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

C
Check Point Blog
IT之家
IT之家
V
Visual Studio Blog
The Cloudflare Blog
博客园 - 司徒正美
Jina AI
Jina AI
博客园_首页
阮一峰的网络日志
阮一峰的网络日志
美团技术团队
S
SegmentFault 最新的问题
博客园 - 聂微东
人人都是产品经理
人人都是产品经理
T
Tailwind CSS Blog
罗磊的独立博客
酷 壳 – CoolShell
酷 壳 – CoolShell
量子位
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Hugging Face - Blog
Hugging Face - Blog
博客园 - 【当耐特】
博客园 - 三生石上(FineUI控件)
爱范儿
爱范儿
博客园 - Franky
Last Week in AI
Last Week in AI
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

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(agents): cover committed delivery fallback · opencla...
steipete · 2026-04-25 · via Recent Commits to openclaw:main

@@ -17,6 +17,7 @@ import {

1717

DEFAULT_REASONING_ONLY_RETRY_LIMIT,

1818

EMPTY_RESPONSE_RETRY_INSTRUCTION,

1919

extractPlanningOnlyPlanDetails,

20+

hasCommittedUserVisibleToolDelivery,

2021

isLikelyExecutionAckPrompt,

2122

PLANNING_ONLY_RETRY_INSTRUCTION,

2223

REASONING_ONLY_RETRY_INSTRUCTION,

@@ -919,6 +920,73 @@ describe("runEmbeddedPiAgent incomplete-turn safety", () => {

919920

expect(incompleteTurnText).toContain("verify before retrying");

920921

});

921922923+

it("does not treat empty committed messaging arrays as user-visible delivery", () => {

924+

expect(

925+

hasCommittedUserVisibleToolDelivery({

926+

messagingToolSentTexts: [" "],

927+

messagingToolSentMediaUrls: [],

928+

}),

929+

).toBe(false);

930+

});

931+932+

it("treats committed messaging media as user-visible delivery", () => {

933+

expect(

934+

hasCommittedUserVisibleToolDelivery({

935+

messagingToolSentTexts: [],

936+

messagingToolSentMediaUrls: ["file:///tmp/render.png"],

937+

}),

938+

).toBe(true);

939+

});

940+941+

it("treats committed messaging text as replay-invalid side effect metadata", () => {

942+

expect(

943+

buildAttemptReplayMetadata({

944+

toolMetas: [],

945+

didSendViaMessagingTool: false,

946+

messagingToolSentTexts: ["Delivered through the message tool."],

947+

messagingToolSentMediaUrls: [],

948+

}),

949+

).toEqual({ hadPotentialSideEffects: true, replaySafe: false });

950+

});

951+952+

it("treats committed messaging media as replay-invalid side effect metadata", () => {

953+

expect(

954+

buildAttemptReplayMetadata({

955+

toolMetas: [],

956+

didSendViaMessagingTool: false,

957+

messagingToolSentTexts: [],

958+

messagingToolSentMediaUrls: ["file:///tmp/render.png"],

959+

}),

960+

).toEqual({ hadPotentialSideEffects: true, replaySafe: false });

961+

});

962+963+

it("leaves committed delivery plus tool errors to the tool-error payload path", () => {

964+

const incompleteTurnText = resolveIncompleteTurnPayloadText({

965+

payloadCount: 0,

966+

aborted: false,

967+

timedOut: false,

968+

attempt: makeAttemptResult({

969+

assistantTexts: [],

970+

didSendViaMessagingTool: true,

971+

messagingToolSentTexts: ["Delivered through the message tool."],

972+

lastToolError: {

973+

toolName: "message",

974+

meta: "send",

975+

error: "delivery failed for second target",

976+

},

977+

lastAssistant: {

978+

role: "assistant",

979+

stopReason: "error",

980+

provider: "openai",

981+

model: "gpt-5.4",

982+

content: [],

983+

} as unknown as EmbeddedRunAttemptResult["lastAssistant"],

984+

}),

985+

});

986+987+

expect(incompleteTurnText).toBeNull();

988+

});

989+922990

it("does not retry reasoning-only GPT turns after side effects", () => {

923991

const retryInstruction = resolveReasoningOnlyRetryInstruction({

924992

provider: "openai",