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

N
Netflix TechBlog - Medium
T
The Blog of Author Tim Ferriss
aimingoo的专栏
aimingoo的专栏
A
About on SuperTechFans
Stack Overflow Blog
Stack Overflow Blog
B
Blog RSS Feed
Microsoft Security Blog
Microsoft Security Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
人人都是产品经理
人人都是产品经理
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
J
Java Code Geeks
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
B
Blog
MongoDB | Blog
MongoDB | Blog
L
LangChain Blog
WordPress大学
WordPress大学
小众软件
小众软件
IT之家
IT之家
腾讯CDC
月光博客
月光博客
量子位
Blog — PlanetScale
Blog — PlanetScale
P
Proofpoint News Feed
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More

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(qa-lab): add runtime parity axis · openclaw/openclaw...
vincentkoc · 2026-05-17 · via Recent Commits to openclaw:main

@@ -1,11 +1,14 @@

11

import { describe, expect, it } from "vitest";

22

import {

33

buildQaAgenticParityComparison,

4+

buildQaRuntimeParityReport,

45

computeQaAgenticParityMetrics,

56

QaParityLabelMismatchError,

67

renderQaAgenticParityMarkdownReport,

8+

renderQaRuntimeParityMarkdownReport,

79

type QaParityReportScenario,

810

type QaParitySuiteSummary,

11+

type QaRuntimeParitySuiteSummary,

912

} from "./agentic-parity-report.js";

10131114

const FULL_PARITY_PASS_SCENARIOS: QaParityReportScenario[] = [

@@ -29,6 +32,82 @@ function withScenarioOverride(name: string, override: Partial<QaParityReportScen

2932

);

3033

}

313435+

function makeRuntimeParitySummary(): QaRuntimeParitySuiteSummary {

36+

return {

37+

scenarios: [

38+

{

39+

name: "Approval turn tool followthrough",

40+

status: "pass",

41+

steps: [],

42+

runtimeParity: {

43+

scenarioId: "approval-turn-tool-followthrough",

44+

drift: "none",

45+

cells: {

46+

pi: {

47+

runtime: "pi",

48+

transcriptBytes: '{"role":"assistant"}\n',

49+

toolCalls: [{ tool: "read_file", argsHash: "a", resultHash: "r" }],

50+

finalText: "done",

51+

usage: { inputTokens: 10, outputTokens: 5, totalTokens: 15 },

52+

wallClockMs: 20,

53+

bootStateLines: [],

54+

},

55+

codex: {

56+

runtime: "codex",

57+

transcriptBytes: '{"role":"assistant"}\n',

58+

toolCalls: [{ tool: "read_file", argsHash: "a", resultHash: "r" }],

59+

finalText: "done",

60+

usage: { inputTokens: 8, outputTokens: 4, totalTokens: 12 },

61+

wallClockMs: 18,

62+

bootStateLines: [],

63+

},

64+

},

65+

},

66+

},

67+

{

68+

name: "Compaction retry after mutating tool",

69+

status: "fail",

70+

steps: [],

71+

runtimeParity: {

72+

scenarioId: "compaction-retry-after-mutating-tool",

73+

drift: "tool-call-shape",

74+

driftDetails: "tool call 1 differs",

75+

cells: {

76+

pi: {

77+

runtime: "pi",

78+

transcriptBytes: '{"role":"assistant"}\n',

79+

toolCalls: [{ tool: "read_file", argsHash: "a", resultHash: "r" }],

80+

finalText: "done",

81+

usage: { inputTokens: 10, outputTokens: 5, totalTokens: 15 },

82+

wallClockMs: 20,

83+

bootStateLines: [],

84+

},

85+

codex: {

86+

runtime: "codex",

87+

transcriptBytes: '{"role":"assistant"}\n',

88+

toolCalls: [{ tool: "read_file", argsHash: "b", resultHash: "r" }],

89+

finalText: "done",

90+

usage: { inputTokens: 9, outputTokens: 4, totalTokens: 13 },

91+

wallClockMs: 19,

92+

bootStateLines: [],

93+

},

94+

},

95+

},

96+

},

97+

],

98+

counts: {

99+

total: 2,

100+

passed: 1,

101+

failed: 1,

102+

},

103+

run: {

104+

providerMode: "mock-openai",

105+

primaryModel: "openai/gpt-5.5",

106+

runtimePair: ["pi", "codex"],

107+

},

108+

};

109+

}

110+32111

describe("qa agentic parity report", () => {

33112

it("computes first-wave parity metrics from suite summaries", () => {

34113

const summary: QaParitySuiteSummary = {

@@ -714,4 +793,33 @@ status=done`,

714793

"# OpenClaw Agentic Parity Report — openai/gpt-5.5-alt vs openai/gpt-5.5",

715794

);

716795

});

796+797+

it("builds a runtime parity report from suite summaries", () => {

798+

const report = buildQaRuntimeParityReport({

799+

summary: makeRuntimeParitySummary(),

800+

comparedAt: "2026-05-10T00:00:00.000Z",

801+

});

802+803+

expect(report.runtimePair).toEqual(["pi", "codex"]);

804+

expect(report.pass).toBe(false);

805+

expect(report.driftCounts.none).toBe(1);

806+

expect(report.driftCounts["tool-call-shape"]).toBe(1);

807+

expect(report.failures).toContain(

808+

"Compaction retry after mutating tool drift=tool-call-shape (tool call 1 differs).",

809+

);

810+

});

811+812+

it("renders a readable runtime parity markdown report", () => {

813+

const report = renderQaRuntimeParityMarkdownReport(

814+

buildQaRuntimeParityReport({

815+

summary: makeRuntimeParitySummary(),

816+

comparedAt: "2026-05-10T00:00:00.000Z",

817+

}),

818+

);

819+820+

expect(report).toContain("# OpenClaw Runtime Parity Report — pi vs codex");

821+

expect(report).toContain("| Tool-call-shape drift | 1 |");

822+

expect(report).toContain("### Compaction retry after mutating tool");

823+

expect(report).toContain("- drift: tool-call-shape");

824+

});

717825

});