mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-28 11:50:02 +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
156 lines
4.0 KiB
TypeScript
156 lines
4.0 KiB
TypeScript
import { completeSimple, type Model } from "openclaw/plugin-sdk/llm";
|
|
|
|
type Usage = {
|
|
input?: number;
|
|
output?: number;
|
|
cacheRead?: number;
|
|
cacheWrite?: number;
|
|
totalTokens?: number;
|
|
};
|
|
|
|
type RunResult = {
|
|
durationMs: number;
|
|
usage?: Usage;
|
|
};
|
|
|
|
const DEFAULT_PROMPT = "Reply with a single word: ok. No punctuation or extra text.";
|
|
const DEFAULT_RUNS = 10;
|
|
|
|
function parseArg(flag: string): string | undefined {
|
|
const idx = process.argv.indexOf(flag);
|
|
if (idx === -1) {
|
|
return undefined;
|
|
}
|
|
return process.argv[idx + 1];
|
|
}
|
|
|
|
function parseRuns(raw: string | undefined): number {
|
|
if (!raw) {
|
|
return DEFAULT_RUNS;
|
|
}
|
|
const parsed = Number(raw);
|
|
if (!Number.isFinite(parsed) || parsed <= 0) {
|
|
return DEFAULT_RUNS;
|
|
}
|
|
return Math.floor(parsed);
|
|
}
|
|
|
|
function median(values: number[]): number {
|
|
if (values.length === 0) {
|
|
return 0;
|
|
}
|
|
const sorted = [...values].toSorted((a, b) => a - b);
|
|
const mid = Math.floor(sorted.length / 2);
|
|
if (sorted.length % 2 === 0) {
|
|
return Math.round((sorted[mid - 1] + sorted[mid]) / 2);
|
|
}
|
|
return sorted[mid];
|
|
}
|
|
|
|
async function runModel(opts: {
|
|
label: string;
|
|
model: Model;
|
|
apiKey: string;
|
|
runs: number;
|
|
prompt: string;
|
|
}): Promise<RunResult[]> {
|
|
const results: RunResult[] = [];
|
|
for (let i = 0; i < opts.runs; i += 1) {
|
|
const started = Date.now();
|
|
const res = await completeSimple(
|
|
opts.model,
|
|
{
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: opts.prompt,
|
|
timestamp: Date.now(),
|
|
},
|
|
],
|
|
},
|
|
{ apiKey: opts.apiKey, maxTokens: 64 },
|
|
);
|
|
const durationMs = Date.now() - started;
|
|
results.push({ durationMs, usage: res.usage });
|
|
console.log(`${opts.label} run ${i + 1}/${opts.runs}: ${durationMs}ms`);
|
|
}
|
|
return results;
|
|
}
|
|
|
|
async function main(): Promise<void> {
|
|
const runs = parseRuns(parseArg("--runs"));
|
|
const prompt = parseArg("--prompt") ?? DEFAULT_PROMPT;
|
|
|
|
const anthropicKey = process.env.ANTHROPIC_API_KEY?.trim();
|
|
const minimaxKey = process.env.MINIMAX_API_KEY?.trim();
|
|
if (!anthropicKey) {
|
|
throw new Error("Missing ANTHROPIC_API_KEY in environment.");
|
|
}
|
|
if (!minimaxKey) {
|
|
throw new Error("Missing MINIMAX_API_KEY in environment.");
|
|
}
|
|
|
|
const minimaxBaseUrl = process.env.MINIMAX_BASE_URL?.trim() || "https://api.minimax.io/v1";
|
|
const minimaxModelId = process.env.MINIMAX_MODEL?.trim() || "MiniMax-M2.1";
|
|
|
|
const minimaxModel: Model<"openai-completions"> = {
|
|
id: minimaxModelId,
|
|
name: `MiniMax ${minimaxModelId}`,
|
|
api: "openai-completions",
|
|
provider: "minimax",
|
|
baseUrl: minimaxBaseUrl,
|
|
reasoning: false,
|
|
input: ["text"],
|
|
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
|
contextWindow: 200000,
|
|
maxTokens: 8192,
|
|
};
|
|
const opusModel: Model<"anthropic-messages"> = {
|
|
id: "claude-opus-4-6",
|
|
name: "Claude Opus 4.6",
|
|
api: "anthropic-messages",
|
|
provider: "anthropic",
|
|
reasoning: true,
|
|
input: ["text", "image"],
|
|
cost: { input: 15, output: 75, cacheRead: 1.5, cacheWrite: 18.75 },
|
|
contextWindow: 200000,
|
|
maxTokens: 32000,
|
|
};
|
|
|
|
console.log(`Prompt: ${prompt}`);
|
|
console.log(`Runs: ${runs}`);
|
|
console.log("");
|
|
|
|
const minimaxResults = await runModel({
|
|
label: "minimax",
|
|
model: minimaxModel,
|
|
apiKey: minimaxKey,
|
|
runs,
|
|
prompt,
|
|
});
|
|
const opusResults = await runModel({
|
|
label: "opus",
|
|
model: opusModel,
|
|
apiKey: anthropicKey,
|
|
runs,
|
|
prompt,
|
|
});
|
|
|
|
const summarize = (label: string, results: RunResult[]) => {
|
|
const durations = results.map((r) => r.durationMs);
|
|
const med = median(durations);
|
|
const min = Math.min(...durations);
|
|
const max = Math.max(...durations);
|
|
return { label, med, min, max };
|
|
};
|
|
|
|
const summary = [summarize("minimax", minimaxResults), summarize("opus", opusResults)];
|
|
console.log("");
|
|
console.log("Summary (ms):");
|
|
for (const row of summary) {
|
|
console.log(`${row.label.padEnd(7)} median=${row.med} min=${row.min} max=${row.max}`);
|
|
}
|
|
}
|
|
|
|
await main();
|