Continue

Continue. Docs checked 2026-10-12.

IDE extension with config.yaml providers, including openai (any /v1) and a native llama.cpp provider.

What it’s for

Chat, edit, apply, and autocomplete roles in the editor.

Local endpoint

llama-server base: http://127.0.0.1:8080/v1
Strata base: http://127.0.0.1:8083/v1
Model name: models[].model
API key: apiKey in config.yaml (placeholder is fine locally)

Tool calling

Set capabilities: [tool_use] on the openai provider when the server actually implements tools. Otherwise not documented as working.

Long context

Server -c. Community reports of leftover context with llama-server — reset / --context-shift is a server concern.

ROCm / Radeon gotchas

Continue does not build HIP. Point apiBase at your Vulkan or HIP llama-server.

Hybrid local + cloud

Yes — mix cloud and local models by role in one config.yaml.

This is the same question as the calculator’sfully localversushybridtoggle. This page does not quote cloud prices.

Official links

Sources

Copy-paste

More on the connect page. Prove http://127.0.0.1:8080/v1/models first.

Continue → llama-server :8080config.yaml

# openai provider — apiBase includes /v1
name: Local llama-server
provider: openai
model: qwen
apiBase: http://127.0.0.1:8080/v1
apiKey: local-not-a-secret
# capabilities: [tool_use]   # only if the server actually implements tools

# Native llama.cpp provider (docs: apiBase *without* /v1):
# provider: llama.cpp
# apiBase: http://127.0.0.1:8080

Exact llama-server flags for our daily driver stay TODO in stacks.yaml. This is the port only.

Continue → Strata :8083config.yaml

# openai provider — apiBase includes /v1
name: Local Strata
provider: openai
model: qwen
apiBase: http://127.0.0.1:8083/v1
apiKey: local-not-a-secret
# capabilities: [tool_use]   # only if the server actually implements tools

# Native llama.cpp provider (docs: apiBase *without* /v1):
# provider: llama.cpp
# apiBase: http://127.0.0.1:8083

Exact Strata flags for our rig stay TODO in stacks.yaml. This is the port only.