Files

T

vh c5bbb90980 fix(fish-s2): reference_id was a silent no-op — populate per-voice dirs + guard the regression

reference_id=<name> resolves against the DIRECTORY references/<name>/
(audio + same-basename .lab), not a flat references/<name>.wav. Voices
were staged flat with the per-name dirs left empty, so every
reference_id resolved to nothing and Fish fell back to its default
speaker — every dropdown voice produced byte-identical audio (proven:
Abigail == Imogen == no-ref, same text+seed). This was the real "no
accent" root cause, independent of the asset-engine "undefined" select
bug.

Server fix (applied to irv-ml1): populated references/<name>/<name>.wav
+ <name>.lab for all 32 voices; re-test confirms Imogen/Eleanor/
Beatrice/Abigail/no-ref now all distinct.

Durable hardening + record correction:
- playbook: normalize-layout step (flat <name>.wav -> nested dir, cp -u
  idempotent, when-gated on count mismatch) + an A/B verify gate that
  hard-fails the deploy if two reference_ids yield identical output.
- services.yaml: correct the reference_id resolution doc (dir + .lab,
  not flat wav).
- README + persistent-memory: correct the "reference_id-by-name is THE
  working path, verified" claim — it was a no-op until this fix; the
  prior ECAPA 0.79 result came through the inline base64 path.

2026-06-01 16:42:30 -07:00

archive/asset-engine

docs: archive asset-engine design-brief.md

2026-05-14 15:33:15 -07:00

asset-engine

fix(fish-s2): reference_id was a silent no-op — populate per-voice dirs + guard the regression

2026-06-01 16:42:30 -07:00

pfi

2026-04-29 17:03:41 -07:00

runbooks

vllm: rename stack from vllm-qwen3 → vllm + add Skywork reward classifier

2026-05-13 22:00:26 -07:00

orientation.md

docs/runbooks/nh3-prune-ritual: write up the quarterly NH3 prune ceremony

2026-04-27 20:54:08 -07:00

README.md

docs/runbooks/nh3-prune-ritual: write up the quarterly NH3 prune ceremony

2026-04-27 20:54:08 -07:00

README.md

docs/

Navigation map for the documentation tree. New session? Read orientation.md first — it's the narrative overview of the fleet, backup architecture, governing principles, and gotchas, and it points at everything else.

Tree

docs/
├── orientation.md            # start here — fleet overview + where-to-look guide
├── runbooks/                 # ops runbooks (recovery, deployment phases)
│   ├── disaster-recovery.md
│   ├── nh3-prune-ritual.md
│   └── pbs-deployment.md
└── pfi/                      # PFI-specific reference (services, models, VMs)
    ├── docker-stack.md
    ├── model-list.md
    ├── proxmox-vms.md
    ├── recommended-model-settings.md
    ├── vm-102-matrix-appservice.md
    └── vm-102-matrix-synapse.md

What goes where

runbooks/ — step-by-step ops procedures. Anything you'd reach for during an incident or while standing up new infrastructure. Examples: disaster recovery (blast-radius tiers + restoration steps), PBS deployment (9-phase rollout). New runbook → new file here.
pfi/ — PFI-specific reference material that's too narrow for the top-level CLAUDE.md but doesn't change incident response. AI model inventory, recommended inference settings, Matrix bridge config, Proxmox VM map. New stable reference → new file here.
Top-level (docs/orientation.md, docs/README.md) — narrative guides about the workspace itself, not about specific infra.

Cross-references

Fleet topology + servers table: top-level CLAUDE.md.
Open work + recent milestones: top-level STATUS.md.
Durable cross-session facts: ~/.claude/projects/-home-lkraven-development-eshpfi-management/memory/.

Conventions

Markdown, GitHub-flavored. CommonMark renders fine in most viewers.
File names are lowercase-kebab-case, descriptive. No dates in filenames — git history covers that.
One topic per file. If a file grows past ~500 lines, look for a natural split before adding more.
No checked-in binaries or checksums. Build/release artifacts belong in a build pipeline or tools/, not docs/.