Two related changes shipped together. The stack rename is independent
but adding `vllm-reward` to the existing `vllm-qwen3` would have made
that name actively misleading.
**Rename:** `stacks/vllm-qwen3/ → stacks/vllm/`. Updated all in-repo
references (README.md root, servers/ana-ml2/, stacks/llama-swap/,
configs/restic/ana-ml2/, docs/runbooks/disaster-recovery.md). Two
intentional history mentions retained (servers/ana-ml2 + stacks/vllm
README).
**Add `vllm-reward` service:** serves Skywork-Reward-V2-Llama-3.1-8B-AWQ
on port 8003. The AWQ output is a locally-quantized model (not from HF),
so bind-mounts `/tank/aimodels/llm:/local-models:ro` rather than the
shared HF cache. Model config.json declares LlamaForSequenceClassification
which vLLM's pooling runner picks up automatically — produces a single
reward score per input via /classify.
**Flag note:** the user's spec listed `--task classify`, but vLLM 0.19.1
deprecated --task in favor of --runner pooling (model architecture in
config.json drives the classification head). Compose uses --runner
pooling with a comment explaining the substitution.
**GPU memory:** no rebalance needed — production had already tuned
EMBED/RERANK down from 0.40 to 0.20 each (canonical .env.example now
matches reality). Adding REWARD at 0.30 totals 0.70, leaving ~14 GB
headroom on the 48 GB Ada.
**Server-side:** brought existing vllm-qwen3 down, mv'd
/opt/docker/compose/vllm-qwen3 → /opt/docker/compose/vllm, appended
REWARD_* lines to existing .env (preserving API_KEY/HF_TOKEN), deployed
new compose via scripts/deploy-stack.sh, brought all 3 services up.
**Smoke tests:**
- /health on 8001/8002/8003 → 200
- /v1/models on 8003 → lists Skywork/Skywork-Reward-V2-Llama-3.1-8B-AWQ
with max_model_len 16384
- /classify with a sample conversation → returns LABEL_0 with prob 0.9999
(single-output regression-style reward score, expected shape for a
reward model)
Playbook handles models, datasets, and spaces (via --var repo_type=...)
since 3025d49 — the "-model" suffix was misleading. Renaming to match
actual scope.
Updates the single in-repo reference (changelog comment in
stacks/llama-swap/conf/config.yaml). config.yaml was scp'd to ana-ml2;
no docker compose restart needed (comment-only).
Adds optional repo_type var (default "model"; valid: model/dataset/space)
that's forwarded to `hf download --repo-type` and threaded through the
verify step (cache-dir prefix tracks repo_type: models--, datasets--,
spaces--).
The playbook was previously model-only because hf download defaults
repo_type=model — pulling a dataset surfaced as a 404 against the wrong
HF API path. Now generic.
Smoke-tested 2026-05-13:
scripts/elway ana-ml2 --playbook playbooks/pull-hf-model.yaml \
--var hf_repo=Skywork/Skywork-Reward-Preference-80K-v0.2 \
--var repo_type=dataset
→ 200 MB parquet cached at
/tank/aimodels/huggingface/hub/datasets--Skywork--Skywork-Reward-Preference-80K-v0.2/
Filename is misleading now (playbook handles more than models); leaving
the rename for a future cleanup since pull-hf-model.yaml is referenced
from the llama-swap config.yaml's 2026-05-13 changelog entry.
AtlaAI's Selene-1-Mini judge model for evaluation/scoring tasks.
Llama 3.1 8B base, mradermacher imatrix-quantized Q6_K (~6.5GB,
quality-leaning quant). Apache-2.0. Per Atla cookbook these defaults
hit 84% on RAGTruth hallucination eval.
New 'JUDGE / EVAL MODELS' section between the dense chat models and
the embedding models — separate category from chat/reasoning since
the run-params shape is different (deterministic-leaning: temp 0.01,
top-p 1.0, no repeat penalty).
q8_0 KV cache to fit 32K ctx cleanly on the 3090 with headroom.
Pre-pulled into the shared HF cache via the new
playbooks/pull-hf-model.yaml playbook (canonical replacement for
ad-hoc huggingface_hub.snapshot_download calls; see CHANGELOG).
Smoke-tested 2026-05-13: GET /v1/models lists selene-1-mini-8b,
POST /v1/chat/completions returns expected output cleanly.
Codifies the previously-manual workflow described in
stacks/llama-swap/README.md: install hf CLI via pipx (one-time),
inject hf_transfer for fast multi-connection downloads,
`hf download` into the shared HF cache at /tank/aimodels/huggingface
with optional --include filter.
Model-format-agnostic by design — same playbook handles GGUFs for
llama-swap and safetensors for vLLM (both stacks read the same cache
dir via HF_HOME=/hfcache). Does NOT edit any consumer's config.yaml;
per-model run params (ctx-size, sampler defaults, quant choice,
chat template, etc.) stay human-curated.
Usage:
scripts/elway ana-ml2 --playbook playbooks/pull-hf-model.yaml \
--var hf_repo=<user>/<repo> \
[--var allow_patterns='*Q6_K*']
Idempotent: hf CLI skips already-cached blobs; re-runs are
sub-second when the snapshot is already complete.
