pod-owning resource shows perpetual
TF plan drift.
The original plan proposed a shared `modules/kubernetes/kyverno_lifecycle/`
module emitting the ignore-paths list as an output that stacks would consume in
their `ignore_changes` blocks. That approach is architecturally impossible:
Terraform's `ignore_changes` meta-argument accepts only static attribute paths
— it rejects module outputs, locals, variables, and any expression (the HCL
spec evaluates `lifecycle` before the regular expression graph). So a DRY
module cannot exist. The canonical pattern IS the repeated snippet.
What the snippet was missing was a *discoverability tag* so that (a) new
resources can be validated for compliance, (b) the existing 27 sites can be
grep'd in a single command, and (c) future maintainers understand the
convention rather than each reinventing it.
## This change
- Introduces `# KYVERNO_LIFECYCLE_V1` as the canonical marker comment.
Attached inline on every `spec[0].template[0].spec[0].dns_config` line
(or `spec[0].job_template[0].spec[0]...` for CronJobs) across all 27
existing suppression sites.
- Documents the convention with rationale and copy-paste snippets in
`AGENTS.md` → new "Kyverno Drift Suppression" section.
- Expands the existing `.claude/CLAUDE.md` Kyverno ndots note to reference
the marker and explain why the module approach is blocked.
- Updates `_template/main.tf.example` so every new stack starts compliant.
## What is NOT in this change
- The `kubernetes_manifest` Kyverno annotation drift (beads `code-seq`)
— that is Phase B with a sibling `# KYVERNO_MANIFEST_V1` marker.
- Behavioral changes — every `ignore_changes` list is byte-identical
save for the inline comment.
- The fallback module the original plan anticipated — skipped because
Terraform rejects expressions in `ignore_changes`.
- `terraform fmt` cleanup on adjacent unrelated blocks in three files
(claude-agent-service, freedify/factory, hermes-agent). Reverted to
keep this commit scoped to the convention rollout.
## Before / after
Before (cannot distinguish accidental-forgotten from intentional-convention):
```hcl
lifecycle {
ignore_changes = [spec[0].template[0].spec[0].dns_config]
}
```
After (greppable, self-documenting, discoverable by tooling):
```hcl
lifecycle {
ignore_changes = [spec[0].template[0].spec[0].dns_config] # KYVERNO_LIFECYCLE_V1
}
```
## Test Plan
### Automated
```
$ rg -c 'KYVERNO_LIFECYCLE_V1' stacks/ --include='*.tf' --include='*.tf.example' \
| awk -F: '{s+=$2} END {print s}'
27
$ git diff --stat | grep -E '\.(tf|tf\.example|md)$' | wc -l
21
# All code-file diffs are 1 insertion + 1 deletion per marker site,
# except beads-server (3), ebooks (4), immich (3), uptime-kuma (2).
$ git diff --stat stacks/ | tail -1
20 files changed, 45 insertions(+), 28 deletions(-)
```
### Manual Verification
No apply required — HCL comments only. Zero effect on any stack's plan output.
Future audits: `rg 'KYVERNO_LIFECYCLE_V1' stacks/ | wc -l` must grow as new
pod-owning resources are added.
## Reproduce locally
1. `cd infra && git pull`
2. `rg 'KYVERNO_LIFECYCLE_V1' stacks/` → expect 27 hits in 19 files
3. Grep any new `kubernetes_deployment` for the marker; absence = missing
suppression.
Closes: code-28m
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 14:15:51 +00:00
|
|
|
spec[0].template[0].spec[0].dns_config # KYVERNO_LIFECYCLE_V1
|
chore: add untracked stacks, scripts, and agent configs
- New stacks: beads-server, hermes-agent
- Terragrunt tiers.tf for infra, phpipam, status-page
- Secrets symlinks for vault, phpipam, hermes-agent
- Scripts: cluster_manager, image_pull, containerd pullthrough setup
- Frigate config, audiblez-web app source, n8n workflows dir
- Claude agent: service-upgrade, reference: upgrade-config.json
- Removed: claudeception skill, excalidraw empty submodule, temp listings
[ci skip]
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 09:33:06 +00:00
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_service" "dolt" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "dolt"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "dolt"
|
|
|
|
|
}
|
|
|
|
|
annotations = {
|
|
|
|
|
"metallb.universe.tf/loadBalancerIPs" = "10.0.20.200"
|
|
|
|
|
"metallb.io/allow-shared-ip" = "shared"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
type = "LoadBalancer"
|
|
|
|
|
external_traffic_policy = "Cluster"
|
|
|
|
|
selector = {
|
|
|
|
|
app = "dolt"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
name = "mysql"
|
|
|
|
|
port = 3306
|
|
|
|
|
target_port = 3306
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
2026-04-15 21:32:45 +00:00
|
|
|
|
|
|
|
|
# ── Dolt Workbench (web UI) ──
|
|
|
|
|
|
2026-04-15 21:53:57 +00:00
|
|
|
resource "kubernetes_config_map" "workbench_store" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "workbench-store"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
data = {
|
|
|
|
|
"store.json" = jsonencode([{
|
2026-04-17 18:12:31 +00:00
|
|
|
name = "beads"
|
|
|
|
|
connectionUrl = "mysql://beads@dolt.beads-server.svc.cluster.local:3306/code"
|
2026-04-15 21:53:57 +00:00
|
|
|
hideDoltFeatures = false
|
2026-04-17 18:12:31 +00:00
|
|
|
useSSL = false
|
|
|
|
|
type = "Mysql"
|
2026-04-15 21:53:57 +00:00
|
|
|
}])
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2026-04-15 21:32:45 +00:00
|
|
|
resource "kubernetes_deployment" "workbench" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "dolt-workbench"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "dolt-workbench"
|
|
|
|
|
tier = local.tiers.aux
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
replicas = 1
|
|
|
|
|
selector {
|
|
|
|
|
match_labels = {
|
|
|
|
|
app = "dolt-workbench"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
template {
|
|
|
|
|
metadata {
|
|
|
|
|
labels = {
|
|
|
|
|
app = "dolt-workbench"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
2026-04-15 21:53:57 +00:00
|
|
|
init_container {
|
|
|
|
|
name = "seed-config"
|
|
|
|
|
image = "dolthub/dolt-workbench:latest"
|
|
|
|
|
command = ["sh", "-c", <<-EOT
|
|
|
|
|
# Seed connection store
|
|
|
|
|
cp /config/store.json /store/store.json
|
|
|
|
|
# Copy static JS to writable volume and patch GraphQL URL
|
|
|
|
|
cp -r /app/web/.next/static/* /static/
|
|
|
|
|
for f in /static/chunks/pages/_app-*.js; do
|
|
|
|
|
sed -i 's|http://localhost:9002/graphql|/graphql|g' "$f"
|
|
|
|
|
done
|
2026-04-16 13:45:04 +00:00
|
|
|
echo "Patched GraphQL URL and store path"
|
2026-04-15 21:53:57 +00:00
|
|
|
EOT
|
|
|
|
|
]
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "store-config"
|
|
|
|
|
mount_path = "/config"
|
|
|
|
|
read_only = true
|
|
|
|
|
}
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "store"
|
|
|
|
|
mount_path = "/store"
|
|
|
|
|
}
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "static-patched"
|
|
|
|
|
mount_path = "/static"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2026-04-15 21:32:45 +00:00
|
|
|
container {
|
|
|
|
|
name = "workbench"
|
|
|
|
|
image = "dolthub/dolt-workbench:latest"
|
2026-04-16 13:45:04 +00:00
|
|
|
command = ["sh", "-c", <<-EOT
|
|
|
|
|
# Patch GraphQL server to listen on 0.0.0.0 (IPv4) — Node 18+ defaults to IPv6
|
|
|
|
|
sed -i 's|app.listen(9002)|app.listen(9002,"0.0.0.0")|g' /app/graphql-server/dist/main.js
|
2026-04-17 18:12:31 +00:00
|
|
|
# Start PM2, then auto-connect to Dolt after GraphQL is ready
|
|
|
|
|
pm2-runtime /app/process.yml &
|
|
|
|
|
PM2_PID=$!
|
|
|
|
|
# Wait for GraphQL server to be ready, then auto-connect
|
|
|
|
|
for i in $(seq 1 30); do
|
|
|
|
|
if node -e "fetch('http://127.0.0.1:9002/graphql',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({query:'{storedConnections{name}}'})}).then(r=>{if(r.ok)process.exit(0);process.exit(1)}).catch(()=>process.exit(1))" 2>/dev/null; then
|
|
|
|
|
node -e "fetch('http://127.0.0.1:9002/graphql',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({query:'mutation{addDatabaseConnection(connectionUrl:\"mysql://beads@dolt.beads-server.svc.cluster.local:3306/code\",name:\"beads\",hideDoltFeatures:false,useSSL:false,type:Mysql){currentDatabase}}'})}).then(r=>r.text()).then(t=>{console.log('Auto-connect:',t);process.exit(0)}).catch(e=>{console.error(e);process.exit(1)})" 2>&1
|
|
|
|
|
break
|
|
|
|
|
fi
|
|
|
|
|
sleep 1
|
|
|
|
|
done &
|
|
|
|
|
wait $PM2_PID
|
2026-04-16 13:45:04 +00:00
|
|
|
EOT
|
|
|
|
|
]
|
2026-04-15 21:32:45 +00:00
|
|
|
|
|
|
|
|
port {
|
|
|
|
|
name = "http"
|
|
|
|
|
container_port = 3000
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
name = "graphql"
|
|
|
|
|
container_port = 9002
|
|
|
|
|
}
|
|
|
|
|
|
2026-04-16 13:45:04 +00:00
|
|
|
env {
|
|
|
|
|
name = "NODE_OPTIONS"
|
|
|
|
|
value = "--dns-result-order=ipv4first"
|
|
|
|
|
}
|
2026-04-17 18:58:59 +00:00
|
|
|
env {
|
|
|
|
|
name = "GRAPHQLAPI_URL"
|
2026-04-17 19:05:47 +00:00
|
|
|
value = "http://localhost:9002/graphql"
|
2026-04-17 18:58:59 +00:00
|
|
|
}
|
2026-04-16 13:45:04 +00:00
|
|
|
|
2026-04-15 21:53:57 +00:00
|
|
|
volume_mount {
|
|
|
|
|
name = "store"
|
2026-04-16 13:45:04 +00:00
|
|
|
mount_path = "/app/graphql-server/store"
|
2026-04-15 21:53:57 +00:00
|
|
|
}
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "static-patched"
|
|
|
|
|
mount_path = "/app/web/.next/static"
|
|
|
|
|
}
|
|
|
|
|
|
2026-04-15 21:32:45 +00:00
|
|
|
startup_probe {
|
|
|
|
|
http_get {
|
|
|
|
|
path = "/"
|
|
|
|
|
port = 3000
|
|
|
|
|
}
|
|
|
|
|
failure_threshold = 30
|
|
|
|
|
period_seconds = 2
|
|
|
|
|
}
|
|
|
|
|
liveness_probe {
|
|
|
|
|
http_get {
|
|
|
|
|
path = "/"
|
|
|
|
|
port = 3000
|
|
|
|
|
}
|
|
|
|
|
initial_delay_seconds = 10
|
|
|
|
|
period_seconds = 30
|
|
|
|
|
}
|
|
|
|
|
readiness_probe {
|
|
|
|
|
http_get {
|
|
|
|
|
path = "/"
|
|
|
|
|
port = 3000
|
|
|
|
|
}
|
|
|
|
|
initial_delay_seconds = 5
|
|
|
|
|
period_seconds = 10
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resources {
|
|
|
|
|
requests = {
|
|
|
|
|
memory = "128Mi"
|
|
|
|
|
cpu = "10m"
|
|
|
|
|
}
|
|
|
|
|
limits = {
|
|
|
|
|
memory = "512Mi"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
2026-04-15 21:53:57 +00:00
|
|
|
|
|
|
|
|
volume {
|
|
|
|
|
name = "store-config"
|
|
|
|
|
config_map {
|
|
|
|
|
name = kubernetes_config_map.workbench_store.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
volume {
|
|
|
|
|
name = "store"
|
|
|
|
|
empty_dir {}
|
|
|
|
|
}
|
|
|
|
|
volume {
|
|
|
|
|
name = "static-patched"
|
|
|
|
|
empty_dir {}
|
|
|
|
|
}
|
2026-04-15 21:32:45 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
lifecycle {
|
|
|
|
|
ignore_changes = [
|
[infra] Establish KYVERNO_LIFECYCLE_V1 drift-suppression convention [ci skip]
## Context
Phase 1 of the state-drift consolidation audit (plan Wave 3) identified that
the entire repo leans on a repeated `lifecycle { ignore_changes = [...dns_config] }`
snippet to suppress Kyverno's admission-webhook dns_config mutation (the ndots=2
override that prevents NxDomain search-domain flooding). 27 occurrences across
19 stacks. Without this suppression, every pod-owning resource shows perpetual
TF plan drift.
