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

B
Blog RSS Feed
V2EX - 技术
V2EX - 技术
P
Privacy & Cybersecurity Law Blog
T
The Exploit Database - CXSecurity.com
美团技术团队
WordPress大学
WordPress大学
博客园 - 司徒正美
S
Securelist
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - Franky
Attack and Defense Labs
Attack and Defense Labs
Security Latest
Security Latest
L
LINUX DO - 最新话题
NISL@THU
NISL@THU
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
腾讯CDC
Y
Y Combinator Blog
The Hacker News
The Hacker News
Security Archives - TechRepublic
Security Archives - TechRepublic
IT之家
IT之家
T
Threatpost
Hugging Face - Blog
Hugging Face - Blog
Scott Helme
Scott Helme
S
SegmentFault 最新的问题
Cyberwarzone
Cyberwarzone
C
Cisco Blogs
阮一峰的网络日志
阮一峰的网络日志
U
Unit 42
B
Blog
Microsoft Azure Blog
Microsoft Azure Blog
P
Proofpoint News Feed
小众软件
小众软件
V
Vulnerabilities – Threatpost
J
Java Code Geeks
V
Visual Studio Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
A
Arctic Wolf
博客园 - 【当耐特】
Microsoft Security Blog
Microsoft Security Blog
S
Security @ Cisco Blogs
雷峰网
雷峰网
Help Net Security
Help Net Security
The Last Watchdog
The Last Watchdog
Recent Announcements
Recent Announcements
G
Google Developers Blog
C
CERT Recently Published Vulnerability Notes
T
Troy Hunt's Blog
MyScale Blog
MyScale Blog

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 Active Memory memory-only recall latency (#75200) · openclaw/openclaw@f2efe33
SYU8384 · 2026-05-05 · via Recent Commits to openclaw:main

@@ -46,6 +46,7 @@ const DEFAULT_PARTIAL_TRANSCRIPT_MAX_CHARS = 32_000;

4646

const DEFAULT_TRANSCRIPT_READ_MAX_LINES = 2_000;

4747

const DEFAULT_TRANSCRIPT_READ_MAX_BYTES = 50 * 1024 * 1024;

4848

const TIMEOUT_PARTIAL_DATA_GRACE_MS = 50;

49+

const MAX_ACTIVE_MEMORY_SEARCH_QUERY_CHARS = 480;

4950

const TERMINAL_MEMORY_SEARCH_POLL_INTERVAL_MS = 25;

50515152

const NO_RECALL_VALUES = new Set([

@@ -940,13 +941,16 @@ function buildPromptStyleLines(style: ActiveMemoryPromptStyle): string[] {

940941

function buildRecallPrompt(params: {

941942

config: ResolvedActiveRecallPluginConfig;

942943

query: string;

944+

searchQuery: string;

943945

}): string {

944946

const defaultInstructions = [

945947

"You are a memory search agent.",

946948

"Another model is preparing the final user-facing answer.",

947949

"Your job is to search memory and return only the most relevant memory context for that model.",

948-

"You receive conversation context, including the user's latest message.",

950+

"You receive a bounded search query plus conversation context, including the user's latest message.",

949951

"Use only the available memory tools.",

952+

"Use the bounded search query as the memory_search or memory_recall query.",

953+

"Do not use channel metadata, provider metadata, debug output, or the full conversation context as the memory tool query.",

950954

"Prefer memory_recall when available.",

951955

"If memory_recall is unavailable, use memory_search and memory_get.",

952956

"When searching for preference or habit recall, use a permissive recall limit or memory_search threshold before deciding that no useful memory exists.",

@@ -998,7 +1002,11 @@ function buildRecallPrompt(params: {

9981002

]

9991003

.filter((section) => section.length > 0)

10001004

.join("\n\n");

1001-

return `${instructionBlock}\n\nConversation context:\n${params.query}`;

1005+

return [

1006+

instructionBlock,

1007+

`Bounded memory search query:\n${params.searchQuery}`,

1008+

`Conversation context:\n${params.query}`,

1009+

].join("\n\n");

10021010

}

1003101110041012

function isEnabledForAgent(

@@ -2056,6 +2064,83 @@ function buildQuery(params: {

20562064

].join("\n");

20572065

}

205820662067+

function stripExternalUntrustedBlocks(text: string): string {

2068+

return text.replace(

2069+

/<<<EXTERNAL_UNTRUSTED_CONTENT\b[^>]*>>>[\s\S]*?<<<END_EXTERNAL_UNTRUSTED_CONTENT\b[^>]*>>>/g,

2070+

" ",

2071+

);

2072+

}

2073+2074+

function stripJsonFences(text: string): string {

2075+

return text.replace(/```(?:json)?\s*[\s\S]*?```/gi, " ");

2076+

}

2077+2078+

function stripActiveMemoryXmlBlocks(text: string): string {

2079+

return text.replace(/<active_memory_plugin>[\s\S]*?<\/active_memory_plugin>/gi, " ");

2080+

}

2081+2082+

function normalizeSearchQueryText(text: string): string {

2083+

return text

2084+

.split("\n")

