Expand description
Re-exported provider implementations. LLM provider implementations.
All provider implementations live in vtcode_llm::providers. This module
re-exports them so the historical crate::llm::providers::* import paths
continue to resolve throughout vtcode-core.
Modules§
- anthropic
- Anthropic Claude API provider implementation
- anthropic_
types - base
- Base trait and common implementations for LLM providers
- common
- Shared provider helpers, grouped by responsibility behind stable imports.
- copilot
- error_
handling - Centralized error handling for LLM providers Eliminates duplicate error handling code across providers
- evolink
- gemini
- huggingface
- llamacpp
- llama.cpp provider: a local, OpenAI-compatible server managed by vtcode.
- lmstudio
- LM Studio provider implementation
- local_
server - merge_
gateway - Merge Gateway provider.
- merge_
gateway_ catalog - Merge Gateway authenticated model catalog discovery.
- meta
- Official Meta AI OpenAI-compatible provider.
- mimo
- minimax
- mistral
- moonshot
- nvidia
- NVIDIA NIM OpenAI-compatible provider.
- ollama
- Ollama provider implementation
- opencode_
go - opencode_
zen - openresponses
- OpenResponses provider module.
- openrouter
- poolside
- qwen
- reasoning
- shared
- Shared provider wire helpers with stable facade imports.
- stepfun
- StepFun provider backed by the native Responses API
(
POST {base}/responses). - streaming_
progress - Provider-agnostic streaming timeout progress tracking
- vercel
- zai
Structs§
- Anthropic
Provider - Copilot
Provider - Deep
Seek Provider - Evolink
Provider - Gemini
Provider - Hugging
Face Provider - Llama
CppProvider - LmStudio
Provider - Merge
Catalog Filters - Optional Merge catalog filters preserved across pagination.
- Merge
Catalog Model - Normalized Merge catalog model metadata.
- Merge
Catalog Snapshot - Full normalized snapshot of the Merge catalog.
- Merge
Gateway Catalog Client - Authenticated Merge Gateway
/v1/modelsdiscovery client. - Merge
Gateway Provider - Meta
Provider - MiMo
Provider - Minimax
Provider - Mistral
Provider - Moonshot
Provider - Nvidia
Provider - Ollama
Provider - OpenAI
Provider - Open
Code GoProvider - Open
Code ZenProvider - Open
Responses Provider - Open
Router Provider - Poolside
Provider - Qwen
Provider - Reasoning
Buffer - Reasoning
Segment - Step
FunProvider - Streaming
Progress Builder - Builder for creating streaming progress trackers with fluent API
- Streaming
Progress Tracker - Unified streaming progress tracker for all LLM providers
- TagStream
Sanitizer - A stateful sanitizer that extracts reasoning from a stream of content chunks.
- Vercel
Provider - XAIProvider
- ZAIProvider
Enums§
- Merge
Catalog Availability - Normalized catalog availability for vtcode-core.
- Merge
Catalog Service Tier - Normalized service tiers for the catalog snapshot.
Constants§
- DEFAULT_
VEC_ CAPACITY - Default capacity hints for common collections
- ERROR_
DETECTION_ PATTERNS - Standard error patterns used for error detection across tools
- MAX_
SEARCH_ RESULTS - Context optimization constants following AGENTS.md guidelines
- OVERFLOW_
INDICATOR_ PREFIX
Functions§
Type Aliases§
- Streaming
Progress Callback - Callback for streaming timeout progress updates Progress value is 0.0-1.0 representing elapsed / total_timeout