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

Microsoft Azure Blog
Microsoft Azure Blog
GbyAI
GbyAI
P
Proofpoint News Feed
Engineering at Meta
Engineering at Meta
Recent Announcements
Recent Announcements
L
LangChain Blog
B
Blog
阮一峰的网络日志
阮一峰的网络日志
Microsoft Security Blog
Microsoft Security Blog
博客园 - 【当耐特】
M
MIT News - Artificial intelligence
D
Docker
WordPress大学
WordPress大学
J
Java Code Geeks
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
The GitHub Blog
The GitHub Blog
博客园 - 叶小钗
Last Week in AI
Last Week in AI
Stack Overflow Blog
Stack Overflow Blog
有赞技术团队
有赞技术团队
MyScale Blog
MyScale Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
MongoDB | Blog
MongoDB | Blog
博客园 - Franky

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
fix(agents): handle empty Claude stop turns · openclaw/op...
steipete · 2026-04-26 · via Recent Commits to openclaw:main

@@ -7,6 +7,7 @@ const FALLBACK_TEXT = "[assistant turn failed before producing content]";

77

function bedrockAssistant(

88

content: unknown,

99

stopReason: "error" | "stop" | "toolUse" | "length" = "error",

10+

usageOverrides: Record<string, number> = {},

1011

): AgentMessage {

1112

return {

1213

role: "assistant",

@@ -21,6 +22,7 @@ function bedrockAssistant(

2122

cacheWrite: 0,

2223

totalTokens: 0,

2324

cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },

25+

...usageOverrides,

2426

},

2527

stopReason,

2628

timestamp: 0,

@@ -60,19 +62,28 @@ describe("normalizeAssistantReplayContent", () => {

6062

expect(repaired.content).toEqual([{ type: "text", text: FALLBACK_TEXT }]);

6163

});

626463-

it("preserves silent-reply turns (stopReason=stop, content=[]) untouched", () => {

65+

it("preserves nonzero-usage silent-reply turns (stopReason=stop, content=[]) untouched", () => {

6466

// run.empty-error-retry.test.ts treats `stopReason:"stop"` + `content:[]`

6567

// as a legitimate NO_REPLY / silent-reply, NOT a crash. Substituting the

6668

// failure sentinel here would inject a fabricated "[assistant turn failed

6769

// before producing content]" into the next provider request and change

6870

// model behavior even though no failure occurred.

69-

const silentStop = bedrockAssistant([], "stop");

71+

const silentStop = bedrockAssistant([], "stop", { input: 100, totalTokens: 100 });

7072

const messages = [userMessage("hello"), silentStop];

7173

const out = normalizeAssistantReplayContent(messages);

7274

expect(out).toBe(messages);

7375

expect(out[1]).toBe(silentStop);

7476

});

757778+

it("converts zero-usage empty stop turns to a replay sentinel", () => {

79+

const falseSuccessStop = bedrockAssistant([], "stop");

80+

const messages = [userMessage("hello"), falseSuccessStop];

81+

const out = normalizeAssistantReplayContent(messages);

82+

expect(out).not.toBe(messages);

83+

const repaired = out[1] as AgentMessage & { content: { type: string; text: string }[] };

84+

expect(repaired.content).toEqual([{ type: "text", text: FALLBACK_TEXT }]);

85+

});

86+7687

it("preserves empty content with non-error stopReasons (toolUse, length) untouched", () => {

7788

// Boundary lock: only `stopReason:"error"` should trip the sentinel

7889

// substitution. `toolUse` and `length` are reachable in practice when a