@@ -425,6 +425,7 @@ Time format in system prompt. Default: `auto` (OS preference).
425425- `model.primary`: format `provider/model` (e.g. `openai/gpt-5.5` for OpenAI API-key or Codex OAuth access). 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.
426426- `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`, `chat_template_kwargs`, `extra_body`/`extraBody`).
427427- Use `provider/*` entries such as `"openai-codex/*": {}` or `"vllm/*": {}` to show all discovered models for selected providers without manually listing every model id.
428+- Add `agentRuntime` to a `provider/*` entry when every dynamically discovered model for that provider should use the same runtime. Exact `provider/model` runtime policy still wins over the wildcard.
428429- 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`.
429430- Provider-scoped configure/onboarding flows merge selected provider models into this map and preserve unrelated providers already configured.
430431- 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).
@@ -458,6 +459,9 @@ Time format in system prompt. Default: `auto` (OS preference).
458459"anthropic/claude-opus-4-7": {
459460 agentRuntime: { id: "claude-cli" },
460461 },
462+"vllm/*": {
463+ agentRuntime: { id: "pi" },
464+ },
461465 },
462466 },
463467 },
@@ -466,6 +470,7 @@ Time format in system prompt. Default: `auto` (OS preference).
466470467471- `id`: `"auto"`, `"pi"`, a registered plugin harness id, or a supported CLI backend alias. The bundled Codex plugin registers `codex`; the bundled Anthropic plugin provides the `claude-cli` CLI backend.
468472- `id: "auto"` lets registered plugin harnesses claim supported turns and uses PI when no harness matches. An explicit plugin runtime such as `id: "codex"` requires that harness and fails closed if it is unavailable or fails.
473+- Runtime precedence is exact model policy first (`agents.list[].models["provider/model"]`, `agents.defaults.models["provider/model"]`, or `models.providers.<provider>.models[]`), then `agents.list[]` / `agents.defaults.models["provider/*"]`, then provider-wide policy at `models.providers.<provider>.agentRuntime`.
469474- Whole-agent runtime keys are legacy. `agents.defaults.agentRuntime`, `agents.list[].agentRuntime`, session runtime pins, and `OPENCLAW_AGENT_RUNTIME` are ignored by runtime selection. Run `openclaw doctor --fix` to remove stale values.
470475- OpenAI agent models use the Codex harness by default; provider/model `agentRuntime.id: "codex"` remains valid when you want to make that explicit.
471476- For Claude CLI deployments, prefer `model: "anthropic/claude-opus-4-7"` plus model-scoped `agentRuntime.id: "claude-cli"`. Legacy `claude-cli/claude-opus-4-7` model refs still work for compatibility, but new config should keep provider/model selection canonical and put the execution backend in provider/model runtime policy.
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。