惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

WordPress大学
WordPress大学
Cyberwarzone
Cyberwarzone
The GitHub Blog
The GitHub Blog
云风的 BLOG
云风的 BLOG
P
Proofpoint News Feed
小众软件
小众软件
Recent Announcements
Recent Announcements
博客园 - 三生石上(FineUI控件)
Security Archives - TechRepublic
Security Archives - TechRepublic
W
WeLiveSecurity
Cloudbric
Cloudbric
博客园 - 司徒正美
美团技术团队
N
News and Events Feed by Topic
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
PCI Perspectives
PCI Perspectives
宝玉的分享
宝玉的分享
H
Help Net Security
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Google DeepMind News
Google DeepMind News
Help Net Security
Help Net Security
Last Week in AI
Last Week in AI
S
Schneier on Security
N
News | PayPal Newsroom
B
Blog RSS Feed
L
LINUX DO - 最新话题
T
Troy Hunt's Blog
S
Secure Thoughts
雷峰网
雷峰网
aimingoo的专栏
aimingoo的专栏
L
Lohrmann on Cybersecurity
G
Google Developers Blog
Microsoft Azure Blog
Microsoft Azure Blog
Hacker News - Newest:
Hacker News - Newest: "LLM"
T
Tenable Blog
S
Securelist
L
LangChain Blog
Recent Commits to openclaw:main
Recent Commits to openclaw:main
I
InfoQ
H
Heimdal Security Blog
Cisco Talos Blog
Cisco Talos Blog
F
Full Disclosure
Y
Y Combinator Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
K
Kaspersky official blog
T
Tailwind CSS Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
阮一峰的网络日志
阮一峰的网络日志
C
Cisco Blogs