The original plan proposed a shared `modules/kubernetes/kyverno_lifecycle/`
module emitting the ignore-paths list as an output that stacks would consume in
their `ignore_changes` blocks. That approach is architecturally impossible:
Terraform's `ignore_changes` meta-argument accepts only static attribute paths
— it rejects module outputs, locals, variables, and any expression (the HCL
spec evaluates `lifecycle` before the regular expression graph). So a DRY
module cannot exist. The canonical pattern IS the repeated snippet.
What the snippet was missing was a *discoverability tag* so that (a) new
resources can be validated for compliance, (b) the existing 27 sites can be
grep'd in a single command, and (c) future maintainers understand the
convention rather than each reinventing it.
## This change
- Introduces `# KYVERNO_LIFECYCLE_V1` as the canonical marker comment.
Attached inline on every `spec[0].template[0].spec[0].dns_config` line
(or `spec[0].job_template[0].spec[0]...` for CronJobs) across all 27
existing suppression sites.
- Documents the convention with rationale and copy-paste snippets in
`AGENTS.md` → new "Kyverno Drift Suppression" section.
- Expands the existing `.claude/CLAUDE.md` Kyverno ndots note to reference
the marker and explain why the module approach is blocked.
- Updates `_template/main.tf.example` so every new stack starts compliant.
## What is NOT in this change
- The `kubernetes_manifest` Kyverno annotation drift (beads `code-seq`)
— that is Phase B with a sibling `# KYVERNO_MANIFEST_V1` marker.
- Behavioral changes — every `ignore_changes` list is byte-identical
save for the inline comment.
- The fallback module the original plan anticipated — skipped because
Terraform rejects expressions in `ignore_changes`.
- `terraform fmt` cleanup on adjacent unrelated blocks in three files
(claude-agent-service, freedify/factory, hermes-agent). Reverted to
keep this commit scoped to the convention rollout.
## Before / after
Before (cannot distinguish accidental-forgotten from intentional-convention):
```hcl
lifecycle {
ignore_changes = [spec[0].template[0].spec[0].dns_config]
}
```
After (greppable, self-documenting, discoverable by tooling):
```hcl
lifecycle {
ignore_changes = [spec[0].template[0].spec[0].dns_config] # KYVERNO_LIFECYCLE_V1
}
```
## Test Plan
### Automated
```
$ rg -c 'KYVERNO_LIFECYCLE_V1' stacks/ --include='*.tf' --include='*.tf.example' \
| awk -F: '{s+=$2} END {print s}'
27
$ git diff --stat | grep -E '\.(tf|tf\.example|md)$' | wc -l
21
# All code-file diffs are 1 insertion + 1 deletion per marker site,
# except beads-server (3), ebooks (4), immich (3), uptime-kuma (2).
$ git diff --stat stacks/ | tail -1
20 files changed, 45 insertions(+), 28 deletions(-)
```
### Manual Verification
No apply required — HCL comments only. Zero effect on any stack's plan output.
Future audits: `rg 'KYVERNO_LIFECYCLE_V1' stacks/ | wc -l` must grow as new
pod-owning resources are added.
## Reproduce locally
1. `cd infra && git pull`
2. `rg 'KYVERNO_LIFECYCLE_V1' stacks/` → expect 27 hits in 19 files
3. Grep any new `kubernetes_deployment` for the marker; absence = missing
suppression.
Closes: code-28m
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 14:15:51 +00:00
|
|
|
spec[0].template[0].spec[0].dns_config # KYVERNO_LIFECYCLE_V1
|
2026-04-15 21:32:45 +00:00
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_service" "workbench" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "dolt-workbench"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "dolt-workbench"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
selector = {
|
|
|
|
|
app = "dolt-workbench"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
name = "http"
|
|
|
|
|
port = 80
|
|
|
|
|
target_port = 3000
|
|
|
|
|
}
|
2026-04-15 21:53:57 +00:00
|
|
|
port {
|
|
|
|
|
name = "graphql"
|
|
|
|
|
port = 9002
|
|
|
|
|
target_port = 9002
|
|
|
|
|
}
|
2026-04-15 21:32:45 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
module "tls_secret" {
|
|
|
|
|
source = "../../modules/kubernetes/setup_tls_secret"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
tls_secret_name = var.tls_secret_name
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
module "ingress" {
|
[infra/beads-server] Wire BeadBoard to claude-agent-service
## Context
BeadBoard is the Next.js task visualization dashboard shipped in this
stack. We want users to trigger headless Claude agent runs directly from
a beads task row — "one-click dispatch" — instead of copy-pasting `bd`
IDs into a terminal. The agent runs in-cluster as claude-agent-service
(see stacks/claude-agent-service/), protected by a bearer token in
Vault at secret/claude-agent-service/api_bearer_token.
For BeadBoard to POST to /execute we need the service URL and the
bearer token available inside the pod as env vars. The URL is static
(cluster DNS); the token must come through External Secrets Operator
so rotation in Vault propagates without re-applying Terraform.
Secondary cleanup: the container was still pinned to :latest which
violates the 8-char-SHA convention and causes stale pulls through the
registry cache (see .claude/CLAUDE.md, Docker images). The image tag
is now variable-driven; the GHA pipeline will override the default
once it publishes the first SHA.
## This change
- Adds an ExternalSecret `beadboard-agent-service` in the
`beads-server` namespace, mirroring the pattern in
stacks/claude-agent-service/main.tf (same Vault path
`secret/claude-agent-service`, same `vault-kv` ClusterSecretStore,
same 15m refresh). Exposes exactly one key: `api_bearer_token`.
- Adds two env vars to the `beadboard` container:
- `CLAUDE_AGENT_SERVICE_URL` — static cluster URL
(`http://claude-agent-service.claude-agent.svc.cluster.local:8080`)
- `CLAUDE_AGENT_BEARER_TOKEN` — `secret_key_ref` pointing at the
ESO-managed Secret, key `api_bearer_token`
- Adds `reloader.stakater.com/auto = "true"` on the Deployment's
top-level metadata — matches the convention used by rybbit,
claude-memory, onlyoffice. When ESO refreshes the K8s Secret
because Vault rotated the token, Reloader restarts the pod so the
new token is picked up (env vars are read once at boot).
- Adds `variable "beadboard_image_tag"` (default `"latest"`, with a
one-line comment flagging the temporary default). The image
reference now interpolates `${var.beadboard_image_tag}`. No tfvars
file is touched — orchestrator will flip the default to the first
real 8-char SHA once GHA publishes it.
## What is NOT in this change
- No GHA workflow additions. The pipeline that builds
`registry.viktorbarzin.me:5050/beadboard` lives in the BeadBoard
repo and is out of scope here.
- No Vault-side changes. `secret/claude-agent-service/api_bearer_token`
already exists (it powers the claude-agent-service deployment
itself).
- No Terraform `apply`. Orchestrator applies.
## Data flow
Vault (secret/claude-agent-service)
│ refresh every 15m
▼
ESO → K8s Secret `beadboard-agent-service` (beads-server ns)
│ envFrom.secretKeyRef
▼
BeadBoard pod (CLAUDE_AGENT_BEARER_TOKEN env)
│ Authorization: Bearer <token>
▼
claude-agent-service.claude-agent.svc:8080 /execute
On Vault rotation: ESO picks up new value at next refresh → K8s
Secret data changes → Reloader sees annotation + referenced Secret
changed → rolling-recreates the beadboard pod with the new token.
## Test Plan
### Automated
- `terraform fmt -recursive stacks/beads-server/` — clean (formatted
the file once; subsequent run is a no-op).
- `terraform -chdir=stacks/beads-server validate` (after
`terraform init -backend=false`) — `Success! The configuration is
valid`. The 14 "Deprecated Resource" warnings are pre-existing
(`kubernetes_namespace` vs `_v1` etc.) and unrelated to this
change.
### Manual Verification
1. Orchestrator applies:
`scripts/tg -chdir=stacks/beads-server apply`
2. Verify the ExternalSecret synced:
`kubectl -n beads-server get externalsecret beadboard-agent-service`
Expected: `Ready=True`, `SyncedAt` recent.
3. Verify the K8s Secret exists with one key:
`kubectl -n beads-server get secret beadboard-agent-service -o jsonpath='{.data.api_bearer_token}' | base64 -d | head -c 8`
Expected: first 8 chars of the bearer token.
4. Verify the deployment picked up the env vars:
`kubectl -n beads-server get deploy beadboard -o yaml | grep -A2 CLAUDE_AGENT`
Expected: both env entries present, bearer via `secretKeyRef`.
5. Verify the reloader annotation is on the Deployment metadata:
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.metadata.annotations.reloader\.stakater\.com/auto}'`
Expected: `true`.
6. Verify the image tag resolved to the variable default (for now):
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.spec.template.spec.containers[0].image}'`
Expected: `registry.viktorbarzin.me:5050/beadboard:latest`
(will become `...:<sha>` once `beadboard_image_tag` default is
updated).