Smoke-tested 2026-05-13 against:
- mradermacher/Selene-1-Mini-Llama-3.1-8B-GGUF (Q6_K, ~6.5 GB)
- Skywork/Skywork-Reward-V2-Llama-3.1-8B (full safetensors, ~16 GB)
Captures the access path + emergency-ops runbook surfaced during the
2026-05-12 demo outage (Z_AI_API_KEY / runtime validator / :latest tag
drift cascade).
- servers/corviduo-dev/{README.md,ssh-target,system-details.txt}
- CLAUDE.md servers table + placement-rules note
The "docker-as-root sudo bypass" pattern (vh's docker-group membership
→ effective root for any bind-mount-able operation) is the canonical
fix path when /opt/worldtree*/.env edits are needed and the deploy
user's sudo is out of reach. The README documents the pattern with
the appropriate "docker-group ≈ sudo" security warning so future
emergency-ops sessions don't have to re-derive it.
Ownership stance matches SF client hosts: PFI hosts + provides
emergency-ops backstop, Worldtree-team owns OS config / deploys /
backup decisions. Coordinate data-affecting work with the architect.
Booted each service on irv-ml1 to capture the wrapper's actual voice
exposure, then took them back down. Initial state restored.
**Voxtral (v1 → v2)** — 20 native presets from live /v1/audio/voices:
neutral_{female,male}, casual_{female,male}, cheerful_female, plus
8 language-code variants ({ar,de,es,fr,hi,it,nl,pt}_{female,male}).
vLLM-Omni does NOT translate OpenAI aliases; `alloy` would 400. Default
flipped to `neutral_female` (matches Mistral docs).
**Qwen3-TTS (v1 → v2)** — 15 voices from live /v1/voices, NOT the 17
the upstream blog cites: 9 Qwen presets (vivian/serena/uncle_fu/ryan/
aiden/ono_anna/sohee/eric/dylan) + 6 OpenAI-compat aliases (alloy/
echo/fable/nova/onyx/shimmer). Default `vivian` matches the wrapper's
OpenAPI default. Catalog previously stated clone-only — wrong; the
wrapper does ship presets, the upstream blog list just doesn't match
the deployed wrapper. Cloning still works alongside via clone:<name>.
**Kyutai-TTS (v1 → v2)** — NillPointer wrapper does NOT expose any voice
listing endpoint (/v1/audio/voices 404; only /health + POST /v1/audio/
speech are wired). Voices are filesystem-discovered. Catalog now drops
the broken source_url, switches voice field to free-text with default
`unmute-prod-website/default_voice.wav` (upstream's named default).
Description lists the on-disk categories with counts + license posture
(vctk = CC BY 4.0 commercial-safe; expresso = CC BY-NC research-only).
Six default + description tightenings from upstream-source research:
- **Kokoro voice**: af_bella → af_heart. Per upstream VOICES.md, af_heart
is the only A-rated voice; also the kokoro-fastapi container's own
default. Applied to both kokoro (v2 → v3) and kokoro-captioned (v1 → v2).
- **SAO negative_prompt**: "Low quality." → "low quality, average quality".
Per diffusers official docs Tips section — the lowercase comma-separated
shape is the explicit recommendation; the period form was a code-example
string, never a documented default. SAO bumped v1 → v2.
- **SAO prompt description**: added the model card's canonical examples
("128 BPM tech house drum loop", "the sound of a hammer hitting a wooden
surface") plus the Tips advice on descriptive prompts.
- **VibeVoice voice**: en-Carter_man → en-Alice_woman. Per upstream model
card, Alice is the documented default. Description now flags the
Alice-injects-BGM-for-intros foot-gun + the `_bgm`-suffix meaning.
VibeVoice bumped v2 → v3.
- **Fish-s2 text description**: added multi-tag placeholder example
combining emotion + physical tags, per upstream best-practice docs
(physical tags "feel flat without emotional context").
- **ace-step prompt description**: added the upstream Gradio UI's
pre-filled tag string as the canonical prompt-shape example.
Surfaced separately to lkraven (NOT applied here, need decisions):
- Voxtral voice "alloy" may need to become a native preset like
"neutral_female" — depends on whether vLLM-Omni translates OpenAI
aliases.
- Qwen3-TTS — research found 17 presets (Cherry, Ethan, ...) that the
catalog currently says don't exist. Catalog says clone-only; needs
wrapper-level verification before adding.
- Kyutai-TTS — service down, can't probe /v1/audio/voices. Default
remains undefaulted.
Three changes prepping infra for asset_engine's orchestration feature
(SSH-driven bring-up / bring-down of irv-ml1 inference services with
per-device VRAM gating, contract in vh/asset-engine commit 5a36f8c):
1. asset-engine compose + .env.example + playbook gain a read-only
bind-mount for /app/runtime/ssh — the dedicated ed25519 keypair
(generated on ana-docker, not in the repo) plus a pinned known_hosts
for irv-ml1's host fingerprint. Env vars SSH_KEY_PATH and
SSH_KNOWN_HOSTS are exposed for the app to consume.