2085+

.map((line) => line.trim())

2086+

.filter((line) => {

2087+

if (!line) {

2088+

return false;

2089+

}

2090+

if (/^(conversation info|sender|untrusted context)\b/i.test(line)) {

2091+

return false;

2092+

}

2093+

if (/^(source: external|---|untrusted discord message body)$/i.test(line)) {

2094+

return false;

2095+

}

2096+

if (/^?\s*Agent couldn't generate a response/i.test(line)) {

2097+

return false;

2098+

}

2099+

if (/^Please try again\.?$/i.test(line)) {

2100+

return false;

2101+

}

2102+

return true;

2103+

})

2104+

.join(" ")

2105+

.replace(/\s+/g, " ")

2106+

.trim();

2107+

}

2108+2109+

function clampSearchQuery(text: string): string {

2110+

const normalized = text.replace(/\s+/g, " ").trim();

2111+

return normalized.length > MAX_ACTIVE_MEMORY_SEARCH_QUERY_CHARS

2112+

? normalized.slice(0, MAX_ACTIVE_MEMORY_SEARCH_QUERY_CHARS).trim()

2113+

: normalized;

2114+

}

2115+2116+

function buildSearchQuery(params: {

2117+

latestUserMessage: string;

2118+

recentTurns?: ActiveRecallRecentTurn[];

2119+

}): string {

2120+

const latest = clampSearchQuery(

2121+

normalizeSearchQueryText(

2122+

stripActiveMemoryXmlBlocks(

2123+

stripJsonFences(stripExternalUntrustedBlocks(params.latestUserMessage)),

2124+

),

2125+

),

2126+

);

2127+

if (latest.length >= 12 || !params.recentTurns?.length) {

2128+

return latest || clampSearchQuery(params.latestUserMessage);

2129+

}

2130+

const previousUser = [...params.recentTurns]

2131+

.toReversed()

2132+

.find((turn) => turn.role === "user" && turn.text.trim() !== params.latestUserMessage.trim());

2133+

if (!previousUser) {

2134+

return latest || clampSearchQuery(params.latestUserMessage);

2135+

}

2136+

const context = clampSearchQuery(

2137+

normalizeSearchQueryText(stripRecalledContextNoise(previousUser.text)),

2138+

)

2139+

.slice(0, 120)

2140+

.trim();

2141+

return clampSearchQuery(context ? `${context} ${latest}` : latest);

2142+

}

2143+20592144

function extractTextContent(content: unknown): string {

20602145

if (typeof content === "string") {

20612146

return content;

@@ -2224,6 +2309,7 @@ async function runRecallSubagent(params: {

22242309

messageProvider?: string;

22252310

channelId?: string;

22262311

query: string;

2312+

searchQuery: string;

22272313

currentModelProviderId?: string;

22282314

currentModelId?: string;

22292315

modelRef?: { provider: string; model: string };

@@ -2278,6 +2364,7 @@ async function runRecallSubagent(params: {

22782364

const prompt = buildRecallPrompt({

22792365

config: params.config,

22802366

query: params.query,

2367+

searchQuery: params.searchQuery,

22812368

});

22822369

const { messageChannel, messageProvider } = resolveRecallRunChannelContext({

22832370

api: params.api,

@@ -2367,6 +2454,7 @@ async function maybeResolveActiveRecall(params: {

23672454

messageProvider?: string;

23682455

channelId?: string;

23692456

query: string;

2457+

searchQuery: string;

23702458

currentModelProviderId?: string;

23712459

currentModelId?: string;

23722460

}): Promise<ActiveRecallResult> {

@@ -2444,7 +2532,9 @@ async function maybeResolveActiveRecall(params: {

2444253224452533

if (params.config.logging) {

24462534

params.api.logger.info?.(

2447-

`${logPrefix} start timeoutMs=${String(params.config.timeoutMs)} queryChars=${String(params.query.length)}`,

2535+

`${logPrefix} start timeoutMs=${String(params.config.timeoutMs)} queryChars=${String(

2536+

params.query.length,

2537+

)} searchQueryChars=${String(params.searchQuery.length)}`,

24482538

);

24492539

}

24502540

@@ -2813,11 +2903,16 @@ export default definePluginEntry({

28132903

});

28142904

return undefined;

28152905

}

2906+

const recentTurns = extractRecentTurns(event.messages);

28162907

const query = buildQuery({

28172908

latestUserMessage: event.prompt,

2818-

recentTurns: extractRecentTurns(event.messages),

2909+

recentTurns,

28192910

config,

28202911

});

2912+

const searchQuery = buildSearchQuery({

2913+

latestUserMessage: event.prompt,

2914+

recentTurns,

2915+

});

28212916

const result = await maybeResolveActiveRecall({

28222917

api,

28232918

config,

@@ -2827,6 +2922,7 @@ export default definePluginEntry({

28272922

messageProvider: ctx.messageProvider,

28282923

channelId: ctx.channelId,

28292924

query,

2925+

searchQuery,

28302926

currentModelProviderId: ctx.modelProviderId,

28312927

currentModelId: ctx.modelId,

28322928

});