* refactor: extract agent core package Introduce packages/agent-core as the OpenClaw-owned home for reusable agent loop, harness, session, prompt, and runtime dependency contracts. * refactor: extract shared llm runtime Move provider model registries, stream wrappers, OAuth helpers, and LLM utilities into src/llm with plugin-sdk barrels instead of depending on the old embedded runtime layout. * refactor: remove pi runtime internals Rename remaining Pi-shaped agent surfaces to OpenClaw agent runtime names, delete obsolete Pi docs and package graph checks, and add the third-party notice for incorporated code. * refactor: tighten agent session runtime Make agent-core/runtime dependencies explicit, consolidate compaction and session transcript helpers, and move model/session helpers behind OpenClaw-owned contracts. * refactor: remove static model and pi auth paths Drop static model catalogs and Pi auth bridges, move model/provider facts to manifest-owned runtime contracts, and harden internal embedded-agent utilities. * refactor: remove legacy provider compat paths * docs: remove agent parity notes * fix: skip provider wildcard metadata parsing * refactor: share session extension sdk loading * refactor: inline acpx proxy error formatter * refactor: fold edit recovery into edit tool * fix: accept extension batch separator * test: align startup provider plugin expectations * fix: restore provider-scoped release discovery * test: align static asset packaging expectations * fix: run static provider catalogs during scoped discovery * fix: add provider entry catalogs for scoped live discovery * fix: load lightweight provider catalog entries * fix: refresh provider-scoped plugin metadata * fix: keep provider catalog entries on release live path * fix: keep static manifest models in release live checks * fix: harden release model discovery * fix: reduce OpenAI live cache probe reasoning * fix: disable OpenAI cache probe reasoning * ci: extend OpenAI gateway live timeout * fix: extend live gateway model budget * fix: stabilize release validation regressions * fix: honor provider aliases in model rows * fix: stabilize release validation lanes * fix: stabilize release memory qa * ci: stabilize release validation lanes * ci: prefer ipv4 for live docker node calls * fix: restore shared tool-call stream wrapper * ci: remove legacy pi test shard alias * fix: clean up embedded agent test drift * fix: stabilize runtime alias status * fix: clean up embedded agent ci drift * fix: restore release ci invariants * fix: clean up post-rebase runtime drift * fix: restore release ci checks * fix: restore release ci after rebase * fix: remove stale pi runtime path * test: align compaction runtime expectations * test: update plugin prerelease expectations * fix: handle claude live tool approvals * fix: stabilize release validation gates * fix: finish agent runtime import * test: finish post-rebase agent runtime mocks * fix: keep codex compaction native * fix: stabilize codex app-server hook tests * test: isolate codex diagnostic active run * test: remove codex diagnostic completion race # Conflicts: # extensions/codex/src/app-server/run-attempt.test.ts * ci: fix full release manifest performance run id * refactor: narrow llm plugin sdk boundary * chore: drop generated google boundary stamps * fix: repair rebase fallout * fix: clean up rebased runtime references * fix: decode codex jwt payloads as base64url * fix: preserve shipped pi runtime alias * fix: add scoped sdk virtual modules * fix: decode llm codex oauth jwt as base64url * fix: avoid stale vertex adc negative cache * fix: harden tool arg decoding and codeql path * fix: keep vertex adc negative checks live * refactor: consolidate codex jwt and edit helpers * fix: await codex oauth node runtime imports * fix: preserve sdk tool and notice contracts * fix: preserve shipped compat config boundaries * fix: align codex oauth callback host * fix: terminate agent-core loop streams on failure * fix: keep codex oauth callback alive during fallback * ci: include session tools in critical codeql scans * fix: keep Cloudflare Anthropic provider auth header * docs: redirect legacy pi runtime pages * fix: honor bundled web provider compat discovery * fix: protect session output spill files * fix: keep legacy agent dir env blocked * fix: contain auto-discovered skill symlinks * fix: harden agent core sdk proxy surfaces * fix: restore approval reaction sdk compat * fix: keep live docker runs bounded * fix: keep codex oauth redirect host aligned * fix: resolve post-rebase agent runtime drift * fix: redact anthropic oauth parse failures * fix: preserve responses strict tool shaping * fix: repair agent runtime rebase cleanup * docs: redirect retired parity pages * fix: bound auto-discovered resources to