Codex harness runtime

Runtime contract for Codex harness turns. For setup and routing, see Codex harness. For config fields, see Codex harness reference.

Overview

Codex owns the native model loop, native thread resume, native tool continuation, and native compaction. OpenClaw owns channel routing, session files, visible message delivery, OpenClaw dynamic tools, approvals, media delivery, and a transcript mirror around that boundary.

Prompt routing follows the selected runtime, not just the provider string. A native Codex turn gets Codex app-server developer instructions; an explicit OpenClaw compatibility route keeps the normal OpenClaw system prompt even when it uses Codex-flavored OpenAI auth or transport.

OpenClaw starts and resumes native Codex threads with Codex's built-in personality disabled (personality: "none") so workspace personality files and OpenClaw agent identity stay authoritative. Native Codex keeps Codex-owned base/model instructions and project-doc loading otherwise. Lightweight OpenClaw runs (for example cron) still suppress project-doc loading.

OpenClaw developer instructions cover OpenClaw runtime concerns: source-channel delivery, OpenClaw dynamic tools, ACP delegation, adapter context, and the active agent workspace profile files. Skill catalogs and tool-routed MEMORY.md pointers are projected as turn-scoped collaboration developer instructions. When memory tools are unavailable, active BOOTSTRAP.md content and full MEMORY.md fall back to plain turn input context instead.

Thread bindings and model changes

When an OpenClaw session is attached to an existing Codex thread, the next turn resends the currently selected model, approval policy, sandbox, approvals reviewer, and service tier to app-server. Switching from openai/gpt-5.5 to openai/gpt-5.2 keeps the thread binding but asks Codex to continue with the newly selected model.

Visible replies and heartbeats

Direct/source chat turns through the Codex harness default to automatic final assistant delivery for internal WebChat surfaces, matching the Pi harness contract: the agent replies normally and OpenClaw posts the final text to the source conversation. Set messages.visibleReplies: "message_tool" to keep final assistant text private unless the agent calls message(action="send").

Codex heartbeat turns get heartbeat_respond in the searchable OpenClaw tool catalog by default so the agent can record whether the wake should stay quiet or notify. Heartbeat initiative guidance is sent as a Codex collaboration-mode developer instruction scoped to the heartbeat turn; ordinary chat turns stay in Codex Default mode. When HEARTBEAT.md is non-empty, the heartbeat instructions point Codex at the file instead of inlining its contents.

Hook boundaries

OpenClaw does not use project or global Codex hooks.json files to route plugin behavior. For the native tool and permission bridge, OpenClaw injects per-thread Codex config for PreToolUse, PostToolUse, PermissionRequest, and Stop.

When Codex app-server approvals are enabled (approvalPolicy is not "never"), the default injected native hook config omits PermissionRequest so Codex's app-server reviewer and OpenClaw's approval bridge handle real escalations after review. Add permission_request to nativeHookRelay.events to force the compatibility relay anyway. Other Codex hooks such as SessionStart and UserPromptSubmit remain Codex-level controls; they are not exposed as OpenClaw plugin hooks in the v1 contract.

For OpenClaw dynamic tools, OpenClaw executes the tool after Codex asks for the call, so plugin and middleware behavior runs in the harness adapter. For Codex-native tools, Codex owns the canonical tool record; OpenClaw can mirror selected events but cannot rewrite the native thread unless Codex exposes that through app-server or native hook callbacks.

Codex app-server report-mode PreToolUse events defer plugin approval to the matching app-server approval. If an OpenClaw before_tool_call hook returns requireApproval while the native payload sets openclaw_approval_mode: "report", the native hook relay records the plugin approval requirement and returns no native decision. When Codex later sends the app-server approval request for the same tool use, OpenClaw opens the plugin approval prompt and maps the decision back to Codex. Codex PermissionRequest events are a separate approval path and can still route through OpenClaw approvals when configured for that bridge.

Codex app-server item notifications also provide async after_tool_call observations for native tool completions not already covered by the native PostToolUse relay. These are telemetry/compatibility only; they cannot block, delay, or mutate the native tool call.

Compaction and LLM lifecycle projections come from Codex app-server notifications and OpenClaw adapter state, not native Codex hook commands. before_compaction, after_compaction, llm_input, and llm_output are adapter-level observations, not byte-for-byte captures of Codex's internal request or compaction payloads.

Codex native hook/started and hook/completed app-server notifications are projected as codex_app_server.hook agent events for trajectory and debugging. They do not invoke OpenClaw plugin hooks.

V1 support contract

Supported in Codex runtime v1:

Not supported in Codex runtime v1:

Native permissions and MCP elicitations

For PermissionRequest, OpenClaw only returns explicit allow or deny decisions when policy decides. A no-decision result is not an allow: Codex treats it as no hook decision and falls through to its own guardian or user approval path.