2. docs/asset-engine/services.yaml gains a `lifecycle: { stack, vram_gb,
gpu_device_id }` block on each of 12 orchestratable irv-ml1 services
(kokoro, chatterbox, index-tts, qwen3-tts, cosyvoice, fish-s2,
kyutai-tts, vibevoice, voxtral, parakeet, stable-audio-open, ace-step).
VRAM numbers are estimates from model footprint at fp16 — tune from
real nvidia-smi measurements once the gate is live. comfyui and
kokoro-captioned are deliberately excluded (variable-VRAM and
shared-container respectively).
3. servers/irv-ml1/README.md docker-stacks table now lists all 13
inference stacks (was only dockge + agents + comfyui) with port +
GPU pinning columns.
Pubkey deployed to ~lkraven/.ssh/authorized_keys on irv-ml1;
end-to-end SSH from ana-docker → irv-ml1 verified with strict
host-key checking.
Adds VOR_WORLDTREE_KEY + VOR_WORLDTREE_BASE + VOR_WORLDTREE_MODEL to vor's
compose environment with sane defaults. Empty key falls back to the
in-process MockWorldtree (the /mockup/ surface returns canned fixtures);
a real key issued by architect routes LLM calls at the demo Saga instance.
Key itself lives in ana-docker:/opt/docker/compose/vor/.env (not in the
repo).
Internal tooling — accessed at http://10.250.50.70:8200, not through
Traefik. Removes the unused traefik labels (router rule, TLS, crowdsec
middleware, loadbalancer port) and the traefik-net network membership;
homepage.href now points at host:port for direct discovery, matching
task-board's pattern. Playbook verify drops the traefik-net membership
check.
Mirrors task-board's build-on-host pattern: elway playbook clones
vh/asset-engine into /opt/docker/build/, docker build, install compose +
seed .env, up -d, verify /health. No registry.
Internal-only tool — LAN port 8200 (bind 0.0.0.0) is primary; Traefik
labels additionally route asset-engine.phasefinal.com with TLS via the
anaprod cert resolver. DB and outputs are separate bind-mounts under
/opt/docker/conf/asset-engine/ so outputs/ can move volumes later
without touching DB state. INFERENCE_HOST defaults to 10.100.79.3
(irv-ml1 over WG). OIDC env seam is pre-allocated empty for v2.
asset-engine's seed_surface contract needs reproducibility.seed_field to name
which CatalogField carries the seed so the UI can render a Roll button and the
server can fill empty seeds before persistence. SAO's seed field is type=number,
satisfying CatalogService._validate_seed_field.
ace-step is intentionally not declared here — actual_seeds is type=json (a list)
with an upstream reproducibility gap; the planned fix surfaces resolved seeds via
response header, pending a separate contract.
Per althing thread 01KRCNSF0V5NDCKB34H663MXHS — the catalog declared
14 services but 6 of them aren't running on irv-ml1 (chatterbox,
index-tts, qwen3-tts, cosyvoice, voxtral, kyutai-tts; missing from
docker ps entirely). Without action, the asset-engine UI would
declare them as available and consumers would hit unreachable
endpoints.
asset-engine consumer chose option (1) of three I sketched: extend
StatusT with `down` and treat it identically to `catalog-deferred`
in the picker (greyed, non-clickable). Lightweight, declarative, no
runtime health-check machinery, easy to revert when services
return.
Changes:
- StatusT enum (in asset_engine/catalog.py — committed there
separately) extended from
Literal["ready", "catalog-deferred", "experimental"]
to
Literal["ready", "catalog-deferred", "experimental", "down"]
- 6 services flipped to status: down.
- CATALOG-CONTRACT.md: replaced the bare-enum status row with a
four-row sub-table that names each value's meaning AND its picker
behavior. `down` and `catalog-deferred` get the same UI treatment
but the tooltip text differentiates ("Catalog-deferred" vs
"Service down — temporarily unreachable on irv-ml1") so the
semantic distinction (design state vs fleet-ops state) is
preserved.
- CATALOG-CONTRACT.md versioning policy table: new row codifying
"extending an existing enum (StatusT, FieldTypeT, ResponseTypeT,
CategoryT) with a non-conflicting value, with the consumer
updated in the same coordinated change" → no catalog_version
bump. Explicit rule for future enum extensions.
- JSON Schema regenerated.
catalog_version stays at 1.
Operational note (not catalog-side): the down services likely got
reaped 13+ days ago per the docker timestamps when other unrelated
work was done on irv-ml1. Bringing them back is a deploy task
outside this commit's scope. Flip status: down → ready in this file
once each one's confirmed running.