roots * fix: repair post-rebase agent test drift * fix: preserve bundled provider allowlist migration * fix: preserve manifest-owned provider aliases * fix: declare photon image dependency * fix: keep provider headers out of proxy body * fix: preserve shipped env aliases * fix: refresh control ui i18n generated state * fix: quote read fallback paths * fix: preview edits through configured backend * test: satisfy core test typecheck * fix: preserve ZAI usage auth fallback * test: repair codex diagnostic test * fix: repair agent runtime rebase drift * test: finish embedded runner import rename * fix: repair agent runtime rebase integrations * test: align compaction oauth fallback expectations * fix: allow sdk-auth session models * fix: update doctor tool schema import * fix: preserve bedrock plugin region * fix: stream harmony-like prose immediately * ci: include session runtime in codeql shards * fix: repair latest rebase integrations * fix: honor explicit codex websocket transport * fix: keep openai-compatible credentials provider-scoped * fix: refresh sdk api baseline after rebase * fix: route cli runtime aliases through openclaw harness * test: rename stale harness mock expectation * test: rename embedded agent overflow calls * test: clean embedded auth test wording * test: use openclaw stream types in deepinfra cache test * fix: refresh sdk api baseline on latest main * fix: honor bundled discovery compat allowlists * fix: refresh sdk api baseline after latest rebase * fix: remove stale rebase imports * test: rename stale model catalog mock * test: mock renamed doctor runtime modules * fix: map canonical kimi env auth * fix: use internal model registry in bench script * fix: migrate deepinfra provider catalog entry * fix: enforce builtin tool suppression * fix: route compaction auth and proxy payloads safely * refactor: prune unused llm registry leftovers * test: update codex hooks session import * test: fix model picker ci coverage * test: align model picker auth mock types
30 KiB
summary, title, sidebarTitle, read_when
| summary | title | sidebarTitle | read_when | |||
|---|---|---|---|---|---|---|
| Import map, registration API reference, and SDK architecture | Plugin SDK overview | Plugin SDK overview |
|
The plugin SDK is the typed contract between plugins and core. This page is the reference for what to import and what you can register.
This page is for plugin authors using `openclaw/plugin-sdk/*` inside OpenClaw. For external apps, scripts, dashboards, CI jobs, and IDE extensions that want to run agents through the Gateway, use the [OpenClaw App SDK](/concepts/openclaw-sdk) and the `@openclaw/sdk` package instead. Looking for a how-to guide instead? Start with [Building plugins](/plugins/building-plugins), use [Channel plugins](/plugins/sdk-channel-plugins) for channel plugins, [Provider plugins](/plugins/sdk-provider-plugins) for provider plugins, [CLI backend plugins](/plugins/cli-backend-plugins) for local AI CLI backends, and [Plugin hooks](/plugins/hooks) for tool or lifecycle hook plugins.Import convention
Always import from a specific subpath:
import { definePluginEntry } from "openclaw/plugin-sdk/plugin-entry";
import { defineChannelPluginEntry } from "openclaw/plugin-sdk/channel-core";
Each subpath is a small, self-contained module. This keeps startup fast and
prevents circular dependency issues. For channel-specific entry/build helpers,
prefer openclaw/plugin-sdk/channel-core; keep openclaw/plugin-sdk/core for
the broader umbrella surface and shared helpers such as
buildChannelConfigSchema.
For channel config, publish the channel-owned JSON Schema through
openclaw.plugin.json#channelConfigs. The plugin-sdk/channel-config-schema
subpath is for shared schema primitives and the generic builder. OpenClaw's
bundled plugins use plugin-sdk/bundled-channel-config-schema for retained
bundled-channel schemas. Deprecated compatibility exports remain on
plugin-sdk/channel-config-schema-legacy; neither bundled schema subpath is a
pattern for new plugins.
A small set of bundled-plugin helper seams still appear in the generated export map when they have tracked owner usage. They exist for bundled-plugin maintenance only and are not recommended import paths for new third-party plugins.
openclaw/plugin-sdk/discord and openclaw/plugin-sdk/telegram-account are
also kept as deprecated compatibility facades for tracked owner usage. Do not
copy those import paths into new plugins; use injected runtime helpers and
generic channel SDK subpaths instead.
Subpath reference
The plugin SDK is exposed as a set of narrow subpaths grouped by area (plugin entry, channel, provider, auth, runtime, capability, memory, and reserved bundled-plugin helpers). For the full catalog — grouped and linked — see Plugin SDK subpaths.
