mirror of
https://github.com/openclaw/openclaw.git
synced 2026-06-01 00:16:34 +00:00
* 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
248 lines
7.7 KiB
TypeScript
248 lines
7.7 KiB
TypeScript
import type { StreamFn } from "openclaw/plugin-sdk/agent-core";
|
|
import type { ProviderWrapStreamFnContext } from "openclaw/plugin-sdk/plugin-entry";
|
|
import { OPENROUTER_THINKING_STREAM_HOOKS } from "openclaw/plugin-sdk/provider-stream-family";
|
|
import {
|
|
createDeepSeekV4OpenAICompatibleThinkingWrapper,
|
|
type DeepSeekV4ReasoningEffort,
|
|
type DeepSeekV4ThinkingLevel,
|
|
createPayloadPatchStreamWrapper,
|
|
} from "openclaw/plugin-sdk/provider-stream-shared";
|
|
import { createSubsystemLogger } from "openclaw/plugin-sdk/runtime-env";
|
|
import { isOpenRouterDeepSeekV4ModelId } from "./models.js";
|
|
import {
|
|
isOpenRouterProxyReasoningUnsupportedModel,
|
|
normalizeOpenRouterBaseUrl,
|
|
OPENROUTER_BASE_URL,
|
|
} from "./provider-catalog.js";
|
|
|
|
const log = createSubsystemLogger("openrouter-stream");
|
|
|
|
function readString(value: unknown): string | undefined {
|
|
return typeof value === "string" ? value.trim() : undefined;
|
|
}
|
|
|
|
function isOpenRouterAnthropicModelId(modelId: unknown): boolean {
|
|
const normalized = readString(modelId)?.toLowerCase();
|
|
return (
|
|
normalized?.startsWith("anthropic/") === true ||
|
|
normalized?.startsWith("openrouter/anthropic/") === true
|
|
);
|
|
}
|
|
|
|
function isVerifiedOpenRouterRoute(model: Parameters<StreamFn>[0]): boolean {
|
|
const provider = readString(model.provider)?.toLowerCase();
|
|
const baseUrl = readString(model.baseUrl);
|
|
if (baseUrl) {
|
|
return normalizeOpenRouterBaseUrl(baseUrl) === OPENROUTER_BASE_URL;
|
|
}
|
|
return provider === "openrouter";
|
|
}
|
|
|
|
function shouldPatchAnthropicOpenRouterPayload(model: Parameters<StreamFn>[0]): boolean {
|
|
const api = readString(model.api);
|
|
return (
|
|
(api === undefined || api === "openai-completions") &&
|
|
isOpenRouterAnthropicModelId(model.id) &&
|
|
isVerifiedOpenRouterRoute(model)
|
|
);
|
|
}
|
|
|
|
function shouldPatchDeepSeekV4OpenRouterPayload(model: Parameters<StreamFn>[0]): boolean {
|
|
const api = readString(model.api);
|
|
return (
|
|
(api === undefined || api === "openai-completions") &&
|
|
isOpenRouterDeepSeekV4ModelId(model.id) &&
|
|
isVerifiedOpenRouterRoute(model)
|
|
);
|
|
}
|
|
|
|
function shouldPatchOpenRouterRoutingPayload(model: Parameters<StreamFn>[0]): boolean {
|
|
const api = readString(model.api);
|
|
return (api === undefined || api === "openai-completions") && isVerifiedOpenRouterRoute(model);
|
|
}
|
|
|
|
function assistantMessageHasOpenAIToolCalls(message: Record<string, unknown>): boolean {
|
|
return Array.isArray(message.tool_calls) && message.tool_calls.length > 0;
|
|
}
|
|
|
|
function isAnthropicToolCallContentBlock(value: unknown): boolean {
|
|
return (
|
|
value !== null &&
|
|
typeof value === "object" &&
|
|
((value as { type?: unknown }).type === "tool_use" ||
|
|
(value as { type?: unknown }).type === "toolCall")
|
|
);
|
|
}
|
|
|
|
function assistantMessageHasAnthropicToolUse(message: Record<string, unknown>): boolean {
|
|
const content = message.content;
|
|
return Array.isArray(content) && content.some(isAnthropicToolCallContentBlock);
|
|
}
|
|
|
|
function shouldStripOpenRouterTrailingMessage(value: unknown): boolean {
|
|
if (!value || typeof value !== "object") {
|
|
return false;
|
|
}
|
|
const message = value as Record<string, unknown>;
|
|
return (
|
|
message.role === "assistant" &&
|
|
!assistantMessageHasOpenAIToolCalls(message) &&
|
|
!assistantMessageHasAnthropicToolUse(message)
|
|
);
|
|
}
|
|
|
|
function stripTrailingOpenRouterAssistantPrefillMessages(payload: Record<string, unknown>): number {
|
|
const messages = payload.messages;
|
|
if (!Array.isArray(messages)) {
|
|
return 0;
|
|
}
|
|
|
|
let keep = messages.length;
|
|
while (keep > 0 && shouldStripOpenRouterTrailingMessage(messages[keep - 1])) {
|
|
keep -= 1;
|
|
}
|
|
if (keep === messages.length) {
|
|
return 0;
|
|
}
|
|
const stripped = messages.length - keep;
|
|
messages.splice(keep);
|
|
return stripped;
|
|
}
|
|
|
|
function resolveOpenRouterDeepSeekV4ReasoningEffort(
|
|
thinkingLevel: DeepSeekV4ThinkingLevel,
|
|
): DeepSeekV4ReasoningEffort {
|
|
switch (thinkingLevel) {
|
|
case "minimal":
|
|
case "low":
|
|
case "medium":
|
|
case "high":
|
|
case "xhigh":
|
|
return thinkingLevel;
|
|
case "max":
|
|
return "xhigh";
|
|
case "adaptive":
|
|
return "medium";
|
|
case "off":
|
|
case undefined:
|
|
return "high";
|
|
}
|
|
return "high";
|
|
}
|
|
|
|
function isEnabledReasoningValue(value: unknown): boolean {
|
|
if (value === undefined || value === null || value === false) {
|
|
return false;
|
|
}
|
|
if (typeof value === "string") {
|
|
const normalized = value.trim().toLowerCase();
|
|
return normalized !== "" && normalized !== "off" && normalized !== "none";
|
|
}
|
|
return true;
|
|
}
|
|
|
|
function isOpenRouterReasoningPayloadEnabled(payload: Record<string, unknown>): boolean {
|
|
return (
|
|
isEnabledReasoningValue(payload.reasoning) || isEnabledReasoningValue(payload.reasoning_effort)
|
|
);
|
|
}
|
|
|
|
function injectOpenRouterRouting(
|
|
baseStreamFn: StreamFn | undefined,
|
|
providerRouting?: Record<string, unknown>,
|
|
): StreamFn | undefined {
|
|
if (!providerRouting) {
|
|
return baseStreamFn;
|
|
}
|
|
const routedStreamFn: StreamFn = (model, context, options) =>
|
|
(
|
|
baseStreamFn ??
