### Changes

- Plugins/runtime: expose provider-backed thinking policy and normalization through `api.runtime.agent`, letting tool plugins validate thinking overrides without duplicating provider/model level lists. Thanks @openclaw.

- Providers: add Cerebras as a bundled plugin with onboarding, static model catalog, docs, and manifest-owned endpoint metadata.

- Memory/OpenAI-compatible: add optional `memorySearch.inputType`, `queryInputType`, and `documentInputType` config for asymmetric embedding endpoints, including direct query embeddings and provider batch indexing. Carries forward #63313 and #60727. Thanks @HOYALIM and @prospect1314521.

- Ollama/memory: add model-specific retrieval query prefixes for `nomic-embed-text`, `qwen3-embedding`, and `mxbai-embed-large` memory-search queries while leaving document batches unchanged. Carries forward #45013. Thanks @laolin5564.

491267e919c6bf426f673a9066e703811c7779a32de87edd0ce493147fd4438e plugin-sdk-api-baseline.json

590d21aeb520f34b5bf23abb7b17602b204f170547c772d60b604bb34a3940bb plugin-sdk-api-baseline.jsonl

b81647828ee6599cdd1d76d96ea02c92ccdebb8c1b3b443cefe10ca8bd2ddbfe plugin-sdk-api-baseline.json

ca9f3569352522621857b51872f30b3c31881505fd9eff2451b1b46d77670726 plugin-sdk-api-baseline.jsonl

const identity = api.runtime.agent.resolveAgentIdentity(cfg);

// Get default thinking level

const thinking = api.runtime.agent.resolveThinkingDefault(cfg, provider, model);

const thinking = api.runtime.agent.resolveThinkingDefault({

cfg,

provider,

model,

});

// Validate a user-provided thinking level against the active provider profile

const policy = api.runtime.agent.resolveThinkingPolicy({ provider, model });

const level = api.runtime.agent.normalizeThinkingLevel("extra high");

if (level && policy.levels.some((entry) => entry.id === level)) {

// pass level to an embedded run

}

// Get agent timeout

const timeoutMs = api.runtime.agent.resolveAgentTimeoutMs(cfg);

`runEmbeddedPiAgent(...)` remains as a compatibility alias.

`resolveThinkingPolicy(...)` returns the provider/model's supported thinking levels and optional default. Provider plugins own the model-specific profile through their thinking hooks, so tool plugins should call this runtime helper instead of importing or duplicating provider lists.

`normalizeThinkingLevel(...)` converts user text such as `on`, `x-high`, or `extra high` to the canonical stored level before checking it against the resolved policy.

