audit(2026-10-26): runaway Gmail digest + dead Nous credential; model default reverted to OmniRoute; conduit 0.69.2 live; freshness floor still 2026-10-08

This commit is contained in:
Tony0410
2026-10-26 00:19:37 +08:00
parent 2df1bce5ea
commit 123a74cb0b
16 changed files with 433 additions and 59 deletions
+38 -9
View File
@@ -3,8 +3,8 @@ title: Model Providers
type: system
status: active
created: 2026-07-22
updated: 2026-10-23
verified_on: 2026-10-23
updated: 2026-10-26
verified_on: 2026-10-26
confidence: high
tags: [model, provider, inference, routing]
sources: [live-probe, config, web-search]
@@ -20,27 +20,56 @@ Verified from live `~/.hermes/config.yaml` → `custom_providers`, 2026-10-01.
| Provider | URL | Models | Role |
|---|---|---|---|
| `custom:omni-101` | `http://100.78.63.20:20128` | 5,384 | **Primary.** OmniRoute on the estate (`omni-101`). 15 of 30 cron jobs reference it |
| `custom:omni-101` | `http://100.78.63.20:20128` | 5,384 | **Primary.** OmniRoute on the estate (`omni-101`). 18 of 28 cron jobs reference it (2026-10-26) |
| `custom:Omniroute:20128` | `http://omniroute:20128/v1` | 5,398 | Secondary OmniRoute host — legacy naming, kept alongside `omni-101` |
| `custom:litellm` | `http://litellm:4000/v1` | 1,728 | Fallback inference (slower path, 6–26s/call) |
| `custom:command-code` | `https://api.commandcode.ai/provider/v1` | 71 | DeepSeek Flash primary via the `deepseek-flash-mix` combo (added 2026-08-19); also the source of the `MODEL_NOT_IN_PLAN` 403 on `gpt-5.6-terra` |
| `custom:guacano` | `http://ollama:11000/v1` | 46 | Guanaco LLM proxy/router on CT205 (Ollama stack). See [[systems/guanaco]] |
| `custom:omni` | *(removed)* | — | **No longer configured.** It once served auxiliary roles (vision, skills, approval, mcp, web_extract, compression). Two cron jobs still name it as their provider key — see [[systems/scheduled-tasks]] |
**Built-in (non-`custom_providers`) routes still in use as fallbacks:** `opencode-go / mimo-v2.5`, `opencode-zen / deepseek-v4-flash-free`, `nous / stepfun/step-3.7-flash:free`, `ollama-cloud / qwen3.5:397b`, `kilocode / poolside/laguna-m.1:free`. `charm-hyper` (Charmbracelet, `hyper.charm.land/v1`, free tier 100 credits/mo) is no longer in the live stack.
**Built-in (non-`custom_providers`) routes still in use as fallbacks:** `opencode-go / mimo-v2.5`, `opencode-zen / deepseek-v4-flash-free`, `nous / stepfun/step-3.7-flash:free`, `ollama-cloud / qwen3.5:397b`, `kilocode / poolside/laguna-m.1:free`. `charm-hyper` (Charmbracelet, `hyper.charm.land/v1`, free tier 100 credits/mo) is no longer in the live stack. **The live `fallback_providers` chain (2026-10-26) is `nous` / `meituan/longcat-2.5-preview:free` → `opencode-zen` / `deepseek-v4.1-flash` → `custom:guacano` / `deepseek-v4.1-flash` → `custom:litellm` / `kilo-reflection-beam-free` → `kilocode` / `poolside/laguna-m.1:free` → `custom` / `or-inclusionai_ling-2_6-1t`.**
**Default provider:** **`nous`** → `https://inference-api.nousresearch.com/v1`. **Default model:** **`meituan/longcat-2.5-preview:free`**.
The default moved OFF OmniRoute on 2026-10-20 — see below. The `custom` provider key is no longer the default.
**Default provider:** **`custom:omni-101`** → `http://100.78.63.20:20128`. **Default model:** **`smart-route`**.
⚠ **The default moved BACK to OmniRoute on 2026-10-24 19:06:10 AWST** (session switch note: *"model was just
switched from meituan/longcat-2.5-preview:free to smart-route via omni-101"*). The `nous` direct window ran
2026-10-20 22:01 → 2026-10-24 19:06 and the 2026-10-22/10-24/10-25 audit entries recorded it as current —
**stale**. `config.yaml` last written 2026-10-25 19:13.
→ [[incidents/2026-10-22-nous-portal-refresh-token-invalid]]
Provider names that appear in job configs but not in `custom_providers` do **not** necessarily fail: the default `custom` block resolves to the same base URL, so a stale provider key can go unnoticed. Prefer routing aliases (`smart-route`) over raw upstream model names in pins.