7. Smoke-test the env var inside the pod:
`kubectl -n beads-server exec deploy/beadboard -- sh -c 'printenv CLAUDE_AGENT_SERVICE_URL; printenv CLAUDE_AGENT_BEARER_TOKEN | head -c 8'`
Expected: URL printed, first 8 chars of token printed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 13:53:51 +00:00
|
|
|
source = "../../modules/kubernetes/ingress_factory"
|
|
|
|
|
dns_type = "proxied"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
name = "dolt-workbench"
|
|
|
|
|
tls_secret_name = var.tls_secret_name
|
|
|
|
|
protected = false
|
|
|
|
|
exclude_crowdsec = true
|
2026-04-15 21:32:45 +00:00
|
|
|
extra_annotations = {
|
|
|
|
|
"gethomepage.dev/enabled" = "true"
|
|
|
|
|
"gethomepage.dev/name" = "Dolt Workbench"
|
|
|
|
|
"gethomepage.dev/description" = "Beads task database UI"
|
|
|
|
|
"gethomepage.dev/icon" = "dolt.png"
|
|
|
|
|
"gethomepage.dev/group" = "Core Platform"
|
|
|
|
|
"gethomepage.dev/pod-selector" = ""
|
|
|
|
|
}
|
|
|
|
|
}
|
2026-04-15 21:53:57 +00:00
|
|
|
|
|
|
|
|
# GraphQL API ingress — the frontend JS hardcodes localhost:9002/graphql,
|
|
|
|
|
# but we rewrite the browser request to hit the same hostname on /graphql
|
|
|
|
|
# routed to port 9002.
|
|
|
|
|
resource "kubernetes_ingress_v1" "graphql" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "dolt-workbench-graphql"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
annotations = {
|
2026-04-17 19:05:47 +00:00
|
|
|
# No Authentik — browser fetch() can't follow 302 redirects on POST.
|
|
|
|
|
# Main page (/) is still protected. GraphQL has no sensitive data beyond task list.
|
2026-04-15 21:53:57 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
ingress_class_name = "traefik"
|
|
|
|
|
tls {
|
|
|
|
|
hosts = ["dolt-workbench.viktorbarzin.me"]
|
|
|
|
|
secret_name = var.tls_secret_name
|
|
|
|
|
}
|
|
|
|
|
rule {
|
|
|
|
|
host = "dolt-workbench.viktorbarzin.me"
|
|
|
|
|
http {
|
|
|
|
|
path {
|
|
|
|
|
path = "/graphql"
|
|
|
|
|
path_type = "Exact"
|
|
|
|
|
backend {
|
|
|
|
|
service {
|
|
|
|
|
name = kubernetes_service.workbench.metadata[0].name
|
|
|
|
|
port {
|
|
|
|
|
number = 9002
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
2026-04-17 11:30:43 +00:00
|
|
|
|
|
|
|
|
# ── BeadBoard (task visualization dashboard) ──
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_config_map" "beadboard_config" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "beadboard-beads-config"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
data = {
|
|
|
|
|
"metadata.json" = jsonencode({
|
2026-04-17 18:12:31 +00:00
|
|
|
database = "dolt"
|
|
|
|
|
backend = "dolt"
|
|
|
|
|
dolt_mode = "server"
|
|
|
|
|
dolt_server_host = "dolt.beads-server.svc.cluster.local"
|
|
|
|
|
dolt_server_port = 3306
|
|
|
|
|
dolt_server_user = "root"
|
|
|
|
|
dolt_database = "code"
|
|
|
|
|
project_id = "a8f8bae7-ce65-4145-a5db-a13d11d297da"
|
2026-04-17 11:30:43 +00:00
|
|
|
})
|
|
|
|
|
"dolt-server.port" = "3306"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
[infra/beads-server] Wire BeadBoard to claude-agent-service
## Context
BeadBoard is the Next.js task visualization dashboard shipped in this
stack. We want users to trigger headless Claude agent runs directly from
a beads task row — "one-click dispatch" — instead of copy-pasting `bd`
IDs into a terminal. The agent runs in-cluster as claude-agent-service
(see stacks/claude-agent-service/), protected by a bearer token in
Vault at secret/claude-agent-service/api_bearer_token.
For BeadBoard to POST to /execute we need the service URL and the
bearer token available inside the pod as env vars. The URL is static
(cluster DNS); the token must come through External Secrets Operator
so rotation in Vault propagates without re-applying Terraform.
Secondary cleanup: the container was still pinned to :latest which
violates the 8-char-SHA convention and causes stale pulls through the
registry cache (see .claude/CLAUDE.md, Docker images). The image tag
is now variable-driven; the GHA pipeline will override the default
once it publishes the first SHA.
## This change
- Adds an ExternalSecret `beadboard-agent-service` in the
`beads-server` namespace, mirroring the pattern in
stacks/claude-agent-service/main.tf (same Vault path
`secret/claude-agent-service`, same `vault-kv` ClusterSecretStore,
same 15m refresh). Exposes exactly one key: `api_bearer_token`.
- Adds two env vars to the `beadboard` container:
- `CLAUDE_AGENT_SERVICE_URL` — static cluster URL
(`http://claude-agent-service.claude-agent.svc.cluster.local:8080`)
- `CLAUDE_AGENT_BEARER_TOKEN` — `secret_key_ref` pointing at the
ESO-managed Secret, key `api_bearer_token`
- Adds `reloader.stakater.com/auto = "true"` on the Deployment's
top-level metadata — matches the convention used by rybbit,
claude-memory, onlyoffice. When ESO refreshes the K8s Secret
because Vault rotated the token, Reloader restarts the pod so the
new token is picked up (env vars are read once at boot).
- Adds `variable "beadboard_image_tag"` (default `"latest"`, with a
one-line comment flagging the temporary default). The image
reference now interpolates `${var.beadboard_image_tag}`. No tfvars
file is touched — orchestrator will flip the default to the first
real 8-char SHA once GHA publishes it.
## What is NOT in this change
- No GHA workflow additions. The pipeline that builds
`registry.viktorbarzin.me:5050/beadboard` lives in the BeadBoard
repo and is out of scope here.
- No Vault-side changes. `secret/claude-agent-service/api_bearer_token`
already exists (it powers the claude-agent-service deployment
itself).
- No Terraform `apply`. Orchestrator applies.
## Data flow
Vault (secret/claude-agent-service)
│ refresh every 15m
▼
ESO → K8s Secret `beadboard-agent-service` (beads-server ns)
│ envFrom.secretKeyRef
▼
BeadBoard pod (CLAUDE_AGENT_BEARER_TOKEN env)
│ Authorization: Bearer <token>
▼
claude-agent-service.claude-agent.svc:8080 /execute
On Vault rotation: ESO picks up new value at next refresh → K8s
Secret data changes → Reloader sees annotation + referenced Secret
changed → rolling-recreates the beadboard pod with the new token.
## Test Plan
### Automated
- `terraform fmt -recursive stacks/beads-server/` — clean (formatted
the file once; subsequent run is a no-op).
- `terraform -chdir=stacks/beads-server validate` (after
`terraform init -backend=false`) — `Success! The configuration is
valid`. The 14 "Deprecated Resource" warnings are pre-existing
(`kubernetes_namespace` vs `_v1` etc.) and unrelated to this
change.
### Manual Verification
1. Orchestrator applies:
`scripts/tg -chdir=stacks/beads-server apply`
2. Verify the ExternalSecret synced:
`kubectl -n beads-server get externalsecret beadboard-agent-service`
Expected: `Ready=True`, `SyncedAt` recent.
3. Verify the K8s Secret exists with one key:
`kubectl -n beads-server get secret beadboard-agent-service -o jsonpath='{.data.api_bearer_token}' | base64 -d | head -c 8`
Expected: first 8 chars of the bearer token.
4. Verify the deployment picked up the env vars:
`kubectl -n beads-server get deploy beadboard -o yaml | grep -A2 CLAUDE_AGENT`
Expected: both env entries present, bearer via `secretKeyRef`.
5. Verify the reloader annotation is on the Deployment metadata:
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.metadata.annotations.reloader\.stakater\.com/auto}'`
Expected: `true`.
6. Verify the image tag resolved to the variable default (for now):
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.spec.template.spec.containers[0].image}'`
Expected: `registry.viktorbarzin.me:5050/beadboard:latest`
(will become `...:<sha>` once `beadboard_image_tag` default is
updated).
7. Smoke-test the env var inside the pod:
`kubectl -n beads-server exec deploy/beadboard -- sh -c 'printenv CLAUDE_AGENT_SERVICE_URL; printenv CLAUDE_AGENT_BEARER_TOKEN | head -c 8'`
Expected: URL printed, first 8 chars of token printed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 13:53:51 +00:00
|
|
|
# Pulls the claude-agent-service bearer token from Vault so BeadBoard can
|
|
|
|
|
# dispatch agent jobs via the in-cluster HTTP API.
|
|
|
|
|
resource "kubernetes_manifest" "beadboard_agent_service_secret" {
|
|
|
|
|
manifest = {
|
|
|
|
|
apiVersion = "external-secrets.io/v1beta1"
|
|
|
|
|
kind = "ExternalSecret"
|
|
|
|
|
metadata = {
|
|
|
|
|
name = "beadboard-agent-service"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
spec = {
|
|
|
|
|
refreshInterval = "15m"
|
|
|
|
|
secretStoreRef = {
|
|
|
|
|
name = "vault-kv"
|
|
|
|
|
kind = "ClusterSecretStore"
|
|
|
|
|
}
|
|
|
|
|
target = {
|
|
|
|
|
name = "beadboard-agent-service"
|
|
|
|
|
}
|
|
|
|
|
data = [
|
|
|
|
|
{
|
|
|
|
|
secretKey = "api_bearer_token"
|
|
|
|
|
remoteRef = {
|
|
|
|
|
key = "claude-agent-service"
|
|
|
|
|
property = "api_bearer_token"
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2026-04-17 11:30:43 +00:00
|
|
|
resource "kubernetes_deployment" "beadboard" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "beadboard"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "beadboard"
|
|
|
|
|
tier = local.tiers.aux
|
|
|
|
|
}
|
[infra/beads-server] Wire BeadBoard to claude-agent-service
## Context
BeadBoard is the Next.js task visualization dashboard shipped in this
stack. We want users to trigger headless Claude agent runs directly from
a beads task row — "one-click dispatch" — instead of copy-pasting `bd`
IDs into a terminal. The agent runs in-cluster as claude-agent-service
(see stacks/claude-agent-service/), protected by a bearer token in
Vault at secret/claude-agent-service/api_bearer_token.
For BeadBoard to POST to /execute we need the service URL and the
bearer token available inside the pod as env vars. The URL is static
(cluster DNS); the token must come through External Secrets Operator
so rotation in Vault propagates without re-applying Terraform.
Secondary cleanup: the container was still pinned to :latest which
violates the 8-char-SHA convention and causes stale pulls through the
registry cache (see .claude/CLAUDE.md, Docker images). The image tag
is now variable-driven; the GHA pipeline will override the default
once it publishes the first SHA.
## This change
- Adds an ExternalSecret `beadboard-agent-service` in the
`beads-server` namespace, mirroring the pattern in
stacks/claude-agent-service/main.tf (same Vault path
`secret/claude-agent-service`, same `vault-kv` ClusterSecretStore,
same 15m refresh). Exposes exactly one key: `api_bearer_token`.
