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

博客园 - 司徒正美
大猫的无限游戏
大猫的无限游戏
腾讯CDC
J
Java Code Geeks
博客园 - 【当耐特】
Microsoft Azure Blog
Microsoft Azure Blog
V
Visual Studio Blog
人人都是产品经理
人人都是产品经理
博客园 - Franky
博客园 - 聂微东
阮一峰的网络日志
阮一峰的网络日志
美团技术团队
云风的 BLOG
云风的 BLOG
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
U
Unit 42
雷峰网
雷峰网
B
Blog RSS Feed
博客园_首页
量子位
F
Fortinet All Blogs
罗磊的独立博客
H
Hackread – Cybersecurity News, Data Breaches, AI and More
酷 壳 – CoolShell
酷 壳 – CoolShell
C
Check Point 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(qa-lab): add codex read vocabulary canary · openclaw...
vincentkoc · 2026-05-17 · via Recent Commits to openclaw:main

@@ -0,0 +1,103 @@

1+

# Codex Pi-shaped Read vocabulary canary

2+3+

```yaml qa-scenario

4+

id: codex-pi-shaped-read-vocabulary

5+

title: Codex Pi-shaped Read vocabulary canary

6+

surface: runtime

7+

runtimeParityTier: live-only

8+

coverage:

9+

primary:

10+

- runtime.codex-native-workspace.read

11+

secondary:

12+

- runtime.prompt-compatibility

13+

- tools.fs.read

14+

objective: Verify Codex-mode agents can satisfy legacy Pi-shaped "Read tool" wording through the native Codex workspace-read capability instead of stopping because duplicate OpenClaw dynamic read is intentionally filtered.

15+

successCriteria:

16+

- Agent reads the seeded workspace file and replies with the exact marker line.

17+

- Agent does not claim that the Read tool is unavailable.

18+

- Any failure is classified as a native prompt-compatibility/product behavior gap, not as missing OpenClaw dynamic read exposure.

19+

docsRefs:

20+

- docs/plugins/codex-harness.md

21+

- docs/tools/tool-search.md

22+

codeRefs:

23+

- extensions/codex/src/app-server/dynamic-tool-profile.ts

24+

- extensions/qa-lab/src/suite.ts

25+

execution:

26+

kind: flow

27+

summary: Seed a workspace file, ask with Pi-shaped "Read tool" wording, and require Codex to complete the read through its native workspace capability.

28+

config:

29+

runtimeParityComparison: codex-native-workspace

30+

fixtureFile: PI_SHAPED_READ_FIXTURE.txt

31+

expectedMarker: PI_SHAPED_READ_OK

32+

unavailableNeedles:

33+

- not in my available tool surface

34+

- read tool is not

35+

- no read tool

36+

- not available

37+

- cannot access

38+

- unable to access

39+

- do not have access

40+

```

41+42+

```yaml qa-flow

43+

steps:

44+

- name: handles Pi-shaped Read tool wording with native Codex read

45+

actions:

46+

- call: waitForGatewayHealthy

47+

args:

48+

- ref: env

49+

- 60000

50+

- call: waitForQaChannelReady

51+

args:

52+

- ref: env

53+

- 60000

54+

- call: reset

55+

- set: fixturePath

56+

value:

57+

expr: "path.join(env.gateway.workspaceDir, config.fixtureFile)"

58+

- call: fs.writeFile

59+

args:

60+

- ref: fixturePath

61+

- expr: "`${config.expectedMarker}\\n`"

62+

- utf8

63+

- set: startIndex

64+

value:

65+

expr: state.getSnapshot().messages.length

66+

- call: runAgentPrompt

67+

args:

68+

- ref: env

69+

- sessionKey:

70+

expr: "`agent:qa:pi-shaped-read:${randomUUID().slice(0, 8)}`"

71+

message:

72+

expr: "`Use the Read tool to read ${fixturePath}. Reply with the exact marker line and nothing else.`"

73+

timeoutMs:

74+

expr: liveTurnTimeoutMs(env, 45000)

75+

- set: unavailableNeedles

76+

value:

77+

expr: "config.unavailableNeedles.map(normalizeLowercaseStringOrEmpty)"

78+

- call: waitForOutboundMessage

79+

saveAs: outbound

80+

args:

81+

- ref: state

82+

- lambda:

83+

params: [candidate]

84+

expr: "candidate.conversation.id === 'qa-operator' && (normalizeLowercaseStringOrEmpty(candidate.text).includes(normalizeLowercaseStringOrEmpty(config.expectedMarker)) || unavailableNeedles.some((needle) => normalizeLowercaseStringOrEmpty(candidate.text).includes(needle)))"

85+

- expr: liveTurnTimeoutMs(env, 30000)

86+

- sinceIndex:

87+

ref: startIndex

88+

- set: outboundText

89+

value:

90+

expr: "String(outbound.text ?? '')"

91+

- set: normalizedOutbound

92+

value:

93+

expr: "normalizeLowercaseStringOrEmpty(outboundText)"

94+

- assert:

95+

expr: "normalizedOutbound.includes(normalizeLowercaseStringOrEmpty(config.expectedMarker))"

96+

message:

97+

expr: "`Pi-shaped Read vocabulary canary did not read marker ${config.expectedMarker}; outbound=${outboundText}`"

98+

- assert:

99+

expr: "!unavailableNeedles.some((needle) => normalizedOutbound.includes(needle))"

100+

message:

101+

expr: "`Pi-shaped Read vocabulary canary stopped on unavailable Read-tool wording: ${outboundText}`"

102+

detailsExpr: outbound.text

103+

```