LLM Providers

Nine provider slots. Switching is a settings change; the graph is provider-agnostic.

Supported providers

Provider	LangChain wrapper	Default model	Notes
Anthropic	`ChatAnthropic`	`claude-sonnet-5`	Native SDK
OpenAI	`ChatOpenAI`	`gpt-4.1`	Native SDK; `openai.reasoningEffort` for o-series/reasoning models
Google Gemini	`ChatGoogleGenerativeAI`	`gemini-2.5-flash`	Native SDK
Groq	`ChatGroq`	`openai/gpt-oss-120b`	Native SDK
xAI Grok	`ChatOpenAI`	model per `grok.model`	OpenAI-compatible, base URL x.ai
DeepSeek	`ChatOpenAI`	`deepseek-v4-flash`	OpenAI-compatible
Qwen	`ChatOpenAI`	`qwen-max`	OpenAI-compatible (DashScope)
GLM (Zhipu AI)	`ChatOpenAI`	`glm-4.6`	OpenAI-compatible
Local	`ChatOpenAI`	`qwen3-coder`	OpenAI-compatible localhost — Ollama, LM Studio, Docker, OpenRouter

Anything that speaks OpenAI’s API works via the Local slot — set local.baseUrl to point at it.

Model defaults are generated from a single source of truth (scripts/model-config.json → package.json via npm run sync:models), so the values above track the shipped defaults.

Switching models

Each provider’s {provider}.model setting picks the model. You don’t have to edit settings by hand: the in-chat model picker lists a curated catalog per provider, badged with tool-calling and thinking/reasoning support and a recommended pick, and writes your choice to that provider’s .model setting. Switching model is a one-click change; switching provider is generativeAi.option.

On xAI Grok: it’s a selectable provider option (generativeAi.option: "XGrok") and key resolution routes it to https://api.x.ai/, but under the hood the canonical PROVIDER_REGISTRY aliases Grok to the Anthropic webview provider rather than giving it a first-class agent-mode entry. Treat the other eight slots as the fully independent ones.

Selection

sequenceDiagram participant Settings participant KM as getAPIKeyAndModel() participant SS as SecretStorage participant Proxy as CredentialProxy participant BC as buildChatModel() Settings->>KM: generativeAi.option = "Anthropic" KM->>SS: Check OS keychain alt Found SS-->>KM: apiKey else Miss KM->>Settings: settings.json fallback end KM->>KM: Reject placeholder keys<br/>("apiKey", "YOUR_API_KEY_HERE") opt Proxy enabled KM->>Proxy: Route via localhost proxy end KM-->>BC: {apiKey, model, baseUrl?, proxyToken?} BC-->>Settings: LangChain ChatModel

Resolution order: SecretStorage (keychain) → settings.json → credential-proxy indirection if enabled. Placeholder strings ("apiKey", "YOUR_API_KEY_HERE", "not-needed") are rejected before the SDK sees them.

Two factory paths

Mode	Factory	Output
Agent	`buildChatModel()` → LangChain wrapper	Fed into the deepagents pipeline via `AgentFactory`
Inline completion	`CompletionProviderFactory.getProvider()`	Returns `ICodeCompleter` — `GroqLLM`, `QwenLLM`, `GeminiLLM`, `LocalLLM`

Automatic failover

ProviderFailoverService monitors provider health, classifies errors, and switches to a backup on failure.

Error classes:

Reason	Triggers	Cooldown
`auth`	HTTP 401, 403	10 min
`rate_limit`	HTTP 429	1 min
`billing`	Billing / quota errors	30 min
`timeout`	Request timeout	30 s
`overloaded`	HTTP 503, 529	2 min
`model_not_found`	HTTP 404	1 hr
`format`	Schema / format errors	—
`unknown`	Everything else	—

Health state machine: healthy → degraded → down → healthy. A probe recovery attempt fires 30 s before cooldown expires, restoring the provider without waiting out the full timer.

Failover resolution: resolveProvider(primary) checks the primary → walks candidate list respecting cooldowns → returns first with valid creds. The response carries an isFallback flag so callers know a switch happened. Emits provider_switch, health_update, probe_recovery events.

Settings:

Setting	Default	Purpose
`codebuddy.failover.enabled`	`true`	Enable automatic failover
`codebuddy.failover.providers`	`[]`	Ordered fallback list; empty = auto-detect from configured keys

Cost tracking

CostTrackingService records per-provider token usage against per-model pricing tables (30+ models, separate input / output / cache-read / cache-creation rates). See Cost Tracking.

Provider settings

Full setting list at Settings Reference. Common shape:

Setting	Purpose
`generativeAi.option`	Active provider — `Anthropic`, `OpenAI`, `Gemini`, `Groq`, `XGrok`, `Deepseek`, `Qwen`, `GLM`, `Local`
`{provider}.apiKey`	API key (typically `anthropic.apiKey`, `openai.apiKey`, `google.gemini.apiKeys`, etc.)
`{provider}.model`	Model name for that provider
`local.baseUrl`	Endpoint for the Local slot