- Adds two env vars to the `beadboard` container:
- `CLAUDE_AGENT_SERVICE_URL` — static cluster URL
(`http://claude-agent-service.claude-agent.svc.cluster.local:8080`)
- `CLAUDE_AGENT_BEARER_TOKEN` — `secret_key_ref` pointing at the
ESO-managed Secret, key `api_bearer_token`
- Adds `reloader.stakater.com/auto = "true"` on the Deployment's
top-level metadata — matches the convention used by rybbit,
claude-memory, onlyoffice. When ESO refreshes the K8s Secret
because Vault rotated the token, Reloader restarts the pod so the
new token is picked up (env vars are read once at boot).
- Adds `variable "beadboard_image_tag"` (default `"latest"`, with a
one-line comment flagging the temporary default). The image
reference now interpolates `${var.beadboard_image_tag}`. No tfvars
file is touched — orchestrator will flip the default to the first
real 8-char SHA once GHA publishes it.
## What is NOT in this change
- No GHA workflow additions. The pipeline that builds
`registry.viktorbarzin.me:5050/beadboard` lives in the BeadBoard
repo and is out of scope here.
- No Vault-side changes. `secret/claude-agent-service/api_bearer_token`
already exists (it powers the claude-agent-service deployment
itself).
- No Terraform `apply`. Orchestrator applies.
## Data flow
Vault (secret/claude-agent-service)
│ refresh every 15m
▼
ESO → K8s Secret `beadboard-agent-service` (beads-server ns)
│ envFrom.secretKeyRef
▼
BeadBoard pod (CLAUDE_AGENT_BEARER_TOKEN env)
│ Authorization: Bearer <token>
▼
claude-agent-service.claude-agent.svc:8080 /execute
On Vault rotation: ESO picks up new value at next refresh → K8s
Secret data changes → Reloader sees annotation + referenced Secret
changed → rolling-recreates the beadboard pod with the new token.
## Test Plan
### Automated
- `terraform fmt -recursive stacks/beads-server/` — clean (formatted
the file once; subsequent run is a no-op).
- `terraform -chdir=stacks/beads-server validate` (after
`terraform init -backend=false`) — `Success! The configuration is
valid`. The 14 "Deprecated Resource" warnings are pre-existing
(`kubernetes_namespace` vs `_v1` etc.) and unrelated to this
change.
### Manual Verification
1. Orchestrator applies:
`scripts/tg -chdir=stacks/beads-server apply`
2. Verify the ExternalSecret synced:
`kubectl -n beads-server get externalsecret beadboard-agent-service`
Expected: `Ready=True`, `SyncedAt` recent.
3. Verify the K8s Secret exists with one key:
`kubectl -n beads-server get secret beadboard-agent-service -o jsonpath='{.data.api_bearer_token}' | base64 -d | head -c 8`
Expected: first 8 chars of the bearer token.
4. Verify the deployment picked up the env vars:
`kubectl -n beads-server get deploy beadboard -o yaml | grep -A2 CLAUDE_AGENT`
Expected: both env entries present, bearer via `secretKeyRef`.
5. Verify the reloader annotation is on the Deployment metadata:
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.metadata.annotations.reloader\.stakater\.com/auto}'`
Expected: `true`.
6. Verify the image tag resolved to the variable default (for now):
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.spec.template.spec.containers[0].image}'`
Expected: `registry.viktorbarzin.me:5050/beadboard:latest`
(will become `...:<sha>` once `beadboard_image_tag` default is
updated).
7. Smoke-test the env var inside the pod:
`kubectl -n beads-server exec deploy/beadboard -- sh -c 'printenv CLAUDE_AGENT_SERVICE_URL; printenv CLAUDE_AGENT_BEARER_TOKEN | head -c 8'`
Expected: URL printed, first 8 chars of token printed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 13:53:51 +00:00
|
|
|
annotations = {
|
|
|
|
|
"reloader.stakater.com/auto" = "true"
|
|
|
|
|
}
|
2026-04-17 11:30:43 +00:00
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
replicas = 1
|
|
|
|
|
selector {
|
|
|
|
|
match_labels = {
|
|
|
|
|
app = "beadboard"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
template {
|
|
|
|
|
metadata {
|
|
|
|
|
labels = {
|
|
|
|
|
app = "beadboard"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
image_pull_secrets {
|
|
|
|
|
name = "registry-credentials"
|
|
|
|
|
}
|
|
|
|
|
|
2026-04-17 11:37:26 +00:00
|
|
|
init_container {
|
2026-04-17 18:12:31 +00:00
|
|
|
name = "seed-beads-config"
|
|
|
|
|
image = "busybox:1.36"
|
2026-04-17 11:37:26 +00:00
|
|
|
command = ["sh", "-c", "cp /config/* /beads/ && mkdir -p /beads/templates /beads/archetypes"]
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "beads-config"
|
|
|
|
|
mount_path = "/config"
|
|
|
|
|
read_only = true
|
|
|
|
|
}
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "beads-writable"
|
|
|
|
|
mount_path = "/beads"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2026-04-17 11:30:43 +00:00
|
|
|
container {
|
|
|
|
|
name = "beadboard"
|
[forgejo] Phases 3+4+5: cutover, decommission, docs sweep
End of forgejo-registry-consolidation. After Phase 0/1 already landed
(Forgejo ready, dual-push CI, integrity probe, retention CronJob,
images migrated via forgejo-migrate-orphan-images.sh), this commit
flips everything off registry.viktorbarzin.me onto Forgejo and
removes the legacy infrastructure.
Phase 3 — image= flips:
* infra/stacks/{payslip-ingest,job-hunter,claude-agent-service,
fire-planner,freedify/factory,chrome-service,beads-server}/main.tf
— image= now points to forgejo.viktorbarzin.me/viktor/<name>.
* infra/stacks/claude-memory/main.tf — also moved off DockerHub
(viktorbarzin/claude-memory-mcp:17 → forgejo.viktorbarzin.me/viktor/...).
* infra/.woodpecker/{default,drift-detection}.yml — infra-ci pulled
from Forgejo. build-ci-image.yml dual-pushes still until next
build cycle confirms Forgejo as canonical.
* /home/wizard/code/CLAUDE.md — claude-memory-mcp install URL updated.
Phase 4 — decommission registry-private:
* registry-credentials Secret: dropped registry.viktorbarzin.me /
registry.viktorbarzin.me:5050 / 10.0.20.10:5050 auths entries.
Forgejo entry is the only one left.
* infra/stacks/infra/main.tf cloud-init: dropped containerd
hosts.toml entries for registry.viktorbarzin.me +
10.0.20.10:5050. (Existing nodes already had the file removed
manually by `setup-forgejo-containerd-mirror.sh` rollout — the
cloud-init template only fires on new VM provision.)
* infra/modules/docker-registry/docker-compose.yml: registry-private
service block removed; nginx 5050 port mapping dropped. Pull-
through caches for upstream registries (5000/5010/5020/5030/5040)
stay on the VM permanently.
* infra/modules/docker-registry/nginx_registry.conf: upstream
`private` block + port 5050 server block removed.
* infra/stacks/monitoring/modules/monitoring/main.tf: registry_
integrity_probe + registry_probe_credentials resources stripped.
forgejo_integrity_probe is the only manifest probe now.
Phase 5 — final docs sweep:
* infra/docs/runbooks/registry-vm.md — VM scope reduced to pull-
through caches; forgejo-registry-breakglass.md cross-ref added.
* infra/docs/architecture/ci-cd.md — registry component table +
diagram now reflect Forgejo. Pre-migration root-cause sentence
preserved as historical context with a pointer to the design doc.
* infra/docs/architecture/monitoring.md — Registry Integrity Probe
row updated to point at the Forgejo probe.
* infra/.claude/CLAUDE.md — Private registry section rewritten end-
to-end (auth, retention, integrity, where the bake came from).
* prometheus_chart_values.tpl — RegistryManifestIntegrityFailure
alert annotation simplified now that only one registry is in
scope.
Operational follow-up (cannot be done from a TF apply):
1. ssh root@10.0.20.10 — edit /opt/registry/docker-compose.yml to
match the new template AND `docker compose up -d --remove-orphans`
to actually stop the registry-private container. Memory id=1078
confirms cloud-init won't redeploy on TF apply alone.
2. After 1 week of no incidents, `rm -rf /opt/registry/data/private/`
on the VM (~2.6GB freed).
3. Open the dual-push step in build-ci-image.yml and drop
registry.viktorbarzin.me:5050 from the `repo:` list — at that
point the post-push integrity check at line 33-107 also needs
to be repointed at Forgejo or removed (the per-build verify is
redundant with the every-15min Forgejo probe).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-07 18:30:02 +00:00
|
|
|
# Phase 3 cutover 2026-05-07 — Forgejo registry consolidation.
|
|
|
|
|
image = "forgejo.viktorbarzin.me/viktor/beadboard:${var.beadboard_image_tag}"
|
2026-04-17 11:30:43 +00:00
|
|
|
|
|
|
|
|
port {
|
|
|
|
|
name = "http"
|
|
|
|
|
container_port = 3000
|
|
|
|
|
}
|
|
|
|
|
|
[infra/beads-server] Wire BeadBoard to claude-agent-service
## Context
BeadBoard is the Next.js task visualization dashboard shipped in this
stack. We want users to trigger headless Claude agent runs directly from
a beads task row — "one-click dispatch" — instead of copy-pasting `bd`
IDs into a terminal. The agent runs in-cluster as claude-agent-service
(see stacks/claude-agent-service/), protected by a bearer token in
Vault at secret/claude-agent-service/api_bearer_token.
For BeadBoard to POST to /execute we need the service URL and the
bearer token available inside the pod as env vars. The URL is static
(cluster DNS); the token must come through External Secrets Operator
so rotation in Vault propagates without re-applying Terraform.
Secondary cleanup: the container was still pinned to :latest which
violates the 8-char-SHA convention and causes stale pulls through the
registry cache (see .claude/CLAUDE.md, Docker images). The image tag
is now variable-driven; the GHA pipeline will override the default
once it publishes the first SHA.
## This change
- Adds an ExternalSecret `beadboard-agent-service` in the
`beads-server` namespace, mirroring the pattern in
stacks/claude-agent-service/main.tf (same Vault path
`secret/claude-agent-service`, same `vault-kv` ClusterSecretStore,
same 15m refresh). Exposes exactly one key: `api_bearer_token`.
- Adds two env vars to the `beadboard` container:
- `CLAUDE_AGENT_SERVICE_URL` — static cluster URL
(`http://claude-agent-service.claude-agent.svc.cluster.local:8080`)
- `CLAUDE_AGENT_BEARER_TOKEN` — `secret_key_ref` pointing at the
ESO-managed Secret, key `api_bearer_token`
- Adds `reloader.stakater.com/auto = "true"` on the Deployment's
top-level metadata — matches the convention used by rybbit,
claude-memory, onlyoffice. When ESO refreshes the K8s Secret
because Vault rotated the token, Reloader restarts the pod so the
new token is picked up (env vars are read once at boot).
