Skip to content

The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.

docs(inference,provider,cost): update readme file references

Steven Enamakel98fb27a2dfbe
diff --git a/crates/openhuman-core/src/inference/README.md b/crates/openhuman-core/src/inference/README.md
index b234d02da4..e747c97c42 100644
--- a/crates/openhuman-core/src/inference/README.md
+++ b/crates/openhuman-core/src/inference/README.md
@@ -203,7 +203,7 @@ picks the provider the same way a provider string does.
| `registry.rs` | Registered provider ownership metadata; provider-neutral retry classification is supplied by TinyInference. |
| `provider/fallback_diagnostics.rs` | Explains background-role fallback when it hits a provider with no credentials. |
| [`provider/`](./provider/) | [`http_error.rs`](./provider/http_error.rs) (host reporter over `tinyinference_llm::failure::http`, `api_error`), `models/` (model catalog listing, local-runtime and OpenRouter entries), `factory/` (chat-model construction and cloud provider resolution). |
-| [`provider/types.rs`](./provider/types.rs) | Host DTOs kept at product and RPC boundaries: `ChatResponse`, `ProviderDelta`, `BilledUsage`, `AGENT_TURN_MAX_OUTPUT_TOKENS`. |
+| `ops/{status,oauth,models,sentiment}.rs` | Inference RPC operations grouped by product surface; sentiment prompts and provider response types come from TinyInference. |
| `host_runtime/` | Product policy, RPC and speech bindings over `tinyinference_local`. See [`host_runtime/README.md`](host_runtime/README.md). |
| `embedding_host/` | Embedding provider selection (managed, Voyage, OpenAI, Cohere, Ollama, custom, noop) and the `embeddings.*` RPC. See [`embedding_host/README.md`](embedding_host/README.md). |
| `tokenjuice/` | Host adapter for the TinyJuice tool-output compression module, the `juice_retrieve` recovery tool, and the `tokenjuice.*` RPC. See [`tokenjuice/README.md`](tokenjuice/README.md). |
diff --git a/crates/openhuman-core/src/inference/provider/README.md b/crates/openhuman-core/src/inference/provider/README.md
index 17917251b4..7ae32656ac 100644
--- a/crates/openhuman-core/src/inference/provider/README.md
+++ b/crates/openhuman-core/src/inference/provider/README.md
@@ -26,8 +26,9 @@ previously `providers/` (pre-consolidation single-crate layout); see
(`inference::registry`); TinyHumans supplies its hosted model vocabulary and request policy.
OpenAI-compatible and Anthropic builders live
in `tinyinference_llm::providers` and are called directly.
-- **DTOs** ([`types.rs`](./types.rs)): `ChatResponse`, `ProviderDelta`,
- `ToolCall`, `UsageInfo`, `AGENT_TURN_MAX_OUTPUT_TOKENS`.
+- **Provider response and usage types**: `ChatResponse`, `ProviderDelta`, and
+ `BilledUsage` come from `tinyinference_llm`; the hosted turn output cap lives
+ with the OpenHuman turn policy.
- **Error classifiers**: reusable classifiers live in
`tinyinference_llm::classification`; this directory retains OpenHuman managed-backend and telemetry policy.
diff --git a/crates/openhuman-core/src/platform/cost/README.md b/crates/openhuman-core/src/platform/cost/README.md
index 9c5c1d1e5c..e6cd6f9906 100644
--- a/crates/openhuman-core/src/platform/cost/README.md
+++ b/crates/openhuman-core/src/platform/cost/README.md
@@ -74,7 +74,7 @@ None. The module has no `bus.rs` and no `DomainEvent` publishers/subscribers.
## Dependencies
- `crate::config`: `CostConfig` / `Config` (legacy display target, dashboard currency/enabled, `workspace_dir`); `config::rpc::load_config_with_timeout` in schemas.
-- `crate::inference::provider::types::UsageInfo` (re-exported as `crate::inference::provider::UsageInfo`): provider usage payload translated into `TokenUsage` in [`global.rs`](./global.rs).
+- `tinyinference_llm::usage::BilledUsage`: provider usage payload translated into `TokenUsage` in [`global.rs`](./global.rs).
- `crate::core::all`: `ControllerFuture`, `RegisteredController` for controller registration.
- `crate::core`: `ControllerSchema`, `FieldSchema`, `TypeSchema`.
- `crate::core::Outcome`: RPC return wrapper.