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

feat(litellm): add glm-5.3, move gen-frontier pair to glm-5.3 (effort low/high), advertise 1M/128K on GLM 5.2/5.3 with a 128K default max_tokens

Browse Source
This commit is contained in:
vh
2026-10-07 17:30:39 -07:00
parent d99f3a1a8d
commit 8a6d2f9433
2 changed files with 72 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
persistent-memory.md
+2
View File
@@ -186,6 +186,8 @@ Every vLLM seat on a shared card (GPU 0, GPU 1) has byte-pinned KV (`--kv-cache-
- `[2026-10-06]` **Scriberr diarization fixed: gated pyannote, a torchcodec/torch mismatch, and WhisperX's CPU defaults; model caches on /tank, HF_TOKEN a placeholder (Prime), GPU+speaker profiles.** Patch 0003 waits for the next rebuild (tracked at `stacks/scriberr/patches/README.md`). → `persistent-memory.d/2026-10-06-scriberr-diarization-fixed.md`
- `[2026-10-06]` **Backup checker: destroyed guests reported as residue, an ssh stdin swallow fixed, snapshot age from the name; residue pruned (Prime); pbs-nh3 mirror keeps pbs-ana's history (Prime "match history"), first prune 10-07 00:00.** → `persistent-memory.d/2026-10-06-backup-checker-fixes-and-mirror-retention.md`
- `[2026-10-07]` **Gateway: glm-5.3 added; gen-frontier / gen-frontier-reasoning moved 5.2 → 5.3 (Prime); every GLM 5.2/5.3 entry advertises 1,048,576 in / 131,072 out with max_tokens 131,072 as the default.** 5.3 cannot turn reasoning off, so the gen-frontier pair is now effort low / high (measured ~260 vs ~1,490 reasoning tokens). ⚠ z.ai's `thinking: disabled` is light thinking, not zero, on 5.1/5.2/5.3 alike (220–340 reasoning tokens on a hard prompt). Restarted 1725 (61 s), held 2 h for albok-dev's load A/B. The gate script's first two runs could never pass: `grep -c` exits 1 on a zero count. Images: glm-5.x is text only (z.ai rejects image parts); glm-4.6v and glm-5.3-flash read images on our plan, but neither is on the gateway. → `stacks/litellm/conf/config.yaml`
- `[2026-10-07]` **Hermes launchers repaired (Miranda relay 8462):** svos-dev's scratch probe had rewritten `~/.hermes/hermes-agent/.hermes/bin/{hermes,hermes-acp}` to exec a /tmp scratch Python. Repointed to `~/.hermes/tools/python-3.14.7…`; the gateway was not restarted. ⚠ Don't run `git` in `~/.hermes/hermes-agent`: a `status` there looped on auto-gc.
- `[2026-10-07]` **albok-service 0.1.13 (unit 4.2, the sensitivity gate) deployed on nh3-albok at 1135 at albok-dev's ask 8413.** Rollback is NOT free: the first-start scan writes `sensitivity` sidecars, which 0.1.12 cannot load, so rolling back needs the strip snippet first. The census found `leaks` 8: six hold the shared all-agents key, two are false positives on a doc placeholder, nothing to rotate. → `stacks/albok-service/README.md`
- `[2026-10-06]` **albok-service 0.1.11 (0202) then 0.1.12 (1254) deployed on nh3-albok at albok-dev's asks 7991/8199**, built from clean archives, pinned by digest, single-file upload (deploy-stack's `--delete` would wipe the on-host rollback copies). Every wing is now migrated to generation collections, so a 0.1.10 rollback needs a full reindex. albok's 2.01×-vs-2× load check awaits Prime. → `stacks/albok-service/README.md`
- `[2026-10-06]` **The LiteLLM gateway keeps no request/response content, and `store_prompts_in_spend_logs: false` is now a marked consumer guarantee (comfy-dev, arbo incognito).** Proved with a canary plus positive controls; per-request `no-log` does NOT cover the proxy's own spend-log callback (v1.97 source). irv-ml1 restic also excludes `input/incognito-*` (dry-run proved with a canary and a control). `847424c`, `0f6c7a0`.