ippadmin/itpp-infrastructure
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update model-chain.md: canonical Fallback Chain vs Operational Models (Jul 27 2026)

Browse Source
This commit is contained in:
root
2026-07-27 11:41:18 -04:00
parent b6a8a31bfb
commit 4cb95b5df2
1 changed files with 46 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/model-chain.md
+46 -11
View File
@@ -1,18 +1,53 @@
# AI Model Chain — IT Pro Partner # AI Model Architecture — IT Pro Partner
**Updated:** July 24, 2026 **Updated:** July 27, 2026
## Active Fallback Chain Two separate concepts that must not be conflated:
---
## Fallback Chain *(auto-failover — config.yaml)*
Survives admin-ai outage. Uses direct API keys for F1–F4.
| Tier | Model | Provider | Notes | | Tier | Model | Provider | Notes |
|---|---|---|---| |---|---|---|---|
| **Primary** | `claude-sonnet-5` | `admin-ai` | Conductor via LiteLLM ($3.33/day cap) | | **Primary** | `deepseek-v4-flash` | `admin-ai` | Fast, cheap conductor via LiteLLM |
| **Fallback 1 (F1)** | `deepseek-v4-pro` | `deepseek` | Direct DeepSeek API | | **F1** | `deepseek-v4-flash` | `deepseek` (direct) | Same model, direct API |
| **Fallback 2 (F2)** | `gpt-5.6-terra` | `admin-ai` | Demoted from Primary via LiteLLM ($3.33/day cap) | | **F2** | `gemini-3.6-flash` | `google` (direct) | Fast, free-tier eligible |
| **Fallback 3 (F3)** | `grok-4.5` (`grok-2-1212`) | `xai` | Direct xAI API | | **F3** | `grok-4.6` | `xai` (direct) | Verified working (NOT grok-4.5) |
| **Fallback 4 (F4)** | `gemini-3.6-flash` | `google` | Direct Google API | | **F4** | `claude-sonnet-5` | `anthropic` (direct) | Premium survival fallback |
**Only fires when the model above it is unreachable.**
---
## Operational Models *(daily toolbox — admin-ai only)*
No direct API keys. Shared $5/day budget via hermes-agent-v3 key.
| Role | Model | When |
|---|---|---|
| Conductor | `deepseek-v4-flash` | Orchestrating, delegating, quick decisions |
| Workhorse | `deepseek-v4-pro` | Large context, big outputs, infra code |
| Workhorse | `deepseek-reasoner` | Multi-step analysis, debugging, planning |
| Auditor | `gemini-3.6-flash` | Sanity checks, every output (essentially free) |
| Auditor | `claude-sonnet-5` | Architecture, security, auth — sparingly ($15/M output) |
---
## Admin-AI Virtual Key ## Admin-AI Virtual Key
- **Key Hash**: `0237186aaff1ed90295c00d73103103900d4bd07252ec1806af8a4358e45d37a`
- **Allowed Models**: `claude-sonnet-5`, `gpt-5.6-terra`, `deepseek-v4-pro`, `deepseek-v4-flash`, `glm-5.2`, `MiniMax-M3`, `qwen3.7-plus` - **Key Name:** `hermes-agent-v3` (generated Jul 27, 2026)
- **Daily Budget Cap**: $3.33 / day - **Daily Budget Cap:** $5/day shared across all operational models
- **Expiry:** Jul 27, 2027
- **Master Key:** stored in Hudu
## Budget Targets
| Component | Daily est. |
|---|---|
| Conductor (ds-v4-flash) | ~$0.30 |
| Workhorses (ds-v4-pro + reasoner) | ~$1.70 |
| Auditors (gemini + claude sparingly) | ~$0.80 |
| **Total** | **$3–5/day** |