- Adds `variable "beadboard_image_tag"` (default `"latest"`, with a
one-line comment flagging the temporary default). The image
reference now interpolates `${var.beadboard_image_tag}`. No tfvars
file is touched — orchestrator will flip the default to the first
real 8-char SHA once GHA publishes it.
## What is NOT in this change
- No GHA workflow additions. The pipeline that builds
`registry.viktorbarzin.me:5050/beadboard` lives in the BeadBoard
repo and is out of scope here.
- No Vault-side changes. `secret/claude-agent-service/api_bearer_token`
already exists (it powers the claude-agent-service deployment
itself).
- No Terraform `apply`. Orchestrator applies.
## Data flow
Vault (secret/claude-agent-service)
│ refresh every 15m
▼
ESO → K8s Secret `beadboard-agent-service` (beads-server ns)
│ envFrom.secretKeyRef
▼
BeadBoard pod (CLAUDE_AGENT_BEARER_TOKEN env)
│ Authorization: Bearer <token>
▼
claude-agent-service.claude-agent.svc:8080 /execute
On Vault rotation: ESO picks up new value at next refresh → K8s
Secret data changes → Reloader sees annotation + referenced Secret
changed → rolling-recreates the beadboard pod with the new token.
## Test Plan
### Automated
- `terraform fmt -recursive stacks/beads-server/` — clean (formatted
the file once; subsequent run is a no-op).
- `terraform -chdir=stacks/beads-server validate` (after
`terraform init -backend=false`) — `Success! The configuration is
valid`. The 14 "Deprecated Resource" warnings are pre-existing
(`kubernetes_namespace` vs `_v1` etc.) and unrelated to this
change.
### Manual Verification
1. Orchestrator applies:
`scripts/tg -chdir=stacks/beads-server apply`
2. Verify the ExternalSecret synced:
`kubectl -n beads-server get externalsecret beadboard-agent-service`
Expected: `Ready=True`, `SyncedAt` recent.
3. Verify the K8s Secret exists with one key:
`kubectl -n beads-server get secret beadboard-agent-service -o jsonpath='{.data.api_bearer_token}' | base64 -d | head -c 8`
Expected: first 8 chars of the bearer token.
4. Verify the deployment picked up the env vars:
`kubectl -n beads-server get deploy beadboard -o yaml | grep -A2 CLAUDE_AGENT`
Expected: both env entries present, bearer via `secretKeyRef`.
5. Verify the reloader annotation is on the Deployment metadata:
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.metadata.annotations.reloader\.stakater\.com/auto}'`
Expected: `true`.
6. Verify the image tag resolved to the variable default (for now):
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.spec.template.spec.containers[0].image}'`
Expected: `registry.viktorbarzin.me:5050/beadboard:latest`
(will become `...:<sha>` once `beadboard_image_tag` default is
updated).
7. Smoke-test the env var inside the pod:
`kubectl -n beads-server exec deploy/beadboard -- sh -c 'printenv CLAUDE_AGENT_SERVICE_URL; printenv CLAUDE_AGENT_BEARER_TOKEN | head -c 8'`
Expected: URL printed, first 8 chars of token printed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 13:53:51 +00:00
|
|
|
env {
|
|
|
|
|
name = "CLAUDE_AGENT_SERVICE_URL"
|
|
|
|
|
value = "http://claude-agent-service.claude-agent.svc.cluster.local:8080"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
env {
|
|
|
|
|
name = "CLAUDE_AGENT_BEARER_TOKEN"
|
|
|
|
|
value_from {
|
|
|
|
|
secret_key_ref {
|
|
|
|
|
name = "beadboard-agent-service"
|
|
|
|
|
key = "api_bearer_token"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2026-04-17 11:30:43 +00:00
|
|
|
volume_mount {
|
2026-04-17 11:37:26 +00:00
|
|
|
name = "beads-writable"
|
2026-04-17 11:30:43 +00:00
|
|
|
mount_path = "/app/.beads"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
startup_probe {
|
|
|
|
|
http_get {
|
|
|
|
|
path = "/"
|
|
|
|
|
port = 3000
|
|
|
|
|
}
|
|
|
|
|
failure_threshold = 30
|
|
|
|
|
period_seconds = 2
|
|
|
|
|
}
|
|
|
|
|
liveness_probe {
|
|
|
|
|
http_get {
|
|
|
|
|
path = "/"
|
|
|
|
|
port = 3000
|
|
|
|
|
}
|
|
|
|
|
initial_delay_seconds = 10
|
|
|
|
|
period_seconds = 30
|
|
|
|
|
}
|
|
|
|
|
readiness_probe {
|
|
|
|
|
http_get {
|
|
|
|
|
path = "/"
|
|
|
|
|
port = 3000
|
|
|
|
|
}
|
|
|
|
|
initial_delay_seconds = 5
|
|
|
|
|
period_seconds = 10
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resources {
|
|
|
|
|
requests = {
|
|
|
|
|
memory = "256Mi"
|
|
|
|
|
cpu = "50m"
|
|
|
|
|
}
|
|
|
|
|
limits = {
|
|
|
|
|
memory = "512Mi"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
volume {
|
|
|
|
|
name = "beads-config"
|
|
|
|
|
config_map {
|
|
|
|
|
name = kubernetes_config_map.beadboard_config.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
}
|
2026-04-17 11:37:26 +00:00
|
|
|
volume {
|
|
|
|
|
name = "beads-writable"
|
|
|
|
|
empty_dir {}
|
|
|
|
|
}
|
2026-04-17 11:30:43 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
lifecycle {
|
|
|
|
|
ignore_changes = [
|
[infra] Establish KYVERNO_LIFECYCLE_V1 drift-suppression convention [ci skip]
## Context
Phase 1 of the state-drift consolidation audit (plan Wave 3) identified that
the entire repo leans on a repeated `lifecycle { ignore_changes = [...dns_config] }`
snippet to suppress Kyverno's admission-webhook dns_config mutation (the ndots=2
override that prevents NxDomain search-domain flooding). 27 occurrences across
19 stacks. Without this suppression, every pod-owning resource shows perpetual
TF plan drift.
The original plan proposed a shared `modules/kubernetes/kyverno_lifecycle/`
module emitting the ignore-paths list as an output that stacks would consume in
their `ignore_changes` blocks. That approach is architecturally impossible:
Terraform's `ignore_changes` meta-argument accepts only static attribute paths
— it rejects module outputs, locals, variables, and any expression (the HCL
spec evaluates `lifecycle` before the regular expression graph). So a DRY
module cannot exist. The canonical pattern IS the repeated snippet.
What the snippet was missing was a *discoverability tag* so that (a) new
resources can be validated for compliance, (b) the existing 27 sites can be
grep'd in a single command, and (c) future maintainers understand the
convention rather than each reinventing it.
## This change
- Introduces `# KYVERNO_LIFECYCLE_V1` as the canonical marker comment.
Attached inline on every `spec[0].template[0].spec[0].dns_config` line
(or `spec[0].job_template[0].spec[0]...` for CronJobs) across all 27
existing suppression sites.
- Documents the convention with rationale and copy-paste snippets in
`AGENTS.md` → new "Kyverno Drift Suppression" section.
- Expands the existing `.claude/CLAUDE.md` Kyverno ndots note to reference
the marker and explain why the module approach is blocked.
- Updates `_template/main.tf.example` so every new stack starts compliant.
## What is NOT in this change
- The `kubernetes_manifest` Kyverno annotation drift (beads `code-seq`)
— that is Phase B with a sibling `# KYVERNO_MANIFEST_V1` marker.
- Behavioral changes — every `ignore_changes` list is byte-identical
save for the inline comment.
- The fallback module the original plan anticipated — skipped because
Terraform rejects expressions in `ignore_changes`.
- `terraform fmt` cleanup on adjacent unrelated blocks in three files
(claude-agent-service, freedify/factory, hermes-agent). Reverted to
keep this commit scoped to the convention rollout.
## Before / after
Before (cannot distinguish accidental-forgotten from intentional-convention):
```hcl
lifecycle {
ignore_changes = [spec[0].template[0].spec[0].dns_config]
}
```
After (greppable, self-documenting, discoverable by tooling):
```hcl
lifecycle {
ignore_changes = [spec[0].template[0].spec[0].dns_config] # KYVERNO_LIFECYCLE_V1
}
```
## Test Plan
### Automated
```
$ rg -c 'KYVERNO_LIFECYCLE_V1' stacks/ --include='*.tf' --include='*.tf.example' \
| awk -F: '{s+=$2} END {print s}'
27
$ git diff --stat | grep -E '\.(tf|tf\.example|md)$' | wc -l
21
# All code-file diffs are 1 insertion + 1 deletion per marker site,
# except beads-server (3), ebooks (4), immich (3), uptime-kuma (2).
$ git diff --stat stacks/ | tail -1
20 files changed, 45 insertions(+), 28 deletions(-)
```
### Manual Verification
No apply required — HCL comments only. Zero effect on any stack's plan output.
Future audits: `rg 'KYVERNO_LIFECYCLE_V1' stacks/ | wc -l` must grow as new
pod-owning resources are added.
## Reproduce locally
1. `cd infra && git pull`
2. `rg 'KYVERNO_LIFECYCLE_V1' stacks/` → expect 27 hits in 19 files
3. Grep any new `kubernetes_deployment` for the marker; absence = missing
suppression.
Closes: code-28m
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 14:15:51 +00:00
|
|
|
spec[0].template[0].spec[0].dns_config # KYVERNO_LIFECYCLE_V1
|
2026-04-17 11:30:43 +00:00
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_service" "beadboard" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "beadboard"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "beadboard"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
selector = {
|
|
|
|
|
app = "beadboard"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
name = "http"
|
|
|
|
|
port = 80
|
|
|
|
|
target_port = 3000
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
module "beadboard_ingress" {
|
[infra/beads-server] Wire BeadBoard to claude-agent-service
## Context
BeadBoard is the Next.js task visualization dashboard shipped in this
stack. We want users to trigger headless Claude agent runs directly from
a beads task row — "one-click dispatch" — instead of copy-pasting `bd`
IDs into a terminal. The agent runs in-cluster as claude-agent-service
(see stacks/claude-agent-service/), protected by a bearer token in
Vault at secret/claude-agent-service/api_bearer_token.
For BeadBoard to POST to /execute we need the service URL and the
bearer token available inside the pod as env vars. The URL is static
(cluster DNS); the token must come through External Secrets Operator
so rotation in Vault propagates without re-applying Terraform.
Secondary cleanup: the container was still pinned to :latest which
violates the 8-char-SHA convention and causes stale pulls through the
registry cache (see .claude/CLAUDE.md, Docker images). The image tag
is now variable-driven; the GHA pipeline will override the default
once it publishes the first SHA.
## This change
- Adds an ExternalSecret `beadboard-agent-service` in the
`beads-server` namespace, mirroring the pattern in
stacks/claude-agent-service/main.tf (same Vault path
`secret/claude-agent-service`, same `vault-kv` ClusterSecretStore,
same 15m refresh). Exposes exactly one key: `api_bearer_token`.
