Repository navigation
Description
speech-runtime runs in the namespace speech-runtime from its attested private GHCR ref, on CPU, with its caller table as a ConfigMap. It is applied by the Kustomization apps and proven in the job cluster on pull requests and on main, then on the PC. It has no route and no caller yet: hopin and presentator wire to it later, and it goes live with P7 (#116), which brings Keycloak.
Caller
- P6: hopin, speech-runtime and presentator's web run in k3d and on the PC beside hal #43, slice row "speech-runtime: its manifests, from speech-runtime's first release, proven in k3d; live with P7 if R5 holds".
- The operator, 07.11.2026, in platform's chat: „ja alles daran setzen dass das voran geht!“
Facts
speech-runtime's head, 07.11.2026, from speech-runtime's main 8adecbd and the image's own files:
- The ref:
ghcr.io/overnightworks/speech-runtime:2026.11.07.1@sha256:18d513fa334de8cb18065a8c6e50162e8d89323eeb20c47f398cfb0b23362f27. It is signed by quality'simage.yml, has SLSA v1 provenance, and is private. - The user is 1001. The root is read-only; the only writable path is
/tmp(tmpfs of 64 MiB in compose, where uploads over 1 MiB are spooled). The voices (/opt/voices) and the hearing model (/opt/hearing) are baked in and only read, so the service needs no egress apart from Keycloak's key set. - Port 8080, with
SPEECH_HOST=0.0.0.0. - Readiness:
GET /healthanswers 200 while the models still load, so readiness is compose's exec probe: bothspeaking.readyandhearing.readytrue, start period 30 s. - Settings to set:
SPEECH_CONFIG_FILE(the caller table's path),SPEECH_HOST=0.0.0.0,SPEECH_DEVICE=cpu,SPEECH_VOICE_CACHE=/opt/voices,SPEECH_HUGGINGFACE_CACHE=/opt/hearing,SPEECH_HEARING_MODEL=small.SPEECH_GPU_VOICESstays unset; Qwen and the card are P8's. The defaults' owner is speech-runtime'sdocs/wire.md. - No Secret of its own. The caller table is plain configuration, and the key set is public.
- The caller table for this image:
[identity]: issuer,jwks_url(https),audience = "speech-service",workload_role = "speech-workload",group_claim = "groups",service_group = "/services/speech-service";[apps.hopin]and[apps.presentator], each withworkload_client,voices = ["piper"]andhear = true(the operator's ruling of 07.11.2026, speech-runtime#184).- The next image drops
hearandvoices, and a removed key stops the start, so the ConfigMap changes with the image tag in one pull request.
Decided by the head
- The pull Secret. The namespace receives its own
ghcr-pullfrom platform-secrets, like hopin's, so it joins the namespaces layer withrestrictedand the prune annotation. The operator puts it with one moresecrets:put-registryfor the namespacespeech-runtime(O2), the path hopin's took. P4: Flux decrypts SOPS-age secrets from platform-secrets #13's P4d include, the credential kept once for every namespace, waits for its own slice, because a SOPS MAC overmetadata.namespacemay rule out a namespace transform before decryption. In the job, the artifact gets the same job-madeghcr-pullin this namespace too. - The issuer until P7 is
https://auth.hallucinai.de/realms/hallucinai, as in hopin's manifest. P7 moves it. - A NetworkPolicy admits 8080 only from the namespaces
hopinandpresentator. - The image is large (about 9.8 GB). The job measures whether k3d on a standard runner pulls and starts it, and reports disk and time. A runner that cannot hold it is reported to the head before any workaround. When the measured pull and start exceed
apps' timeout of 5 minutes, that timeout and the job's wait on the Kustomizations rise to the measurement with a margin, inclusters/pc/apps.yamland the job.
Done when
- D1 In the job, the Deployment
speech-runtimepulls its attested ref throughghcr-pulland becomes Available with one Ready pod (both models ready) in a namespace that enforcesrestricted.imagesis green on the ref. - D2 It runs on CPU with a read-only root,
/tmpthe only writable path, user 1001, and no service account token; the caller table comes from a ConfigMap. - D3 A Pod in another namespace than
hopinandpresentatorgets no answer on 8080. - D4 On the PC,
appsis Ready at main's revision with the pod Ready. - D5
AGENTS.mdnamesapps/speech-runtime/, andquality hygiene .printshygiene: clean.
Operator actions
- O1 On GHCR, in the package speech-runtime under "Manage Actions access", add
overnightworks/platformwith Read. Without it, the job cannot pull. - O2 One
secrets:put-registryfor the namespacespeech-runtimein platform-secrets, as for hopin.
version = 1
now = "PR #120 is built; its pull and images check wait for O1. O2 is done: platform-secrets#13 holds the encrypted pull Secret and merges after this item lands."
next = "Review PR #120 while O1 is done, then rerun its CI and measure the pull against apps' timeout."
done_when = "speech-runtime runs in k3d and on the PC from its attested private ref through ghcr-pull, Available with both models ready, on CPU in a restricted namespace with a read-only root and its caller table from a ConfigMap, reachable on 8080 only from hopin and presentator; AGENTS.md names apps/speech-runtime/ and quality hygiene . prints hygiene: clean."
scope = [".github/workflows/ci.yml", "AGENTS.md", "apps/speech-runtime/speech-runtime.yaml", "clusters/pc/apps.yaml", "infrastructure/namespaces/namespaces.yaml"]
size = "M"
whole = "One Deployment, its Namespace and its job proof have no caller apart, and AGENTS.md describes them in the same change."
Metadata
Metadata
Assignees
Labels
No labels
Activity