Crate agent_sdk_providers 

LLM provider trait, streaming primitives, and first-party provider implementations.

This crate defines the LlmProvider trait that all LLM backends implement, streaming types for incremental response processing, attachment validation, model capability metadata, and seven first-party provider implementations.

Provider Implementations

Provider	Module	Protocol
Anthropic (Messages API)	impls::anthropic	SSE streaming
OpenAI (Chat Completions)	impls::openai	SSE streaming
OpenAI (Responses API)	impls::openai_responses	SSE streaming
OpenAI Codex / ChatGPT	impls::openai_codex_responses	WebSocket
Google Gemini	impls::gemini	SSE streaming
Google Vertex AI	impls::vertex	SSE streaming
Cloudflare AI Gateway	impls::cloudflare_ai_gateway	Proxy wrapper

Re-exports

pub use fallback::FallbackProvider;

pub use provider::LlmProvider;

pub use provider::ModelInfo;

pub use provider::StructuredOutputSupport;

pub use provider::collect_stream;

pub use record_replay::RecordReplayMode;

pub use record_replay::RecordReplayProvider;

pub use refresh::RefreshingProvider;

pub use refresh::is_unauthorized_error;

pub use router::ModelRouter;

pub use router::ModelTier;

pub use router::TaskComplexity;

pub use streaming::StreamAccumulator;

pub use streaming::StreamBox;

pub use streaming::StreamDelta;

pub use structured::StructuredConfig;

pub use structured::StructuredOutput;

pub use structured::StructuredOutputError;

pub use structured::StructuredStream;

pub use structured::StructuredStreamUpdate;

pub use structured::run_structured;

pub use structured::run_structured_stream;

pub use impls::CloudflareAIGatewayProvider;

pub use impls::GeminiProvider;

pub use impls::OpenAICodexResponsesProvider;

pub use impls::VertexProvider;

pub use impls::AnthropicProvider;

pub use impls::is_oauth_token;

pub use impls::OpenAIAllowedToolsMode;

pub use impls::OpenAIApiSurface;

pub use impls::OpenAIPromptCacheMode;

pub use impls::OpenAIPromptCacheTtl;

pub use impls::OpenAIProvider;

pub use impls::OpenAIReasoningConfig;

pub use impls::OpenAIReasoningContext;

pub use impls::OpenAIReasoningEffort;

pub use impls::OpenAIReasoningMode;

pub use impls::OpenAIReasoningSummary;

pub use impls::OpenAIResponsesProvider;

pub use impls::OpenAITextVerbosity;

pub use impls::OpenAIToolChoice;

pub use model_capabilities::ModelCapabilities;

pub use model_capabilities::PricePoint;

pub use model_capabilities::Pricing;

pub use model_capabilities::SourceStatus;

pub use model_capabilities::get_model_capabilities;

pub use model_capabilities::supported_model_capabilities;

pub use model_features::ModelApiSurface;

pub use model_features::ModelFeatureSet;

pub use model_features::ModelFeatures;

pub use model_features::ModelInputModality;

pub use model_features::ModelPromptCacheFeatures;

pub use model_features::ModelPromptCacheMode;

pub use model_features::ModelPromptCacheTtl;

pub use model_features::ModelReasoningContext;

pub use model_features::ModelReasoningEffort;

pub use model_features::ModelReasoningFeatures;

pub use model_features::ModelReasoningMode;

pub use model_features::ModelReasoningStateReplay;

pub use model_features::ModelReasoningSummary;

pub use model_features::ModelToolChoice;

pub use model_features::ModelToolFeatures;

pub use model_features::get_model_features;

pub use model_features::supported_model_features;

pub use model_catalog::CatalogEntry;

pub use model_catalog::ModelCatalogSource;

pub use model_catalog::ModelRegistry;

pub use model_catalog::ModelsDevSource;

pub use model_catalog::OpenRouterSource;

pub use model_catalog::ResolvedModel;

pub use model_catalog::ResolvedSource;

pub use search::BraveSearchProvider;

pub use search::SearchProvider;

pub use search::SearchResponse;

pub use search::SearchResult;

Modules

attachments

fallback

Provider failover: try an ordered list of providers until one succeeds.

impls

First-party LLM provider implementations.

model_capabilities

model_catalog

Dynamic model capability/pricing discovery from third-party feeds.

model_features

Static feature metadata for OpenAI models.

provider

LLM provider trait and streaming helpers.

record_replay

Deterministic record / replay provider wrapper (feature record-replay).

refresh

Provider wrapper that refreshes credentials on 401 and retries once.

router

search

Search provider trait and implementations.

streaming

Streaming types for LLM responses.

structured

Schema-validated structured output.

Structs

CacheConfig

Caller-facing control over provider-side prompt caching.

ChatRequest

ChatResponse

ContentSource

Source data for image and document content blocks.

Message

ResponseFormat

Requests that the model constrain its final answer to a JSON Schema.

ThinkingConfig

Configuration for extended thinking.

Tool

Usage

Enums

CacheTtl

Time-to-live for a provider-side prompt-cache breakpoint.

ChatOutcome

Content

ContentBlock

Effort

Effort level for adaptive thinking via output_config.

Role

StopReason

ThinkingMode

The mode of extended thinking.

ToolChoice

Controls whether the model must use a tool.

Constants

USER_CANCELLED_TOOL_RESULT

Default tool_result text used to close a tool_use block the user cancelled (or otherwise abandoned) before it produced a real result.

Functions

balance_tool_results

Close every unanswered tool_use loop in messages.

has_unbalanced_tool_use

True when messages contains a tool_use block whose id is not answered by any tool_result block anywhere in the conversation.

parse_retry_after

Parse the value of an HTTP Retry-After header into a Duration.