- Adds two env vars to the `beadboard` container:
- `CLAUDE_AGENT_SERVICE_URL` — static cluster URL
(`http://claude-agent-service.claude-agent.svc.cluster.local:8080`)
- `CLAUDE_AGENT_BEARER_TOKEN` — `secret_key_ref` pointing at the
ESO-managed Secret, key `api_bearer_token`
- Adds `reloader.stakater.com/auto = "true"` on the Deployment's
top-level metadata — matches the convention used by rybbit,
claude-memory, onlyoffice. When ESO refreshes the K8s Secret
because Vault rotated the token, Reloader restarts the pod so the
new token is picked up (env vars are read once at boot).
- Adds `variable "beadboard_image_tag"` (default `"latest"`, with a
one-line comment flagging the temporary default). The image
reference now interpolates `${var.beadboard_image_tag}`. No tfvars
file is touched — orchestrator will flip the default to the first
real 8-char SHA once GHA publishes it.
## What is NOT in this change
- No GHA workflow additions. The pipeline that builds
`registry.viktorbarzin.me:5050/beadboard` lives in the BeadBoard
repo and is out of scope here.
- No Vault-side changes. `secret/claude-agent-service/api_bearer_token`
already exists (it powers the claude-agent-service deployment
itself).
- No Terraform `apply`. Orchestrator applies.
## Data flow
Vault (secret/claude-agent-service)
│ refresh every 15m
▼
ESO → K8s Secret `beadboard-agent-service` (beads-server ns)
│ envFrom.secretKeyRef
▼
BeadBoard pod (CLAUDE_AGENT_BEARER_TOKEN env)
│ Authorization: Bearer <token>
▼
claude-agent-service.claude-agent.svc:8080 /execute
On Vault rotation: ESO picks up new value at next refresh → K8s
Secret data changes → Reloader sees annotation + referenced Secret
changed → rolling-recreates the beadboard pod with the new token.
## Test Plan
### Automated
- `terraform fmt -recursive stacks/beads-server/` — clean (formatted
the file once; subsequent run is a no-op).
- `terraform -chdir=stacks/beads-server validate` (after
`terraform init -backend=false`) — `Success! The configuration is
valid`. The 14 "Deprecated Resource" warnings are pre-existing
(`kubernetes_namespace` vs `_v1` etc.) and unrelated to this
change.
### Manual Verification
1. Orchestrator applies:
`scripts/tg -chdir=stacks/beads-server apply`
2. Verify the ExternalSecret synced:
`kubectl -n beads-server get externalsecret beadboard-agent-service`
Expected: `Ready=True`, `SyncedAt` recent.
3. Verify the K8s Secret exists with one key:
`kubectl -n beads-server get secret beadboard-agent-service -o jsonpath='{.data.api_bearer_token}' | base64 -d | head -c 8`
Expected: first 8 chars of the bearer token.
4. Verify the deployment picked up the env vars:
`kubectl -n beads-server get deploy beadboard -o yaml | grep -A2 CLAUDE_AGENT`
Expected: both env entries present, bearer via `secretKeyRef`.
5. Verify the reloader annotation is on the Deployment metadata:
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.metadata.annotations.reloader\.stakater\.com/auto}'`
Expected: `true`.
6. Verify the image tag resolved to the variable default (for now):
`kubectl -n beads-server get deploy beadboard -o jsonpath='{.spec.template.spec.containers[0].image}'`
Expected: `registry.viktorbarzin.me:5050/beadboard:latest`
(will become `...:<sha>` once `beadboard_image_tag` default is
updated).
7. Smoke-test the env var inside the pod:
`kubectl -n beads-server exec deploy/beadboard -- sh -c 'printenv CLAUDE_AGENT_SERVICE_URL; printenv CLAUDE_AGENT_BEARER_TOKEN | head -c 8'`
Expected: URL printed, first 8 chars of token printed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 13:53:51 +00:00
|
|
|
source = "../../modules/kubernetes/ingress_factory"
|
|
|
|
|
dns_type = "proxied"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
name = "beadboard"
|
|
|
|
|
tls_secret_name = var.tls_secret_name
|
|
|
|
|
protected = true
|
|
|
|
|
exclude_crowdsec = true
|
2026-04-17 11:30:43 +00:00
|
|
|
extra_annotations = {
|
|
|
|
|
"gethomepage.dev/enabled" = "true"
|
|
|
|
|
"gethomepage.dev/name" = "BeadBoard"
|
|
|
|
|
"gethomepage.dev/description" = "Agent task visualization dashboard"
|
|
|
|
|
"gethomepage.dev/icon" = "mdi-chart-gantt"
|
|
|
|
|
"gethomepage.dev/group" = "Core Platform"
|
|
|
|
|
"gethomepage.dev/pod-selector" = ""
|
|
|
|
|
}
|
|
|
|
|
}
|
[beads-server] Auto-dispatch agent beads via CronJobs
## Context
Until now, handing work to the in-cluster `beads-task-runner` agent required
opening BeadBoard and clicking the manual Dispatch button on each bead. We
want users to be able to describe work as a bead, set `assignee=agent`, and
have the agent pick it up within a couple of minutes — no clicks.
The existing pieces already provide everything we need:
- `claude-agent-service` exposes `/execute` with a single-slot `asyncio.Lock`
- BeadBoard's `/api/agent-dispatch` builds the prompt and forwards the bearer
- BeadBoard's `/api/agent-status` reports `busy` via a cached `/health` poll
- Dolt stores beads and is already in-cluster at `dolt.beads-server:3306`
So the only missing component is a poller that ties them together. This
commit adds that poller as two Kubernetes CronJobs — matching the existing
infra pattern (OpenClaw task-processor, certbot-renewal, backups) rather than
introducing n8n or in-service polling.
## Flow
```
user: bd assign <id> agent
│
▼
Dolt @ dolt.beads-server.svc:3306 ◄──── every 2 min ────┐
│ │
▼ │
CronJob: beads-dispatcher │
1. GET beadboard/api/agent-status (busy? skip) │
2. bd query 'assignee=agent AND status=open' │
3. bd update -s in_progress (claim) │
4. POST beadboard/api/agent-dispatch │
5. bd note "dispatched: job=…" │
│ │
▼ │
claude-agent-service /execute │
beads-task-runner agent runs; notes/closes bead │
│ │
▼ │
done ──► next tick picks up the next bead ───────────────┘
CronJob: beads-reaper (every 10 min)
for bead (assignee=agent, status=in_progress, updated_at > 30 min):
bd note "reaper: no progress for Nm — blocking"
bd update -s blocked
```
## Decisions
- **Sentinel assignee `agent`** — free-form, no Beads schema change. Any bd
client can set it (`bd assign <id> agent`).
- **Sequential dispatch** — matches the service's `asyncio.Lock`. With a
2-min poll cadence and ~5-min average run, throughput is ~12 beads/hour.
Parallelism is a separate plan.
- **Fixed agent `beads-task-runner`** — read-only rails, matches the manual
Dispatch button. Broader-privilege agents stay manual via BeadBoard UI.
- **Image reuse** — the claude-agent-service image already ships `bd`, `jq`,
`curl`; a new CronJob-specific image would duplicate 400MB of infra tooling.
Mirror `claude_agent_service_image_tag` locally; bump on rebuild.
- **ConfigMap-mounted `metadata.json`** — declarative TF rather than reusing
the image-seeded file. The script copies it into `/tmp/.beads/` because bd
may touch the parent dir and ConfigMap mounts are read-only.
- **Kill switch (`beads_dispatcher_enabled`)** — single bool, default true.
When false, `suspend: true` on both CronJobs; manual Dispatch keeps working.
- **Reaper threshold 30 min** — `bd note` bumps `updated_at`, so a well-behaved
`beads-task-runner` never trips the reaper. Failures trip it; pod crashes
(in-memory job state lost) also trip it.
## What is NOT in this change
- No Terraform apply — requires Vault OIDC + cluster access. Apply manually:
`cd infra/stacks/beads-server && scripts/tg apply`
- No change to `claude-agent-service/` (already ships bd/jq/curl)
- No change to `beadboard/` (`/api/agent-dispatch` + `/api/agent-status` reused)
- No change to the `beads-task-runner` agent definition (rails unchanged)
- Parallelism: single-slot is MVP; multi-slot dispatch is a separate plan.
## Deviations from plan
Minor, documented in code comments:
- Reaper uses `.updated_at` instead of the plan's `.notes[].created_at`. bd
serializes `notes` as a string (not an array), and every `bd note` bumps
`updated_at` — equivalent for the reaper's purpose.
- ISO-8601 parsed via `python3`, not `date -d` — Alpine's busybox lacks GNU
`-d` and the image has python3.
- `HOME=/tmp` set as a safety net — bd may try to write state/lock files.
## Test plan
### Automated
```
$ cd infra/stacks/beads-server && terraform init -backend=false
Terraform has been successfully initialized!
$ terraform validate
Warning: Deprecated Resource (kubernetes_namespace → v1) # pre-existing, unrelated
Success! The configuration is valid, but there were some validation warnings as shown above.
$ terraform fmt stacks/beads-server/main.tf
# (no output — already formatted)
```
### Manual verification
1. **Apply**
```
vault login -method=oidc
cd infra/stacks/beads-server
scripts/tg apply
```
Expect: `kubernetes_config_map.beads_metadata`,
`kubernetes_cron_job_v1.beads_dispatcher`, `kubernetes_cron_job_v1.beads_reaper`
created. No changes to existing resources.
2. **CronJobs exist with right schedule**
```
kubectl -n beads-server get cronjob
```
Expect `beads-dispatcher */2 * * * *` and `beads-reaper */10 * * * *`,
both with `SUSPEND=False`.
3. **End-to-end smoke**
```
bd create "auto-dispatch smoke test" \
-d "Read /etc/hostname inside the agent sandbox and close." \
--acceptance "bd note includes 'hostname=' line and bead is closed."
bd assign <new-id> agent
# within 2 min:
bd show <new-id> --json | jq '{status, notes}'
```
Expect notes to contain `auto-dispatcher claimed at …` and
`dispatched: job=<uuid>`, status `in_progress`.
4. **Reaper smoke**
Assign + dispatch a long bead, then
`kubectl -n claude-agent delete pod -l app=claude-agent-service`. Within
30 min + one reaper tick, `bd show <id>` shows `blocked` with a
`reaper: no progress for Nm — blocking` note.
5. **Kill switch**
```
cd infra/stacks/beads-server
scripts/tg apply -var=beads_dispatcher_enabled=false
kubectl -n beads-server get cronjob
```
Expect `SUSPEND=True` on both CronJobs. Assign a bead to `agent`; verify
nothing happens within 5 min. Re-apply with `=true` to re-enable.
Runbook with all above plus reaper semantics + design choices at
`infra/docs/runbooks/beads-auto-dispatch.md`.