Recent Commits to openclaw:main

test: merge chat side-result checks · openclaw/openclaw@ddd2c2a test: merge cron history checks · openclaw/openclaw@f7eb746 test: merge responsive navigation shell checks · openclaw/openclaw@c2e4b47 docs(changelog): add codex oauth fixes · openclaw/openclaw@628e6cd test: merge navigation routing cases · openclaw/openclaw@5d8cecb Tests: mock channel registry bundled fallback · openclaw/openclaw@2b08233 Secrets: avoid broad web search discovery for single plugin config · openclaw/openclaw@a464f59 test: merge config view browser checks · openclaw/openclaw@20cf511 fix(status): align oauth health with runtime · openclaw/openclaw@eed7116 feat: add macOS screen snapshots for monitor preview (#67954) thanks … · openclaw/openclaw@f377db1 fix: report shared auth scopes in hello-ok (#67810) thanks @BunsDev · openclaw/openclaw@0b6c39b Auto-reply: avoid eager bundled route fallback · openclaw/openclaw@3ea1bf4 Tests: narrow session binding contract setup · openclaw/openclaw@54e4e16 fix(macOS): enable undo/redo in webchat composer text input (#34962) · openclaw/openclaw@00951dc Tests: speed up channel setup promotion · openclaw/openclaw@82b529a Docs: refresh agent instructions · openclaw/openclaw@5775fe2 fix(auth): serialize OAuth refresh across agents to fix #26322 (#67876) · openclaw/openclaw@8e79080 test: allow ollama public surface boundary test · openclaw/openclaw@7d4f1a6 Docs: add test performance guardrails · openclaw/openclaw@89706d3 Tests: restore context-engine usage proof · openclaw/openclaw@e4c4f95 Tests: slim context engine runtime coverage · openclaw/openclaw@74c198f ci: retry failed custom checkouts · openclaw/openclaw@0ee5baf test: trim duplicate provider auth onboarding cases · openclaw/openclaw@1ffc02e matrix: fix sessions_spawn --thread subagent session spawning (#67643) · openclaw/openclaw@1ce2596 test: reduce auth choice fixture churn · openclaw/openclaw@857b9cd test: mock health status config boundaries · openclaw/openclaw@9d5ab4a test: mock onboard config io boundary · openclaw/openclaw@299694d test: mock legacy state plugin boundaries · openclaw/openclaw@2713089 test: mock channel install boundaries · openclaw/openclaw@b945248 test: mock doctor preview channel boundaries · openclaw/openclaw@b1a3ad4 test: trim doctor command hotspots · openclaw/openclaw@c66f16a test: isolate agent auth and spawn hotspots · openclaw/openclaw@9285935 test: stabilize MCP startup disposal race · openclaw/openclaw@dd9d2eb test: merge browser contract server suites · openclaw/openclaw@5817a76 test: narrow ollama provider discovery setup · openclaw/openclaw@a0d9598 build: declare qa-lab aimock runtime dependency · openclaw/openclaw@24431e5 test: speed up safe-bins exec harness · openclaw/openclaw@ee856ab test: preserve tool helpers in embedded runner mocks · openclaw/openclaw@acd86a0 refactor: move memory embeddings into provider plugins · openclaw/openclaw@77e6e4c test: reuse system-run temp fixtures · openclaw/openclaw@7e9ff0f test: trim hotspot wait overhead · openclaw/openclaw@12a59b0 Check: avoid duplicate boundary prep · openclaw/openclaw@baf11b8 test: reduce hotspot fixture overhead · openclaw/openclaw@3a59edd feat(ui): overhaul settings and slash command UX (#67819) thanks @Bun… · openclaw/openclaw@2cfb660 QA Matrix: exit cleanly on failure · openclaw/openclaw@42805d2 QA Matrix: isolate scenario coverage · openclaw/openclaw@7e659e1 Matrix: refresh crypto bootstrap state · openclaw/openclaw@94081d8 QA Lab: add provider registry · openclaw/openclaw@bb7e982 Matrix: add plugin changelog · openclaw/openclaw@4acab55 test: trim more hotspot overhead · openclaw/openclaw@f485311 test: trim remaining hotspot tests · openclaw/openclaw@6ba8626 test: narrow hotspot mocks · openclaw/openclaw@dbc8179 test: isolate gemini embedding request helpers · openclaw/openclaw@cd330f5 test: trim memory and mcp hotspots · openclaw/openclaw@fd48dfa test: slim provider registry mocks · openclaw/openclaw@2e08c77 test: harden Parallels update smoke · openclaw/openclaw@1a98090 feat: default Anthropic to Opus 4.7 · openclaw/openclaw@628b454 fix: harden node-host shell payload mutability checks · openclaw/openclaw@75c551e fix: land node-host approval binding for native binaries (#66731) (th… · openclaw/openclaw@29919bb CI: add daily schedule to CodeQL workflow (#67645) · openclaw/openclaw@69d25f5 fix(gateway): capture config hash after plugin auto-enable to prevent… · openclaw/openclaw@8c11210 fix: repair sanitized replay tool results before send (#67620) (thank… · openclaw/openclaw@c3c7a99 fix: restrict HTML timeout short-circuit to transient statuses · openclaw/openclaw@de129a6 fix: keep TUI watchdog bound to active run (#67401) (thanks @xantorres) · openclaw/openclaw@3525273 Gateway/skills: dedupe skills prefix-match + drop dead fallback on log · openclaw/openclaw@d7f489f Extensions/lmstudio: back off inference preload after consecutive fai… · openclaw/openclaw@b555214 TUI/streaming: add watchdog that resets the activity indicator after … · openclaw/openclaw@f44ab20 Agents/tool-loop: enable unknown-tool stream guard by default · openclaw/openclaw@36ed367 Gateway/skills: invalidate session skills snapshot on config write · openclaw/openclaw@b23d59a fix: classify HTML provider error pages correctly (#67642) (thanks @s… · openclaw/openclaw@e588e90 fix(skills): remove unused model-usage import (#67641) · openclaw/openclaw@55f05df docs(changelog): credit codex fix superseded PRs · openclaw/openclaw@e485f24 fix(openai-codex): normalize stale transport metadata in resolution a… · openclaw/openclaw@90801ba CI: pin Docker-related GitHub Actions (#67632) · openclaw/openclaw@f697b01 Android: modernize WebView and discovery API usage (#67627) · openclaw/openclaw@44a6e50 fix(deps): bump hono to 4.12.14 and @hono/node-server to 1.19.14 (GHS… · openclaw/openclaw@fbccc18 fix(deps): bump dompurify to 3.4.0 (#67614) · openclaw/openclaw@2c2dc00 CI: add explicit permissions to all workflow jobs (fixes code-scannin… · openclaw/openclaw@01b7516 fix: register bundled TTS providers and route overrides correctly (#6… · openclaw/openclaw@6ea3cdd fix: align host tilde paths with OS home (#62804) (thanks @stainlu) · openclaw/openclaw@ecfaf64 fix: flush creds queue before reconnect socket open (#67464) (thanks … · openclaw/openclaw@405c63f fix: strip standalone <function> tool call tags from visible text (#6… · openclaw/openclaw@78df859 fix(agents): preserve cli session metadata before transcript persist … · openclaw/openclaw@898fd04 docs(changelog): move cli transcript entry · openclaw/openclaw@c1817c6 fix(agents): normalize cli transcript api field · openclaw/openclaw@3a3fae0 docs(changelog): note cli transcript persistence · openclaw/openclaw@6c343f1 fix(agents): persist cli transcript turns · openclaw/openclaw@b8ef507 fix(msteams): harden security-sensitive flows (#65841) · openclaw/openclaw@c56b56e [Dashboard] Fix exec approval modal overflow for long command content… · openclaw/openclaw@053c5b0 Docs: remove QA changelog entry · openclaw/openclaw@7fd5771 QA: fix private runtime source loading (#67428) · openclaw/openclaw@d5933af docs(gateway): correct protocol.md schema path, hello-ok example, aut… · openclaw/openclaw@489404d CI: pin Node 22 runners to 22.18.0 · openclaw/openclaw@4ffa621 models.authStatus: normalize provider ids + tighten env-backed escape… · openclaw/openclaw@f2fdb9d Update CHANGELOG.md · openclaw/openclaw@7694a92 test(parallels): clean up npm update guard jobs · openclaw/openclaw@045ea7b Plugins: prefer scanDir override paths · openclaw/openclaw@b2974da fix(dreaming): default storage.mode to "separate" so phase blocks sto… · openclaw/openclaw@8c392f0 fix(memory-core): skip dreaming transcript ingestion via session stor… · openclaw/openclaw@a1b01f0 fix: dedupe replayed exec.finished node events (#67281) · openclaw/openclaw@5dcf526
fix: match codex openai websocket continuation · openclaw/openclaw@cabdf5b
steipete · 2026-04-25 · via Recent Commits to openclaw:main

