Infrastructure
Inference, models, fallback chain, and review automation. Each section has its own Save button — presets do not persist until saved.
read-only — power user or admin required to edit
inference-mode
Where reviews run. Local and hybrid use Ollama; cloud uses Groq (free) or OpenRouter — determined by the cloud model name you set.
Ollama compute profile
default-models
Local model (Ollama)
Ollama offline — type slug manually
Cloud primary (quality)
Used for large PRs, security/deep reviews, and sensitive paths. Set GROQ_API_KEY and/or OPENROUTER_API_KEY on API
Cloud fast (volume)
Small/medium routine PRs when cloud fast routing is on (≤ threshold lines).
Recommended fast: openai/gpt-oss-20b · toggle in system-config
cloud-fallback
On Groq HTTP 429, try the next cloud model in the chain. Each entry is a Groq or OpenRouter slug — not Ollama. Use a preset, edit the chain, then Save section below.
Effective order on 429
- 1. Picked model (primary or fast)
- 2. openai/gpt-oss-20b
- 3. qwen/qwen3.6-27b
openai/gpt-oss-20b → qwen/qwen3.6-27b
Fallback chain
Top 5 Groq models for rate limits
qwen/qwen3.8-27b
Balanced primary
- Why
- Recommended default — 8K TPM, strong reasoning; replaces qwen3-32b.
openai/gpt-oss-20b
Fast / volume
- Why
- Routine PRs and fallback step — replaces llama-3.1-8b-instant.
openai/gpt-oss-120b
Security / deep only
- Why
- Best quality — but only 1K RPD; never as global primary.
qwen/qwen3.6-27b
Fallback backup
- Why
- Second step in chain when 3.8 or 20B rate-limits.
| Model | Role | Why |
|---|---|---|
| qwen/qwen3.8-27b | Balanced primary | Recommended default — 8K TPM, strong reasoning; replaces qwen3-32b. |
| openai/gpt-oss-20b | Fast / volume | Routine PRs and fallback step — replaces llama-3.1-8b-instant. |
| openai/gpt-oss-120b | Security / deep only | Best quality — but only 1K RPD; never as global primary. |
| qwen/qwen3.6-27b | Fallback backup | Second step in chain when 3.8 or 20B rate-limits. |
Qwen 32B vs Llama: Qwen = 60 RPM + better reasoning; Llama 8B = 14.4K RPD (best volume); 70B = security/deep only.
review-actions
Per-action model routing and prompts. Cloud tier picks fast vs primary by diff size (see Infrastructure). Tier auto uses inference mode and diff heuristics; force local or cloud to override. Edit prompts
ai-models
Live Ollama, Groq, and OpenRouter connectivity. Default models are set above.
Preferred:
Model:
Set GROQ_API_KEY on API
Model:
Per-action routing in the table below. Repo overrides in Routing rules.
model-catalog
Loading model catalog…
system-config
Chunk and routing settings affect Groq RPM/TPM usage. With many repos, keep cloud_fast_routing on and use 8B for fast tier.