Crate sim_codec_chat 

Canonical chat transcript codec for SIM.

This crate provides codec:chat, a provider-neutral text format for model request, response, event, and card transcripts represented as Expr::Map values.

Re-exports

pub use providers::anthropic::AnthropicCodec;

pub use providers::anthropic::AnthropicCodecLib;

pub use providers::anthropic::AnthropicCodecOptions;

pub use providers::anthropic::AnthropicRequestOptions;

pub use providers::anthropic::anthropic_codec_symbol;

pub use providers::anthropic::decode_anthropic_request;

pub use providers::anthropic::decode_anthropic_response;

pub use providers::anthropic::decode_anthropic_stream;

pub use providers::anthropic::decode_anthropic_stream_events;

pub use providers::anthropic::encode_anthropic_request;

pub use providers::anthropic::encode_anthropic_response;

pub use providers::lemonade::LemonadeCodec;

pub use providers::lemonade::LemonadeCodecLib;

pub use providers::lemonade::LemonadeCodecOptions;

pub use providers::lemonade::LemonadeRequestOptions;

pub use providers::lemonade::decode_lemonade_request;

pub use providers::lemonade::decode_lemonade_response;

pub use providers::lemonade::decode_lemonade_stream;

pub use providers::lemonade::encode_lemonade_request;

pub use providers::lemonade::encode_lemonade_response;

pub use providers::lemonade::lemonade_codec_symbol;

pub use providers::lm_studio::LmStudioCodec;

pub use providers::lm_studio::LmStudioCodecLib;

pub use providers::lm_studio::LmStudioCodecOptions;

pub use providers::lm_studio::LmStudioRequestOptions;

pub use providers::lm_studio::decode_lm_studio_request;

pub use providers::lm_studio::decode_lm_studio_response;

pub use providers::lm_studio::decode_lm_studio_stream;

pub use providers::lm_studio::encode_lm_studio_request;

pub use providers::lm_studio::encode_lm_studio_response;

pub use providers::lm_studio::lm_studio_codec_symbol;

pub use providers::openai::OpenAiCodec;

pub use providers::openai::OpenAiCodecLib;

pub use providers::openai::OpenAiCodecOptions;

pub use providers::openai::OpenAiRequestOptions;

pub use providers::openai::decode_openai_request;

pub use providers::openai::decode_openai_response;

pub use providers::openai::decode_openai_stream;

pub use providers::openai::encode_openai_request;

pub use providers::openai::encode_openai_response;

pub use providers::openai::openai_codec_symbol;

pub use providers::profile::CodecProfile;

pub use providers::profile::RequestWire;

pub use providers::profile::StreamWire;

pub use providers::profile::anthropic_profile;

pub use providers::profile::lemonade_profile;

pub use providers::profile::lm_studio_profile;

pub use providers::profile::ollama_profile;

pub use providers::profile::openai_profile;

Modules

providers

Provider-specific chat wire codecs built on the canonical transcript shape.

Structs

ChatCodec

Provider-neutral transcript codec.

ChatCodecLib

Host-registered lib for codec:chat, built on the shared DomainCodecLib scaffold.

OllamaCodec

Runtime codec for Ollama chat JSON and NDJSON response bodies.

OllamaCodecLib

Host-registered lib for codec:ollama.

OllamaRequestOptions

Options controlling how a chat model-request transcript is projected into an Ollama JSON request body.

Statics

RECIPES

Cookbook recipes for this codec, embedded at build time.

Functions

decode_ollama_response

Decodes a non-streamed Ollama JSON response body into a canonical model-response transcript attributed to runner and model.

decode_ollama_stream

Decodes a newline-delimited Ollama streaming response body into a single canonical model-response transcript attributed to runner and model.

encode_ollama_request

Encodes a chat model-request transcript into an Ollama JSON request body.

is_model_request_expr

Returns true when expr is a chat transcript map carrying a true model-request marker.

model_card_expr

Builds a model-card transcript map describing a model’s identity and capabilities (provider, locality, modalities, and stream/tool/JSON/shape support), with conservative defaults the caller can override.

model_error_expr

Builds a model-response transcript carrying an error: a single text content part holding message, a stop-reason of error, and text/shape-ok fields recording the failure.

model_request_messages_expr

Returns the messages list of a model-request transcript, erroring if expr is not a valid request or its messages field is not a list.

model_response_expr

Builds a model-response transcript map from a runner, model name, content parts, and stop_reason.

number_field

A numbers/f64-domain map entry (name, value) for usage and metric records.

text_part

A chat text content part: the map {type: text, text: <text>}.

usage_record

The canonical token-usage entries built from optional counts, in the fixed order input-tokens, output-tokens, total-tokens. Each present count becomes one number_field; absent counts are skipped. The caller decides how to wrap the result, because providers differ: some emit a usage map even when empty, others omit usage entirely when no counts are present.

validate_chat_transcript

Validates that expr is a well-formed chat transcript and fails closed otherwise.