Sweep round caught vibevoice catalog drift in three dimensions; all
verified against the live OpenAPI + endpoint exercise, NOT against
documentation (which is what produced the bad values originally).
model:
was: options=[vibevoice], default=vibevoice
now: options=[tts-1, tts-1-hd, vibevoice], default=tts-1
why: the wrapper accepts all three (OpenAI-compat aliases all map
to VibeVoice internally per upstream README); wire default is tts-1
per /openapi.json. Catalog over-constrained users to a single value.
voice:
was: default=Carter; description listed [Carter, Davis, Emma, Frank,
Grace, Mike, Samuel] as built-ins
now: default=en-Carter_man; options enumerated:
OpenAI: alloy, echo, fable, onyx, nova, shimmer
VibeVoice: en-Alice_woman, en-Carter_man, en-Frank_man,
en-Mary_woman_bgm, en-Maya_woman, in-Samuel_man,
zh-Anchen_man_bgm, zh-Bowen_man, zh-Xinran_woman
why: discovered by hitting the endpoint with the catalog's claimed
"Carter" — wrapper returned 400 with the actual valid list inline
in the error body. The previous catalog values were fabrications,
not derived from any real source.
response_format:
was: options=[wav, mp3]
now: options=[wav, mp3, opus, flac, pcm]; default mp3 (was wav)
why: probed all 7 plausible formats; 5 return audio (200), aac and
m4a return 500. Catalog was over-restrictive; an earlier sweep
draft over-claimed [wav, mp3, opus, aac, flac, pcm, m4a] from
documentation that I refused to apply unverified. Now matches the
empirically-confirmed set.
Bumped vibevoice version 1 -> 2. catalog_version stays at 1.
Lesson reinforced: the only source-of-truth for catalog values is
the live wire. /openapi.json doesn't enumerate enums (returns bare
"string"); error responses from the endpoint with bad inputs are
the most reliable enum-discovery mechanism.
asset_engine consumer audited the entire ace-step entry's defaults
and slider ranges against acestep/ui/components.py (althing thread
01KRCN0SHP9YJGQD58EE95DC5P). The catalog had been authored from
documentation rather than from source; ten defaults were wrong and
several slider ranges were either too narrow or impractically wide.
Defaults changed (catalog -> upstream-authoritative):
infer_step 20 -> 60
guidance_scale 7.5 -> 15.0
cfg_type cfg -> apg
omega_scale 0.5 -> 10.0
guidance_interval 0.0 -> 0.5
guidance_interval_decay 1.0 -> 0.0
min_guidance_scale 1.0 -> 3.0
use_erg_tag false -> true
use_erg_diffusion false -> true
actual_seeds [42] -> [] (random per call)
Slider ranges adopted from upstream where reasonable; bounded
locally where upstream's range is so wide it's unusable as a UI
slider:
guidance_scale [1.0, 15.0] -> [0.0, 30.0] (upstream)
guidance_scale_text [0.0, 15.0] -> [0.0, 10.0] (upstream)
guidance_scale_lyric [0.0, 15.0] -> [0.0, 10.0] (upstream)
lora_weight [0.0, 2.0] -> [-3.0, 3.0] (upstream)
audio_duration [5.0, 600.0] -> [5.0, 240.0] (upstream max)
omega_scale [0.0, 1.0] -> [-10.0, 30.0] (UI bound; upstream is [-100, 100])
min_guidance_scale [0.0, 10.0] -> [0.0, 20.0] (UI bound; upstream is [0, 200])
Verified empty-string actual_seeds path against the live pipeline
source: pipeline_ace_step.py:set_seeds() falls through to
torch.randint when manual_seeds is "" (string, no comma, not all
digits). Smoked end-to-end: HTTP 200 in 11s, real WAV bytes back.
Reproducibility gap honestly documented in the entry's
reproducibility.notes and the actual_seeds field description: with
the new default `actual_seeds: []`, the wrapper rolls a random seed
inside the pipeline but doesn't capture or surface the chosen seed
back through the response. Default-defaulted assets cannot be
regenerated bit-exact; users requiring reproducibility must set
actual_seeds explicitly. Wrapper enhancement to surface the chosen
seed via X-Actual-Seeds header + a CatalogResponse.header_accessories
schema field is the planned fix.
ace-step bumped version 4 -> 5. catalog_version stays at 1 (no
schema changes).
Also added a "source-of-truth precedence" subsection to
CATALOG-CONTRACT.md's service-authoring notes, codifying the
read-order (Pydantic model > handler/pipeline code > Gradio UI >
README). Three ace-step bugs in three rounds (missing field, wrong
enums, stranded bytes, wrong defaults — really four) all share the
same root cause: catalog authored from doc surfaces that lie by
omission.
The pre-fix wrapper at stacks/ace-step/infer-api.py returned a JSON
{output_path: "..."} reference to a file written inside the
container at /app/outputs/. That path was unreachable from outside
the container — every consumer got 134 bytes of JSON-pretending-to-
be-WAV instead of audio. Surfaced by the asset_engine consumer's
end-to-end smoke (althing thread 01KRCJF7NGMXYE9F62Q1A6KFD4 msg 5);
my own earlier smoke missed it because I checked HTTP=200 and stopped
reading instead of inspecting the response body.
Wrapper now reads back the file the pipeline writes and streams the
bytes via fastapi.responses.Response with media_type set from the
audio_format request field (audio/wav | audio/mpeg | audio/flac).
The in-container path is exposed via X-Output-Path header for log
correlation but is no longer load-bearing.
Verified end-to-end against live ace-step on irv-ml1:
POST /generate -> HTTP 200 in 80s
content-type: audio/wav
content-length: 945226
x-output-path: /app/outputs/output_cfe87d1d....wav
$ file response.wav
RIFF (little-endian) data, WAVE audio, Microsoft PCM, 16 bit,
stereo 48000 Hz
Catalog: ace-step bumped version 3 -> 4. Dropped
response.output_field (no longer applicable). reproducibility.notes
expanded to record both the v2 18-arg-tuple fix and this v4
inline-streaming change so the history is auditable from the
catalog itself.
