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

GbyAI
GbyAI
Jina AI
Jina AI
月光博客
月光博客
博客园_首页
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
IT之家
IT之家
Hugging Face - Blog
Hugging Face - Blog
T
Tailwind CSS Blog
V
Visual Studio Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
大猫的无限游戏
大猫的无限游戏
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
阮一峰的网络日志
阮一峰的网络日志
量子位
博客园 - 【当耐特】
The Cloudflare Blog
宝玉的分享
宝玉的分享
博客园 - 聂微东
博客园 - 叶小钗
美团技术团队
G
Google Developers Blog
人人都是产品经理
人人都是产品经理
博客园 - Franky
小众软件
小众软件

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
Handle Codex turns missing completion (#85107) · openclaw...
joshavant · 2026-05-22 · via Recent Commits to openclaw:main

@@ -1991,6 +1991,95 @@ describe("CodexAppServerEventProjector", () => {

19911991

expect(payload.text).toContain("```txt\nopened\n```");

19921992

});

199319931994+

it("keeps side-effect evidence for dynamic tools that error after execution", async () => {

1995+

const projector = await createProjector();

1996+1997+

projector.recordDynamicToolCall({

1998+

callId: "call-process-kill",

1999+

tool: "process",

2000+

arguments: { action: "kill", sessionId: "session-1" },

2001+

});

2002+

projector.recordDynamicToolResult({

2003+

callId: "call-process-kill",

2004+

tool: "process",

2005+

success: false,

2006+

terminalType: "error",

2007+

sideEffectEvidence: true,

2008+

contentItems: [{ type: "inputText", text: "process exited" }],

2009+

});

2010+2011+

const result = projector.buildResult(buildEmptyToolTelemetry());

2012+2013+

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

2014+

});

2015+2016+

it("does not keep side-effect evidence for pre-execution dynamic tool errors", async () => {

2017+

const projector = await createProjector();

2018+2019+

projector.recordDynamicToolCall({

2020+

callId: "call-unknown-message",

2021+

tool: "message",

2022+

arguments: { action: "send", text: "hello" },

2023+

});

2024+

projector.recordDynamicToolResult({

2025+

callId: "call-unknown-message",

2026+

tool: "message",

2027+

success: false,

2028+

terminalType: "error",

2029+

contentItems: [{ type: "inputText", text: "Unknown OpenClaw tool: message" }],

2030+

});

2031+2032+

const result = projector.buildResult(buildEmptyToolTelemetry());

2033+2034+

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

2035+

});

2036+2037+

it("does not mark blocked dynamic tools as side-effecting", async () => {

2038+

const projector = await createProjector();

2039+2040+

projector.recordDynamicToolCall({

2041+

callId: "call-bash-blocked",

2042+

tool: "bash",

2043+

arguments: { command: "touch blocked.txt" },

2044+

});

2045+

projector.recordDynamicToolResult({

2046+

callId: "call-bash-blocked",

2047+

tool: "bash",

2048+

success: false,

2049+

terminalType: "blocked",

2050+

sideEffectEvidence: true,

2051+

contentItems: [{ type: "inputText", text: "blocked" }],

2052+

});

2053+2054+

const result = projector.buildResult(buildEmptyToolTelemetry());

2055+2056+

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

2057+

});

2058+2059+

it("treats completed native MCP tool calls as side-effect evidence", async () => {

2060+

const projector = await createProjector();

2061+2062+

await projector.handleNotification({

2063+

method: "item/completed",

2064+

params: {

2065+

threadId: "thread-1",

2066+

turnId: "turn-1",

2067+

item: {

2068+

id: "mcp-1",

2069+

type: "mcpToolCall",

2070+

server: "github",

2071+

tool: "create_issue",

2072+

status: "completed",

2073+

arguments: { title: "check replay safety" },

2074+

},

2075+

},

2076+

});

2077+2078+

const result = projector.buildResult(buildEmptyToolTelemetry());

2079+2080+

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

2081+

});

2082+19942083

it("suppresses transcript progress for message-like tools", async () => {

19952084

const onAgentEvent = vi.fn();

19962085

const onToolResult = vi.fn();

@@ -2021,7 +2110,7 @@ describe("CodexAppServerEventProjector", () => {

20212110

expect(onToolResult).not.toHaveBeenCalled();

20222111

});

202321122024-

it("suppresses transcript progress for activity-log bash commands", async () => {

2113+

it("does not parse shell command text to suppress transcript progress", async () => {

20252114

const onAgentEvent = vi.fn();

20262115

const onToolResult = vi.fn();

20272116

const projector = await createProjector({

@@ -2047,12 +2136,11 @@ describe("CodexAppServerEventProjector", () => {

20472136

contentItems: [{ type: "inputText", text: "Logged: [web_search] Grilled salmon research" }],

20482137

});

204921382050-

const toolEvents = onAgentEvent.mock.calls.filter(([event]) => {

2051-

const record = requireRecord(event, "agent event");

2052-

return record.stream === "tool";

2053-

});

2054-

expect(toolEvents).toHaveLength(0);

2055-

expect(onToolResult).not.toHaveBeenCalled();

2139+

expect(onAgentEvent).not.toHaveBeenCalled();

2140+

const toolProgressText = onToolResult.mock.calls

2141+

.map(([payload]) => (payload as { text?: string }).text ?? "")

2142+

.join("\n");

2143+

expect(toolProgressText).toContain("log_activity.sh");

2056214420572145

const result = projector.buildResult(buildEmptyToolTelemetry());

20582146

expect(result.messagesSnapshot.some((message) => message.role === "toolResult")).toBe(true);