## Default Model
- **`meituan/longcat-2.5-preview:free`** on **`nous`** (`https://inference-api.nousresearch.com/v1`, `api_mode: chat_completions`) — the live default since 2026-10-20. Verified against live `~/.hermes/config.yaml` 2026-10-23.
- **No fallback chain under `model`.** The 6-provider fallback recorded at the 2026-10-02 snapshot is gone; `model` now carries only `base_url`, `default`, `provider`, `api_mode`, `persist_switch_by_default`. An unreachable `nous` has no automatic failover — per-job pins are the only routing control that remains.
- **`smart-route`** on **`custom:omni-101`** (`http://100.78.63.20:20128`, `api_mode: chat_completions`) — the
live default since **2026-10-24 19:06:10 AWST**, re-verified against live `~/.hermes/config.yaml`
**2026-10-26 00:1x**.
- **⚠ A six-provider top-level `fallback_providers` chain is live again** (re-verified 2026-10-26): `nous` /
`meituan/longcat-2.5-preview:free` → `opencode-zen` / `deepseek-v4.1-flash` → `custom:guacano` /
`deepseek-v4.1-flash` → `custom:litellm` / `kilo-reflection-beam-free` → `kilocode` /
`poolside/laguna-m.1:free` → `custom` (`http://litellm:4000/v1`) / `or-inclusionai_ling-2_6-1t`. The
2026-10-21 claim that **no** fallback chain exists is **stale**; the `model` block itself still carries only
`base_url`, `default`, `provider`, `api_mode`, `persist_switch_by_default`.
- ⚠ **The first fallback entry is the dead `nous` credential** (`Invalid refresh token`, since 2026-10-22)
→ [[incidents/2026-10-22-nous-portal-refresh-token-invalid]]
- Anthony has explicitly **rejected** `free-lkgp` as a default; stable defaults are `smart-route` / `deepseek-paid-smart` (paid, not free)
- `resilient-free` was the default after the 2026-08-14 OmniRoute factory reset, but that combo is now in the broken set
- Previous default `auto/best-free` was misconfigured — had no combo definition and routed to a paid `gpt-5.6-sol`
- **20 of 28 scheduled jobs still pin OmniRoute explicitly** (`smart-route` ×11, `free-stack` ×6, `deepseek-paid-smart` ×1, `custom:omni` ×2). The fleet now runs two upstream paths. → [[systems/scheduled-tasks]]
- **18 of 28 scheduled jobs pin OmniRoute explicitly** (`smart-route` ×11, `free-stack` ×6, `deepseek-paid-smart` ×1, `custom:omni` ×2). The remaining 8 follow the global default, which is **also** OmniRoute — so the fleet is back to a **single upstream path**. → [[systems/scheduled-tasks]]
## Auxiliary Role Routing (re-verified live 2026-10-26)
**All eight `auxiliary:` slots** — `approval`, `compression`, `curator`, `mcp`, `profile_describer`,
`skills_hub`, `title_generation`, `vision` — are **`no-think/freeapi/auto` on `custom:omni-101`**, each with
the chain `no-think/freeapi/deepseek-v4-flash` → `no-think/kg/kilo-auto/free` and `free_only: true`.
**Compression timeout 90 s; vision timeout 180 s.**
- Re-placed **2026-10-25 19:13 AWST**, replacing the `nous` / `stepfun/step-3.7-flash:free` and `custom:omni`
aux paths recorded on 2026-10-02 and 2026-10-25 (17:50).
- ⚠ The move was made **because the Nous Portal credential is dead** (`Invalid refresh token`), so it **masks
rather than fixes** that fault → [[incidents/2026-10-22-nous-portal-refresh-token-invalid]]
- Probe results from that session (17:50–19:13, not re-run 2026-10-26): `freeapi/auto` healthy for text and
vision; `kg/kilo-auto/free` returns **empty content on image input**; `stepfun/step-3.7-flash:free` → 401
*no active credentials*; freeapi pinned models in cooldown (429). ⚠ A **vision fallback returning empty
content** is a silent failure mode — check `freeapi/auto` itself, not the fallback order, if image calls
go blank.
## Retired / Unavailable Models (2026-09-25 → 2026-10-01)
Pins that fail at request time, with the exact upstream error. Each is an open cron-repin in [[systems/scheduled-tasks]].