Stale ACEStepOutput Pydantic model left in infer-api.py for now —
unused but small; future cleanup.
Smoke testing in the asset_engine consumer surfaced an
UnboundLocalError 500 from ace-step (althing thread
01KRCJF7NGMXYE9F62Q1A6KFD4 msg 3). Root cause: this catalog had
invented enum values for scheduler_type and cfg_type that don't
exist in the upstream pipeline.
Read pipeline_ace_step.py inside the running container:
scheduler_type dispatch:
if == "euler": scheduler = FlowMatchEulerDiscreteScheduler(...)
elif== "heun": scheduler = FlowMatchHeunDiscreteScheduler(...)
elif== "pingpong": scheduler = FlowMatchPingPongScheduler(...)
# no else -> "linear" / "squared" / "sqrt" leave scheduler unbound
cfg_type dispatch:
accepts: apg | cfg | cfg_star
Catalog had:
scheduler_type: [linear, squared, sqrt] / default linear <- all invalid
cfg_type: [none, cfg, cfg_rw] / default cfg <- only cfg works
Fixed:
scheduler_type: [euler, heun, pingpong] / default euler
cfg_type: [apg, cfg, cfg_star] / default cfg
Bumped ace-step version 2 -> 3. Existing assets generated under v2
with scheduler_type=linear cannot reproduce (the value is now invalid);
v2 assets with the accidentally-valid cfg_type=cfg + a corrected
scheduler can be regenerated under v3 by mapping linear -> euler.
catalog_version stays at 1 (no schema change).
Verified end-to-end against live ace-step on irv-ml1:
POST /generate { scheduler_type: euler, cfg_type: cfg, ... }
-> 200, output_path returned, ~8s wall time
Lesson: OpenAPI introspection isn't enough for accurate catalog
authoring. Upstream OpenAPI returns bare `string` for both fields.
Reading the actual dispatch code is the only way to capture the
allowed values. Will sweep the other 11 service entries against
their implementations before P2 (scale to all services) lands.
asset_engine consumer (althing thread 01KRCJF7NGMXYE9F62Q1A6KFD4)
needed structure for ace-step's 27-field form. Two additive Pydantic
changes — backward-compatible, no catalog_version bump per the
policy table:
- CatalogField.section: str | None = None
- CatalogService.section_groups: list[CatalogSectionGroup] = []
- new CatalogSectionGroup model: {id, label, hint?}
Validator: every Field.section value must reference a declared
section_groups[].id within the same service; section_groups[].id
values are unique. CATALOG-CONTRACT.md updated with both the new
service-fields row and a versioning-policy row covering
"add optional Field/Service keys -> no bump."
ace-step entry rewritten to use the new schema:
- bumped version 1 -> 2
- declared 6 section groups (basic / generation / conditioning /
a2a / lora / output) with hints
- tagged every field with a section
- added previously-missing checkpoint_path (required: true,
default: "/app/checkpoints" — the container's mount path).
Wrapper-side cleanup (default in infer-api.py) queued as
follow-up.
- changed lyrics from optional: true -> required: true with
default "" to match upstream's `lyrics: str` shape (empty
string satisfies it).
JSON Schema regenerated.
Pydantic-model side of this change lives in asset_engine at
src/asset_engine/catalog.py — committed there separately.
Consumer-side renderer for the JSON-envelope + timestamps shape
shipped (althing thread 01KRCF4W66X3, msg 5). Smoke + regression
clean. Per the contract on the entry's notes block, flipping to
ready now that the renderer is in place.
asset_engine consumer needed to render kokoro-captioned, whose wire
shape is a JSON envelope carrying base64-encoded audio plus a
structured timestamps array. Modeling it as response.type=json
would force either a per-service-id renderer (forbidden by
brief §1.7) or extending the closed response-type vocabulary
(forbidden by brief §2.2 without a coordinated bump).
Resolution (per althing thread 01KRCF4W66X3): keep response.type
closed at the existing six values and decompose at the response
*field* level instead — the same flexibility seam already used by
mime / mime_from_field / output_field. Adds three optional keys:
- audio_field: JSON key holding base64-encoded audio bytes
- audio_format_field: JSON key holding the decoded audio MIME
- timestamps_field: JSON key holding a structured timestamps array
(independent of type, declared by any service emitting time-
aligned markers)
Validators in CatalogResponse enforce sane combinations:
- audio_field requires response.type=audio
- audio_field forbids mime_from_field
- audio_format_field requires audio_field
This is additive and backward-compatible — no catalog_version bump,
existing services parse unchanged. CATALOG-CONTRACT.md updated with
the new rows in the response-field table and a versioning-policy
row codifying that adding optional keys to response: doesn't bump.
kokoro-captioned re-shaped to use the new schema:
response:
type: audio
audio_field: audio
audio_format_field: audio_format
timestamps_field: timestamps
And marked status: experimental until the asset_engine consumer's
audio-with-timestamps renderer ships.
