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

Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
G
Google Developers Blog
S
SegmentFault 最新的问题
Microsoft Security Blog
Microsoft Security Blog
J
Java Code Geeks
罗磊的独立博客
H
Hackread – Cybersecurity News, Data Breaches, AI and More
量子位
P
Proofpoint News Feed
博客园 - 【当耐特】
MongoDB | Blog
MongoDB | Blog
L
LangChain Blog
F
Fortinet All Blogs
C
Check Point Blog
博客园_首页
I
InfoQ
Jina AI
Jina AI
Blog — PlanetScale
Blog — PlanetScale
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
酷 壳 – CoolShell
酷 壳 – CoolShell
Engineering at Meta
Engineering at Meta
美团技术团队
Vercel News
Vercel News
Apple Machine Learning Research
Apple Machine Learning Research

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: avoid stale dashboard child context budgets (#97332)...
galiniliev · 2026-06-28 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -90,7 +90,7 @@ test("sessions.create stores dashboard session model and parent linkage, and cre

9090

expect(header.id).toBe(created.payload?.sessionId);

9191

});

9292
93-

test("sessions.create inherits parent runtime model selection when model is omitted", async () => {

93+

test("sessions.create inherits parent runtime model selection without stale context metadata", async () => {

9494

const { storePath } = await createSessionStoreDir();

9595

await writeSessionStore({

9696

entries: {

@@ -102,6 +102,29 @@ test("sessions.create inherits parent runtime model selection when model is omit

102102

modelProvider: "codex",

103103

model: "gpt-5.5",

104104

contextTokens: 272000,

105+

inputTokens: 12000,

106+

outputTokens: 340,

107+

totalTokens: 12340,

108+

totalTokensFresh: false,

109+

contextBudgetStatus: {

110+

schemaVersion: 1,

111+

source: "pre-prompt-estimate",

112+

updatedAt: 1,

113+

provider: "codex",

114+

model: "gpt-5.5",

115+

route: "compact_then_truncate",

116+

shouldCompact: true,

117+

estimatedPromptTokens: 250000,

118+

contextTokenBudget: 128000,

119+

promptBudgetBeforeReserve: 112000,

120+

reserveTokens: 16000,

121+

effectiveReserveTokens: 16000,

122+

remainingPromptBudgetTokens: 0,

123+

overflowTokens: 138000,

124+

toolResultReducibleChars: 5000,

125+

messageCount: 12,

126+

unwindowedMessageCount: 12,

127+

},

105128

thinkingLevel: "off",

106129

fastMode: "auto",

107130

traceLevel: "debug",

@@ -121,6 +144,11 @@ test("sessions.create inherits parent runtime model selection when model is omit

121144

modelProvider?: string;

122145

model?: string;

123146

contextTokens?: number;

147+

inputTokens?: number;

148+

outputTokens?: number;

149+

totalTokens?: number;

150+

totalTokensFresh?: boolean;

151+

contextBudgetStatus?: unknown;

124152

thinkingLevel?: string;

125153

fastMode?: string;

126154

traceLevel?: string;

@@ -142,7 +170,12 @@ test("sessions.create inherits parent runtime model selection when model is omit

142170

expect(created.payload?.entry?.agentRuntimeOverride).toBe("codex");

143171

expect(created.payload?.entry?.modelProvider).toBe("codex");

144172

expect(created.payload?.entry?.model).toBe("gpt-5.5");

145-

expect(created.payload?.entry?.contextTokens).toBe(272000);

173+

expect(created.payload?.entry?.contextTokens).toBeUndefined();

174+

expect(created.payload?.entry?.inputTokens).toBeUndefined();

175+

expect(created.payload?.entry?.outputTokens).toBeUndefined();

176+

expect(created.payload?.entry?.totalTokens).toBeUndefined();

177+

expect(created.payload?.entry?.totalTokensFresh).toBeUndefined();

178+

expect(created.payload?.entry?.contextBudgetStatus).toBeUndefined();

146179

expect(created.payload?.entry?.thinkingLevel).toBe("off");

147180

expect(created.payload?.entry?.fastMode).toBe("auto");

148181

expect(created.payload?.entry?.traceLevel).toBe("debug");