Skip to content

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

docs(inference): update provider documentation regarding codex routing

Steven Enamakel7f95bfd07fbd
diff --git a/crates/openhuman-core/src/inference/README.md b/crates/openhuman-core/src/inference/README.md
index 2a7b4e9636..0f0dd39d3b 100644
--- a/crates/openhuman-core/src/inference/README.md
+++ b/crates/openhuman-core/src/inference/README.md
@@ -87,9 +87,9 @@ publishes `DomainEvent::SessionExpired` locally when that check fails. Its typed
failure callback publishes the same event for managed endpoint authentication failures, using the
owner's explicit provenance rather than inferring ownership from the provider label.
-[`provider/openai_codex.rs`](./provider/openai_codex.rs) is related but is not a model. When ChatGPT/Codex OAuth tokens exist
-for the `openai` slug, `resolve_openai_codex_routing` re-targets that slug at the Codex backend
-with the account and originator headers. The OAuth flow itself (start, complete, import from the
+When ChatGPT/Codex OAuth tokens exist for the `openai` slug, the host selects the OAuth
+credential and TinyInference's `resolve_codex_routing` supplies the Codex backend route. OpenHuman
+adds the account and originator headers. The OAuth flow itself (start, complete, import from the
Codex CLI, status, disconnect) and its token store live in [`security/credentials/openai_oauth/`](../security/credentials/openai_oauth/);
this domain only exposes the RPC wrappers in [`ops.rs`](./ops.rs).
@@ -202,7 +202,6 @@ picks the provider the same way a provider string does.
| `provider/` | Model construction and provider policy. See [`provider/README.md`](provider/README.md). |
| `provider/factory.rs`, [`provider/factory/`](./provider/factory/) | Provider-string grammar and model construction: `routing`, `primary_cloud`, `access_gates`, `credentials`, `managed_backend`, `local_runtime`, `cloud_slug`, `cloud_spec`, `subprocess_providers`, `discovery`, `chat_model`, `turn_model`. |
| `provider_model.rs`, `registry.rs` | Provider-neutral model hooks and caller adapters; hosted aliases, model defaults, pricing, and request metadata are registered by `openhuman-tinyhumans`. |
-| `provider/openai_codex.rs` | Codex routing metadata for the `openai` slug when Codex OAuth is connected. |
| `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). |
diff --git a/crates/openhuman-core/src/inference/provider/README.md b/crates/openhuman-core/src/inference/provider/README.md
index 7ae32656ac..9495d5bfc1 100644
--- a/crates/openhuman-core/src/inference/provider/README.md
+++ b/crates/openhuman-core/src/inference/provider/README.md
@@ -39,7 +39,7 @@ previously `providers/` (pre-consolidation single-crate layout); see
| Managed OpenHuman backend | registered chat model (`openhuman-tinyhumans`, `src/inference/`) | `openhuman` / `cloud` (session JWT + billing metadata) |
| OpenAI-compatible (BYOK cloud slugs, local runtimes) | `tinyinference_llm::providers::openai` | `<slug>:<model>`, `ollama:<model>`, `lmstudio:<model>`, `mlx:<model>`, `omlx:<model>`, `local-openai:<model>` |
| Anthropic Messages API (prompt caching) | `tinyinference_llm::providers::anthropic` | `<slug>:<model>` whose endpoint is the first-party Messages API and native tool calling is on |
-| Codex OAuth / Responses API | [`openai_codex.rs`](./openai_codex.rs) host OAuth selection plus `tinyinference_llm::providers::openai::codex` metadata | the `openai` cloud slug once Codex OAuth tokens exist |
+| Codex OAuth / Responses API | Host OAuth selection plus `tinyinference_llm::providers::openai::codex` routing metadata | the `openai` cloud slug once Codex OAuth tokens exist |
| Claude Agent SDK subprocess | `tinyagents_harness::providers::claude_agent_sdk` | `claude_agent_sdk` / `claude_agent_sdk:<model>` |
| Claude Code CLI subprocess | `tinyagents_harness::providers::claude_code` (see the [Claude Code provider guide](../../../../../docs/gitbooks/en/developing/providers/claude-code.md)) | `claude-code:<model>` |
diff --git a/crates/openhuman-core/src/inference/provider/factory.rs b/crates/openhuman-core/src/inference/provider/factory.rs
index 3341cf2c88..89ddf2bd94 100644
--- a/crates/openhuman-core/src/inference/provider/factory.rs
+++ b/crates/openhuman-core/src/inference/provider/factory.rs
@@ -100,7 +100,6 @@ use tinyinference_llm::providers::openai::codex::{
openai_codex_client_version, openai_codex_user_agent, OPENAI_CODEX_ACCOUNT_HEADER,
OPENAI_CODEX_ORIGINATOR, OPENAI_CODEX_ORIGINATOR_HEADER,
};
-use tinyinference_llm::providers::openai::AuthStyle as CompatAuthStyle;
/// Redact a configured endpoint to its origin for host diagnostics.
///