Connect Continue to NekoCloud
This guide adapts the tool’s official third-party provider documentation for NekoCloud. It does not imply official certification of this service. NekoCloud has not individually tested the toolchains described here. These are configuration references and acceptance steps for you to perform; no paid requests were made while preparing this guide. Install the tool, create a NekoCloud API key, and confirm the model is available in the model plaza and your key’s group. Replace REPLACE_WITH_MODEL_ID with the exact model ID, not its display name.
Open the active Local Config
Open the Continue Chat sidebar with Ctrl/Cmd + L in VS Code or Ctrl/Cmd + J in JetBrains. Click the Agent / configuration selector above the chat input, locate Local Config, and click its gear icon to open the active config.yaml. Common paths are ~/.continue/config.yaml on Linux/macOS and %USERPROFILE%\.continue\config.yaml on Windows. Use the file opened by the UI rather than creating a legacy config.json.
Read and back up the existing YAML first. Append only the model entry below to the existing models: list. Keep the existing top-level name, version, and schema, along with other models, rules, context, and MCP configuration. Do not overwrite the whole file or introduce a second models: key. The following is a minimal complete structure for a new configuration; extract only its list item for an existing file:
name: NekoCloud Local
version: 1.0.0
schema: v1
models:
- name: NekoCloud Chat
provider: openai
model: REPLACE_WITH_MODEL_ID
apiBase: https://api.nekocloud.vip/v1
apiKey: REPLACE_WITH_API_KEY
roles:
- chat
useResponsesApi: falseThe field is apiBase, not baseURL or base_url. provider: openai supports OpenAI-compatible services; it does not mean requests must go to OpenAI’s official host. Replace apiKey with your own key. This form stores it in plaintext, so do not commit the configuration. If you prefer secrets, follow Continue’s official secret-management mechanism separately. Do not use the literal string NEKOCLOUD_API_KEY as a key or assume YAML automatically reads shell variables.
According to the official documentation, saving the file automatically refreshes Continue’s configuration. Select Local Config and the NekoCloud Chat model again. If it has not updated, save your work and run VS Code’s Developer: Reload Window. In JetBrains, reopen the plugin session or restart the IDE, then start a new conversation. For YAML errors, inspect indentation and duplicate keys rather than deleting the entire file.
Chat and Agent capabilities, and protocol differences
The example explicitly sets useResponsesApi: false to use Chat Completions, not the legacy /completions endpoint. The official documentation notes that some model names trigger Responses by default. Adjust useResponsesApi according to the documentation only after confirming the selected route supports /v1/responses; do not infer protocol compatibility from a model name. Do not append a final request path to the base URL. Anthropic Messages requires a separate anthropic provider adapter. NekoCloud’s Anthropic root is https://api.nekocloud.vip, not a direct replacement value for this OpenAI YAML.
roles: [chat] configures the client’s usage role; it does not promise autocomplete, embedding, or reranking support. Agent mode requires tool support. First confirm that the model and route support tools, then add capabilities: [tool_use] according to the official reference only if automatic detection fails to recognize it. This declaration overrides client detection; it cannot add tool support to a model that lacks it. After chat acceptance passes, select Agent mode for the read-only test below and retain per-call approval. Do not enable images or all capabilities simply to remove a warning.
Acceptance: reply, usage record, and a read-only tool round trip
These steps send model requests and may incur charges. Run them only with your consent. Disable automatic approval, automatic command execution, and unnecessary background requests first. Use a small workspace without sensitive information.
- Start a new conversation, confirm the active provider and model, and send “Reply only OK; do not call tools.” After a normal reply, check the NekoCloud dashboard’s usage records for matching request time, model, and usage/token information. Client cost estimates are not the NekoCloud bill.
- Send “Use only a file-reading tool to read the first few lines of the existing README.md. Return its first line and a one-sentence summary. Do not edit files, run commands, or access the network.” If there is no README.md, choose another existing non-sensitive text file and change the prompt’s path; do not ask the agent to create a file.
- Manually approve that read-only call. Confirm the task trace contains an actual tool name, arguments, and file-reading result, followed by a model answer based on that result. A reply merely claiming to have read the file is not a pass. Check usage records again and verify that the workspace was not modified.
A text reply proves only the chat connection. Matching usage records confirm the request reached the intended account. The tool invocation, tool result, and subsequent model answer must all complete to pass this read-only round trip. If a step fails, stop retrying and retain the request time, model, error code, and redacted request ID rather than repeatedly starting long tasks.
Safety and troubleshooting
Back up existing configuration and merge only the new provider or model entries. Do not replace the whole file or remove other models, rules, tools, or login information. Enter the key itself without a Bearer prefix; REPLACE_WITH_API_KEY is only a placeholder. Never commit real keys, authorization headers, secret-bearing configurations, or sensitive source code to Git, include them in screenshots, or send them to support. Protect local configuration and backup copies too.
For 401 errors, check the active configuration, key, and authentication source. For missing models, check the exact ID and key-group permissions. For 404 errors, check the URL and protocol; avoid duplicate /v1 segments or using a full request path as the base URL. For 429 errors, reduce request frequency according to the response and usage records rather than retrying indefinitely. Do not disable TLS verification, expand execution permissions, or change system network settings to troubleshoot. With Remote SSH, WSL, or containers, ensure configuration and environment variables belong to the host actually running the extension, not just your local terminal.