The compiler entrypoint inventory lives in
scripts/lib/plugin-sdk-entrypoints.json; package exports are generated from
the public subset after subtracting repo-local test/internal subpaths listed in
scripts/lib/plugin-sdk-private-local-only-subpaths.json. Run
pnpm plugin-sdk:surface to audit the public export count. Deprecated public
subpaths that are old enough and unused by bundled extension production code are
tracked in scripts/lib/plugin-sdk-deprecated-public-subpaths.json; broad
deprecated re-export barrels are tracked in
scripts/lib/plugin-sdk-deprecated-barrel-subpaths.json.
Registration API
The register(api) callback receives an OpenClawPluginApi object with these
methods:
Capability registration
| Method | What it registers |
|---|---|
api.registerProvider(...) |
Text inference (LLM) |
api.registerAgentHarness(...) |
Experimental low-level agent executor |
api.registerCliBackend(...) |
Local CLI inference backend |
api.registerChannel(...) |
Messaging channel |
api.registerEmbeddingProvider(...) |
Reusable vector embedding provider |
api.registerSpeechProvider(...) |
Text-to-speech / STT synthesis |
api.registerRealtimeTranscriptionProvider(...) |
Streaming realtime transcription |
api.registerRealtimeVoiceProvider(...) |
Duplex realtime voice sessions |
api.registerMediaUnderstandingProvider(...) |
Image/audio/video analysis |
api.registerImageGenerationProvider(...) |
Image generation |
api.registerMusicGenerationProvider(...) |
Music generation |
api.registerVideoGenerationProvider(...) |
Video generation |
api.registerWebFetchProvider(...) |
Web fetch / scrape provider |
api.registerWebSearchProvider(...) |
Web search |
Embedding providers registered with api.registerEmbeddingProvider(...) must
also be listed in contracts.embeddingProviders in the plugin manifest. This
is the generic embedding surface for reusable vector generation. Memory search
can consume this generic provider surface. The older
api.registerMemoryEmbeddingProvider(...) and
contracts.memoryEmbeddingProviders seam is deprecated compatibility while
existing memory-specific providers migrate.
Tools and commands
Use defineToolPlugin for simple tool-only plugins
with fixed tool names. Use api.registerTool(...) directly for mixed plugins
or fully dynamic tool registration.
| Method | What it registers |
|---|---|
api.registerTool(tool, opts?) |
Agent tool (required or { optional: true }) |
api.registerCommand(def) |
Custom command (bypasses the LLM) |
Plugin commands can set agentPromptGuidance when the agent needs a short,
command-owned routing hint. Keep that text about the command itself; do not add
provider- or plugin-specific policy to core prompt builders.
Guidance entries may be legacy strings, which apply to every prompt surface, or structured entries:
agentPromptGuidance: [
"Global command hint.",
{ text: "Only show this in the main OpenClaw prompt.", surfaces: ["openclaw_main"] },
];
Structured surfaces may include openclaw_main, codex_app_server,
cli_backend, acp_backend, or subagent. pi_main remains a deprecated alias
for openclaw_main. Omit surfaces for intentional all-surface guidance. Do
not pass an empty surfaces array; it is rejected so accidental scope loss does
not become global prompt text.
Native Codex app-server developer instructions are stricter than other prompt
surfaces: only guidance explicitly scoped to codex_app_server is promoted into
that higher-priority lane. Legacy string guidance and unscoped structured
guidance remain available to non-Codex prompt surfaces for compatibility.
Infrastructure
| Method | What it registers |
|---|---|
api.registerHook(events, handler, opts?) |
Event hook |
api.registerHttpRoute(params) |
Gateway HTTP endpoint |
api.registerGatewayMethod(name, handler) |
Gateway RPC method |
api.registerGatewayDiscoveryService(service) |
Local Gateway discovery advertiser |
api.registerCli(registrar, opts?) |
CLI subcommand |
api.registerNodeCliFeature(registrar, opts?) |
Node feature CLI under openclaw nodes |
api.registerService(service) |
Background service |
api.registerInteractiveHandler(registration) |
Interactive handler |
api.registerAgentToolResultMiddleware(...) |
Runtime tool-result middleware |
api.registerMemoryPromptSupplement(builder) |
Additive memory-adjacent prompt section |
api.registerMemoryCorpusSupplement(adapter) |
Additive memory search/read corpus |
Host hooks for workflow plugins
Host hooks are the SDK seams for plugins that need to participate in the host lifecycle rather than only adding a provider, channel, or tool. They are generic contracts; Plan Mode can use them, but so can approval workflows, workspace policy gates, background monitors, setup wizards, and UI companion plugins.