@@ -11,7 +11,10 @@

1111

import { createAssistantMessageEventStream } from "@mariozechner/pi-ai";

1212

import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";

1313

import type { ResponseObject } from "./openai-ws-connection.js";

14-

import { buildOpenAIWebSocketResponseCreatePayload } from "./openai-ws-request.js";

14+

import {

15+

buildOpenAIWebSocketResponseCreatePayload,

16+

planOpenAIWebSocketRequestPayload,

17+

} from "./openai-ws-request.js";

1518

import {

1619

__testing as openAIWsStreamTesting,

1720

buildAssistantMessageFromResponse,

@@ -22,6 +25,7 @@ import {

2225

planTurnInput,

2326

releaseWsSession,

2427

} from "./openai-ws-stream.js";

28+

import type { InputItem, ResponseCreateEvent } from "./openai-ws-types.js";

2529

import { log } from "./pi-embedded-runner/logger.js";

2630

import { SYSTEM_PROMPT_CACHE_BOUNDARY } from "./system-prompt-cache-boundary.js";

2731

@@ -152,6 +156,10 @@ const { MockManager } = vi.hoisted(() => {

152156153157

// Test helper: simulate a server event

154158

simulateEvent(event: unknown): void {

159+

const maybeEvent = event as { type?: string; response?: { id?: string } };

160+

if (maybeEvent.type === "response.completed" && maybeEvent.response?.id) {

161+

this._previousResponseId = maybeEvent.response.id;

162+

}

155163

for (const fn of this._listeners) {

156164

fn(event);

157165

}

@@ -1678,6 +1686,101 @@ describe("planTurnInput", () => {

1678168616791687

// ─────────────────────────────────────────────────────────────────────────────

168016881689+

describe("planOpenAIWebSocketRequestPayload", () => {

1690+

it("sends only the strict suffix when the full input extends the prior response chain", () => {

1691+

const previousInputItems: InputItem[] = [{ type: "message", role: "user", content: "Hello" }];

1692+

const previousRequest: ResponseCreateEvent = {

1693+

type: "response.create",

1694+

model: "gpt-5.4",

1695+

store: false,

1696+

instructions: "You are helpful.",

1697+

input: previousInputItems,

1698+

};

1699+

const previousResponseInputItems: InputItem[] = [

1700+

{ type: "message", role: "assistant", content: "Hi" },

1701+

];

