llm/

September 6, 2026 · View on GitHub

English | 中文

Summary

The llm group provides the harness's model-call capability: one provider-neutral service through which any composition streams requests to a model provider, plus adapters, provider-specific request metadata, retry execution, and measurement. The core llm package defines the message, content-block, and stream-chunk vocabulary every plugin and the session log use; provider adapters translate a provider's wire format into that vocabulary; DeepSeek request-extension plugins contribute lifecycle-owned metadata outside model input; llm-retry re-runs failed requests at durable agent-step boundaries; and token-meter measures request and context pressure from the durable log. This page maps the group; each package README owns its per-package contract.

Table of Contents


Packages

PackageRolectx key
llm/Streams one model call through a registered provider adapter and shares the harness message, block, and chunk vocabularyctx.llm
llm-deepseek/Serves the deepseek-official route with direct DeepSeek chat-completions, thinking, and image inputregisters on ctx.llm
llm-pi-ai/Serves configured provider routes through pi-ai catalogs and wire protocols, including hand-declared gatewaysregisters on ctx.llm
deepseek-llm-api-extensions/Registers lifecycle-owned top-level fields on official DeepSeek requestsctx.deepseekLlmApiExtensions
plugin-package-inventory-deepseek/Contributes the active Loader package inventory to official DeepSeek requestscontributes dsh_plugin_packages
llm-retry/Retries failed model requests under each provider's policy at durable agent-step boundarieslistens to agent/request-error
token-meter/Measures request and context pressure from the durable session log with a fixed heuristicctx.tokenMeter

Dev Note

None.