| Method | Contract it owns |
|---|---|
api.session.state.registerSessionExtension(...) |
Plugin-owned, JSON-compatible session state projected through Gateway sessions |
api.session.workflow.enqueueNextTurnInjection(...) |
Durable exactly-once context injected into the next agent turn for one session |
api.registerTrustedToolPolicy(...) |
Bundled/trusted pre-plugin tool policy that can block or rewrite tool params |
api.registerToolMetadata(...) |
Tool catalog display metadata without changing the tool implementation |
api.registerCommand(...) |
Scoped plugin commands; command results can set continueAgent: true; Discord native commands support descriptionLocalizations |
api.session.controls.registerControlUiDescriptor(...) |
Control UI contribution descriptors for session, tool, run, or settings surfaces |
api.lifecycle.registerRuntimeLifecycle(...) |
Cleanup callbacks for plugin-owned runtime resources on reset/delete/reload paths |
api.agent.events.registerAgentEventSubscription(...) |
Sanitized event subscriptions for workflow state and monitors |
api.runContext.setRunContext(...) / getRunContext(...) / clearRunContext(...) |
Per-run plugin scratch state cleared on terminal run lifecycle |
api.session.workflow.registerSessionSchedulerJob(...) |
Cleanup metadata for plugin-owned scheduler jobs; does not schedule work or create task records |
api.session.workflow.sendSessionAttachment(...) |
Bundled-only host-mediated file attachment delivery to the active direct-outbound session route |
api.session.workflow.scheduleSessionTurn(...) / unscheduleSessionTurnsByTag(...) |
Bundled-only Cron-backed scheduled session turns plus tag-based cleanup |
api.session.controls.registerSessionAction(...) |
Typed session actions clients can dispatch through the Gateway |
Use the grouped namespaces for new plugin code:
api.session.state.registerSessionExtension(...)api.session.workflow.enqueueNextTurnInjection(...)api.session.workflow.registerSessionSchedulerJob(...)api.session.workflow.sendSessionAttachment(...)api.session.workflow.scheduleSessionTurn(...)api.session.workflow.unscheduleSessionTurnsByTag(...)api.session.controls.registerSessionAction(...)api.session.controls.registerControlUiDescriptor(...)api.agent.events.registerAgentEventSubscription(...)api.agent.events.emitAgentEvent(...)api.runContext.setRunContext(...)/getRunContext(...)/clearRunContext(...)api.lifecycle.registerRuntimeLifecycle(...)
The equivalent flat methods remain available as deprecated compatibility
aliases for existing plugins. Do not add new plugin code that calls
api.registerSessionExtension, api.enqueueNextTurnInjection,
api.registerControlUiDescriptor, api.registerRuntimeLifecycle,
api.registerAgentEventSubscription, api.emitAgentEvent,
api.setRunContext, api.getRunContext, api.clearRunContext,
api.registerSessionSchedulerJob, api.registerSessionAction,
api.sendSessionAttachment, api.scheduleSessionTurn, or
api.unscheduleSessionTurnsByTag directly.
scheduleSessionTurn(...) is a session-scoped convenience over the Gateway
Cron scheduler. Cron owns timing and creates the background task record when the
turn runs; the Plugin SDK only constrains the target session, plugin-owned
naming, and cleanup. Use api.runtime.tasks.managedFlows inside the scheduled
turn when the work itself needs durable multi-step Task Flow state.
The contracts intentionally split authority:
- External plugins can own session extensions, UI descriptors, commands, tool metadata, next-turn injections, and normal hooks.
- Trusted tool policies run before ordinary
before_tool_callhooks and are bundled-only because they participate in host safety policy. - Reserved command ownership is bundled-only. External plugins should use their own command names or aliases.
allowPromptInjection=falsedisables prompt-mutating hooks includingagent_turn_prepare,before_prompt_build,heartbeat_prompt_contribution, prompt fields from legacybefore_agent_start, andenqueueNextTurnInjection.