JSON Schema regenerated to reflect the new Pydantic shape.
Pydantic-model side of this change lives in the asset_engine repo
at src/asset_engine/catalog.py — committed there separately.
Per a request from the asset_engine consumer (althing thread
01KRCF4W66X3N24B01FF2Y7V3D), and verified against the live kokoro
OpenAPI + exercised endpoints:
* kokoro: version 1 → 2; adds three fields surfaced by the upstream
schema but not previously declared:
- speed (slider 0.25–4.0, default 1.0)
- volume_multiplier (slider 0.5–2.0, default 1.0; UI-bounded
since upstream is unbounded — noted in description)
- lang_code (text, optional override of the voice-name-derived
language hint)
* kokoro-captioned: new service entry wrapping
/dev/captioned_speech. Same model + image as kokoro proper but
separate catalog entry because the response shape is structured
JSON (audio inline as base64 + word-level timestamps), not raw
audio bytes. Verified shape captured in reproducibility.notes
so future consumers don't have to re-discover it. response.type
= json (consumer renders custom: player + subtitle overlay).
* reproducibility_audit: row added for kokoro-captioned.
Deferred (separate from this commit):
- kokoro-blend-voice. /v1/audio/voices/combine returns 403 on the
default config (allow_local_voice_saving=False); even with the
flag flipped it writes to a temp dir, not /worktank/kokoro/user_voices.
The persistent blend mechanism in this fleet is
playbooks/blend-kokoro-voice.yaml. Ad-hoc blending already works
through /v1/audio/speech via the inline syntax voice="a(w)+b(w)";
consumer can surface that as a UI affordance without any
catalog change.
catalog_version stays at 1 (no field-type vocabulary changes).
JSON Schema regeneration produced byte-identical output.
Adds the supporting infra around the service catalog now that it
has external consumers (the asset_engine UI being the first; CLIs,
monitoring, other services may follow):
- CATALOG-CONTRACT.md: the consumer-facing contract. Defines
versioning policy (catalog_version vs per-service version),
closed field-type and response-type vocabularies, recommended
vendor+drift-check sync workflow, known-consumers list, service
authoring notes.
- services.schema.json: JSON Schema (draft 2020-12) for the
catalog. Generated from the Pydantic model in
~/development/asset_engine/src/asset_engine/catalog.py via
`uv run scripts/dump_schema.py --publish`. Lets non-Python
consumers validate against the same shape.
- services.yaml: adds catalog_version: 1 at the root and reframes
the file's header to call out its first-class-contract status.
Quotes a vibevoice label that contained an unescaped colon
(caught by the asset_engine's strict YAML parser on first sync).
services.yaml: form-generator contract for the forthcoming
asset-generation UI. 13 inference services on irv-ml1 (TTS, ASR,
SFX, music) catalogued with field schemas extracted from Pydantic
models, response types, reproducibility audit, and license
warnings. ComfyUI flagged catalog-deferred (workflow-DAG API
doesn't fit a form-based UI without a per-asset-type wrapper).
design-brief.md: the prompt to give a frontend-design agent before
any pixels. Locks in the data-model decisions whose later cost is
asymmetric (asset-as-first-class entity, content-addressed output
storage, reproducibility hard requirement, job table, auth as a
no-op DI seam, API surface ≠ UI surface, schema versioning,
tags/collections plumbed in v1 with no UI). Defines a closed
field-type vocabulary (8 types) and response-renderer vocabulary
(6 types) — agent isn't allowed to extend them. Pre-decides the
required UI surfaces; leaves IA, library-nav pattern, long-job
UX, and big-form ergonomics open for the agent to opine on.
StableAudioPipeline isn't reentrant — concurrent requests share the
scheduler's step_index counter and corrupt each other mid-run
(observed: IndexError in cosine_dpmsolver_multistep when two requests
overlap). Wrap the pipeline call + audio decode in a single
asyncio.Lock created at startup, and run the (sync, GPU-bound)
pipeline call via asyncio.to_thread so the event loop stays
responsive. Concurrent requests now queue cleanly instead of racing.
Verified: 5 parallel POSTs at steps=50 all return 200, clear ~4s
serialization spacing (4, 8, 12, 16, 20s wall time), distinct
output hashes per seed.
server.py accepted cfg_scale in the request schema and the README
documented its 0–20 range, but the pipeline call never received it
— so changing cfg_scale between requests silently produced identical
output (the pipeline ran at its own default of 7.0 every time). Add
guidance_scale=req.cfg_scale to the pipe(...) call.
Verified: (prompt, seed, steps) held constant, cfg_scale=3.0 vs 15.0
now produce different SHA256s; same triple at cfg_scale=7.0 is
deterministic across repeated calls.
Wrapper only enumerates one voice directory (settings.voices_dir,
default /app/api/src/voices/v1_0 — inside the container's writable
layer, not bind-mounted). Override via VOICES_DIR=/app/user_voices
(host bind mount) and add a command shim that cp -r's built-ins from
the in-image v1_0 into user_voices on every start. Built-ins re-seed
fresh from the image (so upgrades that add voices propagate); custom
.pt files in user_voices are preserved (cp -r is additive).
