mathias/tapir
1
0
Fork 0
Code Issues 25 Pull Requests Actions Packages Projects Releases Wiki Activity

docs(homelab): pin verified LiteLLM endpoint (NodePort 30401, not 31234)
CI / Lint / Test / Vet (push) Successful in 4s
Details
CI / Build & Import (push) Failing after 0s
Details
CI / Mirror to GitHub (push) Has been skipped
Details

Browse Source 
Conductor verified against the live koala k3s cluster before launching the
adapter workers: LiteLLM is in ns ai-stack, ClusterIP 10.43.159.89:4000,
off-cluster NodePort 30401. The doc's 31234 was actually llama-swap. Also
flag that sk-local-123 now 401s — use LITELLM_MASTER_KEY from the vault.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
mathias
2026-06-02 16:58:07 +02:00
co-authored by Claude Opus 4.8
parent 6421a1334a
commit bb47f54a41
1 changed files with 10 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/homelab-integration.md
+10 -5
View File
@@ -6,11 +6,16 @@ it** — endpoints and aliases drift, and this file is a snapshot (2026-06-02),
## Local AI (the Primary in `llm.Router`)
- **LiteLLM gateway:** `http://koala:4000/v1/` (OpenAI-compatible). In-cluster callers use this;
there is also a NodePort (`31234`) for off-cluster access — **confirm** which Tapir should use
based on where it runs.
- **Auth key:** `sk-local-123` (the local LiteLLM gateway key). Treat as a secret via the
SecretStore port; do not hardcode in committed code.
- **LiteLLM gateway:** OpenAI-compatible, lives in k3s namespace `ai-stack` (verified 2026-06-02
from koala via `kubectl get svc -n ai-stack`):
- **In-cluster:** `http://litellm.ai-stack.svc.cluster.local:4000/v1/` (ClusterIP `10.43.159.89:4000`).
- **Off-cluster (host / NodePort):** `http://koala:30401/v1/` — service `litellm-nodeport` (`4000:30401`).
- NOTE: the earlier `31234` was **wrong** — `31234` is the `llama-swap` NodePort (`8080:31234`),
not LiteLLM. Use `30401` for off-cluster LiteLLM. `confirm` resolved.
- **Auth key:** treat as a secret via the SecretStore port; do not hardcode in committed code.
NOTE: the documented `sk-local-123` returned `401` on `30401/v1/models` (2026-06-02) — it is
stale or the gateway now enforces the `LITELLM_MASTER_KEY` (1Password `op://HomeLab/LITELLM_MASTER_KEY`).
Resolve the live key from the vault when wiring; `sk-local-123` is no longer valid. `confirm` partially resolved.
- **Model alias format:** `host/name`, e.g. `koala/qwen3-coder-30b`, `koala/phi4-mini`,
`iguana/devstral`, `iguana/deepseek-r1-14b`. **Not** the `ollama/` prefix form.
- **Which alias for summarization:** NOT yet decided. Tapir summarizes transcript text, so a