Examples of non-Plan consumers:
| Plugin archetype | Hooks used |
|---|---|
| Approval workflow | Session extension, command continuation, next-turn injection, UI descriptor |
| Budget/workspace policy gate | Trusted tool policy, tool metadata, session projection |
| Background lifecycle monitor | Runtime lifecycle cleanup, agent event subscription, session scheduler ownership/cleanup, heartbeat prompt contribution, UI descriptor |
| Setup or onboarding wizard | Session extension, scoped commands, Control UI descriptor |
Bundled plugins must declare contracts.agentToolResultMiddleware for each
targeted runtime, for example ["openclaw", "codex"]. External plugins
cannot register this middleware; keep normal OpenClaw plugin hooks for work
that does not need pre-model tool-result timing. The old embedded-runner-only
extension factory registration path has been removed.
Gateway discovery registration
api.registerGatewayDiscoveryService(...) lets a plugin advertise the active
Gateway on a local discovery transport such as mDNS/Bonjour. OpenClaw calls the
service during Gateway startup when local discovery is enabled, passes the
current Gateway ports and non-secret TXT hint data, and calls the returned
stop handler during Gateway shutdown.
api.registerGatewayDiscoveryService({
id: "my-discovery",
async advertise(ctx) {
const handle = await startMyAdvertiser({
gatewayPort: ctx.gatewayPort,
tls: ctx.gatewayTlsEnabled,
displayName: ctx.machineDisplayName,
});
return { stop: () => handle.stop() };
},
});
Gateway discovery plugins must not treat advertised TXT values as secrets or authentication. Discovery is a routing hint; Gateway auth and TLS pinning still own trust.
CLI registration metadata
api.registerCli(registrar, opts?) accepts two kinds of command metadata:
commands: explicit command names owned by the registrardescriptors: parse-time command descriptors used for CLI help, routing, and lazy plugin CLI registrationparentPath: optional parent command path for nested command groups, such as["nodes"]
For paired-node features, prefer
api.registerNodeCliFeature(registrar, opts?). It is a small wrapper around
api.registerCli(..., { parentPath: ["nodes"] }) and makes commands such as
openclaw nodes canvas explicit plugin-owned node features.
If you want a plugin command to stay lazy-loaded in the normal root CLI path,
provide descriptors that cover every top-level command root exposed by that
registrar.
api.registerCli(
async ({ program }) => {
const { registerMatrixCli } = await import("./src/cli.js");
registerMatrixCli({ program });
},
{
descriptors: [
{
name: "matrix",
description: "Manage Matrix accounts, verification, devices, and profile state",
hasSubcommands: true,
},
],
},
);
Nested commands receive the resolved parent command as program:
api.registerCli(
async ({ program }) => {
const { registerNodesCanvasCommands } = await import("./src/cli.js");
registerNodesCanvasCommands(program);
},
{
parentPath: ["nodes"],
descriptors: [
{
name: "canvas",
description: "Capture or render canvas content from a paired node",
hasSubcommands: true,
},
],
},
);
Use commands by itself only when you do not need lazy root CLI registration.
That eager compatibility path remains supported, but it does not install
descriptor-backed placeholders for parse-time lazy loading.
CLI backend registration
api.registerCliBackend(...) lets a plugin own the default config for a local
AI CLI backend such as claude-cli or my-cli.
- The backend
idbecomes the provider prefix in model refs likemy-cli/gpt-5. - The backend
configuses the same shape asagents.defaults.cliBackends.<id>. - User config still wins. OpenClaw merges
agents.defaults.cliBackends.<id>over the plugin default before running the CLI. - Use
normalizeConfigwhen a backend needs compatibility rewrites after merge (for example normalizing old flag shapes). - Use
resolveExecutionArgsfor request-scoped argv rewrites that belong to the CLI dialect, such as mapping OpenClaw thinking levels to a native effort flag.
For an end-to-end authoring guide, see CLI backend plugins.
Exclusive slots
| Method | What it registers |
|---|---|
api.registerContextEngine(id, factory) |
Context engine (one active at a time). The assemble() callback receives availableTools and citationsMode so the engine can tailor prompt additions. |
api.registerMemoryCapability(capability) |
Unified memory capability |
api.registerMemoryPromptSection(builder) |
Memory prompt section builder |
api.registerMemoryFlushPlan(resolver) |
Memory flush plan resolver |
api.registerMemoryRuntime(runtime) |
Memory runtime adapter |
Deprecated memory embedding adapters
| Method | What it registers |
|---|---|
api.registerMemoryEmbeddingProvider(adapter) |
Memory embedding adapter for the active plugin |
registerMemoryCapabilityis the preferred exclusive memory-plugin API.registerMemoryCapabilitymay also exposepublicArtifacts.listArtifacts(...)so companion plugins can consume exported memory artifacts throughopenclaw/plugin-sdk/memory-host-coreinstead of reaching into a specific memory plugin's private layout.registerMemoryPromptSection,registerMemoryFlushPlan, andregisterMemoryRuntimeare legacy-compatible exclusive memory-plugin APIs.MemoryFlushPlan.modelcan pin the flush turn to an exactprovider/modelreference, such asollama/qwen3:8b, without inheriting the active fallback chain.registerMemoryEmbeddingProvideris deprecated. New embedding providers should useapi.registerEmbeddingProvider(...)andcontracts.embeddingProviders.- Existing memory-specific providers continue to work during the migration window, but plugin inspection reports this as compatibility debt for non-bundled plugins.