Codex app-server approval modes omit this native hook by default. This applies unless permission_request is explicitly included in nativeHookRelay.events or a compatibility runtime installs it.

When an operator chooses allow-always for a Codex native permission request, OpenClaw remembers that exact provider/session/tool input/cwd fingerprint for a bounded session window. The remembered decision is intentionally exact-match only: a changed command, arguments, tool payload, or cwd creates a fresh approval.

Codex MCP tool approval elicitations route through OpenClaw's plugin approval flow when Codex marks _meta.codex_approval_kind as "mcp_tool_call". Codex request_user_input prompts are sent back to the originating chat, and the next queued follow-up message answers that native server request instead of being steered as extra context. Other MCP elicitation requests fail closed.

For the general plugin approval flow that carries these prompts, see Plugin permission requests.

Queue steering

Active-run queue steering maps onto Codex app-server turn/steer. With the default messages.queue.mode: "steer", OpenClaw batches steer-mode chat messages for the configured quiet window and sends them as one turn/steer request in arrival order.

Codex review and manual compaction turns can reject same-turn steering. In that case, OpenClaw waits for the active run to finish before starting the prompt. Use /queue followup or /queue collect when messages should queue by default instead of steering. See Steering queue.

Codex feedback upload

When /diagnostics [note] is approved for a session on the native Codex harness, OpenClaw also calls Codex app-server feedback/upload for relevant Codex threads, including logs for each listed thread and spawned Codex subthreads when available.

The upload goes through Codex's normal feedback path to OpenAI servers. If Codex feedback is disabled in that app-server, the command returns the app-server error. The completed diagnostics reply lists the channels, OpenClaw session ids, Codex thread ids, and local codex resume <thread-id> commands for the threads that were sent.

If you deny or ignore the approval, OpenClaw does not print those Codex ids and does not send Codex feedback. The upload does not replace the local Gateway diagnostics export. See Diagnostics export for the approval, privacy, local bundle, and group-chat behavior.

Use /codex diagnostics [note] only when you want the Codex feedback upload for the currently attached thread without the full Gateway diagnostics bundle.

Compaction and transcript mirror

When the selected model uses the Codex harness, native thread compaction belongs to Codex app-server. OpenClaw does not run preflight compaction for Codex turns, replace Codex compaction with context-engine compaction, or fall back to OpenClaw or public OpenAI summarization when native compaction cannot be started. OpenClaw keeps a transcript mirror for channel history, search, /new, /reset, and future model or harness switching.

Explicit compaction requests, such as /compact or a plugin-requested manual compact operation, start native Codex compaction with thread/compact/start. OpenClaw keeps the request and shared-client lease open until Codex emits the matching contextCompaction completion item and then reports the compaction turn as completed. If that terminal turn exceeds the configured compaction timeout, OpenClaw requests a native turn interrupt. The lease and per-thread compaction fence remain held until Codex reports terminal state or confirms the interrupt RPC. If Codex does not confirm within the interrupt grace period, OpenClaw retires the connection before releasing the fence. Remote connections also detach the matching thread binding so later work cannot overlap an unconfirmed remote turn. Other turns on a retired connection fail and can retry on a fresh client. Client closure, request cancellation, or a failed compaction turn returns a failed operation. Automatic context-pressure compaction is Codex's job; OpenClaw only starts native compaction for manually requested triggers.

When a context engine requests Codex thread-bootstrap projection, OpenClaw projects tool-call names and ids, input shapes, and redacted tool-result content into the fresh Codex thread. It does not copy raw tool-call argument values into that projection.

The mirror includes the user prompt, final assistant text, and lightweight Codex reasoning or plan records when the app-server emits them. OpenClaw records the native compaction start and terminal status, but it does not expose a human-readable compaction summary or an auditable list of which entries Codex kept after compaction.

Because Codex owns the canonical native thread, tool_result_persist does not rewrite Codex-native tool result records. It only applies when OpenClaw writes an OpenClaw-owned session transcript tool result.

Media and delivery

OpenClaw continues to own media delivery and media provider selection. Image, video, music, PDF, TTS, and media understanding use matching provider/model settings such as agents.defaults.imageGenerationModel, videoGenerationModel, pdfModel, and messages.tts.

Text, images, video, music, TTS, approvals, and messaging-tool output continue through the normal OpenClaw delivery path; media generation does not require the legacy runtime. When Codex emits a native image-generation item with a savedPath, OpenClaw forwards that exact file through the normal reply-media path even if the Codex turn has no assistant text.

Related

• Codex harness
• Codex harness reference
• Native Codex plugins
• Plugin hooks
• Agent harness plugins
• Diagnostics export
• Trajectory export