1702+

const fullPayload: ResponseCreateEvent = {

1703+

type: "response.create",

1704+

model: "gpt-5.4",

1705+

store: false,

1706+

instructions: "You are helpful.",

1707+

input: [

1708+

...previousInputItems,

1709+

...previousResponseInputItems,

1710+

{ type: "message", role: "user", content: "Next" },

1711+

],

1712+

};

1713+1714+

const plan = planOpenAIWebSocketRequestPayload({

1715+

fullPayload,

1716+

previousRequestPayload: previousRequest,

1717+

previousResponseId: "resp_prev",

1718+

previousResponseInputItems: [...previousResponseInputItems],

1719+

});

1720+1721+

expect(plan.mode).toBe("incremental");

1722+

expect(plan.payload.previous_response_id).toBe("resp_prev");

1723+

expect(plan.payload.input).toEqual([{ type: "message", role: "user", content: "Next" }]);

1724+

});

1725+1726+

it("falls back to full context when non-input fields differ", () => {

1727+

const previousInputItems: InputItem[] = [{ type: "message", role: "user", content: "Hello" }];

1728+

const previousRequest: ResponseCreateEvent = {

1729+

type: "response.create",

1730+

model: "gpt-5.4",

1731+

store: false,

1732+

instructions: "Old instructions",

1733+

input: previousInputItems,

1734+

};

1735+

const fullPayload: ResponseCreateEvent = {

1736+

...previousRequest,

1737+

instructions: "New instructions",

1738+

input: [

1739+

...previousInputItems,

1740+

{ type: "message", role: "assistant", content: "Hi" },

1741+

{ type: "message", role: "user", content: "Next" },

1742+

],

1743+

};

1744+1745+

const plan = planOpenAIWebSocketRequestPayload({

1746+

fullPayload,

1747+

previousRequestPayload: previousRequest,

1748+

previousResponseId: "resp_prev",

1749+

previousResponseInputItems: [{ type: "message", role: "assistant", content: "Hi" }],

1750+

});

1751+1752+

expect(plan.mode).toBe("full_context");

1753+

expect(plan.payload.previous_response_id).toBeUndefined();

1754+

expect(plan.payload.input).toEqual(fullPayload.input);

1755+

});

1756+1757+

it("falls back to full context when the input is not a strict response-chain extension", () => {

1758+

const previousRequest: ResponseCreateEvent = {

1759+

type: "response.create",

1760+

model: "gpt-5.4",

1761+

store: false,

1762+

input: [{ type: "message", role: "user", content: "Hello" }],

1763+

};

1764+

const fullPayload: ResponseCreateEvent = {

1765+

...previousRequest,

1766+

input: [{ type: "message", role: "user", content: "Different" }],

1767+

};

1768+1769+

const plan = planOpenAIWebSocketRequestPayload({

1770+

fullPayload,

1771+

previousRequestPayload: previousRequest,

1772+

previousResponseId: "resp_prev",

1773+

previousResponseInputItems: [{ type: "message", role: "assistant", content: "Hi" }],

1774+

});

1775+1776+

expect(plan.mode).toBe("full_context");

1777+

expect(plan.payload.previous_response_id).toBeUndefined();

1778+

expect(plan.payload.input).toEqual(fullPayload.input);

1779+

});

1780+

});

1781+1782+

// ─────────────────────────────────────────────────────────────────────────────

1783+16811784

describe("createOpenAIWebSocketStreamFn", () => {

16821785

const modelStub = {

16831786

api: "openai-responses",

@@ -2738,7 +2841,6 @@ describe("createOpenAIWebSocketStreamFn", () => {

2738284127392842

// Server responds with a tool call

27402843

const turn1Response = makeResponseObject("resp_turn1", undefined, "exec");

2741-

manager.setPreviousResponseId("resp_turn1");

27422844

manager.simulateEvent({ type: "response.completed", response: turn1Response });

27432845

await done1;

27442846

@@ -2747,8 +2849,8 @@ describe("createOpenAIWebSocketStreamFn", () => {

27472849

systemPrompt: "You are helpful.",

27482850

messages: [

27492851

userMsg("Run ls"),

2750-

assistantMsg([], [{ id: "call_1", name: "exec", args: { cmd: "ls" } }]),

2751-

toolResultMsg("call_1", "file.txt"),

2852+

buildAssistantMessageFromResponse(turn1Response, modelStub),

2853+

toolResultMsg("call_abc|item_2", "file.txt"),

27522854

] as Parameters<typeof convertMessagesToInputItems>[0],

27532855

tools: [],

27542856

};