Events and lifecycle
| Method | What it does |
|---|---|
api.on(hookName, handler, opts?) |
Typed lifecycle hook |
api.onConversationBindingResolved(handler) |
Conversation binding callback |
See Plugin hooks for examples, common hook names, and guard semantics.
Hook decision semantics
before_tool_call: returning{ block: true }is terminal. Once any handler sets it, lower-priority handlers are skipped.before_tool_call: returning{ block: false }is treated as no decision (same as omittingblock), not as an override.before_install: returning{ block: true }is terminal. Once any handler sets it, lower-priority handlers are skipped.before_install: returning{ block: false }is treated as no decision (same as omittingblock), not as an override.reply_dispatch: returning{ handled: true, ... }is terminal. Once any handler claims dispatch, lower-priority handlers and the default model dispatch path are skipped.message_sending: returning{ cancel: true }is terminal. Once any handler sets it, lower-priority handlers are skipped.message_sending: returning{ cancel: false }is treated as no decision (same as omittingcancel), not as an override.message_received: use the typedthreadIdfield when you need inbound thread/topic routing. Keepmetadatafor channel-specific extras.message_sending: use typedreplyToId/threadIdrouting fields before falling back to channel-specificmetadata.gateway_start: usectx.config,ctx.workspaceDir, andctx.getCron?.()for gateway-owned startup state instead of relying on internalgateway:startuphooks.cron_changed: observe gateway-owned cron lifecycle changes. Useevent.job?.state?.nextRunAtMsandctx.getCron?.()when syncing external wake schedulers, and keep OpenClaw as the source of truth for due checks and execution.
API object fields
| Field | Type | Description |
|---|---|---|
api.id |
string |
Plugin id |
api.name |
string |
Display name |
api.version |
string? |
Plugin version (optional) |
api.description |
string? |
Plugin description (optional) |
api.source |
string |
Plugin source path |
api.rootDir |
string? |
Plugin root directory (optional) |
api.config |
OpenClawConfig |
Current config snapshot (active in-memory runtime snapshot when available) |
api.pluginConfig |
Record<string, unknown> |
Plugin-specific config from plugins.entries.<id>.config |
api.runtime |
PluginRuntime |
Runtime helpers |
api.logger |
PluginLogger |
Scoped logger (debug, info, warn, error) |
api.registrationMode |
PluginRegistrationMode |
Current load mode; "setup-runtime" is the lightweight pre-full-entry startup/setup window |
api.resolvePath(input) |
(string) => string |
Resolve path relative to plugin root |
Internal module convention
Within your plugin, use local barrel files for internal imports:
my-plugin/
api.ts # Public exports for external consumers
runtime-api.ts # Internal-only runtime exports
index.ts # Plugin entry point
setup-entry.ts # Lightweight setup-only entry (optional)
Facade-loaded bundled plugin public surfaces (api.ts, runtime-api.ts,
index.ts, setup-entry.ts, and similar public entry files) prefer the
active runtime config snapshot when OpenClaw is already running. If no runtime
snapshot exists yet, they fall back to the resolved config file on disk.
Packaged bundled plugin facades should be loaded through OpenClaw's plugin
facade loaders; direct imports from dist/extensions/... bypass the manifest
and runtime sidecar checks that packaged installs use for plugin-owned code.
Provider plugins can expose a narrow plugin-local contract barrel when a helper is intentionally provider-specific and does not belong in a generic SDK subpath yet. Bundled examples:
- Anthropic: public
api.ts/contract-api.tsseam for Claude beta-header andservice_tierstream helpers. @openclaw/openai-provider:api.tsexports provider builders, default-model helpers, and realtime provider builders.@openclaw/openrouter-provider:api.tsexports the provider builder plus onboarding/config helpers.