From 86b87df7e3df110bbbccd3a5e392e3a9119c5950 Mon Sep 17 00:00:00 2001 From: Peter Steinberger Date: Fri, 22 May 2026 19:22:40 +0100 Subject: [PATCH] docs: refine maintainer docs sweep Co-authored-by: Niels Kaspers Co-authored-by: Zhaocun Co-authored-by: Henson --- CHANGELOG.md | 1 + docs/.i18n/glossary.zh-CN.json | 2 +- docs/.i18n/glossary.zh-TW.json | 22 +++++++++++----------- docs/nodes/media-understanding.md | 26 ++++++++++++++++++++++++++ docs/plugins/codex-harness.md | 4 ++++ docs/reference/code-mode.md | 22 +++++++++++++++------- 6 files changed, 58 insertions(+), 19 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9d7038119e97..c5ceb8024add 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,7 @@ Docs: https://docs.openclaw.ai ### Changes +- Docs: clarify media provider credentials, Codex/OpenClaw code-mode boundaries, Slack and Telegram ack reactions, Feishu dynamic agents, secrets plaintext boundaries, memory guidance, and Chinese glossary terms. Thanks @nielskaspers, @cosmopolitan033, @drclaw-iq, @alexgduarte, @zccyman, @chengoak, and @cassthebandit. - Packaging: exclude documentation images and assets from the npm tarball, reducing published package size without affecting runtime docs search or CLI behavior. Thanks @SebTardif. - Agents/subagents: limit default sub-agent bootstrap context to `AGENTS.md` and `TOOLS.md`, keeping persona, identity, user, memory, heartbeat, and setup files out of delegated workers by default. (#85283) Thanks @100yenadmin. - Maintainer skills: exclude plugin SDK/API boundary work from `openclaw-landable-bug-sweep` so bugbash sweeps stay focused on small paper-cut fixes. diff --git a/docs/.i18n/glossary.zh-CN.json b/docs/.i18n/glossary.zh-CN.json index 8d035d521429..99fbffb7a504 100644 --- a/docs/.i18n/glossary.zh-CN.json +++ b/docs/.i18n/glossary.zh-CN.json @@ -101,7 +101,7 @@ }, { "source": "Status", - "target": "Status" + "target": "状态" }, { "source": "Gateway", diff --git a/docs/.i18n/glossary.zh-TW.json b/docs/.i18n/glossary.zh-TW.json index eda82bba3b5c..4515fe7e92fd 100644 --- a/docs/.i18n/glossary.zh-TW.json +++ b/docs/.i18n/glossary.zh-TW.json @@ -5,7 +5,7 @@ }, { "source": "Active Memory", - "target": "Active Memory" + "target": "主動記憶" }, { "source": "ClawHub", @@ -13,27 +13,27 @@ }, { "source": "CLI", - "target": "CLI" + "target": "命令列介面" }, { "source": "Compaction", - "target": "Compaction" + "target": "壓縮" }, { "source": "Cron", - "target": "Cron" + "target": "排程" }, { "source": "Dreaming", - "target": "Dreaming" + "target": "夢境整理" }, { "source": "Gateway", - "target": "Gateway" + "target": "閘道" }, { "source": "Heartbeat", - "target": "Heartbeat" + "target": "心跳偵測" }, { "source": "Mintlify", @@ -41,7 +41,7 @@ }, { "source": "Node", - "target": "Node" + "target": "節點" }, { "source": "OpenClaw", @@ -53,7 +53,7 @@ }, { "source": "Plugin", - "target": "Plugin" + "target": "外掛" }, { "source": "Skills", @@ -69,10 +69,10 @@ }, { "source": "TUI", - "target": "TUI" + "target": "終端介面" }, { "source": "Webhook", - "target": "Webhook" + "target": "網路鉤子" } ] diff --git a/docs/nodes/media-understanding.md b/docs/nodes/media-understanding.md index 40714dae2f48..feef5af3e26d 100644 --- a/docs/nodes/media-understanding.md +++ b/docs/nodes/media-understanding.md @@ -137,6 +137,32 @@ Each `models[]` entry can be **provider** or **CLI**: +### Provider credentials (`apiKey`) + +Provider media understanding uses the same provider auth resolution as normal +model calls: auth profiles, environment variables, then +`models.providers..apiKey`. + +`tools.media.*.models[]` entries do not accept an inline `apiKey` field. The +`provider` value in a media model entry, such as `openai` or `moonshot`, must +have credentials available through one of the standard provider auth sources. + +Minimal example: + +```json5 +{ + models: { + providers: { + openai: { apiKey: "" }, + moonshot: { apiKey: "" }, + }, + }, +} +``` + +For the full provider auth reference, including profiles, environment +variables, and custom base URLs, see [Tools and custom providers](/gateway/config-tools). + ## Defaults and limits Recommended defaults: diff --git a/docs/plugins/codex-harness.md b/docs/plugins/codex-harness.md index d992d21abf60..765e77222789 100644 --- a/docs/plugins/codex-harness.md +++ b/docs/plugins/codex-harness.md @@ -28,6 +28,10 @@ OpenClaw dynamic tools continue through the app-server `item/tool/call` bridge. Active OpenClaw sandboxing and restricted tool policies disable native code mode entirely unless you opt into the experimental sandbox exec-server path. +This Codex-native feature is separate from +[OpenClaw code mode](/reference/code-mode), which is an opt-in QuickJS-WASI +runtime for generic OpenClaw runs with a different `exec` input shape. + For the broader model/provider/runtime split, start with [Agent runtimes](/concepts/agent-runtimes). The short version is: `openai/gpt-5.5` is the model ref, `codex` is the runtime, and Telegram, diff --git a/docs/reference/code-mode.md b/docs/reference/code-mode.md index cda2b270aebd..b150e608cd01 100644 --- a/docs/reference/code-mode.md +++ b/docs/reference/code-mode.md @@ -13,13 +13,21 @@ default. When you enable it, OpenClaw changes what the model sees for one run: instead of exposing every enabled tool schema directly, the model sees only `exec` and `wait`. -This page documents OpenClaw code mode. It is not Codex Code mode. Codex Code -mode is part of the Codex coding harness and has its own project workspace, -runtime, tools, and execution semantics. Codex Code mode and Codex-native -dynamic tool search are stable Codex harness surfaces. OpenClaw code mode is an -OpenClaw-owned experimental tool-surface adapter for generic OpenClaw runs. It -uses `quickjs-wasi`, a hidden OpenClaw tool catalog, and the normal OpenClaw -tool executor. +This page documents OpenClaw code mode. It is not Codex Code mode. The two +features share a name, but they are implemented by different runtimes and expose +different `exec` contracts: + +- Codex Code Mode is enabled for Codex app-server threads unless restricted + tool policy disables native code mode. It runs in the Codex coding harness, + where the model writes shell commands through an `exec.command` contract. +- OpenClaw code mode is disabled unless `tools.codeMode.enabled: true` is + configured. It runs in the OpenClaw generic agent runtime, where the model + writes JavaScript or TypeScript programs through an `exec.code` contract. + +Codex Code Mode and Codex-native dynamic tool search are stable Codex harness +surfaces. OpenClaw code mode is an OpenClaw-owned experimental tool-surface +adapter for generic OpenClaw runs. It uses `quickjs-wasi`, a hidden OpenClaw +tool catalog, and the normal OpenClaw tool executor. ## What is this?