**Session store helpers** are under `api.runtime.agent.session`:

```typescript

| `plugin-sdk/allow-from` | `formatAllowFromLowercase` |

| `plugin-sdk/channel-secret-runtime` | Narrow secret-contract collection helpers for channel/plugin secret surfaces |

| `plugin-sdk/secret-ref-runtime` | Narrow `coerceSecretRef` and SecretRef typing helpers for secret-contract/config parsing |

| `plugin-sdk/security-runtime` | Shared trust, DM gating, external-content, constant-time secret comparison, and secret-collection helpers |

| `plugin-sdk/security-runtime` | Shared trust, DM gating, external-content, sensitive text redaction, constant-time secret comparison, and secret-collection helpers |

| `plugin-sdk/ssrf-policy` | Host allowlist and private-network SSRF policy helpers |

| `plugin-sdk/ssrf-dispatcher` | Narrow pinned-dispatcher helpers without the broad infra runtime surface |

| `plugin-sdk/ssrf-runtime` | Pinned-dispatcher, SSRF-guarded fetch, SSRF error, and SSRF policy helpers |

| `plugin-sdk/provider-zai-endpoint` | Z.AI endpoint detection helpers |

| `plugin-sdk/infra-runtime` | System event/heartbeat helpers |

| `plugin-sdk/collection-runtime` | Small bounded cache helpers |

| `plugin-sdk/diagnostic-runtime` | Diagnostic flag and event helpers |

| `plugin-sdk/diagnostic-runtime` | Diagnostic flag, event, and trace-context helpers |

| `plugin-sdk/error-runtime` | Error graph, formatting, shared error classification helpers, `isApprovalNotFoundError` |

| `plugin-sdk/fetch-runtime` | Wrapped fetch, proxy, and pinned lookup helpers |

| `plugin-sdk/runtime-fetch` | Dispatcher-aware runtime fetch without proxy/guarded-fetch imports |

- Provider plugins can expose `resolveThinkingProfile(ctx)` to define the model's supported levels and default.

- Each profile level has a stored canonical `id` (`off`, `minimal`, `low`, `medium`, `high`, `xhigh`, `adaptive`, or `max`) and may include a display `label`. Binary providers use `{ id: "low", label: "on" }`.

- Tool plugins that need to validate an explicit thinking override should use `api.runtime.agent.resolveThinkingPolicy({ provider, model })` plus `api.runtime.agent.normalizeThinkingLevel(...)`; they should not keep their own provider/model level lists.

- Published legacy hooks (`supportsXHighThinking`, `isBinaryThinking`, and `resolveDefaultThinkingLevel`) remain as compatibility adapters, but new custom level sets should use `resolveThinkingProfile`.

- Gateway rows/defaults expose `thinkingLevels`, `thinkingOptions`, and `thinkingDefault` so ACP/chat clients render the same profile ids and labels that runtime validation uses.

export * from "openclaw/plugin-sdk/diagnostics-otel";

export {

createChildDiagnosticTraceContext,

createDiagnosticTraceContext,

emitDiagnosticEvent,

formatDiagnosticTraceparent,

isValidDiagnosticSpanId,

isValidDiagnosticTraceFlags,

isValidDiagnosticTraceId,

onDiagnosticEvent,

parseDiagnosticTraceparent,

type DiagnosticEventMetadata,

type DiagnosticEventPayload,

type DiagnosticTraceContext,

} from "openclaw/plugin-sdk/diagnostic-runtime";

export { emptyPluginConfigSchema, type OpenClawPluginApi } from "openclaw/plugin-sdk/plugin-entry";

export type {

OpenClawPluginService,

OpenClawPluginServiceContext,

} from "openclaw/plugin-sdk/plugin-entry";

export { redactSensitiveText } from "openclaw/plugin-sdk/security-runtime";

export * from "openclaw/plugin-sdk/diagnostics-prometheus";

export type {

DiagnosticEventMetadata,

DiagnosticEventPayload,

} from "openclaw/plugin-sdk/diagnostic-runtime";

export {

emptyPluginConfigSchema,

type OpenClawPluginApi,

type OpenClawPluginHttpRouteHandler,

type OpenClawPluginService,

type OpenClawPluginServiceContext,

} from "openclaw/plugin-sdk/plugin-entry";

export { redactSensitiveText } from "openclaw/plugin-sdk/security-runtime";

export * from "openclaw/plugin-sdk/diffs";

export type { OpenClawConfig } from "openclaw/plugin-sdk/config-runtime";

export {

definePluginEntry,

type AnyAgentTool,

type OpenClawPluginApi,

type OpenClawPluginConfigSchema,

type OpenClawPluginToolContext,

type PluginLogger,

} from "openclaw/plugin-sdk/plugin-entry";

export { resolvePreferredOpenClawTmpDir } from "openclaw/plugin-sdk/temp-path";

export { PAIRING_APPROVED_MESSAGE } from "openclaw/plugin-sdk/channel-status";

export { chunkTextForOutbound } from "openclaw/plugin-sdk/text-chunking";

export type { OpenClawConfig } from "openclaw/plugin-sdk/config-runtime";

export { GoogleChatConfigSchema } from "openclaw/plugin-sdk/channel-config-schema-legacy";

export {

GROUP_POLICY_BLOCKED_LABEL,

isDangerousNameMatchingEnabled,

export { loadOutboundMediaFromUrl } from "openclaw/plugin-sdk/outbound-media";

export type { PluginRuntime } from "openclaw/plugin-sdk/runtime-store";

export { fetchWithSsrFGuard } from "openclaw/plugin-sdk/ssrf-runtime";

export {

GoogleChatConfigSchema,

type GoogleChatAccountConfig,

type GoogleChatConfig,

} from "openclaw/plugin-sdk/googlechat-runtime-shared";

export type { GoogleChatAccountConfig, GoogleChatConfig } from "openclaw/plugin-sdk/config-runtime";

export { extractToolSend } from "openclaw/plugin-sdk/tool-send";

export { resolveInboundMentionDecision } from "openclaw/plugin-sdk/channel-inbound";

export { resolveInboundRouteEnvelopeBuilderWithRuntime } from "openclaw/plugin-sdk/inbound-envelope";

export * from "openclaw/plugin-sdk/llm-task";

export * from "./src/runtime-api.js";

export {

definePluginEntry,

type AnyAgentTool,

type OpenClawPluginApi,

} from "openclaw/plugin-sdk/plugin-entry";