Directories
¶
| Path | Synopsis |
|---|---|
|
Package chatservice persists the conversation thread.
|
Package chatservice persists the conversation thread. |
|
backends.go contains helpers for LLM backend and provider config KV storage.
|
backends.go contains helpers for LLM backend and provider config KV storage. |
|
Package hitlservice evaluates approval policies for tool calls.
|
Package hitlservice evaluates approval policies for tool calls. |
|
internal
|
|
|
setupcheck
Package setupcheck evaluates local runtime readiness (defaults, backends) for the CLI.
|
Package setupcheck evaluates local runtime readiness (defaults, backends) for the CLI. |
|
tools
internal/tools/multi_repo.go
|
internal/tools/multi_repo.go |
|
Package llmrepo provides a unified facade over LLM backends discovered via runtimestate: prompt, chat, streaming, embedding, and tokenization through a single ModelRepo interface.
|
Package llmrepo provides a unified facade over LLM backends discovered via runtimestate: prompt, chat, streaming, embedding, and tokenization through a single ModelRepo interface. |
|
Package localtools provides tools that fire around chain execution: approval gates and host-side helpers.
|
Package localtools provides tools that fire around chain execution: approval gates and host-side helpers. |
|
mcpoauth
Package mcpoauth implements the MCP OAuth 2.1 Authorization Code + PKCE flow for CLI clients.
|
Package mcpoauth implements the MCP OAuth 2.1 Authorization Code + PKCE flow for CLI clients. |
|
Package mcpserverservice stores MCP server configs.
|
Package mcpserverservice stores MCP server configs. |
|
Package mcpworker keeps MCP server connections alive across chain steps.
|
Package mcpworker keeps MCP server connections alive across chain steps. |
|
Package modelrepo defines the provider-facing contracts for LLM backends: the Provider interface (capabilities + client factories), the per-capability client interfaces (LLMPromptExecClient, LLMChatClient, LLMEmbedClient, LLMStreamClient), and the shared request/response types (Message, ChatResult, StreamParcel, Tool, ChatArgument).
|
Package modelrepo defines the provider-facing contracts for LLM backends: the Provider interface (capabilities + client factories), the per-capability client interfaces (LLMPromptExecClient, LLMChatClient, LLMEmbedClient, LLMStreamClient), and the shared request/response types (Message, ChatResult, StreamParcel, Tool, ChatArgument). |
|
anthropic
Package anthropic is a direct (non-Vertex) provider for the Anthropic API (api.anthropic.com), which speaks the Messages API.
|
Package anthropic is a direct (non-Vertex) provider for the Anthropic API (api.anthropic.com), which speaks the Messages API. |
|
bedrock
Package bedrock is a provider for AWS Bedrock via the unified Converse API.
|
Package bedrock is a provider for AWS Bedrock via the unified Converse API. |
|
codec/chatcompletions
Package chatcompletions is a transport-agnostic codec for the OpenAI Chat Completions wire format (`/chat/completions`-style request/response and SSE streaming).
|
Package chatcompletions is a transport-agnostic codec for the OpenAI Chat Completions wire format (`/chat/completions`-style request/response and SSE streaming). |
|
codec/messages
Package messages is a transport-agnostic codec for Anthropic's Messages API wire format (request, content-block response, and named-SSE-event streaming).
|
Package messages is a transport-agnostic codec for Anthropic's Messages API wire format (request, content-block response, and named-SSE-event streaming). |
|
gemini
Package gemini implements the modelrepo.Provider contract against Google's Gemini Generative Language API.
|
Package gemini implements the modelrepo.Provider contract against Google's Gemini Generative Language API. |
|
local
Package local implements the modelrepo.Provider contract for in-process inference using llama.cpp via github.com/ollama/ollama/llama (CGo).
|
Package local implements the modelrepo.Provider contract for in-process inference using llama.cpp via github.com/ollama/ollama/llama (CGo). |
|
mistral
Package mistral is a direct (non-Vertex) provider for the Mistral API (api.mistral.ai), which speaks the OpenAI-compatible chat/completions format.
|
Package mistral is a direct (non-Vertex) provider for the Mistral API (api.mistral.ai), which speaks the OpenAI-compatible chat/completions format. |
|
ollama
Package ollama implements the modelrepo.Provider contract against Ollama HTTP endpoints.
|
Package ollama implements the modelrepo.Provider contract against Ollama HTTP endpoints. |
|
openai
Package openai implements the modelrepo.Provider contract against the OpenAI HTTP API and OpenAI-compatible endpoints.
|
Package openai implements the modelrepo.Provider contract against the OpenAI HTTP API and OpenAI-compatible endpoints. |
|
vertex
Package vertex implements the modelrepo.Provider contract against Google Vertex AI publisher endpoints, using OAuth bearer tokens minted from service-account credentials.
|
Package vertex implements the modelrepo.Provider contract against Google Vertex AI publisher endpoints, using OAuth bearer tokens minted from service-account credentials. |
|
vllm
Package vllm implements the modelrepo.Provider contract against vLLM OpenAI-compatible HTTP endpoints.
|
Package vllm implements the modelrepo.Provider contract against vLLM OpenAI-compatible HTTP endpoints. |
|
Package ollamatokenizer provides Tokenizer implementations used by llmrepo to count and split tokens for a given model.
|
Package ollamatokenizer provides Tokenizer implementations used by llmrepo to count and split tokens for a given model. |
|
Package runtimestate reconciles the declared state of LLM backends (from dbInstance) with their actual observed state.
|
Package runtimestate reconciles the declared state of LLM backends (from dbInstance) with their actual observed state. |
|
Package sessionservice stores CLI chat sessions so conversations persist across terminal restarts.
|
Package sessionservice stores CLI chat sessions so conversations persist across terminal restarts. |
|
Package taskengine orchestrates an agent: it drives LLM turns, tool calls, and routing in a loop, defined as a JSON chain you version in git.
|
Package taskengine orchestrates an agent: it drives LLM turns, tool calls, and routing in a loop, defined as a JSON chain you version in git. |
|
llmretry
Package llmretry wraps a single LLM call with classified retry, exponential backoff, and an optional model fallback.
|
Package llmretry wraps a single LLM call with classified retry, exponential backoff, and an optional model fallback. |
Click to show internal directories.
Click to hide internal directories.