Closes: code-8sm
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 22:35:46 +00:00
|
|
|
|
|
|
|
|
# ── Beads auto-dispatch (dispatcher + reaper CronJobs) ──
|
|
|
|
|
#
|
|
|
|
|
# Flow:
|
|
|
|
|
# user: bd assign <id> agent
|
|
|
|
|
# └──> CronJob: beads-dispatcher (every 2 min)
|
|
|
|
|
# 1. GET BeadBoard /api/agent-status — skip if claude-agent-service busy
|
|
|
|
|
# 2. bd query 'assignee=agent AND status=open' — pick highest priority
|
|
|
|
|
# 3. bd update -s in_progress (claim; next tick won't re-pick)
|
|
|
|
|
# 4. POST BeadBoard /api/agent-dispatch — reuses prompt-build + bearer flow
|
|
|
|
|
# 5. bd note "dispatched: job=<id>" (or rollback + note on failure)
|
|
|
|
|
#
|
|
|
|
|
# CronJob: beads-reaper (every 10 min)
|
|
|
|
|
# └── for bead (assignee=agent, status=in_progress, updated_at > 30m):
|
|
|
|
|
# bd update -s blocked + bd note (recover from pod crashes mid-run)
|
|
|
|
|
#
|
|
|
|
|
# The claude-agent-service image ships bd + jq + curl — no separate image built.
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_config_map" "beads_metadata" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "beads-metadata"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
data = {
|
|
|
|
|
"metadata.json" = jsonencode({
|
|
|
|
|
database = "dolt"
|
|
|
|
|
backend = "dolt"
|
|
|
|
|
dolt_mode = "server"
|
|
|
|
|
dolt_server_host = "${kubernetes_service.dolt.metadata[0].name}.${kubernetes_namespace.beads.metadata[0].name}.svc.cluster.local"
|
|
|
|
|
dolt_server_port = 3306
|
|
|
|
|
dolt_server_user = "beads"
|
|
|
|
|
dolt_database = "code"
|
|
|
|
|
project_id = "a8f8bae7-ce65-4145-a5db-a13d11d297da"
|
|
|
|
|
})
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
locals {
|
[forgejo] Phases 3+4+5: cutover, decommission, docs sweep
End of forgejo-registry-consolidation. After Phase 0/1 already landed
(Forgejo ready, dual-push CI, integrity probe, retention CronJob,
images migrated via forgejo-migrate-orphan-images.sh), this commit
flips everything off registry.viktorbarzin.me onto Forgejo and
removes the legacy infrastructure.
Phase 3 — image= flips:
* infra/stacks/{payslip-ingest,job-hunter,claude-agent-service,
fire-planner,freedify/factory,chrome-service,beads-server}/main.tf
— image= now points to forgejo.viktorbarzin.me/viktor/<name>.
* infra/stacks/claude-memory/main.tf — also moved off DockerHub
(viktorbarzin/claude-memory-mcp:17 → forgejo.viktorbarzin.me/viktor/...).
* infra/.woodpecker/{default,drift-detection}.yml — infra-ci pulled
from Forgejo. build-ci-image.yml dual-pushes still until next
build cycle confirms Forgejo as canonical.
* /home/wizard/code/CLAUDE.md — claude-memory-mcp install URL updated.
Phase 4 — decommission registry-private:
* registry-credentials Secret: dropped registry.viktorbarzin.me /
registry.viktorbarzin.me:5050 / 10.0.20.10:5050 auths entries.
Forgejo entry is the only one left.
* infra/stacks/infra/main.tf cloud-init: dropped containerd
hosts.toml entries for registry.viktorbarzin.me +
10.0.20.10:5050. (Existing nodes already had the file removed
manually by `setup-forgejo-containerd-mirror.sh` rollout — the
cloud-init template only fires on new VM provision.)
* infra/modules/docker-registry/docker-compose.yml: registry-private
service block removed; nginx 5050 port mapping dropped. Pull-
through caches for upstream registries (5000/5010/5020/5030/5040)
stay on the VM permanently.
* infra/modules/docker-registry/nginx_registry.conf: upstream
`private` block + port 5050 server block removed.
* infra/stacks/monitoring/modules/monitoring/main.tf: registry_
integrity_probe + registry_probe_credentials resources stripped.
forgejo_integrity_probe is the only manifest probe now.
Phase 5 — final docs sweep:
* infra/docs/runbooks/registry-vm.md — VM scope reduced to pull-
through caches; forgejo-registry-breakglass.md cross-ref added.
* infra/docs/architecture/ci-cd.md — registry component table +
diagram now reflect Forgejo. Pre-migration root-cause sentence
preserved as historical context with a pointer to the design doc.
* infra/docs/architecture/monitoring.md — Registry Integrity Probe
row updated to point at the Forgejo probe.
* infra/.claude/CLAUDE.md — Private registry section rewritten end-
to-end (auth, retention, integrity, where the bake came from).
* prometheus_chart_values.tpl — RegistryManifestIntegrityFailure
alert annotation simplified now that only one registry is in
scope.
Operational follow-up (cannot be done from a TF apply):
1. ssh root@10.0.20.10 — edit /opt/registry/docker-compose.yml to
match the new template AND `docker compose up -d --remove-orphans`
to actually stop the registry-private container. Memory id=1078
confirms cloud-init won't redeploy on TF apply alone.
2. After 1 week of no incidents, `rm -rf /opt/registry/data/private/`
on the VM (~2.6GB freed).
3. Open the dual-push step in build-ci-image.yml and drop
registry.viktorbarzin.me:5050 from the `repo:` list — at that
point the post-push integrity check at line 33-107 also needs
to be repointed at Forgejo or removed (the per-build verify is
redundant with the every-15min Forgejo probe).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-07 18:30:02 +00:00
|
|
|
# Phase 3 cutover 2026-05-07 — Forgejo registry consolidation.
|
|
|
|
|
claude_agent_service_image = "forgejo.viktorbarzin.me/viktor/claude-agent-service:${var.claude_agent_service_image_tag}"
|
[beads-server] Auto-dispatch agent beads via CronJobs
## Context
Until now, handing work to the in-cluster `beads-task-runner` agent required
opening BeadBoard and clicking the manual Dispatch button on each bead. We
want users to be able to describe work as a bead, set `assignee=agent`, and
have the agent pick it up within a couple of minutes — no clicks.
The existing pieces already provide everything we need:
- `claude-agent-service` exposes `/execute` with a single-slot `asyncio.Lock`
- BeadBoard's `/api/agent-dispatch` builds the prompt and forwards the bearer
- BeadBoard's `/api/agent-status` reports `busy` via a cached `/health` poll
- Dolt stores beads and is already in-cluster at `dolt.beads-server:3306`
So the only missing component is a poller that ties them together. This
commit adds that poller as two Kubernetes CronJobs — matching the existing
infra pattern (OpenClaw task-processor, certbot-renewal, backups) rather than
introducing n8n or in-service polling.
## Flow
```
user: bd assign <id> agent
│
▼
Dolt @ dolt.beads-server.svc:3306 ◄──── every 2 min ────┐
│ │
▼ │
CronJob: beads-dispatcher │
1. GET beadboard/api/agent-status (busy? skip) │
2. bd query 'assignee=agent AND status=open' │
3. bd update -s in_progress (claim) │
4. POST beadboard/api/agent-dispatch │
5. bd note "dispatched: job=…" │
│ │
▼ │
claude-agent-service /execute │
beads-task-runner agent runs; notes/closes bead │
│ │
▼ │
done ──► next tick picks up the next bead ───────────────┘
CronJob: beads-reaper (every 10 min)
for bead (assignee=agent, status=in_progress, updated_at > 30 min):
bd note "reaper: no progress for Nm — blocking"
bd update -s blocked
```
## Decisions
- **Sentinel assignee `agent`** — free-form, no Beads schema change. Any bd
client can set it (`bd assign <id> agent`).
- **Sequential dispatch** — matches the service's `asyncio.Lock`. With a
2-min poll cadence and ~5-min average run, throughput is ~12 beads/hour.
Parallelism is a separate plan.
- **Fixed agent `beads-task-runner`** — read-only rails, matches the manual
Dispatch button. Broader-privilege agents stay manual via BeadBoard UI.
- **Image reuse** — the claude-agent-service image already ships `bd`, `jq`,
`curl`; a new CronJob-specific image would duplicate 400MB of infra tooling.
Mirror `claude_agent_service_image_tag` locally; bump on rebuild.
- **ConfigMap-mounted `metadata.json`** — declarative TF rather than reusing
the image-seeded file. The script copies it into `/tmp/.beads/` because bd
may touch the parent dir and ConfigMap mounts are read-only.
- **Kill switch (`beads_dispatcher_enabled`)** — single bool, default true.
When false, `suspend: true` on both CronJobs; manual Dispatch keeps working.
- **Reaper threshold 30 min** — `bd note` bumps `updated_at`, so a well-behaved
`beads-task-runner` never trips the reaper. Failures trip it; pod crashes
(in-memory job state lost) also trip it.
## What is NOT in this change
- No Terraform apply — requires Vault OIDC + cluster access. Apply manually:
`cd infra/stacks/beads-server && scripts/tg apply`
- No change to `claude-agent-service/` (already ships bd/jq/curl)
- No change to `beadboard/` (`/api/agent-dispatch` + `/api/agent-status` reused)
- No change to the `beads-task-runner` agent definition (rails unchanged)
- Parallelism: single-slot is MVP; multi-slot dispatch is a separate plan.
## Deviations from plan
Minor, documented in code comments:
- Reaper uses `.updated_at` instead of the plan's `.notes[].created_at`. bd
serializes `notes` as a string (not an array), and every `bd note` bumps
`updated_at` — equivalent for the reaper's purpose.
- ISO-8601 parsed via `python3`, not `date -d` — Alpine's busybox lacks GNU
`-d` and the image has python3.
- `HOME=/tmp` set as a safety net — bd may try to write state/lock files.
## Test plan
### Automated
```
$ cd infra/stacks/beads-server && terraform init -backend=false
Terraform has been successfully initialized!
$ terraform validate
Warning: Deprecated Resource (kubernetes_namespace → v1) # pre-existing, unrelated
Success! The configuration is valid, but there were some validation warnings as shown above.
$ terraform fmt stacks/beads-server/main.tf
# (no output — already formatted)
```
### Manual verification
1. **Apply**
```
vault login -method=oidc
cd infra/stacks/beads-server
scripts/tg apply
```
Expect: `kubernetes_config_map.beads_metadata`,
`kubernetes_cron_job_v1.beads_dispatcher`, `kubernetes_cron_job_v1.beads_reaper`
created. No changes to existing resources.
2. **CronJobs exist with right schedule**
```
kubectl -n beads-server get cronjob
```
Expect `beads-dispatcher */2 * * * *` and `beads-reaper */10 * * * *`,
both with `SUSPEND=False`.
3. **End-to-end smoke**
```
bd create "auto-dispatch smoke test" \
-d "Read /etc/hostname inside the agent sandbox and close." \
--acceptance "bd note includes 'hostname=' line and bead is closed."
bd assign <new-id> agent
# within 2 min:
bd show <new-id> --json | jq '{status, notes}'
```
Expect notes to contain `auto-dispatcher claimed at …` and
`dispatched: job=<uuid>`, status `in_progress`.