Also adds scripts/blend_kokoro_voice.py + a playbook around it that
mirrors the wrapper's request-time voice="a(w)+b(w)" math but writes
the result as a named .pt to user_voices, making it discoverable via
GET /v1/audio/voices and persistent across recreate. Defaults to
athena = af_bella(2)+af_aoede(1) normalized.
Same shape as task-board: build-on-host from vh/vor, bind-mounted
persistence for sessions/ and responses/ (the user-published markdown
files), exposed at port 7879 (adjacent to task-board's 7878 since both
are claude-tooling sidecars).
Workflow template assumes the same DEPLOY_SSH_KEY + MGMT_REPO_TOKEN
secrets at user scope; nothing new to provision. Playbook accepts SHA
or branch refs (same fix as deploy-task-board.yaml) so manual runs
and CI runs share the same code path.
Centralized vs upstream-local: README documents the trade. Claude
fetches response markdown via /api/sessions/{id} JSON instead of a
local file read — the only API-flow change from the upstream README.
Runner is now re-registered with `:docker://node:20-bookworm-slim`
schema in its labels, so workflows targeting `pfi-fleet` get that
image automatically. Saves a few lines per workflow and gives us one
place (the runner config) to bump the default image when a new
node/debian release lands.
CI passes --var ref=<github.sha> (a full SHA), but the playbook
hardcoded `git reset --hard origin/{{ ref }}` which only works for
branch names — `origin/<sha>` is invalid syntax. Resolve ref via
git rev-parse with `^{commit}` (try origin/<ref> first for branch
names, fall back to bare <ref> for SHAs/tags) so manual runs (ref=main)
and CI runs (ref=<sha>) both work.
Same fix applied to the changed_when comparison so no-op reruns still
report ok instead of changed.
Runner's .runner registration cached :host mode at first start; env-var
label updates aren't sticky once the runner is registered. Until we
re-register with docker-schema labels, workflows must declare their
own container. node:20-bookworm-slim has node (for actions/checkout)
and apt (for python3-yaml + openssh-client install).
debian:bookworm-slim lacks node, so actions/checkout@v4 (a JS action
running dist/index.js) fails with `exec: "node": executable file not
found in $PATH`. Dropping the explicit `container:` directive lets
the runner use its label-default — node:20-bookworm-slim has node +
git out of the box. Install step shrinks to python3 + pyyaml +
openssh-client.
Central runner on ana-docker (gitea is local; existing fleet tooling
already SSHes from there). Playbook is parameterized so future
site-local runners (nh3-docker, esh-docker-vm) drop in via --var
overrides instead of copy-paste.
Includes a workflow template for vh/task-board that calls the existing
deploy-task-board.yaml playbook — keeps the playbook as the single
source of truth for "how task-board is deployed", manual or automated.
Labels embed `:docker://node:20-bookworm-slim` schema; without it,
act_runner v0.6+ silently falls back to host-mode and runs job steps
inside the Alpine runner container (no apt/python/node), breaking any
real workflow. node:20-bookworm-slim is small + has git + node so
actions/checkout works out of the box.
The applet outgrew "stack alongside the infra-management workspace" —
it has its own pyproject, multi-tenant deploy story, separate
release cadence, and isn't actually about managing infrastructure.
Lives at https://gitea.phasefinal.com/vh/nevermore now, with
provenance noted in its initial commit.
This commit removes:
stacks/news-digest/ (full stack tree)
playbooks/deploy-news-digest.yaml
scripts/add-digest-user.sh
The existing ana-docker deployment continues running on its baked
local/news-digest:v5 image — nothing changes for the live install
until you choose to redeploy from the new repo. Migration steps
(rename data dir, redeploy, retire old compose dir) are in
nevermore's README.
Updated:
README.md — Current stacks listing now points at the new repo
STATUS.md — milestones entry for the extraction
Replaced the 9-month-stale 'Last Updated: 2025-07-14' line with a
status disclaimer — this is KB-derived advisory material, not
something we maintain in lockstep with code. Tracer-date claim was
implying a freshness contract we don't fulfill. Found via
/tend-docs.
Same anti-pattern as the deleted model-list.md — a hardcoded snapshot
of mutable config that's guaranteed to drift. Replaced the 15-row
table with a one-liner pointing at stacks/llama-swap/conf/config.yaml
(the canonical source) and the live /v1/models HTTP endpoint. Found
via /tend-docs.
The compose-side default was still pinning qwen3.5-35-a3b — broken
on launch since its GGUF stopped working months ago. Real .env on
ana-docker overrides to granite-4-small so live deploys are unaffected,
but the default was misleading for anyone forking the stack. Found
via /tend-docs.
The original default model in .env.example was changed to
granite-4-small months ago when qwen3.5-35-a3b's GGUF file started
exiting on launch, but the README still named the old one as
"current". Also bumped the summarization-style description from
"one sentence" to "2-3 sentences" to match the post-trafilatura
prompt rewrite. Found via /tend-docs.
Bumped "Last updated" to 2026-04-29 and added a milestones section
for the audio-gen + news-digest applet + task-board + tooling work
that landed since 2026-04-24. Found via /tend-docs.
