Commit 1280ea0
hermes config.yaml: add auxiliary LLM block pointing at mios-ai
Operator-flagged 2026-05-11 (inside the mios-hermes container shell
after running setup-hermes.sh): every agent invocation logs
WARNING agent.auxiliary_client: Auxiliary auto-detect: no provider
available (tried: openrouter, nous, local/custom, api-key)
Compression, summarization, and memory flush will not work.
Set OPENROUTER_API_KEY or configure a local model in config.yaml.
Hermes-Agent has two model slots:
* `backend` -- the operator-facing chat model (already wired here
to mios-ollama:11434 / qwen2.5-coder:7b)
* `auxiliary` -- a separate model used for context compression,
summarization, and memory flush. With no config block Hermes
falls through openrouter/nous/local-custom/api-key and lands on
nothing, so those features silently degrade.
Added an `auxiliary` block pointing at the same mios-ai (LocalAI
OpenAI-compatible /v1) surface every other MiOS AI client uses
(Architectural Law 5). Reuses the API_SERVER_KEY from
/etc/mios/hermes/api.env so we don't ship a second secret.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>1 parent 1a73021 commit 1280ea0
1 file changed
Lines changed: 16 additions & 0 deletions
File tree
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
24 | 24 | | |
25 | 25 | | |
26 | 26 | | |
| 27 | + | |
| 28 | + | |
| 29 | + | |
| 30 | + | |
| 31 | + | |
| 32 | + | |
| 33 | + | |
| 34 | + | |
| 35 | + | |
| 36 | + | |
| 37 | + | |
| 38 | + | |
| 39 | + | |
| 40 | + | |
| 41 | + | |
| 42 | + | |
27 | 43 | | |
28 | 44 | | |
29 | 45 | | |
| |||
0 commit comments