4. **Reaper smoke**
Assign + dispatch a long bead, then
`kubectl -n claude-agent delete pod -l app=claude-agent-service`. Within
30 min + one reaper tick, `bd show <id>` shows `blocked` with a
`reaper: no progress for Nm — blocking` note.
5. **Kill switch**
```
cd infra/stacks/beads-server
scripts/tg apply -var=beads_dispatcher_enabled=false
kubectl -n beads-server get cronjob
```
Expect `SUSPEND=True` on both CronJobs. Assign a bead to `agent`; verify
nothing happens within 5 min. Re-apply with `=true` to re-enable.
Runbook with all above plus reaper semantics + design choices at
`infra/docs/runbooks/beads-auto-dispatch.md`.
Closes: code-8sm
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 22:35:46 +00:00
|
|
|
beadboard_internal_url = "http://${kubernetes_service.beadboard.metadata[0].name}.${kubernetes_namespace.beads.metadata[0].name}.svc.cluster.local"
|
|
|
|
|
|
|
|
|
|
beads_script_prelude = <<-EOT
|
|
|
|
|
set -euo pipefail
|
|
|
|
|
# bd with Dolt server mode needs metadata.json in a directory it can walk.
|
|
|
|
|
# ConfigMap mounts are read-only — copy to a writable location before use.
|
|
|
|
|
mkdir -p /tmp/.beads
|
|
|
|
|
cp /etc/beads-metadata/metadata.json /tmp/.beads/metadata.json
|
|
|
|
|
EOT
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_cron_job_v1" "beads_dispatcher" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "beads-dispatcher"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
schedule = "*/2 * * * *"
|
|
|
|
|
concurrency_policy = "Forbid"
|
|
|
|
|
successful_jobs_history_limit = 3
|
|
|
|
|
failed_jobs_history_limit = 3
|
|
|
|
|
starting_deadline_seconds = 60
|
|
|
|
|
suspend = !var.beads_dispatcher_enabled
|
|
|
|
|
job_template {
|
|
|
|
|
metadata {}
|
|
|
|
|
spec {
|
|
|
|
|
backoff_limit = 0
|
|
|
|
|
ttl_seconds_after_finished = 600
|
|
|
|
|
template {
|
|
|
|
|
metadata {
|
|
|
|
|
labels = {
|
|
|
|
|
app = "beads-dispatcher"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
restart_policy = "Never"
|
|
|
|
|
image_pull_secrets {
|
|
|
|
|
name = "registry-credentials"
|
|
|
|
|
}
|
|
|
|
|
container {
|
|
|
|
|
name = "dispatcher"
|
|
|
|
|
image = local.claude_agent_service_image
|
|
|
|
|
command = ["/bin/sh", "-c", <<-EOT
|
|
|
|
|
${local.beads_script_prelude}
|
|
|
|
|
|
|
|
|
|
BUSY=$(curl -sf "$${BEADBOARD_URL}/api/agent-status" | jq -r '.busy // false')
|
|
|
|
|
if [ "$BUSY" != "false" ]; then
|
|
|
|
|
echo "claude-agent-service is busy — skipping tick"
|
|
|
|
|
exit 0
|
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
BEAD=$(bd --db /tmp/.beads query 'assignee=agent AND status=open' --json \
|
|
|
|
|
| jq -r '[.[] | select(.acceptance_criteria and (.acceptance_criteria | length) > 0)]
|
|
|
|
|
| sort_by(.priority, .updated_at)[0].id // empty')
|
|
|
|
|
|
|
|
|
|
if [ -z "$BEAD" ]; then
|
|
|
|
|
echo "no eligible beads (assignee=agent, status=open, has acceptance_criteria)"
|
|
|
|
|
exit 0
|
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
echo "picked bead: $BEAD"
|
|
|
|
|
|
|
|
|
|
bd --db /tmp/.beads update "$BEAD" -s in_progress
|
|
|
|
|
bd --db /tmp/.beads note "$BEAD" "auto-dispatcher claimed at $(date -u +%Y-%m-%dT%H:%M:%SZ)"
|
|
|
|
|
|
|
|
|
|
RESP=$(curl -sS -w '\n%%{http_code}' -X POST \
|
|
|
|
|
-H 'Content-Type: application/json' \
|
|
|
|
|
-d "{\"taskId\":\"$BEAD\"}" \
|
|
|
|
|
"$${BEADBOARD_URL}/api/agent-dispatch")
|
|
|
|
|
CODE=$(printf '%s' "$RESP" | tail -n1)
|
|
|
|
|
BODY=$(printf '%s' "$RESP" | sed '$d')
|
|
|
|
|
|
|
|
|
|
if [ "$CODE" = "200" ]; then
|
|
|
|
|
JOB_ID=$(printf '%s' "$BODY" | jq -r '.job_id // "unknown"')
|
|
|
|
|
bd --db /tmp/.beads note "$BEAD" "dispatched: job=$JOB_ID"
|
|
|
|
|
echo "dispatched $BEAD as job $JOB_ID"
|
|
|
|
|
else
|
|
|
|
|
# Roll the claim back so the next tick can retry.
|
|
|
|
|
bd --db /tmp/.beads update "$BEAD" -s open
|
|
|
|
|
bd --db /tmp/.beads note "$BEAD" "dispatch failed HTTP $CODE: $BODY"
|
|
|
|
|
echo "dispatch FAILED for $BEAD: HTTP $CODE — $BODY" >&2
|
|
|
|
|
exit 1
|
|
|
|
|
fi
|
|
|
|
|
EOT
|
|
|
|
|
]
|
|
|
|
|
env {
|
|
|
|
|
name = "BEADBOARD_URL"
|
|
|
|
|
value = local.beadboard_internal_url
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "API_BEARER_TOKEN"
|
|
|
|
|
value_from {
|
|
|
|
|
secret_key_ref {
|
|
|
|
|
name = "beadboard-agent-service"
|
|
|
|
|
key = "api_bearer_token"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "BEADS_ACTOR"
|
|
|
|
|
value = "beads-dispatcher"
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "HOME"
|
|
|
|
|
value = "/tmp"
|
|
|
|
|
}
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "beads-metadata"
|
|
|
|
|
mount_path = "/etc/beads-metadata"
|
|
|
|
|
read_only = true
|
|
|
|
|
}
|
|
|
|
|
resources {
|
|
|
|
|
requests = {
|
|
|
|
|
cpu = "50m"
|
|
|
|
|
memory = "128Mi"
|
|
|
|
|
}
|
|
|
|
|
limits = {
|
|
|
|
|
memory = "256Mi"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
volume {
|
|
|
|
|
name = "beads-metadata"
|
|
|
|
|
config_map {
|
|
|
|
|
name = kubernetes_config_map.beads_metadata.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
lifecycle {
|
|
|
|
|
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
|
|
|
|
|
ignore_changes = [spec[0].job_template[0].spec[0].template[0].spec[0].dns_config]
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_cron_job_v1" "beads_reaper" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "beads-reaper"
|
|
|
|
|
namespace = kubernetes_namespace.beads.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
schedule = "*/10 * * * *"
|
|
|
|
|
concurrency_policy = "Forbid"
|
|
|
|
|
successful_jobs_history_limit = 3
|
|
|
|
|
failed_jobs_history_limit = 3
|
|
|
|
|
starting_deadline_seconds = 60
|
|
|
|
|
suspend = !var.beads_dispatcher_enabled
|
|
|
|
|
job_template {
|
|
|
|
|
metadata {}
|
|
|
|
|
spec {
|
|
|
|
|
backoff_limit = 0
|
|
|
|
|
ttl_seconds_after_finished = 600
|
|
|
|
|
template {
|
|
|
|
|
metadata {
|
|
|
|
|
labels = {
|
|
|
|
|
app = "beads-reaper"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
restart_policy = "Never"
|
|
|
|
|
image_pull_secrets {
|
|
|
|
|
name = "registry-credentials"
|
|
|
|
|
}
|
|
|
|
|
container {
|
|
|
|
|
name = "reaper"
|
|
|
|
|
image = local.claude_agent_service_image
|
|
|
|
|
command = ["/bin/sh", "-c", <<-EOT
|
|
|
|
|
${local.beads_script_prelude}
|
|
|
|
|
|
|
|
|
|
THRESHOLD_MIN=30
|
|
|
|
|
NOW=$(date -u +%s)
|
|
|
|
|
|
|
|
|
|
bd --db /tmp/.beads query 'assignee=agent AND status=in_progress' --json \
|
|
|
|
|
| jq -c '.[]' \
|
|
|
|
|
| while read -r BEAD_JSON; do
|
|
|
|
|
ID=$(printf '%s' "$BEAD_JSON" | jq -r '.id')
|
|
|
|
|
LAST_UPDATE=$(printf '%s' "$BEAD_JSON" | jq -r '.updated_at')
|
|
|
|
|
# Alpine's busybox date lacks GNU -d; parse ISO-8601 with python3.
|
|
|
|
|
LAST_TS=$(python3 -c "from datetime import datetime; print(int(datetime.fromisoformat('$LAST_UPDATE'.replace('Z','+00:00')).timestamp()))")
|
|
|
|
|
AGE_MIN=$(( (NOW - LAST_TS) / 60 ))
|
|
|
|
|
if [ "$AGE_MIN" -gt "$THRESHOLD_MIN" ]; then
|
|
|
|
|
bd --db /tmp/.beads note "$ID" "reaper: no progress for $${AGE_MIN}m (threshold $${THRESHOLD_MIN}m) — blocking"
|
|
|
|
|
bd --db /tmp/.beads update "$ID" -s blocked
|
|
|
|
|
echo "REAPED $ID (stale $${AGE_MIN}m)"
|
|
|
|
|
else
|
|
|
|
|
echo "keeping $ID (age $${AGE_MIN}m < $${THRESHOLD_MIN}m)"
|
|
|
|
|
fi
|
|
|
|
|
done
|
|
|
|
|
EOT
|
|
|
|
|
]
|
|
|
|
|
env {
|
|
|
|
|
name = "BEADS_ACTOR"
|
|
|
|
|
value = "beads-reaper"
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "HOME"
|
|
|
|
|
value = "/tmp"
|
|
|
|
|
}
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "beads-metadata"
|
|
|
|
|
mount_path = "/etc/beads-metadata"
|
|
|
|
|
read_only = true
|
|
|
|
|
}
|
|
|
|
|
resources {
|
|
|
|
|
requests = {
|
|
|
|
|
cpu = "50m"
|
|
|
|
|
memory = "128Mi"
|
|
|
|
|
}
|
|
|
|
|
limits = {
|
|
|
|
|
memory = "256Mi"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
volume {
|
|
|
|
|
name = "beads-metadata"
|
|
|
|
|
config_map {
|
|
|
|
|
name = kubernetes_config_map.beads_metadata.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
lifecycle {
|
|
|
|
|
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
|
|
|
|
|
ignore_changes = [spec[0].job_template[0].spec[0].template[0].spec[0].dns_config]
|
|
|
|
|
}
|
|
|
|
|
}
|