@@ -2785,7 +2887,68 @@ describe("createOpenAIWebSocketStreamFn", () => {

27852887

expect(inputTypes).toHaveLength(1);

27862888

});

278728892788-

it("omits previous_response_id when replaying full context on follow-up turns", async () => {

2890+

it("sends only a follow-up user message when the full context is a strict extension", async () => {

2891+

const sessionId = "sess-user-delta";

2892+

const streamFn = createOpenAIWebSocketStreamFn("sk-test", sessionId);

2893+2894+

const ctx1 = {

2895+

systemPrompt: "You are helpful.",

2896+

messages: [userMsg("Hello")] as Parameters<typeof convertMessagesToInputItems>[0],

2897+

tools: [],

2898+

};

2899+2900+

const stream1 = streamFn(

2901+

modelStub as Parameters<typeof streamFn>[0],

2902+

ctx1 as Parameters<typeof streamFn>[1],

2903+

);

2904+

const done1 = (async () => {

2905+

for await (const _ of await resolveStream(stream1)) {

2906+

/* consume */

2907+

}

2908+

})();

2909+2910+

await new Promise((r) => setImmediate(r));

2911+

const manager = MockManager.lastInstance!;

2912+

const turn1Response = makeResponseObject("resp_turn1_text", "Hi there.");

2913+

manager.simulateEvent({ type: "response.completed", response: turn1Response });

2914+

await done1;

2915+2916+

const ctx2 = {

2917+

systemPrompt: "You are helpful.",

2918+

messages: [

2919+

userMsg("Hello"),

2920+

buildAssistantMessageFromResponse(turn1Response, modelStub),

2921+

userMsg("What can you do?"),

2922+

] as Parameters<typeof convertMessagesToInputItems>[0],

2923+

tools: [],

2924+

};

2925+2926+

const stream2 = streamFn(

2927+

modelStub as Parameters<typeof streamFn>[0],

2928+

ctx2 as Parameters<typeof streamFn>[1],

2929+

);

2930+

const done2 = (async () => {

2931+

for await (const _ of await resolveStream(stream2)) {

2932+

/* consume */

2933+

}

2934+

})();

2935+2936+

await new Promise((r) => setImmediate(r));

2937+

manager.simulateEvent({

2938+

type: "response.completed",

2939+

response: makeResponseObject("resp_turn2_text", "I can help."),

2940+

});

2941+

await done2;

2942+2943+

const sent2 = manager.sentEvents[1] as {

2944+

previous_response_id?: string;

2945+

input: Array<{ type: string; role?: string; content?: unknown }>;

2946+

};

2947+

expect(sent2.previous_response_id).toBe("resp_turn1_text");

2948+

expect(sent2.input).toEqual([{ type: "message", role: "user", content: "What can you do?" }]);

2949+

});

2950+2951+

it("uses an empty incremental payload when replay context exactly matches the response chain", async () => {

27892952

const sessionId = "sess-full-context-replay";

27902953

const streamFn = createOpenAIWebSocketStreamFn("sk-test", sessionId);

27912954

@@ -2830,7 +2993,6 @@ describe("createOpenAIWebSocketStreamFn", () => {

2830299328312994

await new Promise((r) => setImmediate(r));

28322995

const manager = MockManager.lastInstance!;

2833-

manager.setPreviousResponseId("resp_turn1_reasoning");

28342996

manager.simulateEvent({ type: "response.completed", response: turn1Response });

28352997

await done1;

28362998

@@ -2864,14 +3026,8 @@ describe("createOpenAIWebSocketStreamFn", () => {

28643026

previous_response_id?: string;

28653027

input: Array<{ type: string; id?: string; call_id?: string }>;

28663028

};

2867-

expect(sent2.previous_response_id).toBeUndefined();

2868-

expect(sent2.input.map((item) => item.type)).toEqual(["message", "reasoning", "function_call"]);

2869-

expect(sent2.input[1]).toMatchObject({ type: "reasoning", id: "rs_turn1" });

2870-

expect(sent2.input[2]).toMatchObject({

2871-

type: "function_call",

2872-

call_id: "call_turn1",

2873-

id: "fc_turn1",

2874-

});

3029+

expect(sent2.previous_response_id).toBe("resp_turn1_reasoning");

3030+

expect(sent2.input).toEqual([]);

28753031

});

2876303228773033

it("sends instructions (system prompt) in each request", async () => {