|
|
((nextModel) => {
|
|
throw new Error(
|
|
`OpenRouter routing wrapper requires an underlying streamFn for ${nextModel.id}.`,
|
|
);
|
|
})
|
|
)(
|
|
{
|
|
...model,
|
|
compat: { ...model.compat, openRouterRouting: providerRouting },
|
|
} as typeof model,
|
|
context,
|
|
options,
|
|
);
|
|
return createPayloadPatchStreamWrapper(
|
|
routedStreamFn,
|
|
({ payload }) => {
|
|
if (payload.provider === undefined) {
|
|
payload.provider = providerRouting;
|
|
}
|
|
},
|
|
{
|
|
shouldPatch: ({ model }) => shouldPatchOpenRouterRoutingPayload(model),
|
|
},
|
|
);
|
|
}
|
|
|
|
function createOpenRouterAnthropicPrefillWrapper(baseStreamFn: StreamFn | undefined): StreamFn {
|
|
return createPayloadPatchStreamWrapper(
|
|
baseStreamFn,
|
|
({ payload }) => {
|
|
if (!isOpenRouterReasoningPayloadEnabled(payload)) {
|
|
return;
|
|
}
|
|
const stripped = stripTrailingOpenRouterAssistantPrefillMessages(payload);
|
|
if (stripped > 0) {
|
|
log.warn(
|
|
`removed ${stripped} trailing assistant prefill message${stripped === 1 ? "" : "s"} because OpenRouter-routed Anthropic reasoning requires conversations to end with a user turn`,
|
|
);
|
|
}
|
|
},
|
|
{
|
|
shouldPatch: ({ model }) => shouldPatchAnthropicOpenRouterPayload(model),
|
|
},
|
|
);
|
|
}
|
|
|
|
function createOpenRouterDeepSeekV4ThinkingWrapper(
|
|
baseStreamFn: StreamFn | undefined,
|
|
thinkingLevel: ProviderWrapStreamFnContext["thinkingLevel"],
|
|
): StreamFn | undefined {
|
|
return createDeepSeekV4OpenAICompatibleThinkingWrapper({
|
|
baseStreamFn,
|
|
thinkingLevel,
|
|
shouldPatchModel: shouldPatchDeepSeekV4OpenRouterPayload,
|
|
resolveReasoningEffort: resolveOpenRouterDeepSeekV4ReasoningEffort,
|
|
shouldBackfillAssistantReasoningContent: (message) =>
|
|
!assistantMessageHasOpenAIToolCalls(message),
|
|
});
|
|
}
|
|
|
|
export function wrapOpenRouterProviderStream(
|
|
ctx: ProviderWrapStreamFnContext,
|
|
): StreamFn | null | undefined {
|
|
const providerRouting =
|
|
ctx.extraParams?.provider != null && typeof ctx.extraParams.provider === "object"
|
|
? (ctx.extraParams.provider as Record<string, unknown>)
|
|
: undefined;
|
|
const routedStreamFn = providerRouting
|
|
? injectOpenRouterRouting(ctx.streamFn, providerRouting)
|
|
: ctx.streamFn;
|
|
const wrapStreamFn = OPENROUTER_THINKING_STREAM_HOOKS.wrapStreamFn ?? undefined;
|
|
if (!wrapStreamFn) {
|
|
return createOpenRouterAnthropicPrefillWrapper(
|
|
createOpenRouterDeepSeekV4ThinkingWrapper(routedStreamFn, ctx.thinkingLevel),
|
|
);
|
|
}
|
|
const wrappedStreamFn =
|
|
wrapStreamFn({
|
|
...ctx,
|
|
streamFn: routedStreamFn,
|
|
thinkingLevel: isOpenRouterProxyReasoningUnsupportedModel(ctx.modelId)
|
|
? undefined
|
|
: ctx.thinkingLevel,
|
|
}) ?? undefined;
|
|
return createOpenRouterAnthropicPrefillWrapper(
|
|
createOpenRouterDeepSeekV4ThinkingWrapper(wrappedStreamFn, ctx.thinkingLevel),
|
|
);
|
|
}
|