vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

memory: ratatoskr dots-tts cutover shipped (v0.22.2) — hold :8197 rollback pending operator ear-check

Browse Source
This commit is contained in:
Vuong Hoang
2026-08-10 07:15:22 -07:00
parent edc9f42da1
commit b846ebf32e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
persistent-memory.md
+1 -1
View File
@@ -119,7 +119,7 @@ _As of 2026-08-08 — long session; all major arcs LANDED (full detail per arc i
- **EVIDENCE HOLD (partial):** WT #394 index-row half LIFTED + swept (kb 8,230→2,876); the **FILE half STILL STANDS** — do NOT delete the on-disk generation dirs (`fiction/rex390-dcc`, `rex392-dcc`, `b59c147c5ce0`). Also un-actioned worldtree-side: the `reconcile --repair` rc=1 git-staging bug (phantom `docs/specs/saga-taxonomy-redesign-plan.md`) — flagged, their code.
- **OPEN LOOPS (2026-08-10):** (1) **dots-tts ratatoskr cutover** — handoff SENT to ratatoskr-dev (thread `01KZNZF1…`: endpoint :8198, OpenAI `/v1/audio/speech` shape, 4 voices, streaming WAV format, the 48k/serialized-single-consumer/no-affect-dials caveats); **awaiting their cutover decision** (chatterbox :8197 kept up as their rollback). (2) **LFM2.5-2.6b bake-off for brokkr — DONE:** `vllm-lfm25` LIVE on ana-ml2 GPU1 :8021 (LiquidAI/LFM2.5-2.6B, Lfm2ForCausalLM/vLLM 0.24.0, BF16, util 0.09 ~8.7GB into GPU1's unreserved slack — no prod reservation touched; max-len 16384; NO `--reasoning-parser` so content non-empty). LiteLLM alias `lfm2.5-2.6b` (vendor sampling temp0.1 + topk50/reppen1.1 via `extra_body` so drop_params doesn't strip them). Smoke: content_len 636, reasoning_content 0, finish stop. brokkr notified (`01KZP08NB7…`). EVAL-ONLY pending operator production ruling (LFM Open License); NOT in any default/fallback chain. Backups: litellm `config.yaml.bak-pre-lfm25-20260810`; targeted `up -d vllm-lfm25` (shared-.env → never bare up-d). Repo: `stacks/vllm/` + `stacks/litellm/conf/config.yaml`.
- **OPEN LOOPS (2026-08-10):** (1) **dots-tts ratatoskr cutover — SHIPPED on ratatoskr's side** (v0.22.2 / commit `38b78d8`: tts.py seam → OpenAI `/v1/audio/speech`, browser Web-Audio SR 24000→48000, default voice glados_25s→glados, donut carries; integration-verified end-to-end on their :8765, 520 tests green; their one-synth-per-turn lock DEC-5 matches the server's serialized model). ⚠ **HOLD chatterbox :8197 as rollback — do NOT tear down** until ratatoskr pings back with the operator's ear-check sign-off ("solid, drop the rollback"). **REMAINING GATE = operator ear-check on the LIVE ratatoskr RP surface** (:8765), distinct from the burn-in booth A/B he already approved. thread `01KZNZF1…`. (2) **LFM2.5-2.6b bake-off for brokkr — DONE:** `vllm-lfm25` LIVE on ana-ml2 GPU1 :8021 (LiquidAI/LFM2.5-2.6B, Lfm2ForCausalLM/vLLM 0.24.0, BF16, util 0.09 ~8.7GB into GPU1's unreserved slack — no prod reservation touched; max-len 16384; NO `--reasoning-parser` so content non-empty). LiteLLM alias `lfm2.5-2.6b` (vendor sampling temp0.1 + topk50/reppen1.1 via `extra_body` so drop_params doesn't strip them). Smoke: content_len 636, reasoning_content 0, finish stop. brokkr notified (`01KZP08NB7…`). EVAL-ONLY pending operator production ruling (LFM Open License); NOT in any default/fallback chain. Backups: litellm `config.yaml.bak-pre-lfm25-20260810`; targeted `up -d vllm-lfm25` (shared-.env → never bare up-d). Repo: `stacks/vllm/` + `stacks/litellm/conf/config.yaml`.
- **OPEN FOLLOW-UPS:** chatterbox-fast **deployed flat-build-context vs package-repo divergence** (reconcile so a repo rebuild matches deploy — repo commit `6bc7bf0` has cap+norm_loudness in package layout; deployed is flat cap-only). Standing/parked: CI-flip runner-auth research, gitea `REQUIRE_SIGNIN_VIEW=false`, #363 research-wing ingest (no deadline), zonos-gateway CI-wire.