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

L
LangChain Blog
V
V2EX
爱范儿
爱范儿
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Martin Fowler
Martin Fowler
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Apple Machine Learning Research
Apple Machine Learning Research
WordPress大学
WordPress大学
有赞技术团队
有赞技术团队
宝玉的分享
宝玉的分享
Last Week in AI
Last Week in AI
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
罗磊的独立博客
小众软件
小众软件
Vercel News
Vercel News
博客园 - 司徒正美
阮一峰的网络日志
阮一峰的网络日志
V
Visual Studio Blog
J
Java Code Geeks
P
Proofpoint News Feed
MongoDB | Blog
MongoDB | Blog
B
Blog
美团技术团队
量子位

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: stabilize gpt55 qa lab scenarios · openclaw/openclaw...
steipete · 2026-04-26 · via Recent Commits to openclaw:main

@@ -13,7 +13,7 @@ objective: Verify GPT-5.5 can switch from disabled thinking to medium thinking w

1313

successCriteria:

1414

- Live runs target openai/gpt-5.5, not a mini or pro variant.

1515

- The session enables reasoning display before the comparison turns.

16-

- The disabled-thinking turn returns its visible marker without a Reasoning-prefixed message.

16+

- The disabled-thinking turn returns its visible marker without a non-empty Reasoning summary.

1717

- The medium-thinking turn returns its visible marker and a separate Reasoning-prefixed message.

1818

docsRefs:

1919

- docs/tools/thinking.md

@@ -77,22 +77,22 @@ steps:

7777

- lambda:

7878

expr: "state.getSnapshot().messages.filter((candidate) => candidate.direction === 'outbound' && candidate.conversation.id === config.conversationId && /Reasoning visibility enabled/i.test(candidate.text)).at(-1)"

7979

- expr: liveTurnTimeoutMs(env, 20000)

80-

- call: state.addInboundMessage

80+

- call: patchConfig

8181

args:

82-

- conversation:

83-

id:

84-

expr: config.conversationId

85-

kind: direct

86-

senderId: qa-operator

87-

senderName: QA Operator

88-

text:

89-

expr: config.offDirective

90-

- call: waitForCondition

91-

saveAs: offAck

82+

- env:

83+

ref: env

84+

patch:

85+

agents:

86+

defaults:

87+

thinkingDefault: "off"

88+

- call: waitForGatewayHealthy

9289

args:

93-

- lambda:

94-

expr: "state.getSnapshot().messages.filter((candidate) => candidate.direction === 'outbound' && candidate.conversation.id === config.conversationId && /Thinking disabled/i.test(candidate.text)).at(-1)"

95-

- expr: liveTurnTimeoutMs(env, 20000)

90+

- ref: env

91+

- 60000

92+

- call: waitForQaChannelReady

93+

args:

94+

- ref: env

95+

- 60000

9696

- set: offCursor

9797

value:

9898

expr: state.getSnapshot().messages.length

@@ -105,7 +105,7 @@ steps:

105105

senderId: qa-operator

106106

senderName: QA Operator

107107

text:

108-

expr: "`${config.offDirective} ${config.offPrompt}`"

108+

expr: config.offPrompt

109109

- call: waitForCondition

110110

saveAs: offAnswer

111111

args:

@@ -120,7 +120,7 @@ steps:

120120

message:

121121

expr: "`missing off marker; saw ${offMessages.map((message) => message.text).join(' | ')}`"

122122

- assert:

123-

expr: "!offMessages.some((candidate) => candidate.text.trimStart().startsWith('Reasoning:'))"

123+

expr: "!offMessages.some((candidate) => candidate.text.trimStart().startsWith('Reasoning:') && !candidate.text.includes('Native reasoning was produced; no summary text was returned.'))"

124124

message:

125125

expr: "`disabled thinking unexpectedly emitted reasoning: ${offMessages.map((message) => message.text).join(' | ')}`"

126126

- if:

@@ -136,26 +136,26 @@ steps:

136136

expr: "String(offRequest?.model ?? '').includes('gpt-5.5')"

137137

message:

138138

expr: "`expected GPT-5.5 off mock request, got ${String(offRequest?.model ?? '')}`"

139-

detailsExpr: "`off ack=${offAck.text}; off answer=${offAnswer.text}`"

139+

detailsExpr: "`reasoning ack=${reasoningAck.text}; off answer=${offAnswer.text}`"

140140

- name: switches to medium thinking

141141

actions:

142-

- call: state.addInboundMessage

142+

- call: patchConfig

143143

args:

144-

- conversation:

145-

id:

146-

expr: config.conversationId

147-

kind: direct

148-

senderId: qa-operator

149-

senderName: QA Operator

150-

text:

151-

expr: config.maxDirective

152-

- call: waitForCondition

153-

saveAs: maxAck

144+

- env:

145+

ref: env

146+

patch:

147+

agents:

148+

defaults:

149+

thinkingDefault: "medium"

150+

- call: waitForGatewayHealthy

154151

args:

155-

- lambda:

156-

expr: "state.getSnapshot().messages.filter((candidate) => candidate.direction === 'outbound' && candidate.conversation.id === config.conversationId && /Thinking level set to medium/i.test(candidate.text)).at(-1)"

157-

- expr: liveTurnTimeoutMs(env, 20000)

158-

detailsExpr: "`max ack=${maxAck.text}`"

152+

- ref: env

153+

- 60000

154+

- call: waitForQaChannelReady

155+

args:

156+

- ref: env

157+

- 60000

158+

detailsExpr: "`thinking default patched to medium`"

159159

- name: verifies medium thinking emits visible reasoning

160160

actions:

161161

- set: maxCursor

@@ -170,7 +170,7 @@ steps:

170170

senderId: qa-operator

171171

senderName: QA Operator

172172

text:

173-

expr: "`${config.maxDirective} ${config.maxPrompt}`"

173+

expr: config.maxPrompt

174174

- call: waitForCondition

175175

saveAs: maxReasoning

176176

args: