@@ -363,12 +363,13 @@ Time format in system prompt. Default: `auto` (OS preference).
363363- `verboseDefault`: default verbose level for agents. Values: `"off"`, `"on"`, `"full"`. Default: `"off"`.
364364- `elevatedDefault`: default elevated-output level for agents. Values: `"off"`, `"on"`, `"ask"`, `"full"`. Default: `"on"`.
365365- `model.primary`: format `provider/model` (e.g. `openai/gpt-5.4` for API-key access or `openai-codex/gpt-5.5` for Codex OAuth). If you omit the provider, OpenClaw tries an alias first, then a unique configured-provider match for that exact model id, and only then falls back to the configured default provider (deprecated compatibility behavior, so prefer explicit `provider/model`). If that provider no longer exposes the configured default model, OpenClaw falls back to the first configured provider/model instead of surfacing a stale removed-provider default.
366-- `models`: the configured model catalog and allowlist for `/model`. Each entry can include `alias` (shortcut) and `params` (provider-specific, for example `temperature`, `maxTokens`, `cacheRetention`, `context1m`, `responsesServerCompaction`, `responsesCompactThreshold`).
366+- `models`: the configured model catalog and allowlist for `/model`. Each entry can include `alias` (shortcut) and `params` (provider-specific, for example `temperature`, `maxTokens`, `cacheRetention`, `context1m`, `responsesServerCompaction`, `responsesCompactThreshold`, `extra_body`/`extraBody`).
367367- Safe edits: use `openclaw config set agents.defaults.models '<json>' --strict-json --merge` to add entries. `config set` refuses replacements that would remove existing allowlist entries unless you pass `--replace`.
368368- Provider-scoped configure/onboarding flows merge selected provider models into this map and preserve unrelated providers already configured.
369369- For direct OpenAI Responses models, server-side compaction is enabled automatically. Use `params.responsesServerCompaction: false` to stop injecting `context_management`, or `params.responsesCompactThreshold` to override the threshold. See [OpenAI server-side compaction](/providers/openai#server-side-compaction-responses-api).
370370- `params`: global default provider parameters applied to all models. Set at `agents.defaults.params` (e.g. `{ cacheRetention: "long" }`).
371371- `params` merge precedence (config): `agents.defaults.params` (global base) is overridden by `agents.defaults.models["provider/model"].params` (per-model), then `agents.list[].params` (matching agent id) overrides by key. See [Prompt Caching](/reference/prompt-caching) for details.
372+- `params.extra_body`/`params.extraBody`: advanced pass-through JSON merged into `api: "openai-completions"` request bodies for OpenAI-compatible proxies. If it collides with generated request keys, the extra body wins; non-native completions routes still strip OpenAI-only `store` afterward.
372373- `embeddedHarness`: default low-level embedded agent runtime policy. Omitted runtime defaults to OpenClaw Pi. Use `runtime: "pi"` to force the built-in PI harness, `runtime: "auto"` to let registered plugin harnesses claim supported models, or a registered harness id such as `runtime: "codex"`. Set `fallback: "none"` to disable automatic PI fallback. Explicit plugin runtimes such as `codex` fail closed by default unless you set `fallback: "pi"` in the same override scope. Keep model refs canonical as `provider/model`; select Codex, Claude CLI, Gemini CLI, and other execution backends through runtime config instead of legacy runtime provider prefixes. See [Agent runtimes](/concepts/agent-runtimes) for how this differs from provider/model selection.
373374- Config writers that mutate these fields (for example `/models set`, `/models set-image`, and fallback add/remove commands) save canonical object form and preserve existing fallback lists when possible.
374375- `maxConcurrent`: max parallel agent runs across sessions (each session still serialized). Default: 4.
@@ -1257,27 +1258,29 @@ Batches rapid text-only messages from the same sender into a single agent turn.
12571258 maxTextLength: 4000,
12581259 timeoutMs: 30000,
12591260 prefsPath: "~/.openclaw/settings/tts.json",
1260- elevenlabs: {
1261- apiKey: "elevenlabs_api_key",
1262- baseUrl: "https://api.elevenlabs.io",
1263- voiceId: "voice_id",
1264- modelId: "eleven_multilingual_v2",
1265- seed: 42,
1266- applyTextNormalization: "auto",
1267- languageCode: "en",
1268- voiceSettings: {
1269- stability: 0.5,
1270- similarityBoost: 0.75,
1271- style: 0.0,
1272- useSpeakerBoost: true,
1273- speed: 1.0,
1261+ providers: {
1262+ elevenlabs: {
1263+ apiKey: "elevenlabs_api_key",
1264+ baseUrl: "https://api.elevenlabs.io",
1265+ voiceId: "voice_id",
1266+ modelId: "eleven_multilingual_v2",
1267+ seed: 42,
1268+ applyTextNormalization: "auto",
1269+ languageCode: "en",
1270+ voiceSettings: {
1271+ stability: 0.5,
1272+ similarityBoost: 0.75,
1273+ style: 0.0,
1274+ useSpeakerBoost: true,
1275+ speed: 1.0,
1276+ },
1277+ },
1278+ openai: {
1279+ apiKey: "openai_api_key",
1280+ baseUrl: "https://api.openai.com/v1",
1281+ model: "gpt-4o-mini-tts",
1282+ voice: "alloy",
12741283 },
1275- },
1276- openai: {
1277- apiKey: "openai_api_key",
1278- baseUrl: "https://api.openai.com/v1",
1279- model: "gpt-4o-mini-tts",
1280- voice: "alloy",
12811284 },
12821285 },
12831286 },
@@ -1288,8 +1291,8 @@ Batches rapid text-only messages from the same sender into a single agent turn.
12881291- `summaryModel` overrides `agents.defaults.model.primary` for auto-summary.
12891292- `modelOverrides` is enabled by default; `modelOverrides.allowProvider` defaults to `false` (opt-in).
12901293- API keys fall back to `ELEVENLABS_API_KEY`/`XI_API_KEY` and `OPENAI_API_KEY`.
1291-- `openai.baseUrl` overrides the OpenAI TTS endpoint. Resolution order is config, then `OPENAI_TTS_BASE_URL`, then `https://api.openai.com/v1`.
1292-- When `openai.baseUrl` points to a non-OpenAI endpoint, OpenClaw treats it as an OpenAI-compatible TTS server and relaxes model/voice validation.
1294+- `providers.openai.baseUrl` overrides the OpenAI TTS endpoint. Resolution order is config, then `OPENAI_TTS_BASE_URL`, then `https://api.openai.com/v1`.
1295+- When `providers.openai.baseUrl` points to a non-OpenAI endpoint, OpenClaw treats it as an OpenAI-compatible TTS server and relaxes model/voice validation.
1293129612941297---
12951298此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。