These four ana-docker stacks were missing from the discoverability
index — readers landing on the README couldn't find them without
walking stacks/. Found via /tend-docs.
Self-reported "Synchronized with llama-swap config.yaml on 2025-07-18"
— 9 months stale. Canonical model truth is stacks/llama-swap/conf/config.yaml;
the static snapshot was guaranteed to drift. No historical value (not
an ADR, post-mortem, or migration runbook).
Found via /tend-docs.
Stock neosmemo/memos:stable, port 5230, SQLite at
/opt/docker/conf/memos/data/. Joins traefik-net and ships homepage
labels (group=Notes) so it auto-appears on the dashboard via docker
discovery — no edit to configs/homepage/services.yaml needed.
First-run bootstrap is via the UI: visit http://10.250.50.70:5230
and create the Host account through the sign-up form.
Playbook idiom note: docker compose pull lines need the literal
block scalar (|) when the grep pattern contains colons — bare-string
shell value made YAML parse the colon as a mapping separator and
elway choked on first try.
Mirrors the reusable tooling (scripts/, generic playbook templates,
.gitignore, conventions section of CLAUDE.md) into a new directory
and strips everything fleet-specific: servers/, stacks/, configs/,
fleet-named playbooks (deploy-*, decouple-*), runbooks, status,
host-pinned scripts.
Output is an empty conventionally-organized workspace with fresh git
history, ready to populate with a different fleet. Skeleton
CLAUDE.md / README.md / STATUS.md are written with the new fleet
name baked in but no server table or placement rules pre-populated.
Deliberately does NOT create a remote or push — the user picks the
namespace + name explicitly via tea / git remote add.
scripts/fork-fleet.sh ~/development/acme-prod-management
scripts/fork-fleet.sh /tmp/test-fork test-fleet
The task-board v0.1.11 orange-while-waiting treatment depends on the
assistant pushing the pending-shells list — hooks can't enumerate
Claude Code's background tasks externally (confirmed against the
hook docs: no payload field, no state file, no lifecycle event, no
JSON form of /tasks). So the discipline lives in CLAUDE.md.
Adds a "Customizing the run schedule" section (DIGEST_CRON_AM/PM env
vars, edit-and-recreate flow) and a "Multi-tenant: one instance per
teammate" section covering scripts/add-digest-user.sh end to end:
what it does, the per-user file layout on ana-docker, idempotent
schedule/password updates, and the teardown path.
Updated the stale "two editions per day" intro line to note the
schedule is now configurable.
Hardcoded crontab → render at container start from
DIGEST_CRON_AM + DIGEST_CRON_PM. Defaults match the original
0800 / 2000 so existing deploys are no-ops.
scripts/add-digest-user.sh learns --am and --pm flags so each
teammate's stack can fire on their hours:
scripts/add-digest-user.sh bob --am "0 6 * * *" --pm "0 17 * * *"
scripts/add-digest-user.sh carol --pm "30 18 * * 1-5" # weekdays only
Standard 5-field cron syntax; busybox crond honors the container's
\$TZ. Removed the now-unused stacks/news-digest/crontab file and
the matching COPY in the Dockerfile.
Two pieces:
1) Multi-tenant onboarding via scripts/add-digest-user.sh
Shared miniflux + per-user digest stack. Onboarding a teammate
takes one command (plus a one-time sudo for dir creation):
scripts/add-digest-user.sh <username>
What the script does:
- Reads miniflux admin creds from ana-docker
- Allocates next free port (scans existing digest-*/.env)
- Generates a random password (or accepts one as 2nd arg)
- Creates the miniflux user via the admin API
- Materializes a per-user .env at /opt/docker/compose/digest-<user>/
(inherits NEWS_DIGEST_TAG from the canonical stack so all
tenants run the same image)
- Brings up `docker compose -p digest-<user> up -d`
- Seeds default world/local feeds in the new user's miniflux
- Triggers a first digest run
compose.yaml now uses ${DIGEST_PROJECT:-news-digest} to namespace
container_name + homepage labels. Default keeps backward-compat
for the singleton install — existing stacks unaffected.
2) Masthead overlap on phone widths
Desktop CSS pinned .masthead-edition to grid-row 1, which collided
with .masthead-brand once the mobile media query collapsed both
to grid-column 1. Result: "MORNING EDITION" badge stacked on top
of the "DAILY DIGEST" hero. Reset grid-row to `auto` for all
three masthead children in the ≤720 px breakpoint so they
auto-flow vertically.
Three things were broken on phones:
1. The collapse button I added to .desk-head had no grid placement,
so it auto-flowed into the desk-sub row and looked like a floating
chevron. Made the desk-head grid 4 columns explicit (num | title |
count | collapse) and pinned the button to col 4 row 1.
2. The 720px breakpoint was the only one — everything inherited
tablet rules at iPhone widths. Added a true-phone tier at
≤480 px that hides the section number badge and the rail
gutter, floats chips inline above the title, makes the jumpnav
horizontally scrollable for narrow widths, drops the edition
number, and bumps touch targets.
3. Long URLs / unbroken tokens could push horizontal overflow.
Added overflow-wrap: anywhere on titles + tldrs and overflow-x:
hidden on body as a belt-and-suspenders catch.
vh